Re: [PATCH v4 3/5] selftests/mm: reimplement is_backed_by_thp() with more precise check

[wang lian <lianux.mm@gmail.com>]

> On Aug 15, 2025, at 10:39, Zi Yan <ziy@nvidia.com> wrote:
> 
> and rename it to is_backed_by_folio().
> 
> is_backed_by_folio() checks if the given vaddr is backed a folio with
> a given order. It does so by:
> 1. getting the pfn of the vaddr;
> 2. checking kpageflags of the pfn;
> 
> if order is greater than 0:
> 3. checking kpageflags of the head pfn;
> 4. checking kpageflags of all tail pfns.
> 
> pmd_order is added to split_huge_page_test.c and replaces max_order.
> 
> Signed-off-by: Zi Yan <ziy@nvidia.com>
> ---
> .../selftests/mm/split_huge_page_test.c       | 90 ++++++++++++++-----
> tools/testing/selftests/mm/vm_util.c          | 13 +++
> tools/testing/selftests/mm/vm_util.h          |  4 +
> 3 files changed, 84 insertions(+), 23 deletions(-)
> 
> diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
> index 89d3dc08fe4c..80f718ca21c7 100644
> --- a/tools/testing/selftests/mm/split_huge_page_test.c
> +++ b/tools/testing/selftests/mm/split_huge_page_test.c
> @@ -25,6 +25,7 @@
> uint64_t pagesize;
> unsigned int pageshift;
> uint64_t pmd_pagesize;
> +unsigned int pmd_order;
> 
> #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages"
> #define SMAP_PATH "/proc/self/smaps"
> @@ -34,27 +35,71 @@ uint64_t pmd_pagesize;
> #define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d"
> #define PATH_FMT "%s,0x%lx,0x%lx,%d"
> 
> -#define PFN_MASK     ((1UL<<55)-1)
> -#define KPF_THP      (1UL<<22)
> #define GET_ORDER(nr_pages)    (31 - __builtin_clz(nr_pages))
> 
> -static int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file)
> +static int is_backed_by_folio(char *vaddr, int order, int pagemap_fd,
> +		int kpageflags_fd)
> {
> -	uint64_t paddr;
> -	uint64_t page_flags;
> +	unsigned long pfn_head;
> +	uint64_t pfn_flags;
> +	unsigned long pfn;
> +	unsigned long i;
> 
> -	if (pagemap_file) {
> -		pread(pagemap_file, &paddr, sizeof(paddr),
> -			((long)vaddr >> pageshift) * sizeof(paddr));
> +	if (pagemap_fd == -1 || kpageflags_fd == -1)
> +		goto fail;
> 
> -		if (kpageflags_file) {
> -			pread(kpageflags_file, &page_flags, sizeof(page_flags),
> -				(paddr & PFN_MASK) * sizeof(page_flags));
> +	pfn = pagemap_get_pfn(pagemap_fd, vaddr);
> 
> -			return !!(page_flags & KPF_THP);
> -		}
> +	/* non present page */
> +	if (pfn == -1UL)
> +		return 0;
> +
> +	if (get_pfn_flags(pfn, kpageflags_fd, &pfn_flags))
> +		goto fail;
> +
> +	/* check for order-0 pages */
> +	if (!order) {
> +		if (pfn_flags & (KPF_THP | KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))
> +			return 0;
> +		return 1;
> 	}
> -	return 0;
> +
> +	/* non THP folio */
> +	if (!(pfn_flags & KPF_THP))
> +		return 0;
> +
> +	pfn_head = pfn & ~((1 << order) - 1);
> +
> +	if (get_pfn_flags(pfn_head, kpageflags_fd, &pfn_flags))
> +		goto fail;
> +
> +	/* head PFN has no compound_head flag set */
> +	if (!(pfn_flags & (KPF_THP | KPF_COMPOUND_HEAD)))
> +		return 0;
> +
> +	/* check all tail PFN flags */
> +	for (i = 1; i < 1UL << order; i++) {
> +		if (get_pfn_flags(pfn_head + i, kpageflags_fd, &pfn_flags))
> +			goto fail;
> +		if (!(pfn_flags & (KPF_THP | KPF_COMPOUND_TAIL)))
> +			return 0;
> +	}
> +
> +	/*
> +	 * check the PFN after this folio, but if its flags cannot be obtained,
> +	 * assume this folio has the expected order
> +	 */
> +	if (get_pfn_flags(pfn_head + (1UL << order), kpageflags_fd, &pfn_flags))
> +		return 1;
> +
> +	/* this folio is bigger than the given order */
> +	if (pfn_flags & (KPF_THP | KPF_COMPOUND_TAIL))
> +		return 0;
> +
> +	return 1;
> +fail:
> +	ksft_exit_fail_msg("Failed to get folio info\n");
> +	return -1;
> }
> 
> static void write_file(const char *path, const char *buf, size_t buflen)
> @@ -235,7 +280,7 @@ static void split_pte_mapped_thp(void)
