hugetlb and vmalloc fixes and perf improvements

[PATCH v1 05/16] mm/page_table_check: Batch-check pmds/puds just like ptes

Posted by Ryan Roberts 10 months, 1 week ago

Convert page_table_check_p[mu]d_set(...) to
page_table_check_p[mu]ds_set(..., nr) to allow checking a contiguous set
of pmds/puds in single batch. We retain page_table_check_p[mu]d_set(...)
as macros that call new batch functions with nr=1 for compatibility.

arm64 is about to reorganise its pte/pmd/pud helpers to reuse more code
and to allow the implementation for huge_pte to more efficiently set
ptes/pmds/puds in batches. We need these batch-helpers to make the
refactoring possible.

Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
 include/linux/page_table_check.h | 30 +++++++++++++++++-----------
 mm/page_table_check.c            | 34 +++++++++++++++++++-------------
 2 files changed, 38 insertions(+), 26 deletions(-)

diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h
index 6722941c7cb8..289620d4aad3 100644
--- a/include/linux/page_table_check.h
+++ b/include/linux/page_table_check.h
@@ -19,8 +19,10 @@ void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd);
 void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud);
 void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte,
 		unsigned int nr);
-void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd);
-void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud);
+void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
+		unsigned int nr);
+void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud,
+		unsigned int nr);
 void __page_table_check_pte_clear_range(struct mm_struct *mm,
 					unsigned long addr,
 					pmd_t pmd);
@@ -74,22 +76,22 @@ static inline void page_table_check_ptes_set(struct mm_struct *mm,
 	__page_table_check_ptes_set(mm, ptep, pte, nr);
 }
 
-static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp,
-					    pmd_t pmd)
+static inline void page_table_check_pmds_set(struct mm_struct *mm,
+		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pmd_set(mm, pmdp, pmd);
+	__page_table_check_pmds_set(mm, pmdp, pmd, nr);
 }
 
-static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp,
-					    pud_t pud)
+static inline void page_table_check_puds_set(struct mm_struct *mm,
+		pud_t *pudp, pud_t pud, unsigned int nr)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pud_set(mm, pudp, pud);
+	__page_table_check_puds_set(mm, pudp, pud, nr);
 }
 
 static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
@@ -129,13 +131,13 @@ static inline void page_table_check_ptes_set(struct mm_struct *mm,
 {
 }
 
-static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp,
-					    pmd_t pmd)
+static inline void page_table_check_pmds_set(struct mm_struct *mm,
+		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
 {
 }
 
-static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp,
-					    pud_t pud)
+static inline void page_table_check_puds_set(struct mm_struct *mm,
+		pud_t *pudp, pud_t pud, unsigned int nr)
 {
 }
 
@@ -146,4 +148,8 @@ static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
 }
 
 #endif /* CONFIG_PAGE_TABLE_CHECK */
+
+#define page_table_check_pmd_set(mm, pmdp, pmd)	page_table_check_pmds_set(mm, pmdp, pmd, 1)
+#define page_table_check_pud_set(mm, pudp, pud)	page_table_check_puds_set(mm, pudp, pud, 1)
+
 #endif /* __LINUX_PAGE_TABLE_CHECK_H */
diff --git a/mm/page_table_check.c b/mm/page_table_check.c
index 509c6ef8de40..dae4a7d776b3 100644
--- a/mm/page_table_check.c
+++ b/mm/page_table_check.c
@@ -234,33 +234,39 @@ static inline void page_table_check_pmd_flags(pmd_t pmd)
 		WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd)));
 }
 
-void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd)
+void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
+		unsigned int nr)
 {
+	unsigned int i;
+	unsigned long stride = PMD_SIZE >> PAGE_SHIFT;
+
 	if (&init_mm == mm)
 		return;
 
 	page_table_check_pmd_flags(pmd);
 
-	__page_table_check_pmd_clear(mm, *pmdp);
-	if (pmd_user_accessible_page(pmd)) {
-		page_table_check_set(pmd_pfn(pmd), PMD_SIZE >> PAGE_SHIFT,
-				     pmd_write(pmd));
-	}
+	for (i = 0; i < nr; i++)
+		__page_table_check_pmd_clear(mm, *(pmdp + i));
+	if (pmd_user_accessible_page(pmd))
+		page_table_check_set(pmd_pfn(pmd), stride * nr, pmd_write(pmd));
 }
-EXPORT_SYMBOL(__page_table_check_pmd_set);
+EXPORT_SYMBOL(__page_table_check_pmds_set);
 
-void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud)
+void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud,
+		unsigned int nr)
 {
+	unsigned int i;
+	unsigned long stride = PUD_SIZE >> PAGE_SHIFT;
+
 	if (&init_mm == mm)
 		return;
 
