From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754092AbcHPUdU (ORCPT ); Tue, 16 Aug 2016 16:33:20 -0400 Received: from smtp1.ccs.ornl.gov ([160.91.203.10]:34054 "EHLO smtp1.ccs.ornl.gov" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753882AbcHPUUZ (ORCPT ); Tue, 16 Aug 2016 16:20:25 -0400 From: James Simmons To: Greg Kroah-Hartman , devel@driverdev.osuosl.org, Andreas Dilger , Oleg Drokin Cc: Linux Kernel Mailing List , Lustre Development List , Jinshan Xiong , James Simmons Subject: [PATCH 31/80] staging: lustre: llite: avoid a deadlock in page write Date: Tue, 16 Aug 2016 16:18:44 -0400 Message-Id: <1471378773-24590-32-git-send-email-jsimmons@infradead.org> X-Mailer: git-send-email 1.7.1 In-Reply-To: <1471378773-24590-1-git-send-email-jsimmons@infradead.org> References: <1471378773-24590-1-git-send-email-jsimmons@infradead.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Jinshan Xiong For a partial page write, it will have to issue a READ RPC firstly to get a full uptodate page. If another page is already locked by this thread it can easily cause deadlock. Signed-off-by: Jinshan Xiong Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4873 Reviewed-on: http://review.whamcloud.com/9928 Reviewed-by: Bobi Jam Reviewed-by: Niu Yawei Reviewed-by: Oleg Drokin Signed-off-by: James Simmons --- drivers/staging/lustre/lustre/llite/rw26.c | 5 +++-- 1 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c index d98c7ac..c14a1b6 100644 --- a/drivers/staging/lustre/lustre/llite/rw26.c +++ b/drivers/staging/lustre/lustre/llite/rw26.c @@ -506,8 +506,9 @@ static int ll_write_begin(struct file *file, struct address_space *mapping, env = lcc->lcc_env; io = lcc->lcc_io; - /* To avoid deadlock, try to lock page first. */ - vmpage = grab_cache_page_nowait(mapping, index); + if (likely(to == PAGE_SIZE)) /* LU-4873 */ + /* To avoid deadlock, try to lock page first. */ + vmpage = grab_cache_page_nowait(mapping, index); if (unlikely(!vmpage || PageDirty(vmpage) || PageWriteback(vmpage))) { struct vvp_io *vio = vvp_env_io(env); struct cl_page_list *plist = &vio->u.write.vui_queue; -- 1.7.1