Introduce clear_pages(), to be overridden by architectures that
support more efficient clearing of consecutive pages.

Also introduce clear_user_pages(), however, we will not expect
this function to be overridden anytime soon.

We have to place the clear_user_pages() variant that uses
clear_user_page() into mm/util.c for now to work around
macro magic on sparc and m68k.

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Acked-by: David Hildenbrand (Red Hat) <david@kernel.org>
---

Notes:
   - Use macros clear_pages, clear_user_page, instead of __HAVE_ARCH_CLEAR_PAGES,
     __HAVE_ARCH_CLEAR_USER_PAGE.

 include/linux/mm.h | 41 +++++++++++++++++++++++++++++++++++++++++
 mm/util.c          | 13 +++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6fa6c188f99a..c397ee2f6dd5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3879,6 +3879,26 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
 				unsigned int order) {}
 #endif	/* CONFIG_DEBUG_PAGEALLOC */
 
+#ifndef clear_pages
+/**
+ * clear_pages() - clear a page range for kernel-internal use.
+ * @addr: start address
+ * @npages: number of pages
+ *
+ * Use clear_user_pages() instead when clearing a page range to be
+ * mapped to user space.
+ *
+ * Does absolutely no exception handling.
+ */
+static inline void clear_pages(void *addr, unsigned int npages)
+{
+	do {
+		clear_page(addr);
+		addr += PAGE_SIZE;
+	} while (--npages);
+}
+#endif
+
 #ifndef clear_user_page
 /**
  * clear_user_page() - clear a page to be mapped to user space
@@ -3901,6 +3921,27 @@ static inline void clear_user_page(void *addr, unsigned long vaddr, struct page
 }
 #endif
 
+/**
+ * clear_user_pages() - clear a page range to be mapped to user space
+ * @addr: start address
+ * @vaddr: start address of the user mapping
+ * @page: start page
+ * @npages: number of pages
+ *
+ * Assumes that the region (@addr, +@npages) has been validated
+ * already so this does no exception handling.
+ */
+#ifdef clear_user_pages
+void clear_user_pages(void *addr, unsigned long vaddr,
+		struct page *page, unsigned int npages);
+#else
+static inline void clear_user_pages(void *addr, unsigned long vaddr,
+		struct page *page, unsigned int npages)
+{
+	clear_pages(addr, npages);
+}
+#endif
+
 #ifdef __HAVE_ARCH_GATE_AREA
 extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
 extern int in_gate_area_no_mm(unsigned long addr);
diff --git a/mm/util.c b/mm/util.c
index 8989d5767528..3c6cd44db1bd 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1344,3 +1344,16 @@ bool page_range_contiguous(const struct page *page, unsigned long nr_pages)
 }
 EXPORT_SYMBOL(page_range_contiguous);
 #endif
+
+#ifdef clear_user_page
+void clear_user_pages(void *addr, unsigned long vaddr,
+		struct page *page, unsigned int npages)
+{
+	do {
+		clear_user_page(addr, vaddr, page);
+		addr += PAGE_SIZE;
+		vaddr += PAGE_SIZE;
+		page++;
+	} while (--npages);
+}
+#endif
-- 
2.31.1

Le 21/11/2025 à 21:23, Ankur Arora a écrit :
> Introduce clear_pages(), to be overridden by architectures that
> support more efficient clearing of consecutive pages.
> 
> Also introduce clear_user_pages(), however, we will not expect
> this function to be overridden anytime soon.
> 
> We have to place the clear_user_pages() variant that uses
> clear_user_page() into mm/util.c for now to work around
> macro magic on sparc and m68k.
> 
> Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
> Acked-by: David Hildenbrand (Red Hat) <david@kernel.org>
> ---
> 
> Notes:
>     - Use macros clear_pages, clear_user_page, instead of __HAVE_ARCH_CLEAR_PAGES,
>       __HAVE_ARCH_CLEAR_USER_PAGE.
> 
>   include/linux/mm.h | 41 +++++++++++++++++++++++++++++++++++++++++
>   mm/util.c          | 13 +++++++++++++
>   2 files changed, 54 insertions(+)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 6fa6c188f99a..c397ee2f6dd5 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3879,6 +3879,26 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
>   				unsigned int order) {}
>   #endif	/* CONFIG_DEBUG_PAGEALLOC */
>   
> +#ifndef clear_pages
> +/**
> + * clear_pages() - clear a page range for kernel-internal use.
> + * @addr: start address
> + * @npages: number of pages
> + *
> + * Use clear_user_pages() instead when clearing a page range to be
> + * mapped to user space.
> + *
> + * Does absolutely no exception handling.
> + */
> +static inline void clear_pages(void *addr, unsigned int npages)
> +{
> +	do {
> +		clear_page(addr);
> +		addr += PAGE_SIZE;
> +	} while (--npages);

Why a 'do while' instead of a 'while' ?

