[v5] Fix stale IOTLB entries for kernel address space

[PATCH v5 2/8] mm: Actually mark kernel page table pages

Posted by Lu Baolu 4 months, 3 weeks ago

From: Dave Hansen <dave.hansen@linux.intel.com>

Now that the API is in place, mark kernel page table pages just
after they are allocated. Unmark them just before they are freed.

Note: Unconditionally clearing the 'kernel' marking (via
ptdesc_clear_kernel()) would be functionally identical to what
is here. But having the if() makes it logically clear that this
function can be used for kernel and non-kernel page tables.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
---
 include/asm-generic/pgalloc.h | 18 ++++++++++++++++++
 include/linux/mm.h            |  3 +++
 2 files changed, 21 insertions(+)

diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 3c8ec3bfea44..b9d2a7c79b93 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -28,6 +28,8 @@ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
 		return NULL;
 	}
 
+	ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __pte_alloc_one_kernel(...)	alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
@@ -146,6 +148,10 @@ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long ad
 		pagetable_free(ptdesc);
 		return NULL;
 	}
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define pmd_alloc_one(...)	alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
@@ -179,6 +185,10 @@ static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long
 		return NULL;
 
 	pagetable_pud_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __pud_alloc_one(...)	alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
@@ -233,6 +243,10 @@ static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long
 		return NULL;
 
 	pagetable_p4d_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __p4d_alloc_one(...)	alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__))
@@ -277,6 +291,10 @@ static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order
 		return NULL;
 
 	pagetable_pgd_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __pgd_alloc(...)	alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__))
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1ae97a0b8ec7..f3db3a5ebefe 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2895,6 +2895,9 @@ static inline void pagetable_free(struct ptdesc *pt)
 {
 	struct page *page = ptdesc_page(pt);
 
+	if (ptdesc_test_kernel(pt))
+		ptdesc_clear_kernel(pt);
+
 	__free_pages(page, compound_order(page));
 }
 
-- 
2.43.0

Re: [PATCH v5 2/8] mm: Actually mark kernel page table pages

Posted by Mike Rapoport 3 months, 3 weeks ago

On Fri, Sep 19, 2025 at 01:40:00PM +0800, Lu Baolu wrote:
> From: Dave Hansen <dave.hansen@linux.intel.com>
> 
> Now that the API is in place, mark kernel page table pages just
> after they are allocated. Unmark them just before they are freed.
> 
> Note: Unconditionally clearing the 'kernel' marking (via
> ptdesc_clear_kernel()) would be functionally identical to what
> is here. But having the if() makes it logically clear that this
> function can be used for kernel and non-kernel page tables.
> 
> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
> Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>

Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>

> ---
>  include/asm-generic/pgalloc.h | 18 ++++++++++++++++++
>  include/linux/mm.h            |  3 +++
>  2 files changed, 21 insertions(+)
> 
> diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
> index 3c8ec3bfea44..b9d2a7c79b93 100644
> --- a/include/asm-generic/pgalloc.h
> +++ b/include/asm-generic/pgalloc.h
> @@ -28,6 +28,8 @@ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
>  		return NULL;
>  	}
>  
> +	ptdesc_set_kernel(ptdesc);
> +
>  	return ptdesc_address(ptdesc);
>  }
>  #define __pte_alloc_one_kernel(...)	alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
> @@ -146,6 +148,10 @@ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long ad
>  		pagetable_free(ptdesc);
>  		return NULL;
>  	}
> +
> +	if (mm == &init_mm)
> +		ptdesc_set_kernel(ptdesc);
> +
>  	return ptdesc_address(ptdesc);
>  }
>  #define pmd_alloc_one(...)	alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
> @@ -179,6 +185,10 @@ static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long
>  		return NULL;
>  
>  	pagetable_pud_ctor(ptdesc);
> +
> +	if (mm == &init_mm)
> +		ptdesc_set_kernel(ptdesc);
> +
>  	return ptdesc_address(ptdesc);
>  }
>  #define __pud_alloc_one(...)	alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
> @@ -233,6 +243,10 @@ static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long
>  		return NULL;
>  
>  	pagetable_p4d_ctor(ptdesc);
> +
> +	if (mm == &init_mm)
> +		ptdesc_set_kernel(ptdesc);
> +
>  	return ptdesc_address(ptdesc);
>  }
>  #define __p4d_alloc_one(...)	alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__))
> @@ -277,6 +291,10 @@ static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order
>  		return NULL;
>  
>  	pagetable_pgd_ctor(ptdesc);
> +
> +	if (mm == &init_mm)
> +		ptdesc_set_kernel(ptdesc);
> +
>  	return ptdesc_address(ptdesc);
>  }
>  #define __pgd_alloc(...)	alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__))
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 1ae97a0b8ec7..f3db3a5ebefe 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2895,6 +2895,9 @@ static inline void pagetable_free(struct ptdesc *pt)
>  {
>  	struct page *page = ptdesc_page(pt);
>  
> +	if (ptdesc_test_kernel(pt))
> +		ptdesc_clear_kernel(pt);
> +
>  	__free_pages(page, compound_order(page));
>  }
>  
> -- 
> 2.43.0
> 

-- 
Sincerely yours,
Mike.

Re: [PATCH v5 2/8] mm: Actually mark kernel page table pages

Posted by David Hildenbrand 4 months ago

On 19.09.25 07:40, Lu Baolu wrote:
> From: Dave Hansen <dave.hansen@linux.intel.com>
> 
> Now that the API is in place, mark kernel page table pages just
> after they are allocated. Unmark them just before they are freed.
> 
> Note: Unconditionally clearing the 'kernel' marking (via
> ptdesc_clear_kernel()) would be functionally identical to what
> is here. But having the if() makes it logically clear that this
> function can be used for kernel and non-kernel page tables.
> 
> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
> Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>
> ---

Acked-by: David Hildenbrand <david@redhat.com>

-- 
Cheers

David / dhildenb