From patchwork Thu Oct 28 09:14:35 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 12589603 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 mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BA8AAC433F5 for ; Thu, 28 Oct 2021 09:15:04 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 9B7D860724 for ; Thu, 28 Oct 2021 09:15:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230155AbhJ1JR3 (ORCPT ); Thu, 28 Oct 2021 05:17:29 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.129.124]:56461 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230106AbhJ1JRZ (ORCPT ); Thu, 28 Oct 2021 05:17:25 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1635412498; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=uzof8A1qRInCZYX4ONpNJOEu4IY+psyAJr3vrozCMe8=; b=Vhg9jepoeMW0x8KZs9US5XNDpnnYarLxgDUXGZqPxsYSXKkTYAKfaCc+w5qIrC3fH808PY 250M05t1jR8C7OAEqjqQP6whqAanhWNqy2kw4jImwEJFuL5ayhzR1IXw49q69lzIAKHVSf Qj6JUVhKYx3ubaSCTQcgfjjgvA847ys= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-161-gmmJXTkAO9ytTgYUEb5adA-1; Thu, 28 Oct 2021 05:14:54 -0400 X-MC-Unique: gmmJXTkAO9ytTgYUEb5adA-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.15]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 6CBF910B3940; Thu, 28 Oct 2021 09:14:53 +0000 (UTC) Received: from lxbceph1.gsslab.pek2.redhat.com (unknown [10.72.47.117]) by smtp.corp.redhat.com (Postfix) with ESMTP id 103CD5F4EE; Thu, 28 Oct 2021 09:14:50 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, vshankar@redhat.com, pdonnell@redhat.com, khiremat@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v3 1/4] ceph: add __ceph_get_caps helper support Date: Thu, 28 Oct 2021 17:14:35 +0800 Message-Id: <20211028091438.21402-2-xiubli@redhat.com> In-Reply-To: <20211028091438.21402-1-xiubli@redhat.com> References: <20211028091438.21402-1-xiubli@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.15 Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li Signed-off-by: Xiubo Li --- fs/ceph/caps.c | 19 +++++++++++++------ fs/ceph/super.h | 2 ++ 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index d628dcdbf869..4e2a588465c5 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2876,10 +2876,9 @@ int ceph_try_get_caps(struct inode *inode, 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 file *filp, int need, int want, loff_t endoff, int *got) +int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need, + int want, loff_t endoff, int *got) { - struct ceph_file_info *fi = filp->private_data; - struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); int ret, _got, flags; @@ -2888,7 +2887,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got if (ret < 0) return ret; - if ((fi->fmode & CEPH_FILE_MODE_WR) && + if (fi && (fi->fmode & CEPH_FILE_MODE_WR) && fi->filp_gen != READ_ONCE(fsc->filp_gen)) return -EBADF; @@ -2896,7 +2895,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got while (true) { flags &= CEPH_FILE_MODE_MASK; - if (atomic_read(&fi->num_locks)) + if (fi && atomic_read(&fi->num_locks)) flags |= CHECK_FILELOCK; _got = 0; ret = try_get_cap_refs(inode, need, want, endoff, @@ -2941,7 +2940,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got continue; } - if ((fi->fmode & CEPH_FILE_MODE_WR) && + if (fi && (fi->fmode & CEPH_FILE_MODE_WR) && fi->filp_gen != READ_ONCE(fsc->filp_gen)) { if (ret >= 0 && _got) ceph_put_cap_refs(ci, _got); @@ -3004,6 +3003,14 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got return 0; } +int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got) +{ + struct ceph_file_info *fi = filp->private_data; + struct inode *inode = file_inode(filp); + + return __ceph_get_caps(inode, fi, need, want, endoff, got); +} + /* * Take cap refs. Caller must already know we hold at least one ref * on the caps in question or we don't know this is safe. diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 7f3976b3319d..027d5f579ba0 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1208,6 +1208,8 @@ 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 inode *inode, struct ceph_file_info *fi, + int need, int want, loff_t endoff, int *got); extern