Are you certain that this function will never ever be called with a nul 
npages ?

> +}
> +#endif
> +
>   #ifndef clear_user_page
>   /**
>    * clear_user_page() - clear a page to be mapped to user space
> @@ -3901,6 +3921,27 @@ static inline void clear_user_page(void *addr, unsigned long vaddr, struct page
>   }
>   #endif
>   
> +/**
> + * clear_user_pages() - clear a page range to be mapped to user space
> + * @addr: start address
> + * @vaddr: start address of the user mapping
> + * @page: start page
> + * @npages: number of pages
> + *
> + * Assumes that the region (@addr, +@npages) has been validated
> + * already so this does no exception handling.
> + */
> +#ifdef clear_user_pages
> +void clear_user_pages(void *addr, unsigned long vaddr,
> +		struct page *page, unsigned int npages);

By doing this you forbid architectures to define it as a static inline, 
is that wanted ?

> +#else
> +static inline void clear_user_pages(void *addr, unsigned long vaddr,
> +		struct page *page, unsigned int npages)
> +{
> +	clear_pages(addr, npages);
> +}
> +#endif
> +
>   #ifdef __HAVE_ARCH_GATE_AREA
>   extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
>   extern int in_gate_area_no_mm(unsigned long addr);
> diff --git a/mm/util.c b/mm/util.c
> index 8989d5767528..3c6cd44db1bd 100644
> --- a/mm/util.c
> +++ b/mm/util.c
> @@ -1344,3 +1344,16 @@ bool page_range_contiguous(const struct page *page, unsigned long nr_pages)
>   }
>   EXPORT_SYMBOL(page_range_contiguous);
>   #endif
> +
> +#ifdef clear_user_page
> +void clear_user_pages(void *addr, 

What happens if clear_user_page is defined but not clear_user_pages ? In 
that case it seems like the definition in linux/mm.h will conflict.

unsigned long vaddr,
> +		struct page *page, unsigned int npages)
> +{
> +	do {
> +		clear_user_page(addr, vaddr, page);
> +		addr += PAGE_SIZE;
> +		vaddr += PAGE_SIZE;
> +		page++;
> +	} while (--npages);

Same, are you sure npages will never be nul ?

> +}
> +#endif

Replying here while I am already at it.

>> +#ifndef clear_pages
>> +/**
>> + * clear_pages() - clear a page range for kernel-internal use.
>> + * @addr: start address
>> + * @npages: number of pages
>> + *
>> + * Use clear_user_pages() instead when clearing a page range to be
>> + * mapped to user space.
>> + *
>> + * Does absolutely no exception handling.
>> + */
>> +static inline void clear_pages(void *addr, unsigned int npages)
>> +{
>> +	do {
>> +		clear_page(addr);
>> +		addr += PAGE_SIZE;
>> +	} while (--npages);
> 
> Why a 'do while' instead of a 'while' ?

More efficient when we know that npages > 0.

> 
> Are you certain that this function will never ever be called with a nul
> npages ?

That is the expectation here, yes. We should probably document that 
expectation.

> 
>> +}
>> +#endif
>> +
>>    #ifndef clear_user_page
>>    /**
>>     * clear_user_page() - clear a page to be mapped to user space
>> @@ -3901,6 +3921,27 @@ static inline void clear_user_page(void *addr, unsigned long vaddr, struct page
>>    }
>>    #endif
>>    
>> +/**
>> + * clear_user_pages() - clear a page range to be mapped to user space
>> + * @addr: start address
>> + * @vaddr: start address of the user mapping
>> + * @page: start page
>> + * @npages: number of pages
>> + *
>> + * Assumes that the region (@addr, +@npages) has been validated
>> + * already so this does no exception handling.
>> + */
>> +#ifdef clear_user_pages
>> +void clear_user_pages(void *addr, unsigned long vaddr,
>> +		struct page *page, unsigned int npages);
> 
> By doing this you forbid architectures to define it as a static inline,
> is that wanted ?

Note that this is not the intention. The intention is to either use a 
direct mapping to clear_pages(), or fallback to the variant in mm/util.c.

The architecture is currently never expected to provide clear_user_pages().

Wondering if we can make that cleaner.

I'm wondering if the dependency on highmem.h here in mm.h is rather the 
problem.

How I hate this macro crap with arch overrides.

