From: Li Wang <liwang@redhat.com>
To: akpm@linux-foundation.org, rppt@kernel.org, david@kernel.org,
ljs@kernel.org, Liam.Howlett@oracle.com, vbabka@kernel.org,
surenb@google.com, mhocko@suse.com, shuah@kernel.org
Cc: aubaker@redhat.com, linux-mm@kvack.org,
linux-kselftest@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-fsdevel@vger.kernel.org
Subject: [PATCH v4] selftests/mm: skip hugetlb_dio tests when DIO alignment is incompatible
Date: Mon, 30 Mar 2026 20:53:07 +0800 [thread overview]
Message-ID: <20260330125307.98581-1-liwang@redhat.com> (raw)
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 skip individual test cases whose file
offset or write size is not a multiple of that alignment. Aligned cases
continue to run so the core coverage is preserved.
While here, open the temporary file once in main() and share the fd
across all test cases instead of reopening it in each invocation.
=== 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>
Suggested-by: Mike Rapoport <rppt@kernel.org>
Suggested-by: David Hildenbrand <david@kernel.org>
---
Notes:
v4:
- Open the file once and pass the fd to functions.
- Add check_dio_alignment dedicated to alignment checking.
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 | 97 ++++++++++++++++++------
1 file changed, 75 insertions(+), 22 deletions(-)
diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c
index 9ac62eb4c97d..1c673c6c685e 100644
--- a/tools/testing/selftests/mm/hugetlb_dio.c
+++ b/tools/testing/selftests/mm/hugetlb_dio.c
@@ -17,12 +17,57 @@
#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)
+#ifndef STATX_DIOALIGN
+#define STATX_DIOALIGN 0x00002000U
+#endif
+
+static int get_dio_alignment(int fd)
+{
+ struct statx stx;
+ int ret;
+
+ ret = syscall(__NR_statx, fd, "", AT_EMPTY_PATH, STATX_DIOALIGN, &stx);
+ if (ret < 0)
+ return -1;
+
+ /*
+ * If STATX_DIOALIGN is unsupported, assume no alignment
+ * constraint and let the test proceed.
+ */
+ if (!(stx.stx_mask & STATX_DIOALIGN) || !stx.stx_dio_offset_align)
+ return 1;
+
+ return stx.stx_dio_offset_align;
+}
+
+static bool check_dio_alignment(unsigned int start_off,
+ unsigned int end_off, unsigned int align)
+{
+ unsigned int writesize = end_off - start_off;
+
+ /*
+ * The kernel's DIO path checks that file offset, length, and
+ * buffer address are all multiples of dio_offset_align. When
+ * this test case's parameters don't satisfy that, the write
+ * would fail with -EINVAL before exercising the hugetlb unpin
+ * path, so skip.
+ */
+ if (start_off % align != 0 || writesize % align != 0) {
+ ksft_test_result_skip("DIO align=%u incompatible with offset %u writesize %u\n",
+ align, start_off, writesize);
+ return false;
+ }
+
+ return true;
+}
+
+static void run_dio_using_hugetlb(int fd, unsigned int start_off,
+ unsigned int end_off)
{
- int fd;
char *buffer = NULL;
char *orig_buffer = NULL;
size_t h_pagesize = 0;
@@ -39,10 +84,9 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
if (!h_pagesize)
ksft_exit_fail_msg("Unable to determine huge page size\n");
- /* Open the file to DIO */
- fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
- if (fd < 0)
- ksft_exit_fail_perror("Error opening file\n");
+ /* Reset file position since fd is shared across tests */
+ if (lseek(fd, 0, SEEK_SET) < 0)
+ ksft_exit_fail_perror("lseek failed\n");
/* Get the free huge pages before allocation */
free_hpage_b = get_free_hugepages();
@@ -71,7 +115,6 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
/* unmap the huge page */
munmap(orig_buffer, h_pagesize);
- close(fd);
/* Get the free huge pages after unmap*/
free_hpage_a = get_free_hugepages();
@@ -87,39 +130,49 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
"free huge pages from %u-%u\n", start_off, end_off);
}
+static void run_test(int fd, unsigned int start_off,
+ unsigned int end_off, unsigned int align)
+{
+ if (!check_dio_alignment(start_off, end_off, align))
+ return;
+
+ run_dio_using_hugetlb(fd, start_off, end_off);
+}
+
int main(void)
{
- size_t pagesize = 0;
- int fd;
+ int fd, align;
+ const size_t pagesize = psize();
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);
+ fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664);
+ if (fd < 0)
+ ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno));
- /* Get base page size */
- pagesize = psize();
+ align = get_dio_alignment(fd);
+ if (align < 0)
+ ksft_exit_skip("Unable to obtain DIO alignment: %s\n",
+ strerror(errno));
+ ksft_set_plan(4);
/* start and end is aligned to pagesize */
- run_dio_using_hugetlb(0, (pagesize * 3));
+ run_test(fd, 0, (pagesize * 3), align);
/* start is aligned but end is not aligned */
- run_dio_using_hugetlb(0, (pagesize * 3) - (pagesize / 2));
+ run_test(fd, 0, (pagesize * 3) - (pagesize / 2), align);
/* start is unaligned and end is aligned */
- run_dio_using_hugetlb(pagesize / 2, (pagesize * 3));
+ run_test(fd, pagesize / 2, (pagesize * 3), align);
/* both start and end are unaligned */
- run_dio_using_hugetlb(pagesize / 2, (pagesize * 3) + (pagesize / 2));
+ run_test(fd, pagesize / 2, (pagesize * 3) + (pagesize / 2), align);
+
+ close(fd);
ksft_finished();
}
--
2.53.0
reply other threads:[~2026-03-30 12:53 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260330125307.98581-1-liwang@redhat.com \
--to=liwang@redhat.com \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=aubaker@redhat.com \
--cc=david@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mhocko@suse.com \
--cc=rppt@kernel.org \
--cc=shuah@kernel.org \
--cc=surenb@google.com \
--cc=vbabka@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox