Russell King - ARM Linux wrote:
> --- a/arch/frv/include/asm/cacheflush.h
> +++ b/arch/frv/include/asm/cacheflush.h
> @@ -95,7 +95,9 @@ static inline void flush_icache_page(struct vm_area_struct
> *vma, struct page *pa
> */
> #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
> d
On Wed, Apr 09, 2014 at 12:33:58PM -0400, David Miller wrote:
> From: Russell King - ARM Linux
> Date: Wed, 9 Apr 2014 17:15:55 +0100
>
> > On Wed, Apr 09, 2014 at 12:09:26PM -0400, David Miller wrote:
> >> From: Russell King - ARM Linux
> >> Date: Wed, 9 Apr 2014 11:01:50 +0100
> >>
> >> > Wha
From: Russell King - ARM Linux
Date: Wed, 9 Apr 2014 17:15:55 +0100
> On Wed, Apr 09, 2014 at 12:09:26PM -0400, David Miller wrote:
>> From: Russell King - ARM Linux
>> Date: Wed, 9 Apr 2014 11:01:50 +0100
>>
>> > What has been proposed for uprobes is a uprobe specific function -
>> > flush_upr
On Wed, Apr 09, 2014 at 12:09:26PM -0400, David Miller wrote:
> From: Russell King - ARM Linux
> Date: Wed, 9 Apr 2014 11:01:50 +0100
>
> > What has been proposed for uprobes is a uprobe specific function -
> > flush_uprobe_xol_access() which is used after uprobes writes via the
> > kmap_atomic()
From: Russell King - ARM Linux
Date: Wed, 9 Apr 2014 11:01:50 +0100
> What has been proposed for uprobes is a uprobe specific function -
> flush_uprobe_xol_access() which is used after uprobes writes via the
> kmap_atomic() mapping of the page:
>
> + xol_page_kaddr = kmap_atomic(area->page
The subject of flush_icache_user_range() recently came up in a discussion
about uprobes on ARM - and it was suggested maybe to make use of it as
the flush_dcache_page() in uprobes doesn't have the desired effect.
However, uprobes does not track the vma for userspace, which would mean
it has to pas
6 matches
Mail list logo
