diff mbox series

[v4,5/5] selftests/mm: add UFFDIO_MOVE ioctl test

Message ID 20231028003819.652322-6-surenb@google.com (mailing list archive)
State New, archived
Headers show
Series userfaultfd move option | expand

Commit Message

Suren Baghdasaryan Oct. 28, 2023, 12:38 a.m. UTC
Add tests for new UFFDIO_MOVE ioctl which uses uffd to move source
into destination buffer while checking the contents of both after
the move. After the operation the content of the destination buffer
should match the original source buffer's content while the source
buffer should be zeroed. Separate tests are designed for PMD aligned and
unaligned cases because they utilize different code paths in the kernel.

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 tools/testing/selftests/mm/uffd-common.c     |  24 ++++
 tools/testing/selftests/mm/uffd-common.h     |   1 +
 tools/testing/selftests/mm/uffd-unit-tests.c | 141 +++++++++++++++++++
 3 files changed, 166 insertions(+)

Comments

Peter Xu Oct. 30, 2023, 8:14 p.m. UTC | #1
On Fri, Oct 27, 2023 at 05:38:15PM -0700, Suren Baghdasaryan wrote:
> Add tests for new UFFDIO_MOVE ioctl which uses uffd to move source
> into destination buffer while checking the contents of both after
> the move. After the operation the content of the destination buffer
> should match the original source buffer's content while the source
> buffer should be zeroed. Separate tests are designed for PMD aligned and
> unaligned cases because they utilize different code paths in the kernel.
> 
> Signed-off-by: Suren Baghdasaryan <surenb@google.com>
> ---
>  tools/testing/selftests/mm/uffd-common.c     |  24 ++++
>  tools/testing/selftests/mm/uffd-common.h     |   1 +
>  tools/testing/selftests/mm/uffd-unit-tests.c | 141 +++++++++++++++++++
>  3 files changed, 166 insertions(+)
> 
> diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
> index 69e6653ad255..98957fd788d8 100644
> --- a/tools/testing/selftests/mm/uffd-common.c
> +++ b/tools/testing/selftests/mm/uffd-common.c
> @@ -643,6 +643,30 @@ int copy_page(int ufd, unsigned long offset, bool wp)
>  	return __copy_page(ufd, offset, false, wp);
>  }
>  
> +int move_page(int ufd, unsigned long offset)
> +{
> +	struct uffdio_move uffdio_move;
> +
> +	if (offset >= nr_pages * page_size)
> +		err("unexpected offset %lu\n", offset);
> +	uffdio_move.dst = (unsigned long) area_dst + offset;
> +	uffdio_move.src = (unsigned long) area_src + offset;
> +	uffdio_move.len = page_size;
> +	uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES;
> +	uffdio_move.move = 0;
> +	if (ioctl(ufd, UFFDIO_MOVE, &uffdio_move)) {
> +		/* real retval in uffdio_move.move */
> +		if (uffdio_move.move != -EEXIST)
> +			err("UFFDIO_MOVE error: %"PRId64,
> +			    (int64_t)uffdio_move.move);
> +		wake_range(ufd, uffdio_move.dst, page_size);
> +	} else if (uffdio_move.move != page_size) {
> +		err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move);
> +	} else
> +		return 1;
> +	return 0;
> +}
> +
>  int uffd_open_dev(unsigned int flags)
>  {
>  	int fd, uffd;
> diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
> index 19930fd6682b..c9526b2cb6b3 100644
> --- a/tools/testing/selftests/mm/uffd-common.h
> +++ b/tools/testing/selftests/mm/uffd-common.h
> @@ -121,6 +121,7 @@ void wp_range(int ufd, __u64 start, __u64 len, bool wp);
>  void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args);
>  int __copy_page(int ufd, unsigned long offset, bool retry, bool wp);
>  int copy_page(int ufd, unsigned long offset, bool wp);
> +int move_page(int ufd, unsigned long offset);
>  void *uffd_poll_thread(void *arg);
>  
>  int uffd_open_dev(unsigned int flags);
> diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
> index debc423bdbf4..89e9529ce941 100644
