On Mon, Jul 16 2007, James Bottomley wrote: > On Mon, 2007-07-16 at 14:16 +0200, Jens Axboe wrote: > > On Mon, Jul 16 2007, Geert Uytterhoeven wrote: > > > On Fri, 13 Jul 2007, Geert Uytterhoeven wrote: > > > > Ah, that explains it. flush_dcache_page() is used in some drivers. > > > > I'll update my patches. Thanks for the comments! > > > > > > Does this look OK? > > > - Replaced KM_USER0 by KM_IRQ0 (all routines are either called from an > > > interrupt handler, from .request_fn (ps3disk), or from .queuecommand > > > (ps3rom)) > > > > That looks good. > > > > > - Add a call to flush_kernel_dcache_page() in routines that write to buffers > > > > Hmm, I would have thought a flush_dcache_page() would be more > > appropriate, the backing could be page cache pages. > > No ... that was the point of flush_kernel_dcache_page(). The page in > question is page cache backed and contains user mappings. However, the > block layer has already done a flush_dcache_page() in get_user_pages() > and the user shouldn't be touching memory under I/O (unless they want > self induced aliasing problems) so we're free to assume all the user > cachelines are purged, hence all we have to do is flush the kernel alias > to bring the page up to date and make the users see it correctly. Oh indeed, I missed the flush_dcache_page() in get_user_pages(). -- Jens Axboe - To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
