From patchwork Thu Apr 25 15:26:30 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Andreas Gruenbacher X-Patchwork-Id: 10917297 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 9394914C0 for ; Thu, 25 Apr 2019 15:26:40 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 8494E28BE8 for ; Thu, 25 Apr 2019 15:26:40 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 78ED928BEC; Thu, 25 Apr 2019 15:26:40 +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 134E128BE8 for ; Thu, 25 Apr 2019 15:26:40 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728925AbfDYP0j (ORCPT ); Thu, 25 Apr 2019 11:26:39 -0400 Received: from mx1.redhat.com ([209.132.183.28]:54352 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727337AbfDYP0j (ORCPT ); Thu, 25 Apr 2019 11:26:39 -0400 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id C371FC04BE09; Thu, 25 Apr 2019 15:26:38 +0000 (UTC) Received: from max.home.com (unknown [10.40.205.80]) by smtp.corp.redhat.com (Postfix) with ESMTP id 428E261B9B; Thu, 25 Apr 2019 15:26:33 +0000 (UTC) From: Andreas Gruenbacher To: cluster-devel@redhat.com, Christoph Hellwig Cc: Bob Peterson , Jan Kara , Dave Chinner , Ross Lagerwall , Mark Syms , =?utf-8?b?RWR3aW4gVMO2csO2aw==?= , linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, Andreas Gruenbacher Subject: [PATCH v2 1/2] iomap: Add a page_prepare callback Date: Thu, 25 Apr 2019 17:26:30 +0200 Message-Id: <20190425152631.633-1-agruenba@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.31]); Thu, 25 Apr 2019 15:26:38 +0000 (UTC) Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Move the page_done callback into a separate iomap_page_ops structure and add a page_prepare calback to be called before a page is written to. In gfs2, we'll want to start a transaction in page_prepare and end it in page_done, and other filesystems that implement data journaling will require the same kind of mechanism. Signed-off-by: Andreas Gruenbacher --- fs/iomap.c | 21 +++++++++++++++++---- include/linux/iomap.h | 18 +++++++++++++----- 2 files changed, 30 insertions(+), 9 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index 97cb9d486a7d..967c985c5310 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -674,9 +674,17 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, if (fatal_signal_pending(current)) return -EINTR; + if (page_ops) { + status = page_ops->page_prepare(inode, pos, len, iomap); + if (status) + return status; + } + page = grab_cache_page_write_begin(inode->i_mapping, index, flags); - if (!page) - return -ENOMEM; + if (!page) { + status = -ENOMEM; + goto no_page; + } if (iomap->type == IOMAP_INLINE) iomap_read_inline_data(inode, page, iomap); @@ -684,12 +692,16 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, status = __block_write_begin_int(page, pos, len, NULL, iomap); else status = __iomap_write_begin(inode, pos, len, page, iomap); + if (unlikely(status)) { unlock_page(page); put_page(page); page = NULL; iomap_write_failed(inode, pos, len); +no_page: + if (page_ops) + page_ops->page_done(inode, pos, 0, NULL, iomap); } *pagep = page; @@ -769,6 +781,7 @@ static int iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page, struct iomap *iomap) { + const struct iomap_page_ops *page_ops = iomap->page_ops; int ret; if (iomap->type == IOMAP_INLINE) { @@ -780,8 +793,8 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, ret = __iomap_write_end(inode, pos, len, copied, page, iomap); } - if (iomap->page_done) - iomap->page_done(inode, pos, copied, page, iomap); + if (page_ops) + page_ops->page_done(inode, pos, copied, page, iomap); if (ret < len) iomap_write_failed(inode, pos, len); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0fefb5455bda..fd65f27d300e 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -53,6 +53,8 @@ struct vm_fault; */ #define IOMAP_NULL_ADDR -1ULL /* addr is not valid */ +struct iomap_page_ops; + struct iomap { u64 addr; /* disk offset of mapping, bytes */ loff_t offset; /* file offset of mapping, bytes */ @@ -63,12 +65,18 @@ struct iomap { struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; void *private; /* filesystem private */ + const struct iomap_page_ops *page_ops; +}; - /* - * Called when finished processing a page in the mapping returned in - * this iomap. At least for now this is only supported in the buffered - * write path. - */ +/* + * Called before / after processing a page in the mapping returned in this + * iomap. At least for now, this is