[PATCH v2] selftests/mm: skip hugetlb_dio tests when DIO alignment is incompatible

[PATCH v2] selftests/mm: skip hugetlb_dio tests when DIO alignment is incompatible

[Li Wang]

hugetlb_dio test uses sub-page offsets (pagesize / 2) to verify that
hugepages used as DIO user buffers are correctly unpinned at completion.

However, on filesystems with a logical block size larger than half the
page size (e.g., 4K-sector block devices), these unaligned DIO writes
are rejected with -EINVAL, causing the test to fail unexpectedly.

Add get_dio_alignment() to query the filesystem's required DIO alignment
via statx(STATX_DIOALIGN) and pass it to run_dio_using_hugetlb(). Skip
individual test cases whose write length is not a multiple of the
alignment, so that aligned cases are still tested.

=== Reproduce Steps ===

  # dd if=/dev/zero of=/tmp/test.img bs=1M count=512
  # losetup --sector-size 4096 /dev/loop0 /tmp/test.img
  # mkfs.xfs /dev/loop0
  # mkdir -p /mnt/dio_test
  # mount /dev/loop0 /mnt/dio_test

  // Modify test to open /mnt/dio_test and rebuild it:
  -       fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
  +       fd = open("/mnt/dio_test", O_TMPFILE | O_RDWR | O_DIRECT, 0664);

  # getconf PAGESIZE
  4096

  # echo 100 >/proc/sys/vm/nr_hugepages

  # ./hugetlb_dio
  TAP version 13
  1..4
  # No. Free pages before allocation : 100
  # No. Free pages after munmap : 100
  ok 1 free huge pages from 0-12288
  Bail out! Error writing to file
  : Invalid argument (22)
  # Planned tests != run tests (4 != 1)
  # Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0

Signed-off-by: Li Wang <liwang@redhat.com>
---

Notes:
    v2:
    	- Pass dio_align as a parameter to run_dio_using_hugetlb()
    	  instead of generally page_size/2 alignment check.

 tools/testing/selftests/mm/hugetlb_dio.c | 56 +++++++++++++++++-------
 1 file changed, 40 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c
index 9ac62eb4c97d..638a8abe3ae2 100644
--- a/tools/testing/selftests/mm/hugetlb_dio.c
+++ b/tools/testing/selftests/mm/hugetlb_dio.c
@@ -20,7 +20,35 @@
 #include "vm_util.h"
 #include "kselftest.h"
 
-void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
+#ifndef STATX_DIOALIGN
+#define STATX_DIOALIGN		0x00002000U
+#endif
+
+unsigned int get_dio_alignment(void)
+{
+	int fd, ret;
+	struct statx stx;
+	unsigned int dio_align = 1;
+
+	fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
+	if (fd < 0)
+		ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno));
+
+	ret = statx(fd, "", AT_EMPTY_PATH, STATX_DIOALIGN, &stx);
+	if (ret < 0) {
+		ksft_perror("statx() failed");
+	} else if ((stx.stx_mask & STATX_DIOALIGN) &&
+			stx.stx_dio_offset_align) {
+		dio_align = stx.stx_dio_offset_align;
+	}
+
+	close(fd);
+
+	return dio_align;
+}
+
+void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off,
+			unsigned int dio_align)
 {
 	int fd;
 	char *buffer =  NULL;
@@ -33,6 +61,11 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
 	const int mmap_prot  = PROT_READ | PROT_WRITE;
 
 	writesize = end_off - start_off;
+	if (writesize % dio_align != 0) {
+		ksft_test_result_skip("DIO alignment (%u) incompatible with offset %zu\n",
+				dio_align, writesize);
+		return;
+	}
 
 	/* Get the default huge page size */
 	h_pagesize = default_huge_page_size();
@@ -89,37 +122,28 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
 
 int main(void)
 {
-	size_t pagesize = 0;
-	int fd;
+	size_t pagesize = psize();
+	unsigned int dio_align = get_dio_alignment();
 
 	ksft_print_header();
 
-	/* Open the file to DIO */
-	fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
-	if (fd < 0)
-		ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno));
-	close(fd);
-
 	/* Check if huge pages are free */
 	if (!get_free_hugepages())
 		ksft_exit_skip("No free hugepage, exiting\n");
 
 	ksft_set_plan(4);
 
-	/* Get base page size */
-	pagesize  = psize();
-
 	/* start and end is aligned to pagesize */
-	run_dio_using_hugetlb(0, (pagesize * 3));
+	run_dio_using_hugetlb(0, (pagesize * 3), dio_align);
 
 	/* start is aligned but end is not aligned */
-	run_dio_using_hugetlb(0, (pagesize * 3) - (pagesize / 2));
+	run_dio_using_hugetlb(0, (pagesize * 3) - (pagesize / 2), dio_align);
 
 	/* start is unaligned and end is aligned */
-	run_dio_using_hugetlb(pagesize / 2, (pagesize * 3));
+	run_dio_using_hugetlb(pagesize / 2, (pagesize * 3), dio_align);
 
 	/* both start and end are unaligned */
-	run_dio_using_hugetlb(pagesize / 2, (pagesize * 3) + (pagesize / 2));
+	run_dio_using_hugetlb(pagesize / 2, (pagesize * 3) + (pagesize / 2), dio_align);
 
 	ksft_finished();
 }
-- 
2.53.0

Re: [PATCH v2] selftests/mm: skip hugetlb_dio tests when DIO alignment is incompatible

