+ selftests-mm-hmm-tests-partial-unmap-mremap-and-anon_write-tests.patch added to mm-new branch

[Andrew Morton <akpm@linux-foundation.org>]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 13134 bytes --]


The patch titled
     Subject: selftests/mm/hmm-tests: partial unmap, mremap and anon_write tests
has been added to the -mm mm-new branch.  Its filename is
     selftests-mm-hmm-tests-partial-unmap-mremap-and-anon_write-tests.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/selftests-mm-hmm-tests-partial-unmap-mremap-and-anon_write-tests.patch

This patch will later appear in the mm-new branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Note, mm-new is a provisional staging ground for work-in-progress
patches, and acceptance into mm-new is a notification for others take
notice and to finish up reviews.  Please do not hesitate to respond to
review feedback and post updated versions to replace or incrementally
fixup patches in mm-new.

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Matthew Brost <matthew.brost@intel.com>
Subject: selftests/mm/hmm-tests: partial unmap, mremap and anon_write tests
Date: Wed, 1 Oct 2025 16:57:05 +1000

Add partial unmap test case which munmaps memory while in the device.

Add tests exercising mremap on faulted-in memory (CPU and GPU) at various
offsets and verify correctness.

Update anon_write_child to read device memory after fork verifying this
flow works in the kernel.

Both THP and non-THP cases are updated.

Link: https://lkml.kernel.org/r/20251001065707.920170-15-balbirs@nvidia.com
Signed-off-by: Balbir Singh <balbirs@nvidia.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: Ying Huang <ying.huang@linux.alibaba.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Mika Penttilä <mpenttil@redhat.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/testing/selftests/mm/hmm-tests.c |  308 ++++++++++++++++++-----
 1 file changed, 250 insertions(+), 58 deletions(-)

--- a/tools/testing/selftests/mm/hmm-tests.c~selftests-mm-hmm-tests-partial-unmap-mremap-and-anon_write-tests
+++ a/tools/testing/selftests/mm/hmm-tests.c
@@ -50,6 +50,8 @@ enum {
 	HMM_COHERENCE_DEVICE_TWO,
 };
 
+#define ONEKB		(1 << 10)
+#define ONEMEG		(1 << 20)
 #define TWOMEG		(1 << 21)
 #define HMM_BUFFER_SIZE (1024 << 12)
 #define HMM_PATH_MAX    64
@@ -525,6 +527,8 @@ TEST_F(hmm, anon_write_prot)
 /*
  * Check that a device writing an anonymous private mapping
  * will copy-on-write if a child process inherits the mapping.
+ *
+ * Also verifies after fork() memory the device can be read by child.
  */
 TEST_F(hmm, anon_write_child)
 {
@@ -532,72 +536,101 @@ TEST_F(hmm, anon_write_child)
 	unsigned long npages;
 	unsigned long size;
 	unsigned long i;
+	void *old_ptr;
+	void *map;
 	int *ptr;
 	pid_t pid;
 	int child_fd;
-	int ret;
+	int ret, use_thp, migrate;
 
-	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
-	ASSERT_NE(npages, 0);
-	size = npages << self->page_shift;
+	for (migrate = 0; migrate < 2; ++migrate) {
+		for (use_thp = 0; use_thp < 2; ++use_thp) {
+			npages = ALIGN(use_thp ? TWOMEG : HMM_BUFFER_SIZE,
+				       self->page_size) >> self->page_shift;
+			ASSERT_NE(npages, 0);
+			size = npages << self->page_shift;
+
+			buffer = malloc(sizeof(*buffer));
+			ASSERT_NE(buffer, NULL);
+
+			buffer->fd = -1;
+			buffer->size = size * 2;
+			buffer->mirror = malloc(size);
+			ASSERT_NE(buffer->mirror, NULL);
+
+			buffer->ptr = mmap(NULL, size * 2,
+					   PROT_READ | PROT_WRITE,
+					   MAP_PRIVATE | MAP_ANONYMOUS,
+					   buffer->fd, 0);
+			ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+			old_ptr = buffer->ptr;
+			if (use_thp) {
+				map = (void *)ALIGN((uintptr_t)buffer->ptr, size);
+				ret = madvise(map, size, MADV_HUGEPAGE);
+				ASSERT_EQ(ret, 0);
+				buffer->ptr = map;
+			}
+
+			/* Initialize buffer->ptr so we can tell if it is written. */
+			for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+				ptr[i] = i;
+
+			/* Initialize data that the device will write to buffer->ptr. */
+			for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+				ptr[i] = -i;
+
+			if (migrate) {
+				ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
+				ASSERT_EQ(ret, 0);
+				ASSERT_EQ(buffer->cpages, npages);
+
+			}
+
+			pid = fork();
+			if (pid == -1)
+				ASSERT_EQ(pid, 0);
+			if (pid != 0) {
+				waitpid(pid, &ret, 0);
+				ASSERT_EQ(WIFEXITED(ret), 1);
+
+				/* Check that the parent's buffer did not change. */
+				for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+					ASSERT_EQ(ptr[i], i);
+
+				buffer->ptr = old_ptr;
+				hmm_buffer_free(buffer);
+				continue;
+			}
+
+			/* Check that we see the parent's values. */
+			for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+				ASSERT_EQ(ptr[i], i);
+			if (!migrate) {
+				for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+					ASSERT_EQ(ptr[i], -i);
+			}
+
+			/* The child process needs its own mirror to its own mm. */
+			child_fd = hmm_open(0);
+			ASSERT_GE(child_fd, 0);
 
