Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Tue, 20 Jun 2023 12:23:55 -0400
From:   Peter Xu <peterx@redhat.com>
To:     David Hildenbrand <david@redhat.com>
Cc:     linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Andrea Arcangeli <aarcange@redhat.com>,
        Mike Rapoport <rppt@kernel.org>,
        Matthew Wilcox <willy@infradead.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        John Hubbard <jhubbard@nvidia.com>,
        "Kirill A . Shutemov" <kirill@shutemov.name>,
        James Houghton <jthoughton@google.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Lorenzo Stoakes <lstoakes@gmail.com>,
        Hugh Dickins <hughd@google.com>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Jason Gunthorpe <jgg@nvidia.com>
Subject: Re: [PATCH v2 5/8] mm/gup: Accelerate thp gup even for "pages !=
 NULL"
Message-ID: <ZJHSm/UbEy3JndZ4@x1n>
References: <20230619231044.112894-1-peterx@redhat.com>
 <20230619231044.112894-6-peterx@redhat.com>
 <02a057a3-3d9e-4013-8762-25ceb1beec86@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <02a057a3-3d9e-4013-8762-25ceb1beec86@redhat.com>
Precedence: bulk

On Tue, Jun 20, 2023 at 05:43:35PM +0200, David Hildenbrand wrote:
> On 20.06.23 01:10, Peter Xu wrote:
> > The acceleration of THP was done with ctx.page_mask, however it'll be
> > ignored if **pages is non-NULL.
> > 
> > The old optimization was introduced in 2013 in 240aadeedc4a ("mm:
> > accelerate mm_populate() treatment of THP pages").  It didn't explain why
> > we can't optimize the **pages non-NULL case.  It's possible that at that
> > time the major goal was for mm_populate() which should be enough back then.
> 
> In the past we had these sub-page refcounts for THP. My best guess (and I
> didn't check if that was still the case in 2013) would be that it was
> simpler regarding refcount handling to to do it one-subpage at a time.
> 
> But I might be just wrong.
> 
> > 
> > Optimize thp for all cases, by properly looping over each subpage, doing
> > cache flushes, and boost refcounts / pincounts where needed in one go.
> > 
> > This can be verified using gup_test below:
> > 
> >    # chrt -f 1 ./gup_test -m 512 -t -L -n 1024 -r 10
> > 
> > Before:    13992.50 ( +-8.75%)
> > After:       378.50 (+-69.62%)
> > 
> > Signed-off-by: Peter Xu <peterx@redhat.com>
> > ---
> >   mm/gup.c | 51 ++++++++++++++++++++++++++++++++++++++++++++-------
> >   1 file changed, 44 insertions(+), 7 deletions(-)
> > 
> > diff --git a/mm/gup.c b/mm/gup.c
> > index 4a00d609033e..b50272012e49 100644
> > --- a/mm/gup.c
> > +++ b/mm/gup.c
> > @@ -1199,16 +1199,53 @@ static long __get_user_pages(struct mm_struct *mm,
> >   			goto out;
> >   		}
> >   next_page:
> > -		if (pages) {
> > -			pages[i] = page;
> > -			flush_anon_page(vma, page, start);
> > -			flush_dcache_page(page);
> > -			ctx.page_mask = 0;
> > -		}
> > -
> >   		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
> >   		if (page_increm > nr_pages)
> >   			page_increm = nr_pages;
> > +
> > +		if (pages) {
> > +			struct page *subpage;
> > +			unsigned int j;
> > +
> > +			/*
> > +			 * This must be a large folio (and doesn't need to
> > +			 * be the whole folio; it can be part of it), do
> > +			 * the refcount work for all the subpages too.
> > +			 *
> > +			 * NOTE: here the page may not be the head page
> > +			 * e.g. when start addr is not thp-size aligned.
> > +			 * try_grab_folio() should have taken care of tail
> > +			 * pages.
> > +			 */
> > +			if (page_increm > 1) {
> > +				struct folio *folio;
> > +
> > +				/*
> > +				 * Since we already hold refcount on the
> > +				 * large folio, this should never fail.
> > +				 */
> > +				folio = try_grab_folio(page, page_increm - 1,
> > +						       foll_flags);
> > +				if (WARN_ON_ONCE(!folio)) {
> > +					/*
> > +					 * Release the 1st page ref if the
> > +					 * folio is problematic, fail hard.
> > +					 */
> > +					gup_put_folio(page_folio(page), 1,
> > +						      foll_flags);
> > +					ret = -EFAULT;
> > +					goto out;
> > +				}
> > +			}
> > +
> > +			for (j = 0; j < page_increm; j++) {
> > +				subpage = nth_page(page, j);
> > +				pages[i+j] = subpage;
> 
> Doe checkpatch like pages[i+j]? I'd have used spaces around the +.

Can do.

> 
> > +				flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
> > +				flush_dcache_page(subpage);
> > +			}
> > +		}
> > +
> >   		i += page_increm;
> >   		start += page_increm * PAGE_SIZE;
> >   		nr_pages -= page_increm;
> 
> 
> So, we did the first try_grab_folio() while our page was PMD-mapped udner
> the PT lock and we had sufficient permissions (e.g., mapped writable, no
> unsharing required). With FOLL_PIN, we incremented the pincount.
> 
> 
> I was wondering if something could have happened ever since we unlocked the
> PT table lock and possibly PTE-mapped the THP. ... but as it's already
> pinned, it cannot get shared during fork() [will stay exclusive].
> 
> So we can just take additional pins on that folio.
> 
> 
> LGTM, although I do like the GUP-fast way of recording+ref'ing it at a
> central place (see gup_huge_pmd() with record_subpages() and friends), not
> after the effects.

My read on this is follow_page_mask() is also used in follow page, which
does not need page*.

No strong opinion here. Maybe we leave this as a follow up even if it can
be justified?  This patch is probably still the smallest (and still clean)
change to speed this whole thing up over either thp or hugetlb.

-- 
Peter Xu