From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934671AbbLPSE3 (ORCPT ); Wed, 16 Dec 2015 13:04:29 -0500 Received: from youngberry.canonical.com ([91.189.89.112]:49898 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S966514AbbLPRka (ORCPT ); Wed, 16 Dec 2015 12:40:30 -0500 From: Kamal Mostafa To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Dmitry Vyukov , Jan Kara , Al Viro , Kamal Mostafa Subject: [PATCH 3.19.y-ckt 069/128] vfs: Avoid softlockups with sendfile(2) Date: Wed, 16 Dec 2015 09:38:29 -0800 Message-Id: <1450287568-19808-70-git-send-email-kamal@canonical.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1450287568-19808-1-git-send-email-kamal@canonical.com> References: <1450287568-19808-1-git-send-email-kamal@canonical.com> X-Extended-Stable: 3.19 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.19.8-ckt12 -stable review patch. If anyone has any objections, please let me know. ------------------ From: Jan Kara commit c2489e07c0a71a56fb2c84bc0ee66cddfca7d068 upstream. The following test program from Dmitry can cause softlockups or RCU stalls as it copies 1GB from tmpfs into eventfd and we don't have any scheduling point at that path in sendfile(2) implementation: int r1 = eventfd(0, 0); int r2 = memfd_create("", 0); unsigned long n = 1<<30; fallocate(r2, 0, 0, n); sendfile(r1, r2, 0, n); Add cond_resched() into __splice_from_pipe() to fix the problem. CC: Dmitry Vyukov Signed-off-by: Jan Kara Signed-off-by: Al Viro Signed-off-by: Kamal Mostafa --- fs/splice.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/splice.c b/fs/splice.c index d934f8e4..c4b93e4 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -888,6 +888,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_from_pipe_begin(sd); do { + cond_resched(); ret = splice_from_pipe_next(pipe, sd); if (ret > 0) ret = splice_from_pipe_feed(pipe, sd, actor); -- 1.9.1