> --- a/tools/testing/selftests/mm/uffd-unit-tests.c
> +++ b/tools/testing/selftests/mm/uffd-unit-tests.c
> @@ -1064,6 +1064,133 @@ static void uffd_poison_test(uffd_test_args_t *targs)
>  	uffd_test_pass();
>  }
>  
> +static void uffd_move_handle_fault(
> +	struct uffd_msg *msg, struct uffd_args *args)
> +{
> +	unsigned long offset;
> +
> +	if (msg->event != UFFD_EVENT_PAGEFAULT)
> +		err("unexpected msg event %u", msg->event);
> +
> +	if (msg->arg.pagefault.flags &
> +	    (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE))
> +		err("unexpected fault type %llu", msg->arg.pagefault.flags);
> +
> +	offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
> +	offset &= ~(page_size-1);
> +
> +	if (move_page(uffd, offset))
> +		args->missing_faults++;
> +}
> +
> +static void uffd_move_test(uffd_test_args_t *targs)
> +{
> +	unsigned long nr;
> +	pthread_t uffd_mon;
> +	char c;
> +	unsigned long long count;
> +	struct uffd_args args = { 0 };
> +
> +	/* Prevent source pages from being mapped more than once */
> +	if (madvise(area_src, nr_pages * page_size, MADV_DONTFORK))
> +		err("madvise(MADV_DONTFORK) failure");
> +
> +	if (uffd_register(uffd, area_dst, nr_pages * page_size,
> +			  true, false, false))
> +		err("register failure");
> +
> +	args.handle_fault = uffd_move_handle_fault;
> +	if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
> +		err("uffd_poll_thread create");
> +
> +	/*
> +	 * Read each of the pages back using the UFFD-registered mapping. We
> +	 * expect that the first time we touch a page, it will result in a missing
> +	 * fault. uffd_poll_thread will resolve the fault by moving source
> +	 * page to destination.
> +	 */
> +	for (nr = 0; nr < nr_pages; nr++) {
> +		/* Check area_src content */
> +		count = *area_count(area_src, nr);
> +		if (count != count_verify[nr])
> +			err("nr %lu source memory invalid %llu %llu\n",
> +			    nr, count, count_verify[nr]);
> +
> +		/* Faulting into area_dst should move the page */
> +		count = *area_count(area_dst, nr);
> +		if (count != count_verify[nr])
> +			err("nr %lu memory corruption %llu %llu\n",
> +			    nr, count, count_verify[nr]);
> +
> +		/* Re-check area_src content which should be empty */
> +		count = *area_count(area_src, nr);
> +		if (count != 0)
> +			err("nr %lu move failed %llu %llu\n",
> +			    nr, count, count_verify[nr]);
> +	}
> +
> +	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
> +		err("pipe write");
> +	if (pthread_join(uffd_mon, NULL))
> +		err("join() failed");
> +
> +	if (args.missing_faults != nr_pages || args.minor_faults != 0)
> +		uffd_test_fail("stats check error");
> +	else
> +		uffd_test_pass();
> +}
> +
> +static int prevent_hugepages(void)
> +{
> +	/* This should be done before source area is populated */
> +	if (madvise(area_src, nr_pages * page_size, MADV_NOHUGEPAGE)) {
> +		/* Ignore if CONFIG_TRANSPARENT_HUGEPAGE=n */
> +		if (errno != EINVAL)
> +			return -errno;
> +	}
> +	return 0;
> +}
> +
> +struct uffd_test_case_ops uffd_move_test_case_ops = {
> +	.post_alloc = prevent_hugepages,
> +};
> +
> +#define ALIGN_UP(x, align_to) \
> +	(__typeof__(x))((((unsigned long)(x)) + ((align_to)-1)) & ~((align_to)-1))
> +
> +static char *orig_area_src, *orig_area_dst;
> +static int pmd_align_areas(void)
> +{
> +	orig_area_src = area_src;
> +	orig_area_dst = area_dst;
> +	area_src = ALIGN_UP(area_src, page_size);
> +	area_dst = ALIGN_UP(area_dst, page_size);
> +	nr_pages--;
> +
> +	return 0;
> +}
> +
> +static void pmd_restore_areas(void)
> +{
> +	area_src = orig_area_src;
> +	area_dst = orig_area_dst;
> +	nr_pages++;
> +}

Please stop using more global variables.. uffd tests are even less
maintainable.

Maybe you can consider add a flag for uffd_test_ctx_init()?  For allocating
either small/thp/default?

