On 3/30/26 07:39, Li Wang 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 writesize/buf-offset 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 <[email protected]>
> ---
>
> Notes:
> v3:
> - Adopt statx raw syscall to build on older glibc.
> - add buf offset alignment check as well
> v2:
> - Pass dio_align as a parameter to run_dio_using_hugetlb()
> instead of generally page_size/2 alignment check.
> - Add O_DIRECT flag back to the first open().
> - Add stx_dio_offset_align zero check.
>
> tools/testing/selftests/mm/hugetlb_dio.c | 62 +++++++++++++++++-------
> 1 file changed, 45 insertions(+), 17 deletions(-)
>
> diff --git a/tools/testing/selftests/mm/hugetlb_dio.c
> b/tools/testing/selftests/mm/hugetlb_dio.c
> index 9ac62eb4c97d..b125092fc6c1 100644
> --- a/tools/testing/selftests/mm/hugetlb_dio.c
> +++ b/tools/testing/selftests/mm/hugetlb_dio.c
> @@ -17,10 +17,41 @@
> #include <unistd.h>
> #include <string.h>
> #include <sys/mman.h>
> +#include <sys/syscall.h>
> #include "vm_util.h"
> #include "kselftest.h"
>
> -void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
> +#define HP_DIO_TMPDIR "/tmp"
> +
> +#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(HP_DIO_TMPDIR, O_TMPFILE | O_RDWR | O_DIRECT, 0664);
> + if (fd < 0)
> + ksft_exit_skip("Unable to allocate file: %s\n",
> strerror(errno));
> +
> + ret = syscall(__NR_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 +64,12 @@ 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 (start_off % dio_align != 0 || writesize % dio_align != 0) {
> + ksft_test_result_skip("DIO alignment (%u) incompatible with "
> + "buf offset %u and writesize %zu\n",
> + dio_align, start_off, writesize);
> + return;
> + }
>
> /* Get the default huge page size */
> h_pagesize = default_huge_page_size();
> @@ -40,7 +77,7 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned
> int end_off)
> ksft_exit_fail_msg("Unable to determine huge page size\n");
>
> /* Open the file to DIO */
This comment is misleading as we are not opening "the" file, but we create a
new one.
See below, maybe we should clean that up.
> - fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
> + fd = open(HP_DIO_TMPDIR, O_TMPFILE | O_RDWR | O_DIRECT, 0664);
> if (fd < 0)
> ksft_exit_fail_perror("Error opening file\n");
>
> @@ -89,37 +126,28 @@ 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();
Both could be const.
>
> 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);
Why can't we simply open the file once and pass the fd to
run_dio_using_hugetlb()?
fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
if (fd < 0)
ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno));
dio_align = get_dio_alignment(fd);
if (dio_align <= 0)
ksft_exit_skip("Unable to obtain DIO alignment: %s\n", strerror(errno));
...
run_dio_using_hugetlb(fd, 0, (pagesize * 3), dio_align);
> -
> /* 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();
> }
--
Cheers,
David
