From patchwork Sat Sep 29 08:43:09 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Xu X-Patchwork-Id: 10620679 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 0229E417B for ; Sat, 29 Sep 2018 08:43:26 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id E72C229630 for ; Sat, 29 Sep 2018 08:43:25 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id DAC8729702; Sat, 29 Sep 2018 08:43:25 +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 629172975D for ; Sat, 29 Sep 2018 08:43:25 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727610AbeI2PLA (ORCPT ); Sat, 29 Sep 2018 11:11:00 -0400 Received: from mx1.redhat.com ([209.132.183.28]:37064 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727620AbeI2PLA (ORCPT ); Sat, 29 Sep 2018 11:11:00 -0400 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 7B9D4308338E; Sat, 29 Sep 2018 08:43:24 +0000 (UTC) Received: from xz-x1.nay.redhat.com (dhcp-14-128.nay.redhat.com [10.66.14.128]) by smtp.corp.redhat.com (Postfix) with ESMTP id 299B3106A790; Sat, 29 Sep 2018 08:43:19 +0000 (UTC) From: Peter Xu To: linux-kernel@vger.kernel.org Cc: Shuah Khan , Jerome Glisse , Mike Rapoport , Mike Kravetz , peterx@redhat.com, linux-mm@kvack.org, Zi Yan , "Kirill A . Shutemov" , linux-kselftest@vger.kernel.org, Shaohua Li , Andrea Arcangeli , "Dr . David Alan Gilbert" , Andrew Morton Subject: [PATCH 1/3] userfaultfd: selftest: cleanup help messages Date: Sat, 29 Sep 2018 16:43:09 +0800 Message-Id: <20180929084311.15600-2-peterx@redhat.com> In-Reply-To: <20180929084311.15600-1-peterx@redhat.com> References: <20180929084311.15600-1-peterx@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.44]); Sat, 29 Sep 2018 08:43:24 +0000 (UTC) Sender: linux-kselftest-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Firstly, the help in the comment region is obsolete, now we support three parameters. Since at it, change it and move it into the help message of the program. Also, the help messages dumped here and there is obsolete too. Use a single usage() helper. Signed-off-by: Peter Xu Acked-by: Mike Rapoport --- tools/testing/selftests/vm/userfaultfd.c | 44 ++++++++++++++---------- 1 file changed, 26 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 7b8171e3128a..2a84adaf8cf8 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -34,18 +34,6 @@ * per-CPU threads 1 by triggering userfaults inside * pthread_mutex_lock will also verify the atomicity of the memory * transfer (UFFDIO_COPY). - * - * The program takes two parameters: the amounts of physical memory in - * megabytes (MiB) of the area and the number of bounces to execute. - * - * # 100MiB 99999 bounces - * ./userfaultfd 100 99999 - * - * # 1GiB 99 bounces - * ./userfaultfd 1000 99 - * - * # 10MiB-~6GiB 999 bounces, continue forever unless an error triggers - * while ./userfaultfd $[RANDOM % 6000 + 10] 999; do true; done */ #define _GNU_SOURCE @@ -115,6 +103,28 @@ pthread_attr_t attr; ~(unsigned long)(sizeof(unsigned long long) \ - 1))) +const char *examples = + "# 100MiB 99999 bounces\n" + "./userfaultfd anon 100 99999\n" + "\n" + "# 1GiB 99 bounces\n" + "./userfaultfd anon 1000 99\n" + "\n" + "# 10MiB-~6GiB 999 bounces, continue forever unless an error triggers\n" + "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n" + "\n"; + +static void usage(void) +{ + fprintf(stderr, "\nUsage: ./userfaultfd " + "[hugetlbfs_file]\n\n"); + fprintf(stderr, "Supported : anon, hugetlb, " + "hugetlb_shared, shmem\n\n"); + fprintf(stderr, "Examples:\n\n"); + fprintf(stderr, examples); + exit(1); +} + static int anon_release_pages(char *rel_area) { int ret = 0; @@ -1272,8 +1282,7 @@ static void sigalrm(int sig) int main(int argc, char **argv) { if (argc < 4) - fprintf(stderr, "Usage: [hugetlbfs_file]\n"), - exit(1); + usage(); if (signal(SIGALRM, sigalrm) == SIG_ERR) fprintf(stderr, "failed to arm SIGALRM"), exit(1); @@ -1286,20 +1295,19 @@ int main(int argc, char **argv) nr_cpus; if (!nr_pages_per_cpu) { fprintf(stderr, "invalid MiB\n"); - fprintf(stderr, "Usage: \n"), exit(1); + usage(); } bounces = atoi(argv[3]); if (bounces <= 0) { fprintf(stderr, "invalid bounces\n"); - fprintf(stderr, "Usage: \n"), exit(1); + usage(); } nr_pages = nr_pages_per_cpu * nr_cpus; if (test_type == TEST_HUGETLB) { if (argc < 5) - fprintf(stderr, "Usage: hugetlb \n"), - exit(1); + usage(); huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755); if (huge_fd < 0) { fprintf(stderr, "Open of %s failed", argv[3]); From patchwork Sat Sep 29 08:43:10 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Xu X-Patchwork-Id: 10620683 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 1C7BB6CB for ; Sat, 29 Sep 2018 08:43:31 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 0F22429630 for ; Sat, 29 Sep 2018 08:43:31 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 0381829734; Sat, 29 Sep 2018 08:43:31 +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 90C9129630 for ; Sat, 29 Sep 2018 08:43:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727559AbeI2PLF (ORCPT ); Sat, 29 Sep 2018 11:11:05 -0400 Received: from mx1.redhat.com ([209.132.183.28]:43454 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727823AbeI2PLF (ORCPT ); Sat, 29 Sep 2018 11:11:05 -0400 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 4C8398762B; Sat, 29 Sep 2018 08:43:29 +0000 (UTC) Received: from xz-x1.nay.redhat.com (dhcp-14-128.nay.redhat.com [10.66.14.128]) by smtp.corp.redhat.com (Postfix) with ESMTP id F0C6A106A790; Sat, 29 Sep 2018 08:43:24 +0000 (UTC) From: Peter Xu To: linux-kernel@vger.kernel.org Cc: Shuah Khan , Jerome Glisse , Mike Rapoport , Mike Kravetz , peterx@redhat.com, linux-mm@kvack.org, Zi Yan , "Kirill A . Shutemov" , linux-kselftest@vger.kernel.org, Shaohua Li , Andrea Arcangeli , "Dr . David Alan Gilbert" , Andrew Morton Subject: [PATCH 2/3] userfaultfd: selftest: generalize read and poll Date: Sat, 29 Sep 2018 16:43:10 +0800 Message-Id: <20180929084311.15600-3-peterx@redhat.com> In-Reply-To: <20180929084311.15600-1-peterx@redhat.com> References: <20180929084311.15600-1-peterx@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.26]); Sat, 29 Sep 2018 08:43:29 +0000 (UTC) Sender: linux-kselftest-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP We do very similar things in read and poll modes, but we're copying the codes around. Share the codes properly on reading the message and handling the page fault to make the code cleaner. Meanwhile this solves previous mismatch of behaviors between the two modes on that the old code: - did not check EAGAIN case in read() mode - ignored BOUNCE_VERIFY check in read() mode Signed-off-by: Peter Xu --- tools/testing/selftests/vm/userfaultfd.c | 76 +++++++++++++----------- 1 file changed, 42 insertions(+), 34 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 2a84adaf8cf8..f79706f13ce7 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -449,6 +449,42 @@ static int copy_page(int ufd, unsigned long offset) return __copy_page(ufd, offset, false); } +static int uffd_read_msg(int ufd, struct uffd_msg *msg) +{ + int ret = read(uffd, msg, sizeof(*msg)); + + if (ret != sizeof(*msg)) { + if (ret < 0) + if (errno == EAGAIN) + return 1; + else + perror("blocking read error"), exit(1); + else + fprintf(stderr, "short read\n"), exit(1); + } + + return 0; +} + +/* Return 1 if page fault handled by us; otherwise 0 */ +static int uffd_handle_page_fault(struct uffd_msg *msg) +{ + unsigned long offset; + + if (msg->event != UFFD_EVENT_PAGEFAULT) + fprintf(stderr, "unexpected msg event %u\n", + msg->event), exit(1); + + if (bounces & BOUNCE_VERIFY && + msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + fprintf(stderr, "unexpected write fault\n"), exit(1); + + offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; + offset &= ~(page_size-1); + + return copy_page(uffd, offset); +} + static void *uffd_poll_thread(void *arg) { unsigned long cpu = (unsigned long) arg; @@ -456,7 +492,6 @@ static void *uffd_poll_thread(void *arg) struct uffd_msg msg; struct uffdio_register uffd_reg; int ret; - unsigned long offset; char tmp_chr; unsigned long userfaults = 0; @@ -480,25 +515,15 @@ static void *uffd_poll_thread(void *arg) if (!