-	buffer = malloc(sizeof(*buffer));
-	ASSERT_NE(buffer, NULL);
-
-	buffer->fd = -1;
-	buffer->size = size;
-	buffer->mirror = malloc(size);
-	ASSERT_NE(buffer->mirror, NULL);
-
-	buffer->ptr = mmap(NULL, size,
-			   PROT_READ | PROT_WRITE,
-			   MAP_PRIVATE | MAP_ANONYMOUS,
-			   buffer->fd, 0);
-	ASSERT_NE(buffer->ptr, MAP_FAILED);
-
-	/* Initialize buffer->ptr so we can tell if it is written. */
-	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
-		ptr[i] = i;
-
-	/* Initialize data that the device will write to buffer->ptr. */
-	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
-		ptr[i] = -i;
+			/* Simulate a device writing system memory. */
+			ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages);
+			ASSERT_EQ(ret, 0);
+			ASSERT_EQ(buffer->cpages, npages);
+			ASSERT_EQ(buffer->faults, 1);
 
-	pid = fork();
-	if (pid == -1)
-		ASSERT_EQ(pid, 0);
-	if (pid != 0) {
-		waitpid(pid, &ret, 0);
-		ASSERT_EQ(WIFEXITED(ret), 1);
+			/* Check what the device wrote. */
+			if (!migrate) {
+				for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+					ASSERT_EQ(ptr[i], -i);
+			}
 
-		/* Check that the parent's buffer did not change. */
-		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
-			ASSERT_EQ(ptr[i], i);
-		return;
+			close(child_fd);
+			exit(0);
+		}
 	}
-
-	/* Check that we see the parent's values. */
-	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
-		ASSERT_EQ(ptr[i], i);
-	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
-		ASSERT_EQ(ptr[i], -i);
-
-	/* The child process needs its own mirror to its own mm. */
-	child_fd = hmm_open(0);
-	ASSERT_GE(child_fd, 0);
-
-	/* Simulate a device writing system memory. */
-	ret = hmm_dmirror_cmd(child_fd, HMM_DMIRROR_WRITE, buffer, npages);
-	ASSERT_EQ(ret, 0);
-	ASSERT_EQ(buffer->cpages, npages);
-	ASSERT_EQ(buffer->faults, 1);
-
-	/* Check what the device wrote. */
-	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
-		ASSERT_EQ(ptr[i], -i);
-
-	close(child_fd);
-	exit(0);
 }
 
