From: Wei Yang <richard.weiyang@gmail.com>
To: "David Hildenbrand (Arm)" <david@kernel.org>
Cc: Balbir Singh <balbirs@nvidia.com>,
Wei Yang <richard.weiyang@gmail.com>,
akpm@linux-foundation.org, ljs@kernel.org, riel@surriel.com,
liam@infradead.org, vbabka@kernel.org, harry@kernel.org,
jannh@google.com, sj@kernel.org, ziy@nvidia.com,
linux-mm@kvack.org, Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
stable@vger.kernel.org
Subject: Re: [PATCH] mm/page_vma_mapped: revalidate and do proper check before return device-private pmd
Date: Tue, 12 May 2026 14:35:42 +0000 [thread overview]
Message-ID: <20260512143542.izpp3gu4iqxttw3f@master> (raw)
In-Reply-To: <0aab59b8-71c5-4059-8281-5dd876946528@kernel.org>
On Tue, May 12, 2026 at 02:43:54PM +0200, David Hildenbrand (Arm) wrote:
>On 5/9/26 00:48, Balbir Singh wrote:
>> On 5/8/26 11:37, Wei Yang wrote:
>>> For pmd_trans_huge() and pmd_is_migration_entry(), we does following
>>> before return the pmd entry:
>>>
>>> * re-validate pmd entry
>>> * check PVMW_MIGRATION
>>> * check_pmd()
>>> * handle on pte level if split under us
>>>
>>> But for device-private pmd, we just return after pmd_lock(). This may
>>> lead to inproper situation.
>>>
>>
>> Could you elaborate a more on the improper situation?
>>
>>> This patch fixes commit 65edfda6f3f2 ("mm/rmap: extend rmap and migration
>>> support device-private entries") by following the same pattern as
>>> pmd_trans_huge() and pmd_is_migration_entry().
>>>
>>> Fixes: 65edfda6f3f2 ("mm/rmap: extend rmap and migration support device-private entries")
>>> Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
>>> Cc: David Hildenbrand <david@kernel.org>
>>> Cc: Balbir Singh <balbirs@nvidia.com>
>>> Cc: SeongJae Park <sj@kernel.org>
>>> Cc: Zi Yan <ziy@nvidia.com>
>>> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
>>> Cc: <stable@vger.kernel.org>
>>> ---
>>> mm/page_vma_mapped.c | 34 +++++++++++++++++++++++-----------
>>> 1 file changed, 23 insertions(+), 11 deletions(-)
>>>
>>> diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
>>> index a4d52fdb3056..5d337ea43019 100644
>>> --- a/mm/page_vma_mapped.c
>>> +++ b/mm/page_vma_mapped.c
>>> @@ -269,21 +269,33 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
>>> spin_unlock(pvmw->ptl);
>>> pvmw->ptl = NULL;
>>> } else if (!pmd_present(pmde)) {
>>> - const softleaf_t entry = softleaf_from_pmd(pmde);
>>> + softleaf_t entry = softleaf_from_pmd(pmde);
>>>
>>> if (softleaf_is_device_private(entry)) {
>>> pvmw->ptl = pmd_lock(mm, pvmw->pmd);
>>> - return true;
>>> - }
>>> -
>>> - if ((pvmw->flags & PVMW_SYNC) &&
>>> - thp_vma_suitable_order(vma, pvmw->address,
>>> - PMD_ORDER) &&
>>> - (pvmw->nr_pages >= HPAGE_PMD_NR))
>>> - sync_with_folio_pmd_zap(mm, pvmw->pmd);
>>> + entry = softleaf_from_pmd(*pvmw->pmd);
>>> +
>>> + if (softleaf_is_device_private(entry)) {
>>
>> Do we need to check softleaf_is_device_private() twice, can't we hold the pmd
>> lock and check once?
>
>I think what we try to do here is, is to only grab the lock if we verified that there is something of interest in there.
>
>I wonder if we should rewrite that whole thing to just do a pmd_same() check after grabbing the lock.
