From patchwork Thu Jun 6 13:47:52 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Yan, Zheng" X-Patchwork-Id: 10979577 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id A04DD17D2 for ; Thu, 6 Jun 2019 13:48:03 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 8AC4928981 for ; Thu, 6 Jun 2019 13:48:03 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 7EDF92898B; Thu, 6 Jun 2019 13:48:03 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 9A90828981 for ; Thu, 6 Jun 2019 13:48:02 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727590AbfFFNsB (ORCPT ); Thu, 6 Jun 2019 09:48:01 -0400 Received: from mx1.redhat.com ([209.132.183.28]:34898 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726877AbfFFNsB (ORCPT ); Thu, 6 Jun 2019 09:48:01 -0400 Received: from smtp.corp.redhat.com (int-mx03.intmail.prod.int.phx2.redhat.com [10.5.11.13]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 8B20D30C1AEA for ; Thu, 6 Jun 2019 13:48:00 +0000 (UTC) Received: from zhyan-laptop.redhat.com (ovpn-12-89.pek2.redhat.com [10.72.12.89]) by smtp.corp.redhat.com (Postfix) with ESMTP id A48665F7D8; Thu, 6 Jun 2019 13:47:57 +0000 (UTC) From: "Yan, Zheng" To: ceph-devel@vger.kernel.org Cc: idryomov@redhat.com, jlayton@redhat.com, "Yan, Zheng" Subject: [PATCH 1/3] ceph: pass filp to ceph_get_caps() Date: Thu, 6 Jun 2019 21:47:52 +0800 Message-Id: <20190606134754.31725-1-zyan@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.13 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.40]); Thu, 06 Jun 2019 13:48:00 +0000 (UTC) Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP This is preparetion for checking filp error. Signed-off-by: "Yan, Zheng" --- fs/ceph/addr.c | 15 +++++++++------ fs/ceph/caps.c | 32 +++++++++++++++++--------------- fs/ceph/file.c | 35 +++++++++++++++++------------------ fs/ceph/super.h | 6 +++--- 4 files changed, 46 insertions(+), 42 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index a47c541f8006..4d39fd4c1dd6 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -322,7 +322,8 @@ static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx, /* caller of readpages does not hold buffer and read caps * (fadvise, madvise and readahead cases) */ int want = CEPH_CAP_FILE_CACHE; - ret = ceph_try_get_caps(ci, CEPH_CAP_FILE_RD, want, true, &got); + ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, + true, &got); if (ret < 0) { dout("start_read %p, error getting cap\n", inode); } else if (!(got & want)) { @@ -1450,7 +1451,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) want = CEPH_CAP_FILE_CACHE; got = 0; - err = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, -1, &got, &pinned_page); + err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_RD, want, -1, + &got, &pinned_page); if (err < 0) goto out_restore; @@ -1566,7 +1568,7 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf) want = CEPH_CAP_FILE_BUFFER; got = 0; - err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, off + len, + err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_WR, want, off + len, &got, NULL); if (err < 0) goto out_free; @@ -1986,10 +1988,11 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, return err; } -int ceph_pool_perm_check(struct ceph_inode_info *ci, int need) +int ceph_pool_perm_check(struct inode *inode, int need) { - s64 pool; + struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_string *pool_ns; + s64 pool; int ret, flags; if (ci->i_vino.snap != CEPH_NOSNAP) { @@ -2001,7 +2004,7 @@ int ceph_pool_perm_check(struct ceph_inode_info *ci, int need) return 0; } - if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode), + if (ceph_test_mount_opt(ceph_inode_to_client(inode), NOPOOLPERM)) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index fd9ab97c7f4e..e88a21d830e1 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2545,10 +2545,10 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got, * * FIXME: how does a 0 return differ from -EAGAIN? */ -static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want, +static int try_get_cap_refs(struct inode *inode, int need, int want, loff_t endoff, bool nonblock, int *got) { - struct inode *inode = &ci->vfs_inode; + struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; int ret = 0; int have, implemented; @@ -2716,18 +2716,18 @@ static void check_max_size(struct inode *inode, loff_t endoff) ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); } -int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, +int ceph_try_get_caps(struct inode *inode, int need, int want, bool nonblock, int *got) { int ret; BUG_ON(need & ~CEPH_CAP_FILE_RD); BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO|CEPH_CAP_FILE_SHARED)); - ret = ceph_pool_perm_check(ci, need); + ret = ceph_pool_perm_check(inode, need); if (ret < 0) return ret; - ret = try_get_cap_refs(ci, need, want, 0, nonblock, got); + ret = try_get_cap_refs(inode, need, want, 0, nonblock, got); return ret == -EAGAIN ? 0 : ret; } @@ -2736,21 +2736,23 @@ int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, * due to a small max_size, make sure we check_max_size (and possibly * ask the mds) so we don't get hung up indefinitely. */ -int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, +int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got, struct page **pinned_page) { + struct inode *inode = file_inode(filp); + struct ceph_inode_info *ci = ceph_inode(inode); int _got, ret; - ret = ceph_pool_perm_check(ci, need); + ret = ceph_pool_perm_check(inode, need); if (ret < 0) return ret; while (true) { if (endoff > 0) - check_max_size(&ci->vfs_inode, endoff); + check_max_size(inode, endoff); _got = 0; - ret = try_get_cap_refs(ci, need, want, endoff, + ret = try_get_cap_refs(inode, need, want, endoff, false, &_got); if (ret == -EAGAIN) continue; @@ -2758,8 +2760,8 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(&ci->i_cap_wq, &wait); - while (!(ret = try_get_cap_refs(ci, need, want, endoff, - true, &_got))) { + while (!(ret = try_get_cap_refs(inode, need, want, + endoff, true, &_got))) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -2774,7 +2776,7 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, if (ret < 0) { if (ret == -ESTALE) { /* session was killed, try renew caps */ - ret = ceph_renew_caps(&ci->vfs_inode); + ret = ceph_renew_caps(inode); if (ret == 0) continue; } @@ -2783,9 +2785,9 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, if (ci->i_inline_version != CEPH_INLINE_NONE && (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) && - i_size_read(&ci->vfs_inode) > 0) { + i_size_read(inode) > 0) { struct page *page = - find_get_page(ci->vfs_inode.i_mapping, 0); + find_get_page(inode->i_mapping, 0); if (page) { if (PageUptodate(page)) { *pinned_page = page; @@ -2804,7 +2806,7 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, * getattr request will bring inline data into * page cache */ - ret = __ceph_do_getattr(&ci->vfs_inode, NULL, + ret = __ceph_do_getattr(inode, NULL, CEPH_STAT_CAP_INLINE_DATA, true); if (ret < 0) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 2fe8ca7805f4..300cbaf09aa1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1260,7 +1260,8 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to) want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO; else want = CEPH_CAP_FILE_CACHE; - ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want, -1, &got, &pinned_page); + ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1, + &got, &pinned_page); if (ret < 0) return ret; @@ -1455,7 +1456,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) else want = CEPH_CAP_FILE_BUFFER; got = 0; - err = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, pos + count, + err = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, pos + count, &got, NULL); if (err < 0) goto out; @@ -1779,7 +1780,7 @@ static long ceph_fallocate(struct file *file, int mode, else want = CEPH_CAP_FILE_BUFFER; - ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, endoff, &got, NULL); + ret = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, endoff, &got, NULL); if (ret < 0) goto unlock; @@ -1808,16 +1809,15 @@ static long ceph_fallocate(struct file *file, int mode, * src_ci. Two attempts are made to obtain both caps, and an error is return if * this fails; zero is returned on success. */ -static int get_rd_wr_caps(struct ceph_inode_info *src_ci, - loff_t src_endoff, int *src_got, - struct ceph_inode_info *dst_ci, +static int get_rd_wr_caps(struct file *src_filp, int *src_got, + struct file *dst_filp, loff_t dst_endoff, int *dst_got) { int ret = 0; bool retrying = false; retry_caps: - ret = ceph_get_caps(dst_ci, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER, + ret = ceph_get_caps(dst_filp, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER, dst_endoff, dst_got, NULL); if (ret < 0) return ret; @@ -1827,24 +1827,24 @@ static int get_rd_wr_caps(struct ceph_inode_info *src_ci, * we would risk a deadlock by using ceph_get_caps. Thus, we'll do some * retry dance instead to try to get both capabilities. */ - ret = ceph_try_get_caps(src_ci, CEPH_CAP_FILE_RD, CEPH_CAP_FILE_SHARED, + ret = ceph_try_get_caps(file_inode(src_filp), + CEPH_CAP_FILE_RD, CEPH_CAP_FILE_SHARED, false, src_got); if (ret <= 0) { /* Start by dropping dst_ci caps and getting src_ci caps */ - ceph_put_cap_refs(dst_ci, *dst_got); + ceph_put_cap_refs(ceph_inode(file_inode(dst_filp)), *dst_got); if (retrying) { if (!ret) /* ceph_try_get_caps masks EAGAIN */ ret = -EAGAIN; return ret; } - ret = ceph_get_caps(src_ci, CEPH_CAP_FILE_RD, - CEPH_CAP_FILE_SHARED, src_endoff, - src_got, NULL); + ret = ceph_get_caps(src_filp, CEPH_CAP_FILE_RD, + CEPH_CAP_FILE_SHARED, -1, src_got, NULL); if (ret < 0) return ret; /*... drop src_ci caps too, and retry */ - ceph_put_cap_refs(src_ci, *src_got); + ceph_put_cap_refs(ceph_inode(file_inode(src_filp)), *src_got); retrying = true; goto retry_caps; } @@ -1958,8 +1958,8 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, * clients may have dirty data in their caches. And OSDs know nothing * about caps, so they can't safely do the remote object copies. */ - err = get_rd_wr_caps(src_ci, (src_off + len), &src_got, - dst_ci, (dst_off + len), &dst_got); + err = get_rd_wr_caps(src_file, &src_got, + dst_file, (dst_off + len), &dst_got); if (err < 0) { dout("get_rd_wr_caps returned %d\n", err); ret = -EOPNOTSUPP; @@ -2016,9 +2016,8 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, goto out; } len -= ret; - err = get_rd_wr_caps(src_ci, (src_off + len), - &src_got, dst_ci, - (dst_off + len), &dst_got); + err = get_rd_wr_caps(src_file, &src_got, + dst_file, (dst_off + len), &dst_got); if (err < 0) goto out; err = is_file_size_ok(src_inode, dst_inode, diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 2e516d47052f..f45a06475f4f 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1061,9 +1061,9 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn, struct inode *dir, int mds, int drop, int unless); -extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, +extern int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got, struct page **pinned_page); -extern int ceph_try_get_caps(struct ceph_inode_info *ci, +extern int ceph_try_get_caps(struct inode *inode, int need, int want, bool nonblock, int *got); /* for counting open files by mode */ @@ -1074,7 +1074,7 @@ extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode); extern const struct address_space_operations ceph_aops; 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 ceph_inode_info *ci, int need); +extern int ceph_pool_perm_check(struct inode *inode, int need); extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc); /* file.c */ From patchwork Thu Jun 6 13:47:53 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Yan, Zheng" X-Patchwork-Id: 10979579 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 2BD1615E6 for ; Thu, 6 Jun 2019 13:48:05 