int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got); extern int ceph_try_get_caps(struct inode *inode, From patchwork Thu Oct 28 09:14:36 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 12589601 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 mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id D0009C433EF for ; Thu, 28 Oct 2021 09:15:04 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id B2D03610CB for ; Thu, 28 Oct 2021 09:15:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230135AbhJ1JRa (ORCPT ); Thu, 28 Oct 2021 05:17:30 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]:20210 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230126AbhJ1JR1 (ORCPT ); Thu, 28 Oct 2021 05:17:27 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1635412500; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=kf8phOVye7nM+NHTRxIT/hREqiW8scqZ5hTj87XZZvA=; b=f0z0I4hUnXfbpdl1136WZkqJfotht9w1NVFjD0tbe7FZxKwOuvwcbYMT8SpzixQw8KX/2Q tEeEhBqWONLSJPnV7p0qTapgCNhcxEcGFx5TuRmqeOR33VTRNaOKZ2yyIUhdJ7A9epg/yp bAHnOtP0d7Mm1DoJ2OCD2HiousW5BqA= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-564-B9Tu_BnsOG2GgL69ZjrVlg-1; Thu, 28 Oct 2021 05:14:57 -0400 X-MC-Unique: B9Tu_BnsOG2GgL69ZjrVlg-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.15]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 5C28C1B2C981; Thu, 28 Oct 2021 09:14:56 +0000 (UTC) Received: from lxbceph1.gsslab.pek2.redhat.com (unknown [10.72.47.117]) by smtp.corp.redhat.com (Postfix) with ESMTP id E95836418A; Thu, 28 Oct 2021 09:14:53 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, vshankar@redhat.com, pdonnell@redhat.com, khiremat@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v3 2/4] ceph: add __ceph_sync_read helper support Date: Thu, 28 Oct 2021 17:14:36 +0800 Message-Id: <20211028091438.21402-3-xiubli@redhat.com> In-Reply-To: <20211028091438.21402-1-xiubli@redhat.com> References: <20211028091438.21402-1-xiubli@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.15 Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li Signed-off-by: Xiubo Li --- fs/ceph/file.c | 31 +++++++++++++++++++++---------- fs/ceph/super.h | 2 ++ 2 files changed, 23 insertions(+), 10 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 6e677b40410e..74db403a4c35 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -901,20 +901,17 @@ static inline void fscrypt_adjust_off_and_len(struct inode *inode, u64 *off, u64 * If we get a short result from the OSD, check against i_size; we need to * only return a short read to the caller if we hit EOF. */ -static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, - int *retry_op) +ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, + struct iov_iter *to, int *retry_op) { - struct file *file = iocb->ki_filp; - struct inode *inode = file_inode(file); 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; ssize_t ret; - u64 off = iocb->ki_pos; + u64 off = *ki_pos; u64 len = iov_iter_count(to); - dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, - (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); + dout("sync_read on inode %p %llu~%u\n", inode, *ki_pos, (unsigned)len); if (!len) return 0; @@ -1058,18 +1055,32 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, break; } - if (off > iocb->ki_pos) { + if (off > *ki_pos) { if (ret >= 0 && iov_iter_count(to) > 0 && off >= i_size_read(inode)) *retry_op = CHECK_EOF; - ret = off - iocb->ki_pos; - iocb->ki_pos = off; + ret = off - *ki_pos; + *ki_pos = off; } out: dout("sync_read result %zd retry_op %d\n", ret, *retry_op); return ret; } +static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, + int *retry_op) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + + dout("sync_read on file %p %llu~%u %s\n", file, iocb->ki_pos, + (unsigned)iov_iter_count(to), + (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); + + return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op); + +} + struct ceph_aio_request { struct kiocb *iocb; size_t total_len; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 027d5f579ba0..57bc952c54e1 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1235,6 +1235,8 @@ extern