Flush the D-cache during copy_user_highpage()
PATCH 1/1 Flush the D-cache during copy_user_highpage()
The I and D caches for copy-on-write pages on processors with write-allocate caches become incoherent causing problems on application relying on CoW for text pages (dynamic linker relocating symbols in a text page). This patch flushes the D-cache for such pages.
--- arch/arm/mm/copypage-v6.c | 8 ++++++++ 1 files changed, 8 insertions(+), 0 deletions(-)
arch/arm/mm/copypage-v6.c +8 -0
@@ -41,6 +41,14 @@ static void v6_copy_user_highpage_nonaliasing(struct page *to, kfrom =kmap_atomic (from,KM_USER0 ); kto =kmap_atomic (to,KM_USER1 );copy_page (kto, kfrom); +#ifdef CONFIG_HIGHMEM +/* +* kmap_atomic() doesn't set the page virtual address, and +* kunmap_atomic() takes care of cache flushing already. +*/ + if (page_address(to) != NULL) +#endif +__cpuc_flush_dcache_page (kto);kunmap_atomic (kto,KM_USER1 );kunmap_atomic (kfrom,KM_USER0 ); }
PATCH 1/1 Flush the D-cache during copy_user_highpage()
Quoted 4 lines · Catalin Marinas
The I and D caches for copy-on-write pages on processors with write-allocate caches become incoherent causing problems on application relying on CoW for text pages (dynamic linker relocating symbols in a text page). This patch flushes the D-cache for such pages.
Don't we need to do this on ARMv7 as well?
PATCH 1/1 Flush the D-cache during copy_user_highpage()
Quoted 7 lines · Russell King - ARM Linux
Quoted 4 lines · Catalin Marinas
The I and D caches for copy-on-write pages on processors with write-allocate caches become incoherent causing problems on application relying on CoW for text pages (dynamic linker relocating symbols in a text page). This patch flushes the D-cache for such pages.
Don't we need to do this on ARMv7 as well?
Do you mean an improvement to the patch description?
Signature · 1 line
Catalin
PATCH 1/1 Flush the D-cache during copy_user_highpage()
Quoted 10 lines · Catalin Marinas
Quoted 7 lines · Russell King - ARM Linux
Quoted 4 lines · Catalin Marinas
The I and D caches for copy-on-write pages on processors with write-allocate caches become incoherent causing problems on application relying on CoW for text pages (dynamic linker relocating symbols in a text page). This patch flushes the D-cache for such pages.
Don't we need to do this on ARMv7 as well?
Do you mean an improvement to the patch description?
Don't worry, I'm being silly - there isn't an ARMv7 version of the copy page functions. Your patch is fine.
PATCH 1/1 Flush the D-cache during copy_user_highpage()
Quoted 8 lines · Russell King - ARM Linux
Quoted 7 lines · Catalin Marinas
Quoted 6 lines · Russell King - ARM Linux
Quoted 4 lines · Catalin Marinas
The I and D caches for copy-on-write pages on processors with write-allocate caches become incoherent causing problems on application relying on CoW for text pages (dynamic linker relocating symbols in a text page). This patch flushes the D-cache for such pages.
Quoted 6 lines
Quoted 3 lines
Quoted 1 line
Don't we need to do this on ARMv7 as well?
Do you mean an improvement to the patch description?
Don't worry, I'm being silly - there isn't an ARMv7 version of the copy page functions. Your patch is fine.
So, do you want a pull request, send it to the patch system or you just pick it up from the list?
Signature · 1 line
Catalin
PATCH 1/1 Flush the D-cache during copy_user_highpage()
Quoted 11 lines · Catalin Marinas
Quoted 10 lines · Russell King - ARM Linux
Quoted 9 lines · Catalin Marinas
Quoted 7 lines · Russell King - ARM Linux
Quoted 4 lines · Catalin Marinas
The I and D caches for copy-on-write pages on processors with write-allocate caches become incoherent causing problems on application relying on CoW for text pages (dynamic linker relocating symbols in a text page). This patch flushes the D-cache for such pages.
Don't we need to do this on ARMv7 as well?
Quoted 7 lines
Quoted 4 lines
Quoted 1 line
Do you mean an improvement to the patch description?
Don't worry, I'm being silly - there isn't an ARMv7 version of the copy page functions. Your patch is fine.
So, do you want a pull request, send it to the patch system or you just pick it up from the list?
Patch system please.