Re: [PATCH v5 8/8] mm: huge_memory: enable debugfs to split huge pages to any order.

From: Zi Yan <ziy@nvidia.com>
To: Aishwarya TCV <aishwarya.tcv@arm.com>
Cc: "\"Pankaj Raghav (Samsung)\"" <kernel@pankajraghav.com>,
	linux-mm@kvack.org,
	"\"Matthew Wilcox (Oracle)\"" <willy@infradead.org>,
	"David Hildenbrand" <david@redhat.com>,
	"Yang Shi" <shy828301@gmail.com>, "Yu Zhao" <yuzhao@google.com>,
	"\"Kirill A . Shutemov\"" <kirill.shutemov@linux.intel.com>,
	"Ryan Roberts" <ryan.roberts@arm.com>,
	"\"Michal Koutný\"" <mkoutny@suse.com>,
	"Roman Gushchin" <roman.gushchin@linux.dev>,
	"\"Zach O'Keefe\"" <zokeefe@google.com>,
	"Hugh Dickins" <hughd@google.com>,
	"Luis Chamberlain" <mcgrof@kernel.org>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	"Mark Brown" <broonie@kernel.org>
Subject: Re: [PATCH v5 8/8] mm: huge_memory: enable debugfs to split huge pages to any order.
Date: Fri, 01 Mar 2024 16:10:26 -0500	[thread overview]
Message-ID: <0685EC19-CDB8-4CD3-BC39-82DE59B5D10C@nvidia.com> (raw)
In-Reply-To: <7E498B77-6CC9-4FC6-B980-D79EEC548CD0@nvidia.com>


[-- Attachment #1.1: Type: text/plain, Size: 1940 bytes --]

On 1 Mar 2024, at 15:02, Zi Yan wrote:

> On 1 Mar 2024, at 14:37, Zi Yan wrote:
>
>> On 1 Mar 2024, at 4:51, Aishwarya TCV wrote:
>>
>>> On 26/02/2024 20:55, Zi Yan wrote:
>>>> From: Zi Yan <ziy@nvidia.com>
>>>>
>>>> It is used to test split_huge_page_to_list_to_order for pagecache THPs.
>>>> Also add test cases for split_huge_page_to_list_to_order via both
>>>> debugfs.
>>>>
>>>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>>>> ---
>>>>  mm/huge_memory.c                              |  34 ++++--
>>>>  .../selftests/mm/split_huge_page_test.c       | 115 +++++++++++++++++-
>>>>  2 files changed, 131 insertions(+), 18 deletions(-)
>>>>
>>>
>>> Hi Zi,
>>>
>>> When booting the kernel against next-master(20240228)with Arm64 on
>>> Marvell Thunder X2 (TX2), the kselftest-mm test 'split_huge_page_test'
>>> is failing in our CI (with rootfs over NFS). I can send the full logs if
>>> required.
>>>
>>> A bisect (full log below) identified this patch as introducing the
>>> failure. Bisected it on the tag "next-20240228" at repo
>>> "https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git".
>>>
>>> This works fine on  Linux version 6.8.0-rc6
>>
>> Hi Aishwarya,
>>
>> Can you try the attached patch and see if it fixes the failure? I changed
>> the test to accept XFS dev as input, mount XFS on a temp folder under /tmp,
>> and skip if no XFS is mounted.
>
> Please try this updated one. It allows you to specify a XFS device path
> in SPLIT_HUGE_PAGE_TEST_XFS_PATH env variable, which is passed to
> split_huge_page_test in run_vmtests.sh. It at least allow CI/CD to run
> the test without too much change.

OK. This hopefully will be my last churn. Now split_huge_page_test accepts
a path that is backed by XFS and run_vmtest.sh creates a XFS image in /tmp,
mounts it in /tmp, and gives the path to split_huge_page_test. I tested
it locally and it works. Let me know if you have any issue. Thanks.

--
Best Regards,
Yan, Zi

[-- Attachment #1.2: selftest.patch --]
[-- Type: text/plain, Size: 5785 bytes --]

diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index fe140a9f4f9d..ffdec5dc0b03 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -412,7 +412,27 @@ CATEGORY="thp" run_test ./khugepaged -s 2
 
 CATEGORY="thp" run_test ./transhuge-stress -d 20
 
-CATEGORY="thp" run_test ./split_huge_page_test
+# Try to create XFS if not provided
+if [ -z "${SPLIT_HUGE_PAGE_TEST_XFS_PATH}" ]; then
+    if test_selected "thp"; then
+        if grep xfs /proc/filesystems &>/dev/null; then
+            XFS_IMG=$(mktemp /tmp/xfs_img_XXXXXX)
+            SPLIT_HUGE_PAGE_TEST_XFS_PATH=$(mktemp -d /tmp/xfs_dir_XXXXXX)
+            truncate -s 314572800 ${XFS_IMG}
+            mkfs.xfs -q ${XFS_IMG}
+            mount -o loop ${XFS_IMG} ${SPLIT_HUGE_PAGE_TEST_XFS_PATH}
+            MOUNTED_XFS=1
+        fi
+    fi
+fi
+
+CATEGORY="thp" run_test ./split_huge_page_test ${SPLIT_HUGE_PAGE_TEST_XFS_PATH}
+
+if [ -n "${MOUNTED_XFS}" ]; then
+    umount ${SPLIT_HUGE_PAGE_TEST_XFS_PATH}
+    rmdir ${SPLIT_HUGE_PAGE_TEST_XFS_PATH}
+    rm -f ${XFS_IMG}
+fi
 