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 1B4B028985 for ; Thu, 6 Jun 2019 13:48:05 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 0F8BB289AF; Thu, 6 Jun 2019 13:48:05 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id B526E28985 for ; Thu, 6 Jun 2019 13:48:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728236AbfFFNsD (ORCPT ); Thu, 6 Jun 2019 09:48:03 -0400 Received: from mx1.redhat.com ([209.132.183.28]:50728 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726877AbfFFNsD (ORCPT ); Thu, 6 Jun 2019 09:48:03 -0400 Received: from smtp.corp.redhat.com (int-mx03.intmail.prod.int.phx2.redhat.com [10.5.11.13]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 9E6807FDF8 for ; Thu, 6 Jun 2019 13:48:03 +0000 (UTC) Received: from zhyan-laptop.redhat.com (ovpn-12-89.pek2.redhat.com [10.72.12.89]) by smtp.corp.redhat.com (Postfix) with ESMTP id 3E741183EF; Thu, 6 Jun 2019 13:48:00 +0000 (UTC) From: "Yan, Zheng" To: ceph-devel@vger.kernel.org Cc: idryomov@redhat.com, jlayton@redhat.com, "Yan, Zheng" Subject: [PATCH 2/3] ceph: check page writeback error during write Date: Thu, 6 Jun 2019 21:47:53 +0800 Message-Id: <20190606134754.31725-2-zyan@redhat.com> In-Reply-To: <20190606134754.31725-1-zyan@redhat.com> References: <20190606134754.31725-1-zyan@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.13 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.27]); Thu, 06 Jun 2019 13:48:03 +0000 (UTC) Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP make write(2) return error prematurely if there is writeback error. User can use fsync() or fdatasync() to clear the error. Signed-off-by: "Yan, Zheng" --- fs/ceph/caps.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index e88a21d830e1..6063e5f4035a 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2816,6 +2816,14 @@ int ceph_get_caps(struct file *filp, int need, int want, break; } + if (_got & CEPH_CAP_FILE_WR) { + ret = filemap_check_wb_err(inode->i_mapping, filp->f_wb_err); + if (ret < 0) { + ceph_put_cap_refs(ci, _got); + return ret; + } + } + if ((_got & CEPH_CAP_FILE_RD) && (_got & CEPH_CAP_FILE_CACHE)) ceph_fscache_revalidate_cookie(ci); From patchwork Thu Jun 6 13:47:54 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Yan, Zheng" X-Patchwork-Id: 10979581 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 5D46515E6 for ; Thu, 6 Jun 2019 13:48:09 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 4D356287E3 for ; Thu, 6 Jun 2019 13:48:09 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 4122428980; Thu, 6 Jun 2019 13:48:09 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id BFE3E287E3 for ; Thu, 6 Jun 2019 13:48:08 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728385AbfFFNsH (ORCPT ); Thu, 6 Jun 2019 09:48:07 -0400 Received: from mx1.redhat.com ([209.132.183.28]:34952 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726877AbfFFNsH (ORCPT ); Thu, 6 Jun 2019 09:48:07 -0400 Received: from smtp.corp.redhat.com (int-mx03.intmail.prod.int.phx2.redhat.com [10.5.11.13]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id E061830C1AFD for ; Thu, 6 Jun 2019 13:48:06 +0000 (UTC) Received: from zhyan-laptop.redhat.com (ovpn-12-89.pek2.redhat.com [10.72.12.89]) by smtp.corp.redhat.com (Postfix) with ESMTP id 6A7805F7D8; Thu, 6 Jun 2019 13:48:04 +0000 (UTC) From: "Yan, Zheng" To: ceph-devel@vger.kernel.org Cc: idryomov@redhat.com, jlayton@redhat.com, "Yan, Zheng" Subject: [PATCH 3/3] ceph: return -EIO if read/write against filp with lost file locks Date: Thu, 6 Jun 2019 21:47:54 +0800 Message-Id: <20190606134754.31725-3-zyan@redhat.com> In-Reply-To: <20190606134754.31725-1-zyan@redhat.com> References: <20190606134754.31725-1-zyan@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.13 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.40]); Thu, 06 Jun 2019 13:48:06 +0000 (UTC) Sender: ceph-devel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP After mds evicts session, file locks get lost sliently. It's not safe to