only supported in the buffered write path. + * When page_prepare returns 0, page_done is called as well + * (possibly with page == NULL). + */ +struct iomap_page_ops { + int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len, + struct iomap *iomap); void (*page_done)(struct inode *inode, loff_t pos, unsigned copied, struct page *page, struct iomap *iomap); }; From patchwork Thu Apr 25 15:26:31 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Andreas Gruenbacher X-Patchwork-Id: 10917301 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 0CF5A933 for ; Thu, 25 Apr 2019 15:26:46 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id F173D28B2A for ; Thu, 25 Apr 2019 15:26:45 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id E5C7928BE1; Thu, 25 Apr 2019 15:26:45 +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 47A9528B2A for ; Thu, 25 Apr 2019 15:26:45 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728930AbfDYP0o (ORCPT ); Thu, 25 Apr 2019 11:26:44 -0400 Received: from mx1.redhat.com ([209.132.183.28]:48296 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727337AbfDYP0o (ORCPT ); Thu, 25 Apr 2019 11:26:44 -0400 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 18558C05B1CB; Thu, 25 Apr 2019 15:26:44 +0000 (UTC) Received: from max.home.com (unknown [10.40.205.80]) by smtp.corp.redhat.com (Postfix) with ESMTP id 28D4161D26; Thu, 25 Apr 2019 15:26:38 +0000 (UTC) From: Andreas Gruenbacher To: cluster-devel@redhat.com, Christoph Hellwig Cc: Bob Peterson , Jan Kara , Dave Chinner , Ross Lagerwall , Mark Syms , =?utf-8?b?RWR3aW4gVMO2csO2aw==?= , linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, Andreas Gruenbacher Subject: [PATCH v2 2/2] gfs2: Fix iomap write page reclaim deadlock Date: Thu, 25 Apr 2019 17:26:31 +0200 Message-Id: <20190425152631.633-2-agruenba@redhat.com> In-Reply-To: <20190425152631.633-1-agruenba@redhat.com> References: <20190425152631.633-1-agruenba@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.32]); Thu, 25 Apr 2019 15:26:44 +0000 (UTC) Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Since commit 64bc06bb32ee ("gfs2: iomap buffered write support"), gfs2 is doing buffered writes by starting a transaction in iomap_begin, writing a range of pages, and ending that transaction in iomap_end. This approach suffers from two problems: (1) Any allocations necessary for the write are done in iomap_begin, so when the data aren't journaled, there is no need for keeping the transaction open until iomap_end. (2) Transactions keep the gfs2 log flush lock held. When iomap_file_buffered_write calls balance_dirty_pages, this can end up calling gfs2_write_inode, which will try to flush the log. This requires taking the log flush lock which is already held, resulting in a deadlock. Fix both of these issues by not keeping transactions open from iomap_begin to iomap_end. Instead, start a small transaction in page_prepare and end it in page_done when necessary. Reported-by: Edwin Török Fixes: 64bc06bb32ee ("gfs2: iomap buffered write support") Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson --- fs/gfs2/aops.c | 14 +++++-- fs/gfs2/bmap.c | 101 ++++++++++++++++++++++++++++--------------------- fs/iomap.c | 1 + 3 files changed, 68 insertions(+), 48 deletions(-) diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 05dd78f4b2b3..6210d4429d84 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -649,7 +649,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping, */ void adjust_fs_space(struct inode *inode) { - struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; + struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode); struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; @@ -657,10 +657,13 @@ void adjust_fs_space(struct inode *inode) struct buffer_head *m_bh, *l_bh; u64 fs_total, new_free; + if (gfs2_trans_begin(sdp, 2 * RES_STATFS, 0) != 0) + return; + /* Total up the file system space, according to the latest rindex. */ fs_total = gfs2_ri_total(sdp); if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0) - return; + goto out; spin_lock(&sdp->sd_statfs_spin); gfs2_statfs_change_in(m_sc, m_bh->b_data + @@ -675,11 +678,14 @@ void adjust_fs_space(struct inode *inode) gfs2_statfs_change(sdp, new_free, new_free, 0); if (gfs2_meta_inode_buffer(l_ip, &l_bh) != 0) - goto out; + goto out2; update_statfs(sdp, m_bh, l_bh); brelse(l_bh); -out: +out2: brelse(m_bh); +out: + sdp->sd_rindex_uptodate = 