Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Ralph Campbell <rcampbell@nvidia.com>
To:     <nouveau@lists.freedesktop.org>, <linux-rdma@vger.kernel.org>,
        <linux-mm@kvack.org>, <linux-kselftest@vger.kernel.org>,
        <linux-kernel@vger.kernel.org>
CC:     Jerome Glisse <jglisse@redhat.com>,
        John Hubbard <jhubbard@nvidia.com>,
        Christoph Hellwig <hch@lst.de>,
        Jason Gunthorpe <jgg@mellanox.com>,
        "Ben Skeggs" <bskeggs@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Shuah Khan <shuah@kernel.org>,
        Ralph Campbell <rcampbell@nvidia.com>
Subject: [PATCH 12/16] mm/hmm: optimize migrate_vma_setup() for holes
Date:   Fri, 19 Jun 2020 14:56:45 -0700
Message-ID: <20200619215649.32297-13-rcampbell@nvidia.com>
In-Reply-To: <20200619215649.32297-1-rcampbell@nvidia.com>
References: <20200619215649.32297-1-rcampbell@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

When migrating system memory to device private memory, if the source
address range is a valid VMA range and there is no memory or a zero page,
the source PFN array is marked as valid but with no PFN. This lets the
device driver allocate private memory and clear it, then insert the new
device private struct page into the CPU's page tables when
migrate_vma_pages() is called. migrate_vma_pages() only inserts the
new page if the VMA is an anonymous range. There is no point in telling
the device driver to allocate device private memory and then throwing
it away. Instead, mark the source PFN array entries as not migrating to
avoid this overhead.

Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
---
 mm/migrate.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 24535281cea3..87c52e0ee580 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2178,9 +2178,13 @@ static int migrate_vma_collect_hole(unsigned long st=
art,
 {
 	struct migrate_vma *migrate =3D walk->private;
 	unsigned long addr;
+	unsigned long flags;
+
+	/* Only allow populating anonymous memory */
+	flags =3D vma_is_anonymous(walk->vma) ? MIGRATE_PFN_MIGRATE : 0;
=20
 	for (addr =3D start; addr < end; addr +=3D PAGE_SIZE) {
-		migrate->src[migrate->npages] =3D MIGRATE_PFN_MIGRATE;
+		migrate->src[migrate->npages] =3D flags;
 		migrate->dst[migrate->npages] =3D 0;
 		migrate->npages++;
 		migrate->cpages++;
@@ -2748,7 +2752,7 @@ static void migrate_vma_insert_page(struct migrate_vm=
a *migrate,
 	pte_t *ptep;
=20
 	/* Only allow populating anonymous memory */
-	if (!vma_is_anonymous(vma))
+	if (WARN_ON_ONCE(!vma_is_anonymous(vma)))
 		goto abort;
=20
 	pgdp =3D pgd_offset(mm, addr);
--=20
2.20.1