On some architectures (like ARM64), it can support CONT-PTE/PMD size
hugetlb, which means it can support not only PMD/PUD size hugetlb
(2M and 1G), but also CONT-PTE/PMD size(64K and 32M) if a 4K page size
specified.

So when looking up a CONT-PTE size hugetlb page by follow_page(), it
will use pte_offset_map_lock() to get the pte entry lock for the CONT-PTE
size hugetlb in follow_page_pte(). However this pte entry lock is incorrect
for the CONT-PTE size hugetlb, since we should use huge_pte_lock() to
get the correct lock, which is mm->page_table_lock.

That means the pte entry of the CONT-PTE size hugetlb under current
pte lock is unstable in follow_page_pte(), we can continue to migrate
or poison the pte entry of the CONT-PTE size hugetlb, which can cause
some potential race issues, even though they are under the 'pte lock'.

For example, suppose thread A is trying to look up a CONT-PTE size
hugetlb page by move_pages() syscall under the lock, however antoher
thread B can migrate the CONT-PTE hugetlb page at the same time, which
will cause thread A to get an incorrect page, if thread A also wants to
do page migration, then data inconsistency error occurs.

Moreover we have the same issue for CONT-PMD size hugetlb in
follow_huge_pmd().

To fix above issues, rename the follow_huge_pmd() as follow_huge_pmd_pte()
to handle PMD and PTE level size hugetlb, which uses huge_pte_lock() to
get the correct pte entry lock to make the pte entry stable.

Cc: <stable@vger.kernel.org>
Suggested-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
Changes from v2:
 - Combine PMD and PTE level hugetlb handling into one function.
 - Drop unnecessary patches.
 - Update the commit message.

Mike, please fold this patch into your series. Thanks.
---
 include/linux/hugetlb.h |  8 ++++----
 mm/gup.c                | 14 +++++++++++++-
 mm/hugetlb.c            | 27 +++++++++++++--------------
 3 files changed, 30 insertions(+), 19 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 852f911..fe4944f 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -207,8 +207,8 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pd(struct vm_area_struct *vma,
 			    unsigned long address, hugepd_t hpd,
 			    int flags, int pdshift);
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-				pmd_t *pmd, int flags);
+struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address,
+				 int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
 struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
@@ -319,8 +319,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
 	return NULL;
 }
 
-static inline struct page *follow_huge_pmd(struct mm_struct *mm,
-				unsigned long address, pmd_t *pmd, int flags)
+static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma,
+				unsigned long address, int flags)
 {
 	return NULL;
 }
diff --git a/mm/gup.c b/mm/gup.c
index 66d8619e..1e74fc0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -530,6 +530,18 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
 			 (FOLL_PIN | FOLL_GET)))
 		return ERR_PTR(-EINVAL);
+
+	/*
+	 * Considering PTE level hugetlb, like continuous-PTE hugetlb on
+	 * ARM64 architecture.
+	 */
+	if (is_vm_hugetlb_page(vma)) {
+		page = follow_huge_pmd_pte(vma, address, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
+	}
+
 retry:
 	if (unlikely(pmd_bad(*pmd)))
 		return no_page_table(vma, flags);
@@ -662,7 +674,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	if (pmd_none(pmdval))
 		return no_page_table(vma, flags);
 	if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
-		page = follow_huge_pmd(mm, address, pmd, flags);
+		page = follow_huge_pmd_pte(vma, address, flags);
 		if (page)
 			return page;
 		return no_page_table(vma, flags);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d0617d6..c613d3c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7156,12 +7156,13 @@ struct page * __weak
 }
 
 struct page * __weak
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int flags)
+follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags)
 {
+	struct hstate *h = hstate_vma(vma);
+	struct mm_struct *mm = vma->vm_mm;
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	pte_t pte;
+	pte_t *ptep, pte;
 
 	/*
 	 * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via
@@ -7171,17 +7172,15 @@ struct page * __weak
 		return NULL;
 
 retry:
-	ptl = pmd_lockptr(mm, pmd);
-	spin_lock(ptl);
-	/*
-	 * make sure that the address range covered by this pmd is not
-	 * unmapped from other threads.
-	 */
-	if (!pmd_huge(*pmd))
-		goto out;
-	pte = huge_ptep_get((pte_t *)pmd);
+	ptep = huge_pte_offset(mm, address, huge_page_size(h));
+	if (!ptep)
+		return NULL;
+
+	ptl = huge_pte_lock(h, mm, ptep);
+	pte = huge_ptep_get(ptep);
 	if (pte_present(pte)) {
-		page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
+		page = pte_page(pte) +
+			((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
 		/*
 		 * try_grab_page() should always succeed here, because: a) we
 		 * hold the pmd (ptl) lock, and b) we've just checked that the
@@ -7197,7 +7196,7 @@ struct page * __weak
 	} else {
 		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);
-			__migration_entry_wait_huge((pte_t *)pmd, ptl);
+			__migration_entry_wait_huge(ptep, ptl);
 			goto retry;
 		}
 		/*
-- 
1.8.3.1

On 09/01/22 18:41, Baolin Wang wrote:
> On some architectures (like ARM64), it can support CONT-PTE/PMD size
> hugetlb, which means it can support not only PMD/PUD size hugetlb
> (2M and 1G), but also CONT-PTE/PMD size(64K and 32M) if a 4K page size
> specified.
> 
> So when looking up a CONT-PTE size hugetlb page by follow_page(), it
> will use pte_offset_map_lock() to get the pte entry lock for the CONT-PTE
> size hugetlb in follow_page_pte(). However this pte entry lock is incorrect
> for the CONT-PTE size hugetlb, since we should use huge_pte_lock() to
> get the correct lock, which is mm->page_table_lock.
> 
> That means the pte entry of the CONT-PTE size hugetlb under current
> pte lock is unstable in follow_page_pte(), we can continue to migrate
> or poison the pte entry of the CONT-PTE size hugetlb, which can cause
> some potential race issues, even though they are under the 'pte lock'.
> 
> For example, suppose thread A is trying to look up a CONT-PTE size
> hugetlb page by move_pages() syscall under the lock, however antoher
> thread B can migrate the CONT-PTE hugetlb page at the same time, which
> will cause thread A to get an incorrect page, if thread A also wants to
> do page migration, then data inconsistency error occurs.
>
> Moreover we have the same issue for CONT-PMD size hugetlb in
> follow_huge_pmd().
> 
> To fix above issues, rename the follow_huge_pmd() as follow_huge_pmd_pte()
> to handle PMD and PTE level size hugetlb, which uses huge_pte_lock() to
> get the correct pte entry lock to make the pte entry stable.
> 
> Cc: <stable@vger.kernel.org>
> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com>
> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> ---
> Changes from v2:
>  - Combine PMD and PTE level hugetlb handling into one function.
>  - Drop unnecessary patches.
>  - Update the commit message.

Baolin, were you able to at least exercise the new code paths?  Especially the
path for CONT_PTE.  Code looks fine to me.

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>

It is a little hackish, but this is only for backports.  So, I think it is OK.
We may want to point out that code cleanup and simplification is going upstream
that will address these issues in a more elegant manner.

> 
> Mike, please fold this patch into your series. Thanks.

If I understand Andrew, this can go in as a separate patch for backport to
address potential bugs.  I will provide a cleanup/simplification that will
remove this going forward.

Andrew also asked for a Fixes tag.
Support for CONT_PMD/_PTE was added with bb9dd3df8ee9 "arm64: hugetlb: refactor
find_num_contig()".  Patch series "Support for contiguous pte hugepages", v4.
However, I do not believe these code paths were executed until migration
support was added with 5480280d3f2d "arm64/mm: enable HugeTLB migration for
contiguous bit HugeTLB pages"
I would go with 5480280d3f2d.
-- 
Mike Kravetz