(pollfd[0].revents & POLLIN)) fprintf(stderr, "pollfd[0].revents %d\n", pollfd[0].revents), exit(1); - ret = read(uffd, &msg, sizeof(msg)); - if (ret < 0) { - if (errno == EAGAIN) - continue; - perror("nonblocking read error"), exit(1); - } + if (uffd_read_msg(uffd, &msg)) + continue; switch (msg.event) { default: fprintf(stderr, "unexpected msg event %u\n", msg.event), exit(1); break; case UFFD_EVENT_PAGEFAULT: - if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) - fprintf(stderr, "unexpected write fault\n"), exit(1); - offset = (char *)(unsigned long)msg.arg.pagefault.address - - area_dst; - offset &= ~(page_size-1); - if (copy_page(uffd, offset)) - userfaults++; + userfaults += uffd_handle_page_fault(&msg); break; case UFFD_EVENT_FORK: close(uffd); @@ -526,8 +551,6 @@ static void *uffd_read_thread(void *arg) { unsigned long *this_cpu_userfaults; struct uffd_msg msg; - unsigned long offset; - int ret; this_cpu_userfaults = (unsigned long *) arg; *this_cpu_userfaults = 0; @@ -536,24 +559,9 @@ static void *uffd_read_thread(void *arg) /* from here cancellation is ok */ for (;;) { - ret = read(uffd, &msg, sizeof(msg)); - if (ret != sizeof(msg)) { - if (ret < 0) - perror("blocking read error"), exit(1); - else - fprintf(stderr, "short read\n"), exit(1); - } - if (msg.event != UFFD_EVENT_PAGEFAULT) - fprintf(stderr, "unexpected msg event %u\n", - msg.event), exit(1); - if (bounces & BOUNCE_VERIFY && - msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) - fprintf(stderr, "unexpected write fault\n"), exit(1); - offset = (char *)(unsigned long)msg.arg.pagefault.address - - area_dst; - offset &= ~(page_size-1); - if (copy_page(uffd, offset)) - (*this_cpu_userfaults)++; + if (uffd_read_msg(uffd, &msg)) + continue; + (*this_cpu_userfaults) += uffd_handle_page_fault(&msg); } return (void *)NULL; } From patchwork Sat Sep 29 08:43:11 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Xu X-Patchwork-Id: 10620689 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 E56E31750 for ; Sat, 29 Sep 2018 08:43:40 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id D98AE2AF98 for ; Sat, 29 Sep 2018 08:43:40 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id CD9442AFA4; Sat, 29 Sep 2018 08:43:40 +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=unavailable 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 82AFD2AF99 for ; Sat, 29 Sep 2018 08:43:40 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727823AbeI2PLK (ORCPT ); Sat, 29 Sep 2018 11:11:10 -0400 Received: from mx1.redhat.com ([209.132.183.28]:37066 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727637AbeI2PLJ (ORCPT ); Sat, 29 Sep 2018 11:11:09 -0400 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 203D688306; Sat, 29 Sep 2018 08:43:34 +0000 (UTC) Received: from xz-x1.nay.redhat.com (dhcp-14-128.nay.redhat.com [10.66.14.128]) by smtp.corp.redhat.com (Postfix) with ESMTP id C5694106A790; Sat, 29 Sep 2018 08:43:29 +0000 (UTC) From: Peter Xu To: linux-kernel@vger.kernel.org Cc: Shuah Khan , Jerome Glisse , Mike Rapoport , Mike Kravetz , peterx@redhat.com, linux-mm@kvack.org, Zi Yan , "Kirill A . Shutemov" , linux-kselftest@vger.kernel.org, Shaohua Li , Andrea Arcangeli , "Dr . David Alan Gilbert" , Andrew Morton Subject: [PATCH 3/3] userfaultfd: selftest: recycle lock threads first Date: Sat, 29 Sep 2018 16:43:11 +0800 Message-Id: <20180929084311.15600-4-peterx@redhat.com> In-Reply-To: <20180929084311.15600-1-peterx@redhat.com> References: <20180929084311.15600-1-peterx@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.28]); Sat, 29 Sep 2018 08:43:34 +0000 (UTC) Sender: linux-kselftest-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Now we recycle the uffd servicing threads earlier than the lock threads. It might happen that when the lock thread is still blocked at a pthread mutex lock while the servicing thread has already quitted for the cpu so the lock thread will be blocked forever and hang the test program. To fix the possible race, recycle the lock threads first. This never happens with current missing-only tests, but when I start to run the write-protection tests (the feature is not yet posted upstream) it happens every time of the run possibly because in that new test we'll need to service two page faults for each lock operation. Signed-off-by: Peter Xu Acked-by: Mike Rapoport --- tools/testing/selftests/vm/userfaultfd.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index f79706f13ce7..a388675b15af 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -623,6 +623,12 @@ static int stress(unsigned long *userfaults) if (uffd_test_ops->release_pages(area_src)) return 1; + + finished = 1; + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pthread_join(locking_threads[cpu], NULL)) + return 1; + for (cpu = 0; cpu < nr_cpus; cpu++) { char c; if (bounces & BOUNCE_POLL) { @@ -640,11 +646,6 @@ static int stress(unsigned long *userfaults) } } - finished = 1; - for (cpu = 0; cpu < nr_cpus; cpu++) - if (pthread_join(locking_threads[cpu], NULL)) - return 1; - return 0; }