int ceph_renew_caps(struct inode *inode, int fmode); extern int ceph_open(struct inode *inode, struct file *file); extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned flags, umode_t mode); +extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, + struct iov_iter *to, int *retry_op); extern int ceph_release(struct inode *inode, struct file *filp); extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, char *data, size_t len); From patchwork Thu Oct 28 09:14:37 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 12589605 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 mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2F37CC433F5 for ; Thu, 28 Oct 2021 09:15:07 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 17987610A0 for ; Thu, 28 Oct 2021 09:15:07 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230124AbhJ1JRc (ORCPT ); Thu, 28 Oct 2021 05:17:32 -0400 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:29992 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230102AbhJ1JRb (ORCPT ); Thu, 28 Oct 2021 05:17:31 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1635412504; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=HQ2h7nXpi5Kisi/xMnS+FVduPYQWKZ4RWQWaNH0w2Fo=; b=YbUX/yv8yyHOnWQgeDsbemCGLHbNccjANxuW/PP1BibzC2d6m88IPa5cdZgfnKaPWQgUnZ zgbQHj6P7NE8EvN0NZCXjDODEzD5DevNpqLfzpLpoNH0cdbP7kuQjyNZBN2CaZ1CQ1XdI+ Tg1q04cP8ZOEUmir4LgwjqEbqRFep88= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-433-yRdfErhzNPibeyqU6NMUYA-1; Thu, 28 Oct 2021 05:15:01 -0400 X-MC-Unique: yRdfErhzNPibeyqU6NMUYA-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.15]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 3DFBB101F000; Thu, 28 Oct 2021 09:15:00 +0000 (UTC) Received: from lxbceph1.gsslab.pek2.redhat.com (unknown [10.72.47.117]) by smtp.corp.redhat.com (Postfix) with ESMTP id D7C0C54469; Thu, 28 Oct 2021 09:14:56 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, vshankar@redhat.com, pdonnell@redhat.com, khiremat@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v3 3/4] ceph: return the real size readed when hit EOF Date: Thu, 28 Oct 2021 17:14:37 +0800 Message-Id: <20211028091438.21402-4-xiubli@redhat.com> In-Reply-To: <20211028091438.21402-1-xiubli@redhat.com> References: <20211028091438.21402-1-xiubli@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.15 Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li Signed-off-by: Xiubo Li --- fs/ceph/file.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 74db403a4c35..1988e75ad4a2 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -910,6 +910,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ssize_t ret; u64 off = *ki_pos; u64 len = iov_iter_count(to); + u64 i_size = i_size_read(inode); dout("sync_read on inode %p %llu~%u\n", inode, *ki_pos, (unsigned)len); @@ -933,7 +934,6 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, struct page **pages; int num_pages; size_t page_off; - u64 i_size; bool more; int idx; size_t left; @@ -980,7 +980,6 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ceph_osdc_put_request(req); - i_size = i_size_read(inode); dout("sync_read %llu~%llu got %zd i_size %llu%s\n", off, len, ret, i_size, (more ? " MORE" : "")); @@ -1056,11 +1055,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, } if (off > *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 - *ki_pos; - *ki_pos = off; + ret = i_size - *ki_pos; + *ki_pos = i_size; + } else { + ret = off - *ki_pos; + *ki_pos = off; + } } out: dout("sync_read result %zd retry_op %d\n", ret, *retry_op); From patchwork Thu Oct 28 09:14:38 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 12589607 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 mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 648FCC433FE for ; Thu, 28 Oct 2021 09:15:10 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 49DEC60724 for ; Thu, 28 Oct 2021 09:15:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230166AbhJ1JRf (ORCPT ); Thu, 28 Oct 2021 05:17:35 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]:57156 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230131AbhJ1JRe (ORCPT ); Thu, 28 Oct 