 CATEGORY="migration" run_test ./migration
 
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index cf09fdc9ef22..0b367affaa0d 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -26,7 +26,6 @@ uint64_t pmd_pagesize;
 
 #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages"
 #define SMAP_PATH "/proc/self/smaps"
-#define THP_FS_PATH "/mnt/thp_fs"
 #define INPUT_MAX 80
 
 #define PID_FMT "%d,0x%lx,0x%lx,%d"
@@ -268,7 +267,37 @@ void split_file_backed_thp(void)
 	ksft_exit_fail_msg("Error occurred\n");
 }
 
-void create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, char **addr)
+bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template,
+		const char **thp_fs_loc)
+{
+	if (xfs_path) {
+		*thp_fs_loc = xfs_path;
+		return false;
+	}
+
+	*thp_fs_loc = mkdtemp(thp_fs_template);
+
+	if (!*thp_fs_loc)
+		ksft_exit_fail_msg("cannot create temp folder\n");
+
+	return true;
+}
+
+void cleanup_thp_fs(const char *thp_fs_loc, bool created_tmp)
+{
+	int status;
+
+	if (!created_tmp)
+		return;
+
+	status = rmdir(thp_fs_loc);
+	if (status)
+		ksft_exit_fail_msg("cannot remove tmp dir: %s\n",
+				   strerror(errno));
+}
+
+int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
+		char **addr)
 {
 	size_t i;
 	int dummy;
@@ -277,7 +306,7 @@ void create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
 
 	*fd = open(testfile, O_CREAT | O_RDWR, 0664);
 	if (*fd == -1)
-		ksft_exit_fail_msg("Failed to create a file at "THP_FS_PATH);
+		ksft_exit_fail_msg("Failed to create a file at %s\n", testfile);
 
 	for (i = 0; i < fd_size; i++) {
 		unsigned char byte = (unsigned char)i;
@@ -299,7 +328,7 @@ void create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
 
 	*fd = open(testfile, O_RDWR);
 	if (*fd == -1) {
-		ksft_perror("Failed to open a file at "THP_FS_PATH);
+		ksft_perror("Failed to open testfile\n");
 		goto err_out_unlink;
 	}
 
@@ -314,26 +343,37 @@ void create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
 		dummy += *(*addr + i);
 
 	if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) {
-		ksft_print_msg("No large pagecache folio generated, please mount a filesystem supporting large folio at "THP_FS_PATH"\n");
-		goto err_out_close;
+		ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n");
+		unlink(testfile);
+		ksft_test_result_skip("Pagecache folio split skipped\n");
+		return -2;
 	}
-	return;
+	return 0;
 err_out_close:
 	close(*fd);
 err_out_unlink:
 	unlink(testfile);
 	ksft_exit_fail_msg("Failed to create large pagecache folios\n");
+	return -1;
 }
 
-void split_thp_in_pagecache_to_order(size_t fd_size, int order)
+void split_thp_in_pagecache_to_order(size_t fd_size, int order, const char *fs_loc)
 {
 	int fd;
 	char *addr;
 	size_t i;
-	const char testfile[] = THP_FS_PATH "/test";
+	char testfile[INPUT_MAX];
 	int err = 0;
 
-	create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr);
+	err = snprintf(testfile, INPUT_MAX, "%s/test", fs_loc);
+
+	if (err < 0)
+		ksft_exit_fail_msg("cannot generate right test file name\n");
+
+	err = create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr);
+	if (err)
+		return;
+	err = 0;
 
 	write_debugfs(PID_FMT, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order);
 
@@ -351,6 +391,7 @@ void split_thp_in_pagecache_to_order(size_t fd_size, int order)
 	}
 
 out:
+	munmap(addr, fd_size);
 	close(fd);
 	unlink(testfile);
 	if (err)
@@ -362,6 +403,10 @@ int main(int argc, char **argv)
 {
 	int i;
 	size_t fd_size;
+	char *optional_xfs_path = NULL;
+	char fs_loc_template[] = "/tmp/thp_fs_XXXXXX";
+	const char *fs_loc;
+	bool created_tmp;
 
 	ksft_print_header();
 
@@ -370,6 +415,9 @@ int main(int argc, char **argv)
 		ksft_finished();
 	}
 
+	if (argc > 1)
+		optional_xfs_path = argv[1];
+
 	ksft_set_plan(3+9);
 
 	pagesize = getpagesize();
@@ -384,8 +432,11 @@ int main(int argc, char **argv)
 	split_pte_mapped_thp();
 	split_file_backed_thp();
 
+	created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template,
+			&fs_loc);
 	for (i = 8; i >= 0; i--)
-		split_thp_in_pagecache_to_order(fd_size, i);
+		split_thp_in_pagecache_to_order(fd_size, i, fs_loc);
+	cleanup_thp_fs(fs_loc, created_tmp);
 
 	ksft_finished();
 

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 854 bytes --]
