diff options
| author | Ilya Loginov <isloginov@gmail.com> | 2009-11-26 09:16:19 +0100 |
|---|---|---|
| committer | Gary King <gking@nvidia.com> | 2010-04-05 14:03:24 -0700 |
| commit | cedfa4f5754c5aa562d545865922626e2239f11b (patch) | |
| tree | b4a6e51490f076e6bfd02fd1e1be048b6922f621 /arch/avr32 | |
| parent | 3274abc33ec2c170acd6fd2732c271ad9dd0b17f (diff) | |
block: add helpers to run flush_dcache_page() against a bio and a request's pages
Mtdblock driver doesn't call flush_dcache_page for pages in request. So,
this causes problems on architectures where the icache doesn't fill from
the dcache or with dcache aliases. The patch fixes this.
The ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE symbol was introduced to avoid
pointless empty cache-thrashing loops on architectures for which
flush_dcache_page() is a no-op. Every architecture was provided with this
flush pages on architectires where ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE is
equal 1 or do nothing otherwise.
See "fix mtd_blkdevs problem with caches on some architectures" discussion
on LKML for more information.
Signed-off-by: Ilya Loginov <isloginov@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Peter Horton <phorton@bitbox.co.uk>
Cc: "Ed L. Cashin" <ecashin@coraid.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Diffstat (limited to 'arch/avr32')
| -rw-r--r-- | arch/avr32/include/asm/cacheflush.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/arch/avr32/include/asm/cacheflush.h b/arch/avr32/include/asm/cacheflush.h index 670674749b20..96e53820bbbd 100644 --- a/arch/avr32/include/asm/cacheflush.h +++ b/arch/avr32/include/asm/cacheflush.h @@ -107,6 +107,7 @@ extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); * do something here, but only for certain configurations. No such * configurations exist at this time. */ +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(page) do { } while (0) #define flush_dcache_mmap_unlock(page) do { } while (0) |