2021 05:17:34 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1635412507; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=LlDooXWjNvco41cenm9G2ylRDjPax2QzD9PNTNyQMlM=; b=IHTozF/dHXV/rQCcOJUqWwSO4lqlHmGENYly2wlgI/K6AwwjI9EWBj4UMc/ZqbjwQ7eG8M XA3EeXO8/HTk1kXH1KgNazd8Kk8fJm9pq+EW38OQ+Dn5NXy2Oxa4OzTppT6l2RUyums7fU eE8tbrAAmiXjZu3Zd7wP9wiMMcQyn+k= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-506-TUZxGrivOL6kL4EALcPjiA-1; Thu, 28 Oct 2021 05:15:04 -0400 X-MC-Unique: TUZxGrivOL6kL4EALcPjiA-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.15]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 24BDA56B21; Thu, 28 Oct 2021 09:15:03 +0000 (UTC) Received: from lxbceph1.gsslab.pek2.redhat.com (unknown [10.72.47.117]) by smtp.corp.redhat.com (Postfix) with ESMTP id B9F7D5F4EE; Thu, 28 Oct 2021 09:15:00 +0000 (UTC) From: xiubli@redhat.com To: jlayton@kernel.org Cc: idryomov@gmail.com, vshankar@redhat.com, pdonnell@redhat.com, khiremat@redhat.com, ceph-devel@vger.kernel.org, Xiubo Li Subject: [PATCH v3 4/4] ceph: add truncate size handling support for fscrypt Date: Thu, 28 Oct 2021 17:14:38 +0800 Message-Id: <20211028091438.21402-5-xiubli@redhat.com> In-Reply-To: <20211028091438.21402-1-xiubli@redhat.com> References: <20211028091438.21402-1-xiubli@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.15 Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li This will transfer the encrypted last block contents to the MDS along with the truncate request only when new size is smaller and not aligned to the fscrypt BLOCK size. Signed-off-by: Xiubo Li --- fs/ceph/caps.c | 2 - fs/ceph/file.c | 10 +- fs/ceph/inode.c | 182 ++++++++++++++++++++++++++++++++++-- fs/ceph/super.h | 3 +- include/linux/ceph/crypto.h | 23 +++++ 5 files changed, 206 insertions(+), 14 deletions(-) create mode 100644 include/linux/ceph/crypto.h diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 4e2a588465c5..c9624b059eb0 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1299,8 +1299,6 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg) * fscrypt_auth holds the crypto context (if any). fscrypt_file * tracks the real i_size as an __le64 field (and we use a rounded-up * i_size in * the traditional size field). - * - * FIXME: should we encrypt fscrypt_file field? */ ceph_encode_32(&p, arg->fscrypt_auth_len); ceph_encode_copy(&p, arg->fscrypt_auth, arg->fscrypt_auth_len); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 1988e75ad4a2..2a780e0133df 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -902,7 +902,8 @@ static inline void fscrypt_adjust_off_and_len(struct inode *inode, u64 *off, u64 * only return a short read to the caller if we hit EOF. */ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, - struct iov_iter *to, int *retry_op) + struct iov_iter *to, int *retry_op, + u64 *assert_ver) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); @@ -978,6 +979,9 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, req->r_end_latency, len, ret); + /* Grab assert version. It must be non-zero. */ + *assert_ver = req->r_version; + WARN_ON_ONCE(assert_ver == 0); ceph_osdc_put_request(req); dout("sync_read %llu~%llu got %zd i_size %llu%s\n", @@ -1074,12 +1078,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); + u64 assert_ver; dout("sync_read on file %p %llu~%u %s\n", file, iocb->ki_pos, (unsigned)iov_iter_count(to), (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); - return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op); + return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op, + &assert_ver); } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9b798690fdc9..abb634866897 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -21,6 +21,7 @@ #include "cache.h" #include "crypto.h" #include +#include /* * Ceph inode operations @@ -1034,10 +1035,14 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page, pool_ns = old_ns; if (IS_ENCRYPTED(inode) && size && - (iinfo->fscrypt_file_len == sizeof(__le64))) { - size = __le64_to_cpu(*(__le64 *)iinfo->fscrypt_file); - if (info->size != round_up(size, CEPH_FSCRYPT_BLOCK_SIZE)) - pr_warn("size=%llu