 /*
@@ -2290,6 +2323,165 @@ TEST_F(hmm, migrate_anon_huge_fault)
 }
 
 /*
+ * Migrate memory and fault back to sysmem after partially unmapping.
+ */
+TEST_F(hmm, migrate_partial_unmap_fault)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size = TWOMEG;
+	unsigned long i;
+	void *old_ptr;
+	void *map;
+	int *ptr;
+	int ret, j, use_thp;
+	int offsets[] = { 0, 512 * ONEKB, ONEMEG };
+
+	for (use_thp = 0; use_thp < 2; ++use_thp) {
+		for (j = 0; j < ARRAY_SIZE(offsets); ++j) {
+			buffer = malloc(sizeof(*buffer));
+			ASSERT_NE(buffer, NULL);
+
+			buffer->fd = -1;
+			buffer->size = 2 * size;
+			buffer->mirror = malloc(size);
+			ASSERT_NE(buffer->mirror, NULL);
+			memset(buffer->mirror, 0xFF, size);
+
+			buffer->ptr = mmap(NULL, 2 * size,
+					   PROT_READ | PROT_WRITE,
+					   MAP_PRIVATE | MAP_ANONYMOUS,
+					   buffer->fd, 0);
+			ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+			npages = size >> self->page_shift;
+			map = (void *)ALIGN((uintptr_t)buffer->ptr, size);
+			if (use_thp)
+				ret = madvise(map, size, MADV_HUGEPAGE);
+			else
+				ret = madvise(map, size, MADV_NOHUGEPAGE);
+			ASSERT_EQ(ret, 0);
+			old_ptr = buffer->ptr;
+			buffer->ptr = map;
+
+			/* Initialize buffer in system memory. */
+			for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+				ptr[i] = i;
+
+			/* Migrate memory to device. */
+			ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
+			ASSERT_EQ(ret, 0);
+			ASSERT_EQ(buffer->cpages, npages);
+
+			/* Check what the device read. */
+			for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+				ASSERT_EQ(ptr[i], i);
+
+			munmap(buffer->ptr + offsets[j], ONEMEG);
+
+			/* Fault pages back to system memory and check them. */
+			for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+				if (i * sizeof(int) < offsets[j] ||
+				    i * sizeof(int) >= offsets[j] + ONEMEG)
+					ASSERT_EQ(ptr[i], i);
+
+			buffer->ptr = old_ptr;
+			hmm_buffer_free(buffer);
+		}
+	}
+}
+
+TEST_F(hmm, migrate_remap_fault)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size = TWOMEG;
+	unsigned long i;
+	void *old_ptr, *new_ptr = NULL;
+	void *map;
+	int *ptr;
+	int ret, j, use_thp, dont_unmap, before;
+	int offsets[] = { 0, 512 * ONEKB, ONEMEG };
+
+	for (before = 0; before < 2; ++before) {
+		for (dont_unmap = 0; dont_unmap < 2; ++dont_unmap) {
+			for (use_thp = 0; use_thp < 2; ++use_thp) {
+				for (j = 0; j < ARRAY_SIZE(offsets); ++j) {
+					int flags = MREMAP_MAYMOVE | MREMAP_FIXED;
+
+					if (dont_unmap)
+						flags |= MREMAP_DONTUNMAP;
+
+					buffer = malloc(sizeof(*buffer));
+					ASSERT_NE(buffer, NULL);
+
+					buffer->fd = -1;
+					buffer->size = 8 * size;
+					buffer->mirror = malloc(size);
+					ASSERT_NE(buffer->mirror, NULL);
+					memset(buffer->mirror, 0xFF, size);
+
+					buffer->ptr = mmap(NULL, buffer->size,
+							   PROT_READ | PROT_WRITE,
+							   MAP_PRIVATE | MAP_ANONYMOUS,
+							   buffer->fd, 0);
+					ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+					npages = size >> self->page_shift;
+					map = (void *)ALIGN((uintptr_t)buffer->ptr, size);
+					if (use_thp)
+						ret = madvise(map, size, MADV_HUGEPAGE);
+					else
+						ret = madvise(map, size, MADV_NOHUGEPAGE);
+					ASSERT_EQ(ret, 0);
+					old_ptr = buffer->ptr;
+					munmap(map + size, size * 2);
+					buffer->ptr = map;
+
+					/* Initialize buffer in system memory. */
+					for (i = 0, ptr = buffer->ptr;
+					     i < size / sizeof(*ptr); ++i)
+						ptr[i] = i;
+
+					if (before) {
+						new_ptr = mremap((void *)map, size, size, flags,
+								 map + size + offsets[j]);
+						ASSERT_NE(new_ptr, MAP_FAILED);
+						buffer->ptr = new_ptr;
+					}
+
+					/* Migrate memory to device. */
+					ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
+					ASSERT_EQ(ret, 0);
+					ASSERT_EQ(buffer->cpages, npages);
+
+					/* Check what the device read. */
+					for (i = 0, ptr = buffer->mirror;
+					     i < size / sizeof(*ptr); ++i)
+						ASSERT_EQ(ptr[i], i);
+
+					if (!before) {
+						new_ptr = mremap((void *)map, size, size, flags,
+								 map + size + offsets[j]);
+						ASSERT_NE(new_ptr, MAP_FAILED);
+						buffer->ptr = new_ptr;
+					}
+
+					/* Fault pages back to system memory and check them. */
+					for (i = 0, ptr = buffer->ptr;
+					     i < size / sizeof(*ptr); ++i)
+						ASSERT_EQ(ptr[i], i);
+
+					munmap(new_ptr, size);
+					buffer->ptr = old_ptr;
+					hmm_buffer_free(buffer);
+				}
+			}
+		}
+	}
+}
+
+/*
  * Migrate private anonymous huge page with allocation errors.
  */
 TEST_F(hmm, migrate_anon_huge_err)
_

Patches currently in -mm which might be from matthew.brost@intel.com are

selftests-mm-hmm-tests-partial-unmap-mremap-and-anon_write-tests.patch