-	__page_table_check_pud_clear(mm, *pudp);
-	if (pud_user_accessible_page(pud)) {
-		page_table_check_set(pud_pfn(pud), PUD_SIZE >> PAGE_SHIFT,
-				     pud_write(pud));
-	}
+	for (i = 0; i < nr; i++)
+		__page_table_check_pud_clear(mm, *(pudp + i));
+	if (pud_user_accessible_page(pud))
+		page_table_check_set(pud_pfn(pud), stride * nr, pud_write(pud));
 }
-EXPORT_SYMBOL(__page_table_check_pud_set);
+EXPORT_SYMBOL(__page_table_check_puds_set);
 
 void __page_table_check_pte_clear_range(struct mm_struct *mm,
 					unsigned long addr,
-- 
2.43.0

Re: [PATCH v1 05/16] mm/page_table_check: Batch-check pmds/puds just like ptes

Posted by Anshuman Khandual 10 months, 1 week ago

On 2/5/25 20:39, Ryan Roberts wrote:
> Convert page_table_check_p[mu]d_set(...) to
> page_table_check_p[mu]ds_set(..., nr) to allow checking a contiguous set
> of pmds/puds in single batch. We retain page_table_check_p[mu]d_set(...)
> as macros that call new batch functions with nr=1 for compatibility.
> 
> arm64 is about to reorganise its pte/pmd/pud helpers to reuse more code
> and to allow the implementation for huge_pte to more efficiently set
> ptes/pmds/puds in batches. We need these batch-helpers to make the
> refactoring possible.

A very small nit.

Although this justification here is reasonable enough but not sure if
platform specific requirements, need to be spelled out in such detail
for a generic MM change.

> 
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---

Regardless, LGTM.

Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>

>  include/linux/page_table_check.h | 30 +++++++++++++++++-----------
>  mm/page_table_check.c            | 34 +++++++++++++++++++-------------
>  2 files changed, 38 insertions(+), 26 deletions(-)
> 
> diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h
> index 6722941c7cb8..289620d4aad3 100644
> --- a/include/linux/page_table_check.h
> +++ b/include/linux/page_table_check.h
> @@ -19,8 +19,10 @@ void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd);
>  void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud);
>  void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte,
>  		unsigned int nr);
> -void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd);
> -void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud);
> +void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
> +		unsigned int nr);
> +void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud,
> +		unsigned int nr);
>  void __page_table_check_pte_clear_range(struct mm_struct *mm,
>  					unsigned long addr,
>  					pmd_t pmd);
> @@ -74,22 +76,22 @@ static inline void page_table_check_ptes_set(struct mm_struct *mm,
>  	__page_table_check_ptes_set(mm, ptep, pte, nr);
>  }
>  
> -static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp,
> -					    pmd_t pmd)
> +static inline void page_table_check_pmds_set(struct mm_struct *mm,
> +		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
>  {
>  	if (static_branch_likely(&page_table_check_disabled))
>  		return;
>  
> -	__page_table_check_pmd_set(mm, pmdp, pmd);
> +	__page_table_check_pmds_set(mm, pmdp, pmd, nr);
>  }
>  
> -static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp,
> -					    pud_t pud)