> +
> +static int adjust_page_size(void)
> +{
> +	page_size = default_huge_page_size();

This is hacky too, currently page_size is the real page_size backing the
memory.

To make thp test simple, maybe just add one more test to MOVE a large chunk
to replace the thp test, which may contain a few thps?  It also doesn't
need to be fault based.

> +	nr_pages = UFFD_TEST_MEM_SIZE / page_size;
> +
> +	return 0;
> +}
> +
> +struct uffd_test_case_ops uffd_move_pmd_test_case_ops = {
> +	.pre_alloc = adjust_page_size,
> +	.post_alloc = pmd_align_areas,
> +	.pre_release = pmd_restore_areas,
> +};
> +
>  /*
>   * Test the returned uffdio_register.ioctls with different register modes.
>   * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test.
> @@ -1141,6 +1268,20 @@ uffd_test_case_t uffd_tests[] = {
>  		.mem_targets = MEM_ALL,
>  		.uffd_feature_required = 0,
>  	},
> +	{
> +		.name = "move",
> +		.uffd_fn = uffd_move_test,
> +		.mem_targets = MEM_ANON,
> +		.uffd_feature_required = UFFD_FEATURE_MOVE,
> +		.test_case_ops = &uffd_move_test_case_ops,
> +	},
> +	{
> +		.name = "move-pmd",
> +		.uffd_fn = uffd_move_test,
> +		.mem_targets = MEM_ANON,
> +		.uffd_feature_required = UFFD_FEATURE_MOVE,
> +		.test_case_ops = &uffd_move_pmd_test_case_ops,
> +	},
>  	{
>  		.name = "wp-fork",
>  		.uffd_fn = uffd_wp_fork_test,
> -- 
> 2.42.0.820.g83a721a137-goog
>
Suren Baghdasaryan Oct. 30, 2023, 8:22 p.m. UTC | #2
On Mon, Oct 30, 2023 at 1:14 PM Peter Xu <peterx@redhat.com> wrote:
>
> On Fri, Oct 27, 2023 at 05:38:15PM -0700, Suren Baghdasaryan wrote:
> > Add tests for new UFFDIO_MOVE ioctl which uses uffd to move source
> > into destination buffer while checking the contents of both after
> > the move. After the operation the content of the destination buffer
> > should match the original source buffer's content while the source
> > buffer should be zeroed. Separate tests are designed for PMD aligned and
> > unaligned cases because they utilize different code paths in the kernel.
> >
> > Signed-off-by: Suren Baghdasaryan <surenb@google.com>
> > ---
> >  tools/testing/selftests/mm/uffd-common.c     |  24 ++++
> >  tools/testing/selftests/mm/uffd-common.h     |   1 +
> >  tools/testing/selftests/mm/uffd-unit-tests.c | 141 +++++++++++++++++++
> >  3 files changed, 166 insertions(+)
> >
> > diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
> > index 69e6653ad255..98957fd788d8 100644
> > --- a/tools/testing/selftests/mm/uffd-common.c
> > +++ b/tools/testing/selftests/mm/uffd-common.c
> > @@ -643,6 +643,30 @@ int copy_page(int ufd, unsigned long offset, bool wp)
> >       return __copy_page(ufd, offset, false, wp);
> >  }
> >
> > +int move_page(int ufd, unsigned long offset)
> > +{
> > +     struct uffdio_move uffdio_move;
> > +
> > +     if (offset >= nr_pages * page_size)
> > +             err("unexpected offset %lu\n", offset);
> > +     uffdio_move.dst = (unsigned long) area_dst + offset;
> > +     uffdio_move.src = (unsigned long) area_src + offset;
> > +     uffdio_move.len = page_size;
> > +     uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES;
> > +     uffdio_move.move = 0;
> > +     if (ioctl(ufd, UFFDIO_MOVE, &uffdio_move)) {
> > +             /* real retval in uffdio_move.move */
> > +             if (uffdio_move.move != -EEXIST)
> > +                     err("UFFDIO_MOVE error: %"PRId64,
> > +                         (int64_t)uffdio_move.move);
> > +             wake_range(ufd, uffdio_move.dst, page_size);
> > +     } else if (uffdio_move.move != page_size) {
> > +             err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move);
> > +     } else
> > +             return 1;
> > +     return 0;
> > +}
> > +
> >  int uffd_open_dev(unsigned int flags)
> >  {
> >       int fd, uffd;
> > diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
> > index 19930fd6682b..c9526b2cb6b3 100644
> > --- a/tools/testing/selftests/mm/uffd-common.h
> > +++ b/tools/testing/selftests/mm/uffd-common.h
> > @@ -121,6 +121,7 @@ void wp_range(int ufd, __u64 start, __u64 len, bool wp);
> >  void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args);
> >  int __copy_page(int ufd, unsigned long offset, bool retry, bool wp);
> >  int copy_page(int ufd, unsigned long offset, bool wp);
> > +int move_page(int ufd, unsigned long offset);
> >  void *uffd_poll_thread(void *arg);
> >
> >  int uffd_open_dev(unsigned int flags);
> > diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
> > index debc423bdbf4..89e9529ce941 100644
> > --- a/tools/testing/selftests/mm/uffd-unit-tests.c
