diff options
Diffstat (limited to 'fs')
82 files changed, 3071 insertions, 3295 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index adafdf86f42f..fac918ccb305 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -108,7 +108,9 @@ static const struct netfs_read_request_ops v9fs_req_ops = { */ static int v9fs_vfs_readpage(struct file *file, struct page *page) { - return netfs_readpage(file, page, &v9fs_req_ops, NULL); + struct folio *folio = page_folio(page); + + return netfs_readpage(file, folio, &v9fs_req_ops, NULL); } /** @@ -130,13 +132,15 @@ static void v9fs_vfs_readahead(struct readahead_control *ractl) static int v9fs_release_page(struct page *page, gfp_t gfp) { - if (PagePrivate(page)) + struct folio *folio = page_folio(page); + + if (folio_test_private(folio)) return 0; #ifdef CONFIG_9P_FSCACHE - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) return 0; - wait_on_page_fscache(page); + folio_wait_fscache(folio); } #endif return 1; @@ -152,55 +156,58 @@ static int v9fs_release_page(struct page *page, gfp_t gfp) static void v9fs_invalidate_page(struct page *page, unsigned int offset, unsigned int length) { - wait_on_page_fscache(page); + struct folio *folio = page_folio(page); + + folio_wait_fscache(folio); } -static int v9fs_vfs_writepage_locked(struct page *page) +static int v9fs_vfs_write_folio_locked(struct folio *folio) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio_inode(folio); struct v9fs_inode *v9inode = V9FS_I(inode); - loff_t start = page_offset(page); - loff_t size = i_size_read(inode); + loff_t start = folio_pos(folio); + loff_t i_size = i_size_read(inode); struct iov_iter from; - int err, len; + size_t len = folio_size(folio); + int err; + + if (start >= i_size) + return 0; /* Simultaneous truncation occurred */ - if (page->index == size >> PAGE_SHIFT) - len = size & ~PAGE_MASK; - else - len = PAGE_SIZE; + len = min_t(loff_t, i_size - start, len); - iov_iter_xarray(&from, WRITE, &page->mapping->i_pages, start, len); + iov_iter_xarray(&from, WRITE, &folio_mapping(folio)->i_pages, start, len); /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); - set_page_writeback(page); + folio_start_writeback(folio); p9_client_write(v9inode->writeback_fid, start, &from, &err); - end_page_writeback(page); + folio_end_writeback(folio); return err; } static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) { + struct folio *folio = page_folio(page); int retval; - p9_debug(P9_DEBUG_VFS, "page %p\n", page); + p9_debug(P9_DEBUG_VFS, "folio %p\n", folio); - retval = v9fs_vfs_writepage_locked(page); + retval = v9fs_vfs_write_folio_locked(folio); if (retval < 0) { if (retval == -EAGAIN) { - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); retval = 0; } else { - SetPageError(page); - mapping_set_error(page->mapping, retval); + mapping_set_error(folio_mapping(folio), retval); } } else retval = 0; - unlock_page(page); + folio_unlock(folio); return retval; } @@ -213,14 +220,15 @@ static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) static int v9fs_launder_page(struct page *page) { + struct folio *folio = page_folio(page); int retval; - if (clear_page_dirty_for_io(page)) { - retval = v9fs_vfs_writepage_locked(page); + if (folio_clear_dirty_for_io(folio)) { + retval = v9fs_vfs_write_folio_locked(folio); if (retval) return retval; } - wait_on_page_fscache(page); + folio_wait_fscache(folio); return 0; } @@ -265,10 +273,10 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static int v9fs_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int flags, - struct page **pagep, void **fsdata) + struct page **subpagep, void **fsdata) { int retval; - struct page *page; + struct folio *folio; struct v9fs_inode *v9inode = V9FS_I(mapping->host); p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); @@ -279,31 +287,32 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - retval = netfs_write_begin(filp, mapping, pos, len, flags, &page, fsdata, + retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata, &v9fs_req_ops, NULL); if (retval < 0) return retval; - *pagep = find_subpage(page, pos / PAGE_SIZE); + *subpagep = &folio->page; return retval; } static int v9fs_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { loff_t last_pos = pos + copied; - struct inode *inode = page->mapping->host; + struct folio *folio = page_folio(subpage); + struct inode *inode = mapping->host; p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (unlikely(copied < len)) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } /* @@ -314,10 +323,10 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, inode_add_bytes(inode, last_pos - inode->i_size); i_size_write(inode, last_pos); } - set_page_dirty(page); + folio_mark_dirty(folio); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return copied; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 4244d48398ef..612e297f3763 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -528,13 +528,13 @@ static vm_fault_t v9fs_vm_page_mkwrite(struct vm_fault *vmf) { struct v9fs_inode *v9inode; - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); struct file *filp = vmf->vma->vm_file; struct inode *inode = file_inode(filp); - p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n", - page, (unsigned long)filp->private_data); + p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n", + folio, (unsigned long)filp->private_data); v9inode = V9FS_I(inode); @@ -542,24 +542,24 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf) * be modified. We then assume the entire page will need writing back. */ #ifdef CONFIG_9P_FSCACHE - if (PageFsCache(page) && - wait_on_page_fscache_killable(page) < 0) - return VM_FAULT_RETRY; + if (folio_test_fscache(folio) && + folio_wait_fscache_killable(folio) < 0) + return VM_FAULT_NOPAGE; #endif /* Update file times before taking page lock */ file_update_time(filp); BUG_ON(!v9inode->writeback_fid); - if (lock_page_killable(page) < 0) + if (folio_lock_killable(folio) < 0) return VM_FAULT_RETRY; - if (page->mapping != inode->i_mapping) + if (folio_mapping(folio) != inode->i_mapping) goto out_unlock; - wait_for_stable_page(page); + folio_wait_stable(folio); return VM_FAULT_LOCKED; out_unlock: - unlock_page(page); + folio_unlock(folio); return VM_FAULT_NOPAGE; } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 4579bbda4634..da9b4f8577a1 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -103,13 +103,13 @@ struct afs_lookup_cookie { }; /* - * Drop the refs that we're holding on the pages we were reading into. We've + * Drop the refs that we're holding on the folios we were reading into. We've * got refs on the first nr_pages pages. */ static void afs_dir_read_cleanup(struct afs_read *req) { struct address_space *mapping = req->vnode->vfs_inode.i_mapping; - struct page *page; + struct folio *folio; pgoff_t last = req->nr_pages - 1; XA_STATE(xas, &mapping->i_pages, 0); @@ -118,65 +118,56 @@ static void afs_dir_read_cleanup(struct afs_read *req) return; rcu_read_lock(); - xas_for_each(&xas, page, last) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, last) { + if (xas_retry(&xas, folio)) continue; - BUG_ON(xa_is_value(page)); - BUG_ON(PageCompound(page)); - ASSERTCMP(page->mapping, ==, mapping); + BUG_ON(xa_is_value(folio)); + ASSERTCMP(folio_file_mapping(folio), ==, mapping); - put_page(page); + folio_put(folio); } rcu_read_unlock(); } /* - * check that a directory page is valid + * check that a directory folio is valid */ -static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page, - loff_t i_size) +static bool afs_dir_check_folio(struct afs_vnode *dvnode, struct folio *folio, + loff_t i_size) { - struct afs_xdr_dir_page *dbuf; - loff_t latter, off; - int tmp, qty; + union afs_xdr_dir_block *block; + size_t offset, size; + loff_t pos; - /* Determine how many magic numbers there should be in this page, but + /* Determine how many magic numbers there should be in this folio, but * we must take care because the directory may change size under us. */ - off = page_offset(page); - if (i_size <= off) + pos = folio_pos(folio); + if (i_size <= pos) goto checked; - latter = i_size - off; - if (latter >= PAGE_SIZE) - qty = PAGE_SIZE; - else - qty = latter; - qty /= sizeof(union afs_xdr_dir_block); - - /* check them */ - dbuf = kmap_atomic(page); - for (tmp = 0; tmp < qty; tmp++) { - if (dbuf->blocks[tmp].hdr.magic != AFS_DIR_MAGIC) { - printk("kAFS: %s(%lx): bad magic %d/%d is %04hx\n", - __func__, dvnode->vfs_inode.i_ino, tmp, qty, - ntohs(dbuf->blocks[tmp].hdr.magic)); - trace_afs_dir_check_failed(dvnode, off, i_size); - kunmap(page); + 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->vfs_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 page + * use string functions on it. The filenames in the folio * *should* be NUL-terminated anyway. */ - ((u8 *)&dbuf->blocks[tmp])[AFS_DIR_BLOCK_SIZE - 1] = 0; - } - - kunmap_atomic(dbuf); + ((u8 *)block)[AFS_DIR_BLOCK_SIZE - 1] = 0; + kunmap_local(block); + } checked: afs_stat_v(dvnode, n_read_dir); return true; @@ -190,11 +181,11 @@ error: */ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req) { - struct afs_xdr_dir_page *dbuf; + union afs_xdr_dir_block *block; struct address_space *mapping = dvnode->vfs_inode.i_mapping; - struct page *page; - unsigned int i, qty = PAGE_SIZE / sizeof(union afs_xdr_dir_block); + struct folio *folio; pgoff_t last = req->nr_pages - 1; + size_t offset, size; XA_STATE(xas, &mapping->i_pages, 0); @@ -205,30 +196,28 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req) req->pos, req->nr_pages, req->iter->iov_offset, iov_iter_count(req->iter)); - xas_for_each(&xas, page, last) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, last) { + if (xas_retry(&xas, folio)) continue; - BUG_ON(PageCompound(page)); - BUG_ON(page->mapping != mapping); - - dbuf = kmap_atomic(page); - for (i = 0; i < qty; i++) { - union afs_xdr_dir_block *block = &dbuf->blocks[i]; + BUG_ON(folio_file_mapping(folio) != mapping); - pr_warn("[%02lx] %32phN\n", page->index * qty + i, block); + 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(folio) + offset, block); + kunmap_local(block); } - kunmap_atomic(dbuf); } } /* - * Check all the pages in a directory. All the pages are held pinned. + * Check all the blocks in a directory. All the folios are held pinned. */ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req) { struct address_space *mapping = dvnode->vfs_inode.i_mapping; - struct page *page; + struct folio *folio; pgoff_t last = req->nr_pages - 1; int ret = 0; @@ -238,14 +227,13 @@ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req) return 0; rcu_read_lock(); - xas_for_each(&xas, page, last) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, last) { + if (xas_retry(&xas, folio)) continue; - BUG_ON(PageCompound(page)); - BUG_ON(page->mapping != mapping); + BUG_ON(folio_file_mapping(folio) != mapping); - if (!afs_dir_check_page(dvnode, page, req->file_size)) { + if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) { afs_dir_dump(dvnode, req); ret = -EIO; break; @@ -274,15 +262,16 @@ 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 pages is returned, pinning them so that they don't + * contents. The list of folios is returned, pinning them so that they don't * get reclaimed during the iteration. */ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) __acquires(&dvnode->validate_lock) { + struct address_space *mapping = dvnode->vfs_inode.i_mapping; struct afs_read *req; loff_t i_size; - int nr_pages, i, n; + int nr_pages, i; int ret; _enter(""); @@ -320,43 +309,30 @@ expand: req->iter = &req->def_iter; /* Fill in any gaps that we might find where the memory reclaimer has - * been at work and pin all the pages. If there are any gaps, we will + * been at work and pin all the folios. If there are any gaps, we will * need to reread the entire directory contents. */ i = req->nr_pages; while (i < nr_pages) { - struct page *pages[8], *page; - - n = find_get_pages_contig(dvnode->vfs_inode.i_mapping, i, - min_t(unsigned int, nr_pages - i, - ARRAY_SIZE(pages)), - pages); - _debug("find %u at %u/%u", n, i, nr_pages); - - if (n == 0) { - gfp_t gfp = dvnode->vfs_inode.i_mapping->gfp_mask; + struct folio *folio; + folio = filemap_get_folio(mapping, i); + if (!folio) { if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_stat_v(dvnode, n_inval); ret = -ENOMEM; - page = __page_cache_alloc(gfp); - if (!page) + folio = __filemap_get_folio(mapping, + i, FGP_LOCK | FGP_CREAT, + mapping->gfp_mask); + if (!folio) goto error; - ret = add_to_page_cache_lru(page, - dvnode->vfs_inode.i_mapping, - i, gfp); - if (ret < 0) - goto error; - - attach_page_private(page, (void *)1); - unlock_page(page); - req->nr_pages++; - i++; - } else { - req->nr_pages += n; - i += n; + folio_attach_private(folio, (void *)1); + folio_unlock(folio); } + + 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 @@ -424,7 +400,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, size_t nlen; int tmp; - _enter("%u,%x,%p,,",(unsigned)ctx->pos,blkoff,block); + _enter("%llx,%x", ctx->pos, blkoff); curr = (ctx->pos - blkoff) / sizeof(union afs_xdr_dirent); @@ -513,12 +489,10 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, struct key *key, afs_dataversion_t *_dir_version) { struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_xdr_dir_page *dbuf; union afs_xdr_dir_block *dblock; struct afs_read *req; - struct page *page; - unsigned blkoff, limit; - void __rcu **slot; + struct folio *folio; + unsigned offset, size; int ret; _enter("{%lu},%u,,", dir->i_ino, (unsigned)ctx->pos); @@ -540,43 +514,30 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, /* walk through the blocks in sequence */ ret = 0; while (ctx->pos < req->actual_len) { - blkoff = ctx->pos & ~(sizeof(union afs_xdr_dir_block) - 1); - - /* Fetch the appropriate page from the directory and re-add it + /* Fetch the appropriate folio from the directory and re-add it * to the LRU. We have all the pages pinned with an extra ref. */ - rcu_read_lock(); - page = NULL; - slot = radix_tree_lookup_slot(&dvnode->vfs_inode.i_mapping->i_pages, - blkoff / PAGE_SIZE); - if (slot) - page = radix_tree_deref_slot(slot); - rcu_read_unlock(); - if (!page) { + folio = __filemap_get_folio(dir->i_mapping, ctx->pos / PAGE_SIZE, + FGP_ACCESSED, 0); + if (!folio) { ret = afs_bad(dvnode, afs_file_error_dir_missing_page); break; } - mark_page_accessed(page); - limit = blkoff & ~(PAGE_SIZE - 1); + offset = round_down(ctx->pos, sizeof(*dblock)) - folio_file_pos(folio); + size = min_t(loff_t, folio_size(folio), + req->actual_len - folio_file_pos(folio)); - dbuf = kmap(page); - - /* deal with the individual blocks stashed on this page */ do { - dblock = &dbuf->blocks[(blkoff % PAGE_SIZE) / - sizeof(union afs_xdr_dir_block)]; - ret = afs_dir_iterate_block(dvnode, ctx, dblock, blkoff); - if (ret != 1) { - kunmap(page); + dblock = kmap_local_folio(folio, offset); + ret = afs_dir_iterate_block(dvnode, ctx, dblock, + folio_file_pos(folio) + offset); + kunmap_local(dblock); + if (ret != 1) goto out; - } - blkoff += sizeof(union afs_xdr_dir_block); + } while (offset += sizeof(*dblock), offset < size); - } while (ctx->pos < dir->i_size && blkoff < limit); - - kunmap(page); ret = 0; } @@ -2037,42 +1998,42 @@ error: } /* - * Release a directory page and clean up its private state if it's not busy - * - return true if the page can now be released, false if not + * 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 int afs_dir_releasepage(struct page *page, gfp_t gfp_flags) +static int afs_dir_releasepage(struct page *subpage, gfp_t gfp_flags) { - struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host); + struct folio *folio = page_folio(subpage); + struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index); + _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio)); - detach_page_private(page); + 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 1; + return true; } /* - * invalidate part or all of a page - * - release a page and clean up its private data if offset is 0 (indicating - * the entire page) + * Invalidate part or all of a folio. */ -static void afs_dir_invalidatepage(struct page *page, unsigned int offset, +static void afs_dir_invalidatepage(struct page *subpage, unsigned int offset, unsigned int length) { - struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host); + struct folio *folio = page_folio(subpage); + struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - _enter("{%lu},%u,%u", page->index, offset, length); + _enter("{%lu},%u,%u", folio_index(folio), offset, length); - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); /* The directory will need reloading. */ if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_stat_v(dvnode, n_inval); - /* we clean up only if the entire page is being invalidated */ - if (offset == 0 && length == thp_size(page)) - detach_page_private(page); + /* we clean up only if the entire folio is being invalidated */ + if (offset == 0 && length == folio_size(folio)) + folio_detach_private(folio); } diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 540b9fc96824..d98e109ecee9 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -105,6 +105,25 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block, } /* + * Get a new directory folio. + */ +static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index) +{ + struct address_space *mapping = vnode->vfs_inode.i_mapping; + struct folio *folio; + + folio = __filemap_get_folio(mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping->gfp_mask); + if (!folio) + clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + else if (folio && !folio_test_private(folio)) + folio_attach_private(folio, (void *)1); + + return folio; +} + +/* * Scan a directory block looking for a dirent of the right name. */ static int afs_dir_scan_block(union afs_xdr_dir_block *block, struct qstr *name, @@ -188,13 +207,11 @@ void afs_edit_dir_add(struct afs_vnode *vnode, enum afs_edit_dir_reason why) { union afs_xdr_dir_block *meta, *block; - struct afs_xdr_dir_page *meta_page, *dir_page; union afs_xdr_dirent *de; - struct page *page0, *page; + struct folio *folio0, *folio; unsigned int need_slots, nr_blocks, b; pgoff_t index; loff_t i_size; - gfp_t gfp; int slot; _enter(",,{%d,%s},", name->len, name->name); @@ -206,10 +223,8 @@ void afs_edit_dir_add(struct afs_vnode *vnode, return; } - gfp = vnode->vfs_inode.i_mapping->gfp_mask; - page0 = find_or_create_page(vnode->vfs_inode.i_mapping, 0, gfp); - if (!page0) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + folio0 = afs_dir_get_folio(vnode, 0); + if (!folio0) { _leave(" [fgp]"); return; } @@ -217,42 +232,35 @@ void afs_edit_dir_add(struct afs_vnode *vnode, /* Work out how many slots we're going to need. */ need_slots = afs_dir_calc_slots(name->len); - meta_page = kmap(page0); - meta = &meta_page->blocks[0]; + meta = kmap_local_folio(folio0, 0); if (i_size == 0) goto new_directory; nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; - /* Find a block that has sufficient slots available. Each VM page + /* Find a block that has sufficient slots available. Each folio * contains two or more directory blocks. */ for (b = 0; b < nr_blocks + 1; b++) { - /* If the directory extended into a new page, then we need to - * tack a new page on the end. + /* 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 (index == 0) { - page = page0; - dir_page = meta_page; - } else { - if (nr_blocks >= AFS_DIR_MAX_BLOCKS) - goto error; - gfp = vnode->vfs_inode.i_mapping->gfp_mask; - page = find_or_create_page(vnode->vfs_inode.i_mapping, - index, gfp); - if (!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; - if (!PagePrivate(page)) - attach_page_private(page, (void *)1); - dir_page = kmap(page); + } else { + folio = folio0; } + block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_file_pos(folio)); + /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) goto invalidated; - block = &dir_page->blocks[b % AFS_DIR_BLOCKS_PER_PAGE]; - _debug("block %u: %2u %3u %u", b, (b < AFS_DIR_BLOCKS_WITH_CTR) ? meta->meta.alloc_ctrs[b] : 99, @@ -266,7 +274,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode, afs_set_i_size(vnode, (b + 1) * AFS_DIR_BLOCK_SIZE); } - /* Only lower dir pages have a counter in the header. */ + /* 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 @@ -279,10 +287,10 @@ void afs_edit_dir_add(struct afs_vnode *vnode, } } - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } } @@ -298,8 +306,8 @@ new_directory: i_size = AFS_DIR_BLOCK_SIZE; afs_set_i_size(vnode, i_size); slot = AFS_DIR_RESV_BLOCKS0; - page = page0; - block = meta; + folio = folio0; + block = kmap_local_folio(folio, 0); nr_blocks = 1; b = 0; @@ -318,10 +326,10 @@ found_space: /* Adjust the bitmap. */ afs_set_contig_bits(block, slot, need_slots); - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } /* Adjust the allocation counter. */ @@ -333,18 +341,19 @@ found_space: _debug("Insert %s in %u[%u]", name->name, b, slot); out_unmap: - unlock_page(page0); - kunmap(page0); - put_page(page0); + kunmap_local(meta); + folio_unlock(folio0); + folio_put(folio0); _leave(""); return; 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); - if (page != page0) { - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } goto out_unmap; @@ -364,10 +373,9 @@ error: void afs_edit_dir_remove(struct afs_vnode *vnode, struct qstr *name, enum afs_edit_dir_reason why) { - struct afs_xdr_dir_page *meta_page, *dir_page; union afs_xdr_dir_block *meta, *block; union afs_xdr_dirent *de; - struct page *page0, *page; + struct folio *folio0, *folio; unsigned int need_slots, nr_blocks, b; pgoff_t index; loff_t i_size; @@ -384,9 +392,8 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, } nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; - page0 = find_lock_page(vnode->vfs_inode.i_mapping, 0); - if (!page0) { - clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + folio0 = afs_dir_get_folio(vnode, 0); + if (!folio0) { _leave(" [fgp]"); return; } @@ -394,30 +401,27 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, /* Work out how many slots we're going to discard. */ need_slots = afs_dir_calc_slots(name->len); - meta_page = kmap(page0); - meta = &meta_page->blocks[0]; + meta = kmap_local_folio(folio0, 0); - /* Find a page that has sufficient slots available. Each VM page + /* 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 != 0) { - page = find_lock_page(vnode->vfs_inode.i_mapping, index); - if (!page) + if (index >= folio_nr_pages(folio0)) { + folio = afs_dir_get_folio(vnode, index); + if (!folio) goto error; - dir_page = kmap(page); } else { - page = page0; - dir_page = meta_page; + folio = folio0; } + block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_file_pos(folio)); + /* Abandon the edit if we got a callback break. */ if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) goto invalidated; - block = &dir_page->blocks[b % AFS_DIR_BLOCKS_PER_PAGE]; - 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); @@ -425,10 +429,10 @@ void afs_edit_dir_remove(struct afs_vnode *vnode, goto found_dirent; } - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } } @@ -449,10 +453,10 @@ found_dirent: /* Adjust the bitmap. */ afs_clear_contig_bits(block, slot, need_slots); - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } /* Adjust the allocation counter. */ @@ -464,9 +468,9 @@ found_dirent: _debug("Remove %s from %u[%u]", name->name, b, slot); out_unmap: - unlock_page(page0); - kunmap(page0); - put_page(page0); + kunmap_local(meta); + folio_unlock(folio0); + folio_put(folio0); _leave(""); return; @@ -474,10 +478,10 @@ invalidated: 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); - if (page != page0) { - unlock_page(page); - kunmap(page); - put_page(page); + kunmap_local(block); + if (folio != folio0) { + folio_unlock(folio); + folio_put(folio); } goto out_unmap; diff --git a/fs/afs/file.c b/fs/afs/file.c index eb11d047c0ae..cb6ad61eec3b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -324,21 +324,24 @@ static int afs_symlink_readpage(struct file *file, struct page *page) { struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); struct afs_read *fsreq; + struct folio *folio = page_folio(page); int ret; fsreq = afs_alloc_read(GFP_NOFS); if (!fsreq) return -ENOMEM; - fsreq->pos = page->index * PAGE_SIZE; - fsreq->len = PAGE_SIZE; + fsreq->pos = folio_pos(folio); + fsreq->len = folio_size(folio); fsreq->vnode = vnode; fsreq->iter = &fsreq->def_iter; iov_iter_xarray(&fsreq->def_iter, READ, &page->mapping->i_pages, fsreq->pos, fsreq->len); ret = afs_fetch_data(fsreq->vnode, fsreq); - page_endio(page, false, ret); + if (ret == 0) + SetPageUptodate(page); + unlock_page(page); return ret; } @@ -362,7 +365,7 @@ static int afs_begin_cache_operation(struct netfs_read_request *rreq) } static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len, - struct page *page, void **_fsdata) + struct folio *folio, void **_fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); @@ -385,7 +388,9 @@ const struct netfs_read_request_ops afs_req_ops = { static int afs_readpage(struct file *file, struct page *page) { - return netfs_readpage(file, page, &afs_req_ops, NULL); + struct folio *folio = page_folio(page); + + return netfs_readpage(file, folio, &afs_req_ops, NULL); } static void afs_readahead(struct readahead_control *ractl) @@ -397,29 +402,29 @@ static void afs_readahead(struct readahead_control *ractl) * Adjust the dirty region of the page on truncation or full invalidation, * getting rid of the markers altogether if the region is entirely invalidated. */ -static void afs_invalidate_dirty(struct page *page, unsigned int offset, +static void afs_invalidate_dirty(struct folio *folio, unsigned int offset, unsigned int length) { - struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); unsigned long priv; unsigned int f, t, end = offset + length; - priv = page_private(page); + priv = (unsigned long)folio_get_private(folio); /* we clean up only if the entire page is being invalidated */ - if (offset == 0 && length == thp_size(page)) + if (offset == 0 && length == folio_size(folio)) goto full_invalidate; /* If the page was dirtied by page_mkwrite(), the PTE stays writable * and we don't get another notification to tell us to expand it * again. */ - if (afs_is_page_dirty_mmapped(priv)) + if (afs_is_folio_dirty_mmapped(priv)) return; /* We may need to shorten the dirty region */ - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (t <= offset || f >= end) return; /* Doesn't overlap */ @@ -437,17 +442,17 @@ static void afs_invalidate_dirty(struct page *page, unsigned int offset, if (f == t) goto undirty; - priv = afs_page_dirty(page, f, t); - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page); + priv = afs_folio_dirty(folio, f, t); + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio); return; undirty: - trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page); - clear_page_dirty_for_io(page); + trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio); + folio_clear_dirty_for_io(folio); full_invalidate: - trace_afs_page_dirty(vnode, tracepoint_string("inval"), page); - detach_page_private(page); + trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio); + folio_detach_private(folio); } /* @@ -458,14 +463,16 @@ full_invalidate: static void afs_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { - _enter("{%lu},%u,%u", page->index, offset, length); + struct folio *folio = page_folio(page); + + _enter("{%lu},%u,%u", folio_index(folio), offset, length); BUG_ON(!PageLocked(page)); if (PagePrivate(page)) - afs_invalidate_dirty(page, offset, length); + afs_invalidate_dirty(folio, offset, length); - wait_on_page_fscache(page); + folio_wait_fscache(folio); _leave(""); } @@ -475,30 +482,31 @@ static void afs_invalidatepage(struct page *page, unsigned int offset, */ static int afs_releasepage(struct page *page, gfp_t gfp_flags) { - struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); + struct folio *folio = page_folio(page); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); _enter("{{%llx:%llu}[%lu],%lx},%x", - vnode->fid.vid, vnode->fid.vnode, page->index, page->flags, + vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags, gfp_flags); /* deny if page is being written to the cache and the caller hasn't * elected to wait */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (!(gfp_flags & __GFP_DIRECT_RECLAIM) || !(gfp_flags & __GFP_FS)) return false; - wait_on_page_fscache(page); + folio_wait_fscache(folio); } #endif - if (PagePrivate(page)) { - trace_afs_page_dirty(vnode, tracepoint_string("rel"), page); - detach_page_private(page); + if (folio_test_private(folio)) { + trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio); + folio_detach_private(folio); } - /* indicate that the page can be released */ + /* Indicate that the folio can be released */ _leave(" = T"); - return 1; + return true; } static void afs_add_open_mmap(struct afs_vnode *vnode) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 9357c53faa69..aa4c0d6c9780 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -876,59 +876,59 @@ struct afs_vnode_cache_aux { } __packed; /* - * We use page->private to hold the amount of the page that we've written to, + * We use folio->private to hold the amount of the folio that we've written to, * splitting the field into two parts. However, we need to represent a range - * 0...PAGE_SIZE, so we reduce the resolution if the size of the page + * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio * exceeds what we can encode. */ #ifdef CONFIG_64BIT -#define __AFS_PAGE_PRIV_MASK 0x7fffffffUL -#define __AFS_PAGE_PRIV_SHIFT 32 -#define __AFS_PAGE_PRIV_MMAPPED 0x80000000UL +#define __AFS_FOLIO_PRIV_MASK 0x7fffffffUL +#define __AFS_FOLIO_PRIV_SHIFT 32 +#define __AFS_FOLIO_PRIV_MMAPPED 0x80000000UL #else -#define __AFS_PAGE_PRIV_MASK 0x7fffUL -#define __AFS_PAGE_PRIV_SHIFT 16 -#define __AFS_PAGE_PRIV_MMAPPED 0x8000UL +#define __AFS_FOLIO_PRIV_MASK 0x7fffUL +#define __AFS_FOLIO_PRIV_SHIFT 16 +#define __AFS_FOLIO_PRIV_MMAPPED 0x8000UL #endif -static inline unsigned int afs_page_dirty_resolution(struct page *page) +static inline unsigned int afs_folio_dirty_resolution(struct folio *folio) { - int shift = thp_order(page) + PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1); + int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1); return (shift > 0) ? shift : 0; } -static inline size_t afs_page_dirty_from(struct page *page, unsigned long priv) +static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv) { - unsigned long x = priv & __AFS_PAGE_PRIV_MASK; + unsigned long x = priv & __AFS_FOLIO_PRIV_MASK; /* The lower bound is inclusive */ - return x << afs_page_dirty_resolution(page); + return x << afs_folio_dirty_resolution(folio); } -static inline size_t afs_page_dirty_to(struct page *page, unsigned long priv) +static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv) { - unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK; + unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK; /* The upper bound is immediately beyond the region */ - return (x + 1) << afs_page_dirty_resolution(page); + return (x + 1) << afs_folio_dirty_resolution(folio); } -static inline unsigned long afs_page_dirty(struct page *page, size_t from, size_t to) +static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to) { - unsigned int res = afs_page_dirty_resolution(page); + unsigned int res = afs_folio_dirty_resolution(folio); from >>= res; to = (to - 1) >> res; - return (to << __AFS_PAGE_PRIV_SHIFT) | from; + return (to << __AFS_FOLIO_PRIV_SHIFT) | from; } -static inline unsigned long afs_page_dirty_mmapped(unsigned long priv) +static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv) { - return priv | __AFS_PAGE_PRIV_MMAPPED; + return priv | __AFS_FOLIO_PRIV_MMAPPED; } -static inline bool afs_is_page_dirty_mmapped(unsigned long priv) +static inline bool afs_is_folio_dirty_mmapped(unsigned long priv) { - return priv & __AFS_PAGE_PRIV_MMAPPED; + return priv & __AFS_FOLIO_PRIV_MMAPPED; } #include <trace/events/afs.h> diff --git a/fs/afs/write.c b/fs/afs/write.c index 8b1d9c2f6bec..ca4909baf5e6 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -32,7 +32,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, struct page **_page, void **fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); - struct page *page; + struct folio *folio; unsigned long priv; unsigned f, from; unsigned t, to; @@ -46,12 +46,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - ret = netfs_write_begin(file, mapping, pos, len, flags, &page, fsdata, + ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata, &afs_req_ops, NULL); if (ret < 0) return ret; - index = page->index; + index = folio_index(folio); from = pos - index * PAGE_SIZE; to = from + len; @@ -59,14 +59,14 @@ try_again: /* See if this page is already partially written in a way that we can * merge the new write with. */ - if (PagePrivate(page)) { - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + if (folio_test_private(folio)) { + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); ASSERTCMP(f, <=, t); - if (PageWriteback(page)) { - trace_afs_page_dirty(vnode, tracepoint_string("alrdy"), page); + if (folio_test_writeback(folio)) { + trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio); goto flush_conflicting_write; } /* If the file is being filled locally, allow inter-write @@ -78,7 +78,7 @@ try_again: goto flush_conflicting_write; } - *_page = page; + *_page = &folio->page; _leave(" = 0"); return 0; @@ -87,17 +87,17 @@ try_again: */ flush_conflicting_write: _debug("flush conflict"); - ret = write_one_page(page); + ret = folio_write_one(folio); if (ret < 0) goto error; - ret = lock_page_killable(page); + ret = folio_lock_killable(folio); if (ret < 0) goto error; goto try_again; error: - put_page(page); + folio_put(folio); _leave(" = %d", ret); return ret; } @@ -107,24 +107,25 @@ error: */ int afs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { + struct folio *folio = page_folio(subpage); struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); unsigned long priv; - unsigned int f, from = pos & (thp_size(page) - 1); + unsigned int f, from = offset_in_folio(folio, pos); unsigned int t, to = from + copied; loff_t i_size, maybe_i_size; _enter("{%llx:%llu},{%lx}", - vnode->fid.vid, vnode->fid.vnode, page->index); + vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (copied < len) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } if (copied == 0) @@ -141,29 +142,29 @@ int afs_write_end(struct file *file, struct address_space *mapping, write_sequnlock(&vnode->cb_lock); } - if (PagePrivate(page)) { - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + if (folio_test_private(folio)) { + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (from < f) f = from; if (to > t) t = to; - priv = afs_page_dirty(page, f, t); - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("dirty+"), page); + priv = afs_folio_dirty(folio, f, t); + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio); } else { - priv = afs_page_dirty(page, from, to); - attach_page_private(page, (void *)priv); - trace_afs_page_dirty(vnode, tracepoint_string("dirty"), page); + priv = afs_folio_dirty(folio, from, to); + folio_attach_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio); } - if (set_page_dirty(page)) - _debug("dirtied %lx", page->index); + if (folio_mark_dirty(folio)) + _debug("dirtied %lx", folio_index(folio)); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return copied; } @@ -174,40 +175,32 @@ static void afs_kill_pages(struct address_space *mapping, loff_t start, loff_t len) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct pagevec pv; - unsigned int loop, psize; + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; _enter("{%llx:%llu},%llx @%llx", vnode->fid.vid, vnode->fid.vnode, len, start); - pagevec_init(&pv); - do { - _debug("kill %llx @%llx", len, start); - - pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE, - PAGEVEC_SIZE, pv.pages); - if (pv.nr == 0) - break; + _debug("kill %lx (to %lx)", index, last); - for (loop = 0; loop < pv.nr; loop++) { - struct page *page = pv.pages[loop]; + folio = filemap_get_folio(mapping, index); + if (!folio) { + next = index + 1; + continue; + } - if (page->index * PAGE_SIZE >= start + len) - break; + next = folio_next_index(folio); - psize = thp_size(page); - start += psize; - len -= psize; - ClearPageUptodate(page); - end_page_writeback(page); - lock_page(page); - generic_error_remove_page(mapping, page); - unlock_page(page); - } + folio_clear_uptodate(folio); + folio_end_writeback(folio); + folio_lock(folio); + generic_error_remove_page(mapping, &folio->page); + folio_unlock(folio); + folio_put(folio); - __pagevec_release(&pv); - } while (len > 0); + } while (index = next, index <= last); _leave(""); } @@ -220,37 +213,27 @@ static void afs_redirty_pages(struct writeback_control *wbc, loff_t start, loff_t len) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct pagevec pv; - unsigned int loop, psize; + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; _enter("{%llx:%llu},%llx @%llx", vnode->fid.vid, vnode->fid.vnode, len, start); - pagevec_init(&pv); - do { _debug("redirty %llx @%llx", len, start); - pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE, - PAGEVEC_SIZE, pv.pages); - if (pv.nr == 0) - break; - - for (loop = 0; loop < pv.nr; loop++) { - struct page *page = pv.pages[loop]; - - if (page->index * PAGE_SIZE >= start + len) - break; - - psize = thp_size(page); - start += psize; - len -= psize; - redirty_page_for_writepage(wbc, page); - end_page_writeback(page); + folio = filemap_get_folio(mapping, index); + if (!folio) { + next = index + 1; + continue; } - __pagevec_release(&pv); - } while (len > 0); + next = index + folio_nr_pages(folio); + folio_redirty_for_writepage(wbc, folio); + folio_end_writeback(folio); + folio_put(folio); + } while (index = next, index <= last); _leave(""); } @@ -261,7 +244,7 @@ static void afs_redirty_pages(struct writeback_control *wbc, static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len) { struct address_space *mapping = vnode->vfs_inode.i_mapping; - struct page *page; + struct folio *folio; pgoff_t end; XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); @@ -272,15 +255,16 @@ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsign rcu_read_lock(); end = (start + len - 1) / PAGE_SIZE; - xas_for_each(&xas, page, end) { - if (!PageWriteback(page)) { - kdebug("bad %x @%llx page %lx %lx", len, start, page->index, end); - ASSERT(PageWriteback(page)); + xas_for_each(&xas, folio, end) { + if (!folio_test_writeback(folio)) { + kdebug("bad %x @%llx page %lx %lx", + len, start, folio_index(folio), end); + ASSERT(folio_test_writeback(folio)); } - trace_afs_page_dirty(vnode, tracepoint_string("clear"), page); - detach_page_private(page); - page_endio(page, true, 0); + trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio); + folio_detach_private(folio); + folio_end_writeback(folio); } rcu_read_unlock(); @@ -437,7 +421,7 @@ static void afs_extend_writeback(struct address_space *mapping, unsigned int *_len) { struct pagevec pvec; - struct page *page; + struct folio *folio; unsigned long priv; unsigned int psize, filler = 0; unsigned int f, t; @@ -456,43 +440,43 @@ static void afs_extend_writeback(struct address_space *mapping, */ rcu_read_lock(); - xas_for_each(&xas, page, ULONG_MAX) { + xas_for_each(&xas, folio, ULONG_MAX) { stop = true; - if (xas_retry(&xas, page)) + if (xas_retry(&xas, folio)) continue; - if (xa_is_value(page)) + if (xa_is_value(folio)) break; - if (page->index != index) + if (folio_index(folio) != index) break; - if (!page_cache_get_speculative(page)) { + if (!folio_try_get_rcu(folio)) { xas_reset(&xas); continue; } /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) { - put_page(page); + if (unlikely(folio != xas_reload(&xas))) { + folio_put(folio); break; } - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); break; } - if (!PageDirty(page) || PageWriteback(page)) { - unlock_page(page); - put_page(page); + if (!folio_test_dirty(folio) || folio_test_writeback(folio)) { + folio_unlock(folio); + folio_put(folio); break; } - psize = thp_size(page); - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + psize = folio_size(folio); + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (f != 0 && !new_content) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); break; } @@ -503,8 +487,8 @@ static void afs_extend_writeback(struct address_space *mapping, else if (t == psize || new_content) stop = false; - index += thp_nr_pages(page); - if (!pagevec_add(&pvec, page)) + index += folio_nr_pages(folio); + if (!pagevec_add(&pvec, &folio->page)) break; if (stop) break; @@ -521,16 +505,16 @@ static void afs_extend_writeback(struct address_space *mapping, break; for (i = 0; i < pagevec_count(&pvec); i++) { - page = pvec.pages[i]; - trace_afs_page_dirty(vnode, tracepoint_string("store+"), page); + folio = page_folio(pvec.pages[i]); + trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio); - if (!clear_page_dirty_for_io(page)) + if (!folio_clear_dirty_for_io(folio)) BUG(); - if (test_set_page_writeback(page)) + if (folio_start_writeback(folio)) BUG(); - *_count -= thp_nr_pages(page); - unlock_page(page); + *_count -= folio_nr_pages(folio); + folio_unlock(folio); } pagevec_release(&pvec); @@ -544,10 +528,10 @@ static void afs_extend_writeback(struct address_space *mapping, * Synchronously write back the locked page and any subsequent non-locked dirty * pages. */ -static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, - struct writeback_control *wbc, - struct page *page, - loff_t start, loff_t end) +static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, + struct writeback_control *wbc, + struct folio *folio, + loff_t start, loff_t end) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); struct iov_iter iter; @@ -558,22 +542,22 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, long count = wbc->nr_to_write; int ret; - _enter(",%lx,%llx-%llx", page->index, start, end); + _enter(",%lx,%llx-%llx", folio_index(folio), start, end); - if (test_set_page_writeback(page)) + if (folio_start_writeback(folio)) BUG(); - count -= thp_nr_pages(page); + count -= folio_nr_pages(folio); /* Find all consecutive lockable dirty pages that have contiguous * written regions, stopping when we find a page that is not * immediately lockable, is not dirty or is missing, or we reach the * end of the range. */ - priv = page_private(page); - offset = afs_page_dirty_from(page, priv); - to = afs_page_dirty_to(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("store"), page); + priv = (unsigned long)folio_get_private(folio); + offset = afs_folio_dirty_from(folio, priv); + to = afs_folio_dirty_to(folio, priv); + trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio); len = to - offset; start += offset; @@ -586,7 +570,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, max_len = min_t(unsigned long long, max_len, i_size - start); if (len < max_len && - (to == thp_size(page) || new_content)) + (to == folio_size(folio) || new_content)) afs_extend_writeback(mapping, vnode, &count, start, max_len, new_content, &len); len = min_t(loff_t, len, max_len); @@ -596,7 +580,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, * set; the first page is still locked at this point, but all the rest * have been unlocked. */ - unlock_page(page); + folio_unlock(folio); if (start < i_size) { _debug("write back %x @%llx [%llx]", len, start, i_size); @@ -657,16 +641,17 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, * write a page back to the server * - the caller locked the page for us */ -int afs_writepage(struct page *page, struct writeback_control *wbc) +int afs_writepage(struct page *subpage, struct writeback_control *wbc) { + struct folio *folio = page_folio(subpage); ssize_t ret; loff_t start; - _enter("{%lx},", page->index); + _enter("{%lx},", folio_index(folio)); - start = page->index * PAGE_SIZE; - ret = afs_write_back_from_locked_page(page->mapping, wbc, page, - start, LLONG_MAX - start); + start = folio_index(folio) * PAGE_SIZE; + ret = afs_write_back_from_locked_folio(folio_mapping(folio), wbc, + folio, start, LLONG_MAX - start); if (ret < 0) { _leave(" = %zd", ret); return ret; @@ -683,7 +668,8 @@ static int afs_writepages_region(struct address_space *mapping, struct writeback_control *wbc, loff_t start, loff_t end, loff_t *_next) { - struct page *page; + struct folio *folio; + struct page *head_page; ssize_t ret; int n; @@ -693,13 +679,14 @@ static int afs_writepages_region(struct address_space *mapping, pgoff_t index = start / PAGE_SIZE; n = find_get_pages_range_tag(mapping, &index, end / PAGE_SIZE, - PAGECACHE_TAG_DIRTY, 1, &page); + PAGECACHE_TAG_DIRTY, 1, &head_page); if (!n) break; - start = (loff_t)page->index * PAGE_SIZE; /* May regress with THPs */ + folio = page_folio(head_page); + start = folio_pos(folio); /* May regress with THPs */ - _debug("wback %lx", page->index); + _debug("wback %lx", folio_index(folio)); /* At this point we hold neither the i_pages lock nor the * page lock: the page may be truncated or invalidated @@ -707,37 +694,38 @@ static int afs_writepages_region(struct address_space *mapping, * back from swapper_space to tmpfs file mapping */ if (wbc->sync_mode != WB_SYNC_NONE) { - ret = lock_page_killable(page); + ret = folio_lock_killable(folio); if (ret < 0) { - put_page(page); + folio_put(folio); return ret; } } else { - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); return 0; } } - if (page->mapping != mapping || !PageDirty(page)) { - start += thp_size(page); - unlock_page(page); - put_page(page); + if (folio_mapping(folio) != mapping || + !folio_test_dirty(folio)) { + start += folio_size(folio); + folio_unlock(folio); + folio_put(folio); continue; } - if (PageWriteback(page)) { - unlock_page(page); + if (folio_test_writeback(folio)) { + folio_unlock(folio); if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); - put_page(page); + folio_wait_writeback(folio); + folio_put(folio); continue; } - if (!clear_page_dirty_for_io(page)) + if (!folio_clear_dirty_for_io(folio)) BUG(); - ret = afs_write_back_from_locked_page(mapping, wbc, page, start, end); - put_page(page); + ret = afs_write_back_from_locked_folio(mapping, wbc, folio, start, end); + folio_put(folio); if (ret < 0) { _leave(" = %zd", ret); return ret; @@ -862,7 +850,6 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) { struct folio *folio = page_folio(vmf->page); - struct page *page = &folio->page; struct file *file = vmf->vma->vm_file; struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); @@ -870,7 +857,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) unsigned long priv; vm_fault_t ret = VM_FAULT_RETRY; - _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); afs_validate(vnode, af->key); @@ -880,18 +867,18 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) * be modified. We then assume the entire page will need writing back. */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page) && - wait_on_page_fscache_killable(page) < 0) + if (folio_test_fscache(folio) && + folio_wait_fscache_killable(folio) < 0) goto out; #endif if (folio_wait_writeback_killable(folio)) goto out; - if (lock_page_killable(page) < 0) + if (folio_lock_killable(folio) < 0) goto out; - /* We mustn't change page->private until writeback is complete as that + /* We mustn't change folio->private until writeback is complete as that * details the portion of the page we need to write back and we might * need to redirty the page if there's a problem. */ @@ -900,14 +887,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) goto out; } - priv = afs_page_dirty(page, 0, thp_size(page)); - priv = afs_page_dirty_mmapped(priv); - if (PagePrivate(page)) { - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("mkwrite+"), page); + priv = afs_folio_dirty(folio, 0, folio_size(folio)); + priv = afs_folio_dirty_mmapped(priv); + if (folio_test_private(folio)) { + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio); } else { - attach_page_private(page, (void *)priv); - trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"), page); + folio_attach_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio); } file_update_time(file); @@ -948,38 +935,38 @@ void afs_prune_wb_keys(struct afs_vnode *vnode) /* * Clean up a page during invalidation. */ -int afs_launder_page(struct page *page) +int afs_launder_page(struct page *subpage) { - struct address_space *mapping = page->mapping; - struct afs_vnode *vnode = AFS_FS_I(mapping->host); + struct folio *folio = page_folio(subpage); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); struct iov_iter iter; struct bio_vec bv[1]; unsigned long priv; unsigned int f, t; int ret = 0; - _enter("{%lx}", page->index); + _enter("{%lx}", folio_index(folio)); - priv = page_private(page); - if (clear_page_dirty_for_io(page)) { + priv = (unsigned long)folio_get_private(folio); + if (folio_clear_dirty_for_io(folio)) { f = 0; - t = thp_size(page); - if (PagePrivate(page)) { - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + t = folio_size(folio); + if (folio_test_private(folio)) { + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); } - bv[0].bv_page = page; + bv[0].bv_page = &folio->page; bv[0].bv_offset = f; bv[0].bv_len = t - f; iov_iter_bvec(&iter, WRITE, bv, 1, bv[0].bv_len); - trace_afs_page_dirty(vnode, tracepoint_string("launder"), page); - ret = afs_store_data(vnode, &iter, page_offset(page) + f, true); + trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio); + ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true); } - trace_afs_page_dirty(vnode, tracepoint_string("laundered"), page); - detach_page_private(page); - wait_on_page_fscache(page); + trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio); + folio_detach_private(folio); + folio_wait_fscache(folio); return ret; } diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index f06b68040352..fc42dd0badd7 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -28,10 +28,10 @@ /* 307s to avoid pathologically clashing with transaction commit */ #define ZSTD_BTRFS_RECLAIM_JIFFIES (307 * HZ) -static ZSTD_parameters zstd_get_btrfs_parameters(unsigned int level, +static zstd_parameters zstd_get_btrfs_parameters(unsigned int level, size_t src_len) { - ZSTD_parameters params = ZSTD_getParams(level, src_len, 0); + zstd_parameters params = zstd_get_params(level, src_len); if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG) params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG; @@ -48,8 +48,8 @@ struct workspace { unsigned long last_used; /* jiffies */ struct list_head list; struct list_head lru_list; - ZSTD_inBuffer in_buf; - ZSTD_outBuffer out_buf; + zstd_in_buffer in_buf; + zstd_out_buffer out_buf; }; /* @@ -155,12 +155,12 @@ static void zstd_calc_ws_mem_sizes(void) unsigned int level; for (level = 1; level <= ZSTD_BTRFS_MAX_LEVEL; level++) { - ZSTD_parameters params = + zstd_parameters params = zstd_get_btrfs_parameters(level, ZSTD_BTRFS_MAX_INPUT); size_t level_size = max_t(size_t, - ZSTD_CStreamWorkspaceBound(params.cParams), - ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT)); + zstd_cstream_workspace_bound(¶ms.cParams), + zstd_dstream_workspace_bound(ZSTD_BTRFS_MAX_INPUT)); max_size = max_t(size_t, max_size, level_size); zstd_ws_mem_sizes[level - 1] = max_size; @@ -371,7 +371,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); - ZSTD_CStream *stream; + zstd_cstream *stream; int ret = 0; int nr_pages = 0; struct page *in_page = NULL; /* The current page to read */ @@ -381,7 +381,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, unsigned long len = *total_out; const unsigned long nr_dest_pages = *out_pages; unsigned long max_out = nr_dest_pages * PAGE_SIZE; - ZSTD_parameters params = zstd_get_btrfs_parameters(workspace->req_level, + zstd_parameters params = zstd_get_btrfs_parameters(workspace->req_level, len); *out_pages = 0; @@ -389,10 +389,10 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, *total_in = 0; /* Initialize the stream */ - stream = ZSTD_initCStream(params, len, workspace->mem, + stream = zstd_init_cstream(¶ms, len, workspace->mem, workspace->size); if (!stream) { - pr_warn("BTRFS: ZSTD_initCStream failed\n"); + pr_warn("BTRFS: zstd_init_cstream failed\n"); ret = -EIO; goto out; } @@ -418,11 +418,11 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, while (1) { size_t ret2; - ret2 = ZSTD_compressStream(stream, &workspace->out_buf, + ret2 = zstd_compress_stream(stream, &workspace->out_buf, &workspace->in_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_compressStream returned %d\n", - ZSTD_getErrorCode(ret2)); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_compress_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto out; } @@ -487,10 +487,10 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, while (1) { size_t ret2; - ret2 = ZSTD_endStream(stream, &workspace->out_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_endStream returned %d\n", - ZSTD_getErrorCode(ret2)); + ret2 = zstd_end_stream(stream, &workspace->out_buf); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_end_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto out; } @@ -548,17 +548,17 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) struct workspace *workspace = list_entry(ws, struct workspace, list); struct page **pages_in = cb->compressed_pages; size_t srclen = cb->compressed_len; - ZSTD_DStream *stream; + zstd_dstream *stream; int ret = 0; unsigned long page_in_index = 0; unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; unsigned long total_out = 0; - stream = ZSTD_initDStream( + stream = zstd_init_dstream( ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); if (!stream) { - pr_debug("BTRFS: ZSTD_initDStream failed\n"); + pr_debug("BTRFS: zstd_init_dstream failed\n"); ret = -EIO; goto done; } @@ -574,11 +574,11 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) while (1) { size_t ret2; - ret2 = ZSTD_decompressStream(stream, &workspace->out_buf, + ret2 = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", - ZSTD_getErrorCode(ret2)); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_decompress_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto done; } @@ -624,16 +624,16 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); - ZSTD_DStream *stream; + zstd_dstream *stream; int ret = 0; size_t ret2; unsigned long total_out = 0; unsigned long pg_offset = 0; - stream = ZSTD_initDStream( + stream = zstd_init_dstream( ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); if (!stream) { - pr_warn("BTRFS: ZSTD_initDStream failed\n"); + pr_warn("BTRFS: zstd_init_dstream failed\n"); ret = -EIO; goto finish; } @@ -657,15 +657,15 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in, /* Check if the frame is over and we still need more input */ if (ret2 == 0) { - pr_debug("BTRFS: ZSTD_decompressStream ended early\n"); + pr_debug("BTRFS: zstd_decompress_stream ended early\n"); ret = -EIO; goto finish; } - ret2 = ZSTD_decompressStream(stream, &workspace->out_buf, + ret2 = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", - ZSTD_getErrorCode(ret2)); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_decompress_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto finish; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 99b80b5c7a93..e53c8541f5b2 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -63,7 +63,7 @@ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct page *page, void **_fsdata); + struct folio *folio, void **_fsdata); static inline struct ceph_snap_context *page_snap_context(struct page *page) { @@ -317,13 +317,14 @@ static const struct netfs_read_request_ops ceph_netfs_read_ops = { }; /* read a single page, without unlocking it. */ -static int ceph_readpage(struct file *file, struct page *page) +static int ceph_readpage(struct file *file, struct page *subpage) { + struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_vino vino = ceph_vino(inode); - u64 off = page_offset(page); - u64 len = thp_size(page); + size_t len = folio_size(folio); + u64 off = folio_file_pos(folio); if (ci->i_inline_version != CEPH_INLINE_NONE) { /* @@ -331,19 +332,19 @@ static int ceph_readpage(struct file *file, struct page *page) * into page cache while getting Fcr caps. */ if (off == 0) { - unlock_page(page); + folio_unlock(folio); return -EINVAL; } - zero_user_segment(page, 0, thp_size(page)); - SetPageUptodate(page); - unlock_page(page); + zero_user_segment(&folio->page, 0, folio_size(folio)); + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; } - dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n", - vino.ino, vino.snap, file, off, len, page, page->index); + dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n", + vino.ino, vino.snap, file, off, len, folio, folio_index(folio)); - return netfs_readpage(file, page, &ceph_netfs_read_ops, NULL); + return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL); } static void ceph_readahead(struct readahead_control *ractl) @@ -724,7 +725,7 @@ static int ceph_writepages_start(struct address_space *mapping, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD")); - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { + if (ceph_inode_is_shutdown(inode)) { if (ci->i_wrbuffer_ref > 0) { pr_warn_ratelimited( "writepage_start %p %lld forced umount\n", @@ -1145,12 +1146,12 @@ static struct ceph_snap_context * ceph_find_incompatible(struct page *page) { struct inode *inode = page->mapping->host; - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - dout(" page %p forced umount\n", page); - return ERR_PTR(-EIO); + if (ceph_inode_is_shutdown(inode)) { + dout(" page %p %llx:%llx is shutdown\n", page, + ceph_vinop(inode)); + return ERR_PTR(-ESTALE); } for (;;) { @@ -1187,18 +1188,18 @@ ceph_find_incompatible(struct page *page) } static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct page *page, void **_fsdata) + struct folio *folio, void **_fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_snap_context *snapc; - snapc = ceph_find_incompatible(page); + snapc = ceph_find_incompatible(folio_page(folio, 0)); if (snapc) { int r; - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (IS_ERR(snapc)) return PTR_ERR(snapc); @@ -1216,12 +1217,12 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned * clean, or already dirty within the same snap context. */ static int ceph_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, unsigned aop_flags, struct page **pagep, void **fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - struct page *page = NULL; + struct folio *folio = NULL; pgoff_t index = pos >> PAGE_SHIFT; int r; @@ -1230,39 +1231,43 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, * for inline_version sent to the MDS. */ if (ci->i_inline_version != CEPH_INLINE_NONE) { - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) + unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) return -ENOMEM; /* * The inline_version on a new inode is set to 1. If that's the - * case, then the page is brand new and isn't yet Uptodate. + * case, then the folio is brand new and isn't yet Uptodate. */ r = 0; if (index == 0 && ci->i_inline_version != 1) { - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { WARN_ONCE(1, "ceph: write_begin called on still-inlined inode (inline_version %llu)!\n", ci->i_inline_version); r = -EINVAL; } goto out; } - zero_user_segment(page, 0, thp_size(page)); - SetPageUptodate(page); + zero_user_segment(&folio->page, 0, folio_size(folio)); + folio_mark_uptodate(folio); goto out; } - r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &page, NULL, + r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL, &ceph_netfs_read_ops, NULL); out: if (r == 0) - wait_on_page_fscache(page); + folio_wait_fscache(folio); if (r < 0) { - if (page) - put_page(page); + if (folio) + folio_put(folio); } else { - WARN_ON_ONCE(!PageLocked(page)); - *pagep = page; + WARN_ON_ONCE(!folio_test_locked(folio)); + *pagep = &folio->page; } return r; } @@ -1273,32 +1278,33 @@ out: */ static int ceph_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { + struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); bool check_cap = false; - dout("write_end file %p inode %p page %p %d~%d (%d)\n", file, - inode, page, (int)pos, (int)copied, (int)len); + dout("write_end file %p inode %p folio %p %d~%d (%d)\n", file, + inode, folio, (int)pos, (int)copied, (int)len); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { /* just return that nothing was copied on a short copy */ if (copied < len) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } /* did file size increase? */ if (pos+copied > i_size_read(inode)) check_cap = ceph_inode_set_size(inode, pos+copied); - set_page_dirty(page); + folio_mark_dirty(folio); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (check_cap) ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL); @@ -1306,17 +1312,6 @@ out: return copied; } -/* - * we set .direct_IO to indicate direct io is supported, but since we - * intercept O_DIRECT reads and writes early, this function should - * never get called. - */ -static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter) -{ - WARN_ON(1); - return -EINVAL; -} - const struct address_space_operations ceph_aops = { .readpage = ceph_readpage, .readahead = ceph_readahead, @@ -1327,7 +1322,7 @@ const struct address_space_operations ceph_aops = { .set_page_dirty = ceph_set_page_dirty, .invalidatepage = ceph_invalidatepage, .releasepage = ceph_releasepage, - .direct_IO = ceph_direct_io, + .direct_IO = noop_direct_IO, }; static void ceph_block_sigs(sigset_t *oldset) @@ -1356,6 +1351,9 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) sigset_t oldset; vm_fault_t ret = VM_FAULT_SIGBUS; + if (ceph_inode_is_shutdown(inode)) + return ret; + ceph_block_sigs(&oldset); dout("filemap_fault %p %llx.%llx %llu trying to get caps\n", @@ -1447,6 +1445,9 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf) sigset_t oldset; vm_fault_t ret = VM_FAULT_SIGBUS; + if (ceph_inode_is_shutdown(inode)) + return ret; + prealloc_cf = ceph_alloc_cap_flush(); if (!prealloc_cf) return VM_FAULT_OOM; diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 9cfadbb86568..457afda5498a 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -12,12 +12,6 @@ #include "super.h" #include "cache.h" -struct ceph_aux_inode { - u64 version; - u64 mtime_sec; - u64 mtime_nsec; -}; - struct fscache_netfs ceph_cache_netfs = { .name = "ceph", .version = 0, @@ -109,20 +103,14 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux( void *cookie_netfs_data, const void *data, uint16_t dlen, loff_t object_size) { - struct ceph_aux_inode aux; struct ceph_inode_info* ci = cookie_netfs_data; struct inode* inode = &ci->vfs_inode; - if (dlen != sizeof(aux) || + if (dlen != sizeof(ci->i_version) || i_size_read(inode) != object_size) return FSCACHE_CHECKAUX_OBSOLETE; - memset(&aux, 0, sizeof(aux)); - aux.version = ci->i_version; - aux.mtime_sec = inode->i_mtime.tv_sec; - aux.mtime_nsec = inode->i_mtime.tv_nsec; - - if (memcmp(data, &aux, sizeof(aux)) != 0) + if (*(u64 *)data != ci->i_version) return FSCACHE_CHECKAUX_OBSOLETE; dout("ceph inode 0x%p cached okay\n", ci); @@ -139,7 +127,6 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - struct ceph_aux_inode aux; /* No caching for filesystem */ if (!fsc->fscache) @@ -151,14 +138,10 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) inode_lock_nested(inode, I_MUTEX_CHILD); if (!ci->fscache) { - memset(&aux, 0, sizeof(aux)); - aux.version = ci->i_version; - aux.mtime_sec = inode->i_mtime.tv_sec; - aux.mtime_nsec = inode->i_mtime.tv_nsec; ci->fscache = fscache_acquire_cookie(fsc->fscache, &ceph_fscache_inode_object_def, &ci->i_vino, sizeof(ci->i_vino), - &aux, sizeof(aux), + &ci->i_version, sizeof(ci->i_version), ci, i_size_read(inode), false); } inode_unlock(inode); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 8f537f1d9d1d..b9460b6fb76f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1188,11 +1188,11 @@ void ceph_remove_cap(struct ceph_cap *cap, bool queue_release) lockdep_assert_held(&ci->i_ceph_lock); - fsc = ceph_sb_to_client(ci->vfs_inode.i_sb); + fsc = ceph_inode_to_client(&ci->vfs_inode); WARN_ON_ONCE(ci->i_auth_cap == cap && !list_empty(&ci->i_dirty_item) && !fsc->blocklisted && - READ_ONCE(fsc->mount_state) != CEPH_MOUNT_SHUTDOWN); + !ceph_inode_is_shutdown(&ci->vfs_inode)); __ceph_remove_cap(cap, queue_release); } @@ -1968,8 +1968,8 @@ retry: } } - dout("check_caps %p file_want %s used %s dirty %s flushing %s" - " issued %s revoking %s retain %s %s%s\n", inode, + dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s" + " issued %s revoking %s retain %s %s%s\n", ceph_vinop(inode), ceph_cap_string(file_wanted), ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps), ceph_cap_string(ci->i_flushing_caps), @@ -1990,7 +1990,8 @@ retry: (revoking & (CEPH_CAP_FILE_CACHE| CEPH_CAP_FILE_LAZYIO)) && /* or revoking cache */ !tried_invalidate) { - dout("check_caps trying to invalidate on %p\n", inode); + dout("check_caps trying to invalidate on %llx.%llx\n", + ceph_vinop(inode)); if (try_nonblocking_invalidate(inode) < 0) { dout("check_caps queuing invalidate\n"); queue_invalidate = true; @@ -2629,9 +2630,9 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got, * * Returns 0 if caps were not able to be acquired (yet), 1 if succeed, * or a negative error code. There are 3 speical error codes: - * -EAGAIN: need to sleep but non-blocking is specified - * -EFBIG: ask caller to call check_max_size() and try again. - * -ESTALE: ask caller to call ceph_renew_caps() and try again. + * -EAGAIN: need to sleep but non-blocking is specified + * -EFBIG: ask caller to call check_max_size() and try again. + * -EUCLEAN: ask caller to call ceph_renew_caps() and try again. */ enum { /* first 8 bits are reserved for CEPH_FILE_MODE_FOO */ @@ -2679,7 +2680,7 @@ again: dout("get_cap_refs %p endoff %llu > maxsize %llu\n", inode, endoff, ci->i_max_size); if (endoff > ci->i_requested_max_size) - ret = ci->i_auth_cap ? -EFBIG : -ESTALE; + ret = ci->i_auth_cap ? -EFBIG : -EUCLEAN; goto out_unlock; } /* @@ -2749,9 +2750,9 @@ again: goto out_unlock; } - if (READ_ONCE(mdsc->fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - dout("get_cap_refs %p forced umount\n", inode); - ret = -EIO; + if (ceph_inode_is_shutdown(inode)) { + dout("get_cap_refs %p inode is shutdown\n", inode); + ret = -ESTALE; goto out_unlock; } mds_wanted = __ceph_caps_mds_wanted(ci, false); @@ -2759,7 +2760,7 @@ again: dout("get_cap_refs %p need %s > mds_wanted %s\n", inode, ceph_cap_string(need), ceph_cap_string(mds_wanted)); - ret = -ESTALE; + ret = -EUCLEAN; goto out_unlock; } @@ -2843,7 +2844,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, ret = try_get_cap_refs(inode, need, want, 0, flags, got); /* three special error codes */ - if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE) + if (ret == -EAGAIN || ret == -EFBIG || ret == -EUCLEAN) ret = 0; return ret; } @@ -2926,7 +2927,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got } if (ret < 0) { - if (ret == -EFBIG || ret == -ESTALE) { + if (ret == -EFBIG || ret == -EUCLEAN) { int ret2 = ceph_wait_on_async_create(inode); if (ret2 < 0) return ret2; @@ -2935,7 +2936,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got check_max_size(inode, endoff); continue; } - if (ret == -ESTALE) { + if (ret == -EUCLEAN) { /* session was killed, try renew caps */ ret = ceph_renew_caps(inode, flags); if (ret == 0) @@ -4315,7 +4316,7 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s) i_dirty_item); inode = &ci->vfs_inode; ihold(inode); - dout("flush_dirty_caps %p\n", inode); + dout("flush_dirty_caps %llx.%llx\n", ceph_vinop(inode)); spin_unlock(&mdsc->cap_dirty_lock); ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL); iput(inode); @@ -4560,3 +4561,119 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, spin_unlock(&dentry->d_lock); return ret; } + +static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_cap_snap *capsnap; + int capsnap_release = 0; + + lockdep_assert_held(&ci->i_ceph_lock); + + dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode); + + while (!list_empty(&ci->i_cap_snaps)) { + capsnap = list_first_entry(&ci->i_cap_snaps, + struct ceph_cap_snap, ci_item); + __ceph_remove_capsnap(inode, capsnap, NULL, NULL); + ceph_put_snap_context(capsnap->context); + ceph_put_cap_snap(capsnap); + capsnap_release++; + } + wake_up_all(&ci->i_cap_wq); + wake_up_all(&mdsc->cap_flushing_wq); + return capsnap_release; +} + +int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate) +{ + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_mds_client *mdsc = fsc->mdsc; + struct ceph_inode_info *ci = ceph_inode(inode); + bool is_auth; + bool dirty_dropped = false; + int iputs = 0; + + lockdep_assert_held(&ci->i_ceph_lock); + + dout("removing cap %p, ci is %p, inode is %p\n", + cap, ci, &ci->vfs_inode); + + is_auth = (cap == ci->i_auth_cap); + __ceph_remove_cap(cap, false); + if (is_auth) { + struct ceph_cap_flush *cf; + + if (ceph_inode_is_shutdown(inode)) { + if (inode->i_data.nrpages > 0) + *invalidate = true; + if (ci->i_wrbuffer_ref > 0) + mapping_set_error(&inode->i_data, -EIO); + } + + spin_lock(&mdsc->cap_dirty_lock); + + /* trash all of the cap flushes for this inode */ + while (!list_empty(&ci->i_cap_flush_list)) { + cf = list_first_entry(&ci->i_cap_flush_list, + struct ceph_cap_flush, i_list); + list_del_init(&cf->g_list); + list_del_init(&cf->i_list); + if (!cf->is_capsnap) + ceph_free_cap_flush(cf); + } + + if (!list_empty(&ci->i_dirty_item)) { + pr_warn_ratelimited( + " dropping dirty %s state for %p %lld\n", + ceph_cap_string(ci->i_dirty_caps), + inode, ceph_ino(inode)); + ci->i_dirty_caps = 0; + list_del_init(&ci->i_dirty_item); + dirty_dropped = true; + } + if (!list_empty(&ci->i_flushing_item)) { + pr_warn_ratelimited( + " dropping dirty+flushing %s state for %p %lld\n", + ceph_cap_string(ci->i_flushing_caps), + inode, ceph_ino(inode)); + ci->i_flushing_caps = 0; + list_del_init(&ci->i_flushing_item); + mdsc->num_cap_flushing--; + dirty_dropped = true; + } + spin_unlock(&mdsc->cap_dirty_lock); + + if (dirty_dropped) { + mapping_set_error(inode->i_mapping, -EIO); + + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } + } + + if (atomic_read(&ci->i_filelock_ref) > 0) { + /* make further file lock syscall return -EIO */ + ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK; + pr_warn_ratelimited(" dropping file locks for %p %lld\n", + inode, ceph_ino(inode)); + } + + if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) { + cf = ci->i_prealloc_cap_flush; + ci->i_prealloc_cap_flush = NULL; + if (!cf->is_capsnap) + ceph_free_cap_flush(cf); + } + + if (!list_empty(&ci->i_cap_snaps)) + iputs = remove_capsnaps(mdsc, inode); + } + if (dirty_dropped) + ++iputs; + return iputs; +} diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 38b78b45811f..3cf7c9c1085b 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -146,82 +146,93 @@ static int mdsc_show(struct seq_file *s, void *p) name, total, avg, _min, max, sum); \ } -static int metric_show(struct seq_file *s, void *p) +static int metrics_file_show(struct seq_file *s, void *p) { struct ceph_fs_client *fsc = s->private; - struct ceph_mds_client *mdsc = fsc->mdsc; - struct ceph_client_metric *m = &mdsc->metric; - int nr_caps = 0; - s64 total, sum, avg, min, max, sq; - u64 sum_sz, avg_sz, min_sz, max_sz; + struct ceph_client_metric *m = &fsc->mdsc->metric; - sum = percpu_counter_sum(&m->total_inodes); seq_printf(s, "item total\n"); seq_printf(s, "------------------------------------------\n"); - seq_printf(s, "%-35s%lld / %lld\n", "opened files / total inodes", - atomic64_read(&m->opened_files), sum); - seq_printf(s, "%-35s%lld / %lld\n", "pinned i_caps / total inodes", - atomic64_read(&m->total_caps), sum); - seq_printf(s, "%-35s%lld / %lld\n", "opened inodes / total inodes", - percpu_counter_sum(&m->opened_inodes), sum); - - seq_printf(s, "\n"); + seq_printf(s, "%-35s%lld\n", "total inodes", + percpu_counter_sum(&m->total_inodes)); + seq_printf(s, "%-35s%lld\n", "opened files", + atomic64_read(&m->opened_files)); + seq_printf(s, "%-35s%lld\n", "pinned i_caps", + atomic64_read(&m->total_caps)); + seq_printf(s, "%-35s%lld\n", "opened inodes", + percpu_counter_sum(&m->opened_inodes)); + return 0; +} + +static const char * const metric_str[] = { + "read", + "write", + "metadata", + "copyfrom" +}; +static int metrics_latency_show(struct seq_file *s, void *p) +{ + struct ceph_fs_client *fsc = s->private; + struct ceph_client_metric *cm = &fsc->mdsc->metric; + struct ceph_metric *m; + s64 total, sum, avg, min, max, sq; + int i; + seq_printf(s, "item total avg_lat(us) min_lat(us) max_lat(us) stdev(us)\n"); seq_printf(s, "-----------------------------------------------------------------------------------\n"); - spin_lock(&m->read_metric_lock); - total = m->total_reads; - sum = m->read_latency_sum; - avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; - min = m->read_latency_min; - max = m->read_latency_max; - sq = m->read_latency_sq_sum; - spin_unlock(&m->read_metric_lock); - CEPH_LAT_METRIC_SHOW("read", total, avg, min, max, sq); - - spin_lock(&m->write_metric_lock); - total = m->total_writes; - sum = m->write_latency_sum; - avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; - min = m->write_latency_min; - max = m->write_latency_max; - sq = m->write_latency_sq_sum; - spin_unlock(&m->write_metric_lock); - CEPH_LAT_METRIC_SHOW("write", total, avg, min, max, sq); - - spin_lock(&m->metadata_metric_lock); - total = m->total_metadatas; - sum = m->metadata_latency_sum; - avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; - min = m->metadata_latency_min; - max = m->metadata_latency_max; - sq = m->metadata_latency_sq_sum; - spin_unlock(&m->metadata_metric_lock); - CEPH_LAT_METRIC_SHOW("metadata", total, avg, min, max, sq); - - seq_printf(s, "\n"); + for (i = 0; i < METRIC_MAX; i++) { + m = &cm->metric[i]; + spin_lock(&m->lock); + total = m->total; + sum = m->latency_sum; + avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; + min = m->latency_min; + max = m->latency_max; + sq = m->latency_sq_sum; + spin_unlock(&m->lock); + CEPH_LAT_METRIC_SHOW(metric_str[i], total, avg, min, max, sq); + } + + return 0; +} + +static int metrics_size_show(struct seq_file *s, void *p) +{ + struct ceph_fs_client *fsc = s->private; + struct ceph_client_metric *cm = &fsc->mdsc->metric; + struct ceph_metric *m; + s64 total; + u64 sum, avg, min, max; + int i; + seq_printf(s, "item total avg_sz(bytes) min_sz(bytes) max_sz(bytes) total_sz(bytes)\n"); seq_printf(s, "----------------------------------------------------------------------------------------\n"); - spin_lock(&m->read_metric_lock); - total = m->total_reads; - sum_sz = m->read_size_sum; - avg_sz = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum_sz, total) : 0; - min_sz = m->read_size_min; - max_sz = m->read_size_max; - spin_unlock(&m->read_metric_lock); - CEPH_SZ_METRIC_SHOW("read", total, avg_sz, min_sz, max_sz, sum_sz); - - spin_lock(&m->write_metric_lock); - total = m->total_writes; - sum_sz = m->write_size_sum; - avg_sz = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum_sz, total) : 0; - min_sz = m->write_size_min; - max_sz = m->write_size_max; - spin_unlock(&m->write_metric_lock); - CEPH_SZ_METRIC_SHOW("write", total, avg_sz, min_sz, max_sz, sum_sz); - - seq_printf(s, "\n"); + for (i = 0; i < METRIC_MAX; i++) { + /* skip 'metadata' as it doesn't use the size metric */ + if (i == METRIC_METADATA) + continue; + m = &cm->metric[i]; + spin_lock(&m->lock); + total = m->total; + sum = m->size_sum; + avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0; + min = m->size_min; + max = m->size_max; + spin_unlock(&m->lock); + CEPH_SZ_METRIC_SHOW(metric_str[i], total, avg, min, max, sum); + } + + return 0; +} + +static int metrics_caps_show(struct seq_file *s, void *p) +{ + struct ceph_fs_client *fsc = s->private; + struct ceph_client_metric *m = &fsc->mdsc->metric; + int nr_caps = 0; + seq_printf(s, "item total miss hit\n"); seq_printf(s, "-------------------------------------------------\n"); @@ -350,8 +361,11 @@ DEFINE_SHOW_ATTRIBUTE(mdsmap); DEFINE_SHOW_ATTRIBUTE(mdsc); DEFINE_SHOW_ATTRIBUTE(caps); DEFINE_SHOW_ATTRIBUTE(mds_sessions); -DEFINE_SHOW_ATTRIBUTE(metric); DEFINE_SHOW_ATTRIBUTE(status); +DEFINE_SHOW_ATTRIBUTE(metrics_file); +DEFINE_SHOW_ATTRIBUTE(metrics_latency); +DEFINE_SHOW_ATTRIBUTE(metrics_size); +DEFINE_SHOW_ATTRIBUTE(metrics_caps); /* @@ -385,8 +399,9 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) debugfs_remove(fsc->debugfs_mdsmap); debugfs_remove(fsc->debugfs_mds_sessions); debugfs_remove(fsc->debugfs_caps); - debugfs_remove(fsc->debugfs_metric); + debugfs_remove(fsc->debugfs_status); debugfs_remove(fsc->debugfs_mdsc); + debugfs_remove_recursive(fsc->debugfs_metrics_dir); } void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) @@ -426,12 +441,6 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) fsc, &mdsc_fops); - fsc->debugfs_metric = debugfs_create_file("metrics", - 0400, - fsc->client->debugfs_dir, - fsc, - &metric_fops); - fsc->debugfs_caps = debugfs_create_file("caps", 0400, fsc->client->debugfs_dir, @@ -443,6 +452,18 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) fsc->client->debugfs_dir, fsc, &status_fops); + + fsc->debugfs_metrics_dir = debugfs_create_dir("metrics", + fsc->client->debugfs_dir); + + debugfs_create_file("file", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_file_fops); + debugfs_create_file("latency", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_latency_fops); + debugfs_create_file("size", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_size_fops); + debugfs_create_file("caps", 0400, fsc->debugfs_metrics_dir, fsc, + &metrics_caps_fops); } diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 1d65934c1262..e0fa66ac8b9f 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -157,6 +157,11 @@ static struct inode *__lookup_inode(struct super_block *sb, u64 ino) ceph_mdsc_put_request(req); if (!inode) return err < 0 ? ERR_PTR(err) : ERR_PTR(-ESTALE); + } else { + if (ceph_inode_is_shutdown(inode)) { + iput(inode); + return ERR_PTR(-ESTALE); + } } return inode; } @@ -223,8 +228,13 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb, return ERR_PTR(-ESTALE); inode = ceph_find_inode(sb, vino); - if (inode) + if (inode) { + if (ceph_inode_is_shutdown(inode)) { + iput(inode); + return ERR_PTR(-ESTALE); + } return d_obtain_alias(inode); + } req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO, USE_ANY_MDS); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b129ea551378..02a0a0fd9ccd 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -525,6 +525,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, if (result) { struct dentry *dentry = req->r_dentry; + struct inode *inode = d_inode(dentry); int pathlen = 0; u64 base = 0; char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen, @@ -534,7 +535,8 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, if (!d_unhashed(dentry)) d_drop(dentry); - /* FIXME: start returning I/O errors on all accesses? */ + ceph_inode_shutdown(inode); + pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n", base, IS_ERR(path) ? "<<bad>>" : path, result); ceph_mdsc_free_path(path, pathlen); @@ -556,7 +558,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, } ceph_kick_flushing_inode_caps(req->r_session, ci); spin_unlock(&ci->i_ceph_lock); - } else { + } else if (!result) { pr_warn("%s: no req->r_target_inode for 0x%llx\n", __func__, req->r_deleg_ino); } @@ -845,6 +847,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, ssize_t ret; u64 off = iocb->ki_pos; u64 len = iov_iter_count(to); + u64 i_size; dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); @@ -868,7 +871,6 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, struct page **pages; int num_pages; size_t page_off; - u64 i_size; bool more; int idx; size_t left; @@ -951,11 +953,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, } if (off > iocb->ki_pos) { - if (ret >= 0 && - iov_iter_count(to) > 0 && off >= i_size_read(inode)) + if (off >= i_size) { *retry_op = CHECK_EOF; - ret = off - iocb->ki_pos; - iocb->ki_pos = off; + ret = i_size - iocb->ki_pos; + iocb->ki_pos = i_size; + } else { + ret = off - iocb->ki_pos; + iocb->ki_pos = off; + } } dout("sync_read result %zd retry_op %d\n", ret, *retry_op); @@ -1526,6 +1531,9 @@ again: dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode); + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + if (direct_lock) ceph_start_io_direct(inode); else @@ -1678,6 +1686,9 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) loff_t pos; loff_t limit = max(i_size_read(inode), fsc->max_file_size); + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; @@ -2200,6 +2211,54 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode, return 0; } +static struct ceph_osd_request * +ceph_alloc_copyfrom_request(struct ceph_osd_client *osdc, + u64 src_snapid, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 truncate_seq, u64 truncate_size) +{ + struct ceph_osd_request *req; + int ret; + u32 src_fadvise_flags = + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE; + u32 dst_fadvise_flags = + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED; + + req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL); + if (!req) + return ERR_PTR(-ENOMEM); + + req->r_flags = CEPH_OSD_FLAG_WRITE; + + ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc); + ceph_oid_copy(&req->r_t.base_oid, dst_oid); + + ret = osd_req_op_copy_from_init(req, src_snapid, 0, + src_oid, src_oloc, + src_fadvise_flags, + dst_fadvise_flags, + truncate_seq, + truncate_size, + CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); + if (ret) + goto out; + + ret = ceph_osdc_alloc_messages(req, GFP_KERNEL); + if (ret) + goto out; + + return req; + +out: + ceph_osdc_put_request(req); + return ERR_PTR(ret); +} + static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off, struct ceph_inode_info *dst_ci, u64 *dst_off, struct ceph_fs_client *fsc, @@ -2207,6 +2266,8 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off { struct ceph_object_locator src_oloc, dst_oloc; struct ceph_object_id src_oid, dst_oid; + struct ceph_osd_client *osdc; + struct ceph_osd_request *req; size_t bytes = 0; u64 src_objnum, src_objoff, dst_objnum, dst_objoff; u32 src_objlen, dst_objlen; @@ -2217,6 +2278,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns); dst_oloc.pool = dst_ci->i_layout.pool_id; dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns); + osdc = &fsc->client->osdc; while (len >= object_size) { ceph_calc_file_object_mapping(&src_ci->i_layout, *src_off, @@ -2232,17 +2294,22 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off ceph_oid_printf(&dst_oid, "%llx.%08llx", dst_ci->i_vino.ino, dst_objnum); /* Do an object remote copy */ - ret = ceph_osdc_copy_from(&fsc->client->osdc, - src_ci->i_vino.snap, 0, - &src_oid, &src_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_NOCACHE, - &dst_oid, &dst_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, - dst_ci->i_truncate_seq, - dst_ci->i_truncate_size, - CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); + req = ceph_alloc_copyfrom_request(osdc, src_ci->i_vino.snap, + &src_oid, &src_oloc, + &dst_oid, &dst_oloc, + dst_ci->i_truncate_seq, + dst_ci->i_truncate_size); + if (IS_ERR(req)) + ret = PTR_ERR(req); + else { + ceph_osdc_start_request(osdc, req, false); + ret = ceph_osdc_wait_request(osdc, req); + ceph_update_copyfrom_metrics(&fsc->mdsc->metric, + req->r_start_latency, + req->r_end_latency, + object_size, ret); + ceph_osdc_put_request(req); + } if (ret) { if (ret == -EOPNOTSUPP) { fsc->have_copy_from2 = false; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 1c7574105478..e3322fcb2e8d 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1841,15 +1841,14 @@ void ceph_queue_inode_work(struct inode *inode, int work_bit) static void ceph_do_invalidate_pages(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); u32 orig_gen; int check = 0; mutex_lock(&ci->i_truncate_mutex); - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n", - inode, ceph_ino(inode)); + if (ceph_inode_is_shutdown(inode)) { + pr_warn_ratelimited("%s: inode %llx.%llx is shut down\n", + __func__, ceph_vinop(inode)); mapping_set_error(inode->i_mapping, -EIO); truncate_pagecache(inode, 0); mutex_unlock(&ci->i_truncate_mutex); @@ -1871,7 +1870,8 @@ static void ceph_do_invalidate_pages(struct inode *inode) ceph_fscache_invalidate(inode); if (invalidate_inode_pages2(inode->i_mapping) < 0) { - pr_err("invalidate_pages %p fails\n", inode); + pr_err("invalidate_inode_pages2 %llx.%llx failed\n", + ceph_vinop(inode)); } spin_lock(&ci->i_ceph_lock); @@ -2103,12 +2103,14 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) loff_t isize = i_size_read(inode); dout("setattr %p size %lld -> %lld\n", inode, isize, attr->ia_size); - if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size > isize) { - i_size_write(inode, attr->ia_size); - inode->i_blocks = calc_inode_blocks(attr->ia_size); - ci->i_reported_size = attr->ia_size; - dirtied |= CEPH_CAP_FILE_EXCL; - ia_valid |= ATTR_MTIME; + if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) { + if (attr->ia_size > isize) { + i_size_write(inode, attr->ia_size); + inode->i_blocks = calc_inode_blocks(attr->ia_size); + ci->i_reported_size = attr->ia_size; + dirtied |= CEPH_CAP_FILE_EXCL; + ia_valid |= ATTR_MTIME; + } } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || attr->ia_size != isize) { req->r_args.setattr.size = cpu_to_le64(attr->ia_size); @@ -2217,6 +2219,9 @@ int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + err = setattr_prepare(&init_user_ns, dentry, attr); if (err != 0) return err; @@ -2347,6 +2352,9 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, u32 valid_mask = STATX_BASIC_STATS; int err = 0; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + /* Skip the getattr altogether if we're asked not to sync */ if (!(flags & AT_STATX_DONT_SYNC)) { err = ceph_do_getattr(inode, @@ -2394,3 +2402,27 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->result_mask = request_mask & valid_mask; return err; } + +void ceph_inode_shutdown(struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct rb_node *p; + int iputs = 0; + bool invalidate = false; + + spin_lock(&ci->i_ceph_lock); + ci->i_ceph_flags |= CEPH_I_SHUTDOWN; + p = rb_first(&ci->i_caps); + while (p) { + struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); + + p = rb_next(p); + iputs += ceph_purge_inode_cap(inode, cap, &invalidate); + } + spin_unlock(&ci->i_ceph_lock); + + if (invalidate) + ceph_queue_invalidate(inode); + while (iputs--) + iput(inode); +} diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index d8c31069fbf2..d1f154aec249 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -241,6 +241,9 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + dout("ceph_lock, fl_owner: %p\n", fl->fl_owner); /* set wait bit as appropriate, then make command as Ceph expects it*/ @@ -303,6 +306,9 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + dout("ceph_flock, fl_file: %p\n", fl->fl_file); spin_lock(&ci->i_ceph_lock); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index d64413adc0fd..250aad330a10 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1590,129 +1590,23 @@ out: return ret; } -static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode) -{ - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_cap_snap *capsnap; - int capsnap_release = 0; - - lockdep_assert_held(&ci->i_ceph_lock); - - dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode); - - while (!list_empty(&ci->i_cap_snaps)) { - capsnap = list_first_entry(&ci->i_cap_snaps, - struct ceph_cap_snap, ci_item); - __ceph_remove_capsnap(inode, capsnap, NULL, NULL); - ceph_put_snap_context(capsnap->context); - ceph_put_cap_snap(capsnap); - capsnap_release++; - } - wake_up_all(&ci->i_cap_wq); - wake_up_all(&mdsc->cap_flushing_wq); - return capsnap_release; -} - static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) { - struct ceph_fs_client *fsc = (struct ceph_fs_client *)arg; - struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); - LIST_HEAD(to_remove); - bool dirty_dropped = false; bool invalidate = false; - int capsnap_release = 0; + int iputs; dout("removing cap %p, ci is %p, inode is %p\n", cap, ci, &ci->vfs_inode); spin_lock(&ci->i_ceph_lock); - __ceph_remove_cap(cap, false); - if (!ci->i_auth_cap) { - struct ceph_cap_flush *cf; - - if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) { - if (inode->i_data.nrpages > 0) - invalidate = true; - if (ci->i_wrbuffer_ref > 0) - mapping_set_error(&inode->i_data, -EIO); - } - - while (!list_empty(&ci->i_cap_flush_list)) { - cf = list_first_entry(&ci->i_cap_flush_list, - struct ceph_cap_flush, i_list); - list_move(&cf->i_list, &to_remove); - } - - spin_lock(&mdsc->cap_dirty_lock); - - list_for_each_entry(cf, &to_remove, i_list) - list_del_init(&cf->g_list); - - if (!list_empty(&ci->i_dirty_item)) { - pr_warn_ratelimited( - " dropping dirty %s state for %p %lld\n", - ceph_cap_string(ci->i_dirty_caps), - inode, ceph_ino(inode)); - ci->i_dirty_caps = 0; - list_del_init(&ci->i_dirty_item); - dirty_dropped = true; - } - if (!list_empty(&ci->i_flushing_item)) { - pr_warn_ratelimited( - " dropping dirty+flushing %s state for %p %lld\n", - ceph_cap_string(ci->i_flushing_caps), - inode, ceph_ino(inode)); - ci->i_flushing_caps = 0; - list_del_init(&ci->i_flushing_item); - mdsc->num_cap_flushing--; - dirty_dropped = true; - } - spin_unlock(&mdsc->cap_dirty_lock); - - if (dirty_dropped) { - mapping_set_error(inode->i_mapping, -EIO); - - if (ci->i_wrbuffer_ref_head == 0 && - ci->i_wr_ref == 0 && - ci->i_dirty_caps == 0 && - ci->i_flushing_caps == 0) { - ceph_put_snap_context(ci->i_head_snapc); - ci->i_head_snapc = NULL; - } - } - - if (atomic_read(&ci->i_filelock_ref) > 0) { - /* make further file lock syscall return -EIO */ - ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK; - pr_warn_ratelimited(" dropping file locks for %p %lld\n", - inode, ceph_ino(inode)); - } - - if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) { - list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); - ci->i_prealloc_cap_flush = NULL; - } - - if (!list_empty(&ci->i_cap_snaps)) - capsnap_release = remove_capsnaps(mdsc, inode); - } + iputs = ceph_purge_inode_cap(inode, cap, &invalidate); spin_unlock(&ci->i_ceph_lock); - while (!list_empty(&to_remove)) { - struct ceph_cap_flush *cf; - cf = list_first_entry(&to_remove, - struct ceph_cap_flush, i_list); - list_del_init(&cf->i_list); - if (!cf->is_capsnap) - ceph_free_cap_flush(cf); - } wake_up_all(&ci->i_cap_wq); if (invalidate) ceph_queue_invalidate(inode); - if (dirty_dropped) - iput(inode); - while (capsnap_release--) + while (iputs--) iput(inode); return 0; } @@ -3467,9 +3361,14 @@ static void handle_session(struct ceph_mds_session *session, if (msg_version >= 3) { u32 len; - /* version >= 2, metadata */ - if (__decode_session_metadata(&p, end, &blocklisted) < 0) + /* version >= 2 and < 5, decode metadata, skip otherwise + * as it's handled via flags. + */ + if (msg_version >= 5) + ceph_decode_skip_map(&p, end, string, string, bad); + else if (__decode_session_metadata(&p, end, &blocklisted) < 0) goto bad; + /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); if (len) { @@ -3478,6 +3377,18 @@ static void handle_session(struct ceph_mds_session *session, } } + if (msg_version >= 5) { + u32 flags; + /* version >= 4, struct_v, struct_cv, len, metric_spec */ + ceph_decode_skip_n(&p, end, 2 + sizeof(u32) * 2, bad); + /* version >= 5, flags */ + ceph_decode_32_safe(&p, end, flags, bad); + if (flags & CEPH_SESSION_BLOCKLISTED) { + pr_warn("mds%d session blocklisted\n", session->s_mds); + blocklisted = true; + } + } + mutex_lock(&mdsc->mutex); if (op == CEPH_SESSION_CLOSE) { ceph_get_mds_session(session); @@ -5072,7 +4983,8 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) return; bad: - pr_err("error decoding fsmap\n"); + pr_err("error decoding fsmap %d. Shutting down mount.