mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Lorenzo Stoakes (ARM)" <ljs@kernel.org>
To: Yeoreum Yun <yeoreum.yun@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	 David Hildenbrand <david@kernel.org>, Zi Yan <ziy@nvidia.com>,
	 Baolin Wang <baolin.wang@linux.alibaba.com>,
	"Liam R. Howlett" <liam@infradead.org>,
	 Nico Pache <nico.pache@linux.dev>,
	Ryan Roberts <ryan.roberts@arm.com>, Dev Jain <dev.jain@arm.com>,
	 Barry Song <baohua@kernel.org>,
	Lance Yang <lance.yang@linux.dev>,
	 Usama Arif <usama.arif@linux.dev>,
	Vlastimil Babka <vbabka@kernel.org>,
	 Mike Rapoport <rppt@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	 Michal Hocko <mhocko@suse.com>, Shuah Khan <shuah@kernel.org>,
	 Kevin Brodsky <kevin.brodsky@arm.com>,
	linux-mm@kvack.org, linux-kselftest@vger.kernel.org,
	 linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 2/2] kselftest: mm: replace usage of /proc/self/smaps for check_huge_xxx() helper
Date: Fri, 28 Aug 2026 10:30:20 +0100	[thread overview]
Message-ID: <apFMvo8pCzaGKope@gremlin> (raw)
In-Reply-To: <20260828-fix_split-v3-2-374022586a4b@arm.com>

On Fri, Aug 28, 2026 at 09:11:34AM +0100, Yeoreum Yun wrote:
> Since glibc commit 321e1fc73f (“malloc: Enable 2MB THP by default on AArch64”),
> glibc may call madvise(MADV_HUGEPAGE) for sufficiently large allocations
> made by memalign().
>
> The underlying VMA may start at a different address from the aligned
> address returned by memalign(). Furthermore, a subsequent
> madvise(MADV_HUGEPAGE) call does not split the VMA because the flag is
> already set.
>
> This causes split_huge_page_test to fail because the check_huge_xxx()
> helpers incorrectly require the address returned by memalign() to
> match the VMA start address reported in /proc/self/smaps.

Hmm, is the test correctly putting sentinels either side of the VMA? Any test
that doesn't risks flaking due to unwanted VMA merges.

>
> Fix this by using /proc/self/pagemap and /proc/kpageflags instead of
> /proc/self/smaps to detect huge pages.

You should probably call out the fact you're doing some refactoring here
also!

>
> Reported-by: David Hildenbrand (Arm) <david@kernel.org>

Should always have a Closes: tag if Reported-by: ideally.

> Suggested-by: Zi Yan <ziy@nvidia.com>
> Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>

Generally looks reasonable to me, some nits above and below though :)

Acked-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>

> ---
>  tools/testing/selftests/mm/vm_util.c | 145 ++++++++++++++++++++++-------------
>  tools/testing/selftests/mm/vm_util.h |   1 +
>  2 files changed, 92 insertions(+), 54 deletions(-)
>
> diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
> index 4821a3563036..083b72d92b14 100644
> --- a/tools/testing/selftests/mm/vm_util.c
> +++ b/tools/testing/selftests/mm/vm_util.c
> @@ -351,31 +351,13 @@ char *__get_smap_entry(void *addr, const char *pattern, char *buf, size_t len)
>  	return entry;
>  }
>
> -static bool __check_pmd_huge(void *addr, char *pattern, int nr_hpages,
> -		  uint64_t hpage_size)
> -{
> -	char buffer[MAX_LINE_LENGTH];
> -	uint64_t thp = -1;
> -	char *entry;
> -
> -	entry = __get_smap_entry(addr, pattern, buffer, sizeof(buffer));
> -	if (!entry)
> -		goto err_out;
> -
> -	if (sscanf(entry, "%9" SCNu64 " kB", &thp) != 1)
> -		ksft_exit_fail_msg("Reading smap error\n");
> -
> -err_out:
> -	return thp == (nr_hpages * (hpage_size >> 10));
> -}
> -
> -static bool check_large_folios(void *addr, size_t len, int nr_hpages,
> -		uint64_t hpage_size)
> +static bool check_large_folios(int pagemap_fd, int kpageflags_fd,
> +			       void *addr, size_t len, int nr_hpages,
> +			       uint64_t hpage_size)
>  {
>  	int order = 0, pagesize = getpagesize();
>  	unsigned int nr_pages = hpage_size / pagesize;
>  	int orders[MAX_NR_ORDERS], status;
> -	int pagemap_fd, kpageflags_fd;
>  	bool ret = false;
>
>  	if (!nr_pages)
> @@ -386,15 +368,6 @@ static bool check_large_folios(void *addr, size_t len, int nr_hpages,
>  		ksft_exit_fail_msg("invalid order\n");
>
>  	memset(orders, 0, sizeof(int) * MAX_NR_ORDERS);
> -	pagemap_fd = open(PAGEMAP_PATH, O_RDONLY);
> -	if (pagemap_fd == -1)
> -		ksft_exit_fail_msg("read pagemap fail\n");
> -
> -	kpageflags_fd = open(KPAGEFLAGS_PATH, O_RDONLY);
> -	if (kpageflags_fd == -1) {
> -		close(pagemap_fd);
> -		ksft_exit_fail_msg("read kpageflags fail\n");
> -	}
>
>  	status = gather_folio_orders(addr, len, pagemap_fd,
>  			kpageflags_fd, orders, MAX_NR_ORDERS);
> @@ -405,48 +378,112 @@ static bool check_large_folios(void *addr, size_t len, int nr_hpages,
>  		ret = true;
>
>  out:
> -	close(pagemap_fd);
> -	close(kpageflags_fd);
>  	return ret;
>  }
>
> -bool check_huge_anon(void *addr, size_t len, int nr_hpages, uint64_t hpage_size)
> -{
> -	uint64_t pmd_pagesize = read_pmd_pagesize();
> -
> -	if (!pmd_pagesize)
> -		ksft_exit_fail_msg("reading PMD pagesize failed\n");
> +enum check_huge_type {
> +	CHECK_HUGE_ANON,
> +	CHECK_HUGE_FILE,
> +	CHECK_HUGE_SHMEM,
> +};
>
> -	if (hpage_size == pmd_pagesize)
> -		return __check_pmd_huge(addr, "AnonHugePages: ", nr_hpages, hpage_size);
> +static bool check_huge_type(uint64_t categories, uint64_t kpageflags,
> +			    enum check_huge_type type)
> +{
> +	bool file = categories & PAGE_IS_FILE;
> +	bool swapbacked = kpageflags & KPF_SWAPBACKED;

