From patchwork Thu Aug 25 13:31:22 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jeff Layton X-Patchwork-Id: 600000 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5AC4AC3F6B0 for ; Thu, 25 Aug 2022 13:32:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S242810AbiHYNcH (ORCPT ); Thu, 25 Aug 2022 09:32:07 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:36862 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S242753AbiHYNbx (ORCPT ); Thu, 25 Aug 2022 09:31:53 -0400 Received: from dfw.source.kernel.org (dfw.source.kernel.org [IPv6:2604:1380:4641:c500::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B8DC6B5169 for ; Thu, 25 Aug 2022 06:31:49 -0700 (PDT) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id 9A0AA61CFD for ; Thu, 25 Aug 2022 13:31:48 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 906E0C43470; Thu, 25 Aug 2022 13:31:47 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1661434308; bh=gzbJ3vpZYn3C2puFdD9XXRBqOjArPCWr5BZ71jGVmDc=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=Pyzzk76vlp4RqqOcMBovHEjmrwlVMrXESTzjPVH+iZ+jrKnoyH8kbUBjvj07etUJQ e804xGz2/u4gCT4iyCtrOjTIbr6YGaxouaVEE2U6xNdXCS30nLLsvDgw3cuQ6qYqbE eFHTo886RhbQBK0cRfpU2fYLC/W+emdazABH2bqJDNm+4ayG/qUZcelnnBmbwE1Yyy w77rlpd/J2Qit1MUjJuNUOwOV03legA2pcnEjpVG8yTayHQV4/U0lJohtR/m+7+1ur Wk37Ia7b0tvBKYtZ2y5BfaH7PftLjwQ8n2jOt9AcrWOIp6eRRMCO9BG3s7W2BLdImM TFPOoGRiEeyWA== From: Jeff Layton To: xiubli@redhat.com, idryomov@gmail.com Cc: lhenriques@suse.de, ceph-devel@vger.kernel.org Subject: [PATCH v15 19/29] ceph: plumb in decryption during sync reads Date: Thu, 25 Aug 2022 09:31:22 -0400 Message-Id: <20220825133132.153657-20-jlayton@kernel.org> X-Mailer: git-send-email 2.37.2 In-Reply-To: <20220825133132.153657-1-jlayton@kernel.org> References: <20220825133132.153657-1-jlayton@kernel.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org Switch to using sparse reads when the inode is encrypted. Note that the crypto block may be smaller than a page, but the reverse cannot be true. Reviewed-by: Xiubo Li Signed-off-by: Jeff Layton --- fs/ceph/file.c | 89 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 65 insertions(+), 24 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 064af05da955..3ebdc43959a4 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -962,7 +962,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, u64 off = *ki_pos; u64 len = iov_iter_count(to); u64 i_size = i_size_read(inode); - bool sparse = ceph_test_mount_opt(fsc, SPARSEREAD); + bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD); u64 objver = 0; dout("sync_read on inode %p %llx~%llx\n", inode, *ki_pos, len); @@ -990,10 +990,19 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, int idx; size_t left; struct ceph_osd_req_op *op; + u64 read_off = off; + u64 read_len = len; + + /* determine new offset/length if encrypted */ + ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len); + + dout("sync_read orig %llu~%llu reading %llu~%llu", + off, len, read_off, read_len); req = ceph_osdc_new_request(osdc, &ci->i_layout, - ci->i_vino, off, &len, 0, 1, - sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ, + ci->i_vino, read_off, &read_len, 0, 1, + sparse ? CEPH_OSD_OP_SPARSE_READ : + CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, NULL, ci->i_truncate_seq, ci->i_truncate_size, false); @@ -1002,10 +1011,13 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } + /* adjust len downward if the request truncated the len */ + if (off + len > read_off + read_len) + len = read_off + read_len - off; more = len < iov_iter_count(to); - num_pages = calc_pages_for(off, len); - page_off = off & ~PAGE_MASK; + num_pages = calc_pages_for(read_off, read_len); + page_off = offset_in_page(off); pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL); if (IS_ERR(pages)) { ceph_osdc_put_request(req); @@ -1013,7 +1025,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } - osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off, + osd_req_op_extent_osd_data_pages(req, 0, pages, read_len, + offset_in_page(read_off), false, false); op = &req->r_ops[0]; @@ -1031,7 +1044,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency, req->r_end_latency, - len, ret); + read_len, ret); if (ret > 0) objver = req->r_version; @@ -1046,8 +1059,34 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, else if (ret == -ENOENT) ret = 0; + if (ret > 0 && IS_ENCRYPTED(inode)) { + int fret; + + fret = ceph_fscrypt_decrypt_extents(inode, pages, read_off, + op->extent.sparse_ext, op->extent.sparse_ext_cnt); + if (fret < 0) { + ret = fret; + ceph_osdc_put_request(req); + break; + } + + /* account for any partial block at the beginning */ + fret -= (off - read_off); + + /* + * Short read after big offset adjustment? + * Nothing is usable, just call it a zero + * len read. + */ + fret = max(fret, 0); + + /* account for partial block at the end */ + ret = min_t(ssize_t, fret, len); + } + ceph_osdc_put_request(req); + /* Short read but not EOF? Zero out the remainder. */ if (ret >= 0 && ret < len && (off + ret < i_size)) { int zlen = min(len - ret, i_size - off - ret); int zoff = page_off + ret; @@ -1061,15 +1100,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, idx = 0; left = ret > 0 ? ret : 0; while (left > 0) { - size_t len, copied; - page_off = off & ~PAGE_MASK; - len = min_t(size_t, left, PAGE_SIZE - page_off); + size_t plen, copied; + + plen = min_t(size_t, left, PAGE_SIZE - page_off); SetPageUptodate(pages[idx]); copied = copy_page_to_iter(pages[idx++], - page_off, len, to); + page_off, plen, to); off += copied; left -= copied; - if (copied < len) { + page_off = 0; + if (copied < plen) { ret = -EFAULT; break; } @@ -1086,20 +1126,21 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } - if (off > *ki_pos) { - if (off >= i_size) { - *retry_op = CHECK_EOF; - ret = i_size - *ki_pos; - *ki_pos = i_size; - } else { - ret = off - *ki_pos; - *ki_pos = off; + if (ret > 0) { + if (off > *ki_pos) { + if (off >= i_size) { + *retry_op = CHECK_EOF; + ret = i_size - *ki_pos; + *ki_pos = i_size; + } else { + ret = off - *ki_pos; + *ki_pos = off; + } } - } - - if (last_objver && ret > 0) - *last_objver = objver; + if (last_objver) + *last_objver = objver; + } dout("sync_read result %zd retry_op %d\n", ret, *retry_op); return ret; }