arm64: define __alloc_zeroed_user_highpage
PATCH 1/1 arm64: define __alloc_zeroed_user_highpage
When running the kernel with init_on_alloc=1, calling the default implementation of __alloc_zeroed_user_highpage() from include/linux/highmem.h leads to double-initialization of the allocated page (first by the page allocator, then by clear_user_page().
Calling alloc_page_vma() with __GFP_ZERO, similarly to e.g. x86, seems to be enough to ensure the user page is zeroed only once.
--- arch/arm64/include/asm/page.h | 4 ++++ 1 file changed, 4 insertions(+)
arch/arm64/include/asm/page.h +4 -0
@@ -21,6 +21,10 @@ extern void __cpu_copy_user_page(void *to, const void *from,extern void copy_page (void *to,const void *from);extern void clear_page (void *to); +#define __alloc_zeroed_user_highpage (movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) +#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE +#define clear_user_page (addr,vaddr,pg) __cpu_clear_user_page(addr, vaddr)#define copy_user_page (to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)
Signature · 1 line
2.25.1.481.gfbce0eb801-goog
Mark Rutland
reviewerQuoted 6 lines · On Thu, Mar 12, 2020 at 04:59:20PM +0100, [email protected] wrote:
When running the kernel with init_on_alloc=1, calling the default implementation of
__alloc_zeroed_user_highpage()frominclude/linux/highmem.hleads to double-initialization of the allocated page (first by the page allocator, then byclear_user_page().
Callingalloc_page_vma()with__GFP_ZERO, similarly to e.g. x86, seems to be enough to ensure the user page is zeroed only once.
Just to check, is there a functional ussue beyond the redundant zeroing, or is this jsut a performance issue?
On architectures with real highmem, does GFP_HIGHUSER prevent the allocator from zeroing the page in this case, or is the architecture prevented from allocating from highmem?
This feels like something we should be able to fix in the generic implementation of __alloc_zeroed_user_highpage(), with an additional check to see if init_on_alloc is in use.
Thanks,
Mark.
Quoted 24 lines
Signed-off-by Alexander Potapenko <[email protected]>--- arch/arm64/include/asm/page.h | 4 ++++ 1 file changed, 4 insertions(+)arch/arm64/include/asm/page.h +4
-0@@ -21,6 +21,10 @@ extern void __cpu_copy_user_page(void *to, const void *from,extern void copy_page (void *to,const void *from);extern void clear_page (void *to); +#define __alloc_zeroed_user_highpage (movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) +#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE +#define clear_user_page (addr,vaddr,pg) __cpu_clear_user_page(addr, vaddr)#define copy_user_page (to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)Signature · 1 line
2.25.1.481.gfbce0eb801-goog
_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Quoted 11 lines · Mark Rutland
Quoted 6 lines · On Thu, Mar 12, 2020 at 04:59:20PM +0100, [email protected] wrote:
When running the kernel with init_on_alloc=1, calling the default implementation of
__alloc_zeroed_user_highpage()frominclude/linux/highmem.hleads to double-initialization of the allocated page (first by the page allocator, then byclear_user_page().
Callingalloc_page_vma()with__GFP_ZERO, similarly to e.g. x86, seems to be enough to ensure the user page is zeroed only once.Just to check, is there a functional ussue beyond the redundant zeroing, or is this jsut a performance issue?
This is just a performance issue that only manifests when running the kernel with init_on_alloc=1.
Quoted 3 lines
On architectures with real highmem, does
GFP_HIGHUSERprevent the allocator from zeroing the page in this case, or is the architecture prevented from allocating from highmem?
I was hoping one of ARM maintainers can answer this question. My understanding was that __GFP_ZERO should be sufficient, but there's probably something I'm missing.
Quoted 27 lines
Thanks,
Mark.Quoted 24 lines
Signed-off-by Alexander Potapenko <[email protected]>--- arch/arm64/include/asm/page.h | 4 ++++ 1 file changed, 4 insertions(+)arch/arm64/include/asm/page.h +4
-1@@ -21,6 +21,10 @@ extern void __cpu_copy_user_page(void *to, const void *from,extern void copy_page (void *to,const void *from);extern void clear_page (void *to); +#define __alloc_zeroed_user_highpage (movableflags, vma, vaddr) \ + alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) +#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE +#define clear_user_page (addr,vaddr,pg) __cpu_clear_user_page(addr, vaddr)#define copy_user_page (to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr) --2.25.1.481.gfbce0eb801-goog
Signature · 10 lines
Alexander Potapenko Software Engineer Google Germany GmbH Erika-Mann-Straße, 33 80636 München Geschäftsführer: Paul Manicle, Halimah DeLaine Prado Registergericht und -nummer: Hamburg, HRB 86891 Sitz der Gesellschaft: Hamburg
Catalin Marinas
maintainerQuoted 16 lines · Alexander Potapenko
Quoted 11 lines · Mark Rutland
Quoted 6 lines · On Thu, Mar 12, 2020 at 04:59:20PM +0100, [email protected] wrote:
When running the kernel with init_on_alloc=1, calling the default implementation of
__alloc_zeroed_user_highpage()frominclude/linux/highmem.hleads to double-initialization of the allocated page (first by the page allocator, then byclear_user_page().
Callingalloc_page_vma()with__GFP_ZERO, similarly to e.g. x86, seems to be enough to ensure the user page is zeroed only once.Just to check, is there a functional ussue beyond the redundant zeroing, or is this jsut a performance issue?
This is just a performance issue that only manifests when running the kernel with init_on_alloc=1.
Quoted 7 lines
Quoted 3 lines
On architectures with real highmem, does
GFP_HIGHUSERprevent the allocator from zeroing the page in this case, or is the architecture prevented from allocating from highmem?I was hoping one of ARM maintainers can answer this question. My understanding was that
__GFP_ZEROshould be sufficient, but there's probably something I'm missing.
On architectures with aliasing D-cache (whether it's VIVT or aliasing VIPT), clear_user_highpage() ensures that the correct alias, as seen by the user, is cleared (see the arm32 v6_clear_user_highpage_aliasing() as an example). The clear_highpage() call as done by page_alloc.c does not have the user address information, so it can only clear the kernel alias.
On arm64 we don't have such issue, so we can optimise this case as per your patch. We may change this function later with MTE if we allow tags other than 0 on the first allocation of anonymous pages.
Signature · 6 lines
Catalin _______________________________________________ linux-arm-kernel mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Quoted 8 lines · On Thu, Mar 12, 2020 at 04:59:20PM +0100, [email protected] wrote:
When running the kernel with init_on_alloc=1, calling the default implementation of
__alloc_zeroed_user_highpage()frominclude/linux/highmem.hleads to double-initialization of the allocated page (first by the page allocator, then byclear_user_page().
Callingalloc_page_vma()with__GFP_ZERO, similarly to e.g. x86, seems to be enough to ensure the user page is zeroed only once.Signed-off-by Alexander Potapenko <[email protected]>
I queued this for 5.7. Thanks.
Signature · 1 line
Catalin