> 	thp_size = 0;
> 	for (i = 0; i < pagesize * 4; i++)
> 		if (i % pagesize == 0 &&
> -		    is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
> +		    is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd) == 1)
> 			thp_size++;
> 
> 	if (thp_size != 4)
> @@ -252,7 +297,7 @@ static void split_pte_mapped_thp(void)
> 			ksft_exit_fail_msg("%ld byte corrupted\n", i);
> 
> 		if (i % pagesize == 0 &&
> -		    is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
> +		    is_backed_by_folio(&pte_mapped[i], 0, pagemap_fd, kpageflags_fd) == 0)
> 			thp_size++;
> 	}
> 
> @@ -524,7 +569,6 @@ int main(int argc, char **argv)
> 	const char *fs_loc;
> 	bool created_tmp;
> 	int offset;
> -	unsigned int max_order;
> 	unsigned int nr_pages;
> 	unsigned int tests;
> 
> @@ -545,28 +589,28 @@ int main(int argc, char **argv)
> 		ksft_exit_fail_msg("Reading PMD pagesize failed\n");
> 
> 	nr_pages = pmd_pagesize / pagesize;
> -	max_order = GET_ORDER(nr_pages);
> -	tests = 2 + (max_order - 1) + (2 * max_order) + (max_order - 1) * 4 + 2;
> +	pmd_order = GET_ORDER(nr_pages);
> +	tests = 2 + (pmd_order - 1) + (2 * pmd_order) + (pmd_order - 1) * 4 + 2;
> 	ksft_set_plan(tests);
> 
> 	fd_size = 2 * pmd_pagesize;
> 
> 	split_pmd_zero_pages();
> 
> -	for (i = 0; i < max_order; i++)
> +	for (i = 0; i < pmd_order; i++)
> 		if (i != 1)
> 			split_pmd_thp_to_order(i);
> 
> 	split_pte_mapped_thp();
> -	for (i = 0; i < max_order; i++)
> +	for (i = 0; i < pmd_order; i++)
> 		split_file_backed_thp(i);
> 
> 	created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template,
> 			&fs_loc);
> -	for (i = max_order - 1; i >= 0; i--)
> +	for (i = pmd_order - 1; i >= 0; i--)
> 		split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, -1);
> 
> -	for (i = 0; i < max_order; i++)
> +	for (i = 0; i < pmd_order; i++)
> 		for (offset = 0;
> 		     offset < nr_pages;
> 		     offset += MAX(nr_pages / 4, 1 << i))
> diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
> index 6a239aa413e2..18b7cb51fc56 100644
> --- a/tools/testing/selftests/mm/vm_util.c
> +++ b/tools/testing/selftests/mm/vm_util.c
> @@ -338,6 +338,19 @@ int detect_hugetlb_page_sizes(size_t sizes[], int max)
> 	return count;
> }
> 
> +int get_pfn_flags(unsigned long pfn, int kpageflags_fd, uint64_t *flags)
> +{
> +	size_t count;
> +
> +	count = pread(kpageflags_fd, flags, sizeof(*flags),
> +		      pfn * sizeof(*flags));
> +
> +	if (count != sizeof(*flags))
> +		return -1;
> +
> +	return 0;
> +}
> +
> /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */
> int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len,
> 			      bool miss, bool wp, bool minor, uint64_t *ioctls)
> diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
> index 1843ad48d32b..03481ca0a1b4 100644
> --- a/tools/testing/selftests/mm/vm_util.h
> +++ b/tools/testing/selftests/mm/vm_util.h
> @@ -18,6 +18,9 @@
> #define PM_SWAP                       BIT_ULL(62)
> #define PM_PRESENT                    BIT_ULL(63)
> 
> +#define KPF_COMPOUND_HEAD             BIT_ULL(15)
> +#define KPF_COMPOUND_TAIL             BIT_ULL(16)
> +#define KPF_THP                       BIT_ULL(22)
> /*
>  * Ignore the checkpatch warning, we must read from x but don't want to do
>  * anything with it in order to trigger a read page fault. We therefore must use
> @@ -85,6 +88,7 @@ bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size);
> int64_t allocate_transhuge(void *ptr, int pagemap_fd);
> unsigned long default_huge_page_size(void);
> int detect_hugetlb_page_sizes(size_t sizes[], int max);
> +int get_pfn_flags(unsigned long pfn, int kpageflags_fd, uint64_t *flags);
> 
> int uffd_register(int uffd, void *addr, uint64_t len,
> 		  bool miss, bool wp, bool minor);
> -- 
> 2.50.1

LGTM.
Reviewed-by: wang lian <lianux.mm@gmail.com>

Best regards,
wang lian