On 9/2/2022 5:06 AM, Mike Kravetz wrote:
> On 09/01/22 18:41, Baolin Wang wrote:
>> On some architectures (like ARM64), it can support CONT-PTE/PMD size
>> hugetlb, which means it can support not only PMD/PUD size hugetlb
>> (2M and 1G), but also CONT-PTE/PMD size(64K and 32M) if a 4K page size
>> specified.
>>
>> So when looking up a CONT-PTE size hugetlb page by follow_page(), it
>> will use pte_offset_map_lock() to get the pte entry lock for the CONT-PTE
>> size hugetlb in follow_page_pte(). However this pte entry lock is incorrect
>> for the CONT-PTE size hugetlb, since we should use huge_pte_lock() to
>> get the correct lock, which is mm->page_table_lock.
>>
>> That means the pte entry of the CONT-PTE size hugetlb under current
>> pte lock is unstable in follow_page_pte(), we can continue to migrate
>> or poison the pte entry of the CONT-PTE size hugetlb, which can cause
>> some potential race issues, even though they are under the 'pte lock'.
>>
>> For example, suppose thread A is trying to look up a CONT-PTE size
>> hugetlb page by move_pages() syscall under the lock, however antoher
>> thread B can migrate the CONT-PTE hugetlb page at the same time, which
>> will cause thread A to get an incorrect page, if thread A also wants to
>> do page migration, then data inconsistency error occurs.
>>
>> Moreover we have the same issue for CONT-PMD size hugetlb in
>> follow_huge_pmd().
>>
>> To fix above issues, rename the follow_huge_pmd() as follow_huge_pmd_pte()
>> to handle PMD and PTE level size hugetlb, which uses huge_pte_lock() to
>> get the correct pte entry lock to make the pte entry stable.
>>
>> Cc: <stable@vger.kernel.org>
>> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com>
>> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>> ---
>> Changes from v2:
>>   - Combine PMD and PTE level hugetlb handling into one function.
>>   - Drop unnecessary patches.
>>   - Update the commit message.
> 
> Baolin, were you able to at least exercise the new code paths?  Especially the
> path for CONT_PTE.  Code looks fine to me.

Yes, I've tested CONT-PTE, CONT-PMD and PMD size hugetlb with 
move_pages() syscall, all works well and the lock is expected.

> 
> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
> 
> It is a little hackish, but this is only for backports.  So, I think it is OK.
> We may want to point out that code cleanup and simplification is going upstream
> that will address these issues in a more elegant manner.
> 
>>
>> Mike, please fold this patch into your series. Thanks.
> 
> If I understand Andrew, this can go in as a separate patch for backport to
> address potential bugs.  I will provide a cleanup/simplification that will
> remove this going forward.
> 
> Andrew also asked for a Fixes tag.
> Support for CONT_PMD/_PTE was added with bb9dd3df8ee9 "arm64: hugetlb: refactor
> find_num_contig()".  Patch series "Support for contiguous pte hugepages", v4.
> However, I do not believe these code paths were executed until migration
> support was added with 5480280d3f2d "arm64/mm: enable HugeTLB migration for
> contiguous bit HugeTLB pages"
> I would go with 5480280d3f2d.

Make sense. And I saw Andrew has helped to add a Fixes tag with your 
suggestion. Thanks Mike and Andrew.

On Thu,  1 Sep 2022 18:41:31 +0800 Baolin Wang <baolin.wang@linux.alibaba.com> wrote:

> On some architectures (like ARM64), it can support CONT-PTE/PMD size
> hugetlb, which means it can support not only PMD/PUD size hugetlb
> (2M and 1G), but also CONT-PTE/PMD size(64K and 32M) if a 4K page size
> specified.
> 
> So when looking up a CONT-PTE size hugetlb page by follow_page(), it
> will use pte_offset_map_lock() to get the pte entry lock for the CONT-PTE
> size hugetlb in follow_page_pte(). However this pte entry lock is incorrect
> for the CONT-PTE size hugetlb, since we should use huge_pte_lock() to
> get the correct lock, which is mm->page_table_lock.
> 
> That means the pte entry of the CONT-PTE size hugetlb under current
> pte lock is unstable in follow_page_pte(), we can continue to migrate
> or poison the pte entry of the CONT-PTE size hugetlb, which can cause
> some potential race issues, even though they are under the 'pte lock'.
> 
> For example, suppose thread A is trying to look up a CONT-PTE size
> hugetlb page by move_pages() syscall under the lock, however antoher
> thread B can migrate the CONT-PTE hugetlb page at the same time, which
> will cause thread A to get an incorrect page, if thread A also wants to
> do page migration, then data inconsistency error occurs.
> 
> Moreover we have the same issue for CONT-PMD size hugetlb in
> follow_huge_pmd().
> 
> To fix above issues, rename the follow_huge_pmd() as follow_huge_pmd_pte()
> to handle PMD and PTE level size hugetlb, which uses huge_pte_lock() to
> get the correct pte entry lock to make the pte entry stable.
> 
> Cc: <stable@vger.kernel.org>

Are we able to think of a Fixes: for this?

> Mike, please fold this patch into your series. Thanks.

As this is cc:stable I'll be looking to get this into mainline during
this -rc cycle, so it shouldn't be part of a for-next-rc patch series.