\n", err); + ceph_umount_begin(mdsc->fsc->sb); err_out: mutex_lock(&mdsc->mutex); mdsc->mdsmap_err = err; @@ -5139,7 +5051,8 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) bad_unlock: mutex_unlock(&mdsc->mutex); bad: - pr_err("error decoding mdsmap %d\n", err); + pr_err("error decoding mdsmap %d. Shutting down mount.\n", err); + ceph_umount_begin(mdsc->fsc->sb); return; } diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 61d67cbcb367..30387733765d 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -263,10 +263,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2) goto nomem; for (j = 0; j < num_export_targets; j++) { target = ceph_decode_32(&pexport_targets); - if (target >= m->possible_max_rank) { - err = -EIO; - goto corrupt; - } info->export_targets[j] = target; } } else { diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c index 04d5df29bbbf..c57699d8408d 100644 --- a/fs/ceph/metric.c +++ b/fs/ceph/metric.c @@ -62,7 +62,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, read->header.ver = 1; read->header.compat = 1; read->header.data_len = cpu_to_le32(sizeof(*read) - header_len); - sum = m->read_latency_sum; + sum = m->metric[METRIC_READ].latency_sum; jiffies_to_timespec64(sum, &ts); read->sec = cpu_to_le32(ts.tv_sec); read->nsec = cpu_to_le32(ts.tv_nsec); @@ -74,7 +74,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, write->header.ver = 1; write->header.compat = 1; write->header.data_len = cpu_to_le32(sizeof(*write) - header_len); - sum = m->write_latency_sum; + sum = m->metric[METRIC_WRITE].latency_sum; jiffies_to_timespec64(sum, &ts); write->sec = cpu_to_le32(ts.tv_sec); write->nsec = cpu_to_le32(ts.tv_nsec); @@ -86,7 +86,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, meta->header.ver = 1; meta->header.compat = 1; meta->header.data_len = cpu_to_le32(sizeof(*meta) - header_len); - sum = m->metadata_latency_sum; + sum = m->metric[METRIC_METADATA].latency_sum; jiffies_to_timespec64(sum, &ts); meta->sec = cpu_to_le32(ts.tv_sec); meta->nsec = cpu_to_le32(ts.tv_nsec); @@ -141,8 +141,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, rsize->header.ver = 1; rsize->header.compat = 1; rsize->header.data_len = cpu_to_le32(sizeof(*rsize) - header_len); - rsize->total_ops = cpu_to_le64(m->total_reads); - rsize->total_size = cpu_to_le64(m->read_size_sum); + rsize->total_ops = cpu_to_le64(m->metric[METRIC_READ].total); + rsize->total_size = cpu_to_le64(m->metric[METRIC_READ].size_sum); items++; /* encode the write io size metric */ @@ -151,8 +151,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, wsize->header.ver = 1; wsize->header.compat = 1; wsize->header.data_len = cpu_to_le32(sizeof(*wsize) - header_len); - wsize->total_ops = cpu_to_le64(m->total_writes); - wsize->total_size = cpu_to_le64(m->write_size_sum); + wsize->total_ops = cpu_to_le64(m->metric[METRIC_WRITE].total); + wsize->total_size = cpu_to_le64(m->metric[METRIC_WRITE].size_sum); items++; put_unaligned_le32(items, &head->num); @@ -220,7 +220,8 @@ static void metric_delayed_work(struct work_struct *work) int ceph_metric_init(struct ceph_client_metric *m) { - int ret; + struct ceph_metric *metric; + int ret, i; if (!m) return -EINVAL; @@ -243,32 +244,18 @@ int ceph_metric_init(struct ceph_client_metric *m) if (ret) goto err_i_caps_mis; - spin_lock_init(&m->read_metric_lock); - m->read_latency_sq_sum = 0; - m->read_latency_min = KTIME_MAX; - m->read_latency_max = 0; - m->total_reads = 0; - m->read_latency_sum = 0; - m->read_size_min = U64_MAX; - m->read_size_max = 0; - m->read_size_sum = 0; - - spin_lock_init(&m->write_metric_lock); - m->write_latency_sq_sum = 0; - m->write_latency_min = KTIME_MAX; - m->write_latency_max = 0; - m->total_writes = 0; - m->write_latency_sum = 0; - m->write_size_min = U64_MAX; - m->write_size_max = 0; - m->write_size_sum = 0; - - spin_lock_init(&m->metadata_metric_lock); - m->metadata_latency_sq_sum = 0; - m->metadata_latency_min = KTIME_MAX; - m->metadata_latency_max = 0; - m->total_metadatas = 0; - m->metadata_latency_sum = 0; + for (i = 0; i < METRIC_MAX; i++) { + metric = &m->metric[i]; + spin_lock_init(&metric->lock); + metric->size_sum = 0; + metric->size_min = U64_MAX; + metric->size_max = 0; + metric->total = 0; + metric->latency_sum = 0; + metric->latency_sq_sum = 0; + metric->latency_min = KTIME_MAX; + metric->latency_max = 0; + } atomic64_set(&m->opened_files, 0); ret = percpu_counter_init(&m->opened_inodes, 0, GFP_KERNEL); @@ -338,9 +325,9 @@ static inline void __update_stdev(ktime_t total, ktime_t lsum, *sq_sump += sq; } -void ceph_update_read_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc) +void ceph_update_metrics(struct ceph_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) { ktime_t lat = ktime_sub(r_end, r_start); ktime_t total; @@ -348,63 +335,12 @@ void ceph_update_read_metrics(struct ceph_client_metric *m, if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT)) return; - spin_lock(&m->read_metric_lock); - total = ++m->total_reads; - m->read_size_sum += size; - m->read_latency_sum += lat; - METRIC_UPDATE_MIN_MAX(m->read_size_min, - m->read_size_max, - size); - METRIC_UPDATE_MIN_MAX(m->read_latency_min, - m->read_latency_max, - lat); - __update_stdev(total, m->read_latency_sum, - &m->read_latency_sq_sum, lat); - spin_unlock(&m->read_metric_lock); -} - -void ceph_update_write_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc) -{ - ktime_t lat = ktime_sub(r_end, r_start); - ktime_t total; - - if (unlikely(rc && rc != -ETIMEDOUT)) - return; - - spin_lock(&m->write_metric_lock); - total = ++m->total_writes; - m->write_size_sum += size; - m->write_latency_sum += lat; - METRIC_UPDATE_MIN_MAX(m->write_size_min, - m->write_size_max, - size); - METRIC_UPDATE_MIN_MAX(m->write_latency_min, - m->write_latency_max, - lat); - __update_stdev(total, m->write_latency_sum, - &m->write_latency_sq_sum, lat); - spin_unlock(&m->write_metric_lock); -} - -void ceph_update_metadata_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - int rc) -{ - ktime_t lat = ktime_sub(r_end, r_start); - ktime_t total; - - if (unlikely(rc && rc != -ENOENT)) - return; - - spin_lock(&m->metadata_metric_lock); - total = ++m->total_metadatas; - m->metadata_latency_sum += lat; - METRIC_UPDATE_MIN_MAX(m->metadata_latency_min, - m->metadata_latency_max, - lat); - __update_stdev(total, m->metadata_latency_sum, - &m->metadata_latency_sq_sum, lat); - spin_unlock(&m->metadata_metric_lock); + spin_lock(&m->lock); + total = ++m->total; + m->size_sum += size; + METRIC_UPDATE_MIN_MAX(m->size_min, m->size_max, size); + m->latency_sum += lat; + METRIC_UPDATE_MIN_MAX(m->latency_min, m->latency_max, lat); + __update_stdev(total, m->latency_sum, &m->latency_sq_sum, lat); + spin_unlock(&m->lock); } diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h index 0133955a3c6a..bb45608181e7 100644 --- a/fs/ceph/metric.h +++ b/fs/ceph/metric.h @@ -125,6 +125,26 @@ struct ceph_metric_head { __le32 num; /* the number of metrics that will be sent */ } __packed; +enum metric_type { + METRIC_READ, + METRIC_WRITE, + METRIC_METADATA, + METRIC_COPYFROM, + METRIC_MAX +}; + +struct ceph_metric { + spinlock_t lock; + u64 total; + u64 size_sum; + u64 size_min; + u64 size_max; + ktime_t latency_sum; + ktime_t latency_sq_sum; + ktime_t latency_min; + ktime_t latency_max; +}; + /* This is the global metrics */ struct ceph_client_metric { atomic64_t total_dentries; @@ -135,32 +155,7 @@ struct ceph_client_metric { struct percpu_counter i_caps_hit; struct percpu_counter i_caps_mis; - spinlock_t read_metric_lock; - u64 total_reads; - u64 read_size_sum; - u64 read_size_min; - u64 read_size_max; - ktime_t read_latency_sum; - ktime_t read_latency_sq_sum; - ktime_t read_latency_min; - ktime_t read_latency_max; - - spinlock_t write_metric_lock; - u64 total_writes; - u64 write_size_sum; - u64 write_size_min; - u64 write_size_max; - ktime_t write_latency_sum; - ktime_t write_latency_sq_sum; - ktime_t write_latency_min; - ktime_t write_latency_max; - - spinlock_t metadata_metric_lock; - u64 total_metadatas; - ktime_t metadata_latency_sum; - ktime_t metadata_latency_sq_sum; - ktime_t metadata_latency_min; - ktime_t metadata_latency_max; + struct ceph_metric metric[METRIC_MAX]; /* The total number of directories and files that are opened */ atomic64_t opened_files; @@ -195,13 +190,36 @@ static inline void ceph_update_cap_mis(struct ceph_client_metric *m) percpu_counter_inc(&m->i_caps_mis); } -extern void ceph_update_read_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc); -extern void ceph_update_write_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - unsigned int size, int rc); -extern void ceph_update_metadata_metrics(struct ceph_client_metric *m, - ktime_t r_start, ktime_t r_end, - int rc); +extern void ceph_update_metrics(struct ceph_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc); + +static inline void ceph_update_read_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) +{ + ceph_update_metrics(&m->metric[METRIC_READ], + r_start, r_end, size, rc); +} +static inline void ceph_update_write_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) +{ + ceph_update_metrics(&m->metric[METRIC_WRITE], + r_start, r_end, size, rc); +} +static inline void ceph_update_metadata_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + int rc) +{ + ceph_update_metrics(&m->metric[METRIC_METADATA], + r_start, r_end, 0, rc); +} +static inline void ceph_update_copyfrom_metrics(struct ceph_client_metric *m, + ktime_t r_start, ktime_t r_end, + unsigned int size, int rc) +{ + ceph_update_metrics(&m->metric[METRIC_COPYFROM], + r_start, r_end, size, rc); +} #endif /* _FS_CEPH_MDS_METRIC_H */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index fd8742bae847..bab61232dc5a 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -52,8 +52,7 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) struct ceph_fs_client *fsc = ceph_inode_to_client(d_inode(dentry)); struct ceph_mon_client *monc = &fsc->client->monc; struct ceph_statfs st; - u64 fsid; - int err; + int i, err; u64 data_pool; if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) { @@ -99,12 +98,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_namelen = NAME_MAX; /* Must convert the fsid, for consistent values across arches */ + buf->f_fsid.val[0] = 0; mutex_lock(&monc->mutex); - fsid = le64_to_cpu(*(__le64 *)(&monc->monmap->fsid)) ^ - le64_to_cpu(*((__le64 *)&monc->monmap->fsid + 1)); + for (i = 0 ; i < sizeof(monc->monmap->fsid) / sizeof(__le32) ; ++i) + buf->f_fsid.val[0] ^= le32_to_cpu(((__le32 *)&monc->monmap->fsid)[i]); mutex_unlock(&monc->mutex); - buf->f_fsid = u64_to_fsid(fsid); + /* fold the fs_cluster_id into the upper bits */ + buf->f_fsid.val[1] = monc->fs_cluster_id; return 0; } @@ -577,8 +578,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER) seq_show_option(m, "recover_session", "clean"); - if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS) - seq_puts(m, ",nowsync"); + if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS)) + seq_puts(m, ",wsync"); if (fsopt->wsize != CEPH_MAX_WRITE_SIZE) seq_printf(m, ",wsize=%u", fsopt->wsize); @@ -842,7 +843,7 @@ static void __ceph_umount_begin(struct ceph_fs_client *fsc) * ceph_umount_begin - initiate forced umount. Tear down the * mount, skipping steps that may hang while waiting for server(s). */ -static void ceph_umount_begin(struct super_block *sb) +void ceph_umount_begin(struct super_block *sb) { struct ceph_fs_client *fsc = ceph_sb_to_client(sb); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 14f951cd5b61..ac331aa07cfa 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -48,7 +48,8 @@ #define CEPH_MOUNT_OPT_DEFAULT \ (CEPH_MOUNT_OPT_DCACHE | \ - CEPH_MOUNT_OPT_NOCOPYFROM) + CEPH_MOUNT_OPT_NOCOPYFROM | \ + CEPH_MOUNT_OPT_ASYNC_DIROPS) #define ceph_set_mount_opt(fsc, opt) \ (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt @@ -128,9 +129,9 @@ struct ceph_fs_client { struct dentry *debugfs_congestion_kb; struct dentry *debugfs_bdi; struct dentry *debugfs_mdsc, *debugfs_mdsmap; - struct dentry *debugfs_metric; struct dentry *debugfs_status; struct dentry *debugfs_mds_sessions; + struct dentry *debugfs_metrics_dir; #endif #ifdef CONFIG_CEPH_FSCACHE @@ -580,6 +581,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */ #define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ #define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) +#define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */ /* * Masks of ceph inode work. @@ -939,6 +941,7 @@ extern void ceph_put_snapid_map(struct ceph_mds_client* mdsc, struct ceph_snapid_map *sm); extern void ceph_trim_snapid_map(struct ceph_mds_client *mdsc); extern void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc); +void ceph_umount_begin(struct super_block *sb); /* @@ -1027,6 +1030,16 @@ extern int ceph_setattr(struct user_namespace *mnt_userns, extern int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); +void ceph_inode_shutdown(struct inode *inode); + +static inline bool ceph_inode_is_shutdown(struct inode *inode) +{ + unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + int state = READ_ONCE(fsc->mount_state); + + return (flags & CEPH_I_SHUTDOWN) || state >= CEPH_MOUNT_SHUTDOWN; +} /* xattr.c */ int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int); @@ -1198,6 +1211,7 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma); extern int ceph_uninline_data(struct file *filp, struct page *locked_page); extern int ceph_pool_perm_check(struct inode *inode, int need); extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc); +int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate); /* file.c */ extern const struct file_operations ceph_file_fops; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index de2c12bcfa4b..d282caf9f037 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -271,7 +271,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) c = 0; spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - if (server->is_channel) + /* channel info will be printed as a part of sessions below */ + if (CIFS_SERVER_IS_CHAN(server)) continue; c++; @@ -358,6 +359,8 @@ skip_rdma: seq_printf(m, " signed"); if (server->posix_ext_supported) seq_printf(m, " posix"); + if (server->nosharesock) + seq_printf(m, " nosharesock"); if (server->rdma) seq_printf(m, "\nRDMA "); @@ -412,12 +415,14 @@ skip_rdma: from_kuid(&init_user_ns, ses->linux_uid), from_kuid(&init_user_ns, ses->cred_uid)); + spin_lock(&ses->chan_lock); if (ses->chan_count > 1) { seq_printf(m, "\n\n\tExtra Channels: %zu ", ses->chan_count-1); for (j = 1; j < ses->chan_count; j++) cifs_dump_channel(m, j, &ses->chans[j]); } + spin_unlock(&ses->chan_lock); seq_puts(m, "\n\n\tShares: "); j = 0; diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 007427ba75e5..b0864da9ef43 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -307,12 +307,8 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt, static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) { struct cifs_sb_info *cifs_sb; - struct cifs_ses *ses; - struct cifs_tcon *tcon; void *page; - char *full_path, *root_path; - unsigned int xid; - int rc; + char *full_path; struct vfsmount *mnt; cifs_dbg(FYI, "in %s\n", __func__); @@ -324,8 +320,6 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) * the double backslashes usually used in the UNC. This function * gives us the latter, so we must adjust the result. */ - mnt = ERR_PTR(-ENOMEM); - cifs_sb = CIFS_SB(mntpt->d_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) { mnt = ERR_PTR(-EREMOTE); @@ -341,60 +335,11 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) } convert_delimiter(full_path, '\\'); - cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); - if (!cifs_sb_master_tlink(cifs_sb)) { - cifs_dbg(FYI, "%s: master tlink is NULL\n", __func__); - goto free_full_path; - } - - tcon = cifs_sb_master_tcon(cifs_sb); - if (!tcon) { - cifs_dbg(FYI, "%s: master tcon is NULL\n", __func__); - goto free_full_path; - } - - root_path = kstrdup(tcon->treeName, GFP_KERNEL); - if (!root_path) { - mnt = ERR_PTR(-ENOMEM); - goto free_full_path; - } - cifs_dbg(FYI, "%s: root path: %s\n", __func__, root_path); - - ses = tcon->ses; - xid = get_xid(); - - /* - * If DFS root has been expired, then unconditionally fetch it again to - * refresh DFS referral cache. - */ - rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), - root_path + 1, NULL, NULL); - if (!rc) { - rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, - cifs_remap(cifs_sb), full_path + 1, - NULL, NULL); - } - - free_xid(xid); - - if (rc) { - mnt = ERR_PTR(rc); - goto free_root_path; - } - /* - * OK - we were able to get and cache a referral for @full_path. - * - * Now, pass it down to cifs_mount() and it will retry every available - * node server in case of failures - no need to do it here. - */ mnt = cifs_dfs_do_mount(mntpt, cifs_sb, full_path); - cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__, - full_path + 1, mnt); + cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__, full_path + 1, mnt); -free_root_path: - kfree(root_path); free_full_path: free_dentry_path(page); cdda_exit: diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index f97407520ea1..013a4bd65280 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -61,11 +61,6 @@ struct cifs_sb_info { /* only used when CIFS_MOUNT_USE_PREFIX_PATH is set */ char *prepath; - /* - * Canonical DFS path initially provided by the mount call. We might connect to something - * different via DFS but we want to keep it to do failover properly. - */ - char *origin_fullpath; /* \\HOST\SHARE\[OPTIONAL PATH] */ /* randomly generated 128-bit number for indexing dfs mount groups in referral cache */ uuid_t dfs_mount_id; /* diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index abff31dcd005..be74606724c7 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/mempool.h> #include <linux/workqueue.h> +#include <linux/utsname.h> #include "cifs_fs_sb.h" #include "cifsacl.h" #include <crypto/internal/hash.h> @@ -75,7 +76,8 @@ #define SMB_ECHO_INTERVAL_MAX 600 #define SMB_ECHO_INTERVAL_DEFAULT 60 -/* dns resolution interval in seconds */ +/* dns resolution intervals in seconds */ +#define SMB_DNS_RESOLVE_INTERVAL_MIN 120 #define SMB_DNS_RESOLVE_INTERVAL_DEFAULT 600 /* maximum number of PDUs in one compound */ @@ -99,6 +101,8 @@ #define XATTR_DOS_ATTRIB "user.DOSATTRIB" #endif +#define CIFS_MAX_WORKSTATION_LEN (__NEW_UTS_LEN + 1) /* reasonable max for client */ + /* * CIFS vfs client Status information (based on what we know.) */ @@ -592,6 +596,7 @@ struct TCP_Server_Info { struct list_head pending_mid_q; bool noblocksnd; /* use blocking sendmsg */ bool noautotune; /* do not autotune send buf sizes */ + bool nosharesock; bool tcp_nodelay; unsigned int credits; /* send no more requests at once */ unsigned int max_credits; /* can override large 32000 default at mnt */ @@ -685,13 +690,34 @@ struct TCP_Server_Info { */ int nr_targets; bool noblockcnt; /* use non-blocking connect() */ - bool is_channel; /* if a session channel */ + + /* + * If this is a session channel, + * primary_server holds the ref-counted + * pointer to primary channel connection for the session. + */ +#define CIFS_SERVER_IS_CHAN(server) (!!(server)->primary_server) + struct TCP_Server_Info *primary_server; + #ifdef CONFIG_CIFS_SWN_UPCALL bool use_swn_dstaddr; struct sockaddr_storage swn_dstaddr; #endif #ifdef CONFIG_CIFS_DFS_UPCALL bool is_dfs_conn; /* if a dfs connection */ + struct mutex refpath_lock; /* protects leaf_fullpath */ + /* + * Canonical DFS full paths that were used to chase referrals in mount and reconnect. + * + * origin_fullpath: first or original referral path + * leaf_fullpath: last referral path (might be changed due to nested links in reconnect) + * + * current_fullpath: pointer to either origin_fullpath or leaf_fullpath + * NOTE: cannot be accessed outside cifs_reconnect() and smb2_reconnect() + * + * format: \\HOST\SHARE\[OPTIONAL PATH] + */ + char *origin_fullpath, *leaf_fullpath, *current_fullpath; #endif }; @@ -908,6 +934,7 @@ struct cifs_ses { and after mount option parsing we fill it */ char *domainName; char *password; + char *workstation_name; struct session_key auth_key; struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */ enum securityEnum sectype; /* what security flavor was specified? */ @@ -933,16 +960,21 @@ struct cifs_ses { * iface_lock should be taken when accessing any of these fields */ spinlock_t iface_lock; + /* ========= begin: protected by iface_lock ======== */ struct cifs_server_iface *iface_list; size_t iface_count; unsigned long iface_last_update; /* jiffies */ + /* ========= end: protected by iface_lock ======== */ + spinlock_t chan_lock; + /* ========= begin: protected by chan_lock ======== */ #define CIFS_MAX_CHANNELS 16 struct cifs_chan chans[CIFS_MAX_CHANNELS]; struct cifs_chan *binding_chan; size_t chan_count; size_t chan_max; atomic_t chan_seq; /* round robin state */ + /* ========= end: protected by chan_lock ======== */ }; /* @@ -1091,7 +1123,6 @@ struct cifs_tcon { struct cached_fid crfid; /* Cached root fid */ /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - char *dfs_path; /* canonical DFS path */ struct list_head ulist; /* cache update list */ #endif }; @@ -1942,4 +1973,14 @@ static inline bool is_tcon_dfs(struct cifs_tcon *tcon) tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT); } +static inline bool cifs_is_referral_server(struct cifs_tcon *tcon, + const struct dfs_info3_param *ref) +{ + /* + * Check if all targets are capable of handling DFS referrals as per + * MS-DFSC 2.2.4 RESP_GET_DFS_REFERRAL. + */ + return is_tcon_dfs(tcon) || (ref && (ref->flags & DFSREF_REFERRAL_SERVER)); +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index d0f85b666662..f3073a62ce57 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -269,8 +269,9 @@ extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon); extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon, const char *path); - -extern struct TCP_Server_Info *cifs_get_tcp_session(struct smb3_fs_context *ctx); +extern struct TCP_Server_Info * +cifs_get_tcp_session(struct smb3_fs_context *ctx, + struct TCP_Server_Info *primary_server); extern void cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect); extern void cifs_put_tcon(struct cifs_tcon *tcon); @@ -607,7 +608,7 @@ int smb2_parse_query_directory(struct cifs_tcon *tcon, struct kvec *rsp_iov, struct super_block *cifs_get_tcp_super(struct TCP_Server_Info *server); void cifs_put_tcp_super(struct super_block *sb); -int update_super_prepath(struct cifs_tcon *tcon, char *prefix); +int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix); char *extract_hostname(const char *unc); char *extract_sharename(const char *unc); @@ -634,4 +635,7 @@ static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options) return options; } +struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon); +void cifs_put_tcon_super(struct super_block *sb); + #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0abbff4e4135..82577a7a5bb1 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -61,6 +61,20 @@ extern bool disable_legacy_dialects; /* Drop the connection to not overload the server */ #define NUM_STATUS_IO_TIMEOUT 5 +struct mount_ctx { + struct cifs_sb_info *cifs_sb; + struct smb3_fs_context *fs_ctx; + unsigned int xid; + struct TCP_Server_Info *server; + struct cifs_ses *ses; + struct cifs_tcon *tcon; +#ifdef CONFIG_CIFS_DFS_UPCALL + struct cifs_ses *root_ses; + uuid_t mount_id; + char *origin_fullpath, *leaf_fullpath; +#endif +}; + static int ip_connect(struct TCP_Server_Info *server); static int generic_ip_connect(struct TCP_Server_Info *server); static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); @@ -115,7 +129,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) * To make sure we don't use the cached entry, retry 1s * after expiry. */ - ttl = (expiry - now + 1); + ttl = max_t(unsigned long, expiry - now, SMB_DNS_RESOLVE_INTERVAL_MIN) + 1; } rc = !rc ? -1 : 0; @@ -148,139 +162,38 @@ static void cifs_resolve_server(struct work_struct *work) mutex_unlock(&server->srv_mutex); } -#ifdef CONFIG_CIFS_DFS_UPCALL -/* These functions must be called with server->srv_mutex held */ -static void reconn_set_next_dfs_target(struct TCP_Server_Info *server, - struct cifs_sb_info *cifs_sb, - struct dfs_cache_tgt_list *tgt_list, - struct dfs_cache_tgt_iterator **tgt_it) -{ - const char *name; - int rc; - - if (!cifs_sb || !cifs_sb->origin_fullpath) - return; - - if (!*tgt_it) { - *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); - } else { - *tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it); - if (!*tgt_it) - *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); - } - - cifs_dbg(FYI, "%s: UNC: %s\n", __func__, cifs_sb->origin_fullpath); - - name = dfs_cache_get_tgt_name(*tgt_it); - - kfree(server->hostname); - - server->hostname = extract_hostname(name); - if (IS_ERR(server->hostname)) { - cifs_dbg(FYI, - "%s: failed to extract hostname from target: %ld\n", - __func__, PTR_ERR(server->hostname)); - return; - } - - rc = reconn_set_ipaddr_from_hostname(server); - if (rc) { - cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", - __func__, rc); - } -} - -static inline int reconn_setup_dfs_targets(struct cifs_sb_info *cifs_sb, - struct dfs_cache_tgt_list *tl) -{ - if (!cifs_sb->origin_fullpath) - return -EOPNOTSUPP; - return dfs_cache_noreq_find(cifs_sb->origin_fullpath + 1, NULL, tl); -} -#endif - -/* - * cifs tcp session reconnection +/** + * Mark all sessions and tcons for reconnect. * - * mark tcp session as reconnecting so temporarily locked - * mark all smb sessions as reconnecting for tcp session - * reconnect tcp session - * wake up waiters on reconnection? - (not needed currently) + * @server needs to be previously set to CifsNeedReconnect. */ -int -cifs_reconnect(struct TCP_Server_Info *server) +static void cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server) { - int rc = 0; - struct list_head *tmp, *tmp2; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct mid_q_entry *mid_entry; + struct mid_q_entry *mid, *nmid; struct list_head retry_list; -#ifdef CONFIG_CIFS_DFS_UPCALL - struct super_block *sb = NULL; - struct cifs_sb_info *cifs_sb = NULL; - struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list); - struct dfs_cache_tgt_iterator *tgt_it = NULL; -#endif + struct TCP_Server_Info *pserver; - spin_lock(&GlobalMid_Lock); - server->nr_targets = 1; -#ifdef CONFIG_CIFS_DFS_UPCALL - spin_unlock(&GlobalMid_Lock); - sb = cifs_get_tcp_super(server); - if (IS_ERR(sb)) { - rc = PTR_ERR(sb); - cifs_dbg(FYI, "%s: will not do DFS failover: rc = %d\n", - __func__, rc); - sb = NULL; - } else { - cifs_sb = CIFS_SB(sb); - rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list); - if (rc) { - cifs_sb = NULL; - if (rc != -EOPNOTSUPP) { - cifs_server_dbg(VFS, "%s: no target servers for DFS failover\n", - __func__); - } - } else { - server->nr_targets = dfs_cache_get_nr_tgts(&tgt_list); - } - } - cifs_dbg(FYI, "%s: will retry %d target(s)\n", __func__, - server->nr_targets); - spin_lock(&GlobalMid_Lock); -#endif - if (server->tcpStatus == CifsExiting) { - /* the demux thread will exit normally - next time through the loop */ - spin_unlock(&GlobalMid_Lock); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_cache_free_tgts(&tgt_list); - cifs_put_tcp_super(sb); -#endif - wake_up(&server->response_q); - return rc; - } else - server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); server->maxBuf = 0; server->max_read = 0; cifs_dbg(FYI, "Mark tcp session as need reconnect\n"); trace_smb3_reconnect(server->CurrentMid, server->conn_id, server->hostname); + /* + * before reconnecting the tcp session, mark the smb session (uid) and the tid bad so they + * are not used until reconnected. + */ + cifs_dbg(FYI, "%s: marking sessions and tcons for reconnect\n", __func__); + + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; - /* before reconnecting the tcp session, mark the smb session (uid) - and the tid bad so they are not used until reconnected */ - cifs_dbg(FYI, "%s: marking sessions and tcons for reconnect\n", - __func__); spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { ses->need_reconnect = true; - list_for_each(tmp2, &ses->tcon_list) { - tcon = list_entry(tmp2, struct cifs_tcon, tcon_list); + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) tcon->need_reconnect = true; - } if (ses->tcon_ipc) ses->tcon_ipc->need_reconnect = true; } @@ -290,11 +203,11 @@ cifs_reconnect(struct TCP_Server_Info *server) cifs_dbg(FYI, "%s: tearing down socket\n", __func__); mutex_lock(&server->srv_mutex); if (server->ssocket) { - cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", - server->ssocket->state, server->ssocket->flags); + cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", server->ssocket->state, + server->ssocket->flags); kernel_sock_shutdown(server->ssocket, SHUT_WR); - cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n", - server->ssocket->state, server->ssocket->flags); + cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n", server->ssocket->state, + server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; } @@ -309,23 +222,21 @@ cifs_reconnect(struct TCP_Server_Info *server) INIT_LIST_HEAD(&retry_list); cifs_dbg(FYI, "%s: moving mids to private list\n", __func__); spin_lock(&GlobalMid_Lock); - list_for_each_safe(tmp, tmp2, &server->pending_mid_q) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - kref_get(&mid_entry->refcount); - if (mid_entry->mid_state == MID_REQUEST_SUBMITTED) - mid_entry->mid_state = MID_RETRY_NEEDED; - list_move(&mid_entry->qhead, &retry_list); - mid_entry->mid_flags |= MID_DELETED; + list_for_each_entry_safe(mid, nmid, &server->pending_mid_q, qhead) { + kref_get(&mid->refcount); + if (mid->mid_state == MID_REQUEST_SUBMITTED) + mid->mid_state = MID_RETRY_NEEDED; + list_move(&mid->qhead, &retry_list); + mid->mid_flags |= MID_DELETED; } spin_unlock(&GlobalMid_Lock); mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); - list_for_each_safe(tmp, tmp2, &retry_list) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - list_del_init(&mid_entry->qhead); - mid_entry->callback(mid_entry); - cifs_mid_q_entry_release(mid_entry); + list_for_each_entry_safe(mid, nmid, &retry_list, qhead) { + list_del_init(&mid->qhead); + mid->callback(mid); + cifs_mid_q_entry_release(mid); } if (cifs_rdma_enabled(server)) { @@ -333,38 +244,48 @@ cifs_reconnect(struct TCP_Server_Info *server) smbd_destroy(server); mutex_unlock(&server->srv_mutex); } +} + +static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num_targets) +{ + spin_lock(&GlobalMid_Lock); + server->nr_targets = num_targets; + if (server->tcpStatus == CifsExiting) { + /* the demux thread will exit normally next time through the loop */ + spin_unlock(&GlobalMid_Lock); + wake_up(&server->response_q); + return false; + } + server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + return true; +} + +/* + * cifs tcp session reconnection + * + * mark tcp session as reconnecting so temporarily locked + * mark all smb sessions as reconnecting for tcp session + * reconnect tcp session + * wake up waiters on reconnection? - (not needed currently) + */ +static int __cifs_reconnect(struct TCP_Server_Info *server) +{ + int rc = 0; + + if (!cifs_tcp_ses_needs_reconnect(server, 1)) + return 0; + + cifs_mark_tcp_ses_conns_for_reconnect(server); do { try_to_freeze(); - mutex_lock(&server->srv_mutex); - if (!cifs_swn_set_server_dstaddr(server)) { -#ifdef CONFIG_CIFS_DFS_UPCALL - if (cifs_sb && cifs_sb->origin_fullpath) - /* - * Set up next DFS target server (if any) for reconnect. If DFS - * feature is disabled, then we will retry last server we - * connected to before. - */ - reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it); - else { -#endif - /* - * Resolve the hostname again to make sure that IP address is up-to-date. - */ + /* resolve the hostname again to make sure that IP address is up-to-date */ rc = reconn_set_ipaddr_from_hostname(server); - if (rc) { - cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", - __func__, rc); - } - -#ifdef CONFIG_CIFS_DFS_UPCALL - } -#endif - - + cifs_dbg(FYI, "%s: reconn_set_ipaddr_from_hostname: rc=%d\n", __func__, rc); } if (cifs_rdma_enabled(server)) @@ -372,8 +293,8 @@ cifs_reconnect(struct TCP_Server_Info *server) else rc = generic_ip_connect(server); if (rc) { - cifs_dbg(FYI, "reconnect error %d\n", rc); mutex_unlock(&server->srv_mutex); + cifs_dbg(FYI, "%s: reconnect error %d\n", __func__, rc); msleep(3000); } else { atomic_inc(&tcpSesReconnectCount); @@ -387,19 +308,128 @@ cifs_reconnect(struct TCP_Server_Info *server) } } while (server->tcpStatus == CifsNeedReconnect); + if (server->tcpStatus == CifsNeedNegotiate) + mod_delayed_work(cifsiod_wq, &server->echo, 0); + + wake_up(&server->response_q); + return rc; +} + #ifdef CONFIG_CIFS_DFS_UPCALL - if (tgt_it) { - rc = dfs_cache_noreq_update_tgthint(cifs_sb->origin_fullpath + 1, - tgt_it); - if (rc) { - cifs_server_dbg(VFS, "%s: failed to update DFS target hint: rc = %d\n", - __func__, rc); +static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const char *target) +{ + int rc; + char *hostname; + + if (!cifs_swn_set_server_dstaddr(server)) { + if (server->hostname != target) { + hostname = extract_hostname(target); + if (!IS_ERR(hostname)) { + kfree(server->hostname); + server->hostname = hostname; + } else { + cifs_dbg(FYI, "%s: couldn't extract hostname or address from dfs target: %ld\n", + __func__, PTR_ERR(hostname)); + cifs_dbg(FYI, "%s: default to last target server: %s\n", __func__, + server->hostname); + } } - dfs_cache_free_tgts(&tgt_list); + /* resolve the hostname again to make sure that IP address is up-to-date. */ + rc = reconn_set_ipaddr_from_hostname(server); + cifs_dbg(FYI, "%s: reconn_set_ipaddr_from_hostname: rc=%d\n", __func__, rc); } + /* Reconnect the socket */ + if (cifs_rdma_enabled(server)) + rc = smbd_reconnect(server); + else + rc = generic_ip_connect(server); - cifs_put_tcp_super(sb); -#endif + 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) +{ + int rc; + struct dfs_cache_tgt_iterator *tit; + + *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); + + /* 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)); + if (!rc) { + *target_hint = tit; + break; + } + } + return rc; +} + +static int reconnect_dfs_server(struct TCP_Server_Info *server) +{ + int rc = 0; + const char *refpath = server->current_fullpath + 1; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + struct dfs_cache_tgt_iterator *target_hint = NULL; + int num_targets = 0; + + /* + * Determine the number of dfs targets the referral path in @cifs_sb resolves to. + * + * smb2_reconnect() needs to know how long it should wait based upon the number of dfs + * targets (server->nr_targets). It's also possible that the cached referral was cleared + * 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. + */ + if (!dfs_cache_noreq_find(refpath, NULL, &tl)) + num_targets = dfs_cache_get_nr_tgts(&tl); + if (!num_targets) + num_targets = 1; + + if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) + return 0; + + cifs_mark_tcp_ses_conns_for_reconnect(server); + + do { + try_to_freeze(); + mutex_lock(&server->srv_mutex); + + rc = reconnect_target_unlocked(server, &tl, &target_hint); + if (rc) { + /* Failed to reconnect socket */ + mutex_unlock(&server->srv_mutex); + cifs_dbg(FYI, "%s: reconnect error %d\n", __func__, rc); + msleep(3000); + continue; + } + /* + * Socket was created. Update tcp session status to CifsNeedNegotiate so that a + * process waiting for reconnect will know it needs to re-establish session and tcon + * through the reconnected target server. + */ + atomic_inc(&tcpSesReconnectCount); + set_credits(server, 1); + spin_lock(&GlobalMid_Lock); + if (server->tcpStatus != CifsExiting) + server->tcpStatus = CifsNeedNegotiate; + spin_unlock(&GlobalMid_Lock); + cifs_swn_reset_server_dstaddr(server); + mutex_unlock(&server->srv_mutex); + } while (server->tcpStatus == CifsNeedReconnect); + + if (target_hint) + dfs_cache_noreq_update_tgthint(refpath, target_hint); + + dfs_cache_free_tgts(&tl); + + /* Need to set up echo worker again once connection has been established */ if (server->tcpStatus == CifsNeedNegotiate) mod_delayed_work(cifsiod_wq, &server->echo, 0); @@ -407,6 +437,25 @@ cifs_reconnect(struct TCP_Server_Info *server) return rc; } +int cifs_reconnect(struct TCP_Server_Info *server) +{ + /* If tcp session is not an dfs connection, then reconnect to last target server */ + spin_lock(&cifs_tcp_ses_lock); + if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) { + spin_unlock(&cifs_tcp_ses_lock); + return __cifs_reconnect(server); + } + spin_unlock(&cifs_tcp_ses_lock); + + return reconnect_dfs_server(server); +} +#else +int cifs_reconnect(struct TCP_Server_Info *server) +{ + return __cifs_reconnect(server); +} +#endif + static void cifs_echo_request(struct work_struct *work) { @@ -665,13 +714,14 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) * Trying to handle/dequeue a mid after the send_recv() * function has finished processing it is a bug. */ - if (mid->mid_flags & MID_DELETED) + if (mid->mid_flags & MID_DELETED) { + spin_unlock(&GlobalMid_Lock); pr_warn_once("trying to dequeue a deleted mid\n"); - else { + } else { list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; + spin_unlock(&GlobalMid_Lock); } - spin_unlock(&GlobalMid_Lock); } static unsigned int @@ -794,6 +844,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) */ } +#ifdef CONFIG_CIFS_DFS_UPCALL + kfree(server->origin_fullpath); + kfree(server->leaf_fullpath); +#endif kfree(server); length = atomic_dec_return(&tcpSesAllocCount); @@ -1217,7 +1271,13 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context * { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; - if (ctx->nosharesock) + if (ctx->nosharesock) { + server->nosharesock = true; + return 0; + } + + /* this server does not share socket */ + if (server->nosharesock) return 0; /* If multidialect negotiation see if existing sessions match one */ @@ -1283,7 +1343,7 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx) * Skip ses channels since they're only handled in lower layers * (e.g. cifs_send_recv). */ - if (server->is_channel || !match_server(server, ctx)) + if (CIFS_SERVER_IS_CHAN(server) || !match_server(server, ctx)) continue; ++server->srv_count; @@ -1314,6 +1374,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) list_del_init(&server->tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); + /* For secondary channels, we pick up ref-count on the primary server */ + if (CIFS_SERVER_IS_CHAN(server)) + cifs_put_tcp_session(server->primary_server, from_reconnect); + cancel_delayed_work_sync(&server->echo); cancel_delayed_work_sync(&server->resolve); @@ -1333,7 +1397,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) spin_unlock(&GlobalMid_Lock); cifs_crypto_secmech_release(server); - cifs_fscache_release_client_cookie(server); + + /* fscache server cookies are based on primary channel only */ + if (!CIFS_SERVER_IS_CHAN(server)) + cifs_fscache_release_client_cookie(server); kfree(server->session_key.response); server->session_key.response = NULL; @@ -1346,7 +1413,8 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) } struct TCP_Server_Info * -cifs_get_tcp_session(struct smb3_fs_context *ctx) +cifs_get_tcp_session(struct smb3_fs_context *ctx, + struct TCP_Server_Info *primary_server) { struct TCP_Server_Info *tcp_ses = NULL; int rc; @@ -1383,6 +1451,10 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx) tcp_ses->in_flight = 0; tcp_ses->max_in_flight = 0; tcp_ses->credits = 1; + if (primary_server) { + ++primary_server->srv_count; + tcp_ses->primary_server = primary_server; + } init_waitqueue_head(&tcp_ses->response_q); init_waitqueue_head(&tcp_ses->request_q); INIT_LIST_HEAD(&tcp_ses->pending_mid_q); @@ -1403,6 +1475,9 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx) INIT_DELAYED_WORK(&tcp_ses->resolve, cifs_resolve_server); 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, @@ -1481,7 +1556,9 @@ smbd_connected: list_add(&tcp_ses->tcp_ses_list, &cifs_tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); - cifs_fscache_get_client_cookie(tcp_ses); + /* fscache server cookies are based on primary channel only */ + if (!CIFS_SERVER_IS_CHAN(tcp_ses)) + cifs_fscache_get_client_cookie(tcp_ses); /* queue echo request delayed work */ queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval); @@ -1501,6 +1578,8 @@ out_err_crypto_release: out_err: if (tcp_ses) { + if (CIFS_SERVER_IS_CHAN(tcp_ses)) + cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); if (tcp_ses->ssocket) sock_release(tcp_ses->ssocket); @@ -1519,8 +1598,12 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) * If an existing session is limited to less channels than * requested, it should not be reused */ - if (ses->chan_max < ctx->max_channels) + spin_lock(&ses->chan_lock); + if (ses->chan_max < ctx->max_channels) { + spin_unlock(&ses->chan_lock); return 0; + } + spin_unlock(&ses->chan_lock); switch (ses->sectype) { case Kerberos: @@ -1655,6 +1738,7 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) void cifs_put_smb_ses(struct cifs_ses *ses) { unsigned int rc, xid; + unsigned int chan_count; struct TCP_Server_Info *server = ses->server; cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); @@ -1696,12 +1780,24 @@ void cifs_put_smb_ses(struct cifs_ses *ses) list_del_init(&ses->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); + spin_lock(&ses->chan_lock); + chan_count = ses->chan_count; + spin_unlock(&ses->chan_lock); + /* close any extra channels */ - if (ses->chan_count > 1) { + if (chan_count > 1) { int i; - for (i = 1; i < ses->chan_count; i++) + for (i = 1; i < chan_count; i++) { + /* + * note: for now, we're okay accessing ses->chans + * without chan_lock. But when chans can go away, we'll + * need to introduce ref counting to make sure that chan + * is not freed from under us. + */ cifs_put_tcp_session(ses->chans[i].server, 0); + ses->chans[i].server = NULL; + } } sesInfoFree(ses); @@ -1885,16 +1981,18 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) ses->status); mutex_lock(&ses->session_mutex); - rc = cifs_negotiate_protocol(xid, ses); - if (rc) { - mutex_unlock(&ses->session_mutex); - /* problem -- put our ses reference */ - cifs_put_smb_ses(ses); - free_xid(xid); - return ERR_PTR(rc); - } if (ses->need_reconnect) { cifs_dbg(FYI, "Session needs reconnect\n"); + + rc = cifs_negotiate_protocol(xid, ses); + if (rc) { + mutex_unlock(&ses->session_mutex); + /* problem -- put our ses reference */ + cifs_put_smb_ses(ses); + free_xid(xid); + return ERR_PTR(rc); + } + rc = cifs_setup_session(xid, ses, ctx->local_nls); if (rc) { @@ -1942,6 +2040,12 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) if (!ses->domainName) goto get_ses_fail; } + if (ctx->workstation_name) { + ses->workstation_name = kstrdup(ctx->workstation_name, + GFP_KERNEL); + if (!ses->workstation_name) + goto get_ses_fail; + } if (ctx->domainauto) ses->domainAuto = ctx->domainauto; ses->cred_uid = ctx->cred_uid; @@ -1952,9 +2056,11 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) mutex_lock(&ses->session_mutex); /* add server as first channel */ + spin_lock(&ses->chan_lock); ses->chans[0].server = server; ses->chan_count = 1; ses->chan_max = ctx->multichannel ? ctx->max_channels:1; + spin_unlock(&ses->chan_lock); rc = cifs_negotiate_protocol(xid, ses); if (!rc) @@ -2286,8 +2392,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) list_add(&tcon->tcon_list, &ses->tcon_list); spin_unlock(&cifs_tcp_ses_lock); - cifs_fscache_get_super_cookie(tcon); - return tcon; out_fail: @@ -2849,73 +2953,64 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) } /* Release all succeed connections */ -static inline void mount_put_conns(struct cifs_sb_info *cifs_sb, - unsigned int xid, - struct TCP_Server_Info *server, - struct cifs_ses *ses, struct cifs_tcon *tcon) +static inline void mount_put_conns(struct mount_ctx *mnt_ctx) { int rc = 0; - if (tcon) - cifs_put_tcon(tcon); - else if (ses) - cifs_put_smb_ses(ses); - else if (server) - cifs_put_tcp_session(server, 0); - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; - free_xid(xid); + if (mnt_ctx->tcon) + cifs_put_tcon(mnt_ctx->tcon); + else if (mnt_ctx->ses) + cifs_put_smb_ses(mnt_ctx->ses); + else if (mnt_ctx->server) + cifs_put_tcp_session(mnt_ctx->server, 0); + mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; + free_xid(mnt_ctx->xid); } /* Get connections for tcp, ses and tcon */ -static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, - unsigned int *xid, - struct TCP_Server_Info **nserver, - struct cifs_ses **nses, struct cifs_tcon **ntcon) +static int mount_get_conns(struct mount_ctx *mnt_ctx) { int rc = 0; - struct TCP_Server_Info *server; - struct cifs_ses *ses; - struct cifs_tcon *tcon; - - *nserver = NULL; - *nses = NULL; - *ntcon = NULL; + struct TCP_Server_Info *server = NULL; + struct cifs_ses *ses = NULL; + struct cifs_tcon *tcon = NULL; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + unsigned int xid; - *xid = get_xid(); + xid = get_xid(); /* get a reference to a tcp session */ - server = cifs_get_tcp_session(ctx); + server = cifs_get_tcp_session(ctx, NULL); if (IS_ERR(server)) { rc = PTR_ERR(server); - return rc; + server = NULL; + goto out; } - *nserver = server; - /* get a reference to a SMB session */ ses = cifs_get_smb_ses(server, ctx); if (IS_ERR(ses)) { rc = PTR_ERR(ses); - return rc; + ses = NULL; + goto out; } - *nses = ses; - if ((ctx->persistent == true) && (!(ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES))) { cifs_server_dbg(VFS, "persistent handles not supported by server\n"); - return -EOPNOTSUPP; + rc = -EOPNOTSUPP; + goto out; } /* search for existing tcon to this server share */ tcon = cifs_get_tcon(ses, ctx); if (IS_ERR(tcon)) { rc = PTR_ERR(tcon); - return rc; + tcon = NULL; + goto out; } - *ntcon = tcon; - /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */ if (tcon->posix_extensions) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; @@ -2926,17 +3021,19 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif * reset of caps checks mount to see if unix extensions disabled * for just this mount. */ - reset_cifs_unix_caps(*xid, tcon, cifs_sb, ctx); + reset_cifs_unix_caps(xid, tcon, cifs_sb, ctx); if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && (le64_to_cpu(tcon->fsUnixInfo.Capability) & - CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) - return -EACCES; + CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) { + rc = -EACCES; + goto out; + } } else tcon->unix_ext = 0; /* server does not support them */ /* do not care if a following call succeed - informational */ if (!tcon->pipe && server->ops->qfs_tcon) { - server->ops->qfs_tcon(*xid, tcon, cifs_sb); + server->ops->qfs_tcon(xid, tcon, cifs_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) { if (tcon->fsDevInfo.DeviceCharacteristics & cpu_to_le32(FILE_READ_ONLY_DEVICE)) @@ -2946,6 +3043,12 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif cifs_dbg(VFS, "read only mount of RW share\n"); /* no need to log a RW mount of a typical RW share */ } + /* + * The cookie is initialized from volume info returned above. + * Inside cifs_fscache_get_super_cookie it checks + * that we do not get super cookie twice. + */ + cifs_fscache_get_super_cookie(tcon); } /* @@ -2960,7 +3063,13 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx))) cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx); - return 0; +out: + mnt_ctx->server = server; + mnt_ctx->ses = ses; + mnt_ctx->tcon = tcon; + mnt_ctx->xid = xid; + + return rc; } static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, @@ -2990,18 +3099,17 @@ static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, } #ifdef CONFIG_CIFS_DFS_UPCALL -static int mount_get_dfs_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, - unsigned int *xid, struct TCP_Server_Info **nserver, - struct cifs_ses **nses, struct cifs_tcon **ntcon) +/* Get unique dfs connections */ +static int mount_get_dfs_conns(struct mount_ctx *mnt_ctx) { int rc; - ctx->nosharesock = true; - rc = mount_get_conns(ctx, cifs_sb, xid, nserver, nses, ntcon); - if (*nserver) { + mnt_ctx->fs_ctx->nosharesock = true; + rc = mount_get_conns(mnt_ctx); + if (mnt_ctx->server) { cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__); spin_lock(&cifs_tcp_ses_lock); - (*nserver)->is_dfs_conn = true; + mnt_ctx->server->is_dfs_conn = true; spin_unlock(&cifs_tcp_ses_lock); } return rc; @@ -3043,190 +3151,38 @@ build_unc_path_to_root(const struct smb3_fs_context *ctx, } /* - * expand_dfs_referral - Perform a dfs referral query and update the cifs_sb + * expand_dfs_referral - Update cifs_sb from dfs referral path * - * If a referral is found, cifs_sb->ctx->mount_options will be (re-)allocated - * to a string containing updated options for the submount. Otherwise it - * will be left untouched. - * - * Returns the rc from get_dfs_path to the caller, which can be used to - * determine whether there were referrals. + * cifs_sb->ctx->mount_options will be (re-)allocated to a string containing updated options for the + * submount. Otherwise it will be left untouched. */ -static int -expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, - struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb, - char *ref_path) -{ - int rc; - struct dfs_info3_param referral = {0}; - char *full_path = NULL, *mdata = NULL; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) - return -EREMOTE; - - full_path = build_unc_path_to_root(ctx, cifs_sb, true); - if (IS_ERR(full_path)) - return PTR_ERR(full_path); - - rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), - ref_path, &referral, NULL); - if (!rc) { - char *fake_devname = NULL; - - mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, - full_path + 1, &referral, - &fake_devname); - free_dfs_info_param(&referral); - - if (IS_ERR(mdata)) { - rc = PTR_ERR(mdata); - mdata = NULL; - } else { - /* - * We can not clear out the whole structure since we - * no longer have an explicit function to parse - * a mount-string. Instead we need to clear out the - * individual fields that are no longer valid. - */ - kfree(ctx->prepath); - ctx->prepath = NULL; - rc = cifs_setup_volume_info(ctx, mdata, fake_devname); - } - kfree(fake_devname); - kfree(cifs_sb->ctx->mount_options); - cifs_sb->ctx->mount_options = mdata; - } - kfree(full_path); - return rc; -} - -static int get_next_dfs_tgt(struct dfs_cache_tgt_list *tgt_list, - struct dfs_cache_tgt_iterator **tgt_it) -{ - if (!*tgt_it) - *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); - else - *tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it); - return !*tgt_it ? -EHOSTDOWN : 0; -} - -static int update_vol_info(const struct dfs_cache_tgt_iterator *tgt_it, - struct smb3_fs_context *fake_ctx, struct smb3_fs_context *ctx) -{ - const char *tgt = dfs_cache_get_tgt_name(tgt_it); - int len = strlen(tgt) + 2; - char *new_unc; - - new_unc = kmalloc(len, GFP_KERNEL); - if (!new_unc) - return -ENOMEM; - scnprintf(new_unc, len, "\\%s", tgt); - - kfree(ctx->UNC); - ctx->UNC = new_unc; - - if (fake_ctx->prepath) { - kfree(ctx->prepath); - ctx->prepath = fake_ctx->prepath; - fake_ctx->prepath = NULL; - } - memcpy(&ctx->dstaddr, &fake_ctx->dstaddr, sizeof(ctx->dstaddr)); - - return 0; -} - -static int do_dfs_failover(const char *path, const char *full_path, struct cifs_sb_info *cifs_sb, - struct smb3_fs_context *ctx, struct cifs_ses *root_ses, - unsigned int *xid, struct TCP_Server_Info **server, - struct cifs_ses **ses, struct cifs_tcon **tcon) +static int expand_dfs_referral(struct mount_ctx *mnt_ctx, const char *full_path, + struct dfs_info3_param *referral) { int rc; - char *npath = NULL; - struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list); - struct dfs_cache_tgt_iterator *tgt_it = NULL; - struct smb3_fs_context tmp_ctx = {NULL}; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) - return -EOPNOTSUPP; - - npath = dfs_cache_canonical_path(path, cifs_sb->local_nls, cifs_remap(cifs_sb)); - if (IS_ERR(npath)) - return PTR_ERR(npath); - - cifs_dbg(FYI, "%s: path=%s full_path=%s\n", __func__, npath, full_path); - - rc = dfs_cache_noreq_find(npath, NULL, &tgt_list); - if (rc) - goto out; - /* - * We use a 'tmp_ctx' here because we need pass it down to the mount_{get,put} functions to - * test connection against new DFS targets. - */ - rc = smb3_fs_context_dup(&tmp_ctx, ctx); - if (rc) - goto out; - - for (;;) { - struct dfs_info3_param ref = {0}; - char *fake_devname = NULL, *mdata = NULL; - - /* Get next DFS target server - if any */ - rc = get_next_dfs_tgt(&tgt_list, &tgt_it); - if (rc) - break; - - rc = dfs_cache_get_tgt_referral(npath, tgt_it, &ref); - if (rc) - break; - - cifs_dbg(FYI, "%s: old ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC, - tmp_ctx.prepath); - - mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, full_path + 1, &ref, - &fake_devname); - free_dfs_info_param(&ref); - - if (IS_ERR(mdata)) { - rc = PTR_ERR(mdata); - mdata = NULL; - } else - rc = cifs_setup_volume_info(&tmp_ctx, mdata, fake_devname); - - kfree(mdata); - kfree(fake_devname); - - if (rc) - break; - - cifs_dbg(FYI, "%s: new ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC, - tmp_ctx.prepath); - - mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon); - rc = mount_get_dfs_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon); - if (!rc || (*server && *ses)) { - /* - * We were able to connect to new target server. Update current context with - * new target server. - */ - rc = update_vol_info(tgt_it, &tmp_ctx, ctx); - break; - } - } - if (!rc) { - cifs_dbg(FYI, "%s: final ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC, - tmp_ctx.prepath); + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + char *fake_devname = NULL, *mdata = NULL; + + mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, full_path + 1, referral, + &fake_devname); + if (IS_ERR(mdata)) { + rc = PTR_ERR(mdata); + mdata = NULL; + } else { /* - * Update DFS target hint in DFS referral cache with the target server we - * successfully reconnected to. + * We can not clear out the whole structure since we no longer have an explicit + * function to parse a mount-string. Instead we need to clear out the individual + * fields that are no longer valid. */ - rc = dfs_cache_update_tgthint(*xid, root_ses ? root_ses : *ses, cifs_sb->local_nls, - cifs_remap(cifs_sb), path, tgt_it); + kfree(ctx->prepath); + ctx->prepath = NULL; + rc = cifs_setup_volume_info(ctx, mdata, fake_devname); } + kfree(fake_devname); + kfree(cifs_sb->ctx->mount_options); + cifs_sb->ctx->mount_options = mdata; -out: - kfree(npath); - smb3_cleanup_fs_context_contents(&tmp_ctx); - dfs_cache_free_tgts(&tgt_list); return rc; } #endif @@ -3333,12 +3289,14 @@ cifs_are_all_path_components_accessible(struct TCP_Server_Info *server, * Check if path is remote (e.g. a DFS share). Return -EREMOTE if it is, * otherwise 0. */ -static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx, - const unsigned int xid, - struct TCP_Server_Info *server, - struct cifs_tcon *tcon) +static int is_path_remote(struct mount_ctx *mnt_ctx) { int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct TCP_Server_Info *server = mnt_ctx->server; + unsigned int xid = mnt_ctx->xid; + struct cifs_tcon *tcon = mnt_ctx->tcon; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; char *full_path; if (!server->ops->is_path_accessible) @@ -3376,280 +3334,289 @@ static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb3_fs_context * } #ifdef CONFIG_CIFS_DFS_UPCALL -static void set_root_ses(struct cifs_sb_info *cifs_sb, const uuid_t *mount_id, struct cifs_ses *ses, - struct cifs_ses **root_ses) +static void set_root_ses(struct mount_ctx *mnt_ctx) { - if (ses) { + if (mnt_ctx->ses) { spin_lock(&cifs_tcp_ses_lock); - ses->ses_count++; + mnt_ctx->ses->ses_count++; spin_unlock(&cifs_tcp_ses_lock); - dfs_cache_add_refsrv_session(mount_id, ses); + dfs_cache_add_refsrv_session(&mnt_ctx->mount_id, mnt_ctx->ses); } - *root_ses = ses; + mnt_ctx->root_ses = mnt_ctx->ses; } -/* Set up next dfs prefix path in @dfs_path */ -static int next_dfs_prepath(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx, - const unsigned int xid, struct TCP_Server_Info *server, - struct cifs_tcon *tcon, char **dfs_path) +static int is_dfs_mount(struct mount_ctx *mnt_ctx, bool *isdfs, struct dfs_cache_tgt_list *root_tl) { - char *path, *npath; - int added_treename = is_tcon_dfs(tcon); int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - path = cifs_build_path_to_root(ctx, cifs_sb, tcon, added_treename); - if (!path) - return -ENOMEM; + *isdfs = true; - rc = is_path_remote(cifs_sb, ctx, xid, server, tcon); - if (rc == -EREMOTE) { - struct smb3_fs_context v = {NULL}; - /* if @path contains a tree name, skip it in the prefix path */ - if (added_treename) { - rc = smb3_parse_devname(path, &v); - if (rc) - goto out; - npath = build_unc_path_to_root(&v, cifs_sb, true); - smb3_cleanup_fs_context_contents(&v); - } else { - v.UNC = ctx->UNC; - v.prepath = path + 1; - npath = build_unc_path_to_root(&v, cifs_sb, true); - } + rc = mount_get_conns(mnt_ctx); + /* + * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally + * try to get an DFS referral (even cached) to determine whether it is an DFS mount. + * + * Skip prefix path to provide support for DFS referrals from w2k8 servers which don't seem + * to respond with PATH_NOT_COVERED to requests that include the prefix. + */ + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) || + dfs_cache_find(mnt_ctx->xid, mnt_ctx->ses, cifs_sb->local_nls, cifs_remap(cifs_sb), + ctx->UNC + 1, NULL, root_tl)) { + if (rc) + return rc; + /* Check if it is fully accessible and then mount it */ + rc = is_path_remote(mnt_ctx); + if (!rc) + *isdfs = false; + else if (rc != -EREMOTE) + return rc; + } + return 0; +} - if (IS_ERR(npath)) { - rc = PTR_ERR(npath); - goto out; - } +static int connect_dfs_target(struct mount_ctx *mnt_ctx, const char *full_path, + const char *ref_path, struct dfs_cache_tgt_iterator *tit) +{ + int rc; + struct dfs_info3_param ref = {}; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + char *oldmnt = cifs_sb->ctx->mount_options; - kfree(*dfs_path); - *dfs_path = npath; - rc = -EREMOTE; + rc = dfs_cache_get_tgt_referral(ref_path, tit, &ref); + if (rc) + goto out; + + rc = expand_dfs_referral(mnt_ctx, full_path, &ref); + if (rc) + goto out; + + /* Connect to new target only if we were redirected (e.g. mount options changed) */ + if (oldmnt != cifs_sb->ctx->mount_options) { + mount_put_conns(mnt_ctx); + rc = mount_get_dfs_conns(mnt_ctx); + } + if (!rc) { + if (cifs_is_referral_server(mnt_ctx->tcon, &ref)) + set_root_ses(mnt_ctx); + rc = dfs_cache_update_tgthint(mnt_ctx->xid, mnt_ctx->root_ses, cifs_sb->local_nls, + cifs_remap(cifs_sb), ref_path, tit); } out: - kfree(path); + free_dfs_info_param(&ref); return rc; } -/* Check if resolved targets can handle any DFS referrals */ -static int is_referral_server(const char *ref_path, struct cifs_sb_info *cifs_sb, - struct cifs_tcon *tcon, bool *ref_server) +static int connect_dfs_root(struct mount_ctx *mnt_ctx, struct dfs_cache_tgt_list *root_tl) { int rc; - struct dfs_info3_param ref = {0}; + char *full_path; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct dfs_cache_tgt_iterator *tit; - cifs_dbg(FYI, "%s: ref_path=%s\n", __func__, ref_path); + /* Put initial connections as they might be shared with other mounts. We need unique dfs + * connections per mount to properly failover, so mount_get_dfs_conns() must be used from + * now on. + */ + mount_put_conns(mnt_ctx); + mount_get_dfs_conns(mnt_ctx); - if (is_tcon_dfs(tcon)) { - *ref_server = true; - } else { - char *npath; + full_path = build_unc_path_to_root(ctx, cifs_sb, true); + if (IS_ERR(full_path)) + return PTR_ERR(full_path); - npath = dfs_cache_canonical_path(ref_path, cifs_sb->local_nls, cifs_remap(cifs_sb)); - if (IS_ERR(npath)) - return PTR_ERR(npath); + mnt_ctx->origin_fullpath = dfs_cache_canonical_path(ctx->UNC, cifs_sb->local_nls, + cifs_remap(cifs_sb)); + if (IS_ERR(mnt_ctx->origin_fullpath)) { + rc = PTR_ERR(mnt_ctx->origin_fullpath); + mnt_ctx->origin_fullpath = NULL; + goto out; + } - rc = dfs_cache_noreq_find(npath, &ref, NULL); - kfree(npath); - if (rc) { - cifs_dbg(VFS, "%s: dfs_cache_noreq_find: failed (rc=%d)\n", __func__, rc); - return rc; + /* Try all dfs root targets */ + for (rc = -ENOENT, tit = dfs_cache_get_tgt_iterator(root_tl); + tit; tit = dfs_cache_get_next_tgt(root_tl, tit)) { + rc = connect_dfs_target(mnt_ctx, full_path, mnt_ctx->origin_fullpath + 1, tit); + if (!rc) { + mnt_ctx->leaf_fullpath = kstrdup(mnt_ctx->origin_fullpath, GFP_KERNEL); + if (!mnt_ctx->leaf_fullpath) + rc = -ENOMEM; + break; } - cifs_dbg(FYI, "%s: ref.flags=0x%x\n", __func__, ref.flags); - /* - * Check if all targets are capable of handling DFS referrals as per - * MS-DFSC 2.2.4 RESP_GET_DFS_REFERRAL. - */ - *ref_server = !!(ref.flags & DFSREF_REFERRAL_SERVER); - free_dfs_info_param(&ref); } - return 0; + +out: + kfree(full_path); + return rc; } -int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) +static int __follow_dfs_link(struct mount_ctx *mnt_ctx) { - int rc = 0; - unsigned int xid; - struct TCP_Server_Info *server = NULL; - struct cifs_ses *ses = NULL, *root_ses = NULL; - struct cifs_tcon *tcon = NULL; - int count = 0; - uuid_t mount_id = {0}; - char *ref_path = NULL, *full_path = NULL; - char *oldmnt = NULL; - bool ref_server = false; + int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + char *full_path; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + struct dfs_cache_tgt_iterator *tit; - rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); - /* - * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally - * try to get an DFS referral (even cached) to determine whether it is an DFS mount. - * - * Skip prefix path to provide support for DFS referrals from w2k8 servers which don't seem - * to respond with PATH_NOT_COVERED to requests that include the prefix. - */ - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) || - dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), ctx->UNC + 1, NULL, - NULL)) { - if (rc) - goto error; - /* Check if it is fully accessible and then mount it */ - rc = is_path_remote(cifs_sb, ctx, xid, server, tcon); - if (!rc) - goto out; - if (rc != -EREMOTE) - goto error; + full_path = build_unc_path_to_root(ctx, cifs_sb, true); + if (IS_ERR(full_path)) + return PTR_ERR(full_path); + + kfree(mnt_ctx->leaf_fullpath); + mnt_ctx->leaf_fullpath = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, + cifs_remap(cifs_sb)); + if (IS_ERR(mnt_ctx->leaf_fullpath)) { + rc = PTR_ERR(mnt_ctx->leaf_fullpath); + mnt_ctx->leaf_fullpath = NULL; + goto out; } - mount_put_conns(cifs_sb, xid, server, ses, tcon); - /* - * Ignore error check here because we may failover to other targets from cached a - * referral. - */ - (void)mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); + /* Get referral from dfs link */ + rc = dfs_cache_find(mnt_ctx->xid, mnt_ctx->root_ses, cifs_sb->local_nls, + cifs_remap(cifs_sb), mnt_ctx->leaf_fullpath + 1, NULL, &tl); + if (rc) + goto out; - /* Get path of DFS root */ - ref_path = build_unc_path_to_root(ctx, cifs_sb, false); - if (IS_ERR(ref_path)) { - rc = PTR_ERR(ref_path); - ref_path = NULL; - goto error; + /* Try all dfs link targets */ + for (rc = -ENOENT, tit = dfs_cache_get_tgt_iterator(&tl); + tit; tit = dfs_cache_get_next_tgt(&tl, tit)) { + rc = connect_dfs_target(mnt_ctx, full_path, mnt_ctx->leaf_fullpath + 1, tit); + if (!rc) { + rc = is_path_remote(mnt_ctx); + break; + } + } + +out: + kfree(full_path); + dfs_cache_free_tgts(&tl); + return rc; +} + +static int follow_dfs_link(struct mount_ctx *mnt_ctx) +{ + int rc; + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + char *full_path; + int num_links = 0; + + full_path = build_unc_path_to_root(ctx, cifs_sb, true); + if (IS_ERR(full_path)) + return PTR_ERR(full_path); + + kfree(mnt_ctx->origin_fullpath); + mnt_ctx->origin_fullpath = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, + cifs_remap(cifs_sb)); + kfree(full_path); + + if (IS_ERR(mnt_ctx->origin_fullpath)) { + rc = PTR_ERR(mnt_ctx->origin_fullpath); + mnt_ctx->origin_fullpath = NULL; + return rc; } - uuid_gen(&mount_id); - set_root_ses(cifs_sb, &mount_id, ses, &root_ses); do { - /* Save full path of last DFS path we used to resolve final target server */ - kfree(full_path); - full_path = build_unc_path_to_root(ctx, cifs_sb, !!count); - if (IS_ERR(full_path)) { - rc = PTR_ERR(full_path); - full_path = NULL; - break; - } - /* Chase referral */ - oldmnt = cifs_sb->ctx->mount_options; - rc = expand_dfs_referral(xid, root_ses, ctx, cifs_sb, ref_path + 1); - if (rc) - break; - /* Connect to new DFS target only if we were redirected */ - if (oldmnt != cifs_sb->ctx->mount_options) { - mount_put_conns(cifs_sb, xid, server, ses, tcon); - rc = mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); - } - if (rc && !server && !ses) { - /* Failed to connect. Try to connect to other targets in the referral. */ - rc = do_dfs_failover(ref_path + 1, full_path, cifs_sb, ctx, root_ses, &xid, - &server, &ses, &tcon); - } - if (rc == -EACCES || rc == -EOPNOTSUPP || !server || !ses) + rc = __follow_dfs_link(mnt_ctx); + if (!rc || rc != -EREMOTE) break; - if (!tcon) - continue; + } while (rc = -ELOOP, ++num_links < MAX_NESTED_LINKS); - /* Make sure that requests go through new root servers */ - rc = is_referral_server(ref_path + 1, cifs_sb, tcon, &ref_server); - if (rc) - break; - if (ref_server) - set_root_ses(cifs_sb, &mount_id, ses, &root_ses); + return rc; +} - /* Get next dfs path and then continue chasing them if -EREMOTE */ - rc = next_dfs_prepath(cifs_sb, ctx, xid, server, tcon, &ref_path); - /* Prevent recursion on broken link referrals */ - if (rc == -EREMOTE && ++count > MAX_NESTED_LINKS) - rc = -ELOOP; - } while (rc == -EREMOTE); +/* Set up DFS referral paths for failover */ +static void setup_server_referral_paths(struct mount_ctx *mnt_ctx) +{ + struct TCP_Server_Info *server = mnt_ctx->server; + + server->origin_fullpath = mnt_ctx->origin_fullpath; + server->leaf_fullpath = mnt_ctx->leaf_fullpath; + server->current_fullpath = mnt_ctx->leaf_fullpath; + mnt_ctx->origin_fullpath = mnt_ctx->leaf_fullpath = NULL; +} - if (rc || !tcon || !ses) +int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) +{ + int rc; + struct mount_ctx mnt_ctx = { .cifs_sb = cifs_sb, .fs_ctx = ctx, }; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + bool isdfs; + + rc = is_dfs_mount(&mnt_ctx, &isdfs, &tl); + if (rc) goto error; + if (!isdfs) + goto out; - kfree(ref_path); - /* - * Store DFS full path in both superblock and tree connect structures. - * - * For DFS root mounts, the prefix path (cifs_sb->prepath) is preserved during reconnect so - * only the root path is set in cifs_sb->origin_fullpath and tcon->dfs_path. And for DFS - * links, the prefix path is included in both and may be changed during reconnect. See - * cifs_tree_connect(). - */ - ref_path = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, cifs_remap(cifs_sb)); - kfree(full_path); - full_path = NULL; + uuid_gen(&mnt_ctx.mount_id); + rc = connect_dfs_root(&mnt_ctx, &tl); + dfs_cache_free_tgts(&tl); - if (IS_ERR(ref_path)) { - rc = PTR_ERR(ref_path); - ref_path = NULL; + if (rc) goto error; - } - cifs_sb->origin_fullpath = ref_path; - ref_path = kstrdup(cifs_sb->origin_fullpath, GFP_KERNEL); - if (!ref_path) { - rc = -ENOMEM; + rc = is_path_remote(&mnt_ctx); + if (rc == -EREMOTE) + rc = follow_dfs_link(&mnt_ctx); + if (rc) goto error; - } - spin_lock(&cifs_tcp_ses_lock); - tcon->dfs_path = ref_path; - ref_path = NULL; - spin_unlock(&cifs_tcp_ses_lock); + setup_server_referral_paths(&mnt_ctx); /* - * After reconnecting to a different server, unique ids won't - * match anymore, so we disable serverino. This prevents - * dentry revalidation to think the dentry are stale (ESTALE). + * After reconnecting to a different server, unique ids won't match anymore, so we disable + * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE). */ cifs_autodisable_serverino(cifs_sb); /* - * Force the use of prefix path to support failover on DFS paths that - * resolve to targets that have different prefix paths. + * Force the use of prefix path to support failover on DFS paths that resolve to targets + * that have different prefix paths. */ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; kfree(cifs_sb->prepath); cifs_sb->prepath = ctx->prepath; ctx->prepath = NULL; - uuid_copy(&cifs_sb->dfs_mount_id, &mount_id); + uuid_copy(&cifs_sb->dfs_mount_id, &mnt_ctx.mount_id); out: - free_xid(xid); - cifs_try_adding_channels(cifs_sb, ses); - return mount_setup_tlink(cifs_sb, ses, tcon); + free_xid(mnt_ctx.xid); + cifs_try_adding_channels(cifs_sb, mnt_ctx.ses); + return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); error: - kfree(ref_path); - kfree(full_path); - kfree(cifs_sb->origin_fullpath); - dfs_cache_put_refsrv_sessions(&mount_id); - mount_put_conns(cifs_sb, xid, server, ses, tcon); + dfs_cache_put_refsrv_sessions(&mnt_ctx.mount_id); + kfree(mnt_ctx.origin_fullpath); + kfree(mnt_ctx.leaf_fullpath); + mount_put_conns(&mnt_ctx); return rc; } #else int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) { int rc = 0; - unsigned int xid; - struct cifs_ses *ses; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; + struct mount_ctx mnt_ctx = { .cifs_sb = cifs_sb, .fs_ctx = ctx, }; - rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); + rc = mount_get_conns(&mnt_ctx); if (rc) goto error; - if (tcon) { - rc = is_path_remote(cifs_sb, ctx, xid, server, tcon); + if (mnt_ctx.tcon) { + rc = is_path_remote(&mnt_ctx); if (rc == -EREMOTE) rc = -EOPNOTSUPP; if (rc) goto error; } - free_xid(xid); - - return mount_setup_tlink(cifs_sb, ses, tcon); + free_xid(mnt_ctx.xid); + return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); error: - mount_put_conns(cifs_sb, xid, server, ses, tcon); + mount_put_conns(&mnt_ctx); return rc; } #endif @@ -3818,7 +3785,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb) kfree(cifs_sb->prepath); #ifdef CONFIG_CIFS_DFS_UPCALL dfs_cache_put_refsrv_sessions(&cifs_sb->dfs_mount_id); - kfree(cifs_sb->origin_fullpath); #endif call_rcu(&cifs_sb->rcu, delayed_free); } @@ -4145,104 +4111,246 @@ cifs_prune_tlinks(struct work_struct *work) } #ifdef CONFIG_CIFS_DFS_UPCALL -int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nlsc) +static void mark_tcon_tcp_ses_for_reconnect(struct cifs_tcon *tcon) +{ + int i; + + for (i = 0; i < tcon->ses->chan_count; i++) { + spin_lock(&GlobalMid_Lock); + if (tcon->ses->chans[i].server->tcpStatus != CifsExiting) + tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + } +} + +/* Update dfs referral path of superblock */ +static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb_info *cifs_sb, + const char *target) +{ + int rc = 0; + size_t len = strlen(target); + char *refpath, *npath; + + if (unlikely(len < 2 || *target != '\\')) + return -EINVAL; + + if (target[1] == '\\') { + len += 1; + refpath = kmalloc(len, GFP_KERNEL); + if (!refpath) + return -ENOMEM; + + scnprintf(refpath, len, "%s", target); + } else { + len += sizeof("\\"); + refpath = kmalloc(len, GFP_KERNEL); + if (!refpath) + return -ENOMEM; + + scnprintf(refpath, len, "\\%s", target); + } + + npath = dfs_cache_canonical_path(refpath, cifs_sb->local_nls, cifs_remap(cifs_sb)); + kfree(refpath); + + if (IS_ERR(npath)) { + rc = PTR_ERR(npath); + } else { + mutex_lock(&server->refpath_lock); + kfree(server->leaf_fullpath); + server->leaf_fullpath = npath; + mutex_unlock(&server->refpath_lock); + server->current_fullpath = server->leaf_fullpath; + } + return rc; +} + +static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host, + size_t tcp_host_len, char *share, bool *target_match) +{ + int rc = 0; + const char *dfs_host; + size_t dfs_host_len; + + *target_match = true; + extract_unc_hostname(share, &dfs_host, &dfs_host_len); + + /* Check if hostnames or addresses match */ + if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { + cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len, + dfs_host, (int)tcp_host_len, tcp_host); + rc = match_target_ip(server, dfs_host, dfs_host_len, target_match); + if (rc) + cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc); + } + return rc; +} + +static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, char *tree, bool islink, + struct dfs_cache_tgt_list *tl) { int rc; struct TCP_Server_Info *server = tcon->ses->server; const struct smb_version_operations *ops = server->ops; - struct dfs_cache_tgt_list tl; - struct dfs_cache_tgt_iterator *it = NULL; - char *tree; + struct cifs_tcon *ipc = tcon->ses->tcon_ipc; + char *share = NULL, *prefix = NULL; const char *tcp_host; size_t tcp_host_len; - const char *dfs_host; - size_t dfs_host_len; - char *share = NULL, *prefix = NULL; - struct dfs_info3_param ref = {0}; - bool isroot; + struct dfs_cache_tgt_iterator *tit; + bool target_match; - tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); - if (!tree) - return -ENOMEM; + extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); - /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */ - if (!tcon->dfs_path || dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl)) { - if (tcon->ipc) { - scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); - rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); - } else { - rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, nlsc); - } + tit = dfs_cache_get_tgt_iterator(tl); + if (!tit) { + rc = -ENOENT; goto out; } - isroot = ref.server_type == DFS_TYPE_ROOT; - free_dfs_info_param(&ref); - - extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len); - - for (it = dfs_cache_get_tgt_iterator(&tl); it; it = dfs_cache_get_next_tgt(&tl, it)) { - bool target_match; + /* Try to tree connect to all dfs targets */ + for (; tit; tit = dfs_cache_get_next_tgt(tl, tit)) { + const char *target = dfs_cache_get_tgt_name(tit); + struct dfs_cache_tgt_list ntl = DFS_CACHE_TGT_LIST_INIT(ntl); kfree(share); kfree(prefix); - share = NULL; - prefix = NULL; + share = prefix = NULL; - rc = dfs_cache_get_tgt_share(tcon->dfs_path + 1, it, &share, &prefix); + /* Check if share matches with tcp ses */ + rc = dfs_cache_get_tgt_share(server->current_fullpath + 1, tit, &share, &prefix); if (rc) { - cifs_dbg(VFS, "%s: failed to parse target share %d\n", - __func__, rc); - continue; + cifs_dbg(VFS, "%s: failed to parse target share: %d\n", __func__, rc); + break; } - extract_unc_hostname(share, &dfs_host, &dfs_host_len); - - if (dfs_host_len != tcp_host_len - || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { - cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len, - dfs_host, (int)tcp_host_len, tcp_host); + rc = target_share_matches_server(server, tcp_host, tcp_host_len, share, + &target_match); + if (rc) + break; + if (!target_match) { + rc = -EHOSTUNREACH; + continue; + } - rc = match_target_ip(server, dfs_host, dfs_host_len, &target_match); - if (rc) { - cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc); + if (ipc->need_reconnect) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); + rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls); + if (rc) break; - } - - if (!target_match) { - cifs_dbg(FYI, "%s: skipping target\n", __func__); - continue; - } } - if (tcon->ipc) { - scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", share); - rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); + scnprintf(tree, MAX_TREE_SIZE, "\\%s", share); + if (!islink) { + rc = ops->tree_connect(xid, tcon->ses, tree, tcon, cifs_sb->local_nls); + break; + } + /* + * If no dfs referrals were returned from link target, then just do a TREE_CONNECT + * to it. Otherwise, cache the dfs referral and then mark current tcp ses for + * reconnect so either the demultiplex thread or the echo worker will reconnect to + * newly resolved target. + */ + if (dfs_cache_find(xid, tcon->ses, cifs_sb->local_nls, cifs_remap(cifs_sb), target, + NULL, &ntl)) { + rc = ops->tree_connect(xid, tcon->ses, tree, tcon, cifs_sb->local_nls); + if (rc) + continue; + rc = dfs_cache_noreq_update_tgthint(server->current_fullpath + 1, tit); + if (!rc) + rc = cifs_update_super_prepath(cifs_sb, prefix); } else { - scnprintf(tree, MAX_TREE_SIZE, "\\%s", share); - rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); - /* Only handle prefix paths of DFS link targets */ - if (!rc && !isroot) { - rc = update_super_prepath(tcon, prefix); - break; - } + /* Target is another dfs share */ + rc = update_server_fullpath(server, cifs_sb, target); + dfs_cache_free_tgts(tl); + + if (!rc) { + rc = -EREMOTE; + list_replace_init(&ntl.tl_list, &tl->tl_list); + } else + dfs_cache_free_tgts(&ntl); } - if (rc == -EREMOTE) - break; + break; } +out: kfree(share); kfree(prefix); - if (!rc) { - if (it) - rc = dfs_cache_noreq_update_tgthint(tcon->dfs_path + 1, it); - else - rc = -ENOENT; + return rc; +} + +static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, char *tree, bool islink, + struct dfs_cache_tgt_list *tl) +{ + int rc; + int num_links = 0; + struct TCP_Server_Info *server = tcon->ses->server; + + do { + rc = __tree_connect_dfs_target(xid, tcon, cifs_sb, tree, islink, tl); + if (!rc || rc != -EREMOTE) + break; + } while (rc = -ELOOP, ++num_links < MAX_NESTED_LINKS); + /* + * If we couldn't tree connect to any targets from last referral path, then retry from + * original referral path. + */ + if (rc && server->current_fullpath != server->origin_fullpath) { + server->current_fullpath = server->origin_fullpath; + mark_tcon_tcp_ses_for_reconnect(tcon); } - dfs_cache_free_tgts(&tl); + + dfs_cache_free_tgts(tl); + return rc; +} + +int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nlsc) +{ + int rc; + struct TCP_Server_Info *server = tcon->ses->server; + const struct smb_version_operations *ops = server->ops; + struct super_block *sb = NULL; + struct cifs_sb_info *cifs_sb; + struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + char *tree; + struct dfs_info3_param ref = {0}; + + tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL); + if (!tree) + return -ENOMEM; + + if (tcon->ipc) { + scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); + rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc); + goto out; + } + + sb = cifs_get_tcp_super(server); + if (IS_ERR(sb)) { + rc = PTR_ERR(sb); + cifs_dbg(VFS, "%s: could not find superblock: %d\n", __func__, rc); + goto out; + } + + cifs_sb = CIFS_SB(sb); + + /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */ + if (!server->current_fullpath || + dfs_cache_noreq_find(server->current_fullpath + 1, &ref, &tl)) { + rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, cifs_sb->local_nls); + goto out; + } + + rc = tree_connect_dfs_target(xid, tcon, cifs_sb, tree, ref.server_type == DFS_TYPE_LINK, + &tl); + free_dfs_info_param(&ref); + out: kfree(tree); + cifs_put_tcp_super(sb); + return rc; } #else diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 283745592844..5c1259d2eeac 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -283,7 +283,7 @@ static int dfscache_proc_show(struct seq_file *m, void *v) seq_printf(m, "cache entry: path=%s,type=%s,ttl=%d,etime=%ld,hdr_flags=0x%x,ref_flags=0x%x,interlink=%s,path_consumed=%d,expired=%s\n", ce->path, ce->srvtype == DFS_TYPE_ROOT ? "root" : "link", - ce->ttl, ce->etime.tv_nsec, ce->ref_flags, ce->hdr_flags, + ce->ttl, ce->etime.tv_nsec, ce->hdr_flags, ce->ref_flags, IS_DFS_INTERLINK(ce->hdr_flags) ? "yes" : "no", ce->path_consumed, cache_entry_expired(ce) ? "yes" : "no"); @@ -1364,9 +1364,9 @@ static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cach } /* Refresh dfs referral of tcon and mark it for reconnect if needed */ -static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh) +static int __refresh_tcon(const char *path, struct cifs_ses **sessions, struct cifs_tcon *tcon, + bool force_refresh) { - const char *path = tcon->dfs_path + 1; struct cifs_ses *ses; struct cache_entry *ce; struct dfs_info3_param *refs = NULL; @@ -1422,6 +1422,20 @@ out: return rc; } +static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh) +{ + struct TCP_Server_Info *server = tcon->ses->server; + + mutex_lock(&server->refpath_lock); + if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + mutex_unlock(&server->refpath_lock); + + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); + + return 0; +} + /** * dfs_cache_remount_fs - remount a DFS share * @@ -1435,6 +1449,7 @@ out: int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) { struct cifs_tcon *tcon; + struct TCP_Server_Info *server; struct mount_group *mg; struct cifs_ses *sessions[CACHE_MAX_ENTRIES + 1] = {NULL}; int rc; @@ -1443,13 +1458,15 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) return -EINVAL; tcon = cifs_sb_master_tcon(cifs_sb); - if (!tcon->dfs_path) { - cifs_dbg(FYI, "%s: not a dfs tcon\n", __func__); + server = tcon->ses->server; + + if (!server->origin_fullpath) { + cifs_dbg(FYI, "%s: not a dfs mount\n", __func__); return 0; } if (uuid_is_null(&cifs_sb->dfs_mount_id)) { - cifs_dbg(FYI, "%s: tcon has no dfs mount group id\n", __func__); + cifs_dbg(FYI, "%s: no dfs mount group id\n", __func__); return -EINVAL; } @@ -1457,7 +1474,7 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) mg = find_mount_group_locked(&cifs_sb->dfs_mount_id); if (IS_ERR(mg)) { mutex_unlock(&mount_group_list_lock); - cifs_dbg(FYI, "%s: tcon has ipc session to refresh referral\n", __func__); + cifs_dbg(FYI, "%s: no ipc session for refreshing referral\n", __func__); return PTR_ERR(mg); } kref_get(&mg->refcount); @@ -1498,9 +1515,12 @@ static void refresh_mounts(struct cifs_ses **sessions) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { + if (!server->is_dfs_conn) + continue; + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { - if (tcon->dfs_path) { + if (!tcon->ipc && !tcon->need_reconnect) { tcon->tc_count++; list_add_tail(&tcon->ulist, &tcons); } @@ -1510,8 +1530,16 @@ static void refresh_mounts(struct cifs_ses **sessions) spin_unlock(&cifs_tcp_ses_lock); list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) { + struct TCP_Server_Info *server = tcon->ses->server; + list_del_init(&tcon->ulist); - refresh_tcon(sessions, tcon, false); + + mutex_lock(&server->refpath_lock); + if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + mutex_unlock(&server->refpath_lock); + + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); cifs_put_tcon(tcon); } } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 1b855fcb179e..9fee3af83a73 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2692,12 +2692,23 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, tcon = tlink_tcon(smbfile->tlink); if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { server = tcon->ses->server; - if (server->ops->flush) - rc = server->ops->flush(xid, tcon, &smbfile->fid); - else + if (server->ops->flush == NULL) { rc = -ENOSYS; + goto strict_fsync_exit; + } + + if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { + smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); + if (smbfile) { + rc = server->ops->flush(xid, tcon, &smbfile->fid); + cifsFileInfo_put(smbfile); + } else + cifs_dbg(FYI, "ignore fsync for file not open for write\n"); + } else + rc = server->ops->flush(xid, tcon, &smbfile->fid); } +strict_fsync_exit: free_xid(xid); return rc; } @@ -2709,6 +2720,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct cifs_tcon *tcon; struct TCP_Server_Info *server; struct cifsFileInfo *smbfile = file->private_data; + struct inode *inode = file_inode(file); struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); rc = file_write_and_wait_range(file, start, end); @@ -2725,12 +2737,23 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) tcon = tlink_tcon(smbfile->tlink); if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { server = tcon->ses->server; - if (server->ops->flush) - rc = server->ops->flush(xid, tcon, &smbfile->fid); - else + if (server->ops->flush == NULL) { rc = -ENOSYS; + goto fsync_exit; + } + + if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { + smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); + if (smbfile) { + rc = server->ops->flush(xid, tcon, &smbfile->fid); + cifsFileInfo_put(smbfile); + } else + cifs_dbg(FYI, "ignore fsync for file not open for write\n"); + } else + rc = server->ops->flush(xid, tcon, &smbfile->fid); } +fsync_exit: free_xid(xid); return rc; } diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 38d96a480745..6a179ae753c1 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -308,7 +308,9 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->nodename = NULL; new_ctx->username = NULL; new_ctx->password = NULL; + new_ctx->server_hostname = NULL; new_ctx->domainname = NULL; + new_ctx->workstation_name = NULL; new_ctx->UNC = NULL; new_ctx->source = NULL; new_ctx->iocharset = NULL; @@ -323,6 +325,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(UNC); DUP_CTX_STR(source); DUP_CTX_STR(domainname); + DUP_CTX_STR(workstation_name); DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); @@ -459,6 +462,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) return -EINVAL; /* record the server hostname */ + kfree(ctx->server_hostname); ctx->server_hostname = kstrndup(devname + 2, pos - devname - 2, GFP_KERNEL); if (!ctx->server_hostname) return -ENOMEM; @@ -720,6 +724,11 @@ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, cifs_errorf(fc, "can not change domainname during remount\n"); return -EINVAL; } + if (new_ctx->workstation_name && + (!old_ctx->workstation_name || strcmp(new_ctx->workstation_name, old_ctx->workstation_name))) { + cifs_errorf(fc, "can not change workstation_name during remount\n"); + return -EINVAL; + } if (new_ctx->nodename && (!old_ctx->nodename || strcmp(new_ctx->nodename, old_ctx->nodename))) { cifs_errorf(fc, "can not change nodename during remount\n"); @@ -753,7 +762,8 @@ static int smb3_reconfigure(struct fs_context *fc) return rc; /* - * We can not change UNC/username/password/domainname/nodename/iocharset + * We can not change UNC/username/password/domainname/ + * workstation_name/nodename/iocharset * during reconnect so ignore what we have in the new context and * just use what we already have in cifs_sb->ctx. */ @@ -762,6 +772,7 @@ static int smb3_reconfigure(struct fs_context *fc) STEAL_STRING(cifs_sb, ctx, username); STEAL_STRING(cifs_sb, ctx, password); STEAL_STRING(cifs_sb, ctx, domainname); + STEAL_STRING(cifs_sb, ctx, workstation_name); STEAL_STRING(cifs_sb, ctx, nodename); STEAL_STRING(cifs_sb, ctx, iocharset); @@ -1414,13 +1425,22 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, int smb3_init_fs_context(struct fs_context *fc) { + int rc; struct smb3_fs_context *ctx; char *nodename = utsname()->nodename; int i; ctx = kzalloc(sizeof(struct smb3_fs_context), GFP_KERNEL); - if (unlikely(!ctx)) - return -ENOMEM; + if (unlikely(!ctx)) { + rc = -ENOMEM; + goto err_exit; + } + + ctx->workstation_name = kstrdup(nodename, GFP_KERNEL); + if (unlikely(!ctx->workstation_name)) { + rc = -ENOMEM; + goto err_exit; + } /* * does not have to be perfect mapping since field is @@ -1493,6 +1513,14 @@ int smb3_init_fs_context(struct fs_context *fc) fc->fs_private = ctx; fc->ops = &smb3_fs_context_ops; return 0; + +err_exit: + if (ctx) { + kfree(ctx->workstation_name); + kfree(ctx); + } + + return rc; } void @@ -1518,6 +1546,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->source = NULL; kfree(ctx->domainname); ctx->domainname = NULL; + kfree(ctx->workstation_name); + ctx->workstation_name = NULL; kfree(ctx->nodename); ctx->nodename = NULL; kfree(ctx->iocharset); diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index b2d22cf9cb18..e54090d9ef36 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -170,6 +170,7 @@ struct smb3_fs_context { char *server_hostname; char *UNC; char *nodename; + char *workstation_name; char *iocharset; /* local code page for mapping to and from Unicode */ char source_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* clnt nb name */ char target_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* srvr nb name */ diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 8eedd20c44ab..7e409a38a2d7 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -87,6 +87,14 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) char *sharename; struct cifs_fscache_super_auxdata auxdata; + /* + * Check if cookie was already initialized so don't reinitialize it. + * In the future, as we integrate with newer fscache features, + * we may want to instead add a check if cookie has changed + */ + if (tcon->fscache == NULL) + return; + sharename = extract_sharename(tcon->treeName); if (IS_ERR(sharename)) { cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index ba2c3e897b29..5148d48d6a35 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -75,6 +75,7 @@ sesInfoAlloc(void) INIT_LIST_HEAD(&ret_buf->tcon_list); mutex_init(&ret_buf->session_mutex); spin_lock_init(&ret_buf->iface_lock); + spin_lock_init(&ret_buf->chan_lock); } return ret_buf; } @@ -94,6 +95,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree_sensitive(buf_to_free->password); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); + kfree(buf_to_free->workstation_name); kfree_sensitive(buf_to_free->auth_key.response); kfree(buf_to_free->iface_list); kfree_sensitive(buf_to_free); @@ -138,9 +140,6 @@ tconInfoFree(struct cifs_tcon *buf_to_free) kfree(buf_to_free->nativeFileSystem); kfree_sensitive(buf_to_free->password); kfree(buf_to_free->crfid.fid); -#ifdef CONFIG_CIFS_DFS_UPCALL - kfree(buf_to_free->dfs_path); -#endif kfree(buf_to_free); } @@ -1287,69 +1286,20 @@ out: return rc; } -static void tcon_super_cb(struct super_block *sb, void *arg) +int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix) { - struct super_cb_data *sd = arg; - struct cifs_tcon *tcon = sd->data; - struct cifs_sb_info *cifs_sb; - - if (sd->sb) - return; - - cifs_sb = CIFS_SB(sb); - if (tcon->dfs_path && cifs_sb->origin_fullpath && - !strcasecmp(tcon->dfs_path, cifs_sb->origin_fullpath)) - sd->sb = sb; -} - -static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon) -{ - return __cifs_get_super(tcon_super_cb, tcon); -} - -static inline void cifs_put_tcon_super(struct super_block *sb) -{ - __cifs_put_super(sb); -} -#else -static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void cifs_put_tcon_super(struct super_block *sb) -{ -} -#endif - -int update_super_prepath(struct cifs_tcon *tcon, char *prefix) -{ - struct super_block *sb; - struct cifs_sb_info *cifs_sb; - int rc = 0; - - sb = cifs_get_tcon_super(tcon); - if (IS_ERR(sb)) - return PTR_ERR(sb); - - cifs_sb = CIFS_SB(sb); - kfree(cifs_sb->prepath); if (prefix && *prefix) { cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC); - if (!cifs_sb->prepath) { - rc = -ENOMEM; - goto out; - } + if (!cifs_sb->prepath) + return -ENOMEM; convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb)); } else cifs_sb->prepath = NULL; cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - -out: - cifs_put_tcon_super(sb); - return rc; + return 0; } +#endif diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 25a2b8ef88b9..fe707f45da89 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -119,7 +119,9 @@ typedef struct _AUTHENTICATE_MESSAGE { */ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses); -void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses); +int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, u16 *buflen, + struct cifs_ses *ses, + const struct nls_table *nls_cp); int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen, struct cifs_ses *ses, const struct nls_table *nls_cp); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 23e02db7923f..2c10b186ed6e 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -54,41 +54,53 @@ bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface) { int i; + spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { - if (is_server_using_iface(ses->chans[i].server, iface)) + if (is_server_using_iface(ses->chans[i].server, iface)) { + spin_unlock(&ses->chan_lock); return true; + } } + spin_unlock(&ses->chan_lock); return false; } /* returns number of channels added */ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) { - int old_chan_count = ses->chan_count; - int left = ses->chan_max - ses->chan_count; + int old_chan_count, new_chan_count; + int left; int i = 0; int rc = 0; int tries = 0; struct cifs_server_iface *ifaces = NULL; size_t iface_count; + if (ses->server->dialect < SMB30_PROT_ID) { + cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n"); + return 0; + } + + spin_lock(&ses->chan_lock); + + new_chan_count = old_chan_count = ses->chan_count; + left = ses->chan_max - ses->chan_count; + if (left <= 0) { cifs_dbg(FYI, "ses already at max_channels (%zu), nothing to open\n", ses->chan_max); - return 0; - } - - if (ses->server->dialect < SMB30_PROT_ID) { - cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n"); + spin_unlock(&ses->chan_lock); return 0; } if (!(ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname); ses->chan_max = 1; + spin_unlock(&ses->chan_lock); return 0; } + spin_unlock(&ses->chan_lock); /* * Make a copy of the iface list at the time and use that @@ -142,10 +154,11 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) cifs_dbg(FYI, "successfully opened new channel on iface#%d\n", i); left--; + new_chan_count++; } kfree(ifaces); - return ses->chan_count - old_chan_count; + return new_chan_count - old_chan_count; } /* @@ -157,10 +170,14 @@ cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server) { int i; + spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { - if (ses->chans[i].server == server) + if (ses->chans[i].server == server) { + spin_unlock(&ses->chan_lock); return &ses->chans[i]; + } } + spin_unlock(&ses->chan_lock); return NULL; } @@ -168,6 +185,7 @@ static int cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, struct cifs_server_iface *iface) { + struct TCP_Server_Info *chan_server; struct cifs_chan *chan; struct smb3_fs_context ctx = {NULL}; static const char unc_fmt[] = "\\%s\\foo"; @@ -240,18 +258,19 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, SMB2_CLIENT_GUID_SIZE); ctx.use_client_guid = true; - mutex_lock(&ses->session_mutex); + chan_server = cifs_get_tcp_session(&ctx, ses->server); + mutex_lock(&ses->session_mutex); + spin_lock(&ses->chan_lock); chan = ses->binding_chan = &ses->chans[ses->chan_count]; - chan->server = cifs_get_tcp_session(&ctx); + chan->server = chan_server; if (IS_ERR(chan->server)) { rc = PTR_ERR(chan->server); chan->server = NULL; + spin_unlock(&ses->chan_lock); goto out; } - spin_lock(&cifs_tcp_ses_lock); - chan->server->is_channel = true; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&ses->chan_lock); /* * We need to allocate the server crypto now as we will need @@ -283,8 +302,11 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, * ses to the new server. */ + spin_lock(&ses->chan_lock); ses->chan_count++; atomic_set(&ses->chan_seq, 0); + spin_unlock(&ses->chan_lock); + out: ses->binding = false; ses->binding_chan = NULL; @@ -599,18 +621,85 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, return 0; } +static int size_of_ntlmssp_blob(struct cifs_ses *ses, int base_size) +{ + int sz = base_size + ses->auth_key.len + - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2; + + if (ses->domainName) + sz += sizeof(__le16) * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN); + else + sz += sizeof(__le16); + + if (ses->user_name) + sz += sizeof(__le16) * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN); + else + sz += sizeof(__le16); + + sz += sizeof(__le16) * strnlen(ses->workstation_name, CIFS_MAX_WORKSTATION_LEN); + + return sz; +} + +static inline void cifs_security_buffer_from_str(SECURITY_BUFFER *pbuf, + char *str_value, + int str_length, + unsigned char *pstart, + unsigned char **pcur, + const struct nls_table *nls_cp) +{ + unsigned char *tmp = pstart; + int len; + + if (!pbuf) + return; + + if (!pcur) + pcur = &tmp; + + if (!str_value) { + pbuf->BufferOffset = cpu_to_le32(*pcur - pstart); + pbuf->Length = 0; + pbuf->MaximumLength = 0; + *pcur += sizeof(__le16); + } else { + len = cifs_strtoUTF16((__le16 *)*pcur, + str_value, + str_length, + nls_cp); + len *= sizeof(__le16); + pbuf->BufferOffset = cpu_to_le32(*pcur - pstart); + pbuf->Length = cpu_to_le16(len); + pbuf->MaximumLength = cpu_to_le16(len); + *pcur += len; + } +} + /* BB Move to ntlmssp.c eventually */ -/* We do not malloc the blob, it is passed in pbuffer, because - it is fixed size, and small, making this approach cleaner */ -void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, - struct cifs_ses *ses) +int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, + u16 *buflen, + struct cifs_ses *ses, + const struct nls_table *nls_cp) { + int rc = 0; struct TCP_Server_Info *server = cifs_ses_server(ses); - NEGOTIATE_MESSAGE *sec_blob = (NEGOTIATE_MESSAGE *)pbuffer; + NEGOTIATE_MESSAGE *sec_blob; __u32 flags; + unsigned char *tmp; + int len; + + len = size_of_ntlmssp_blob(ses, sizeof(NEGOTIATE_MESSAGE)); + *pbuffer = kmalloc(len, GFP_KERNEL); + if (!*pbuffer) { + rc = -ENOMEM; + cifs_dbg(VFS, "Error %d during NTLMSSP allocation\n", rc); + *buflen = 0; + goto setup_ntlm_neg_ret; + } + sec_blob = (NEGOTIATE_MESSAGE *)*pbuffer; - memset(pbuffer, 0, sizeof(NEGOTIATE_MESSAGE)); + memset(*pbuffer, 0, sizeof(NEGOTIATE_MESSAGE)); memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmNegotiate; @@ -624,34 +713,25 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, if (!server->session_estab || ses->ntlmssp->sesskey_per_smbsess) flags |= NTLMSSP_NEGOTIATE_KEY_XCH; + tmp = *pbuffer + sizeof(NEGOTIATE_MESSAGE); sec_blob->NegotiateFlags = cpu_to_le32(flags); - sec_blob->WorkstationName.BufferOffset = 0; - sec_blob->WorkstationName.Length = 0; - sec_blob->WorkstationName.MaximumLength = 0; + /* these fields should be null in negotiate phase MS-NLMP 3.1.5.1.1 */ + cifs_security_buffer_from_str(&sec_blob->DomainName, + NULL, + CIFS_MAX_DOMAINNAME_LEN, + *pbuffer, &tmp, + nls_cp); - /* Domain name is sent on the Challenge not Negotiate NTLMSSP request */ - sec_blob->DomainName.BufferOffset = 0; - sec_blob->DomainName.Length = 0; - sec_blob->DomainName.MaximumLength = 0; -} - -static int size_of_ntlmssp_blob(struct cifs_ses *ses) -{ - int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len - - CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2; - - if (ses->domainName) - sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN); - else - sz += 2; - - if (ses->user_name) - sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN); - else - sz += 2; + cifs_security_buffer_from_str(&sec_blob->WorkstationName, + NULL, + CIFS_MAX_WORKSTATION_LEN, + *pbuffer, &tmp, + nls_cp); - return sz; + *buflen = tmp - *pbuffer; +setup_ntlm_neg_ret: + return rc; } int build_ntlmssp_auth_blob(unsigned char **pbuffer, @@ -663,6 +743,7 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, AUTHENTICATE_MESSAGE *sec_blob; __u32 flags; unsigned char *tmp; + int len; rc = setup_ntlmv2_rsp(ses, nls_cp); if (rc) { @@ -670,7 +751,9 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, *buflen = 0; goto setup_ntlmv2_ret; } - *pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL); + + len = size_of_ntlmssp_blob(ses, sizeof(AUTHENTICATE_MESSAGE)); + *pbuffer = kmalloc(len, GFP_KERNEL); if (!*pbuffer) { rc = -ENOMEM; cifs_dbg(VFS, "Error %d during NTLMSSP allocation\n", rc); @@ -686,7 +769,7 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO | NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC | - NTLMSSP_NEGOTIATE_SEAL; + NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED; if (ses->server->sign) flags |= NTLMSSP_NEGOTIATE_SIGN; if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) @@ -719,42 +802,23 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, sec_blob->NtChallengeResponse.MaximumLength = 0; } - if (ses->domainName == NULL) { - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->DomainName.Length = 0; - sec_blob->DomainName.MaximumLength = 0; - tmp += 2; - } else { - int len; - len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName, - CIFS_MAX_DOMAINNAME_LEN, nls_cp); - len *= 2; /* unicode is 2 bytes each */ - sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->DomainName.Length = cpu_to_le16(len); - sec_blob->DomainName.MaximumLength = cpu_to_le16(len); - tmp += len; - } + cifs_security_buffer_from_str(&sec_blob->DomainName, + ses->domainName, + CIFS_MAX_DOMAINNAME_LEN, + *pbuffer, &tmp, + nls_cp); - if (ses->user_name == NULL) { - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->UserName.Length = 0; - sec_blob->UserName.MaximumLength = 0; - tmp += 2; - } else { - int len; - len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name, - CIFS_MAX_USERNAME_LEN, nls_cp); - len *= 2; /* unicode is 2 bytes each */ - sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->UserName.Length = cpu_to_le16(len); - sec_blob->UserName.MaximumLength = cpu_to_le16(len); - tmp += len; - } + cifs_security_buffer_from_str(&sec_blob->UserName, + ses->user_name, + CIFS_MAX_USERNAME_LEN, + *pbuffer, &tmp, + nls_cp); - sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer); - sec_blob->WorkstationName.Length = 0; - sec_blob->WorkstationName.MaximumLength = 0; - tmp += 2; + cifs_security_buffer_from_str(&sec_blob->WorkstationName, + ses->workstation_name, + CIFS_MAX_WORKSTATION_LEN, + *pbuffer, &tmp, + nls_cp); if (((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) || (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) @@ -1230,6 +1294,7 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data) struct cifs_ses *ses = sess_data->ses; __u16 bytes_remaining; char *bcc_ptr; + unsigned char *ntlmsspblob = NULL; u16 blob_len; cifs_dbg(FYI, "rawntlmssp session setup negotiate phase\n"); @@ -1253,10 +1318,15 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data) pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; /* Build security blob before we assemble the request */ - build_ntlmssp_negotiate_blob(pSMB->req.SecurityBlob, ses); - sess_data->iov[1].iov_len = sizeof(NEGOTIATE_MESSAGE); - sess_data->iov[1].iov_base = pSMB->req.SecurityBlob; - pSMB->req.SecurityBlobLength = cpu_to_le16(sizeof(NEGOTIATE_MESSAGE)); + rc = build_ntlmssp_negotiate_blob(&ntlmsspblob, + &blob_len, ses, + sess_data->nls_cp); + if (rc) + goto out; + + sess_data->iov[1].iov_len = blob_len; + sess_data->iov[1].iov_base = ntlmsspblob; + pSMB->req.SecurityBlobLength = cpu_to_le16(blob_len); rc = _sess_auth_rawntlmssp_assemble_req(sess_data); if (rc) diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 8297703492ee..fe5bfa245fa7 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -46,6 +46,10 @@ struct cop_vars { struct smb2_file_link_info link_info; }; +/* + * note: If cfile is passed, the reference to it is dropped here. + * So make sure that you do not reuse cfile after return from this func. + */ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, @@ -536,10 +540,11 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ + cifs_get_readable_path(tcon, full_path, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_QUERY_INFO, NULL); + smb2_data, SMB2_OP_QUERY_INFO, cfile); } if (rc) goto out; @@ -587,10 +592,11 @@ smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ + cifs_get_readable_path(tcon, full_path, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_POSIX_QUERY_INFO, NULL); + smb2_data, SMB2_OP_POSIX_QUERY_INFO, cfile); } if (rc) goto out; @@ -707,10 +713,12 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, bool set_alloc) { __le64 eof = cpu_to_le64(size); + struct cifsFileInfo *cfile; + cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); return smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE, - &eof, SMB2_OP_SET_EOF, NULL); + &eof, SMB2_OP_SET_EOF, cfile); } int @@ -719,6 +727,8 @@ smb2_set_file_info(struct inode *inode, const char *full_path, { struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink; + struct cifs_tcon *tcon; + struct cifsFileInfo *cfile; int rc; if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) && @@ -729,10 +739,12 @@ smb2_set_file_info(struct inode *inode, const char *full_path, tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); - rc = smb2_compound_op(xid, tlink_tcon(tlink), cifs_sb, full_path, + cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_ATTRIBUTES, FILE_OPEN, - 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, NULL); + 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile); cifs_put_tlink(tlink); return rc; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 7acf71defea7..c5b1dea54ebc 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2844,6 +2844,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, struct fsctl_get_dfs_referral_req *dfs_req = NULL; struct get_dfs_referral_rsp *dfs_rsp = NULL; u32 dfs_req_size = 0, dfs_rsp_size = 0; + int retry_count = 0; cifs_dbg(FYI, "%s: path: %s\n", __func__, search_name); @@ -2895,11 +2896,14 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, true /* is_fsctl */, (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); - } while (rc == -EAGAIN); + if (!is_retryable_error(rc)) + break; + usleep_range(512, 2048); + } while (++retry_count < 5); if (rc) { - if ((rc != -ENOENT) && (rc != -EOPNOTSUPP)) - cifs_tcon_dbg(VFS, "ioctl error in %s rc=%d\n", __func__, rc); + if (!is_retryable_error(rc) && rc != -ENOENT && rc != -EOPNOTSUPP) + cifs_tcon_dbg(VFS, "%s: ioctl error: rc=%d\n", __func__, rc); goto out; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index d2ecb2ea37c0..2f5f2c4c6183 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -155,7 +155,11 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, if (tcon == NULL) return 0; - if (smb2_command == SMB2_TREE_CONNECT) + /* + * Need to also skip SMB2_IOCTL because it is used for checking nested dfs links in + * cifs_tree_connect(). + */ + if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL) return 0; if (tcon->tidStatus == CifsExiting) { @@ -253,7 +257,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, /* * If we are reconnecting an extra channel, bind */ - if (server->is_channel) { + if (CIFS_SERVER_IS_CHAN(server)) { ses->binding = true; ses->binding_chan = cifs_ses_find_chan(ses, server); } @@ -1456,7 +1460,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) int rc; struct cifs_ses *ses = sess_data->ses; struct smb2_sess_setup_rsp *rsp = NULL; - char *ntlmssp_blob = NULL; + unsigned char *ntlmssp_blob = NULL; bool use_spnego = false; /* else use raw ntlmssp */ u16 blob_length = 0; @@ -1475,22 +1479,17 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data) if (rc) goto out_err; - ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE), - GFP_KERNEL); - if (ntlmssp_blob == NULL) { - rc = -ENOMEM; - goto out; - } + rc = build_ntlmssp_negotiate_blob(&ntlmssp_blob, + &blob_length, ses, + sess_data->nls_cp); + if (rc) + goto out_err; - build_ntlmssp_negotiate_blob(ntlmssp_blob, ses); if (use_spnego) { /* BB eventually need to add this */ cifs_dbg(VFS, "spnego not supported for SMB2 yet\n"); rc = -EOPNOTSUPP; goto out; - } else { - blob_length = sizeof(struct _NEGOTIATE_MESSAGE); - /* with raw NTLMSSP we don't encapsulate in SPNEGO */ } sess_data->iov[1].iov_base = ntlmssp_blob; sess_data->iov[1].iov_len = blob_length; @@ -1841,7 +1840,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, cifs_small_buf_release(req); rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base; trace_smb3_tcon(xid, tcon->tid, ses->Suid, tree, rc); - if (rc != 0) { + if ((rc != 0) || (rsp == NULL)) { cifs_stats_fail_inc(tcon, SMB2_TREE_CONNECT_HE); tcon->need_reconnect = true; goto tcon_error_exit; @@ -2669,7 +2668,18 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, goto err_free_rsp_buf; } + /* + * Although unlikely to be possible for rsp to be null and rc not set, + * adding check below is slightly safer long term (and quiets Coverity + * warning) + */ rsp = (struct smb2_create_rsp *)rsp_iov.iov_base; + if (rsp == NULL) { + rc = -EIO; + kfree(pc_buf); + goto err_free_req; + } + trace_smb3_posix_mkdir_done(xid, le64_to_cpu(rsp->PersistentFileId), tcon->tid, ses->Suid, CREATE_NOT_FILE, @@ -2942,7 +2952,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, tcon->need_reconnect = true; } goto creat_exit; - } else + } else if (rsp == NULL) /* unlikely to happen, but safer to check */ + goto creat_exit; + else trace_smb3_open_done(xid, le64_to_cpu(rsp->PersistentFileId), tcon->tid, ses->Suid, oparms->create_options, @@ -3163,6 +3175,16 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, if ((plen == NULL) || (out_data == NULL)) goto ioctl_exit; + /* + * Although unlikely to be possible for rsp to be null and rc not set, + * adding check below is slightly safer long term (and quiets Coverity + * warning) + */ + if (rsp == NULL) { + rc = -EIO; + goto ioctl_exit; + } + *plen = le32_to_cpu(rsp->OutputCount); /* We check for obvious errors in the output buffer length and offset */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b7379329b741..61ea3d3f95b4 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -1044,14 +1044,17 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) if (!ses) return NULL; + spin_lock(&ses->chan_lock); if (!ses->binding) { /* round robin */ if (ses->chan_count > 1) { index = (uint)atomic_inc_return(&ses->chan_seq); index %= ses->chan_count; } + spin_unlock(&ses->chan_lock); return ses->chans[index].server; } else { + spin_unlock(&ses->chan_lock); return cifs_ses_server(ses); } } diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index bcb1b91b234f..9a249bfc2770 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -96,16 +96,9 @@ static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl) DBG_BUGON(1); } -/* - * a compressed_pages[] placeholder in order to avoid - * being filled with file pages for in-place decompression. - */ -#define PAGE_UNALLOCATED ((void *)0x5F0E4B1D) - /* how to allocate cached pages for a pcluster */ enum z_erofs_cache_alloctype { DONTALLOC, /* don't allocate any cached pages */ - DELAYEDALLOC, /* delayed allocation (at the time of submitting io) */ /* * try to use cached I/O if page allocation succeeds or fallback * to in-place I/O instead to avoid any direct reclaim. @@ -267,10 +260,6 @@ static void preload_compressed_pages(struct z_erofs_collector *clt, /* I/O is needed, no possible to decompress directly */ standalone = false; switch (type) { - case DELAYEDALLOC: - t = tagptr_init(compressed_page_t, - PAGE_UNALLOCATED); - break; case TRYALLOC: newpage = erofs_allocpage(pagepool, gfp); if (!newpage) @@ -371,8 +360,8 @@ static bool z_erofs_try_inplace_io(struct z_erofs_collector *clt, /* callers must be with collection lock held */ static int z_erofs_attach_page(struct z_erofs_collector *clt, - struct page *page, - enum z_erofs_page_type type) + struct page *page, enum z_erofs_page_type type, + bool pvec_safereuse) { int ret; @@ -382,9 +371,9 @@ static int z_erofs_attach_page(struct z_erofs_collector *clt, z_erofs_try_inplace_io(clt, page)) return 0; - ret = z_erofs_pagevec_enqueue(&clt->vector, page, type); + ret = z_erofs_pagevec_enqueue(&clt->vector, page, type, + pvec_safereuse); clt->cl->vcnt += (unsigned int)ret; - return ret ? 0 : -EAGAIN; } @@ -727,7 +716,8 @@ hitted: tight &= (clt->mode >= COLLECT_PRIMARY_FOLLOWED); retry: - err = z_erofs_attach_page(clt, page, page_type); + err = z_erofs_attach_page(clt, page, page_type, + clt->mode >= COLLECT_PRIMARY_FOLLOWED); /* should allocate an additional short-lived page for pagevec */ if (err == -EAGAIN) { struct page *const newpage = @@ -735,7 +725,7 @@ retry: set_page_private(newpage, Z_EROFS_SHORTLIVED_PAGE); err = z_erofs_attach_page(clt, newpage, - Z_EROFS_PAGE_TYPE_EXCLUSIVE); + Z_EROFS_PAGE_TYPE_EXCLUSIVE, true); if (!err) goto retry; } @@ -1089,15 +1079,6 @@ repeat: if (!page) goto out_allocpage; - /* - * the cached page has not been allocated and - * an placeholder is out there, prepare it now. - */ - if (page == PAGE_UNALLOCATED) { - tocache = true; - goto out_allocpage; - } - /* process the target tagged pointer */ t = tagptr_init(compressed_page_t, page); justfound = tagptr_unfold_tags(t); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index 879df5362777..4a69515dea75 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -179,4 +179,3 @@ static inline void z_erofs_onlinepage_endio(struct page *page) #define Z_EROFS_VMAP_GLOBAL_PAGES 2048 #endif - diff --git a/fs/erofs/zpvec.h b/fs/erofs/zpvec.h index dfd7fe0503bb..b05464f4a808 100644 --- a/fs/erofs/zpvec.h +++ b/fs/erofs/zpvec.h @@ -106,11 +106,18 @@ static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor, static inline bool z_erofs_pagevec_enqueue(struct z_erofs_pagevec_ctor *ctor, struct page *page, - enum z_erofs_page_type type) + enum z_erofs_page_type type, + bool pvec_safereuse) { - if (!ctor->next && type) - if (ctor->index + 1 == ctor->nr) + if (!ctor->next) { + /* some pages cannot be reused as pvec safely without I/O */ + if (type == Z_EROFS_PAGE_TYPE_EXCLUSIVE && !pvec_safereuse) + type = Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED; + + if (type != Z_EROFS_PAGE_TYPE_EXCLUSIVE && + ctor->index + 1 == ctor->nr) return false; + } if (ctor->index >= ctor->nr) z_erofs_pagevec_ctor_pagedown(ctor, false); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 83e9bc0f91ff..f1693d45bb78 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -653,7 +653,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) return PTR_ERR(inode); } - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) { iput(inode); goto err_out; @@ -705,9 +705,6 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) } #ifdef CONFIG_QUOTA - /* Needed for iput() to work correctly and not trash data */ - sbi->sb->s_flags |= SB_ACTIVE; - /* * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. @@ -1162,7 +1159,8 @@ static bool __need_flush_quota(struct f2fs_sb_info *sbi) if (!is_journalled_quota(sbi)) return false; - down_write(&sbi->quota_sem); + if (!down_write_trylock(&sbi->quota_sem)) + return true; if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) { ret = false; } else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) { diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 20a083dc9042..49121a21f749 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -336,8 +336,8 @@ static const struct f2fs_compress_ops f2fs_lz4_ops = { static int zstd_init_compress_ctx(struct compress_ctx *cc) { - ZSTD_parameters params; - ZSTD_CStream *stream; + zstd_parameters params; + zstd_cstream *stream; void *workspace; unsigned int workspace_size; unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> @@ -346,17 +346,17 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) if (!level) level = F2FS_ZSTD_DEFAULT_CLEVEL; - params = ZSTD_getParams(level, cc->rlen, 0); - workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams); + params = zstd_get_params(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen); + workspace_size = zstd_cstream_workspace_bound(¶ms.cParams); workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode), workspace_size, GFP_NOFS); if (!workspace) return -ENOMEM; - stream = ZSTD_initCStream(params, 0, workspace, workspace_size); + stream = zstd_init_cstream(¶ms, 0, workspace, workspace_size); if (!stream) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initCStream failed\n", + printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_cstream failed\n", KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, __func__); kvfree(workspace); @@ -379,9 +379,9 @@ static void zstd_destroy_compress_ctx(struct compress_ctx *cc) static int zstd_compress_pages(struct compress_ctx *cc) { - ZSTD_CStream *stream = cc->private2; - ZSTD_inBuffer inbuf; - ZSTD_outBuffer outbuf; + zstd_cstream *stream = cc->private2; + zstd_in_buffer inbuf; + zstd_out_buffer outbuf; int src_size = cc->rlen; int dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE; int ret; @@ -394,19 +394,19 @@ static int zstd_compress_pages(struct compress_ctx *cc) outbuf.dst = cc->cbuf->cdata; outbuf.size = dst_size; - ret = ZSTD_compressStream(stream, &outbuf, &inbuf); - if (ZSTD_isError(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n", + ret = zstd_compress_stream(stream, &outbuf, &inbuf); + if (zstd_is_error(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s zstd_compress_stream failed, ret: %d\n", KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, - __func__, ZSTD_getErrorCode(ret)); + __func__, zstd_get_error_code(ret)); return -EIO; } - ret = ZSTD_endStream(stream, &outbuf); - if (ZSTD_isError(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_endStream returned %d\n", + ret = zstd_end_stream(stream, &outbuf); + if (zstd_is_error(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s zstd_end_stream returned %d\n", KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, - __func__, ZSTD_getErrorCode(ret)); + __func__, zstd_get_error_code(ret)); return -EIO; } @@ -423,22 +423,22 @@ static int zstd_compress_pages(struct compress_ctx *cc) static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) { - ZSTD_DStream *stream; + zstd_dstream *stream; void *workspace; unsigned int workspace_size; unsigned int max_window_size = MAX_COMPRESS_WINDOW_SIZE(dic->log_cluster_size); - workspace_size = ZSTD_DStreamWorkspaceBound(max_window_size); + workspace_size = zstd_dstream_workspace_bound(max_window_size); workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode), workspace_size, GFP_NOFS); if (!workspace) return -ENOMEM; - stream = ZSTD_initDStream(max_window_size, workspace, workspace_size); + stream = zstd_init_dstream(max_window_size, workspace, workspace_size); if (!stream) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initDStream failed\n", + printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_dstream failed\n", KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, __func__); kvfree(workspace); @@ -460,9 +460,9 @@ static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic) static int zstd_decompress_pages(struct decompress_io_ctx *dic) { - ZSTD_DStream *stream = dic->private2; - ZSTD_inBuffer inbuf; - ZSTD_outBuffer outbuf; + zstd_dstream *stream = dic->private2; + zstd_in_buffer inbuf; + zstd_out_buffer outbuf; int ret; inbuf.pos = 0; @@ -473,11 +473,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic) outbuf.dst = dic->rbuf; outbuf.size = dic->rlen; - ret = ZSTD_decompressStream(stream, &outbuf, &inbuf); - if (ZSTD_isError(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n", + ret = zstd_decompress_stream(stream, &outbuf, &inbuf); + if (zstd_is_error(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s zstd_decompress_stream failed, ret: %d\n", KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, - __func__, ZSTD_getErrorCode(ret)); + __func__, zstd_get_error_code(ret)); return -EIO; } @@ -882,6 +882,25 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index) return is_page_in_cluster(cc, index); } +bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec, + int index, int nr_pages) +{ + unsigned long pgidx; + int i; + + if (nr_pages - index < cc->cluster_size) + return false; + + pgidx = pvec->pages[index]->index; + + for (i = 1; i < cc->cluster_size; i++) { + if (pvec->pages[index + i]->index != pgidx + i) + return false; + } + + return true; +} + static bool cluster_has_invalid_data(struct compress_ctx *cc) { loff_t i_size = i_size_read(cc->inode); @@ -1531,6 +1550,7 @@ int f2fs_write_multi_pages(struct compress_ctx *cc, if (cluster_may_compress(cc)) { err = f2fs_compress_pages(cc); if (err == -EAGAIN) { + add_compr_block_stat(cc->inode, cc->cluster_size); goto write; } else if (err) { f2fs_put_rpages_wbc(cc, wbc, true, 1); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f4fd6c246c9a..9f754aaef558 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1465,10 +1465,15 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, struct extent_info ei = {0, }; block_t blkaddr; unsigned int start_pgofs; + int bidx = 0; if (!maxblocks) return 0; + map->m_bdev = inode->i_sb->s_bdev; + map->m_multidev_dio = + f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag); + map->m_len = 0; map->m_flags = 0; @@ -1491,6 +1496,21 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, if (flag == F2FS_GET_BLOCK_DIO) f2fs_wait_on_block_writeback_range(inode, map->m_pblk, map->m_len); + + if (map->m_multidev_dio) { + block_t blk_addr = map->m_pblk; + + bidx = f2fs_target_device_index(sbi, map->m_pblk); + + map->m_bdev = FDEV(bidx).bdev; + map->m_pblk -= FDEV(bidx).start_blk; + map->m_len = min(map->m_len, + FDEV(bidx).end_blk + 1 - map->m_pblk); + + if (map->m_may_create) + f2fs_update_device_state(sbi, inode->i_ino, + blk_addr, map->m_len); + } goto out; } @@ -1609,6 +1629,9 @@ next_block: if (flag == F2FS_GET_BLOCK_PRE_AIO) goto skip; + if (map->m_multidev_dio) + bidx = f2fs_target_device_index(sbi, blkaddr); + if (map->m_len == 0) { /* preallocated unwritten block should be mapped for fiemap. */ if (blkaddr == NEW_ADDR) @@ -1617,10 +1640,15 @@ next_block: map->m_pblk = blkaddr; map->m_len = 1; + + if (map->m_multidev_dio) + map->m_bdev = FDEV(bidx).bdev; } else if ((map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs)) || (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) || flag == F2FS_GET_BLOCK_PRE_DIO) { + if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev) + goto sync_out; ofs++; map->m_len++; } else { @@ -1673,10 +1701,32 @@ skip: sync_out: - /* for hardware encryption, but to avoid potential issue in future */ - if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) + if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) { + /* + * for hardware encryption, but to avoid potential issue + * in future + */ f2fs_wait_on_block_writeback_range(inode, map->m_pblk, map->m_len); + invalidate_mapping_pages(META_MAPPING(sbi), + map->m_pblk, map->m_pblk); + + if (map->m_multidev_dio) { + block_t blk_addr = map->m_pblk; + + bidx = f2fs_target_device_index(sbi, map->m_pblk); + + map->m_bdev = FDEV(bidx).bdev; + map->m_pblk -= FDEV(bidx).start_blk; + + if (map->m_may_create) + f2fs_update_device_state(sbi, inode->i_ino, + blk_addr, map->m_len); + + f2fs_bug_on(sbi, blk_addr + map->m_len > + FDEV(bidx).end_blk + 1); + } + } if (flag == F2FS_GET_BLOCK_PRECACHE) { if (map->m_flags & F2FS_MAP_MAPPED) { @@ -1696,7 +1746,7 @@ unlock_out: f2fs_balance_fs(sbi, dn.node_changed); } out: - trace_f2fs_map_blocks(inode, map, err); + trace_f2fs_map_blocks(inode, map, create, flag, err); return err; } @@ -1755,6 +1805,9 @@ static int __get_data_block(struct inode *inode, sector_t iblock, map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags; bh->b_size = blks_to_bytes(inode, map.m_len); + + if (map.m_multidev_dio) + bh->b_bdev = map.m_bdev; } return err; } @@ -2989,6 +3042,10 @@ readd: need_readd = false; #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { + void *fsdata = NULL; + struct page *pagep; + int ret2; + ret = f2fs_init_compress_ctx(&cc); if (ret) { done = 1; @@ -3007,27 +3064,23 @@ readd: if (unlikely(f2fs_cp_error(sbi))) goto lock_page; - if (f2fs_cluster_is_empty(&cc)) { - void *fsdata = NULL; - struct page *pagep; - int ret2; + if (!f2fs_cluster_is_empty(&cc)) + goto lock_page; - ret2 = f2fs_prepare_compress_overwrite( + ret2 = f2fs_prepare_compress_overwrite( inode, &pagep, page->index, &fsdata); - if (ret2 < 0) { - ret = ret2; - done = 1; - break; - } else if (ret2 && - !f2fs_compress_write_end(inode, - fsdata, page->index, - 1)) { - retry = 1; - break; - } - } else { - goto lock_page; + if (ret2 < 0) { + ret = ret2; + done = 1; + break; + } else if (ret2 && + (!f2fs_compress_write_end(inode, + fsdata, page->index, 1) || + !f2fs_all_cluster_page_loaded(&cc, + &pvec, i, nr_pages))) { + retry = 1; + break; } } #endif diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b339ae89c1ad..ce9fc9f13000 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -55,6 +55,7 @@ enum { FAULT_DISCARD, FAULT_WRITE_IO, FAULT_SLAB_ALLOC, + FAULT_DQUOT_INIT, FAULT_MAX, }; @@ -561,6 +562,9 @@ enum { #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ +/* dirty segments threshold for triggering CP */ +#define DEFAULT_DIRTY_THRESHOLD 4 + /* for in-memory extent cache entry */ #define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ @@ -617,6 +621,7 @@ struct extent_tree { F2FS_MAP_UNWRITTEN) struct f2fs_map_blocks { + struct block_device *m_bdev; /* for multi-device dio */ block_t m_pblk; block_t m_lblk; unsigned int m_len; @@ -625,6 +630,7 @@ struct f2fs_map_blocks { pgoff_t *m_next_extent; /* point to next possible extent */ int m_seg_type; bool m_may_create; /* indicate it is from write path */ + bool m_multidev_dio; /* indicate it allows multi-device dio */ }; /* for flag in get_data_block */ @@ -1284,8 +1290,10 @@ enum { }; enum { - FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ - FS_MODE_LFS, /* use lfs allocation only */ + FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ + FS_MODE_LFS, /* use lfs allocation only */ + FS_MODE_FRAGMENT_SEG, /* segment fragmentation mode */ + FS_MODE_FRAGMENT_BLK, /* block fragmentation mode */ }; enum { @@ -1728,12 +1736,15 @@ struct f2fs_sb_info { /* For shrinker support */ struct list_head s_list; + struct mutex umount_mutex; + unsigned int shrinker_run_no; + + /* For multi devices */ int s_ndevs; /* number of devices */ struct f2fs_dev_info *devs; /* for device list */ unsigned int dirty_device; /* for checkpoint data flush */ spinlock_t dev_lock; /* protect dirty_device */ - struct mutex umount_mutex; - unsigned int shrinker_run_no; + bool aligned_blksize; /* all devices has the same logical blksize */ /* For write statistics */ u64 sectors_written_start; @@ -1756,6 +1767,9 @@ struct f2fs_sb_info { unsigned long seq_file_ra_mul; /* multiplier for ra_pages of seq. files in fadvise */ + int max_fragment_chunk; /* max chunk size for block fragmentation mode */ + int max_fragment_hole; /* max hole size for block fragmentation mode */ + #ifdef CONFIG_F2FS_FS_COMPRESSION struct kmem_cache *page_array_slab; /* page array entry */ unsigned int page_array_slab_size; /* default page array slab size */ @@ -3363,6 +3377,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) */ int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); +int f2fs_dquot_initialize(struct inode *inode); int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); int f2fs_quota_sync(struct super_block *sb, int type); loff_t max_file_blocks(struct inode *inode); @@ -3492,6 +3507,8 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio); +void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino, + block_t blkaddr, unsigned int blkcnt); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered, bool locked); void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); @@ -3516,6 +3533,16 @@ unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, unsigned int segno); +#define DEF_FRAGMENT_SIZE 4 +#define MIN_FRAGMENT_SIZE 1 +#define MAX_FRAGMENT_SIZE 512 + +static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi) +{ + return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG || + F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK; +} + /* * checkpoint.c */ @@ -4027,6 +4054,8 @@ void f2fs_end_read_compressed_page(struct page *page, bool failed, block_t blkaddr); bool f2fs_cluster_is_empty(struct compress_ctx *cc); bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index); +bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec, + int index, int nr_pages); bool f2fs_sanity_check_cluster(struct dnode_of_data *dn); void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page); int f2fs_write_multi_pages(struct compress_ctx *cc, @@ -4152,8 +4181,7 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) if (!f2fs_compressed_file(inode)) return true; - if (S_ISREG(inode->i_mode) && - (get_dirty_pages(inode) || atomic_read(&fi->i_compr_blocks))) + if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) return false; fi->i_flags &= ~F2FS_COMPR_FL; @@ -4302,6 +4330,16 @@ static inline int block_unaligned_IO(struct inode *inode, return align & blocksize_mask; } +static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, + int flag) +{ + if (!f2fs_is_multi_device(sbi)) + return false; + if (flag != F2FS_GET_BLOCK_DIO) + return false; + return sbi->aligned_blksize; +} + static inline bool f2fs_force_buffered_io(struct inode *inode, struct kiocb *iocb, struct iov_iter *iter) { @@ -4310,7 +4348,9 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, if (f2fs_post_read_required(inode)) return true; - if (f2fs_is_multi_device(sbi)) + + /* disallow direct IO if any of devices has unaligned blksize */ + if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) return true; /* * for blkzoned device, fallback direct IO to buffered IO, so diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index eb971e1e7227..92ec2699bc85 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -786,7 +786,7 @@ int f2fs_truncate(struct inode *inode) return -EIO; } - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; @@ -916,7 +916,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, return err; if (is_quota_modification(inode, attr)) { - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; } @@ -3020,7 +3020,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid) } f2fs_put_page(ipage, 1); - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 77391e3b7d68..a946ce0ead34 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -14,6 +14,7 @@ #include <linux/delay.h> #include <linux/freezer.h> #include <linux/sched/signal.h> +#include <linux/random.h> #include "f2fs.h" #include "node.h" @@ -257,7 +258,9 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, p->max_search = sbi->max_victim_search; /* let's select beginning hot/small space first in no_heap mode*/ - if (test_opt(sbi, NOHEAP) && + if (f2fs_need_rand_seg(sbi)) + p->offset = prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec); + else if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) p->offset = 0; else diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 56a20d5c15da..ea08f0dfa1bd 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -192,7 +192,7 @@ int f2fs_convert_inline_inode(struct inode *inode) f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb)) return 0; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 9141147b5bb0..0f8b2df3e1e0 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -527,7 +527,7 @@ make_now: inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - inode_nohighmem(inode); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); } else if (S_ISLNK(inode->i_mode)) { if (file_is_encrypt(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; @@ -754,7 +754,7 @@ void f2fs_evict_inode(struct inode *inode) if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) { err = 0; set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 9c528e583c9d..a728a0af9ce0 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -74,7 +74,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (err) goto fail_drop; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) goto fail_drop; @@ -345,7 +345,7 @@ static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -404,7 +404,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, F2FS_I(old_dentry->d_inode)->i_projid))) return -EXDEV; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -460,7 +460,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) return 0; } - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -598,10 +598,10 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) goto fail; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) goto fail; @@ -675,7 +675,7 @@ static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -746,7 +746,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (unlikely(f2fs_cp_error(sbi))) return -EIO; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -757,7 +757,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - inode_nohighmem(inode); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); @@ -803,7 +803,7 @@ static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -841,7 +841,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, struct inode *inode; int err; - err = dquot_initialize(dir); + err = f2fs_dquot_initialize(dir); if (err) return err; @@ -965,16 +965,16 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, return err; } - err = dquot_initialize(old_dir); + err = f2fs_dquot_initialize(old_dir); if (err) goto out; - err = dquot_initialize(new_dir); + err = f2fs_dquot_initialize(new_dir); if (err) goto out; if (new_inode) { - err = dquot_initialize(new_inode); + err = f2fs_dquot_initialize(new_inode); if (err) goto out; } @@ -1138,11 +1138,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, F2FS_I(new_dentry->d_inode)->i_projid))) return -EXDEV; - err = dquot_initialize(old_dir); + err = f2fs_dquot_initialize(old_dir); if (err) goto out; - err = dquot_initialize(new_dir); + err = f2fs_dquot_initialize(new_dir); if (err) goto out; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e863136081b4..556fcd8457f3 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1443,6 +1443,7 @@ page_hit: nid, nid_of_node(page), ino_of_node(page), ofs_of_node(page), cpver_of_node(page), next_blkaddr_of_node(page)); + set_sbi_flag(sbi, SBI_NEED_FSCK); err = -EINVAL; out_err: ClearPageUptodate(page); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index ff14a6e5ac1c..18b98cf0465b 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -138,11 +138,6 @@ static inline bool excess_cached_nats(struct f2fs_sb_info *sbi) return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD; } -static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi) -{ - return get_pages(sbi, F2FS_DIRTY_NODES) >= sbi->blocks_per_seg * 8; -} - enum mem_type { FREE_NIDS, /* indicates the free nid list */ NAT_ENTRIES, /* indicates the cached nat entry */ diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 04655511d7f5..6a1b4668d933 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -81,7 +81,7 @@ static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi, if (IS_ERR(inode)) return ERR_CAST(inode); - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) goto err_out; @@ -203,7 +203,7 @@ retry: goto out_put; } - err = dquot_initialize(einode); + err = f2fs_dquot_initialize(einode); if (err) { iput(einode); goto out_put; @@ -508,7 +508,7 @@ got_it: if (IS_ERR(inode)) return PTR_ERR(inode); - ret = dquot_initialize(inode); + ret = f2fs_dquot_initialize(inode); if (ret) { iput(inode); return ret; @@ -787,8 +787,6 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) } #ifdef CONFIG_QUOTA - /* Needed for iput() to work correctly and not trash data */ - sbi->sb->s_flags |= SB_ACTIVE; /* Turn on quotas so that they are updated correctly */ quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY); #endif @@ -816,10 +814,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); - else { - /* restore s_flags to let iput() trash data */ - sbi->sb->s_flags = s_flags; - } + else + f2fs_bug_on(sbi, sbi->sb->s_flags & SB_ACTIVE); skip: fix_curseg_write_pointer = !check_only || list_empty(&inode_list); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a135d2247415..df9ed75f0b7a 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -15,6 +15,7 @@ #include <linux/timer.h> #include <linux/freezer.h> #include <linux/sched/signal.h> +#include <linux/random.h> #include "f2fs.h" #include "segment.h" @@ -529,6 +530,25 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) } } +static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi) +{ + int factor = rwsem_is_locked(&sbi->cp_rwsem) ? 