NIT: nice to const these :)

> +
> +	switch (type) {
> +	case CHECK_HUGE_ANON:
> +		return !file;
> +	case CHECK_HUGE_FILE:
> +		return file && !swapbacked;
> +	case CHECK_HUGE_SHMEM:
> +		return file & swapbacked;
> +	}
>
> -	return check_large_folios(addr, len, nr_hpages, hpage_size);
> +	return false;
>  }
>
> -bool check_huge_file(void *addr, size_t len, int nr_hpages, uint64_t hpage_size)
> +static bool __check_huge(void *addr, size_t len, int nr_hpages,
> +			 uint64_t hpage_size, enum check_huge_type type)
>  {
> -	uint64_t pmd_pagesize = read_pmd_pagesize();
> +	bool ret = false;
> +	int pagemap_fd, kpageflags_fd;
> +	int nr_pmd_mappings = 0;
> +	uint64_t pmd_pagesize, scan_mapping_size;
> +	uint64_t categories, kpf;
> +	unsigned long pfn;
> +	bool check_pmd_mapping, allow_nonpresent;
> +	char *start = addr;
> +	char *end = start + len;
>
> +	pmd_pagesize = read_pmd_pagesize();
>  	if (!pmd_pagesize)
>  		ksft_exit_fail_msg("reading PMD pagesize failed\n");
>
> -	if (hpage_size == pmd_pagesize)
> -		return __check_pmd_huge(addr, "FilePmdMapped:", nr_hpages, hpage_size);
> +	check_pmd_mapping = (hpage_size == pmd_pagesize);
> +	scan_mapping_size = (nr_hpages > 0) ? hpage_size : psize();
> +	/* Some mTHP tests check a partially populated PMD-sized range. */
> +	allow_nonpresent = (uint64_t)nr_hpages * hpage_size < len;
>
> -	return check_large_folios(addr, len, nr_hpages, hpage_size);
> +	pagemap_fd = open(PAGEMAP_PATH, O_RDONLY);
> +	if (pagemap_fd < 0)
> +		ksft_exit_fail_msg("open pagemap fail\n");
> +
> +	kpageflags_fd = open(KPAGEFLAGS_PATH, O_RDONLY);
> +	if (kpageflags_fd < 0) {
> +		close(pagemap_fd);
> +		ksft_exit_fail_msg("open kpageflags fail\n");
> +	}
> +
> +	if (!check_pmd_mapping &&
> +	    !check_large_folios(pagemap_fd, kpageflags_fd,
> +				addr, len, nr_hpages, hpage_size))
> +		goto out;
> +
> +	for (; start < end; start += scan_mapping_size) {
> +		categories = pagemap_scan_get_categories(pagemap_fd, start);
> +		pfn = pagemap_get_pfn(pagemap_fd, start);
> +		if (pfn == -1UL) {
> +			if (!allow_nonpresent)
> +				goto out;
> +			else
> +				continue;
> +		}
> +		if (pageflags_get(pfn, kpageflags_fd, &kpf))
> +			ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno));
> +		if (check_pmd_mapping && (categories & PAGE_IS_HUGE))
> +			nr_pmd_mappings++;
> +		if (kpf & KPF_COMPOUND_TAIL)
> +			continue;
> +		if (!check_huge_type(categories, kpf, type))
> +			goto out;
> +	}
> +
> +	if (check_pmd_mapping && (nr_pmd_mappings != nr_hpages))
> +		goto out;
> +	ret = true;
> +
> +out:
> +	close(pagemap_fd);
> +	close(kpageflags_fd);
> +	return ret;
>  }
>
> -bool check_huge_shmem(void *addr, size_t len, int nr_hpages, uint64_t hpage_size)
> +bool check_huge_anon(void *addr, size_t len, int nr_hpages, uint64_t hpage_size)
>  {