0; + gfs2_trans_end(sdp); } /** diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 5da4ca9041c0..2fae3f4f5db6 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -991,15 +991,31 @@ static void gfs2_write_unlock(struct inode *inode) gfs2_glock_dq_uninit(&ip->i_gh); } -static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos, - unsigned copied, struct page *page, - struct iomap *iomap) +static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, + unsigned len, struct iomap *iomap) +{ + struct gfs2_sbd *sdp = GFS2_SB(inode); + + return gfs2_trans_begin(sdp, RES_DINODE + (len >> inode->i_blkbits), 0); +} + +static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, + unsigned copied, struct page *page, + struct iomap *iomap) { struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); - gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + if (page && !gfs2_is_stuffed(ip)) + gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + gfs2_trans_end(sdp); } +const struct iomap_page_ops gfs2_iomap_page_ops = { + .page_prepare = gfs2_iomap_page_prepare, + .page_done = gfs2_iomap_page_done, +}; + static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, loff_t length, unsigned flags, struct iomap *iomap, @@ -1052,32 +1068,46 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, if (alloc_required) rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks); - ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits); - if (ret) - goto out_trans_fail; + if (unstuff || iomap->type == IOMAP_HOLE) { + struct gfs2_trans *tr; - if (unstuff) { - ret = gfs2_unstuff_dinode(ip, NULL); - if (ret) - goto out_trans_end; - release_metapath(mp); - ret = gfs2_iomap_get(inode, iomap->offset, iomap->length, - flags, iomap, mp); + ret = gfs2_trans_begin(sdp, rblocks, + iomap->length >> inode->i_blkbits); if (ret) - goto out_trans_end; - } + goto out_trans_fail; - if (iomap->type == IOMAP_HOLE) { - ret = gfs2_iomap_alloc(inode, iomap, flags, mp); - if (ret) { - gfs2_trans_end(sdp); - gfs2_inplace_release(ip); - punch_hole(ip, iomap->offset, iomap->length); - goto out_qunlock; + if (unstuff) { + ret = gfs2_unstuff_dinode(ip, NULL); + if (ret) + goto out_trans_end; + release_metapath(mp); + ret = gfs2_iomap_get(inode, iomap->offset, + iomap->length, flags, iomap, mp); + if (ret) + goto out_trans_end; } + + if (iomap->type == IOMAP_HOLE) { + ret = gfs2_iomap_alloc(inode, iomap, flags, mp); + if (ret) { + gfs2_trans_end(sdp); + gfs2_inplace_release(ip); + punch_hole(ip, iomap->offset, iomap->length); + goto out_qunlock; + } + } + + tr = current->journal_info; + if (tr->tr_num_buf_new) + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + else + gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]); + + gfs2_trans_end(sdp); } - if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip)) - iomap->page_done = gfs2_iomap_journaled_page_done; + + if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip)) + iomap->page_ops = &gfs2_iomap_page_ops; return 0; out_trans_end: @@ -1116,10 +1146,6 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->type != IOMAP_MAPPED) ret = -ENOTBLK; } - if (!ret) { - get_bh(mp.mp_bh[0]); - iomap->private = mp.mp_bh[0]; - } release_metapath(&mp); trace_gfs2_iomap_end(ip, iomap, ret); return ret; @@ -1130,27 +1156,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); - struct gfs2_trans *tr = current->journal_info; - struct buffer_head *dibh = iomap->private; if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != IOMAP_WRITE) goto out; - if (iomap->type != IOMAP_INLINE) { + if (!gfs2_is_stuffed(ip)) gfs2_ordered_add_inode(ip); - if (tr->tr_num_buf_new) - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - else - gfs2_trans_add_meta(ip->i_gl, dibh); - } - - if (inode == sdp->sd_rindex) { + if (inode == sdp->sd_rindex) adjust_fs_space(inode); - sdp->sd_rindex_uptodate = 0; - } - gfs2_trans_end(sdp); gfs2_inplace_release(ip); if (length != written && (iomap->flags & IOMAP_F_NEW)) { @@ -1170,8 +1185,6 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, gfs2_write_unlock(inode); out: - if (dibh) - brelse(dibh); return 0; } diff --git a/fs/iomap.c b/fs/iomap.c index 967c985c5310..667a822ecb7d 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -665,6 +665,7 @@ static int iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, struct page **pagep, struct iomap *iomap) { + const struct iomap_page_ops *page_ops = iomap->page_ops; pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status = 0;