fscrypt_file=%llu\n", info->size, size); + (iinfo->fscrypt_file_len >= sizeof(__le64))) { + u64 fsize = __le64_to_cpu(*(__le64 *)iinfo->fscrypt_file); + if (fsize) { + size = fsize; + if (info->size != round_up(size, CEPH_FSCRYPT_BLOCK_SIZE)) + pr_warn("size=%llu fscrypt_file=%llu\n", + info->size, size); + } } queue_trunc = ceph_fill_file_size(inode, issued, @@ -2229,6 +2234,130 @@ static const struct inode_operations ceph_encrypted_symlink_iops = { .listxattr = ceph_listxattr, }; +/* + * Transfer the encrypted last block to the MDS and the MDS + * will update the file when truncating a smaller size. + * + * We don't support a PAGE_SIZE that is smaller than the + * CEPH_FSCRYPT_BLOCK_SIZE. + */ +static int fill_fscrypt_truncate(struct inode *inode, + struct ceph_mds_request *req, + struct iattr *attr) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + int boff = attr->ia_size % CEPH_FSCRYPT_BLOCK_SIZE; + loff_t pos, orig_pos = round_down(attr->ia_size, CEPH_FSCRYPT_BLOCK_SIZE); + u64 block = orig_pos >> CEPH_FSCRYPT_BLOCK_SHIFT; + struct ceph_pagelist *pagelist = NULL; + struct kvec iov; + struct iov_iter iter; + struct page *page = NULL; + struct ceph_fscrypt_truncate_size_header header; + int retry_op = 0; + int len = CEPH_FSCRYPT_BLOCK_SIZE; + loff_t i_size = i_size_read(inode); + bool fill_header_only = false; + u64 assert_ver = cpu_to_le64(0); + int got, ret, issued; + + ret = __ceph_get_caps(inode, NULL, CEPH_CAP_FILE_RD, 0, -1, &got); + if (ret < 0) + return ret; + + dout("%s size %lld -> %lld got cap refs on %s\n", __func__, + i_size, attr->ia_size, ceph_cap_string(got)); + + issued = __ceph_caps_issued(ci, NULL); + + /* Try to writeback the dirty pagecaches */ + if (issued & (CEPH_CAP_FILE_BUFFER)) + filemap_fdatawrite(&inode->i_data); + + page = __page_cache_alloc(GFP_KERNEL); + if (page == NULL) { + ret = -ENOMEM; + goto out; + } + + iov.iov_base = kmap_local_page(page); + iov.iov_len = len; + iov_iter_kvec(&iter, READ, &iov, 1, len); + + pos = orig_pos; + ret = __ceph_sync_read(inode, &pos, &iter, &retry_op, &assert_ver); + + /* + * If we hit a hole here, we should just skip filling + * the fscrypt for the request, because once the fscrypt + * is enabled, the file will be split into many blocks + * with the size of CEPH_FSCRYPT_BLOCK_SIZE, if there + * has a hole, the hole size should be multiple of block + * size. + */ + if (pos < i_size && ret < len) { + dout("%s hit hole, ppos %lld < size %lld\n", + __func__, pos, i_size); + + ret = 0; + fill_header_only = true; + goto fill_last_block; + } + + /* truncate and zero out the extra contents for the last block */ + memset(iov.iov_base + boff, 0, PAGE_SIZE - boff); + + /* encrypt the last block */ + ret = fscrypt_encrypt_block_inplace(inode, page, + CEPH_FSCRYPT_BLOCK_SIZE, + 0, block, + GFP_KERNEL); + if (ret) + goto out; + +fill_last_block: + pagelist = ceph_pagelist_alloc(GFP_KERNEL); + if (!pagelist) + return -ENOMEM; + + /* Insert the header first */ + header.ver = 1; + header.compat = 1; + if (fill_header_only) { + header.data_len = cpu_to_le32(8 + 8 + 4); + header.assert_ver = cpu_to_le64(0); + header.file_offset = cpu_to_le64(0); + header.block_size = cpu_to_le64(0); + } else { + header.data_len = cpu_to_le32(8 + 8 + 4 + CEPH_FSCRYPT_BLOCK_SIZE); + header.assert_ver = assert_ver; + header.file_offset = cpu_to_le64(orig_pos); + header.block_size = cpu_to_le64(CEPH_FSCRYPT_BLOCK_SIZE); + } + ret = ceph_pagelist_append(pagelist, &header, sizeof(header)); + if (ret) + goto out; + + if (!fill_header_only) { + /* Append the last block contents to pagelist */ + ret = ceph_pagelist_append(pagelist, iov.iov_base, + CEPH_FSCRYPT_BLOCK_SIZE); + if (ret) + goto out; + } + req->r_pagelist = pagelist; +out: + dout("%s %p size dropping cap refs on %s\n", __func__, + inode, ceph_cap_string(got)); + kunmap_local(iov.iov_base); + if (page) + __free_pages(page, 0); + if (ret && pagelist) + ceph_pagelist_release(pagelist); + ceph_put_cap_refs(ci, got); + return ret; +} + int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *cia) { struct ceph_inode_info *ci = ceph_inode(inode); @@ -2236,12 +2365,14 