> > +++ b/tools/testing/selftests/mm/uffd-unit-tests.c
> > @@ -1064,6 +1064,133 @@ static void uffd_poison_test(uffd_test_args_t *targs)
> >       uffd_test_pass();
> >  }
> >
> > +static void uffd_move_handle_fault(
> > +     struct uffd_msg *msg, struct uffd_args *args)
> > +{
> > +     unsigned long offset;
> > +
> > +     if (msg->event != UFFD_EVENT_PAGEFAULT)
> > +             err("unexpected msg event %u", msg->event);
> > +
> > +     if (msg->arg.pagefault.flags &
> > +         (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE))
> > +             err("unexpected fault type %llu", msg->arg.pagefault.flags);
> > +
> > +     offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
> > +     offset &= ~(page_size-1);
> > +
> > +     if (move_page(uffd, offset))
> > +             args->missing_faults++;
> > +}
> > +
> > +static void uffd_move_test(uffd_test_args_t *targs)
> > +{
> > +     unsigned long nr;
> > +     pthread_t uffd_mon;
> > +     char c;
> > +     unsigned long long count;
> > +     struct uffd_args args = { 0 };
> > +
> > +     /* Prevent source pages from being mapped more than once */
> > +     if (madvise(area_src, nr_pages * page_size, MADV_DONTFORK))
> > +             err("madvise(MADV_DONTFORK) failure");
> > +
> > +     if (uffd_register(uffd, area_dst, nr_pages * page_size,
> > +                       true, false, false))
> > +             err("register failure");
> > +
> > +     args.handle_fault = uffd_move_handle_fault;
> > +     if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
> > +             err("uffd_poll_thread create");
> > +
> > +     /*
> > +      * Read each of the pages back using the UFFD-registered mapping. We
> > +      * expect that the first time we touch a page, it will result in a missing
> > +      * fault. uffd_poll_thread will resolve the fault by moving source
> > +      * page to destination.
> > +      */
> > +     for (nr = 0; nr < nr_pages; nr++) {
> > +             /* Check area_src content */
> > +             count = *area_count(area_src, nr);
> > +             if (count != count_verify[nr])
> > +                     err("nr %lu source memory invalid %llu %llu\n",
> > +                         nr, count, count_verify[nr]);
> > +
> > +             /* Faulting into area_dst should move the page */
> > +             count = *area_count(area_dst, nr);
> > +             if (count != count_verify[nr])
> > +                     err("nr %lu memory corruption %llu %llu\n",
> > +                         nr, count, count_verify[nr]);
> > +
> > +             /* Re-check area_src content which should be empty */
> > +             count = *area_count(area_src, nr);
> > +             if (count != 0)
> > +                     err("nr %lu move failed %llu %llu\n",
> > +                         nr, count, count_verify[nr]);
> > +     }
> > +
> > +     if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
> > +             err("pipe write");
> > +     if (pthread_join(uffd_mon, NULL))
> > +             err("join() failed");
> > +
> > +     if (args.missing_faults != nr_pages || args.minor_faults != 0)
> > +             uffd_test_fail("stats check error");
> > +     else
> > +             uffd_test_pass();
> > +}
> > +
> > +static int prevent_hugepages(void)
> > +{
> > +     /* This should be done before source area is populated */
> > +     if (madvise(area_src, nr_pages * page_size, MADV_NOHUGEPAGE)) {
> > +             /* Ignore if CONFIG_TRANSPARENT_HUGEPAGE=n */
> > +             if (errno != EINVAL)
> > +                     return -errno;
> > +     }
> > +     return 0;
> > +}
> > +
> > +struct uffd_test_case_ops uffd_move_test_case_ops = {
> > +     .post_alloc = prevent_hugepages,
> > +};
> > +
> > +#define ALIGN_UP(x, align_to) \
> > +     (__typeof__(x))((((unsigned long)(x)) + ((align_to)-1)) & ~((align_to)-1))
> > +
> > +static char *orig_area_src, *orig_area_dst;
> > +static int pmd_align_areas(void)
> > +{
> > +     orig_area_src = area_src;
> > +     orig_area_dst = area_dst;
> > +     area_src = ALIGN_UP(area_src, page_size);
> > +     area_dst = ALIGN_UP(area_dst, page_size);
> > +     nr_pages--;
> > +
> > +     return 0;
> > +}
> > +
> > +static void pmd_restore_areas(void)
> > +{
> > +     area_src = orig_area_src;
> > +     area_dst = orig_area_dst;
> > +     nr_pages++;
> > +}
>
> Please stop using more global variables.. uffd tests are even less
> maintainable.
>
> Maybe you can consider add a flag for uffd_test_ctx_init()?  For allocating
> either small/thp/default?

