Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-19.0 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id EB78BC63798 for ; Fri, 20 Nov 2020 15:30:13 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A85402245B for ; Fri, 20 Nov 2020 15:30:13 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=kernel.org header.i=@kernel.org header.b="tKEDmCdP" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728269AbgKTPaL (ORCPT ); Fri, 20 Nov 2020 10:30:11 -0500 Received: from mail.kernel.org ([198.145.29.99]:35118 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728101AbgKTPaL (ORCPT ); Fri, 20 Nov 2020 10:30:11 -0500 Received: from tleilax.com (68-20-15-154.lightspeed.rlghnc.sbcglobal.net [68.20.15.154]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 49FD82240B; Fri, 20 Nov 2020 15:30:10 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1605886210; bh=HgptVtXk0KODIViYZ6gP3+OylZjrA9DS/b4BGh5+odc=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=tKEDmCdPOjGJu/k9p61WmbqM6cMXFI/NaK9SmQhFY4QPW85gn08jwEeAEi6M8Hb/G lGrbOb7QId7eylMHqk6oQAO7NCXIjEbNqBQycWZd2IqWcuR0IcshYLmqNgep87pUob 9ZHPtSCNp+pLpqoy0M2gkFk6Vf6tEua47t00prNg= From: Jeff Layton To: ceph-devel@vger.kernel.org Cc: linux-cachefs@redhat.com, idryomov@redhat.com, dhowells@redhat.com Subject: [PATCH 3/5] ceph: plug write_begin into read helper Date: Fri, 20 Nov 2020 10:30:04 -0500 Message-Id: <20201120153006.304296-4-jlayton@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: <20201120153006.304296-1-jlayton@kernel.org> References: <20201120153006.304296-1-jlayton@kernel.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org Convert ceph_write_begin to use the netfs_write_begin helper. Most of the ops we need for it are already in place from the readpage conversion but we do add a new check_write_begin op since ceph needs to be able to vet whether there is an incompatible writeback already in flight before reading in the page. With this, we can also remove the old ceph_do_readpage helper. Signed-off-by: Jeff Layton --- fs/ceph/addr.c | 187 ++++++++++++++++--------------------------------- 1 file changed, 61 insertions(+), 126 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 9dd9bb3f4696..dfd9fa05e0e1 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -342,76 +342,6 @@ static int ceph_readpage(struct file *filp, struct page *page) return netfs_readpage(filp, page, &ceph_readpage_netfs_ops, NULL); } -/* read a single page, without unlocking it. */ -static int ceph_do_readpage(struct file *filp, struct page *page) -{ - struct inode *inode = file_inode(filp); - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - struct ceph_osd_client *osdc = &fsc->client->osdc; - struct ceph_osd_request *req; - struct ceph_vino vino = ceph_vino(inode); - int err = 0; - u64 off = page_offset(page); - u64 len = PAGE_SIZE; - - if (off >= i_size_read(inode)) { - zero_user_segment(page, 0, PAGE_SIZE); - SetPageUptodate(page); - return 0; - } - - if (ci->i_inline_version != CEPH_INLINE_NONE) { - /* - * Uptodate inline data should have been added - * into page cache while getting Fcr caps. - */ - if (off == 0) - return -EINVAL; - zero_user_segment(page, 0, PAGE_SIZE); - SetPageUptodate(page); - return 0; - } - - dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n", - vino.ino, vino.snap, filp, off, len, page, page->index); - req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len, 0, 1, - CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, NULL, - ci->i_truncate_seq, ci->i_truncate_size, - false); - if (IS_ERR(req)) - return PTR_ERR(req); - - osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false); - - err = ceph_osdc_start_request(osdc, req, false); - if (!err) - err = ceph_osdc_wait_request(osdc, req); - - ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency, - req->r_end_latency, err); - - ceph_osdc_put_request(req); - dout("readpage result %d\n", err); - - if (err == -ENOENT) - err = 0; - if (err < 0) { - if (err == -EBLOCKLISTED) - fsc->blocklisted = true; - goto out; - } - if (err < PAGE_SIZE) - /* zero fill remainder of page */ - zero_user_segment(page, err, PAGE_SIZE); - else - flush_dcache_page(page); - - SetPageUptodate(page); -out: - return err < 0 ? err : 0; -} - /* * Finish an async read(ahead) op. */ @@ -1432,6 +1362,40 @@ ceph_find_incompatible(struct page *page) return NULL; } +static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, + struct page *page, 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); + if (snapc) { + int r; + + unlock_page(page); + put_page(page); + if (IS_ERR(snapc)) + return PTR_ERR(snapc); + + ceph_queue_writeback(inode); + r = wait_event_killable(ci->i_cap_wq, + context_is_writeable_or_written(inode, snapc)); + ceph_put_snap_context(snapc); + return r == 0 ? -EAGAIN : r; + } + return 0; +} + +const struct netfs_read_request_ops ceph_netfs_write_begin_ops = { + .init_rreq = ceph_init_rreq, + .is_cache_enabled = ceph_is_cache_enabled, + .begin_cache_operation = ceph_begin_cache_operation, + .issue_op = ceph_netfs_issue_op, + .clamp_length = ceph_netfs_clamp_length, + .check_write_begin = ceph_netfs_check_write_begin, +}; + /* * We are only allowed to write into/dirty the page if the page is * clean, or already dirty within the same snap context. @@ -1442,75 +1406,46 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_snap_context *snapc; struct page *page = NULL; pgoff_t index = pos >> PAGE_SHIFT; - int pos_in_page = pos & ~PAGE_MASK; - int r = 0; - - dout("write_begin file %p inode %p page %p %d~%d\n", file, inode, page, (int)pos, (int)len); - - for (;;) { - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) { - r = -ENOMEM; - break; - } - - snapc = ceph_find_incompatible(page); - if (snapc) { - if (IS_ERR(snapc)) { - r = PTR_ERR(snapc); - break; - } - unlock_page(page); - put_page(page); - page = NULL; - ceph_queue_writeback(inode); - r = wait_event_killable(ci->i_cap_wq, - context_is_writeable_or_written(inode, snapc)); - ceph_put_snap_context(snapc); - if (r != 0) - break; - continue; - } - - if (PageUptodate(page)) { - dout(" page %p already uptodate\n", page); - break; - } + int r; + if (ci->i_inline_version != CEPH_INLINE_NONE) { /* - * In some cases we don't need to read at all: - * - full page write - * - write that lies completely beyond EOF - * - write that covers the the page from start to EOF or beyond it + * In principle, we should never get here, as the inode should have been uninlined + * before we're allowed to write to the page (in write_iter or page_mkwrite). */ - if ((pos_in_page == 0 && len == PAGE_SIZE) || - (pos >= i_size_read(inode)) || - (pos_in_page == 0 && (pos + len) >= i_size_read(inode))) { - zero_user_segments(page, 0, pos_in_page, - pos_in_page + len, PAGE_SIZE); - break; - } + WARN_ONCE(1, "ceph: write_begin called on still-inlined inode!\n"); /* - * We need to read it. If we get back -EINPROGRESS, then the page was - * handed off to fscache and it will be unlocked when the read completes. - * Refind the page in that case so we can reacquire the page lock. Otherwise - * we got a hard error or the read was completed synchronously. + * Uptodate inline data should have been added + * into page cache while getting Fcr caps. */ - r = ceph_do_readpage(file, page); - if (r != -EINPROGRESS) - break; + if (index == 0) { + r = -EINVAL; + goto out; + } + + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; + + zero_user_segment(page, 0, PAGE_SIZE); + SetPageUptodate(page); + r = 0; + goto out; } + r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &page, NULL, + &ceph_netfs_write_begin_ops, NULL); +out: + if (r == 0) + ceph_wait_on_page_fscache(page); if (r < 0) { - if (page) { - unlock_page(page); + if (page) put_page(page); - } } else { + WARN_ON_ONCE(!PageLocked(page)); *pagep = page; } return r; -- 2.28.0