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;
Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates
 216.228.112.34 as permitted sender) receiver=protection.outlook.com;
 client-ip=216.228.112.34; helo=mail.nvidia.com;
From:   Alistair Popple <apopple@nvidia.com>
To:     <akpm@linux-foundation.org>
CC:     <jglisse@redhat.com>, <jhubbard@nvidia.com>, <ziy@nvidia.com>,
        <rcampbell@nvidia.com>, <Felix.Kuehling@amd.com>,
        <linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>,
        <jgg@nvidia.com>, Alistair Popple <apopple@nvidia.com>
Subject: [PATCH] mm/hmm.c: Allow VM_MIXEDMAP to work with hmm_range_fault
Date:   Thu, 4 Nov 2021 12:20:01 +1100
Message-ID: <20211104012001.2555676-1-apopple@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 04 Nov 2021 01:20:29.0911
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 5e9504b3-e912-416e-33c3-08d99f3149eb
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[216.228.112.34];Helo=[mail.nvidia.com]
X-MS-Exchange-CrossTenant-AuthSource: CO1NAM11FT021.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MWHPR1201MB0046
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

hmm_range_fault() can be used instead of get_user_pages() for devices
which allow faulting however unlike get_user_pages() it will return an
error when used on a VM_MIXEDMAP range.

To make hmm_range_fault() more closely match get_user_pages() remove
this restriction. This requires dealing with the !ARCH_HAS_PTE_SPECIAL
case in hmm_vma_handle_pte(). Rather than replicating the logic of
vm_normal_page() call it directly and do a check for the zero pfn
similar to what get_user_pages() currently does.

Also add a test to hmm selftest to verify functionality.

Signed-off-by: Alistair Popple <apopple@nvidia.com>
---
 lib/test_hmm.c                         | 24 +++++++++++++++
 mm/hmm.c                               |  5 +--
 tools/testing/selftests/vm/hmm-tests.c | 42 ++++++++++++++++++++++++++
 3 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index c259842f6d44..ac794e354069 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -1087,9 +1087,33 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp,
 	return 0;
 }
 
+static int dmirror_fops_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	unsigned long addr;
+
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
+		struct page *page;
+		int ret;
+
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			return -ENOMEM;
+
+		ret = vm_insert_page(vma, addr, page);
+		if (ret) {
+			__free_page(page);
+			return ret;
+		}
+		put_page(page);
+	}
+
+	return 0;
+}
+
 static const struct file_operations dmirror_fops = {
 	.open		= dmirror_fops_open,
 	.release	= dmirror_fops_release,
+	.mmap		= dmirror_fops_mmap,
 	.unlocked_ioctl = dmirror_fops_unlocked_ioctl,
 	.llseek		= default_llseek,
 	.owner		= THIS_MODULE,
diff --git a/mm/hmm.c b/mm/hmm.c
index fad6be2bf072..70fa81a3b629 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -298,7 +298,8 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 	 * Since each architecture defines a struct page for the zero page, just
 	 * fall through and treat it like a normal page.
 	 */
-	if (pte_special(pte) && !is_zero_pfn(pte_pfn(pte))) {
+	if (!vm_normal_page(walk->vma, addr, pte) &&
+		!is_zero_pfn(pte_pfn(pte))) {
 		if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) {
 			pte_unmap(ptep);
 			return -EFAULT;
@@ -515,7 +516,7 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
 	struct hmm_range *range = hmm_vma_walk->range;
 	struct vm_area_struct *vma = walk->vma;
 
-	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP | VM_MIXEDMAP)) &&
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)) &&
 	    vma->vm_flags & VM_READ)
 		return 0;
 
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 864f126ffd78..203323967b50 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -1248,6 +1248,48 @@ TEST_F(hmm, anon_teardown)
 	}
 }
 
+/*
+ * Test memory snapshot without faulting in pages accessed by the device.
+ */
+TEST_F(hmm, mixedmap)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned char *m;
+	int ret;
+
+	npages = 1;
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(npages);
+	ASSERT_NE(buffer->mirror, NULL);
+
+
+	/* Reserve a range of addresses. */
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE,
+			   self->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Simulate a device snapshotting CPU pagetables. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device saw. */
+	m = buffer->mirror;
+	ASSERT_EQ(m[0], HMM_DMIRROR_PROT_READ);
+
+	hmm_buffer_free(buffer);
+}
+
 /*
  * Test memory snapshot without faulting in pages accessed by the device.
  */
-- 
2.30.2