3 : 2; + unsigned int dents = get_pages(sbi, F2FS_DIRTY_DENTS); + unsigned int qdata = get_pages(sbi, F2FS_DIRTY_QDATA); + unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES); + unsigned int meta = get_pages(sbi, F2FS_DIRTY_META); + unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA); + unsigned int threshold = sbi->blocks_per_seg * factor * + DEFAULT_DIRTY_THRESHOLD; + unsigned int global_threshold = threshold * 3 / 2; + + if (dents >= threshold || qdata >= threshold || + nodes >= threshold || meta >= threshold || + imeta >= threshold) + return true; + return dents + qdata + nodes + meta + imeta > global_threshold; +} + void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) { if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) @@ -547,8 +567,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) else f2fs_build_free_nids(sbi, false, false); - if (excess_dirty_nats(sbi) || excess_dirty_nodes(sbi) || - excess_prefree_segs(sbi)) + if (excess_dirty_nats(sbi) || excess_dirty_threshold(sbi) || + excess_prefree_segs(sbi) || !f2fs_space_for_roll_forward(sbi)) goto do_sync; /* there is background inflight IO or foreground operation recently */ @@ -561,7 +581,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg) goto do_sync; /* checkpoint is the only way to shrink partial cached entries */ - if (f2fs_available_free_memory(sbi, NAT_ENTRIES) || + if (f2fs_available_free_memory(sbi, NAT_ENTRIES) && f2fs_available_free_memory(sbi, INO_ENTRIES)) return; @@ -2630,6 +2650,8 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) unsigned short seg_type = curseg->seg_type; sanity_check_seg_type(sbi, seg_type); + if (f2fs_need_rand_seg(sbi)) + return prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec); /* if segs_per_sec is large than 1, we need to keep original policy. */ if (__is_large_section(sbi)) @@ -2681,6 +2703,9 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) curseg->next_segno = segno; reset_curseg(sbi, type, 1); curseg->alloc_type = LFS; + if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) + curseg->fragment_remained_chunk = + prandom_u32() % sbi->max_fragment_chunk + 1; } static int __next_free_blkoff(struct f2fs_sb_info *sbi, @@ -2707,12 +2732,22 @@ static int __next_free_blkoff(struct f2fs_sb_info *sbi, static void __refresh_next_blkoff(struct f2fs_sb_info *sbi, struct curseg_info *seg) { - if (seg->alloc_type == SSR) + if (seg->alloc_type == SSR) { seg->next_blkoff = __next_free_blkoff(sbi, seg->segno, seg->next_blkoff + 1); - else + } else { seg->next_blkoff++; + if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) { + /* To allocate block chunks in different sizes, use random number */ + if (--seg->fragment_remained_chunk <= 0) { + seg->fragment_remained_chunk = + prandom_u32() % sbi->max_fragment_chunk + 1; + seg->next_blkoff += + prandom_u32() % sbi->max_fragment_hole + 1; + } + } + } } bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno) @@ -3485,24 +3520,30 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, up_read(&SM_I(sbi)->curseg_lock); } -static void update_device_state(struct f2fs_io_info *fio) +void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino, + block_t blkaddr, unsigned int blkcnt) { - struct f2fs_sb_info *sbi = fio->sbi; - unsigned int devidx; - if (!f2fs_is_multi_device(sbi)) return; - devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); + while (1) { + unsigned int devidx = f2fs_target_device_index(sbi, blkaddr); + unsigned int blks = FDEV(devidx).end_blk - blkaddr + 1; - /* update device state for fsync */ - f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO); + /* update device state for fsync */ + f2fs_set_dirty_device(sbi, ino, devidx, FLUSH_INO); - /* update device state for checkpoint */ - if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { - spin_lock(&sbi->dev_lock); - f2fs_set_bit(devidx, (char *)&sbi->dirty_device); - spin_unlock(&sbi->dev_lock); + /* update device state for checkpoint */ + if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { + spin_lock(&sbi->dev_lock); + f2fs_set_bit(devidx, (char *)&sbi->dirty_device); + spin_unlock(&sbi->dev_lock); + } + + if (blkcnt <= blks) + break; + blkcnt -= blks; + blkaddr += blks; } } @@ -3529,7 +3570,7 @@ reallocate: goto reallocate; } - update_device_state(fio); + f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1); if (keep_order) up_read(&fio->sbi->io_order_lock); @@ -3611,6 +3652,9 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) goto drop_bio; } + invalidate_mapping_pages(META_MAPPING(sbi), + fio->new_blkaddr, fio->new_blkaddr); + stat_inc_inplace_blocks(fio->sbi); if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE))) @@ -3618,7 +3662,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) else err = f2fs_submit_page_bio(fio); if (!err) { - update_device_state(fio); + f2fs_update_device_state(fio->sbi, fio->ino, + fio->new_blkaddr, 1); f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 89fff258727d..46fde9f3f28e 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -314,6 +314,7 @@ struct curseg_info { unsigned short next_blkoff; /* next block offset to write */ unsigned int zone; /* current zone number */ unsigned int next_segno; /* preallocated segment */ + int fragment_remained_chunk; /* remained block size in a chunk for block fragmentation mode */ bool inited; /* indicate inmem log is inited */ }; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index cf049a042482..040b6d02e1d8 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -58,6 +58,7 @@ const char *f2fs_fault_name[FAULT_MAX] = { [FAULT_DISCARD] = "discard error", [FAULT_WRITE_IO] = "write IO error", [FAULT_SLAB_ALLOC] = "slab alloc", + [FAULT_DQUOT_INIT] = "dquot initialize", }; void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, @@ -592,7 +593,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (!level || level > ZSTD_maxCLevel()) { + if (!level || level > zstd_max_clevel()) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; } @@ -817,6 +818,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; } else if (!strcmp(name, "lfs")) { F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; + } else if (!strcmp(name, "fragment:segment")) { + F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_SEG; + } else if (!strcmp(name, "fragment:block")) { + F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_BLK; } else { kfree(name); return -EINVAL; @@ -1292,7 +1297,7 @@ default_check: /* Not pass down write hints if the number of active logs is lesser * than NR_CURSEG_PERSIST_TYPE. */ - if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE) + if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE) F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { @@ -1896,6 +1901,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, "adaptive"); else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS) seq_puts(seq, "lfs"); + else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG) + seq_puts(seq, "fragment:segment"); + else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) + seq_puts(seq, "fragment:block"); seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs); if (test_opt(sbi, RESERVE_ROOT)) seq_printf(seq, ",reserve_root=%u,resuid=%u,resgid=%u", @@ -2491,6 +2500,16 @@ retry: return len - towrite; } +int f2fs_dquot_initialize(struct inode *inode) +{ + if (time_to_inject(F2FS_I_SB(inode), FAULT_DQUOT_INIT)) { + f2fs_show_injection_info(F2FS_I_SB(inode), FAULT_DQUOT_INIT); + return -ESRCH; + } + + return dquot_initialize(inode); +} + static struct dquot **f2fs_get_dquots(struct inode *inode) { return F2FS_I(inode)->i_dquot; @@ -2875,6 +2894,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = { .get_nextdqblk = dquot_get_next_dqblk, }; #else +int f2fs_dquot_initialize(struct inode *inode) +{ + return 0; +} + int f2fs_quota_sync(struct super_block *sb, int type) { return 0; @@ -3486,7 +3510,7 @@ skip_cross: NR_CURSEG_PERSIST_TYPE + nat_bits_blocks >= blocks_per_seg)) { f2fs_warn(sbi, "Insane cp_payload: %u, nat_bits_blocks: %u)", cp_payload, nat_bits_blocks); - return -EFSCORRUPTED; + return 1; } if (unlikely(f2fs_cp_error(sbi))) { @@ -3522,6 +3546,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; sbi->migration_granularity = sbi->segs_per_sec; sbi->seq_file_ra_mul = MIN_RA_MUL; + sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE; + sbi->max_fragment_hole = DEF_FRAGMENT_SIZE; sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; @@ -3746,6 +3772,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); unsigned int max_devices = MAX_DEVICES; + unsigned int logical_blksize; int i; /* Initialize single device information */ @@ -3766,6 +3793,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) if (!sbi->devs) return -ENOMEM; + logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev); + sbi->aligned_blksize = true; + for (i = 0; i < max_devices; i++) { if (i > 0 && !RDEV(i).path[0]) @@ -3802,6 +3832,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) /* to release errored devices */ sbi->s_ndevs = i + 1; + if (logical_blksize != bdev_logical_block_size(FDEV(i).bdev)) + sbi->aligned_blksize = false; + #ifdef CONFIG_BLK_DEV_ZONED if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM && !f2fs_sb_has_blkzoned(sbi)) { @@ -4351,6 +4384,8 @@ free_node_inode: free_stats: f2fs_destroy_stats(sbi); free_nm: + /* stop discard thread before destroying node manager */ + f2fs_stop_discard_thread(sbi); f2fs_destroy_node_manager(sbi); free_sm: f2fs_destroy_segment_manager(sbi); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a32fe31c33b8..7d289249cd7e 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -196,7 +196,7 @@ static ssize_t encoding_show(struct f2fs_attr *a, struct super_block *sb = sbi->sb; if (f2fs_sb_has_casefold(sbi)) - return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n", + return sysfs_emit(buf, "%s (%d.%d.%d)\n", sb->s_encoding->charset, (sb->s_encoding->version >> 16) & 0xff, (sb->s_encoding->version >> 8) & 0xff, @@ -245,7 +245,7 @@ static ssize_t avg_vblocks_show(struct f2fs_attr *a, static ssize_t main_blkaddr_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", (unsigned long long)MAIN_BLKADDR(sbi)); } @@ -551,6 +551,22 @@ out: return count; } + if (!strcmp(a->attr.name, "max_fragment_chunk")) { + if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE) + sbi->max_fragment_chunk = t; + else + return -EINVAL; + return count; + } + + if (!strcmp(a->attr.name, "max_fragment_hole")) { + if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE) + sbi->max_fragment_hole = t; + else + return -EINVAL; + return count; + } + *ui = (unsigned int)t; return count; @@ -781,6 +797,8 @@ F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_threshold, age_threshold); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, seq_file_ra_mul, seq_file_ra_mul); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_segment_mode, gc_segment_mode); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_reclaimed_segments, gc_reclaimed_segs); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_chunk, max_fragment_chunk); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_hole, max_fragment_hole); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -859,6 +877,8 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(seq_file_ra_mul), ATTR_LIST(gc_segment_mode), ATTR_LIST(gc_reclaimed_segments), + ATTR_LIST(max_fragment_chunk), + ATTR_LIST(max_fragment_hole), NULL, }; ATTRIBUTE_GROUPS(f2fs); diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index 03549b5ba204..fe5acdccaae1 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -136,7 +136,7 @@ static int f2fs_begin_enable_verity(struct file *filp) * here and not rely on ->open() doing it. This must be done before * evicting the inline data. */ - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 1d2d29dcd41c..e348f33bcb2b 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -773,7 +773,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = dquot_initialize(inode); + err = f2fs_dquot_initialize(inode); if (err) return err; diff --git a/fs/io-wq.c b/fs/io-wq.c index afd955d53db9..88202de519f6 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -423,9 +423,10 @@ static inline unsigned int io_get_work_hash(struct io_wq_work *work) return work->flags >> IO_WQ_HASH_SHIFT; } -static void io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) +static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) { struct io_wq *wq = wqe->wq; + bool ret = false; spin_lock_irq(&wq->hash->wait.lock); if (list_empty(&wqe->wait.entry)) { @@ -433,9 +434,11 @@ static void io_wait_on_hash(struct io_wqe *wqe, unsigned int hash) if (!test_bit(hash, &wq->hash->map)) { __set_current_state(TASK_RUNNING); list_del_init(&wqe->wait.entry); + ret = true; } } spin_unlock_irq(&wq->hash->wait.lock); + return ret; } static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, @@ -475,14 +478,21 @@ static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct, } if (stall_hash != -1U) { + bool unstalled; + /* * Set this before dropping the lock to avoid racing with new * work being added and clearing the stalled bit. */ set_bit(IO_ACCT_STALLED_BIT, &acct->flags); raw_spin_unlock(&wqe->lock); - io_wait_on_hash(wqe, stall_hash); + unstalled = io_wait_on_hash(wqe, stall_hash); raw_spin_lock(&wqe->lock); + if (unstalled) { + clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + if (wq_has_sleeper(&wqe->wq->hash->wait)) + wake_up(&wqe->wq->hash->wait); + } } return NULL; @@ -564,8 +574,11 @@ get_next: io_wqe_enqueue(wqe, linked); if (hash != -1U && !next_hashed) { + /* serialize hash clear with wake_up() */ + spin_lock_irq(&wq->hash->wait.lock); clear_bit(hash, &wq->hash->map); clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); + spin_unlock_irq(&wq->hash->wait.lock); if (wq_has_sleeper(&wq->hash->wait)) wake_up(&wq->hash->wait); raw_spin_lock(&wqe->lock); diff --git a/fs/ksmbd/Kconfig b/fs/ksmbd/Kconfig index b83cbd756ae5..e1fe17747ed6 100644 --- a/fs/ksmbd/Kconfig +++ b/fs/ksmbd/Kconfig @@ -6,7 +6,6 @@ config SMB_SERVER select NLS select NLS_UTF8 select CRYPTO - select CRYPTO_MD4 select CRYPTO_MD5 select CRYPTO_HMAC select CRYPTO_ECB @@ -19,6 +18,7 @@ config SMB_SERVER select CRYPTO_GCM select ASN1 select OID_REGISTRY + select CRC32 default n help Choose Y here if you want to allow SMB3 compliant clients diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index 30a92ddc1817..3503b1c48cb4 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -873,9 +873,9 @@ int ksmbd_gen_preauth_integrity_hash(struct ksmbd_conn *conn, char *buf, __u8 *pi_hash) { int rc; - struct smb2_hdr *rcv_hdr = (struct smb2_hdr *)buf; + struct smb2_hdr *rcv_hdr = smb2_get_msg(buf); char *all_bytes_msg = (char *)&rcv_hdr->ProtocolId; - int msg_size = be32_to_cpu(rcv_hdr->smb2_buf_length); + int msg_size = get_rfc1002_len(buf); struct ksmbd_crypto_ctx *ctx = NULL; if (conn->preauth_info->Preauth_HashId != @@ -983,7 +983,7 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec, u8 *sign) { struct scatterlist *sg; - unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24; + unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int i, nr_entries[3] = {0}, total_entries = 0, sg_idx = 0; if (!nvec) @@ -1047,9 +1047,8 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec, int ksmbd_crypt_message(struct ksmbd_conn *conn, struct kvec *iov, unsigned int nvec, int enc) { - struct smb2_transform_hdr *tr_hdr = - (struct smb2_transform_hdr *)iov[0].iov_base; - unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24; + struct smb2_transform_hdr *tr_hdr = smb2_get_msg(iov[0].iov_base); + unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int rc; struct scatterlist *sg; u8 sign[SMB2_SIGNATURE_SIZE] = {}; diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index b57a0d8a392f..83a94d0bb480 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -158,26 +158,25 @@ void ksmbd_conn_wait_idle(struct ksmbd_conn *conn) int ksmbd_conn_write(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb_hdr *rsp_hdr = work->response_buf; size_t len = 0; int sent; struct kvec iov[3]; int iov_idx = 0; ksmbd_conn_try_dequeue_request(work); - if (!rsp_hdr) { + if (!work->response_buf) { pr_err("NULL response header\n"); return -EINVAL; } if (work->tr_buf) { iov[iov_idx] = (struct kvec) { work->tr_buf, - sizeof(struct smb2_transform_hdr) }; + sizeof(struct smb2_transform_hdr) + 4 }; len += iov[iov_idx++].iov_len; } if (work->aux_payload_sz) { - iov[iov_idx] = (struct kvec) { rsp_hdr, work->resp_hdr_sz }; + iov[iov_idx] = (struct kvec) { work->response_buf, work->resp_hdr_sz }; len += iov[iov_idx++].iov_len; iov[iov_idx] = (struct kvec) { work->aux_payload_buf, work->aux_payload_sz }; len += iov[iov_idx++].iov_len; @@ -185,8 +184,8 @@ int ksmbd_conn_write(struct ksmbd_work *work) if (work->tr_buf) iov[iov_idx].iov_len = work->resp_hdr_sz; else - iov[iov_idx].iov_len = get_rfc1002_len(rsp_hdr) + 4; - iov[iov_idx].iov_base = rsp_hdr; + iov[iov_idx].iov_len = get_rfc1002_len(work->response_buf) + 4; + iov[iov_idx].iov_base = work->response_buf; len += iov[iov_idx++].iov_len; } diff --git a/fs/ksmbd/ksmbd_work.c b/fs/ksmbd/ksmbd_work.c index fd58eb4809f6..14b9caebf7a4 100644 --- a/fs/ksmbd/ksmbd_work.c +++ b/fs/ksmbd/ksmbd_work.c @@ -69,7 +69,6 @@ int ksmbd_workqueue_init(void) void ksmbd_workqueue_destroy(void) { - flush_workqueue(ksmbd_wq); destroy_workqueue(ksmbd_wq); ksmbd_wq = NULL; } diff --git a/fs/ksmbd/ksmbd_work.h b/fs/ksmbd/ksmbd_work.h index f7156bc50049..5ece58e40c97 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/ksmbd/ksmbd_work.h @@ -92,7 +92,7 @@ struct ksmbd_work { */ static inline void *ksmbd_resp_buf_next(struct ksmbd_work *work) { - return work->response_buf + work->next_smb2_rsp_hdr_off; + return work->response_buf + work->next_smb2_rsp_hdr_off + 4; } /** @@ -101,7 +101,7 @@ static inline void *ksmbd_resp_buf_next(struct ksmbd_work *work) */ static inline void *ksmbd_req_buf_next(struct ksmbd_work *work) { - return work->request_buf + work->next_smb2_rcv_hdr_off; + return work->request_buf + work->next_smb2_rcv_hdr_off + 4; } struct ksmbd_work *ksmbd_alloc_work_struct(void); diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index f9dae6ef2115..077b8761d099 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -629,10 +629,10 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) return; } - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(0); @@ -645,7 +645,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = work->response_buf; + rsp = smb2_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(24); if (!br_info->open_trunc && @@ -659,7 +659,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp->PersistentFid = cpu_to_le64(fp->persistent_id); rsp->VolatileFid = cpu_to_le64(fp->volatile_id); - inc_rfc1001_len(rsp, 24); + inc_rfc1001_len(work->response_buf, 24); ksmbd_debug(OPLOCK, "sending oplock break v_id %llu p_id = %llu lock level = %d\n", @@ -736,10 +736,10 @@ static void __smb2_lease_break_noti(struct work_struct *wk) return; } - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(0); @@ -752,7 +752,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = work->response_buf; + rsp = smb2_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(44); rsp->Epoch = br_info->epoch; rsp->Flags = 0; @@ -768,7 +768,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) rsp->AccessMaskHint = 0; rsp->ShareMaskHint = 0; - inc_rfc1001_len(rsp, 44); + inc_rfc1001_len(work->response_buf, 44); ksmbd_conn_write(work); ksmbd_free_work_struct(work); @@ -1335,19 +1335,16 @@ __u8 smb2_map_lease_to_oplock(__le32 lease_state) */ void create_lease_buf(u8 *rbuf, struct lease *lease) { - char *LeaseKey = (char *)&lease->lease_key; - if (lease->version == 2) { struct create_lease_v2 *buf = (struct create_lease_v2 *)rbuf; - char *ParentLeaseKey = (char *)&lease->parent_lease_key; memset(buf, 0, sizeof(struct create_lease_v2)); - buf->lcontext.LeaseKeyLow = *((__le64 *)LeaseKey); - buf->lcontext.LeaseKeyHigh = *((__le64 *)(LeaseKey + 8)); + memcpy(buf->lcontext.LeaseKey, lease->lease_key, + SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; buf->lcontext.LeaseState = lease->state; - buf->lcontext.ParentLeaseKeyLow = *((__le64 *)ParentLeaseKey); - buf->lcontext.ParentLeaseKeyHigh = *((__le64 *)(ParentLeaseKey + 8)); + memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, + SMB2_LEASE_KEY_SIZE); buf->ccontext.DataOffset = cpu_to_le16(offsetof (struct create_lease_v2, lcontext)); buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2)); @@ -1362,8 +1359,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) struct create_lease *buf = (struct create_lease *)rbuf; memset(buf, 0, sizeof(struct create_lease)); - buf->lcontext.LeaseKeyLow = *((__le64 *)LeaseKey); - buf->lcontext.LeaseKeyHigh = *((__le64 *)(LeaseKey + 8)); + memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; buf->lcontext.LeaseState = lease->state; buf->ccontext.DataOffset = cpu_to_le16(offsetof @@ -1398,7 +1394,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req) if (!lreq) return NULL; - data_offset = (char *)req + 4 + le32_to_cpu(req->CreateContextsOffset); + data_offset = (char *)req + le32_to_cpu(req->CreateContextsOffset); cc = (struct create_context *)data_offset; do { cc = (struct create_context *)((char *)cc + next); @@ -1416,19 +1412,17 @@ struct lease_ctx_info *parse_lease_state(void *open_req) if (sizeof(struct lease_context_v2) == le32_to_cpu(cc->DataLength)) { struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; - *((__le64 *)lreq->lease_key) = lc->lcontext.LeaseKeyLow; - *((__le64 *)(lreq->lease_key + 8)) = lc->lcontext.LeaseKeyHigh; + memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; lreq->duration = lc->lcontext.LeaseDuration; - *((__le64 *)lreq->parent_lease_key) = lc->lcontext.ParentLeaseKeyLow; - *((__le64 *)(lreq->parent_lease_key + 8)) = lc->lcontext.ParentLeaseKeyHigh; + memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, + SMB2_LEASE_KEY_SIZE); lreq->version = 2; } else { struct create_lease *lc = (struct create_lease *)cc; - *((__le64 *)lreq->lease_key) = lc->lcontext.LeaseKeyLow; - *((__le64 *)(lreq->lease_key + 8)) = lc->lcontext.LeaseKeyHigh; + memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; lreq->duration = lc->lcontext.LeaseDuration; @@ -1462,7 +1456,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) * CreateContextsOffset and CreateContextsLength are guaranteed to * be valid because of ksmbd_smb2_check_message(). */ - cc = (struct create_context *)((char *)req + 4 + + cc = (struct create_context *)((char *)req + le32_to_cpu(req->CreateContextsOffset)); remain_len = le32_to_cpu(req->CreateContextsLength); do { diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 119b8047cfbd..0cf7a2b5bbc0 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -28,8 +28,6 @@ #define OPLOCK_WRITE_TO_NONE 0x04 #define OPLOCK_READ_TO_NONE 0x08 -#define SMB2_LEASE_KEY_SIZE 16 - struct lease_ctx_info { __u8 lease_key[SMB2_LEASE_KEY_SIZE]; __le32 req_state; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 2a2b2135bfde..2e12f6d8483b 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -622,7 +622,6 @@ MODULE_DESCRIPTION("Linux kernel CIFS/SMB SERVER"); MODULE_LICENSE("GPL"); MODULE_SOFTDEP("pre: ecb"); MODULE_SOFTDEP("pre: hmac"); -MODULE_SOFTDEP("pre: md4"); MODULE_SOFTDEP("pre: md5"); MODULE_SOFTDEP("pre: nls"); MODULE_SOFTDEP("pre: aes"); @@ -632,5 +631,6 @@ MODULE_SOFTDEP("pre: sha512"); MODULE_SOFTDEP("pre: aead2"); MODULE_SOFTDEP("pre: ccm"); MODULE_SOFTDEP("pre: gcm"); +MODULE_SOFTDEP("pre: crc32"); module_init(ksmbd_server_init) module_exit(ksmbd_server_exit) diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index 030ca57c3784..50d0b1022289 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -6,7 +6,6 @@ #include "glob.h" #include "nterr.h" -#include "smb2pdu.h" #include "smb_common.h" #include "smbstatus.h" #include "mgmt/user_session.h" @@ -347,23 +346,16 @@ static int smb2_validate_credit_charge(struct ksmbd_conn *conn, int ksmbd_smb2_check_message(struct ksmbd_work *work) { - struct smb2_pdu *pdu = work->request_buf; + struct smb2_pdu *pdu = ksmbd_req_buf_next(work); struct smb2_hdr *hdr = &pdu->hdr; int command; __u32 clc_len; /* calculated length */ - __u32 len = get_rfc1002_len(pdu); + __u32 len = get_rfc1002_len(work->request_buf); - if (work->next_smb2_rcv_hdr_off) { - pdu = ksmbd_req_buf_next(work); - hdr = &pdu->hdr; - } - - if (le32_to_cpu(hdr->NextCommand) > 0) { + if (le32_to_cpu(hdr->NextCommand) > 0) len = le32_to_cpu(hdr->NextCommand); - } else if (work->next_smb2_rcv_hdr_off) { + else if (work->next_smb2_rcv_hdr_off) len -= work->next_smb2_rcv_hdr_off; - len = round_up(len, 8); - } if (check_smb2_hdr(hdr)) return 1; diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c index fb6a65d23139..0a5d8450e835 100644 --- a/fs/ksmbd/smb2ops.c +++ b/fs/ksmbd/smb2ops.c @@ -6,7 +6,6 @@ #include <linux/slab.h> #include "glob.h" -#include "smb2pdu.h" #include "auth.h" #include "connection.h" @@ -199,7 +198,7 @@ void init_smb2_1_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256; + conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; @@ -217,7 +216,7 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_AES_CMAC; + conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; @@ -242,7 +241,7 @@ void init_smb3_02_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_AES_CMAC; + conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; @@ -267,7 +266,7 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->cmds = smb2_0_server_cmds; conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds); conn->max_credits = SMB2_MAX_CREDITS; - conn->signing_algorithm = SIGNING_ALG_AES_CMAC; + conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 7e448df3f847..121f8e8c70ac 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -13,7 +13,6 @@ #include <linux/falloc.h> #include "glob.h" -#include "smb2pdu.h" #include "smbfsctl.h" #include "oplock.h" #include "smbacl.h" @@ -44,8 +43,8 @@ static void __wbuf(struct ksmbd_work *work, void **req, void **rsp) *req = ksmbd_req_buf_next(work); *rsp = ksmbd_resp_buf_next(work); } else { - *req = work->request_buf; - *rsp = work->response_buf; + *req = smb2_get_msg(work->request_buf); + *rsp = smb2_get_msg(work->response_buf); } } @@ -93,13 +92,14 @@ struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn */ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) { - struct smb2_hdr *req_hdr = work->request_buf; + struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf); + unsigned int cmd = le16_to_cpu(req_hdr->Command); int tree_id; work->tcon = NULL; - if (work->conn->ops->get_cmd_val(work) == SMB2_TREE_CONNECT_HE || - work->conn->ops->get_cmd_val(work) == SMB2_CANCEL_HE || - work->conn->ops->get_cmd_val(work) == SMB2_LOGOFF_HE) { + if (cmd == SMB2_TREE_CONNECT_HE || + cmd == SMB2_CANCEL_HE || + cmd == SMB2_LOGOFF_HE) { ksmbd_debug(SMB, "skip to check tree connect request\n"); return 0; } @@ -130,7 +130,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) err_rsp = ksmbd_resp_buf_next(work); else - err_rsp = work->response_buf; + err_rsp = smb2_get_msg(work->response_buf); if (err_rsp->hdr.Status != STATUS_STOPPED_ON_SYMLINK) { err_rsp->StructureSize = SMB2_ERROR_STRUCTURE_SIZE2_LE; @@ -150,7 +150,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work) */ bool is_smb2_neg_cmd(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); /* is it SMB2 header ? */ if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -174,7 +174,7 @@ bool is_smb2_neg_cmd(struct ksmbd_work *work) */ bool is_smb2_rsp(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->response_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->response_buf); /* is it SMB2 header ? */ if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -200,7 +200,7 @@ u16 get_smb2_cmd_val(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) rcv_hdr = ksmbd_req_buf_next(work); else - rcv_hdr = work->request_buf; + rcv_hdr = smb2_get_msg(work->request_buf); return le16_to_cpu(rcv_hdr->Command); } @@ -216,7 +216,7 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) if (work->next_smb2_rcv_hdr_off) rsp_hdr = ksmbd_resp_buf_next(work); else - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Status = err; smb2_set_err_rsp(work); } @@ -237,13 +237,11 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) if (conn->need_neg == false) return -EINVAL; - rsp_hdr = work->response_buf; + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); + rsp_hdr = smb2_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); - rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->CreditRequest = cpu_to_le16(2); @@ -256,7 +254,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = work->response_buf; + rsp = smb2_get_msg(work->response_buf); WARN_ON(ksmbd_conn_good(work)); @@ -277,12 +275,12 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp->SecurityBufferOffset = cpu_to_le16(128); rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH); - ksmbd_copy_gss_neg_header(((char *)(&rsp->hdr) + - sizeof(rsp->hdr.smb2_buf_length)) + + ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) + le16_to_cpu(rsp->SecurityBufferOffset)); - inc_rfc1001_len(rsp, sizeof(struct smb2_negotiate_rsp) - - sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + - AUTH_GSS_LENGTH); + inc_rfc1001_len(work->response_buf, + sizeof(struct smb2_negotiate_rsp) - + sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + + AUTH_GSS_LENGTH); rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE; if (server_conf.signing == KSMBD_CONFIG_OPT_MANDATORY) rsp->SecurityMode |= SMB2_NEGOTIATE_SIGNING_REQUIRED_LE; @@ -387,8 +385,8 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) next_hdr_offset = le32_to_cpu(req->NextCommand); new_len = ALIGN(len, 8); - inc_rfc1001_len(work->response_buf, ((sizeof(struct smb2_hdr) - 4) - + new_len - len)); + inc_rfc1001_len(work->response_buf, + sizeof(struct smb2_hdr) + new_len - len); rsp->NextCommand = cpu_to_le32(new_len); work->next_smb2_rcv_hdr_off += next_hdr_offset; @@ -406,7 +404,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) work->compound_fid = KSMBD_NO_FID; work->compound_pfid = KSMBD_NO_FID; } - memset((char *)rsp_hdr + 4, 0, sizeof(struct smb2_hdr) + 2); + memset((char *)rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->Command = rcv_hdr->Command; @@ -432,7 +430,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) */ bool is_chained_smb2_message(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); unsigned int len, next_cmd; if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -483,13 +481,13 @@ bool is_chained_smb2_message(struct ksmbd_work *work) */ int init_smb2_rsp_hdr(struct ksmbd_work *work) { - struct smb2_hdr *rsp_hdr = work->response_buf; - struct smb2_hdr *rcv_hdr = work->request_buf; + struct smb2_hdr *rsp_hdr = smb2_get_msg(work->response_buf); + struct smb2_hdr *rcv_hdr = smb2_get_msg(work->request_buf); struct ksmbd_conn *conn = work->conn; memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); - rsp_hdr->smb2_buf_length = - cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals)); + *(__be32 *)work->response_buf = + cpu_to_be32(conn->vals->header_size); rsp_hdr->ProtocolId = rcv_hdr->ProtocolId; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->Command = rcv_hdr->Command; @@ -522,7 +520,7 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) */ int smb2_allocate_rsp_buf(struct ksmbd_work *work) { - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); size_t small_sz = MAX_CIFS_SMALL_BUFFER_SIZE; size_t large_sz = small_sz + work->conn->vals->max_trans_size; size_t sz = small_sz; @@ -534,7 +532,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) if (cmd == SMB2_QUERY_INFO_HE) { struct smb2_query_info_req *req; - req = work->request_buf; + req = smb2_get_msg(work->request_buf); if (req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || req->FileInfoClass == FILE_ALL_INFORMATION)) @@ -561,7 +559,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) */ int smb2_check_user_session(struct ksmbd_work *work) { - struct smb2_hdr *req_hdr = work->request_buf; + struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf); struct ksmbd_conn *conn = work->conn; unsigned int cmd = conn->ops->get_cmd_val(work); unsigned long long sess_id; @@ -642,7 +640,7 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) struct ksmbd_conn *conn = work->conn; int id; - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND; id = ksmbd_acquire_async_msg_id(&conn->async_ida); @@ -674,7 +672,7 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) { struct smb2_hdr *rsp_hdr; - rsp_hdr = work->response_buf; + rsp_hdr = smb2_get_msg(work->response_buf); smb2_set_err_rsp(work); rsp_hdr->Status = status; @@ -715,17 +713,17 @@ static int smb2_get_dos_mode(struct kstat *stat, int attribute) int attr = 0; if (S_ISDIR(stat->mode)) { - attr = ATTR_DIRECTORY | - (attribute & (ATTR_HIDDEN | ATTR_SYSTEM)); + attr = FILE_ATTRIBUTE_DIRECTORY | + (attribute & (FILE_ATTRIBUTE_HIDDEN | FILE_ATTRIBUTE_SYSTEM)); } else { - attr = (attribute & 0x00005137) | ATTR_ARCHIVE; - attr &= ~(ATTR_DIRECTORY); + attr = (attribute & 0x00005137) | FILE_ATTRIBUTE_ARCHIVE; + attr &= ~(FILE_ATTRIBUTE_DIRECTORY); if (S_ISREG(stat->mode) && (server_conf.share_fake_fscaps & FILE_SUPPORTS_SPARSE_FILES)) - attr |= ATTR_SPARSE; + attr |= FILE_ATTRIBUTE_SPARSE_FILE; if (smb2_get_reparse_tag_special_file(stat->mode)) - attr |= ATTR_REPARSE; + attr |= FILE_ATTRIBUTE_REPARSE_POINT; } return attr; @@ -753,16 +751,16 @@ static void build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt, pneg_ctxt->Ciphers[0] = cipher_type; } -static void build_compression_ctxt(struct smb2_compression_ctx *pneg_ctxt, +static void build_compression_ctxt(struct smb2_compression_capabilities_context *pneg_ctxt, __le16 comp_algo) { pneg_ctxt->ContextType = SMB2_COMPRESSION_CAPABILITIES; pneg_ctxt->DataLength = - cpu_to_le16(sizeof(struct smb2_compression_ctx) + cpu_to_le16(sizeof(struct smb2_compression_capabilities_context) - sizeof(struct smb2_neg_context)); pneg_ctxt->Reserved = cpu_to_le32(0); pneg_ctxt->CompressionAlgorithmCount = cpu_to_le16(1); - pneg_ctxt->Reserved1 = cpu_to_le32(0); + pneg_ctxt->Flags = cpu_to_le32(0); pneg_ctxt->CompressionAlgorithms[0] = comp_algo; } @@ -802,11 +800,11 @@ static void build_posix_ctxt(struct smb2_posix_neg_context *pneg_ctxt) } static void assemble_neg_contexts(struct ksmbd_conn *conn, - struct smb2_negotiate_rsp *rsp) + struct smb2_negotiate_rsp *rsp, + void *smb2_buf_len) { - /* +4 is to account for the RFC1001 len field */ char *pneg_ctxt = (char *)rsp + - le32_to_cpu(rsp->NegotiateContextOffset) + 4; + le32_to_cpu(rsp->NegotiateContextOffset); int neg_ctxt_cnt = 1; int ctxt_size; @@ -815,7 +813,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt, conn->preauth_info->Preauth_HashId); rsp->NegotiateContextCount = cpu_to_le16(neg_ctxt_cnt); - inc_rfc1001_len(rsp, AUTH_GSS_PADDING); + inc_rfc1001_len(smb2_buf_len, AUTH_GSS_PADDING); ctxt_size = sizeof(struct smb2_preauth_neg_context); /* Round to 8 byte boundary */ pneg_ctxt += round_up(sizeof(struct smb2_preauth_neg_context), 8); @@ -839,12 +837,12 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, ksmbd_debug(SMB, "assemble SMB2_COMPRESSION_CAPABILITIES context\n"); /* Temporarily set to SMB3_COMPRESS_NONE */ - build_compression_ctxt((struct smb2_compression_ctx *)pneg_ctxt, + build_compression_ctxt((struct smb2_compression_capabilities_context *)pneg_ctxt, conn->compress_algorithm); rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); - ctxt_size += sizeof(struct smb2_compression_ctx) + 2; + ctxt_size += sizeof(struct smb2_compression_capabilities_context) + 2; /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_compression_ctx) + 2, + pneg_ctxt += round_up(sizeof(struct smb2_compression_capabilities_context) + 2, 8); } @@ -869,7 +867,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, ctxt_size += sizeof(struct smb2_signing_capabilities) + 2; } - inc_rfc1001_len(rsp, ctxt_size); + inc_rfc1001_len(smb2_buf_len, ctxt_size); } static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, @@ -918,7 +916,7 @@ static void decode_encrypt_ctxt(struct ksmbd_conn *conn, } static void decode_compress_ctxt(struct ksmbd_conn *conn, - struct smb2_compression_ctx *pneg_ctxt) + struct smb2_compression_capabilities_context *pneg_ctxt) { conn->compress_algorithm = SMB3_COMPRESS_NONE; } @@ -939,8 +937,8 @@ static void decode_sign_cap_ctxt(struct ksmbd_conn *conn, } for (i = 0; i < sign_algo_cnt; i++) { - if (pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_HMAC_SHA256 || - pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_AES_CMAC) { + if (pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_HMAC_SHA256_LE || + pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_AES_CMAC_LE) { ksmbd_debug(SMB, "Signing Algorithm ID = 0x%x\n", pneg_ctxt->SigningAlgorithms[i]); conn->signing_negotiated = true; @@ -952,14 +950,14 @@ static void decode_sign_cap_ctxt(struct ksmbd_conn *conn, } static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, - struct smb2_negotiate_req *req) + struct smb2_negotiate_req *req, + int len_of_smb) { /* +4 is to account for the RFC1001 len field */ - struct smb2_neg_context *pctx = (struct smb2_neg_context *)((char *)req + 4); + struct smb2_neg_context *pctx = (struct smb2_neg_context *)req; int i = 0, len_of_ctxts; int offset = le32_to_cpu(req->NegotiateContextOffset); int neg_ctxt_cnt = le16_to_cpu(req->NegotiateContextCount); - int len_of_smb = be32_to_cpu(req->hdr.smb2_buf_length); __le32 status = STATUS_INVALID_PARAMETER; ksmbd_debug(SMB, "decoding %d negotiate contexts\n", neg_ctxt_cnt); @@ -1011,7 +1009,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, break; decode_compress_ctxt(conn, - (struct smb2_compression_ctx *)pctx); + (struct smb2_compression_capabilities_context *)pctx); } else if (pctx->ContextType == SMB2_NETNAME_NEGOTIATE_CONTEXT_ID) { ksmbd_debug(SMB, "deassemble SMB2_NETNAME_NEGOTIATE_CONTEXT_ID context\n"); @@ -1044,8 +1042,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, int smb2_handle_negotiate(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_negotiate_req *req = work->request_buf; - struct smb2_negotiate_rsp *rsp = work->response_buf; + struct smb2_negotiate_req *req = smb2_get_msg(work->request_buf); + struct smb2_negotiate_rsp *rsp = smb2_get_msg(work->response_buf); int rc = 0; unsigned int smb2_buf_len, smb2_neg_size; __le32 status; @@ -1066,7 +1064,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) } smb2_buf_len = get_rfc1002_len(work->request_buf); - smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects) - 4; + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; @@ -1115,7 +1113,8 @@ int smb2_handle_negotiate(struct ksmbd_work *work) goto err_out; } - status = deassemble_neg_contexts(conn, req); + status = deassemble_neg_contexts(conn, req, + get_rfc1002_len(work->request_buf)); if (status != STATUS_SUCCESS) { pr_err("deassemble_neg_contexts error(0x%x)\n", status); @@ -1135,7 +1134,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) conn->preauth_info->Preauth_HashValue); rsp->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT); - assemble_neg_contexts(conn, rsp); + assemble_neg_contexts(conn, rsp, work->response_buf); break; case SMB302_PROT_ID: init_smb3_02_server(conn); @@ -1183,10 +1182,9 @@ int smb2_handle_negotiate(struct ksmbd_work *work) rsp->SecurityBufferOffset = cpu_to_le16(128); rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH); - ksmbd_copy_gss_neg_header(((char *)(&rsp->hdr) + - sizeof(rsp->hdr.smb2_buf_length)) + - le16_to_cpu(rsp->SecurityBufferOffset)); - inc_rfc1001_len(rsp, sizeof(struct smb2_negotiate_rsp) - + ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) + + le16_to_cpu(rsp->SecurityBufferOffset)); + inc_rfc1001_len(work->response_buf, sizeof(struct smb2_negotiate_rsp) - sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) + AUTH_GSS_LENGTH); rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE; @@ -1278,7 +1276,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, struct negotiate_message *negblob, size_t negblob_len) { - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct challenge_message *chgblob; unsigned char *spnego_blob = NULL; u16 spnego_blob_len; @@ -1386,8 +1384,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, static int ntlm_authenticate(struct ksmbd_work *work) { - struct smb2_sess_setup_req *req = work->request_buf; - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf); + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; struct channel *chann = NULL; @@ -1410,7 +1408,7 @@ static int ntlm_authenticate(struct ksmbd_work *work) memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); kfree(spnego_blob); - inc_rfc1001_len(rsp, spnego_blob_len - 1); + inc_rfc1001_len(work->response_buf, spnego_blob_len - 1); } user = session_user(conn, req); @@ -1522,8 +1520,8 @@ binding_session: #ifdef CONFIG_SMB_SERVER_KERBEROS5 static int krb5_authenticate(struct ksmbd_work *work) { - struct smb2_sess_setup_req *req = work->request_buf; - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf); + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; char *in_blob, *out_blob; @@ -1538,8 +1536,7 @@ static int krb5_authenticate(struct ksmbd_work *work) out_blob = (char *)&rsp->hdr.ProtocolId + le16_to_cpu(rsp->SecurityBufferOffset); out_len = work->response_sz - - offsetof(struct smb2_hdr, smb2_buf_length) - - le16_to_cpu(rsp->SecurityBufferOffset); + (le16_to_cpu(rsp->SecurityBufferOffset) + 4); /* Check previous session */ prev_sess_id = le64_to_cpu(req->PreviousSessionId); @@ -1556,7 +1553,7 @@ static int krb5_authenticate(struct ksmbd_work *work) return -EINVAL; } rsp->SecurityBufferLength = cpu_to_le16(out_len); - inc_rfc1001_len(rsp, out_len - 1); + inc_rfc1001_len(work->response_buf, out_len - 1); if ((conn->sign || server_conf.enforced_signing) || (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED)) @@ -1612,8 +1609,8 @@ static int krb5_authenticate(struct ksmbd_work *work) int smb2_sess_setup(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_sess_setup_req *req = work->request_buf; - struct smb2_sess_setup_rsp *rsp = work->response_buf; + struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf); + struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess; struct negotiate_message *negblob; unsigned int negblob_len, negblob_off; @@ -1625,7 +1622,7 @@ int smb2_sess_setup(struct ksmbd_work *work) rsp->SessionFlags = 0; rsp->SecurityBufferOffset = cpu_to_le16(72); rsp->SecurityBufferLength = 0; - inc_rfc1001_len(rsp, 9); + inc_rfc1001_len(work->response_buf, 9); if (!req->hdr.SessionId) { sess = ksmbd_smb2_session_create(); @@ -1699,7 +1696,7 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off = le16_to_cpu(req->SecurityBufferOffset); negblob_len = le16_to_cpu(req->SecurityBufferLength); - if (negblob_off < (offsetof(struct smb2_sess_setup_req, Buffer) - 4) || + if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) || negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) return -EINVAL; @@ -1739,7 +1736,8 @@ int smb2_sess_setup(struct ksmbd_work *work) * Note: here total size -1 is done as an * adjustment for 0 size blob */ - inc_rfc1001_len(rsp, le16_to_cpu(rsp->SecurityBufferLength) - 1); + inc_rfc1001_len(work->response_buf, + le16_to_cpu(rsp->SecurityBufferLength) - 1); } else if (negblob->MessageType == NtLmAuthenticate) { rc = ntlm_authenticate(work); @@ -1828,8 +1826,8 @@ out_err: int smb2_tree_connect(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_tree_connect_req *req = work->request_buf; - struct smb2_tree_connect_rsp *rsp = work->response_buf; + struct smb2_tree_connect_req *req = smb2_get_msg(work->request_buf); + struct smb2_tree_connect_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess = work->sess; char *treename = NULL, *name = NULL; struct ksmbd_tree_conn_status status; @@ -1894,7 +1892,7 @@ out_err1: rsp->Reserved = 0; /* default manual caching */ rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING; - inc_rfc1001_len(rsp, 16); + inc_rfc1001_len(work->response_buf, 16); if (!IS_ERR(treename)) kfree(treename); @@ -1999,17 +1997,18 @@ static int smb2_create_open_flags(bool file_present, __le32 access, */ int smb2_tree_disconnect(struct ksmbd_work *work) { - struct smb2_tree_disconnect_rsp *rsp = work->response_buf; + struct smb2_tree_disconnect_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess = work->sess; struct ksmbd_tree_connect *tcon = work->tcon; rsp->StructureSize = cpu_to_le16(4); - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); ksmbd_debug(SMB, "request\n"); if (!tcon) { - struct smb2_tree_disconnect_req *req = work->request_buf; + struct smb2_tree_disconnect_req *req = + smb2_get_msg(work->request_buf); ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -2031,11 +2030,11 @@ int smb2_tree_disconnect(struct ksmbd_work *work) int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_logoff_rsp *rsp = work->response_buf; + struct smb2_logoff_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess = work->sess; rsp->StructureSize = cpu_to_le16(4); - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); ksmbd_debug(SMB, "request\n"); @@ -2048,7 +2047,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_conn_wait_idle(conn); if (ksmbd_tree_conn_session_logoff(sess)) { - struct smb2_logoff_req *req = work->request_buf; + struct smb2_logoff_req *req = smb2_get_msg(work->request_buf); ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -2075,8 +2074,8 @@ int smb2_session_logoff(struct ksmbd_work *work) */ static noinline int create_smb2_pipe(struct ksmbd_work *work) { - struct smb2_create_rsp *rsp = work->response_buf; - struct smb2_create_req *req = work->request_buf; + struct smb2_create_rsp *rsp = smb2_get_msg(work->response_buf); + struct smb2_create_req *req = smb2_get_msg(work->request_buf); int id; int err; char *name; @@ -2099,7 +2098,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) rsp->hdr.Status = STATUS_SUCCESS; rsp->StructureSize = cpu_to_le16(89); rsp->OplockLevel = SMB2_OPLOCK_LEVEL_NONE; - rsp->Reserved = 0; + rsp->Flags = 0; rsp->CreateAction = cpu_to_le32(FILE_OPENED); rsp->CreationTime = cpu_to_le64(0); @@ -2107,14 +2106,14 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) rsp->ChangeTime = cpu_to_le64(0); rsp->AllocationSize = cpu_to_le64(0); rsp->EndofFile = cpu_to_le64(0); - rsp->FileAttributes = ATTR_NORMAL_LE; + rsp->FileAttributes = FILE_ATTRIBUTE_NORMAL_LE; rsp->Reserved2 = 0; rsp->VolatileFileId = cpu_to_le64(id); rsp->PersistentFileId = 0; rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; - inc_rfc1001_len(rsp, 88); /* StructureSize - 1*/ + inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/ kfree(name); return 0; @@ -2353,7 +2352,7 @@ static void smb2_update_xattrs(struct ksmbd_tree_connect *tcon, struct xattr_dos_attrib da; int rc; - fp->f_ci->m_fattr &= ~(ATTR_HIDDEN_LE | ATTR_SYSTEM_LE); + fp->f_ci->m_fattr &= ~(FILE_ATTRIBUTE_HIDDEN_LE | FILE_ATTRIBUTE_SYSTEM_LE); /* get FileAttributes from XATTR_NAME_DOS_ATTRIBUTE */ if (!test_share_config_flag(tcon->share_conf, @@ -2463,7 +2462,7 @@ int smb2_open(struct ksmbd_work *work) struct ksmbd_session *sess = work->sess; struct ksmbd_tree_connect *tcon = work->tcon; struct smb2_create_req *req; - struct smb2_create_rsp *rsp, *rsp_org; + struct smb2_create_rsp *rsp; struct path path; struct ksmbd_share_config *share = tcon->share_conf; struct ksmbd_file *fp = NULL; @@ -2489,7 +2488,6 @@ int smb2_open(struct ksmbd_work *work) umode_t posix_mode = 0; __le32 daccess, maximal_access = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (req->hdr.NextCommand && !work->next_smb2_rcv_hdr_off && @@ -2559,7 +2557,7 @@ int smb2_open(struct ksmbd_work *work) if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) lc = parse_lease_state(req); - if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE_LE)) { + if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", le32_to_cpu(req->ImpersonationLevel)); rc = -EIO; @@ -2567,7 +2565,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK)) { + if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK_LE)) { pr_err("Invalid create options : 0x%x\n", le32_to_cpu(req->CreateOptions)); rc = -EINVAL; @@ -2609,7 +2607,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - if (req->FileAttributes && !