Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751029AbdFTC5j (ORCPT ); Mon, 19 Jun 2017 22:57:39 -0400 Received: from mail-pf0-f174.google.com ([209.85.192.174]:36744 "EHLO mail-pf0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750916AbdFTC5h (ORCPT ); Mon, 19 Jun 2017 22:57:37 -0400 Date: Mon, 19 Jun 2017 19:57:27 -0700 (PDT) From: Hugh Dickins X-X-Sender: hugh@eggly.anvils To: Willy Tarreau cc: Ben Hutchings , linux-kernel@vger.kernel.org, stable@vger.kernel.org, linux@roeck-us.net, Boris Ostrovsky , Juergen Gross Subject: Re: [PATCH 3.10 060/268] xen/gntdev: Use VM_MIXEDMAP instead of VM_IO to avoid NUMA balancing In-Reply-To: <1497897167-14556-61-git-send-email-w@1wt.eu> Message-ID: References: <1497897167-14556-1-git-send-email-w@1wt.eu> <1497897167-14556-61-git-send-email-w@1wt.eu> User-Agent: Alpine 2.11 (LSU 23 2013-08-11) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2761 Lines: 82 On Mon, 19 Jun 2017, Willy Tarreau wrote: > From: Boris Ostrovsky > > commit 30faaafdfa0c754c91bac60f216c9f34a2bfdf7e upstream. > > Commit 9c17d96500f7 ("xen/gntdev: Grant maps should not be subject to > NUMA balancing") set VM_IO flag to prevent grant maps from being > subjected to NUMA balancing. > > It was discovered recently that this flag causes get_user_pages() to > always fail with -EFAULT. > > check_vma_flags > __get_user_pages > __get_user_pages_locked > __get_user_pages_unlocked > get_user_pages_fast > iov_iter_get_pages > dio_refill_pages > do_direct_IO > do_blockdev_direct_IO > do_blockdev_direct_IO > ext4_direct_IO_read > generic_file_read_iter > aio_run_iocb > > (which can happen if guest's vdisk has direct-io-safe option). > > To avoid this let's use VM_MIXEDMAP flag instead --- it prevents > NUMA balancing just as VM_IO does and has no effect on > check_vma_flags(). This is only valid if kernel/sched/fair.c is checking for VM_MIXEDMAP, and that came in v4.1's 8e76d4eecf7a ("sched, numa: do not hint for NUMA balancing on VM_MIXEDMAP mappings"), which I don't see in your tree nor in this series (please double check, I may have missed it). It would be good to have that one in too, and it was marked for stable; but maybe it didn't apply, because of depending on another commit adding the is_vm_hugetlb_page(vma) check there? Which I expect would also be good to have, but I haven't looked it up. Maybe drop this one for this round, and gather up its dependencies for the next round. Ben's 3.16 tree appeared to be in the same position, I didn't look at the EOL 3.18. (I've not yet checked through backports of the "larger stack guard gap" - thank you all for those - will do so, but won't get through them tonight - I must look into DaveJ's trinity VM_BUG_ON now.) Hugh > > Reported-by: Olaf Hering > Suggested-by: Hugh Dickins > Signed-off-by: Boris Ostrovsky > Acked-by: Hugh Dickins > Tested-by: Olaf Hering > Signed-off-by: Juergen Gross > Signed-off-by: Willy Tarreau > --- > drivers/xen/gntdev.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c > index 3d8e609..6c6d253 100644 > --- a/drivers/xen/gntdev.c > +++ b/drivers/xen/gntdev.c > @@ -770,7 +770,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) > > vma->vm_ops = &gntdev_vmops; > > - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_IO; > + vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP; > > if (use_ptemod) > vma->vm_flags |= VM_DONTCOPY; > -- > 2.8.0.rc2.1.gbe9624a