mm: huge_memory: enable debugfs to split huge pages to any order

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.

[ziy@nvidia.com: fix issue discovered with NFS]
  Link: https://lkml.kernel.org/r/262E4DAA-4A78-4328-B745-1355AE356A07@nvidia.com
Link: https://lkml.kernel.org/r/20240226205534.1603748-9-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Tested-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Koutny <mkoutny@suse.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Cc: Aishwarya TCV <aishwarya.tcv@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/huge_memory.c

@@ -3419,7 +3419,7 @@ static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma)
 }
 
 static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
-				unsigned long vaddr_end)
+				unsigned long vaddr_end, unsigned int new_order)
 {
 	int ret = 0;
 	struct task_struct *task;
@@ -3483,13 +3483,19 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 			goto next;
 
 		total++;
-		if (!can_split_folio(folio, NULL))
+		/*
+		 * For folios with private, split_huge_page_to_list_to_order()
+		 * will try to drop it before split and then check if the folio
+		 * can be split or not. So skip the check here.
+		 */
+		if (!folio_test_private(folio) &&
+		    !can_split_folio(folio, NULL))
 			goto next;
 
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio(folio))
+		if (!split_folio_to_order(folio, new_order))
 			split++;
 
 		folio_unlock(folio);
@@ -3507,7 +3513,7 @@ out:
 }
 
 static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
-				pgoff_t off_end)
+				pgoff_t off_end, unsigned int new_order)
 {
 	struct filename *file;
 	struct file *candidate;
@@ -3546,7 +3552,7 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio(folio))
+		if (!split_folio_to_order(folio, new_order))
 			split++;
 
 		folio_unlock(folio);
@@ -3571,10 +3577,14 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
 {
 	static DEFINE_MUTEX(split_debug_mutex);
 	ssize_t ret;
-	/* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */
+	/*
+	 * hold pid, start_vaddr, end_vaddr, new_order or
+	 * file_path, off_start, off_end, new_order
+	 */
 	char input_buf[MAX_INPUT_BUF_SZ];
 	int pid;
 	unsigned long vaddr_start, vaddr_end;
+	unsigned int new_order = 0;
 
 	ret = mutex_lock_interruptible(&split_debug_mutex);
 	if (ret)
@@ -3603,29 +3613,29 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
 			goto out;
 		}
 
-		ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end);
-		if (ret != 2) {
+		ret = sscanf(buf, "0x%lx,0x%lx,%d", &off_start, &off_end, &new_order);
+		if (ret != 2 && ret != 3) {
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = split_huge_pages_in_file(file_path, off_start, off_end);
+		ret = split_huge_pages_in_file(file_path, off_start, off_end, new_order);
 		if (!ret)
 			ret = input_len;
 
 		goto out;
 	}
 
-	ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
+	ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d", &pid, &vaddr_start, &vaddr_end, &new_order);
 	if (ret == 1 && pid == 1) {
 		split_huge_pages_all();
 		ret = strlen(input_buf);
 		goto out;
-	} else if (ret != 3) {
+	} else if (ret != 3 && ret != 4) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end);
+	ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order);
 	if (!ret)
 		ret = strlen(input_buf);
 out:

tools/testing/selftests/mm/run_vmtests.sh

@@ -399,7 +399,27 @@ 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
 

tools/testing/selftests/mm/split_huge_page_test.c

@@ -16,6 +16,7 @@
 #include <sys/mount.h>
 #include <malloc.h>
 #include <stdbool.h>
+#include <time.h>
 #include "vm_util.h"
 #include "../kselftest.h"
 
@@ -24,10 +25,11 @@ unsigned int pageshift;
 uint64_t pmd_pagesize;
 
 #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages"
+#define SMAP_PATH "/proc/self/smaps"
 #define INPUT_MAX 80
 
-#define PID_FMT "%d,0x%lx,0x%lx"
-#define PATH_FMT "%s,0x%lx,0x%lx"
+#define PID_FMT "%d,0x%lx,0x%lx,%d"
+#define PATH_FMT "%s,0x%lx,0x%lx,%d"
 
 #define PFN_MASK     ((1UL<<55)-1)
 #define KPF_THP      (1UL<<22)
@@ -102,7 +104,7 @@ void split_pmd_thp(void)
 