[Andrew Morton]

On Fri, 27 Mar 2026 20:03:05 +0800 Li Wang <liwang@redhat.com> wrote:

> hugetlb_dio test uses sub-page offsets (pagesize / 2) to verify that
> hugepages used as DIO user buffers are correctly unpinned at completion.
> 
> However, on filesystems with a logical block size larger than half the
> page size (e.g., 4K-sector block devices), these unaligned DIO writes
> are rejected with -EINVAL, causing the test to fail unexpectedly.
> 
> Add get_dio_alignment() to query the filesystem's required DIO alignment
> via statx(STATX_DIOALIGN) and pass it to run_dio_using_hugetlb(). Skip
> individual test cases whose write length is not a multiple of the
> alignment, so that aligned cases are still tested.
> 
> === Reproduce Steps ===
> 
>   # dd if=/dev/zero of=/tmp/test.img bs=1M count=512
>   # losetup --sector-size 4096 /dev/loop0 /tmp/test.img
>   # mkfs.xfs /dev/loop0
>   # mkdir -p /mnt/dio_test
>   # mount /dev/loop0 /mnt/dio_test
> 
>   // Modify test to open /mnt/dio_test and rebuild it:
>   -       fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
>   +       fd = open("/mnt/dio_test", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
> 
>   # getconf PAGESIZE
>   4096
> 
>   # echo 100 >/proc/sys/vm/nr_hugepages
> 
>   # ./hugetlb_dio
>   TAP version 13
>   1..4
>   # No. Free pages before allocation : 100
>   # No. Free pages after munmap : 100
>   ok 1 free huge pages from 0-12288
>   Bail out! Error writing to file
>   : Invalid argument (22)
>   # Planned tests != run tests (4 != 1)
>   # Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
> 
> ...
>
>     v2:
>     	- Pass dio_align as a parameter to run_dio_using_hugetlb()
>     	  instead of generally page_size/2 alignment check.
> 

Whee, AI review has decided that pre glibc-2.36 is a problem (last time
it was pre-2.37).

And it's forgotten the previous fs-doesnt-support-DIO issues.  Did you
alter that?

The get_dio_alignment-before-ksft_print_header thing seems legit.

https://sashiko.dev/#/patchset/20260327120305.58653-1-liwang@redhat.com

Re: [PATCH v2] selftests/mm: skip hugetlb_dio tests when DIO alignment is incompatible

[Li Wang]

On Fri, Mar 27, 2026 at 12:13:50PM -0700, Andrew Morton wrote:
> On Fri, 27 Mar 2026 20:03:05 +0800 Li Wang <liwang@redhat.com> wrote:
> 
> > hugetlb_dio test uses sub-page offsets (pagesize / 2) to verify that
> > hugepages used as DIO user buffers are correctly unpinned at completion.
> > 
> > However, on filesystems with a logical block size larger than half the
> > page size (e.g., 4K-sector block devices), these unaligned DIO writes
> > are rejected with -EINVAL, causing the test to fail unexpectedly.
> > 
> > Add get_dio_alignment() to query the filesystem's required DIO alignment
> > via statx(STATX_DIOALIGN) and pass it to run_dio_using_hugetlb(). Skip
> > individual test cases whose write length is not a multiple of the
> > alignment, so that aligned cases are still tested.
> > 
> > === Reproduce Steps ===
> > 
> >   # dd if=/dev/zero of=/tmp/test.img bs=1M count=512
> >   # losetup --sector-size 4096 /dev/loop0 /tmp/test.img
> >   # mkfs.xfs /dev/loop0
> >   # mkdir -p /mnt/dio_test
> >   # mount /dev/loop0 /mnt/dio_test
> > 
> >   // Modify test to open /mnt/dio_test and rebuild it:
> >   -       fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
> >   +       fd = open("/mnt/dio_test", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
> > 
> >   # getconf PAGESIZE
> >   4096
> > 
> >   # echo 100 >/proc/sys/vm/nr_hugepages
> > 
> >   # ./hugetlb_dio
> >   TAP version 13
> >   1..4
> >   # No. Free pages before allocation : 100
> >   # No. Free pages after munmap : 100
> >   ok 1 free huge pages from 0-12288
> >   Bail out! Error writing to file
> >   : Invalid argument (22)
> >   # Planned tests != run tests (4 != 1)
> >   # Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
> > 
> > ...
> >
> >     v2:
> >     	- Pass dio_align as a parameter to run_dio_using_hugetlb()
> >     	  instead of generally page_size/2 alignment check.
> > 
> 
> Whee, AI review has decided that pre glibc-2.36 is a problem (last time
> it was pre-2.37).

Ok, will handle this build issue with old glibc.

> And it's forgotten the previous fs-doesnt-support-DIO issues.  Did you
> alter that?

[Sorry, forgot to mention in change logs]

Yes, I added O_DIRECT flag back to the first open(). Then it'd skip into
a failure on filesystems that doesn't support O_DIRECT.

Also, statx on FS doesn't support DIO will set stx_dio_offset_align to 0,
which may led a division by zero issue, I added a zero check.

	} else if ((stx.stx_mask & STATX_DIOALIGN) &&
			stx.stx_dio_offset_align) {


> The get_dio_alignment-before-ksft_print_header thing seems legit.

+1

And, before sending v3, I would leave this patch for more days to
see if others comment.

-- 
Regards,
Li Wang