> 
>> +#else
>> +static inline void clear_user_pages(void *addr, unsigned long vaddr,
>> +		struct page *page, unsigned int npages)
>> +{
>> +	clear_pages(addr, npages);
>> +}
>> +#endif
>> +
>>    #ifdef __HAVE_ARCH_GATE_AREA
>>    extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
>>    extern int in_gate_area_no_mm(unsigned long addr);
>> diff --git a/mm/util.c b/mm/util.c
>> index 8989d5767528..3c6cd44db1bd 100644
>> --- a/mm/util.c
>> +++ b/mm/util.c
>> @@ -1344,3 +1344,16 @@ bool page_range_contiguous(const struct page *page, unsigned long nr_pages)
>>    }
>>    EXPORT_SYMBOL(page_range_contiguous);
>>    #endif
>> +
>> +#ifdef clear_user_page
>> +void clear_user_pages(void *addr,
> 
> What happens if clear_user_page is defined but not clear_user_pages ? In
> that case it seems like the definition in linux/mm.h will conflict.

The generic mm.h variant will not set clear_user_page() and consequently 
we map directly to clear_pages().

-- 
Cheers

David

From: Lance Yang <lance.yang@linux.dev>


On Mon, 24 Nov 2025 11:26:56 +0100, David Hildenbrand (Red Hat) wrote:
> Replying here while I am already at it.
> 
> >> +#ifndef clear_pages
> >> +/**
> >> + * clear_pages() - clear a page range for kernel-internal use.
> >> + * @addr: start address
> >> + * @npages: number of pages
> >> + *
> >> + * Use clear_user_pages() instead when clearing a page range to be
> >> + * mapped to user space.
> >> + *
> >> + * Does absolutely no exception handling.
> >> + */
> >> +static inline void clear_pages(void *addr, unsigned int npages)
> >> +{
> >> +	do {
> >> +		clear_page(addr);
> >> +		addr += PAGE_SIZE;
> >> +	} while (--npages);
> > 
> > Why a 'do while' instead of a 'while' ?
> 
> More efficient when we know that npages > 0.
> 
> > 
> > Are you certain that this function will never ever be called with a nul
> > npages ?
> 
> That is the expectation here, yes. We should probably document that 
> expectation.
> 
> > 
> >> +}
> >> +#endif
> >> +
> >>    #ifndef clear_user_page
> >>    /**
> >>     * clear_user_page() - clear a page to be mapped to user space
> >> @@ -3901,6 +3921,27 @@ static inline void clear_user_page(void *addr, unsigned long vaddr, struct page
> >>    }
> >>    #endif
> >>    
> >> +/**
> >> + * clear_user_pages() - clear a page range to be mapped to user space
> >> + * @addr: start address
> >> + * @vaddr: start address of the user mapping
> >> + * @page: start page
> >> + * @npages: number of pages
> >> + *
> >> + * Assumes that the region (@addr, +@npages) has been validated
> >> + * already so this does no exception handling.
> >> + */
> >> +#ifdef clear_user_pages
> >> +void clear_user_pages(void *addr, unsigned long vaddr,
> >> +		struct page *page, unsigned int npages);
> > 
> > By doing this you forbid architectures to define it as a static inline,
> > is that wanted ?
> 
> Note that this is not the intention. The intention is to either use a 
> direct mapping to clear_pages(), or fallback to the variant in mm/util.c.
> 
> The architecture is currently never expected to provide clear_user_pages().
> 
> Wondering if we can make that cleaner.
> 
> I'm wondering if the dependency on highmem.h here in mm.h is rather the 
> problem.
> 
> How I hate this macro crap with arch overrides.
> 
> > 
> >> +#else
> >> +static inline void clear_user_pages(void *addr, unsigned long vaddr,
> >> +		struct page *page, unsigned int npages)
> >> +{
> >> +	clear_pages(addr, npages);
> >> +}
> >> +#endif
> >> +
> >>    #ifdef __HAVE_ARCH_GATE_AREA
> >>    extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
> >>    extern int in_gate_area_no_mm(unsigned long addr);
> >> diff --git a/mm/util.c b/mm/util.c
> >> index 8989d5767528..3c6cd44db1bd 100644
> >> --- a/mm/util.c
> >> +++ b/mm/util.c
> >> @@ -1344,3 +1344,16 @@ bool page_range_contiguous(const struct page *page, unsigned long nr_pages)
> >>    }
> >>    EXPORT_SYMBOL(page_range_contiguous);
> >>    #endif
> >> +
> >> +#ifdef clear_user_page
> >> +void clear_user_pages(void *addr,
> > 
> > What happens if clear_user_page is defined but not clear_user_pages ? In
> > that case it seems like the definition in linux/mm.h will conflict.
> 
> The generic mm.h variant will not set clear_user_page() and consequently 
> we map directly to clear_pages().

Hmm, I suspect there might be a subtle issue with the build flow on SPARC ...

Inside include/linux/mm.h, the guard checks for clear_user_pages (plural).
Since SPARC doesn't define that, the header provides the static inline
fallback.

However, mm/util.c includes that header. And since SPARC does define
clear_user_page (singular), the .c file proceeds to compile the non-static
definition as well.