> +static inline void page_table_check_puds_set(struct mm_struct *mm,
> +		pud_t *pudp, pud_t pud, unsigned int nr)
>  {
>  	if (static_branch_likely(&page_table_check_disabled))
>  		return;
>  
> -	__page_table_check_pud_set(mm, pudp, pud);
> +	__page_table_check_puds_set(mm, pudp, pud, nr);
>  }
>  
>  static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
> @@ -129,13 +131,13 @@ static inline void page_table_check_ptes_set(struct mm_struct *mm,
>  {
>  }
>  
> -static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp,
> -					    pmd_t pmd)
> +static inline void page_table_check_pmds_set(struct mm_struct *mm,
> +		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
>  {
>  }
>  
> -static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp,
> -					    pud_t pud)
> +static inline void page_table_check_puds_set(struct mm_struct *mm,
> +		pud_t *pudp, pud_t pud, unsigned int nr)
>  {
>  }
>  
> @@ -146,4 +148,8 @@ static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
>  }
>  
>  #endif /* CONFIG_PAGE_TABLE_CHECK */
> +
> +#define page_table_check_pmd_set(mm, pmdp, pmd)	page_table_check_pmds_set(mm, pmdp, pmd, 1)
> +#define page_table_check_pud_set(mm, pudp, pud)	page_table_check_puds_set(mm, pudp, pud, 1)
> +
>  #endif /* __LINUX_PAGE_TABLE_CHECK_H */
> diff --git a/mm/page_table_check.c b/mm/page_table_check.c
> index 509c6ef8de40..dae4a7d776b3 100644
> --- a/mm/page_table_check.c
> +++ b/mm/page_table_check.c
> @@ -234,33 +234,39 @@ static inline void page_table_check_pmd_flags(pmd_t pmd)
>  		WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd)));
>  }
>  
> -void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd)
> +void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
> +		unsigned int nr)
>  {
> +	unsigned int i;
> +	unsigned long stride = PMD_SIZE >> PAGE_SHIFT;
> +
>  	if (&init_mm == mm)
>  		return;
>  
>  	page_table_check_pmd_flags(pmd);
>  
> -	__page_table_check_pmd_clear(mm, *pmdp);
> -	if (pmd_user_accessible_page(pmd)) {
> -		page_table_check_set(pmd_pfn(pmd), PMD_SIZE >> PAGE_SHIFT,
> -				     pmd_write(pmd));
> -	}
> +	for (i = 0; i < nr; i++)
> +		__page_table_check_pmd_clear(mm, *(pmdp + i));
> +	if (pmd_user_accessible_page(pmd))
> +		page_table_check_set(pmd_pfn(pmd), stride * nr, pmd_write(pmd));
>  }
> -EXPORT_SYMBOL(__page_table_check_pmd_set);
> +EXPORT_SYMBOL(__page_table_check_pmds_set);
>  
> -void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud)
> +void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud,
> +		unsigned int nr)
>  {
> +	unsigned int i;
> +	unsigned long stride = PUD_SIZE >> PAGE_SHIFT;
> +
>  	if (&init_mm == mm)
>  		return;
>  
> -	__page_table_check_pud_clear(mm, *pudp);
> -	if (pud_user_accessible_page(pud)) {
> -		page_table_check_set(pud_pfn(pud), PUD_SIZE >> PAGE_SHIFT,
> -				     pud_write(pud));
> -	}
> +	for (i = 0; i < nr; i++)
> +		__page_table_check_pud_clear(mm, *(pudp + i));
> +	if (pud_user_accessible_page(pud))
> +		page_table_check_set(pud_pfn(pud), stride * nr, pud_write(pud));
>  }
> -EXPORT_SYMBOL(__page_table_check_pud_set);
> +EXPORT_SYMBOL(__page_table_check_puds_set);
>  
>  void __page_table_check_pte_clear_range(struct mm_struct *mm,
>  					unsigned long addr,