> -	uint64_t pmd_pagesize = read_pmd_pagesize();
> -
> -	if (!pmd_pagesize)
> -		ksft_exit_fail_msg("reading PMD pagesize failed\n");
> +	return __check_huge(addr, len, nr_hpages, hpage_size, CHECK_HUGE_ANON);
> +}
>
> -	if (hpage_size == pmd_pagesize)
> -		return __check_pmd_huge(addr, "ShmemPmdMapped:", nr_hpages, hpage_size);
> +bool check_huge_file(void *addr, size_t len, int nr_hpages, uint64_t hpage_size)
> +{
> +	return __check_huge(addr, len, nr_hpages, hpage_size, CHECK_HUGE_FILE);
> +}
>
> -	return check_large_folios(addr, len, nr_hpages, hpage_size);
> +bool check_huge_shmem(void *addr, size_t len, int nr_hpages, uint64_t hpage_size)
> +{
> +	return __check_huge(addr, len, nr_hpages, hpage_size, CHECK_HUGE_SHMEM);
>  }
>
>  int64_t allocate_transhuge(void *ptr, int pagemap_fd)
> diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
> index 9a49af88702e..f19bd17817e5 100644
> --- a/tools/testing/selftests/mm/vm_util.h
> +++ b/tools/testing/selftests/mm/vm_util.h
> @@ -18,6 +18,7 @@
>  #define PM_SWAP                       BIT_ULL(62)
>  #define PM_PRESENT                    BIT_ULL(63)
>
> +#define KPF_SWAPBACKED                BIT_ULL(14)
>  #define KPF_COMPOUND_HEAD             BIT_ULL(15)
>  #define KPF_COMPOUND_TAIL             BIT_ULL(16)
>  #define KPF_HWPOISON                  BIT_ULL(19)
>
> --
> 2.43.0
>

--
Cheers, Lorenzo

  reply	other threads:[~2026-08-28  9:30 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-28  8:11 [PATCH v3 0/2] kselftest: mm: fix some failure of split_huge_page_test Yeoreum Yun
2026-08-28  8:11 ` [PATCH v3 1/2] kselftest: mm: prevent random failure of huge page split for khugepaged Yeoreum Yun
2026-08-28  9:39   ` Lorenzo Stoakes (ARM)
2026-08-28 10:04     ` Yeoreum Yun
2026-08-28  8:11 ` [PATCH v3 2/2] kselftest: mm: replace usage of /proc/self/smaps for check_huge_xxx() helper Yeoreum Yun
2026-08-28  9:30   ` Lorenzo Stoakes (ARM) [this message]
2026-08-28 10:17     ` Yeoreum Yun
2026-08-28 10:31       ` Lorenzo Stoakes (ARM)
2026-08-28 14:35         ` Yeoreum Yun
2026-08-28 17:21           ` Lorenzo Stoakes (ARM)
2026-08-28 15:13   ` Zi Yan
2026-08-28 15:22     ` Yeoreum Yun

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=apFMvo8pCzaGKope@gremlin \
    --to=ljs@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=david@kernel.org \
    --cc=dev.jain@arm.com \
    --cc=kevin.brodsky@arm.com \
    --cc=lance.yang@linux.dev \
    --cc=liam@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=nico.pache@linux.dev \
    --cc=rppt@kernel.org \
    --cc=ryan.roberts@arm.com \
    --cc=shuah@kernel.org \
    --cc=surenb@google.com \
    --cc=usama.arif@linux.dev \
    --cc=vbabka@kernel.org \
    --cc=yeoreum.yun@arm.com \
    --cc=ziy@nvidia.com \
    /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

all inboxes | Powered by JetHome®