I was considering that but was not sure which way would be more
preferable - using these new callbacks or adding new page size
requirements. I'll change to the latter.

>
>
> > +
> > +static int adjust_page_size(void)
> > +{
> > +     page_size = default_huge_page_size();
>
> This is hacky too, currently page_size is the real page_size backing the
> memory.
>
> To make thp test simple, maybe just add one more test to MOVE a large chunk
> to replace the thp test, which may contain a few thps?  It also doesn't
> need to be fault based.

Sorry, I didn't get your suggestion. Could you please clarify? Which
thp test are you referring to?

Thanks,
Suren.

>
> > +     nr_pages = UFFD_TEST_MEM_SIZE / page_size;
> > +
> > +     return 0;
> > +}
> > +
> > +struct uffd_test_case_ops uffd_move_pmd_test_case_ops = {
> > +     .pre_alloc = adjust_page_size,
> > +     .post_alloc = pmd_align_areas,
> > +     .pre_release = pmd_restore_areas,
> > +};
> > +
> >  /*
> >   * Test the returned uffdio_register.ioctls with different register modes.
> >   * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test.
> > @@ -1141,6 +1268,20 @@ uffd_test_case_t uffd_tests[] = {
> >               .mem_targets = MEM_ALL,
> >               .uffd_feature_required = 0,
> >       },
> > +     {
> > +             .name = "move",
> > +             .uffd_fn = uffd_move_test,
> > +             .mem_targets = MEM_ANON,
> > +             .uffd_feature_required = UFFD_FEATURE_MOVE,
> > +             .test_case_ops = &uffd_move_test_case_ops,
> > +     },
> > +     {
> > +             .name = "move-pmd",
> > +             .uffd_fn = uffd_move_test,
> > +             .mem_targets = MEM_ANON,
> > +             .uffd_feature_required = UFFD_FEATURE_MOVE,
> > +             .test_case_ops = &uffd_move_pmd_test_case_ops,
> > +     },
> >       {
> >               .name = "wp-fork",
> >               .uffd_fn = uffd_wp_fork_test,
> > --
> > 2.42.0.820.g83a721a137-goog
> >
>
> --
> Peter Xu
>
Peter Xu Oct. 30, 2023, 8:35 p.m. UTC | #3
On Mon, Oct 30, 2023 at 01:22:02PM -0700, Suren Baghdasaryan wrote:
> > > +static int adjust_page_size(void)
> > > +{
> > > +     page_size = default_huge_page_size();
> >
> > This is hacky too, currently page_size is the real page_size backing the
> > memory.
> >
> > To make thp test simple, maybe just add one more test to MOVE a large chunk
> > to replace the thp test, which may contain a few thps?  It also doesn't
> > need to be fault based.
> 
> Sorry, I didn't get your suggestion. Could you please clarify? Which
> thp test are you referring to?

The new "move-pmd" test.

I meant maybe it makes sense to have one separate MOVE test for when one
ioctl(MOVE) covers a large range which can cover some thps.  Then that will
trigger thp paths.  Assuming the fault paths are already covered in the
generic "move" test.

