On Thursday December 1, akpm@xxxxxxxx wrote: > NeilBrown <neilb@xxxxxxx> wrote: > > > > + paddr = kmap_atomic(page, KM_USER0); > > + memset(paddr + offset, 0xff, > > PAGE_SIZE - offset); > > This page which is being altered is a user-visible one, no? A pagecache > page? It can be, but also may not be.. > > We must always run flush_dcache_page() against a page when the kernel > modifies a user-visible page's contents. Otherwise, on some architectures, > the modification won't be visible at the different virtual address. Ok, I'll add that at an appropriate place, thanks. NeilBrown - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