Wouldn't that result in the compiler seeing both a static inline and a
non-static definition in the same translation unit? It seems like this
would trigger a redefinition error ...

Thanks,
Lance

Lance Yang <ioworker0@gmail.com> writes:

> From: Lance Yang <lance.yang@linux.dev>
>
>
> On Mon, 24 Nov 2025 11:26:56 +0100, David Hildenbrand (Red Hat) wrote:
>> Replying here while I am already at it.
>>
>> >> +#ifndef clear_pages
>> >> +/**
>> >> + * clear_pages() - clear a page range for kernel-internal use.
>> >> + * @addr: start address
>> >> + * @npages: number of pages
>> >> + *
>> >> + * Use clear_user_pages() instead when clearing a page range to be
>> >> + * mapped to user space.
>> >> + *
>> >> + * Does absolutely no exception handling.
>> >> + */
>> >> +static inline void clear_pages(void *addr, unsigned int npages)
>> >> +{
>> >> +	do {
>> >> +		clear_page(addr);
>> >> +		addr += PAGE_SIZE;
>> >> +	} while (--npages);
>> >
>> > Why a 'do while' instead of a 'while' ?
>>
>> More efficient when we know that npages > 0.
>>
>> >
>> > Are you certain that this function will never ever be called with a nul
>> > npages ?
>>
>> That is the expectation here, yes. We should probably document that
>> expectation.
>>
>> >
>> >> +}
>> >> +#endif
>> >> +
>> >>    #ifndef clear_user_page
>> >>    /**
>> >>     * clear_user_page() - clear a page to be mapped to user space
>> >> @@ -3901,6 +3921,27 @@ static inline void clear_user_page(void *addr, unsigned long vaddr, struct page
>> >>    }
>> >>    #endif
>> >>
>> >> +/**
>> >> + * clear_user_pages() - clear a page range to be mapped to user space
>> >> + * @addr: start address
>> >> + * @vaddr: start address of the user mapping
>> >> + * @page: start page
>> >> + * @npages: number of pages
>> >> + *
>> >> + * Assumes that the region (@addr, +@npages) has been validated
>> >> + * already so this does no exception handling.
>> >> + */
>> >> +#ifdef clear_user_pages
>> >> +void clear_user_pages(void *addr, unsigned long vaddr,
>> >> +		struct page *page, unsigned int npages);
>> >
>> > By doing this you forbid architectures to define it as a static inline,
>> > is that wanted ?
>>
>> Note that this is not the intention. The intention is to either use a
>> direct mapping to clear_pages(), or fallback to the variant in mm/util.c.
>>
>> The architecture is currently never expected to provide clear_user_pages().
>>
>> Wondering if we can make that cleaner.
>>
>> I'm wondering if the dependency on highmem.h here in mm.h is rather the
>> problem.
>>
>> How I hate this macro crap with arch overrides.
>>
>> >
>> >> +#else
>> >> +static inline void clear_user_pages(void *addr, unsigned long vaddr,
>> >> +		struct page *page, unsigned int npages)
>> >> +{
>> >> +	clear_pages(addr, npages);
>> >> +}
>> >> +#endif
>> >> +
>> >>    #ifdef __HAVE_ARCH_GATE_AREA
>> >>    extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
>> >>    extern int in_gate_area_no_mm(unsigned long addr);
>> >> diff --git a/mm/util.c b/mm/util.c
>> >> index 8989d5767528..3c6cd44db1bd 100644
>> >> --- a/mm/util.c
>> >> +++ b/mm/util.c
>> >> @@ -1344,3 +1344,16 @@ bool page_range_contiguous(const struct page *page, unsigned long nr_pages)
>> >>    }
>> >>    EXPORT_SYMBOL(page_range_contiguous);
>> >>    #endif
>> >> +
>> >> +#ifdef clear_user_page
>> >> +void clear_user_pages(void *addr,
>> >
>> > What happens if clear_user_page is defined but not clear_user_pages ? In
>> > that case it seems like the definition in linux/mm.h will conflict.
>>
>> The generic mm.h variant will not set clear_user_page() and consequently
>> we map directly to clear_pages().
>
> Hmm, I suspect there might be a subtle issue with the build flow on SPARC ...
>
> Inside include/linux/mm.h, the guard checks for clear_user_pages (plural).
> Since SPARC doesn't define that, the header provides the static inline
> fallback.
>
> However, mm/util.c includes that header. And since SPARC does define
> clear_user_page (singular), the .c file proceeds to compile the non-static
> definition as well.
>
> Wouldn't that result in the compiler seeing both a static inline and a
> non-static definition in the same translation unit? It seems like this
> would trigger a redefinition error ...

Yeah it would.

I had only posted the linux/highmem.h header bits for brevity but the
full patch removes the mm/util.c bits.

Sorry about the confusion.

--
ankur