(req->FileAttributes & ATTR_MASK_LE)) { + if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) { pr_err("Invalid file attribute : 0x%x\n", le32_to_cpu(req->FileAttributes)); rc = -EINVAL; @@ -2740,7 +2738,7 @@ int smb2_open(struct ksmbd_work *work) } if (req->CreateOptions & FILE_DIRECTORY_FILE_LE && - req->FileAttributes & ATTR_NORMAL_LE) { + req->FileAttributes & FILE_ATTRIBUTE_NORMAL_LE) { rsp->hdr.Status = STATUS_NOT_A_DIRECTORY; rc = -EIO; } @@ -3119,7 +3117,7 @@ int smb2_open(struct ksmbd_work *work) opinfo = rcu_dereference(fp->f_opinfo); rsp->OplockLevel = opinfo != NULL ? opinfo->level : 0; rcu_read_unlock(); - rsp->Reserved = 0; + rsp->Flags = 0; rsp->CreateAction = cpu_to_le32(file_info); rsp->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); @@ -3140,7 +3138,7 @@ int smb2_open(struct ksmbd_work *work) rsp->CreateContextsOffset = 0; rsp->CreateContextsLength = 0; - inc_rfc1001_len(rsp_org, 88); /* StructureSize - 1*/ + inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/ /* If lease is request send lease context response */ if (opinfo && opinfo->is_lease) { @@ -3155,7 +3153,8 @@ int smb2_open(struct ksmbd_work *work) create_lease_buf(rsp->Buffer, opinfo->o_lease); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_lease_size); - inc_rfc1001_len(rsp_org, conn->vals->create_lease_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_lease_size); next_ptr = &lease_ccontext->Next; next_off = conn->vals->create_lease_size; } @@ -3175,7 +3174,8 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(maximal_access)); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_mxac_size); - inc_rfc1001_len(rsp_org, conn->vals->create_mxac_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_mxac_size); if (next_ptr) *next_ptr = cpu_to_le32(next_off); next_ptr = &mxac_ccontext->Next; @@ -3193,7 +3193,8 @@ int smb2_open(struct ksmbd_work *work) stat.ino, tcon->id); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_disk_id_size); - inc_rfc1001_len(rsp_org, conn->vals->create_disk_id_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_disk_id_size); if (next_ptr) *next_ptr = cpu_to_le32(next_off); next_ptr = &disk_id_ccontext->Next; @@ -3207,15 +3208,15 @@ int smb2_open(struct ksmbd_work *work) fp); le32_add_cpu(&rsp->CreateContextsLength, conn->vals->create_posix_size); - inc_rfc1001_len(rsp_org, conn->vals->create_posix_size); + inc_rfc1001_len(work->response_buf, + conn->vals->create_posix_size); if (next_ptr) *next_ptr = cpu_to_le32(next_off); } if (contxt_cnt > 0) { rsp->CreateContextsOffset = - cpu_to_le32(offsetof(struct smb2_create_rsp, Buffer) - - 4); + cpu_to_le32(offsetof(struct smb2_create_rsp, Buffer)); } err_out: @@ -3422,9 +3423,9 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, ffdinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (ffdinfo->EaSize) - ffdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + ffdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; if (d_info->hide_dot_file && d_info->name[0] == '.') - ffdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + ffdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(ffdinfo->FileName, conv_name, conv_len); ffdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3438,11 +3439,11 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, fbdinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (fbdinfo->EaSize) - fbdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + fbdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; fbdinfo->ShortNameLength = 0; fbdinfo->Reserved = 0; if (d_info->hide_dot_file && d_info->name[0] == '.') - fbdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + fbdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(fbdinfo->FileName, conv_name, conv_len); fbdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3454,7 +3455,7 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, fdinfo = (struct file_directory_info *)kstat; fdinfo->FileNameLength = cpu_to_le32(conv_len); if (d_info->hide_dot_file && d_info->name[0] == '.') - fdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + fdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(fdinfo->FileName, conv_name, conv_len); fdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3478,11 +3479,11 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, dinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (dinfo->EaSize) - dinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + dinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; dinfo->Reserved = 0; dinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino); if (d_info->hide_dot_file && d_info->name[0] == '.') - dinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + dinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(dinfo->FileName, conv_name, conv_len); dinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3496,13 +3497,13 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, fibdinfo->EaSize = smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode); if (fibdinfo->EaSize) - fibdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE; + fibdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE; fibdinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino); fibdinfo->ShortNameLength = 0; fibdinfo->Reserved = 0; fibdinfo->Reserved2 = cpu_to_le16(0); if (d_info->hide_dot_file && d_info->name[0] == '.') - fibdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE; + fibdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; memcpy(fibdinfo->FileName, conv_name, conv_len); fibdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset); break; @@ -3528,9 +3529,10 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode); posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino); posix_info->DosAttributes = - S_ISDIR(ksmbd_kstat->kstat->mode) ? ATTR_DIRECTORY_LE : ATTR_ARCHIVE_LE; + S_ISDIR(ksmbd_kstat->kstat->mode) ? + FILE_ATTRIBUTE_DIRECTORY_LE : FILE_ATTRIBUTE_ARCHIVE_LE; if (d_info->hide_dot_file && d_info->name[0] == '.') - posix_info->DosAttributes |= ATTR_HIDDEN_LE; + posix_info->DosAttributes |= FILE_ATTRIBUTE_HIDDEN_LE; id_to_sid(from_kuid_munged(&init_user_ns, ksmbd_kstat->kstat->uid), SIDNFS_USER, (struct smb_sid *)&posix_info->SidBuffer[0]); id_to_sid(from_kgid_munged(&init_user_ns, ksmbd_kstat->kstat->gid), @@ -3816,7 +3818,7 @@ int smb2_query_dir(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; struct smb2_query_directory_req *req; - struct smb2_query_directory_rsp *rsp, *rsp_org; + struct smb2_query_directory_rsp *rsp; struct ksmbd_share_config *share = work->tcon->share_conf; struct ksmbd_file *dir_fp = NULL; struct ksmbd_dir_info d_info; @@ -3826,7 +3828,6 @@ int smb2_query_dir(struct ksmbd_work *work) int buffer_sz; struct smb2_query_dir_private query_dir_private = {NULL, }; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (ksmbd_override_fsids(work)) { @@ -3947,7 +3948,7 @@ int smb2_query_dir(struct ksmbd_work *work) rsp->OutputBufferOffset = cpu_to_le16(0); rsp->OutputBufferLength = cpu_to_le32(0); rsp->Buffer[0] = 0; - inc_rfc1001_len(rsp_org, 9); + inc_rfc1001_len(work->response_buf, 9); } else { ((struct file_directory_info *) ((char *)rsp->Buffer + d_info.last_entry_offset)) @@ -3956,7 +3957,7 @@ int smb2_query_dir(struct ksmbd_work *work) rsp->StructureSize = cpu_to_le16(9); rsp->OutputBufferOffset = cpu_to_le16(72); rsp->OutputBufferLength = cpu_to_le32(d_info.data_count); - inc_rfc1001_len(rsp_org, 8 + d_info.data_count); + inc_rfc1001_len(work->response_buf, 8 + d_info.data_count); } kfree(srch_ptr); @@ -3999,26 +4000,28 @@ err_out2: * Return: 0 on success, otherwise error */ static int buffer_check_err(int reqOutputBufferLength, - struct smb2_query_info_rsp *rsp, int infoclass_size) + struct smb2_query_info_rsp *rsp, + void *rsp_org, int infoclass_size) { if (reqOutputBufferLength < le32_to_cpu(rsp->OutputBufferLength)) { if (reqOutputBufferLength < infoclass_size) { pr_err("Invalid Buffer Size Requested\n"); rsp->hdr.Status = STATUS_INFO_LENGTH_MISMATCH; - rsp->hdr.smb2_buf_length = cpu_to_be32(sizeof(struct smb2_hdr) - 4); + *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr)); return -EINVAL; } ksmbd_debug(SMB, "Buffer Overflow\n"); rsp->hdr.Status = STATUS_BUFFER_OVERFLOW; - rsp->hdr.smb2_buf_length = cpu_to_be32(sizeof(struct smb2_hdr) - 4 + + *(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr) + reqOutputBufferLength); rsp->OutputBufferLength = cpu_to_le32(reqOutputBufferLength); } return 0; } -static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp) +static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp, + void *rsp_org) { struct smb2_file_standard_info *sinfo; @@ -4031,10 +4034,11 @@ static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp) sinfo->Directory = 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_standard_info)); - inc_rfc1001_len(rsp, sizeof(struct smb2_file_standard_info)); + inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_standard_info)); } -static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num) +static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num, + void *rsp_org) { struct smb2_file_internal_info *file_info; @@ -4044,12 +4048,13 @@ static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num) file_info->IndexNumber = cpu_to_le64(num | (1ULL << 63)); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_internal_info)); - inc_rfc1001_len(rsp, sizeof(struct smb2_file_internal_info)); + inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_internal_info)); } static int smb2_get_info_file_pipe(struct ksmbd_session *sess, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp) + struct smb2_query_info_rsp *rsp, + void *rsp_org) { u64 id; int rc; @@ -4067,14 +4072,16 @@ static int smb2_get_info_file_pipe(struct ksmbd_session *sess, switch (req->FileInfoClass) { case FILE_STANDARD_INFORMATION: - get_standard_info_pipe(rsp); + get_standard_info_pipe(rsp, rsp_org); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, FILE_STANDARD_INFORMATION_SIZE); + rsp, rsp_org, + FILE_STANDARD_INFORMATION_SIZE); break; case FILE_INTERNAL_INFORMATION: - get_internal_info_pipe(rsp, id); + get_internal_info_pipe(rsp, id, rsp_org); rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, FILE_INTERNAL_INFORMATION_SIZE); + rsp, rsp_org, + FILE_INTERNAL_INFORMATION_SIZE); break; default: ksmbd_debug(SMB, "smb2_info_file_pipe for %u not supported\n", @@ -4688,7 +4695,7 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, static int smb2_get_info_file(struct ksmbd_work *work, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp, void *rsp_org) + struct smb2_query_info_rsp *rsp) { struct ksmbd_file *fp; int fileinfoclass = 0; @@ -4699,7 +4706,8 @@ static int smb2_get_info_file(struct ksmbd_work *work, if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { /* smb2 info file called for pipe */ - return smb2_get_info_file_pipe(work->sess, req, rsp); + return smb2_get_info_file_pipe(work->sess, req, rsp, + work->response_buf); } if (work->next_smb2_rcv_hdr_off) { @@ -4724,77 +4732,77 @@ static int smb2_get_info_file(struct ksmbd_work *work, switch (fileinfoclass) { case FILE_ACCESS_INFORMATION: - get_file_access_info(rsp, fp, rsp_org); + get_file_access_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_ACCESS_INFORMATION_SIZE; break; case FILE_BASIC_INFORMATION: - rc = get_file_basic_info(rsp, fp, rsp_org); + rc = get_file_basic_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_BASIC_INFORMATION_SIZE; break; case FILE_STANDARD_INFORMATION: - get_file_standard_info(rsp, fp, rsp_org); + get_file_standard_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_STANDARD_INFORMATION_SIZE; break; case FILE_ALIGNMENT_INFORMATION: - get_file_alignment_info(rsp, rsp_org); + get_file_alignment_info(rsp, work->response_buf); file_infoclass_size = FILE_ALIGNMENT_INFORMATION_SIZE; break; case FILE_ALL_INFORMATION: - rc = get_file_all_info(work, rsp, fp, rsp_org); + rc = get_file_all_info(work, rsp, fp, work->response_buf); file_infoclass_size = FILE_ALL_INFORMATION_SIZE; break; case FILE_ALTERNATE_NAME_INFORMATION: - get_file_alternate_info(work, rsp, fp, rsp_org); + get_file_alternate_info(work, rsp, fp, work->response_buf); file_infoclass_size = FILE_ALTERNATE_NAME_INFORMATION_SIZE; break; case FILE_STREAM_INFORMATION: - get_file_stream_info(work, rsp, fp, rsp_org); + get_file_stream_info(work, rsp, fp, work->response_buf); file_infoclass_size = FILE_STREAM_INFORMATION_SIZE; break; case FILE_INTERNAL_INFORMATION: - get_file_internal_info(rsp, fp, rsp_org); + get_file_internal_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_INTERNAL_INFORMATION_SIZE; break; case FILE_NETWORK_OPEN_INFORMATION: - rc = get_file_network_open_info(rsp, fp, rsp_org); + rc = get_file_network_open_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_NETWORK_OPEN_INFORMATION_SIZE; break; case FILE_EA_INFORMATION: - get_file_ea_info(rsp, rsp_org); + get_file_ea_info(rsp, work->response_buf); file_infoclass_size = FILE_EA_INFORMATION_SIZE; break; case FILE_FULL_EA_INFORMATION: - rc = smb2_get_ea(work, fp, req, rsp, rsp_org); + rc = smb2_get_ea(work, fp, req, rsp, work->response_buf); file_infoclass_size = FILE_FULL_EA_INFORMATION_SIZE; break; case FILE_POSITION_INFORMATION: - get_file_position_info(rsp, fp, rsp_org); + get_file_position_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_POSITION_INFORMATION_SIZE; break; case FILE_MODE_INFORMATION: - get_file_mode_info(rsp, fp, rsp_org); + get_file_mode_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_MODE_INFORMATION_SIZE; break; case FILE_COMPRESSION_INFORMATION: - get_file_compression_info(rsp, fp, rsp_org); + get_file_compression_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_COMPRESSION_INFORMATION_SIZE; break; case FILE_ATTRIBUTE_TAG_INFORMATION: - rc = get_file_attribute_tag_info(rsp, fp, rsp_org); + rc = get_file_attribute_tag_info(rsp, fp, work->response_buf); file_infoclass_size = FILE_ATTRIBUTE_TAG_INFORMATION_SIZE; break; case SMB_FIND_FILE_POSIX_INFO: @@ -4802,7 +4810,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, pr_err("client doesn't negotiate with SMB3.1.1 POSIX Extensions\n"); rc = -EOPNOTSUPP; } else { - rc = find_file_posix_info(rsp, fp, rsp_org); + rc = find_file_posix_info(rsp, fp, work->response_buf); file_infoclass_size = sizeof(struct smb311_posix_qinfo); } break; @@ -4813,7 +4821,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, } if (!rc) rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, + rsp, work->response_buf, file_infoclass_size); ksmbd_fd_put(work, fp); return rc; @@ -4821,7 +4829,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, static int smb2_get_info_filesystem(struct ksmbd_work *work, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp, void *rsp_org) + struct smb2_query_info_rsp *rsp) { struct ksmbd_session *sess = work->sess; struct ksmbd_conn *conn = sess->conn; @@ -4857,7 +4865,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->DeviceType = cpu_to_le32(stfs.f_type); info->DeviceCharacteristics = cpu_to_le32(0x00000020); rsp->OutputBufferLength = cpu_to_le32(8); - inc_rfc1001_len(rsp_org, 8); + inc_rfc1001_len(work->response_buf, 8); fs_infoclass_size = FS_DEVICE_INFORMATION_SIZE; break; } @@ -4883,7 +4891,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->FileSystemNameLen = cpu_to_le32(len); sz = sizeof(struct filesystem_attribute_info) - 2 + len; rsp->OutputBufferLength = cpu_to_le32(sz); - inc_rfc1001_len(rsp_org, sz); + inc_rfc1001_len(work->response_buf, sz); fs_infoclass_size = FS_ATTRIBUTE_INFORMATION_SIZE; break; } @@ -4891,11 +4899,18 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, { struct filesystem_vol_info *info; size_t sz; + unsigned int serial_crc = 0; info = (struct filesystem_vol_info *)(rsp->Buffer); info->VolumeCreationTime = 0; + serial_crc = crc32_le(serial_crc, share->name, + strlen(share->name)); + serial_crc = crc32_le(serial_crc, share->path, + strlen(share->path)); + serial_crc = crc32_le(serial_crc, ksmbd_netbios_name(), + strlen(ksmbd_netbios_name())); /* Taking dummy value of serial number*/ - info->SerialNumber = cpu_to_le32(0xbc3ac512); + info->SerialNumber = cpu_to_le32(serial_crc); len = smbConvertToUTF16((__le16 *)info->VolumeLabel, share->name, PATH_MAX, conn->local_nls, 0); @@ -4904,7 +4919,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->Reserved = 0; sz = sizeof(struct filesystem_vol_info) - 2 + len; rsp->OutputBufferLength = cpu_to_le32(sz); - inc_rfc1001_len(rsp_org, sz); + inc_rfc1001_len(work->response_buf, sz); fs_infoclass_size = FS_VOLUME_INFORMATION_SIZE; break; } @@ -4918,7 +4933,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->SectorsPerAllocationUnit = cpu_to_le32(1); info->BytesPerSector = cpu_to_le32(stfs.f_bsize); rsp->OutputBufferLength = cpu_to_le32(24); - inc_rfc1001_len(rsp_org, 24); + inc_rfc1001_len(work->response_buf, 24); fs_infoclass_size = FS_SIZE_INFORMATION_SIZE; break; } @@ -4935,7 +4950,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->SectorsPerAllocationUnit = cpu_to_le32(1); info->BytesPerSector = cpu_to_le32(stfs.f_bsize); rsp->OutputBufferLength = cpu_to_le32(32); - inc_rfc1001_len(rsp_org, 32); + inc_rfc1001_len(work->response_buf, 32); fs_infoclass_size = FS_FULL_SIZE_INFORMATION_SIZE; break; } @@ -4956,7 +4971,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->extended_info.rel_date = 0; memcpy(info->extended_info.version_string, "1.1.0", strlen("1.1.0")); rsp->OutputBufferLength = cpu_to_le32(64); - inc_rfc1001_len(rsp_org, 64); + inc_rfc1001_len(work->response_buf, 64); fs_infoclass_size = FS_OBJECT_ID_INFORMATION_SIZE; break; } @@ -4977,7 +4992,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->ByteOffsetForSectorAlignment = 0; info->ByteOffsetForPartitionAlignment = 0; rsp->OutputBufferLength = cpu_to_le32(28); - inc_rfc1001_len(rsp_org, 28); + inc_rfc1001_len(work->response_buf, 28); fs_infoclass_size = FS_SECTOR_SIZE_INFORMATION_SIZE; break; } @@ -4999,7 +5014,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID); info->Padding = 0; rsp->OutputBufferLength = cpu_to_le32(48); - inc_rfc1001_len(rsp_org, 48); + inc_rfc1001_len(work->response_buf, 48); fs_infoclass_size = FS_CONTROL_INFORMATION_SIZE; break; } @@ -5020,7 +5035,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, info->TotalFileNodes = cpu_to_le64(stfs.f_files); info->FreeFileNodes = cpu_to_le64(stfs.f_ffree); rsp->OutputBufferLength = cpu_to_le32(56); - inc_rfc1001_len(rsp_org, 56); + inc_rfc1001_len(work->response_buf, 56); fs_infoclass_size = FS_POSIX_INFORMATION_SIZE; } break; @@ -5030,7 +5045,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, return -EOPNOTSUPP; } rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength), - rsp, + rsp, work->response_buf, fs_infoclass_size); path_put(&path); return rc; @@ -5038,7 +5053,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, static int smb2_get_info_sec(struct ksmbd_work *work, struct smb2_query_info_req *req, - struct smb2_query_info_rsp *rsp, void *rsp_org) + struct smb2_query_info_rsp *rsp) { struct ksmbd_file *fp; struct user_namespace *user_ns; @@ -5065,7 +5080,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, secdesclen = sizeof(struct smb_ntsd); rsp->OutputBufferLength = cpu_to_le32(secdesclen); - inc_rfc1001_len(rsp_org, secdesclen); + inc_rfc1001_len(work->response_buf, secdesclen); return 0; } @@ -5107,7 +5122,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, return rc; rsp->OutputBufferLength = cpu_to_le32(secdesclen); - inc_rfc1001_len(rsp_org, secdesclen); + inc_rfc1001_len(work->response_buf, secdesclen); return 0; } @@ -5120,10 +5135,9 @@ static int smb2_get_info_sec(struct ksmbd_work *work, int smb2_query_info(struct ksmbd_work *work) { struct smb2_query_info_req *req; - struct smb2_query_info_rsp *rsp, *rsp_org; + struct smb2_query_info_rsp *rsp; int rc = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); ksmbd_debug(SMB, "GOT query info request\n"); @@ -5131,15 +5145,15 @@ int smb2_query_info(struct ksmbd_work *work) switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); - rc = smb2_get_info_file(work, req, rsp, (void *)rsp_org); + rc = smb2_get_info_file(work, req, rsp); break; case SMB2_O_INFO_FILESYSTEM: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILESYSTEM\n"); - rc = smb2_get_info_filesystem(work, req, rsp, (void *)rsp_org); + rc = smb2_get_info_filesystem(work, req, rsp); break; case SMB2_O_INFO_SECURITY: ksmbd_debug(SMB, "GOT SMB2_O_INFO_SECURITY\n"); - rc = smb2_get_info_sec(work, req, rsp, (void *)rsp_org); + rc = smb2_get_info_sec(work, req, rsp); break; default: ksmbd_debug(SMB, "InfoType %d not supported yet\n", @@ -5164,7 +5178,7 @@ int smb2_query_info(struct ksmbd_work *work) } rsp->StructureSize = cpu_to_le16(9); rsp->OutputBufferOffset = cpu_to_le16(72); - inc_rfc1001_len(rsp_org, 8); + inc_rfc1001_len(work->response_buf, 8); return 0; } @@ -5177,8 +5191,8 @@ int smb2_query_info(struct ksmbd_work *work) static noinline int smb2_close_pipe(struct ksmbd_work *work) { u64 id; - struct smb2_close_req *req = work->request_buf; - struct smb2_close_rsp *rsp = work->response_buf; + struct smb2_close_req *req = smb2_get_msg(work->request_buf); + struct smb2_close_rsp *rsp = smb2_get_msg(work->response_buf); id = le64_to_cpu(req->VolatileFileId); ksmbd_session_rpc_close(work->sess, id); @@ -5193,7 +5207,7 @@ static noinline int smb2_close_pipe(struct ksmbd_work *work) rsp->AllocationSize = 0; rsp->EndOfFile = 0; rsp->Attributes = 0; - inc_rfc1001_len(rsp, 60); + inc_rfc1001_len(work->response_buf, 60); return 0; } @@ -5209,14 +5223,12 @@ int smb2_close(struct ksmbd_work *work) u64 sess_id; struct smb2_close_req *req; struct smb2_close_rsp *rsp; - struct smb2_close_rsp *rsp_org; struct ksmbd_conn *conn = work->conn; struct ksmbd_file *fp; struct inode *inode; u64 time; int err = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (test_share_config_flag(work->tcon->share_conf, @@ -5306,7 +5318,7 @@ out: rsp->hdr.Status = STATUS_FILE_CLOSED; smb2_set_err_rsp(work); } else { - inc_rfc1001_len(rsp_org, 60); + inc_rfc1001_len(work->response_buf, 60); } return 0; @@ -5320,11 +5332,11 @@ out: */ int smb2_echo(struct ksmbd_work *work) { - struct smb2_echo_rsp *rsp = work->response_buf; + struct smb2_echo_rsp *rsp = smb2_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(4); rsp->Reserved = 0; - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); return 0; } @@ -5566,14 +5578,14 @@ static int set_file_basic_info(struct ksmbd_file *fp, if (file_info->Attributes) { if (!S_ISDIR(inode->i_mode) && - file_info->Attributes & ATTR_DIRECTORY_LE) { + file_info->Attributes & FILE_ATTRIBUTE_DIRECTORY_LE) { pr_err("can't change a file to a directory\n"); return -EINVAL; } - if (!(S_ISDIR(inode->i_mode) && file_info->Attributes == ATTR_NORMAL_LE)) + if (!(S_ISDIR(inode->i_mode) && file_info->Attributes == FILE_ATTRIBUTE_NORMAL_LE)) fp->f_ci->m_fattr = file_info->Attributes | - (fp->f_ci->m_fattr & ATTR_DIRECTORY_LE); + (fp->f_ci->m_fattr & FILE_ATTRIBUTE_DIRECTORY_LE); } if (test_share_config_flag(share, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS) && @@ -5794,9 +5806,7 @@ static int set_file_mode_info(struct ksmbd_file *fp, mode = file_info->Mode; - if ((mode & ~FILE_MODE_INFO_MASK) || - (mode & FILE_SYNCHRONOUS_IO_ALERT_LE && - mode & FILE_SYNCHRONOUS_IO_NONALERT_LE)) { + if ((mode & ~FILE_MODE_INFO_MASK)) { pr_err("Mode is not valid : 0x%x\n", le32_to_cpu(mode)); return -EINVAL; } @@ -5943,14 +5953,13 @@ static int smb2_set_info_sec(struct ksmbd_file *fp, int addition_info, int smb2_set_info(struct ksmbd_work *work) { struct smb2_set_info_req *req; - struct smb2_set_info_rsp *rsp, *rsp_org; + struct smb2_set_info_rsp *rsp; struct ksmbd_file *fp; int rc = 0; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; ksmbd_debug(SMB, "Received set info request\n"); - rsp_org = work->response_buf; if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); @@ -5961,8 +5970,8 @@ int smb2_set_info(struct ksmbd_work *work) pid = work->compound_pfid; } } else { - req = work->request_buf; - rsp = work->response_buf; + req = smb2_get_msg(work->request_buf); + rsp = smb2_get_msg(work->response_buf); } if (!has_file_id(id)) { @@ -6002,7 +6011,7 @@ int smb2_set_info(struct ksmbd_work *work) goto err_out; rsp->StructureSize = cpu_to_le16(2); - inc_rfc1001_len(rsp_org, 2); + inc_rfc1001_len(work->response_buf, 2); ksmbd_fd_put(work, fp); return 0; @@ -6042,12 +6051,12 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) int nbytes = 0, err; u64 id; struct ksmbd_rpc_command *rpc_resp; - struct smb2_read_req *req = work->request_buf; - struct smb2_read_rsp *rsp = work->response_buf; + struct smb2_read_req *req = smb2_get_msg(work->request_buf); + struct smb2_read_rsp *rsp = smb2_get_msg(work->response_buf); id = le64_to_cpu(req->VolatileFileId); - inc_rfc1001_len(rsp, 16); + inc_rfc1001_len(work->response_buf, 16); rpc_resp = ksmbd_rpc_read(work->sess, id); if (rpc_resp) { if (rpc_resp->flags != KSMBD_RPC_OK) { @@ -6066,7 +6075,7 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; - work->resp_hdr_sz = get_rfc1002_len(rsp) + 4; + work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4; work->aux_payload_sz = nbytes; kvfree(rpc_resp); } @@ -6076,8 +6085,8 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) rsp->Reserved = 0; rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = 0; - rsp->Reserved2 = 0; - inc_rfc1001_len(rsp, nbytes); + rsp->Flags = 0; + inc_rfc1001_len(work->response_buf, nbytes); return 0; out: @@ -6127,14 +6136,13 @@ int smb2_read(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; struct smb2_read_req *req; - struct smb2_read_rsp *rsp, *rsp_org; + struct smb2_read_rsp *rsp; struct ksmbd_file *fp; loff_t offset; size_t length, mincount; ssize_t nbytes = 0, remain_bytes = 0; int err = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (test_share_config_flag(work->tcon->share_conf, @@ -6215,11 +6223,11 @@ int smb2_read(struct ksmbd_work *work) rsp->Reserved = 0; rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = cpu_to_le32(remain_bytes); - rsp->Reserved2 = 0; - inc_rfc1001_len(rsp_org, 16); - work->resp_hdr_sz = get_rfc1002_len(rsp_org) + 4; + rsp->Flags = 0; + inc_rfc1001_len(work->response_buf, 16); + work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4; work->aux_payload_sz = nbytes; - inc_rfc1001_len(rsp_org, nbytes); + inc_rfc1001_len(work->response_buf, nbytes); ksmbd_fd_put(work, fp); return 0; @@ -6254,8 +6262,8 @@ out: */ static noinline int smb2_write_pipe(struct ksmbd_work *work) { - struct smb2_write_req *req = work->request_buf; - struct smb2_write_rsp *rsp = work->response_buf; + struct smb2_write_req *req = smb2_get_msg(work->request_buf); + struct smb2_write_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_rpc_command *rpc_resp; u64 id = 0; int err = 0, ret = 0; @@ -6266,13 +6274,14 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work) id = le64_to_cpu(req->VolatileFileId); if (le16_to_cpu(req->DataOffset) == - (offsetof(struct smb2_write_req, Buffer) - 4)) { + offsetof(struct smb2_write_req, Buffer)) { data_buf = (char *)&req->Buffer[0]; } else { - if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) { + if ((u64)le16_to_cpu(req->DataOffset) + length > + get_rfc1002_len(work->request_buf)) { pr_err("invalid write data offset %u, smb_len %u\n", le16_to_cpu(req->DataOffset), - get_rfc1002_len(req)); + get_rfc1002_len(work->request_buf)); err = -EINVAL; goto out; } @@ -6304,7 +6313,7 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(length); rsp->DataRemaining = 0; rsp->Reserved2 = 0; - inc_rfc1001_len(rsp, 16); + inc_rfc1001_len(work->response_buf, 16); return 0; out: if (err) { @@ -6372,7 +6381,7 @@ static ssize_t smb2_write_rdma_channel(struct ksmbd_work *work, int smb2_write(struct ksmbd_work *work) { struct smb2_write_req *req; - struct smb2_write_rsp *rsp, *rsp_org; + struct smb2_write_rsp *rsp; struct ksmbd_file *fp = NULL; loff_t offset; size_t length; @@ -6381,7 +6390,6 @@ int smb2_write(struct ksmbd_work *work) bool writethrough = false; int err = 0; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { @@ -6424,13 +6432,14 @@ int smb2_write(struct ksmbd_work *work) if (req->Channel != SMB2_CHANNEL_RDMA_V1 && req->Channel != SMB2_CHANNEL_RDMA_V1_INVALIDATE) { if (le16_to_cpu(req->DataOffset) == - (offsetof(struct smb2_write_req, Buffer) - 4)) { + offsetof(struct smb2_write_req, Buffer)) { data_buf = (char *)&req->Buffer[0]; } else { - if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) { + if ((u64)le16_to_cpu(req->DataOffset) + length > + get_rfc1002_len(work->request_buf)) { pr_err("invalid write data offset %u, smb_len %u\n", le16_to_cpu(req->DataOffset), - get_rfc1002_len(req)); + get_rfc1002_len(work->request_buf)); err = -EINVAL; goto out; } @@ -6468,7 +6477,7 @@ int smb2_write(struct ksmbd_work *work) rsp->DataLength = cpu_to_le32(nbytes); rsp->DataRemaining = 0; rsp->Reserved2 = 0; - inc_rfc1001_len(rsp_org, 16); + inc_rfc1001_len(work->response_buf, 16); ksmbd_fd_put(work, fp); return 0; @@ -6502,10 +6511,9 @@ out: int smb2_flush(struct ksmbd_work *work) { struct smb2_flush_req *req; - struct smb2_flush_rsp *rsp, *rsp_org; + struct smb2_flush_rsp *rsp; int err; - rsp_org = work->response_buf; WORK_BUFFERS(work, req, rsp); ksmbd_debug(SMB, "SMB2_FLUSH called for fid %llu\n", @@ -6519,7 +6527,7 @@ int smb2_flush(struct ksmbd_work *work) rsp->StructureSize = cpu_to_le16(4); rsp->Reserved = 0; - inc_rfc1001_len(rsp_org, 4); + inc_rfc1001_len(work->response_buf, 4); return 0; out: @@ -6540,7 +6548,7 @@ out: int smb2_cancel(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *hdr = work->request_buf; + struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); struct smb2_hdr *chdr; struct ksmbd_work *cancel_work = NULL; int canceled = 0; @@ -6555,7 +6563,7 @@ int smb2_cancel(struct ksmbd_work *work) spin_lock(&conn->request_lock); list_for_each_entry(cancel_work, command_list, async_request_entry) { - chdr = cancel_work->request_buf; + chdr = smb2_get_msg(cancel_work->request_buf); if (cancel_work->async_id != le64_to_cpu(hdr->Id.AsyncId)) @@ -6574,7 +6582,7 @@ int smb2_cancel(struct ksmbd_work *work) spin_lock(&conn->request_lock); list_for_each_entry(cancel_work, command_list, request_entry) { - chdr = cancel_work->request_buf; + chdr = smb2_get_msg(cancel_work->request_buf); if (chdr->MessageId != hdr->MessageId || cancel_work == work) @@ -6709,8 +6717,8 @@ static inline bool lock_defer_pending(struct file_lock *fl) */ int smb2_lock(struct ksmbd_work *work) { - struct smb2_lock_req *req = work->request_buf; - struct smb2_lock_rsp *rsp = work->response_buf; + struct smb2_lock_req *req = smb2_get_msg(work->request_buf); + struct smb2_lock_rsp *rsp = smb2_get_msg(work->response_buf); struct smb2_lock_element *lock_ele; struct ksmbd_file *fp = NULL; struct file_lock *flock = NULL; @@ -7017,7 +7025,7 @@ skip: ksmbd_debug(SMB, "successful in taking lock\n"); rsp->hdr.Status = STATUS_SUCCESS; rsp->Reserved = 0; - inc_rfc1001_len(rsp, 4); + inc_rfc1001_len(work->response_buf, 4); ksmbd_fd_put(work, fp); return 0; @@ -7312,7 +7320,7 @@ static int fsctl_validate_negotiate_info(struct ksmbd_conn *conn, int ret = 0; int dialect; - if (in_buf_len < sizeof(struct validate_negotiate_info_req) + + if (in_buf_len < offsetof(struct validate_negotiate_info_req, Dialects) + le16_to_cpu(neg_req->DialectCount) * sizeof(__le16)) return -EINVAL; @@ -7435,9 +7443,9 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, old_fattr = fp->f_ci->m_fattr; if (sparse->SetSparse) - fp->f_ci->m_fattr |= ATTR_SPARSE_FILE_LE; + fp->f_ci->m_fattr |= FILE_ATTRIBUTE_SPARSE_FILE_LE; else - fp->f_ci->m_fattr &= ~ATTR_SPARSE_FILE_LE; + fp->f_ci->m_fattr &= ~FILE_ATTRIBUTE_SPARSE_FILE_LE; if (fp->f_ci->m_fattr != old_fattr && test_share_config_flag(work->tcon->share_conf, @@ -7490,13 +7498,12 @@ static int fsctl_request_resume_key(struct ksmbd_work *work, int smb2_ioctl(struct ksmbd_work *work) { struct smb2_ioctl_req *req; - struct smb2_ioctl_rsp *rsp, *rsp_org; + struct smb2_ioctl_rsp *rsp; unsigned int cnt_code, nbytes = 0, out_buf_len, in_buf_len; u64 id = KSMBD_NO_FID; struct ksmbd_conn *conn = work->conn; int ret = 0; - rsp_org = work->response_buf; if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); @@ -7506,8 +7513,8 @@ int smb2_ioctl(struct ksmbd_work *work) id = work->compound_fid; } } else { - req = work->request_buf; - rsp = work->response_buf; + req = smb2_get_msg(work->request_buf); + rsp = smb2_get_msg(work->response_buf); } if (!has_file_id(id)) @@ -7787,7 +7794,7 @@ dup_ext_out: rsp->Reserved = cpu_to_le16(0); rsp->Flags = cpu_to_le32(0); rsp->Reserved2 = cpu_to_le32(0); - inc_rfc1001_len(rsp_org, 48 + nbytes); + inc_rfc1001_len(work->response_buf, 48 + nbytes); return 0; @@ -7814,8 +7821,8 @@ out: */ static void smb20_oplock_break_ack(struct ksmbd_work *work) { - struct smb2_oplock_break *req = work->request_buf; - struct smb2_oplock_break *rsp = work->response_buf; + struct smb2_oplock_break *req = smb2_get_msg(work->request_buf); + struct smb2_oplock_break *rsp = smb2_get_msg(work->response_buf); struct ksmbd_file *fp; struct oplock_info *opinfo = NULL; __le32 err = 0; @@ -7922,7 +7929,7 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->Reserved2 = 0; rsp->VolatileFid = cpu_to_le64(volatile_id); rsp->PersistentFid = cpu_to_le64(persistent_id); - inc_rfc1001_len(rsp, 24); + inc_rfc1001_len(work->response_buf, 24); return; err_out: @@ -7958,8 +7965,8 @@ static int check_lease_state(struct lease *lease, __le32 req_state) static void smb21_lease_break_ack(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_lease_ack *req = work->request_buf; - struct smb2_lease_ack *rsp = work->response_buf; + struct smb2_lease_ack *req = smb2_get_msg(work->request_buf); + struct smb2_lease_ack *rsp = smb2_get_msg(work->response_buf); struct oplock_info *opinfo; __le32 err = 0; int ret = 0; @@ -8071,7 +8078,7 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) memcpy(rsp->LeaseKey, req->LeaseKey, 16); rsp->LeaseState = lease_state; rsp->LeaseDuration = 0; - inc_rfc1001_len(rsp, 36); + inc_rfc1001_len(work->response_buf, 36); return; err_out: @@ -8092,8 +8099,8 @@ err_out: */ int smb2_oplock_break(struct ksmbd_work *work) { - struct smb2_oplock_break *req = work->request_buf; - struct smb2_oplock_break *rsp = work->response_buf; + struct smb2_oplock_break *req = smb2_get_msg(work->request_buf); + struct smb2_oplock_break *rsp = smb2_get_msg(work->response_buf); switch (le16_to_cpu(req->StructureSize)) { case OP_BREAK_STRUCT_SIZE_20: @@ -8120,8 +8127,8 @@ int smb2_oplock_break(struct ksmbd_work *work) */ int smb2_notify(struct ksmbd_work *work) { - struct smb2_notify_req *req; - struct smb2_notify_rsp *rsp; + struct smb2_change_notify_req *req; + struct smb2_change_notify_rsp *rsp; WORK_BUFFERS(work, req, rsp); @@ -8145,7 +8152,7 @@ int smb2_notify(struct ksmbd_work *work) */ bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command) { - struct smb2_hdr *rcv_hdr2 = work->request_buf; + struct smb2_hdr *rcv_hdr2 = smb2_get_msg(work->request_buf); if ((rcv_hdr2->Flags & SMB2_FLAGS_SIGNED) && command != SMB2_NEGOTIATE_HE && @@ -8164,22 +8171,22 @@ bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command) */ int smb2_check_sign_req(struct ksmbd_work *work) { - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *hdr; char signature_req[SMB2_SIGNATURE_SIZE]; char signature[SMB2_HMACSHA256_SIZE]; struct kvec iov[1]; size_t len; - hdr_org = hdr = work->request_buf; + hdr = smb2_get_msg(work->request_buf); if (work->next_smb2_rcv_hdr_off) hdr = ksmbd_req_buf_next(work); if (!hdr->NextCommand && !work->next_smb2_rcv_hdr_off) - len = be32_to_cpu(hdr_org->smb2_buf_length); + len = get_rfc1002_len(work->request_buf); else if (hdr->NextCommand) len = le32_to_cpu(hdr->NextCommand); else - len = be32_to_cpu(hdr_org->smb2_buf_length) - + len = get_rfc1002_len(work->request_buf) - work->next_smb2_rcv_hdr_off; memcpy(signature_req, hdr->Signature, SMB2_SIGNATURE_SIZE); @@ -8207,25 +8214,26 @@ int smb2_check_sign_req(struct ksmbd_work *work) */ void smb2_set_sign_rsp(struct ksmbd_work *work) { - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *hdr; struct smb2_hdr *req_hdr; char signature[SMB2_HMACSHA256_SIZE]; struct kvec iov[2]; size_t len; int n_vec = 1; - hdr_org = hdr = work->response_buf; + hdr = smb2_get_msg(work->response_buf); if (work->next_smb2_rsp_hdr_off) hdr = ksmbd_resp_buf_next(work); req_hdr = ksmbd_req_buf_next(work); if (!work->next_smb2_rsp_hdr_off) { - len = get_rfc1002_len(hdr_org); + len = get_rfc1002_len(work->response_buf); if (req_hdr->NextCommand) len = ALIGN(len, 8); } else { - len = get_rfc1002_len(hdr_org) - work->next_smb2_rsp_hdr_off; + len = get_rfc1002_len(work->response_buf) - + work->next_smb2_rsp_hdr_off; len = ALIGN(len, 8); } @@ -8261,23 +8269,23 @@ int smb3_check_sign_req(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; char *signing_key; - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *hdr; struct channel *chann; char signature_req[SMB2_SIGNATURE_SIZE]; char signature[SMB2_CMACAES_SIZE]; struct kvec iov[1]; size_t len; - hdr_org = hdr = work->request_buf; + hdr = smb2_get_msg(work->request_buf); if (work->next_smb2_rcv_hdr_off) hdr = ksmbd_req_buf_next(work); if (!hdr->NextCommand && !work->next_smb2_rcv_hdr_off) - len = be32_to_cpu(hdr_org->smb2_buf_length); + len = get_rfc1002_len(work->request_buf); else if (hdr->NextCommand) len = le32_to_cpu(hdr->NextCommand); else - len = be32_to_cpu(hdr_org->smb2_buf_length) - + len = get_rfc1002_len(work->request_buf) - work->next_smb2_rcv_hdr_off; if (le16_to_cpu(hdr->Command) == SMB2_SESSION_SETUP_HE) { @@ -8318,8 +8326,7 @@ int smb3_check_sign_req(struct ksmbd_work *work) void smb3_set_sign_rsp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *req_hdr; - struct smb2_hdr *hdr, *hdr_org; + struct smb2_hdr *req_hdr, *hdr; struct channel *chann; char signature[SMB2_CMACAES_SIZE]; struct kvec iov[2]; @@ -8327,18 +8334,19 @@ void smb3_set_sign_rsp(struct ksmbd_work *work) size_t len; char *signing_key; - hdr_org = hdr = work->response_buf; + hdr = smb2_get_msg(work->response_buf); if (work->next_smb2_rsp_hdr_off) hdr = ksmbd_resp_buf_next(work); req_hdr = ksmbd_req_buf_next(work); if (!work->next_smb2_rsp_hdr_off) { - len = get_rfc1002_len(hdr_org); + len = get_rfc1002_len(work->response_buf); if (req_hdr->NextCommand) len = ALIGN(len, 8); } else { - len = get_rfc1002_len(hdr_org) - work->next_smb2_rsp_hdr_off; + len = get_rfc1002_len(work->response_buf) - + work->next_smb2_rsp_hdr_off; len = ALIGN(len, 8); } @@ -8391,7 +8399,7 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE && conn->preauth_info) - ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp, + ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, conn->preauth_info->Preauth_HashValue); if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE && sess) { @@ -8409,35 +8417,34 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) if (!hash_value) return; } - ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp, + ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, hash_value); } } -static void fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, char *old_buf, - __le16 cipher_type) +static void fill_transform_hdr(void *tr_buf, char *old_buf, __le16 cipher_type) { - struct smb2_hdr *hdr = (struct smb2_hdr *)old_buf; + struct smb2_transform_hdr *tr_hdr = tr_buf + 4; + struct smb2_hdr *hdr = smb2_get_msg(old_buf); unsigned int orig_len = get_rfc1002_len(old_buf); - memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr)); + memset(tr_buf, 0, sizeof(struct smb2_transform_hdr) + 4); tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM; tr_hdr->OriginalMessageSize = cpu_to_le32(orig_len); - tr_hdr->Flags = cpu_to_le16(0x01); + tr_hdr->Flags = cpu_to_le16(TRANSFORM_FLAG_ENCRYPTED); if (cipher_type == SMB2_ENCRYPTION_AES128_GCM || cipher_type == SMB2_ENCRYPTION_AES256_GCM) get_random_bytes(&tr_hdr->Nonce, SMB3_AES_GCM_NONCE); else get_random_bytes(&tr_hdr->Nonce, SMB3_AES_CCM_NONCE); memcpy(&tr_hdr->SessionId, &hdr->SessionId, 8); - inc_rfc1001_len(tr_hdr, sizeof(struct smb2_transform_hdr) - 4); - inc_rfc1001_len(tr_hdr, orig_len); + inc_rfc1001_len(tr_buf, sizeof(struct smb2_transform_hdr)); + inc_rfc1001_len(tr_buf, orig_len); } int smb3_encrypt_resp(struct ksmbd_work *work) { char *buf = work->response_buf; - struct smb2_transform_hdr *tr_hdr; struct kvec iov[3]; int rc = -ENOMEM; int buf_size = 0, rq_nvec = 2 + (work->aux_payload_sz ? 