Thanks,
Suren Baghdasaryan Oct. 30, 2023, 9:22 p.m. UTC | #4
On Mon, Oct 30, 2023 at 1:35 PM Peter Xu <peterx@redhat.com> wrote:
>
> On Mon, Oct 30, 2023 at 01:22:02PM -0700, Suren Baghdasaryan wrote:
> > > > +static int adjust_page_size(void)
> > > > +{
> > > > +     page_size = default_huge_page_size();
> > >
> > > This is hacky too, currently page_size is the real page_size backing the
> > > memory.
> > >
> > > To make thp test simple, maybe just add one more test to MOVE a large chunk
> > > to replace the thp test, which may contain a few thps?  It also doesn't
> > > need to be fault based.
> >
> > Sorry, I didn't get your suggestion. Could you please clarify? Which
> > thp test are you referring to?
>
> The new "move-pmd" test.
>
> I meant maybe it makes sense to have one separate MOVE test for when one
> ioctl(MOVE) covers a large range which can cover some thps.  Then that will
> trigger thp paths.  Assuming the fault paths are already covered in the
> generic "move" test.

Oh, you mean I should not share uffd_move_test() between move and
move-pmd test and have separate logic instead that does not rely on
the page_size overrides? If so then I think that's doable. Some more
code but probably cleaner.

>
> Thanks,
>
> --
> Peter Xu
>
diff mbox series

Patch

diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 69e6653ad255..98957fd788d8 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -643,6 +643,30 @@  int copy_page(int ufd, unsigned long offset, bool wp)
 	return __copy_page(ufd, offset, false, wp);
 }
 
+int move_page(int ufd, unsigned long offset)
+{
+	struct uffdio_move uffdio_move;
+
+	if (offset >= nr_pages * page_size)
+		err("unexpected offset %lu\n", offset);
+	uffdio_move.dst = (unsigned long) area_dst + offset;
+	uffdio_move.src = (unsigned long) area_src + offset;
+	uffdio_move.len = page_size;
+	uffdio_move.mode = UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES;
+	uffdio_move.move = 0;
+	if (ioctl(ufd, UFFDIO_MOVE, &uffdio_move)) {
+		/* real retval in uffdio_move.move */
+		if (uffdio_move.move != -EEXIST)
+			err("UFFDIO_MOVE error: %"PRId64,
+			    (int64_t)uffdio_move.move);
+		wake_range(ufd, uffdio_move.dst, page_size);
+	} else if (uffdio_move.move != page_size) {
+		err("UFFDIO_MOVE error: %"PRId64, (int64_t)uffdio_move.move);
+	} else
+		return 1;
+	return 0;
+}
+
 int uffd_open_dev(unsigned int flags)
 {
 	int fd, uffd;
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index 19930fd6682b..c9526b2cb6b3 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -121,6 +121,7 @@  void wp_range(int ufd, __u64 start, __u64 len, bool wp);
 void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args);
 int __copy_page(int ufd, unsigned long offset, bool retry, bool wp);
 int copy_page(int ufd, unsigned long offset, bool wp);
+int move_page(int ufd, unsigned long offset);
 void *uffd_poll_thread(void *arg);
 
 int uffd_open_dev(unsigned int flags);
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index debc423bdbf4..89e9529ce941 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -1064,6 +1064,133 @@  static void uffd_poison_test(uffd_test_args_t *targs)
 	uffd_test_pass();
 }
 