Re: [PATCH v1 05/16] mm/page_table_check: Batch-check pmds/puds just like ptes

Posted by Ryan Roberts 10 months, 1 week ago

On 06/02/2025 10:55, Anshuman Khandual wrote:
> On 2/5/25 20:39, Ryan Roberts wrote:
>> Convert page_table_check_p[mu]d_set(...) to
>> page_table_check_p[mu]ds_set(..., nr) to allow checking a contiguous set
>> of pmds/puds in single batch. We retain page_table_check_p[mu]d_set(...)
>> as macros that call new batch functions with nr=1 for compatibility.
>>
>> arm64 is about to reorganise its pte/pmd/pud helpers to reuse more code
>> and to allow the implementation for huge_pte to more efficiently set
>> ptes/pmds/puds in batches. We need these batch-helpers to make the
>> refactoring possible.
> 
> A very small nit.
> 
> Although this justification here is reasonable enough but not sure if
> platform specific requirements, need to be spelled out in such detail
> for a generic MM change.

Personally I find the "why" to be the most useful part of a commit log. I'd
prefer to leave it in unless any mm people complain.


> 
>>
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> ---
> 
> Regardless, LGTM.
> 
> Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>

Thanks!

> 
>>  include/linux/page_table_check.h | 30 +++++++++++++++++-----------
>>  mm/page_table_check.c            | 34 +++++++++++++++++++-------------
>>  2 files changed, 38 insertions(+), 26 deletions(-)
>>
>> diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h
>> index 6722941c7cb8..289620d4aad3 100644
>> --- a/include/linux/page_table_check.h
>> +++ b/include/linux/page_table_check.h
>> @@ -19,8 +19,10 @@ void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd);
>>  void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud);
>>  void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte,
>>  		unsigned int nr);
>> -void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd);
>> -void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud);
>> +void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
>> +		unsigned int nr);
>> +void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud,
>> +		unsigned int nr);
>>  void __page_table_check_pte_clear_range(struct mm_struct *mm,
>>  					unsigned long addr,
>>  					pmd_t pmd);
>> @@ -74,22 +76,22 @@ static inline void page_table_check_ptes_set(struct mm_struct *mm,
>>  	__page_table_check_ptes_set(mm, ptep, pte, nr);
>>  }
>>  
>> -static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp,
>> -					    pmd_t pmd)
>> +static inline void page_table_check_pmds_set(struct mm_struct *mm,
>> +		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
>>  {
>>  	if (static_branch_likely(&page_table_check_disabled))
>>  		return;
>>  
>> -	__page_table_check_pmd_set(mm, pmdp, pmd);
>> +	__page_table_check_pmds_set(mm, pmdp, pmd, nr);
>>  }
>>  
>> -static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp,
>> -					    pud_t pud)
>> +static inline void page_table_check_puds_set(struct mm_struct *mm,
>> +		pud_t *pudp, pud_t pud, unsigned int nr)
>>  {
>>  	if (static_branch_likely(&page_table_check_disabled))
>>  		return;
>>  
>> -	__page_table_check_pud_set(mm, pudp, pud);
>> +	__page_table_check_puds_set(mm, pudp, pud, nr);
>>  }
>>  
>>  static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
>> @@ -129,13 +131,13 @@ static inline void page_table_check_ptes_set(struct mm_struct *mm,
>>  {
>>  }
>>  
>> -static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp,
>> -					    pmd_t pmd)
>> +static inline void page_table_check_pmds_set(struct mm_struct *mm,
>> +		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
>>  {
>>  }
>>  
>> -static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp,
>> -					    pud_t pud)
>> +static inline void page_table_check_puds_set(struct mm_struct *mm,
>> +		pud_t *pudp, pud_t pud, unsigned int nr)
>>  {
>>  }
>>  
>> @@ -146,4 +148,8 @@ static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
>>  }
>>  
>>  #endif /* CONFIG_PAGE_TABLE_CHECK */
>> +
>> +#define page_table_check_pmd_set(mm, pmdp, pmd)	page_table_check_pmds_set(mm, pmdp, pmd, 1)
>> +#define page_table_check_pud_set(mm, pudp, pud)	page_table_check_puds_set(mm, pudp, pud, 1)
>> +
>>  #endif /* __LINUX_PAGE_TABLE_CHECK_H */
>> diff --git a/mm/page_table_check.c b/mm/page_table_check.c
>> index 509c6ef8de40..dae4a7d776b3 100644
>> --- a/mm/page_table_check.c
>> +++ b/mm/page_table_check.c
>> @@ -234,33 +234,39 @@ static inline void page_table_check_pmd_flags(pmd_t pmd)
>>  		WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd)));
>>  }
>>  
>> -void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd)
>> +void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
>> +		unsigned int nr)
>>  {
>> +	unsigned int i;
>> +	unsigned long stride = PMD_SIZE >> PAGE_SHIFT;
>> +
>>  	if (&init_mm == mm)
>>  		return;
>>  
>>  	page_table_check_pmd_flags(pmd);
>>  
>> -	__page_table_check_pmd_clear(mm, *pmdp);
>> -	if (pmd_user_accessible_page(pmd)) {
>> -		page_table_check_set(pmd_pfn(pmd), PMD_SIZE >> PAGE_SHIFT,
>> -				     pmd_write(pmd));
>> -	}
>> +	for (i = 0; i < nr; i++)
>> +		__page_table_check_pmd_clear(mm, *(pmdp + i));
>> +	if (pmd_user_accessible_page(pmd))
>> +		page_table_check_set(pmd_pfn(pmd), stride * nr, pmd_write(pmd));
>>  }
>> -EXPORT_SYMBOL(__page_table_check_pmd_set);
>> +EXPORT_SYMBOL(__page_table_check_pmds_set);
>>  
>> -void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud)
>> +void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud,
>> +		unsigned int nr)
>>  {
>> +	unsigned int i;
>> +	unsigned long stride = PUD_SIZE >> PAGE_SHIFT;
>> +
>>  	if (&init_mm == mm)
>>  		return;
>>  
>> -	__page_table_check_pud_clear(mm, *pudp);
>> -	if (pud_user_accessible_page(pud)) {
>> -		page_table_check_set(pud_pfn(pud), PUD_SIZE >> PAGE_SHIFT,
>> -				     pud_write(pud));
>> -	}
>> +	for (i = 0; i < nr; i++)
>> +		__page_table_check_pud_clear(mm, *(pudp + i));
>> +	if (pud_user_accessible_page(pud))
>> +		page_table_check_set(pud_pfn(pud), stride * nr, pud_write(pud));
>>  }
>> -EXPORT_SYMBOL(__page_table_check_pud_set);
>> +EXPORT_SYMBOL(__page_table_check_puds_set);
>>  
>>  void __page_table_check_pte_clear_range(struct mm_struct *mm,
>>  					unsigned long addr,