1 : 0); @@ -8445,15 +8452,15 @@ int smb3_encrypt_resp(struct ksmbd_work *work) if (ARRAY_SIZE(iov) < rq_nvec) return -ENOMEM; - tr_hdr = kzalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL); - if (!tr_hdr) + work->tr_buf = kzalloc(sizeof(struct smb2_transform_hdr) + 4, GFP_KERNEL); + if (!work->tr_buf) return rc; /* fill transform header */ - fill_transform_hdr(tr_hdr, buf, work->conn->cipher_type); + fill_transform_hdr(work->tr_buf, buf, work->conn->cipher_type); - iov[0].iov_base = tr_hdr; - iov[0].iov_len = sizeof(struct smb2_transform_hdr); + iov[0].iov_base = work->tr_buf; + iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; buf_size += iov[0].iov_len - 4; iov[1].iov_base = buf + 4; @@ -8473,15 +8480,14 @@ int smb3_encrypt_resp(struct ksmbd_work *work) return rc; memmove(buf, iov[1].iov_base, iov[1].iov_len); - tr_hdr->smb2_buf_length = cpu_to_be32(buf_size); - work->tr_buf = tr_hdr; + *(__be32 *)work->tr_buf = cpu_to_be32(buf_size); return rc; } bool smb3_is_transform_hdr(void *buf) { - struct smb2_transform_hdr *trhdr = buf; + struct smb2_transform_hdr *trhdr = smb2_get_msg(buf); return trhdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM; } @@ -8491,12 +8497,10 @@ int smb3_decrypt_req(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess; char *buf = work->request_buf; - struct smb2_hdr *hdr; unsigned int pdu_length = get_rfc1002_len(buf); struct kvec iov[2]; - int buf_data_size = pdu_length + 4 - - sizeof(struct smb2_transform_hdr); - struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf; + int buf_data_size = pdu_length - sizeof(struct smb2_transform_hdr); + struct smb2_transform_hdr *tr_hdr = smb2_get_msg(buf); int rc = 0; if (buf_data_size < sizeof(struct smb2_hdr)) { @@ -8518,16 +8522,15 @@ int smb3_decrypt_req(struct ksmbd_work *work) } iov[0].iov_base = buf; - iov[0].iov_len = sizeof(struct smb2_transform_hdr); - iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr); + iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; + iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr) + 4; iov[1].iov_len = buf_data_size; rc = ksmbd_crypt_message(conn, iov, 2, 0); if (rc) return rc; memmove(buf + 4, iov[1].iov_base, buf_data_size); - hdr = (struct smb2_hdr *)buf; - hdr->smb2_buf_length = cpu_to_be32(buf_data_size); + *(__be32 *)buf = cpu_to_be32(buf_data_size); return rc; } @@ -8535,7 +8538,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *rsp = work->response_buf; + struct smb2_hdr *rsp = smb2_get_msg(work->response_buf); if (conn->dialect < SMB30_PROT_ID) return false; diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index ff5a2f01d34a..4a3e4339d4c4 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -10,60 +10,6 @@ #include "ntlmssp.h" #include "smbacl.h" -/* - * Note that, due to trying to use names similar to the protocol specifications, - * there are many mixed case field names in the structures below. Although - * this does not match typical Linux kernel style, it is necessary to be - * able to match against the protocol specfication. - * - * SMB2 commands - * Some commands have minimal (wct=0,bcc=0), or uninteresting, responses - * (ie no useful data other than the SMB error code itself) and are marked such. - * Knowing this helps avoid response buffer allocations and copy in some cases. - */ - -/* List of commands in host endian */ -#define SMB2_NEGOTIATE_HE 0x0000 -#define SMB2_SESSION_SETUP_HE 0x0001 -#define SMB2_LOGOFF_HE 0x0002 /* trivial request/resp */ -#define SMB2_TREE_CONNECT_HE 0x0003 -#define SMB2_TREE_DISCONNECT_HE 0x0004 /* trivial req/resp */ -#define SMB2_CREATE_HE 0x0005 -#define SMB2_CLOSE_HE 0x0006 -#define SMB2_FLUSH_HE 0x0007 /* trivial resp */ -#define SMB2_READ_HE 0x0008 -#define SMB2_WRITE_HE 0x0009 -#define SMB2_LOCK_HE 0x000A -#define SMB2_IOCTL_HE 0x000B -#define SMB2_CANCEL_HE 0x000C -#define SMB2_ECHO_HE 0x000D -#define SMB2_QUERY_DIRECTORY_HE 0x000E -#define SMB2_CHANGE_NOTIFY_HE 0x000F -#define SMB2_QUERY_INFO_HE 0x0010 -#define SMB2_SET_INFO_HE 0x0011 -#define SMB2_OPLOCK_BREAK_HE 0x0012 - -/* The same list in little endian */ -#define SMB2_NEGOTIATE cpu_to_le16(SMB2_NEGOTIATE_HE) -#define SMB2_SESSION_SETUP cpu_to_le16(SMB2_SESSION_SETUP_HE) -#define SMB2_LOGOFF cpu_to_le16(SMB2_LOGOFF_HE) -#define SMB2_TREE_CONNECT cpu_to_le16(SMB2_TREE_CONNECT_HE) -#define SMB2_TREE_DISCONNECT cpu_to_le16(SMB2_TREE_DISCONNECT_HE) -#define SMB2_CREATE cpu_to_le16(SMB2_CREATE_HE) -#define SMB2_CLOSE cpu_to_le16(SMB2_CLOSE_HE) -#define SMB2_FLUSH cpu_to_le16(SMB2_FLUSH_HE) -#define SMB2_READ cpu_to_le16(SMB2_READ_HE) -#define SMB2_WRITE cpu_to_le16(SMB2_WRITE_HE) -#define SMB2_LOCK cpu_to_le16(SMB2_LOCK_HE) -#define SMB2_IOCTL cpu_to_le16(SMB2_IOCTL_HE) -#define SMB2_CANCEL cpu_to_le16(SMB2_CANCEL_HE) -#define SMB2_ECHO cpu_to_le16(SMB2_ECHO_HE) -#define SMB2_QUERY_DIRECTORY cpu_to_le16(SMB2_QUERY_DIRECTORY_HE) -#define SMB2_CHANGE_NOTIFY cpu_to_le16(SMB2_CHANGE_NOTIFY_HE) -#define SMB2_QUERY_INFO cpu_to_le16(SMB2_QUERY_INFO_HE) -#define SMB2_SET_INFO cpu_to_le16(SMB2_SET_INFO_HE) -#define SMB2_OPLOCK_BREAK cpu_to_le16(SMB2_OPLOCK_BREAK_HE) - /*Create Action Flags*/ #define FILE_SUPERSEDED 0x00000000 #define FILE_OPENED 0x00000001 @@ -96,9 +42,6 @@ /* SMB2 Max Credits */ #define SMB2_MAX_CREDITS 8192 -#define SMB2_CLIENT_GUID_SIZE 16 -#define SMB2_CREATE_GUID_SIZE 16 - /* Maximum buffer size value we can send with 1 credit */ #define SMB2_MAX_BUFFER_SIZE 65536 @@ -107,9 +50,6 @@ /* BB FIXME - analyze following length BB */ #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */ -#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) /* 'B''M''S' */ -#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) - #define SMB21_DEFAULT_IOSIZE (1024 * 1024) #define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024) #define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) @@ -117,78 +57,6 @@ #define SMB3_MAX_IOSIZE (8 * 1024 * 1024) /* - * SMB2 Header Definition - * - * "MBZ" : Must be Zero - * "BB" : BugBug, Something to check/review/analyze later - * "PDU" : "Protocol Data Unit" (ie a network "frame") - * - */ - -#define __SMB2_HEADER_STRUCTURE_SIZE 64 -#define SMB2_HEADER_STRUCTURE_SIZE \ - cpu_to_le16(__SMB2_HEADER_STRUCTURE_SIZE) - -struct smb2_hdr { - __be32 smb2_buf_length; /* big endian on wire */ - /* - * length is only two or three bytes - with - * one or two byte type preceding it that MBZ - */ - __le32 ProtocolId; /* 0xFE 'S' 'M' 'B' */ - __le16 StructureSize; /* 64 */ - __le16 CreditCharge; /* MBZ */ - __le32 Status; /* Error from server */ - __le16 Command; - __le16 CreditRequest; /* CreditResponse */ - __le32 Flags; - __le32 NextCommand; - __le64 MessageId; - union { - struct { - __le32 ProcessId; - __le32 TreeId; - } __packed SyncId; - __le64 AsyncId; - } __packed Id; - __le64 SessionId; - __u8 Signature[16]; -} __packed; - -struct smb2_pdu { - struct smb2_hdr hdr; - __le16 StructureSize2; /* size of wct area (varies, request specific) */ -} __packed; - -#define SMB3_AES_CCM_NONCE 11 -#define SMB3_AES_GCM_NONCE 12 - -struct smb2_transform_hdr { - __be32 smb2_buf_length; /* big endian on wire */ - /* - * length is only two or three bytes - with - * one or two byte type preceding it that MBZ - */ - __le32 ProtocolId; /* 0xFD 'S' 'M' 'B' */ - __u8 Signature[16]; - __u8 Nonce[16]; - __le32 OriginalMessageSize; - __u16 Reserved1; - __le16 Flags; /* EncryptionAlgorithm */ - __le64 SessionId; -} __packed; - -/* - * SMB2 flag definitions - */ -#define SMB2_FLAGS_SERVER_TO_REDIR cpu_to_le32(0x00000001) -#define SMB2_FLAGS_ASYNC_COMMAND cpu_to_le32(0x00000002) -#define SMB2_FLAGS_RELATED_OPERATIONS cpu_to_le32(0x00000004) -#define SMB2_FLAGS_SIGNED cpu_to_le32(0x00000008) -#define SMB2_FLAGS_DFS_OPERATIONS cpu_to_le32(0x10000000) -#define SMB2_FLAGS_REPLAY_OPERATIONS cpu_to_le32(0x20000000) - -/* * Definitions for SMB2 Protocol Data Units (network frames) * * See MS-SMB2.PDF specification for protocol details. @@ -209,425 +77,30 @@ struct smb2_err_rsp { __u8 ErrorData[1]; /* variable length */ } __packed; -struct smb2_negotiate_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 36 */ - __le16 DialectCount; - __le16 SecurityMode; - __le16 Reserved; /* MBZ */ - __le32 Capabilities; - __u8 ClientGUID[SMB2_CLIENT_GUID_SIZE]; - /* In SMB3.02 and earlier next three were MBZ le64 ClientStartTime */ - __le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */ - __le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */ - __le16 Reserved2; - __le16 Dialects[1]; /* One dialect (vers=) at a time for now */ -} __packed; - -/* SecurityMode flags */ -#define SMB2_NEGOTIATE_SIGNING_ENABLED_LE cpu_to_le16(0x0001) -#define SMB2_NEGOTIATE_SIGNING_REQUIRED 0x0002 -#define SMB2_NEGOTIATE_SIGNING_REQUIRED_LE cpu_to_le16(0x0002) -/* Capabilities flags */ -#define SMB2_GLOBAL_CAP_DFS 0x00000001 -#define SMB2_GLOBAL_CAP_LEASING 0x00000002 /* Resp only New to SMB2.1 */ -#define SMB2_GLOBAL_CAP_LARGE_MTU 0X00000004 /* Resp only New to SMB2.1 */ -#define SMB2_GLOBAL_CAP_MULTI_CHANNEL 0x00000008 /* New to SMB3 */ -#define SMB2_GLOBAL_CAP_PERSISTENT_HANDLES 0x00000010 /* New to SMB3 */ -#define SMB2_GLOBAL_CAP_DIRECTORY_LEASING 0x00000020 /* New to SMB3 */ -#define SMB2_GLOBAL_CAP_ENCRYPTION 0x00000040 /* New to SMB3 */ -/* Internal types */ -#define SMB2_NT_FIND 0x00100000 -#define SMB2_LARGE_FILES 0x00200000 - -#define SMB311_SALT_SIZE 32 -/* Hash Algorithm Types */ -#define SMB2_PREAUTH_INTEGRITY_SHA512 cpu_to_le16(0x0001) - -#define PREAUTH_HASHVALUE_SIZE 64 - struct preauth_integrity_info { /* PreAuth integrity Hash ID */ __le16 Preauth_HashId; /* PreAuth integrity Hash Value */ - __u8 Preauth_HashValue[PREAUTH_HASHVALUE_SIZE]; + __u8 Preauth_HashValue[SMB2_PREAUTH_HASH_SIZE]; }; -/* offset is sizeof smb2_negotiate_rsp - 4 but rounded up to 8 bytes. */ +/* offset is sizeof smb2_negotiate_rsp but rounded up to 8 bytes. */ #ifdef CONFIG_SMB_SERVER_KERBEROS5 -/* sizeof(struct smb2_negotiate_rsp) - 4 = +/* sizeof(struct smb2_negotiate_rsp) = * header(64) + response(64) + GSS_LENGTH(96) + GSS_PADDING(0) */ #define OFFSET_OF_NEG_CONTEXT 0xe0 #else -/* sizeof(struct smb2_negotiate_rsp) - 4 = +/* sizeof(struct smb2_negotiate_rsp) = * header(64) + response(64) + GSS_LENGTH(74) + GSS_PADDING(6) */ #define OFFSET_OF_NEG_CONTEXT 0xd0 #endif -#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1) -#define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2) -#define SMB2_COMPRESSION_CAPABILITIES cpu_to_le16(3) -#define SMB2_NETNAME_NEGOTIATE_CONTEXT_ID cpu_to_le16(5) -#define SMB2_SIGNING_CAPABILITIES cpu_to_le16(8) -#define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100) - -struct smb2_neg_context { - __le16 ContextType; - __le16 DataLength; - __le32 Reserved; - /* Followed by array of data */ -} __packed; - -struct smb2_preauth_neg_context { - __le16 ContextType; /* 1 */ - __le16 DataLength; - __le32 Reserved; - __le16 HashAlgorithmCount; /* 1 */ - __le16 SaltLength; - __le16 HashAlgorithms; /* HashAlgorithms[0] since only one defined */ - __u8 Salt[SMB311_SALT_SIZE]; -} __packed; - -/* Encryption Algorithms Ciphers */ -#define SMB2_ENCRYPTION_AES128_CCM cpu_to_le16(0x0001) -#define SMB2_ENCRYPTION_AES128_GCM cpu_to_le16(0x0002) -#define SMB2_ENCRYPTION_AES256_CCM cpu_to_le16(0x0003) -#define SMB2_ENCRYPTION_AES256_GCM cpu_to_le16(0x0004) - -struct smb2_encryption_neg_context { - __le16 ContextType; /* 2 */ - __le16 DataLength; - __le32 Reserved; - /* CipherCount usally 2, but can be 3 when AES256-GCM enabled */ - __le16 CipherCount; /* AES-128-GCM and AES-128-CCM by default */ - __le16 Ciphers[]; -} __packed; - -#define SMB3_COMPRESS_NONE cpu_to_le16(0x0000) -#define SMB3_COMPRESS_LZNT1 cpu_to_le16(0x0001) -#define SMB3_COMPRESS_LZ77 cpu_to_le16(0x0002) -#define SMB3_COMPRESS_LZ77_HUFF cpu_to_le16(0x0003) - -struct smb2_compression_ctx { - __le16 ContextType; /* 3 */ - __le16 DataLength; - __le32 Reserved; - __le16 CompressionAlgorithmCount; - __u16 Padding; - __le32 Reserved1; - __le16 CompressionAlgorithms[]; -} __packed; - -#define POSIX_CTXT_DATA_LEN 16 -struct smb2_posix_neg_context { - __le16 ContextType; /* 0x100 */ - __le16 DataLength; - __le32 Reserved; - __u8 Name[16]; /* POSIX ctxt GUID 93AD25509CB411E7B42383DE968BCD7C */ -} __packed; - -struct smb2_netname_neg_context { - __le16 ContextType; /* 0x100 */ - __le16 DataLength; - __le32 Reserved; - __le16 NetName[]; /* hostname of target converted to UCS-2 */ -} __packed; - -/* Signing algorithms */ -#define SIGNING_ALG_HMAC_SHA256 cpu_to_le16(0) -#define SIGNING_ALG_AES_CMAC cpu_to_le16(1) -#define SIGNING_ALG_AES_GMAC cpu_to_le16(2) - -struct smb2_signing_capabilities { - __le16 ContextType; /* 8 */ - __le16 DataLength; - __le32 Reserved; - __le16 SigningAlgorithmCount; - __le16 SigningAlgorithms[]; -} __packed; - -struct smb2_negotiate_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 65 */ - __le16 SecurityMode; - __le16 DialectRevision; - __le16 NegotiateContextCount; /* Prior to SMB3.1.1 was Reserved & MBZ */ - __u8 ServerGUID[16]; - __le32 Capabilities; - __le32 MaxTransactSize; - __le32 MaxReadSize; - __le32 MaxWriteSize; - __le64 SystemTime; /* MBZ */ - __le64 ServerStartTime; - __le16 SecurityBufferOffset; - __le16 SecurityBufferLength; - __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */ - __u8 Buffer[1]; /* variable length GSS security buffer */ -} __packed; - -/* Flags */ -#define SMB2_SESSION_REQ_FLAG_BINDING 0x01 -#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA 0x04 - #define SMB2_SESSION_EXPIRED (0) #define SMB2_SESSION_IN_PROGRESS BIT(0) #define SMB2_SESSION_VALID BIT(1) -/* Flags */ -#define SMB2_SESSION_REQ_FLAG_BINDING 0x01 -#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA 0x04 - -struct smb2_sess_setup_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 25 */ - __u8 Flags; - __u8 SecurityMode; - __le32 Capabilities; - __le32 Channel; - __le16 SecurityBufferOffset; - __le16 SecurityBufferLength; - __le64 PreviousSessionId; - __u8 Buffer[1]; /* variable length GSS security buffer */ -} __packed; - -/* Flags/Reserved for SMB3.1.1 */ -#define SMB2_SHAREFLAG_CLUSTER_RECONNECT 0x0001 - -/* Currently defined SessionFlags */ -#define SMB2_SESSION_FLAG_IS_GUEST_LE cpu_to_le16(0x0001) -#define SMB2_SESSION_FLAG_IS_NULL_LE cpu_to_le16(0x0002) -#define SMB2_SESSION_FLAG_ENCRYPT_DATA_LE cpu_to_le16(0x0004) -struct smb2_sess_setup_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 SessionFlags; - __le16 SecurityBufferOffset; - __le16 SecurityBufferLength; - __u8 Buffer[1]; /* variable length GSS security buffer */ -} __packed; - -struct smb2_logoff_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_logoff_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_tree_connect_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 Reserved; /* Flags in SMB3.1.1 */ - __le16 PathOffset; - __le16 PathLength; - __u8 Buffer[1]; /* variable length */ -} __packed; - -struct smb2_tree_connect_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 16 */ - __u8 ShareType; /* see below */ - __u8 Reserved; - __le32 ShareFlags; /* see below */ - __le32 Capabilities; /* see below */ - __le32 MaximalAccess; -} __packed; - -/* Possible ShareType values */ -#define SMB2_SHARE_TYPE_DISK 0x01 -#define SMB2_SHARE_TYPE_PIPE 0x02 -#define SMB2_SHARE_TYPE_PRINT 0x03 - -/* - * Possible ShareFlags - exactly one and only one of the first 4 caching flags - * must be set (any of the remaining, SHI1005, flags may be set individually - * or in combination. - */ -#define SMB2_SHAREFLAG_MANUAL_CACHING 0x00000000 -#define SMB2_SHAREFLAG_AUTO_CACHING 0x00000010 -#define SMB2_SHAREFLAG_VDO_CACHING 0x00000020 -#define SMB2_SHAREFLAG_NO_CACHING 0x00000030 -#define SHI1005_FLAGS_DFS 0x00000001 -#define SHI1005_FLAGS_DFS_ROOT 0x00000002 -#define SHI1005_FLAGS_RESTRICT_EXCLUSIVE_OPENS 0x00000100 -#define SHI1005_FLAGS_FORCE_SHARED_DELETE 0x00000200 -#define SHI1005_FLAGS_ALLOW_NAMESPACE_CACHING 0x00000400 -#define SHI1005_FLAGS_ACCESS_BASED_DIRECTORY_ENUM 0x00000800 -#define SHI1005_FLAGS_FORCE_LEVELII_OPLOCK 0x00001000 -#define SHI1005_FLAGS_ENABLE_HASH 0x00002000 - -/* Possible share capabilities */ -#define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) - -struct smb2_tree_disconnect_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -struct smb2_tree_disconnect_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 4 */ - __le16 Reserved; -} __packed; - -#define ATTR_READONLY_LE cpu_to_le32(ATTR_READONLY) -#define ATTR_HIDDEN_LE cpu_to_le32(ATTR_HIDDEN) -#define ATTR_SYSTEM_LE cpu_to_le32(ATTR_SYSTEM) -#define ATTR_DIRECTORY_LE cpu_to_le32(ATTR_DIRECTORY) -#define ATTR_ARCHIVE_LE cpu_to_le32(ATTR_ARCHIVE) -#define ATTR_NORMAL_LE cpu_to_le32(ATTR_NORMAL) -#define ATTR_TEMPORARY_LE cpu_to_le32(ATTR_TEMPORARY) -#define ATTR_SPARSE_FILE_LE cpu_to_le32(ATTR_SPARSE) -#define ATTR_REPARSE_POINT_LE cpu_to_le32(ATTR_REPARSE) -#define ATTR_COMPRESSED_LE cpu_to_le32(ATTR_COMPRESSED) -#define ATTR_OFFLINE_LE cpu_to_le32(ATTR_OFFLINE) -#define ATTR_NOT_CONTENT_INDEXED_LE cpu_to_le32(ATTR_NOT_CONTENT_INDEXED) -#define ATTR_ENCRYPTED_LE cpu_to_le32(ATTR_ENCRYPTED) -#define ATTR_INTEGRITY_STREAML_LE cpu_to_le32(0x00008000) -#define ATTR_NO_SCRUB_DATA_LE cpu_to_le32(0x00020000) -#define ATTR_MASK_LE cpu_to_le32(0x00007FB7) - -/* Oplock levels */ -#define SMB2_OPLOCK_LEVEL_NONE 0x00 -#define SMB2_OPLOCK_LEVEL_II 0x01 -#define SMB2_OPLOCK_LEVEL_EXCLUSIVE 0x08 -#define SMB2_OPLOCK_LEVEL_BATCH 0x09 -#define SMB2_OPLOCK_LEVEL_LEASE 0xFF -/* Non-spec internal type */ -#define SMB2_OPLOCK_LEVEL_NOCHANGE 0x99 - -/* Desired Access Flags */ -#define FILE_READ_DATA_LE cpu_to_le32(0x00000001) -#define FILE_LIST_DIRECTORY_LE cpu_to_le32(0x00000001) -#define FILE_WRITE_DATA_LE cpu_to_le32(0x00000002) -#define FILE_ADD_FILE_LE cpu_to_le32(0x00000002) -#define FILE_APPEND_DATA_LE cpu_to_le32(0x00000004) -#define FILE_ADD_SUBDIRECTORY_LE cpu_to_le32(0x00000004) -#define FILE_READ_EA_LE cpu_to_le32(0x00000008) -#define FILE_WRITE_EA_LE cpu_to_le32(0x00000010) -#define FILE_EXECUTE_LE cpu_to_le32(0x00000020) -#define FILE_TRAVERSE_LE cpu_to_le32(0x00000020) -#define FILE_DELETE_CHILD_LE cpu_to_le32(0x00000040) -#define FILE_READ_ATTRIBUTES_LE cpu_to_le32(0x00000080) -#define FILE_WRITE_ATTRIBUTES_LE cpu_to_le32(0x00000100) -#define FILE_DELETE_LE cpu_to_le32(0x00010000) -#define FILE_READ_CONTROL_LE cpu_to_le32(0x00020000) -#define FILE_WRITE_DAC_LE cpu_to_le32(0x00040000) -#define FILE_WRITE_OWNER_LE cpu_to_le32(0x00080000) -#define FILE_SYNCHRONIZE_LE cpu_to_le32(0x00100000) -#define FILE_ACCESS_SYSTEM_SECURITY_LE cpu_to_le32(0x01000000) -#define FILE_MAXIMAL_ACCESS_LE cpu_to_le32(0x02000000) -#define FILE_GENERIC_ALL_LE cpu_to_le32(0x10000000) -#define FILE_GENERIC_EXECUTE_LE cpu_to_le32(0x20000000) -#define FILE_GENERIC_WRITE_LE cpu_to_le32(0x40000000) -#define FILE_GENERIC_READ_LE cpu_to_le32(0x80000000) -#define DESIRED_ACCESS_MASK cpu_to_le32(0xF21F01FF) - -/* ShareAccess Flags */ -#define FILE_SHARE_READ_LE cpu_to_le32(0x00000001) -#define FILE_SHARE_WRITE_LE cpu_to_le32(0x00000002) -#define FILE_SHARE_DELETE_LE cpu_to_le32(0x00000004) -#define FILE_SHARE_ALL_LE cpu_to_le32(0x00000007) - -/* CreateDisposition Flags */ -#define FILE_SUPERSEDE_LE cpu_to_le32(0x00000000) -#define FILE_OPEN_LE cpu_to_le32(0x00000001) -#define FILE_CREATE_LE cpu_to_le32(0x00000002) -#define FILE_OPEN_IF_LE cpu_to_le32(0x00000003) -#define FILE_OVERWRITE_LE cpu_to_le32(0x00000004) -#define FILE_OVERWRITE_IF_LE cpu_to_le32(0x00000005) -#define FILE_CREATE_MASK_LE cpu_to_le32(0x00000007) - -#define FILE_READ_DESIRED_ACCESS_LE (FILE_READ_DATA_LE | \ - FILE_READ_EA_LE | \ - FILE_GENERIC_READ_LE) -#define FILE_WRITE_DESIRE_ACCESS_LE (FILE_WRITE_DATA_LE | \ - FILE_APPEND_DATA_LE | \ - FILE_WRITE_EA_LE | \ - FILE_WRITE_ATTRIBUTES_LE | \ - FILE_GENERIC_WRITE_LE) - -/* Impersonation Levels */ -#define IL_ANONYMOUS_LE cpu_to_le32(0x00000000) -#define IL_IDENTIFICATION_LE cpu_to_le32(0x00000001) -#define IL_IMPERSONATION_LE cpu_to_le32(0x00000002) -#define IL_DELEGATE_LE cpu_to_le32(0x00000003) - -/* Create Context Values */ -#define SMB2_CREATE_EA_BUFFER "ExtA" /* extended attributes */ -#define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */ -#define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ" -#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC" -#define SMB2_CREATE_ALLOCATION_SIZE "AlSi" -#define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc" -#define SMB2_CREATE_TIMEWARP_REQUEST "TWrp" -#define SMB2_CREATE_QUERY_ON_DISK_ID "QFid" -#define SMB2_CREATE_REQUEST_LEASE "RqLs" -#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2 "DH2Q" -#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 "DH2C" -#define SMB2_CREATE_APP_INSTANCE_ID "\x45\xBC\xA6\x6A\xEF\xA7\xF7\x4A\x90\x08\xFA\x46\x2E\x14\x4D\x74" - #define SMB2_CREATE_APP_INSTANCE_VERSION "\xB9\x82\xD0\xB7\x3B\x56\x07\x4F\xA0\x7B\x52\x4A\x81\x16\xA0\x10" -#define SVHDX_OPEN_DEVICE_CONTEXT 0x83CE6F1AD851E0986E34401CC9BCFCE9 -#define SMB2_CREATE_TAG_POSIX "\x93\xAD\x25\x50\x9C\xB4\x11\xE7\xB4\x23\x83\xDE\x96\x8B\xCD\x7C" - -struct smb2_create_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 57 */ - __u8 SecurityFlags; - __u8 RequestedOplockLevel; - __le32 ImpersonationLevel; - __le64 SmbCreateFlags; - __le64 Reserved; - __le32 DesiredAccess; - __le32 FileAttributes; - __le32 ShareAccess; - __le32 CreateDisposition; - __le32 CreateOptions; - __le16 NameOffset; - __le16 NameLength; - __le32 CreateContextsOffset; - __le32 CreateContextsLength; - __u8 Buffer[0]; -} __packed; - -struct smb2_create_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 89 */ - __u8 OplockLevel; - __u8 Reserved; - __le32 CreateAction; - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 AllocationSize; - __le64 EndofFile; - __le32 FileAttributes; - __le32 Reserved2; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 CreateContextsOffset; - __le32 CreateContextsLength; - __u8 Buffer[1]; -} __packed; - -struct create_context { - __le32 Next; - __le16 NameOffset; - __le16 NameLength; - __le16 Reserved; - __le16 DataOffset; - __le32 DataLength; - __u8 Buffer[0]; -} __packed; - struct create_durable_req_v2 { struct create_context ccontext; __u8 Name[8]; @@ -743,22 +216,21 @@ struct create_posix_rsp { #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) +#define SMB2_LEASE_KEY_SIZE 16 + struct lease_context { - __le64 LeaseKeyLow; - __le64 LeaseKeyHigh; + __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; __le32 LeaseFlags; __le64 LeaseDuration; } __packed; struct lease_context_v2 { - __le64 LeaseKeyLow; - __le64 LeaseKeyHigh; + __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; __le32 LeaseFlags; __le64 LeaseDuration; - __le64 ParentLeaseKeyLow; - __le64 ParentLeaseKeyHigh; + __u8 ParentLeaseKey[SMB2_LEASE_KEY_SIZE]; __le16 Epoch; __le16 Reserved; } __packed; @@ -776,114 +248,12 @@ struct create_lease_v2 { __u8 Pad[4]; } __packed; -/* Currently defined values for close flags */ -#define SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB cpu_to_le16(0x0001) -struct smb2_close_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 24 */ - __le16 Flags; - __le32 Reserved; - __le64 PersistentFileId; - __le64 VolatileFileId; -} __packed; - -struct smb2_close_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* 60 */ - __le16 Flags; - __le32 Reserved; - __le64 CreationTime; - __le64 LastAccessTime; - __le64 LastWriteTime; - __le64 ChangeTime; - __le64 AllocationSize; /* Beginning of FILE_STANDARD_INFO equivalent */ - __le64 EndOfFile; - __le32 Attributes; -} __packed; - -struct smb2_flush_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 24 */ - __le16 Reserved1; - __le32 Reserved2; - __le64 PersistentFileId; - __le64 VolatileFileId; -} __packed; - -struct smb2_flush_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; - __le16 Reserved; -} __packed; - struct smb2_buffer_desc_v1 { __le64 offset; __le32 token; __le32 length; } __packed; -#define SMB2_CHANNEL_NONE cpu_to_le32(0x00000000) -#define SMB2_CHANNEL_RDMA_V1 cpu_to_le32(0x00000001) -#define SMB2_CHANNEL_RDMA_V1_INVALIDATE cpu_to_le32(0x00000002) - -struct smb2_read_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 49 */ - __u8 Padding; /* offset from start of SMB2 header to place read */ - __u8 Reserved; - __le32 Length; - __le64 Offset; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 MinimumCount; - __le32 Channel; /* Reserved MBZ */ - __le32 RemainingBytes; - __le16 ReadChannelInfoOffset; /* Reserved MBZ */ - __le16 ReadChannelInfoLength; /* Reserved MBZ */ - __u8 Buffer[1]; -} __packed; - -struct smb2_read_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 17 */ - __u8 DataOffset; - __u8 Reserved; - __le32 DataLength; - __le32 DataRemaining; - __u32 Reserved2; - __u8 Buffer[1]; -} __packed; - -/* For write request Flags field below the following flag is defined: */ -#define SMB2_WRITEFLAG_WRITE_THROUGH 0x00000001 - -struct smb2_write_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 49 */ - __le16 DataOffset; /* offset from start of SMB2 header to write data */ - __le32 Length; - __le64 Offset; - __le64 PersistentFileId; - __le64 VolatileFileId; - __le32 Channel; /* Reserved MBZ */ - __le32 RemainingBytes; - __le16 WriteChannelInfoOffset; /* Reserved MBZ */ - __le16 WriteChannelInfoLength; /* Reserved MBZ */ - __le32 Flags; - __u8 Buffer[1]; -} __packed; - -struct smb2_write_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 17 */ - __u8 DataOffset; - __u8 Reserved; - __le32 DataLength; - __le32 DataRemaining; - __u32 Reserved2; - __u8 Buffer[1]; -} __packed; - #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 struct duplicate_extents_to_file { @@ -1033,43 +403,6 @@ struct reparse_data_buffer { __u8 DataBuffer[]; /* Variable Length */ } __packed; -/* Completion Filter flags for Notify */ -#define FILE_NOTIFY_CHANGE_FILE_NAME 0x00000001 -#define FILE_NOTIFY_CHANGE_DIR_NAME 0x00000002 -#define FILE_NOTIFY_CHANGE_NAME 0x00000003 -#define FILE_NOTIFY_CHANGE_ATTRIBUTES 0x00000004 -#define FILE_NOTIFY_CHANGE_SIZE 0x00000008 -#define FILE_NOTIFY_CHANGE_LAST_WRITE 0x00000010 -#define FILE_NOTIFY_CHANGE_LAST_ACCESS 0x00000020 -#define FILE_NOTIFY_CHANGE_CREATION 0x00000040 -#define FILE_NOTIFY_CHANGE_EA 0x00000080 -#define FILE_NOTIFY_CHANGE_SECURITY 0x00000100 -#define FILE_NOTIFY_CHANGE_STREAM_NAME 0x00000200 -#define FILE_NOTIFY_CHANGE_STREAM_SIZE 0x00000400 -#define FILE_NOTIFY_CHANGE_STREAM_WRITE 0x00000800 - -/* Flags */ -#define SMB2_WATCH_TREE 0x0001 - -struct smb2_notify_req { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 32 */ - __le16 Flags; - __le32 OutputBufferLength; - __le64 PersistentFileId; - __le64 VolatileFileId; - __u32 CompletionFileter; - __u32 Reserved; -} __packed; - -struct smb2_notify_rsp { - struct smb2_hdr hdr; - __le16 StructureSize; /* Must be 9 */ - __le16 OutputBufferOffset; - __le32 OutputBufferLength; - __u8 Buffer[1]; -} __packed; - /* SMB2 Notify Action Flags */ #define FILE_ACTION_ADDED 0x00000001 #define FILE_ACTION_REMOVED 0x00000002 @@ -1528,7 +861,7 @@ struct smb2_file_pos_info { __le64 CurrentByteOffset; } __packed; -#define FILE_MODE_INFO_MASK cpu_to_le32(0x0000103e) +#define FILE_MODE_INFO_MASK cpu_to_le32(0x0000100e) struct smb2_file_mode_info { __le32 Mode; @@ -1705,4 +1038,13 @@ int smb2_ioctl(struct ksmbd_work *work); int smb2_oplock_break(struct ksmbd_work *work); int smb2_notify(struct ksmbd_work *ksmbd_work); +/* + * Get the body of the smb2 message excluding the 4 byte rfc1002 headers + * from request/response buffer. + */ +static inline void *smb2_get_msg(void *buf) +{ + return buf + 4; +} + #endif /* _SMB2PDU_H */ diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 707490ab1f4c..ef7f42b0290a 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -132,7 +132,7 @@ int ksmbd_lookup_protocol_idx(char *str) */ int ksmbd_verify_smb_message(struct ksmbd_work *work) { - struct smb2_hdr *smb2_hdr = work->request_buf + work->next_smb2_rcv_hdr_off; + struct smb2_hdr *smb2_hdr = ksmbd_req_buf_next(work); struct smb_hdr *hdr; if (smb2_hdr->ProtocolId == SMB2_PROTO_NUMBER) @@ -239,14 +239,14 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count) static int ksmbd_negotiate_smb_dialect(void *buf) { int smb_buf_length = get_rfc1002_len(buf); - __le32 proto = ((struct smb2_hdr *)buf)->ProtocolId; + __le32 proto = ((struct smb2_hdr *)smb2_get_msg(buf))->ProtocolId; if (proto == SMB2_PROTO_NUMBER) { struct smb2_negotiate_req *req; int smb2_neg_size = - offsetof(struct smb2_negotiate_req, Dialects) - 4; + offsetof(struct smb2_negotiate_req, Dialects); - req = (struct smb2_negotiate_req *)buf; + req = (struct smb2_negotiate_req *)smb2_get_msg(buf); if (smb2_neg_size > smb_buf_length) goto err_out; @@ -445,11 +445,12 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) struct ksmbd_conn *conn = work->conn; int ret; - conn->dialect = ksmbd_negotiate_smb_dialect(work->request_buf); + conn->dialect = + ksmbd_negotiate_smb_dialect(work->request_buf); ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); if (command == SMB2_NEGOTIATE_HE) { - struct smb2_hdr *smb2_hdr = work->request_buf; + struct smb2_hdr *smb2_hdr = smb2_get_msg(work->request_buf); if (smb2_hdr->ProtocolId != SMB2_PROTO_NUMBER) { ksmbd_debug(SMB, "Downgrade to SMB1 negotiation\n"); diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index 6e79e7577f6b..50590842b651 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -10,6 +10,7 @@ #include "glob.h" #include "nterr.h" +#include "../smbfs_common/smb2pdu.h" #include "smb2pdu.h" /* ksmbd's Specific ERRNO */ @@ -32,17 +33,6 @@ #define SMB302_VERSION_STRING "3.02" #define SMB311_VERSION_STRING "3.1.1" -/* Dialects */ -#define SMB10_PROT_ID 0x00 -#define SMB20_PROT_ID 0x0202 -#define SMB21_PROT_ID 0x0210 -/* multi-protocol negotiate request */ -#define SMB2X_PROT_ID 0x02FF -#define SMB30_PROT_ID 0x0300 -#define SMB302_PROT_ID 0x0302 -#define SMB311_PROT_ID 0x0311 -#define BAD_PROT_ID 0xFFFF - #define SMB_ECHO_INTERVAL (60 * HZ) #define CIFS_DEFAULT_IOSIZE (64 * 1024) @@ -59,21 +49,6 @@ /* * File Attribute flags */ -#define ATTR_READONLY 0x0001 -#define ATTR_HIDDEN 0x0002 -#define ATTR_SYSTEM 0x0004 -#define ATTR_VOLUME 0x0008 -#define ATTR_DIRECTORY 0x0010 -#define ATTR_ARCHIVE 0x0020 -#define ATTR_DEVICE 0x0040 -#define ATTR_NORMAL 0x0080 -#define ATTR_TEMPORARY 0x0100 -#define ATTR_SPARSE 0x0200 -#define ATTR_REPARSE 0x0400 -#define ATTR_COMPRESSED 0x0800 -#define ATTR_OFFLINE 0x1000 -#define ATTR_NOT_CONTENT_INDEXED 0x2000 -#define ATTR_ENCRYPTED 0x4000 #define ATTR_POSIX_SEMANTICS 0x01000000 #define ATTR_BACKUP_SEMANTICS 0x02000000 #define ATTR_DELETE_ON_CLOSE 0x04000000 @@ -82,23 +57,6 @@ #define ATTR_NO_BUFFERING 0x20000000 #define ATTR_WRITE_THROUGH 0x80000000 -#define ATTR_READONLY_LE cpu_to_le32(ATTR_READONLY) -#define ATTR_HIDDEN_LE cpu_to_le32(ATTR_HIDDEN) -#define ATTR_SYSTEM_LE cpu_to_le32(ATTR_SYSTEM) -#define ATTR_DIRECTORY_LE cpu_to_le32(ATTR_DIRECTORY) -#define ATTR_ARCHIVE_LE cpu_to_le32(ATTR_ARCHIVE) -#define ATTR_NORMAL_LE cpu_to_le32(ATTR_NORMAL) -#define ATTR_TEMPORARY_LE cpu_to_le32(ATTR_TEMPORARY) -#define ATTR_SPARSE_FILE_LE cpu_to_le32(ATTR_SPARSE) -#define ATTR_REPARSE_POINT_LE cpu_to_le32(ATTR_REPARSE) -#define ATTR_COMPRESSED_LE cpu_to_le32(ATTR_COMPRESSED) -#define ATTR_OFFLINE_LE cpu_to_le32(ATTR_OFFLINE) -#define ATTR_NOT_CONTENT_INDEXED_LE cpu_to_le32(ATTR_NOT_CONTENT_INDEXED) -#define ATTR_ENCRYPTED_LE cpu_to_le32(ATTR_ENCRYPTED) -#define ATTR_INTEGRITY_STREAML_LE cpu_to_le32(0x00008000) -#define ATTR_NO_SCRUB_DATA_LE cpu_to_le32(0x00020000) -#define ATTR_MASK_LE cpu_to_le32(0x00007FB7) - /* List of FileSystemAttributes - see 2.5.1 of MS-FSCC */ #define FILE_SUPPORTS_SPARSE_VDL 0x10000000 /* faster nonsparse extend */ #define FILE_SUPPORTS_BLOCK_REFCOUNTING 0x08000000 /* allow ioctl dup extents */ @@ -160,11 +118,6 @@ /* file_execute, file_read_attributes*/ /* write_dac, and delete. */ -#define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA | FILE_READ_ATTRIBUTES) -#define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \ - | FILE_WRITE_EA | FILE_WRITE_ATTRIBUTES) -#define FILE_EXEC_RIGHTS (FILE_EXECUTE) - #define SET_FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA \ | FILE_READ_ATTRIBUTES \ | DELETE | READ_CONTROL | WRITE_DAC \ @@ -477,12 +430,6 @@ struct smb_version_cmds { int (*proc)(struct ksmbd_work *swork); }; -static inline size_t -smb2_hdr_size_no_buflen(struct smb_version_values *vals) -{ - return vals->header_size - 4; -} - int ksmbd_min_protocol(void); int ksmbd_max_protocol(void); diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index a2fd5a4d4cd5..7e57cbb0bb35 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -484,7 +484,7 @@ static int smb_direct_check_recvmsg(struct smb_direct_recvmsg *recvmsg) struct smb_direct_data_transfer *req = (struct smb_direct_data_transfer *)recvmsg->packet; struct smb2_hdr *hdr = (struct smb2_hdr *)(recvmsg->packet - + le32_to_cpu(req->data_offset) - 4); + + le32_to_cpu(req->data_offset)); ksmbd_debug(RDMA, "CreditGranted: %u, CreditRequested: %u, DataLength: %u, RemainingDataLength: %u, SMB: %x, Command: %u\n", le16_to_cpu(req->credits_granted), @@ -2043,7 +2043,6 @@ int ksmbd_rdma_destroy(void) smb_direct_listener.cm_id = NULL; if (smb_direct_wq) { - flush_workqueue(smb_direct_wq); destroy_workqueue(smb_direct_wq); smb_direct_wq = NULL; } diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 835b384b0895..19d36393974c 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -1013,7 +1013,7 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp, loff_t off, loff_t len) { smb_break_all_levII_oplock(work, fp, 1); - if (fp->f_ci->m_fattr & ATTR_SPARSE_FILE_LE) + if (fp->f_ci->m_fattr & FILE_ATTRIBUTE_SPARSE_FILE_LE) return vfs_fallocate(fp->filp, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, off, len); @@ -1624,7 +1624,7 @@ void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat) time = ksmbd_UnixTimeToNT(kstat->ctime); info->ChangeTime = cpu_to_le64(time); - if (ksmbd_kstat->file_attributes & ATTR_DIRECTORY_LE) { + if (ksmbd_kstat->file_attributes & FILE_ATTRIBUTE_DIRECTORY_LE) { info->EndOfFile = 0; info->AllocationSize = 0; } else { @@ -1654,9 +1654,9 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, * or that acl is disable in server's filesystem and the config is yes. */ if (S_ISDIR(ksmbd_kstat->kstat->mode)) - ksmbd_kstat->file_attributes = ATTR_DIRECTORY_LE; + ksmbd_kstat->file_attributes = FILE_ATTRIBUTE_DIRECTORY_LE; else - ksmbd_kstat->file_attributes = ATTR_ARCHIVE_LE; + ksmbd_kstat->file_attributes = FILE_ATTRIBUTE_ARCHIVE_LE; if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS)) { diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index b0d5b8feb4a3..adf94a4f22fa 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -25,48 +25,9 @@ enum { }; /* CreateOptions */ -/* Flag is set, it must not be a file , valid for directory only */ -#define FILE_DIRECTORY_FILE_LE cpu_to_le32(0x00000001) -#define FILE_WRITE_THROUGH_LE cpu_to_le32(0x00000002) -#define FILE_SEQUENTIAL_ONLY_LE cpu_to_le32(0x00000004) - -/* Should not buffer on server*/ -#define FILE_NO_INTERMEDIATE_BUFFERING_LE cpu_to_le32(0x00000008) -/* MBZ */ -#define FILE_SYNCHRONOUS_IO_ALERT_LE cpu_to_le32(0x00000010) -/* MBZ */ -#define FILE_SYNCHRONOUS_IO_NONALERT_LE cpu_to_le32(0x00000020) - -/* Flaf must not be set for directory */ -#define FILE_NON_DIRECTORY_FILE_LE cpu_to_le32(0x00000040) - -/* Should be zero */ #define CREATE_TREE_CONNECTION cpu_to_le32(0x00000080) -#define FILE_COMPLETE_IF_OPLOCKED_LE cpu_to_le32(0x00000100) -#define FILE_NO_EA_KNOWLEDGE_LE cpu_to_le32(0x00000200) -#define FILE_OPEN_REMOTE_INSTANCE cpu_to_le32(0x00000400) - -/** - * Doc says this is obsolete "open for recovery" flag should be zero - * in any case. - */ -#define CREATE_OPEN_FOR_RECOVERY cpu_to_le32(0x00000400) -#define FILE_RANDOM_ACCESS_LE cpu_to_le32(0x00000800) -#define FILE_DELETE_ON_CLOSE_LE cpu_to_le32(0x00001000) -#define FILE_OPEN_BY_FILE_ID_LE cpu_to_le32(0x00002000) -#define FILE_OPEN_FOR_BACKUP_INTENT_LE cpu_to_le32(0x00004000) -#define FILE_NO_COMPRESSION_LE cpu_to_le32(0x00008000) - -/* Should be zero*/ -#define FILE_OPEN_REQUIRING_OPLOCK cpu_to_le32(0x00010000) -#define FILE_DISALLOW_EXCLUSIVE cpu_to_le32(0x00020000) #define FILE_RESERVE_OPFILTER_LE cpu_to_le32(0x00100000) -#define FILE_OPEN_REPARSE_POINT_LE cpu_to_le32(0x00200000) -#define FILE_OPEN_NO_RECALL_LE cpu_to_le32(0x00400000) -/* Should be zero */ -#define FILE_OPEN_FOR_FREE_SPACE_QUERY_LE cpu_to_le32(0x00800000) -#define CREATE_OPTIONS_MASK cpu_to_le32(0x00FFFFFF) #define CREATE_OPTION_READONLY 0x10000000 /* system. NB not sent over wire */ #define CREATE_OPTION_SPECIAL 0x20000000 diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 994ec22d4040..9320a42dfaf9 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -230,7 +230,7 @@ static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async /* * Deal with the completion of writing the data to the cache. We have to clear - * the PG_fscache bits on the pages involved and release the caller's ref. + * the PG_fscache bits on the folios involved and release the caller's ref. * * May be called in softirq mode and we inherit a ref from the caller. */ @@ -238,7 +238,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, bool was_async) { struct netfs_read_subrequest *subreq; - struct page *page; + struct folio *folio; pgoff_t unlocked = 0; bool have_unlocked = false; @@ -247,14 +247,14 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); - xas_for_each(&xas, page, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { /* We might have multiple writes from the same huge - * page, but we mustn't unlock a page more than once. + * folio, but we mustn't unlock a folio more than once. */ - if (have_unlocked && page->index <= unlocked) + if (have_unlocked && folio_index(folio) <= unlocked) continue; - unlocked = page->index; - end_page_fscache(page); + unlocked = folio_index(folio); + folio_end_fscache(folio); have_unlocked = true; } } @@ -367,18 +367,17 @@ static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq, } /* - * Unlock the pages in a read operation. We need to set PG_fscache on any - * pages we're going to write back before we unlock them. + * Unlock the folios in a read operation. We need to set PG_fscache on any + * folios we're going to write back before we unlock them. */ static void netfs_rreq_unlock(struct netfs_read_request *rreq) { struct netfs_read_subrequest *subreq; - struct page *page; + struct folio *folio; unsigned int iopos, account = 0; pgoff_t start_page = rreq->start / PAGE_SIZE; pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; bool subreq_failed = false; - int i; XA_STATE(xas, &rreq->mapping->i_pages, start_page); @@ -403,9 +402,9 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); rcu_read_lock(); - xas_for_each(&xas, page, last_page) { - unsigned int pgpos = (page->index - start_page) * PAGE_SIZE; - unsigned int pgend = pgpos + thp_size(page); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); bool pg_failed = false; for (;;) { @@ -414,7 +413,7 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) break; } if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - set_page_fscache(page); + folio_start_fscache(folio); pg_failed |= subreq_failed; if (pgend < iopos + subreq->len) break; @@ -433,17 +432,16 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) } if (!pg_failed) { - for (i = 0; i < thp_nr_pages(page); i++) - flush_dcache_page(page); - SetPageUptodate(page); + flush_dcache_folio(folio); + folio_mark_uptodate(folio); } - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_PAGES, &rreq->flags)) { - if (page->index == rreq->no_unlock_page && - test_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags)) + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio_index(folio) == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) _debug("no unlock"); else - unlock_page(page); + folio_unlock(folio); } } rcu_read_unlock(); @@ -876,7 +874,6 @@ void netfs_readahead(struct readahead_control *ractl, void *netfs_priv) { struct netfs_read_request *rreq; - struct page *page; unsigned int debug_index = 0; int ret; @@ -911,11 +908,11 @@ void netfs_readahead(struct readahead_control *ractl, } while (rreq->submitted < rreq->len); - /* Drop the refs on the pages here rather than in the cache or + /* Drop the refs on the folios here rather than in the cache or * filesystem. The locks will be dropped in netfs_rreq_unlock(). */ - while ((page = readahead_page(ractl))) - put_page(page); + while (readahead_folio(ractl)) + ; /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ if (atomic_dec_and_test(&rreq->nr_rd_ops)) @@ -935,7 +932,7 @@ EXPORT_SYMBOL(netfs_readahead); /** * netfs_readpage - Helper to manage a readpage request * @file: The file to read from - * @page: The page to read + * @folio: The folio to read * @ops: The network filesystem's operations for the helper to use * @netfs_priv: Private netfs data to be retained in the request * @@ -950,7 +947,7 @@ EXPORT_SYMBOL(netfs_readahead); * This is usable whether or not caching is enabled. */ int netfs_readpage(struct file *file, - struct page *page, + struct folio *folio, const struct netfs_read_request_ops *ops, void *netfs_priv) { @@ -958,23 +955,23 @@ int netfs_readpage(struct file *file, unsigned int debug_index = 0; int ret; - _enter("%lx", page_index(page)); + _enter("%lx", folio_index(folio)); rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) { if (netfs_priv) - ops->cleanup(netfs_priv, page_file_mapping(page)); - unlock_page(page); + ops->cleanup(netfs_priv, folio_file_mapping(folio)); + folio_unlock(folio); return -ENOMEM; } - rreq->mapping = page_file_mapping(page); - rreq->start = page_file_offset(page); - rreq->len = thp_size(page); + rreq->mapping = folio_file_mapping(folio); + rreq->start = folio_file_pos(folio); + rreq->len = folio_size(folio); if (ops->begin_cache_operation) { ret = ops->begin_cache_operation(rreq); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) { - unlock_page(page); + folio_unlock(folio); goto out; } } @@ -1012,40 +1009,40 @@ out: EXPORT_SYMBOL(netfs_readpage); /** - * netfs_skip_page_read - prep a page for writing without reading first - * @page: page being prepared + * netfs_skip_folio_read - prep a folio for writing without reading first + * @folio: The folio being prepared * @pos: starting position for the write * @len: length of write * * In some cases, write_begin doesn't need to read at all: - * - full page write - * - write that lies in a page that is completely beyond EOF - * - write that covers the the page from start to EOF or beyond it + * - full folio write + * - write that lies in a folio that is completely beyond EOF + * - write that covers the folio from start to EOF or beyond it * * If any of these criteria are met, then zero out the unwritten parts - * of the page and return true. Otherwise, return false. + * of the folio and return true. Otherwise, return false. */ -static bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len) +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio_inode(folio); loff_t i_size = i_size_read(inode); - size_t offset = offset_in_thp(page, pos); + size_t offset = offset_in_folio(folio, pos); - /* Full page write */ - if (offset == 0 && len >= thp_size(page)) + /* Full folio write */ + if (offset == 0 && len >= folio_size(folio)) return true; - /* pos beyond last page in the file */ + /* pos beyond last folio in the file */ if (pos - offset >= i_size) goto zero_out; - /* Write that covers from the start of the page to EOF or beyond */ + /* Write that covers from the start of the folio to EOF or beyond */ if (offset == 0 && (pos + len) >= i_size) goto zero_out; return false; zero_out: - zero_user_segments(page, 0, offset, offset + len, thp_size(page)); + zero_user_segments(&folio->page, 0, offset, offset + len, folio_size(folio)); return true; } @@ -1054,9 +1051,9 @@ zero_out: * @file: The file to read from * @mapping: The mapping to read from * @pos: File position at which the write will begin - * @len: The length of the write (may extend beyond the end of the page chosen) - * @flags: AOP_* flags - * @_page: Where to put the resultant page + * @len: The length of the write (may extend beyond the end of the folio chosen) + * @aop_flags: AOP_* flags + * @_folio: Where to put the resultant folio * @_fsdata: Place for the netfs to store a cookie * @ops: The network filesystem's operations for the helper to use * @netfs_priv: Private netfs data to be retained in the request @@ -1072,37 +1069,41 @@ zero_out: * issue_op, is mandatory. * * The check_write_begin() operation can be provided to check for and flush - * conflicting writes once the page is grabbed and locked. It is passed a + * conflicting writes once the folio is grabbed and locked. It is passed a * pointer to the fsdata cookie that gets returned to the VM to be passed to * write_end. It is permitted to sleep. It should return 0 if the request - * should go ahead; unlock the page and return -EAGAIN to cause the page to be - * regot; or return an error. + * should go ahead; unlock the folio and return -EAGAIN to cause the folio to + * be regot; or return an error. * * This is usable whether or not caching is enabled. */ int netfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int flags, - struct page **_page, void **_fsdata, + loff_t pos, unsigned int len, unsigned int aop_flags, + struct folio **_folio, void **_fsdata, const struct netfs_read_request_ops *ops, void *netfs_priv) { struct netfs_read_request *rreq; - struct page *page, *xpage; + struct folio *folio; struct inode *inode = file_inode(file); - unsigned int debug_index = 0; + unsigned int debug_index = 0, fgp_flags; pgoff_t index = pos >> PAGE_SHIFT; int ret; DEFINE_READAHEAD(ractl, file, NULL, mapping, index); retry: - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) + fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) return -ENOMEM; if (ops->check_write_begin) { /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ops->check_write_begin(file, pos, len, page, _fsdata); + ret = ops->check_write_begin(file, pos, len, folio, _fsdata); if (ret < 0) { trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); if (ret == -EAGAIN) @@ -1111,28 +1112,28 @@ retry: } } - if (PageUptodate(page)) - goto have_page; + if (folio_test_uptodate(folio)) + goto have_folio; /* If the page is beyond the EOF, we want to clear it - unless it's * within the cache granule containing the EOF, in which case we need * to preload the granule. */ if (!ops->is_cache_enabled(inode) && - netfs_skip_page_read(page, pos, len)) { + netfs_skip_folio_read(folio, pos, len)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_page_no_wait; + goto have_folio_no_wait; } ret = -ENOMEM; rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) goto error; - rreq->mapping = page->mapping; - rreq->start = page_offset(page); - rreq->len = thp_size(page); - rreq->no_unlock_page = page->index; - __set_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags); + rreq->mapping = folio_file_mapping(folio); + rreq->start = folio_file_pos(folio); + rreq->len = folio_size(folio); + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); netfs_priv = NULL; if (ops->begin_cache_operation) { @@ -1147,14 +1148,14 @@ retry: /* Expand the request to meet caching requirements and download * preferences. */ - ractl._nr_pages = thp_nr_pages(page); + ractl._nr_pages = folio_nr_pages(folio); netfs_rreq_expand(rreq, &ractl); netfs_get_read_request(rreq); - /* We hold the page locks, so we can drop the references */ - while ((xpage = readahead_page(&ractl))) - if (xpage != page) - put_page(xpage); + /* We hold the folio locks, so we can drop the references */ + folio_get(folio); + while (readahead_folio(&ractl)) + ; atomic_set(&rreq->nr_rd_ops, 1); do { @@ -1184,22 +1185,22 @@ retry: if (ret < 0) goto error; -have_page: - ret = wait_on_page_fscache_killable(page); +have_folio: + ret = folio_wait_fscache_killable(folio); if (ret < 0) goto error; -have_page_no_wait: +have_folio_no_wait: if (netfs_priv) ops->cleanup(netfs_priv, mapping); - *_page = page; + *_folio = folio; _leave(" = 0"); return 0; error_put: netfs_put_read_request(rreq, false); error: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (netfs_priv) ops->cleanup(netfs_priv, mapping); _leave(" = %d", ret); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index b9614db48b1d..f243cb5e6a4f 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -218,7 +218,7 @@ static int zbufsize_842(size_t size) #if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS) static int zbufsize_zstd(size_t size) { - return ZSTD_compressBound(size); + return zstd_compress_bound(size); } #endif diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c index 0015cf8b5582..c40445dbf38c 100644 --- a/fs/squashfs/zstd_wrapper.c +++ b/fs/squashfs/zstd_wrapper.c @@ -34,7 +34,7 @@ static void *zstd_init(struct squashfs_sb_info *msblk, void *buff) goto failed; wksp->window_size = max_t(size_t, msblk->block_size, SQUASHFS_METADATA_SIZE); - wksp->mem_size = ZSTD_DStreamWorkspaceBound(wksp->window_size); + wksp->mem_size = zstd_dstream_workspace_bound(wksp->window_size); wksp->mem = vmalloc(wksp->mem_size); if (wksp->mem == NULL) goto failed; @@ -63,15 +63,15 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, struct squashfs_page_actor *output) { struct workspace *wksp = strm; - ZSTD_DStream *stream; + zstd_dstream *stream; size_t total_out = 0; int error = 0; - ZSTD_inBuffer in_buf = { NULL, 0, 0 }; - ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + zstd_in_buffer in_buf = { NULL, 0, 0 }; + zstd_out_buffer out_buf = { NULL, 0, 0 }; struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); - stream = ZSTD_initDStream(wksp->window_size, wksp->mem, wksp->mem_size); + stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size); if (!stream) { ERROR("Failed to initialize zstd decompressor\n"); @@ -116,14 +116,14 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, } total_out -= out_buf.pos; - zstd_err = ZSTD_decompressStream(stream, &out_buf, &in_buf); + zstd_err = zstd_decompress_stream(stream, &out_buf, &in_buf); total_out += out_buf.pos; /* add the additional data produced */ if (zstd_err == 0) break; - if (ZSTD_isError(zstd_err)) { + if (zstd_is_error(zstd_err)) { ERROR("zstd decompression error: %d\n", - (int)ZSTD_getErrorCode(zstd_err)); + (int)zstd_get_error_code(zstd_err)); error = -EIO; break; } |