+static void uffd_move_handle_fault(
+	struct uffd_msg *msg, struct uffd_args *args)
+{
+	unsigned long offset;
+
+	if (msg->event != UFFD_EVENT_PAGEFAULT)
+		err("unexpected msg event %u", msg->event);
+
+	if (msg->arg.pagefault.flags &
+	    (UFFD_PAGEFAULT_FLAG_WP | UFFD_PAGEFAULT_FLAG_MINOR | UFFD_PAGEFAULT_FLAG_WRITE))
+		err("unexpected fault type %llu", msg->arg.pagefault.flags);
+
+	offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+	offset &= ~(page_size-1);
+
+	if (move_page(uffd, offset))
+		args->missing_faults++;
+}
+
+static void uffd_move_test(uffd_test_args_t *targs)
+{
+	unsigned long nr;
+	pthread_t uffd_mon;
+	char c;
+	unsigned long long count;
+	struct uffd_args args = { 0 };
+
+	/* Prevent source pages from being mapped more than once */
+	if (madvise(area_src, nr_pages * page_size, MADV_DONTFORK))
+		err("madvise(MADV_DONTFORK) failure");
+
+	if (uffd_register(uffd, area_dst, nr_pages * page_size,
+			  true, false, false))
+		err("register failure");
+
+	args.handle_fault = uffd_move_handle_fault;
+	if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args))
+		err("uffd_poll_thread create");
+
+	/*
+	 * Read each of the pages back using the UFFD-registered mapping. We
+	 * expect that the first time we touch a page, it will result in a missing
+	 * fault. uffd_poll_thread will resolve the fault by moving source
+	 * page to destination.
+	 */
+	for (nr = 0; nr < nr_pages; nr++) {
+		/* Check area_src content */
+		count = *area_count(area_src, nr);
+		if (count != count_verify[nr])
+			err("nr %lu source memory invalid %llu %llu\n",
+			    nr, count, count_verify[nr]);
+
+		/* Faulting into area_dst should move the page */
+		count = *area_count(area_dst, nr);
+		if (count != count_verify[nr])
+			err("nr %lu memory corruption %llu %llu\n",
+			    nr, count, count_verify[nr]);
+
+		/* Re-check area_src content which should be empty */
+		count = *area_count(area_src, nr);
+		if (count != 0)
+			err("nr %lu move failed %llu %llu\n",
+			    nr, count, count_verify[nr]);
+	}
+
+	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+		err("pipe write");
+	if (pthread_join(uffd_mon, NULL))
+		err("join() failed");
+
+	if (args.missing_faults != nr_pages || args.minor_faults != 0)
+		uffd_test_fail("stats check error");
+	else
+		uffd_test_pass();
+}
+
+static int prevent_hugepages(void)
+{
+	/* This should be done before source area is populated */
+	if (madvise(area_src, nr_pages * page_size, MADV_NOHUGEPAGE)) {
+		/* Ignore if CONFIG_TRANSPARENT_HUGEPAGE=n */
+		if (errno != EINVAL)
+			return -errno;
+	}
+	return 0;
+}
+
+struct uffd_test_case_ops uffd_move_test_case_ops = {
+	.post_alloc = prevent_hugepages,
+};
+
+#define ALIGN_UP(x, align_to) \
+	(__typeof__(x))((((unsigned long)(x)) + ((align_to)-1)) & ~((align_to)-1))
+
+static char *orig_area_src, *orig_area_dst;
+static int pmd_align_areas(void)
+{
+	orig_area_src = area_src;
+	orig_area_dst = area_dst;
+	area_src = ALIGN_UP(area_src, page_size);
+	area_dst = ALIGN_UP(area_dst, page_size);
+	nr_pages--;
+
+	return 0;
+}
+
+static void pmd_restore_areas(void)
+{
+	area_src = orig_area_src;
+	area_dst = orig_area_dst;
+	nr_pages++;
+}
+
+static int adjust_page_size(void)
+{
+	page_size = default_huge_page_size();
+	nr_pages = UFFD_TEST_MEM_SIZE / page_size;
+
+	return 0;
+}
+
+struct uffd_test_case_ops uffd_move_pmd_test_case_ops = {
+	.pre_alloc = adjust_page_size,
+	.post_alloc = pmd_align_areas,
+	.pre_release = pmd_restore_areas,
+};
+
 /*
  * Test the returned uffdio_register.ioctls with different register modes.
  * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test.
@@ -1141,6 +1268,20 @@  uffd_test_case_t uffd_tests[] = {
 		.mem_targets = MEM_ALL,
 		.uffd_feature_required = 0,
 	},
+	{
+		.name = "move",
+		.uffd_fn = uffd_move_test,
+		.mem_targets = MEM_ANON,
+		.uffd_feature_required = UFFD_FEATURE_MOVE,
+		.test_case_ops = &uffd_move_test_case_ops,
+	},
+	{
+		.name = "move-pmd",
+		.uffd_fn = uffd_move_test,
+		.mem_targets = MEM_ANON,
+		.uffd_feature_required = UFFD_FEATURE_MOVE,
+		.test_case_ops = &uffd_move_pmd_test_case_ops,
+	},
 	{
 		.name = "wp-fork",
 		.uffd_fn = uffd_wp_fork_test,