 	/* split all THPs */
 	write_debugfs(PID_FMT, getpid(), (uint64_t)one_page,
-		(uint64_t)one_page + len);
+		(uint64_t)one_page + len, 0);
 
 	for (i = 0; i < len; i++)
 		if (one_page[i] != (char)i)
@@ -177,7 +179,7 @@ void split_pte_mapped_thp(void)
 
 	/* split all remapped THPs */
 	write_debugfs(PID_FMT, getpid(), (uint64_t)pte_mapped,
-		      (uint64_t)pte_mapped + pagesize * 4);
+		      (uint64_t)pte_mapped + pagesize * 4, 0);
 
 	/* smap does not show THPs after mremap, use kpageflags instead */
 	thp_size = 0;
@@ -237,7 +239,7 @@ void split_file_backed_thp(void)
 	}
 
 	/* split the file-backed THP */
-	write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end);
+	write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end, 0);
 
 	status = unlink(testfile);
 	if (status) {
@@ -265,8 +267,149 @@ cleanup:
 	ksft_exit_fail_msg("Error occurred\n");
 }
 
+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;
+
+	srand(time(NULL));
+
+	*fd = open(testfile, O_CREAT | O_RDWR, 0664);
+	if (*fd == -1)
+		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;
+
+		write(*fd, &byte, sizeof(byte));
+	}
+	close(*fd);
+	sync();
+	*fd = open("/proc/sys/vm/drop_caches", O_WRONLY);
+	if (*fd == -1) {
+		ksft_perror("open drop_caches");
+		goto err_out_unlink;
+	}
+	if (write(*fd, "3", 1) != 1) {
+		ksft_perror("write to drop_caches");
+		goto err_out_unlink;
+	}
+	close(*fd);
+
+	*fd = open(testfile, O_RDWR);
+	if (*fd == -1) {
+		ksft_perror("Failed to open testfile\n");
+		goto err_out_unlink;
+	}
+
+	*addr = mmap(NULL, fd_size, PROT_READ|PROT_WRITE, MAP_SHARED, *fd, 0);
+	if (*addr == (char *)-1) {
+		ksft_perror("cannot mmap");
+		goto err_out_close;
+	}
+	madvise(*addr, fd_size, MADV_HUGEPAGE);
+
+	for (size_t i = 0; i < fd_size; i++)
+		dummy += *(*addr + i);
+
+	if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) {
+		ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n");
+		munmap(*addr, fd_size);
+		close(*fd);
+		unlink(testfile);
+		ksft_test_result_skip("Pagecache folio split skipped\n");
+		return -2;
+	}
+	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, const char *fs_loc)
+{
+	int fd;
+	char *addr;
+	size_t i;
+	char testfile[INPUT_MAX];
+	int err = 0;
+
+	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);
+
+	for (i = 0; i < fd_size; i++)
+		if (*(addr + i) != (char)i) {
+			ksft_print_msg("%lu byte corrupted in the file\n", i);
+			err = EXIT_FAILURE;
+			goto out;
+		}
+
+	if (!check_huge_file(addr, 0, pmd_pagesize)) {
+		ksft_print_msg("Still FilePmdMapped not split\n");
+		err = EXIT_FAILURE;
+		goto out;
+	}
+
+out:
+	munmap(addr, fd_size);
+	close(fd);
+	unlink(testfile);
+	if (err)
+		ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d failed\n", order);
+	ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d passed\n", order);
+}
+
 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();
 
 	if (geteuid() != 0) {
@@ -274,7 +417,10 @@ int main(int argc, char **argv)
 		ksft_finished();
 	}
 
-	ksft_set_plan(3);
+	if (argc > 1)
+		optional_xfs_path = argv[1];
+
+	ksft_set_plan(3+9);
 
 	pagesize = getpagesize();
 	pageshift = ffs(pagesize) - 1;
@@ -282,9 +428,19 @@ int main(int argc, char **argv)
 	if (!pmd_pagesize)
 		ksft_exit_fail_msg("Reading PMD pagesize failed\n");
 
+	fd_size = 2 * pmd_pagesize;
+
 	split_pmd_thp();
 	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, fs_loc);
+	cleanup_thp_fs(fs_loc, created_tmp);
+
 	ksft_finished();
+
+	return 0;
 }