let programs continue to do read/write. Signed-off-by: "Yan, Zheng" --- fs/ceph/caps.c | 28 ++++++++++++++++++++++------ fs/ceph/locks.c | 8 ++++++-- fs/ceph/super.h | 1 + 3 files changed, 29 insertions(+), 8 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 6063e5f4035a..d96bd516ee78 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2545,8 +2545,13 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got, * * FIXME: how does a 0 return differ from -EAGAIN? */ +enum { + NON_BLOCKING = 1, + CHECK_FILELOCK = 2, +}; + static int try_get_cap_refs(struct inode *inode, int need, int want, - loff_t endoff, bool nonblock, int *got) + loff_t endoff, int flags, int *got) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; @@ -2561,6 +2566,13 @@ static int try_get_cap_refs(struct inode *inode, int need, int want, again: spin_lock(&ci->i_ceph_lock); + if ((flags & CHECK_FILELOCK) && + (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK)) { + dout("try_get_cap_refs %p error filelock\n", inode); + ret = -EIO; + goto out_unlock; + } + /* make sure file is actually open */ file_wanted = __ceph_caps_file_wanted(ci); if ((file_wanted & need) != need) { @@ -2622,7 +2634,7 @@ static int try_get_cap_refs(struct inode *inode, int need, int want, * we can not call down_read() when * task isn't in TASK_RUNNING state */ - if (nonblock) { + if (flags & NON_BLOCKING) { ret = -EAGAIN; goto out_unlock; } @@ -2727,7 +2739,8 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, if (ret < 0) return ret; - ret = try_get_cap_refs(inode, need, want, 0, nonblock, got); + ret = try_get_cap_refs(inode, need, want, 0, + (nonblock ? NON_BLOCKING : 0), got); return ret == -EAGAIN ? 0 : ret; } @@ -2739,9 +2752,10 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got, struct page **pinned_page) { + struct ceph_file_info *fi = filp->private_data; struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); - int _got, ret; + int ret, _got, flags; ret = ceph_pool_perm_check(inode, need); if (ret < 0) @@ -2751,17 +2765,19 @@ int ceph_get_caps(struct file *filp, int need, int want, if (endoff > 0) check_max_size(inode, endoff); + flags = atomic_read(&fi->num_locks) ? CHECK_FILELOCK : 0; _got = 0; ret = try_get_cap_refs(inode, need, want, endoff, - false, &_got); + flags, &_got); if (ret == -EAGAIN) continue; if (!ret) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(&ci->i_cap_wq, &wait); + flags |= NON_BLOCKING; while (!(ret = try_get_cap_refs(inode, need, want, - endoff, true, &_got))) { + endoff, flags, &_got))) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index ac9b53b89365..cb216501c959 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -32,14 +32,18 @@ void __init ceph_flock_init(void) static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src) { - struct inode *inode = file_inode(src->fl_file); + struct ceph_file_info *fi = dst->fl_file->private_data; + struct inode *inode = file_inode(dst->fl_file); atomic_inc(&ceph_inode(inode)->i_filelock_ref); + atomic_inc(&fi->num_locks); } static void ceph_fl_release_lock(struct file_lock *fl) { + struct ceph_file_info *fi = fl->fl_file->private_data; struct inode *inode = file_inode(fl->fl_file); struct ceph_inode_info *ci = ceph_inode(inode); + atomic_dec(&fi->num_locks); if (atomic_dec_and_test(&ci->i_filelock_ref)) { /* clear error when all locks are released */ spin_lock(&ci->i_ceph_lock); @@ -73,7 +77,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode, * window. Caller function will decrease the counter. */ fl->fl_ops = &ceph_fl_lock_ops; - atomic_inc(&ceph_inode(inode)->i_filelock_ref); + fl->fl_ops->fl_copy_lock(fl, NULL); } if (operation != CEPH_MDS_OP_SETFILELOCK || cmd == CEPH_LOCK_UNLOCK) diff --git a/fs/ceph/super.h b/fs/ceph/super.h index f45a06475f4f..999fd3244907 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -705,6 +705,7 @@ struct ceph_file_info { struct list_head rw_contexts; errseq_t meta_err; + atomic_t num_locks; }; struct ceph_dir_file_info {