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c struct ceph_mds_request *req; struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_cap_flush *prealloc_cf; + loff_t isize = i_size_read(inode); int issued; int release = 0, dirtied = 0; int mask = 0; int err = 0; int inode_dirty_flags = 0; bool lock_snap_rwsem = false; + bool fill_fscrypt; prealloc_cf = ceph_alloc_cap_flush(); if (!prealloc_cf) @@ -2254,6 +2385,8 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c return PTR_ERR(req); } +retry: + fill_fscrypt = false; spin_lock(&ci->i_ceph_lock); issued = __ceph_caps_issued(ci, NULL); @@ -2367,10 +2500,27 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c } } if (ia_valid & ATTR_SIZE) { - 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) { + /* + * Only when the new size is smaller and not aligned to + * CEPH_FSCRYPT_BLOCK_SIZE will the RMW is needed. + */ + if (IS_ENCRYPTED(inode) && attr->ia_size < isize && + (attr->ia_size % CEPH_FSCRYPT_BLOCK_SIZE)) { + mask |= CEPH_SETATTR_SIZE; + release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL | + CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; + set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags); + mask |= CEPH_SETATTR_FSCRYPT_FILE; + req->r_args.setattr.size = + cpu_to_le64(round_up(attr->ia_size, + CEPH_FSCRYPT_BLOCK_SIZE)); + req->r_args.setattr.old_size = + cpu_to_le64(round_up(isize, + CEPH_FSCRYPT_BLOCK_SIZE)); + req->r_fscrypt_file = attr->ia_size; + fill_fscrypt = true; + } else 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); @@ -2393,7 +2543,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c cpu_to_le64(round_up(isize, CEPH_FSCRYPT_BLOCK_SIZE)); req->r_fscrypt_file = attr->ia_size; - /* FIXME: client must zero out any partial blocks! */ } else { req->r_args.setattr.size = cpu_to_le64(attr->ia_size); req->r_args.setattr.old_size = cpu_to_le64(isize); @@ -2465,7 +2614,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c if (inode_dirty_flags) __mark_inode_dirty(inode, inode_dirty_flags); - if (mask) { req->r_inode = inode; ihold(inode); @@ -2473,7 +2621,23 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr, struct ceph_iattr *c req->r_args.setattr.mask = cpu_to_le32(mask); req->r_num_caps = 1; req->r_stamp = attr->ia_ctime; + if (fill_fscrypt) { + err = fill_fscrypt_truncate(inode, req, attr); + if (err) + goto out; + } + + /* + * The truncate will return -EAGAIN when some one + * has updated the last block before the MDS hold + * the xlock for the FILE lock. Need to retry it. + */ err = ceph_mdsc_do_request(mdsc, NULL, req); + if (err == -EAGAIN) { + dout("setattr %p result=%d (%s locally, %d remote), retry it!\n", + inode, err, ceph_cap_string(dirtied), mask); + goto retry; + } } out: dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err, diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 57bc952c54e1..c8144273ff28 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1236,7 +1236,8 @@ extern int ceph_open(struct inode *inode, struct file *file); extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry, struct file *file, unsigned flags, umode_t mode); extern ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, - struct iov_iter *to, int *retry_op); + struct iov_iter *to, int *retry_op, + u64 *assert_ver); extern int ceph_release(struct inode *inode, struct file *filp); extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, char *data, size_t len); diff --git a/include/linux/ceph/crypto.h b/include/linux/ceph/crypto.h new file mode 100644 index 000000000000..e0f799d4d4ee --- /dev/null +++ b/include/linux/ceph/crypto.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _FS_CEPH_CRYPTO_H +#define _FS_CEPH_CRYPTO_H + +#include + +/* + * Header for the crypted file when truncating the size, this + * will be sent to MDS, and MDS will do the encrypted last + * block's update and size truncating. + */ +struct ceph_fscrypt_truncate_size_header { + __u8 ver; + __u8 compat; + /* length of sizeof(assert_ver + file_offset + block_size + CEPH_FSCRYPT_BLOCK_SIZE) */ + __le32 data_len; + + __le64 assert_ver; + __le64 file_offset; + __le32 block_size; +} __packed; + +#endif