>
>Something a lot cleaner like:
>
>diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
>index a4d52fdb3056..de6a255cc847 100644
>--- a/mm/page_vma_mapped.c
>+++ b/mm/page_vma_mapped.c
>@@ -242,40 +242,28 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
> */
> pmde = pmdp_get_lockless(pvmw->pmd);
>
>- if (pmd_trans_huge(pmde) || pmd_is_migration_entry(pmde)) {
>- pvmw->ptl = pmd_lock(mm, pvmw->pmd);
>- pmde = *pvmw->pmd;
>- if (!pmd_present(pmde)) {
>- softleaf_t entry;
>-
>- if (!thp_migration_supported() ||
>- !(pvmw->flags & PVMW_MIGRATION))
>- return not_found(pvmw);
>- entry = softleaf_from_pmd(pmde);
>-
>- if (!softleaf_is_migration(entry) ||
>- !check_pmd(softleaf_to_pfn(entry), pvmw))
>- return not_found(pvmw);
>- return true;
>- }
>- if (likely(pmd_trans_huge(pmde))) {
>- if (pvmw->flags & PVMW_MIGRATION)
>- return not_found(pvmw);
>- if (!check_pmd(pmd_pfn(pmde), pvmw))
>- return not_found(pvmw);
>- return true;
>- }
>- /* THP pmd was split under us: handle on pte level */
>- spin_unlock(pvmw->ptl);
>- pvmw->ptl = NULL;
>- } else if (!pmd_present(pmde)) {
>- const softleaf_t entry = softleaf_from_pmd(pmde);
>-
>- if (softleaf_is_device_private(entry)) {
>- pvmw->ptl = pmd_lock(mm, pvmw->pmd);
>- return true;
>- }
>+ if (pmd_present(pmde)) {
>+ if (!pmd_leaf(pmde))
>+ goto pte_table;
>+ if (pvmw->flags & PVMW_MIGRATION)
>+ return not_found(pvmw);
>+ if (!check_pmd(pmd_pfn(pmde), pvmw))
>+ return not_found(pvmw);
>+ } else if (pmd_is_migration_entry(pmde)) {
>+ softleaf_t entry = softleaf_from_pmd(pmde);
>+
>+ if (!(pvmw->flags & PVMW_MIGRATION))
>+ return not_found(pvmw);
>+ if (!check_pmd(softleaf_to_pfn(entry), pvmw))
>+ return not_found(pvmw);
>+ } else if (pmd_is_device_private_entry(pmde)) {
>+ softleaf_t entry = softleaf_from_pmd(pmde);
>
>+ if (pvmw->flags & PVMW_MIGRATION)
>+ return not_found(pvmw);
>+ if (!check_pmd(softleaf_to_pfn(entry), pvmw))
>+ return not_found(pvmw);
>+ } else {
> if ((pvmw->flags & PVMW_SYNC) &&
> thp_vma_suitable_order(vma, pvmw->address,
> PMD_ORDER) &&
>@@ -285,6 +273,15 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
> step_forward(pvmw, PMD_SIZE);
> continue;
> }
>+
>+ /* Double-check under PTL that the PMD didn't change. */
>+ pvmw->ptl = pmd_lock(mm, pvmw->pmd);
>+ if (pmd_same(pmde, pmdp_get(pvmw->pmd)))
>+ return true;
>+ spin_unlock(pvmw->ptl);
>+ pvmw->ptl = NULL;
>+ goto restart;
>+pte_table:
> if (!map_pte(pvmw, &pmde, &ptl)) {
> if (!pvmw->pte)
>
>
>
>
>There is likely room to clean this up / compress it further.
I tried to compress above logic like this, hope it could look cleaner.
if (pmd_trans_huge(pmde) || pmd_is_valid_softleaf(pmde)) {
unsigned long pfn;
bool is_migration = pmd_is_migration_entry(pmde);
bool for_migration = !!(pvmw->flags & PVMW_MIGRATION);
if (is_migration != for_migration)
return not_found(pvmw);
if (pmd_trans_huge(pmde))
pfn = pmd_pfn(pmde);
else
pfn = softleaf_to_pfn(softleaf_from_pmd(pmde));
if (!check_pmd(pfn, pvmw))
return not_found(pvmw);
} else if (!pmd_present(pmde)) {
>I'll note that this now also adds proper check_pmd() checks to pmd_is_device_private_entry().
>
>The not_found(pvmw) if check_pmd() fails is rather weird ... but likely this works because
>THPs can really only be mapped through one PMD, and we always will look at the right spot ...
>
>--
>Cheers,
>
>David
--
Wei Yang
Help you, Help me
next prev parent reply other threads:[~2026-05-12 14:35 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-08 1:37 [PATCH] mm/page_vma_mapped: revalidate and do proper check before return device-private pmd Wei Yang
2026-05-08 21:51 ` Andrew Morton
2026-05-10 1:22 ` Wei Yang
2026-05-08 22:48 ` Balbir Singh
2026-05-10 1:20 ` Wei Yang
2026-05-12 12:43 ` David Hildenbrand (Arm)
2026-05-12 14:35 ` Wei Yang [this message]
2026-05-12 18:55 ` David Hildenbrand (Arm)
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=20260512143542.izpp3gu4iqxttw3f@master \
--to=richard.weiyang@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=balbirs@nvidia.com \
--cc=david@kernel.org \
--cc=harry@kernel.org \
--cc=jannh@google.com \
--cc=liam@infradead.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=riel@surriel.com \
--cc=sj@kernel.org \
--cc=stable@vger.kernel.org \
--cc=vbabka@kernel.org \
--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