On Fri, Jan 20, 2023 at 05:07:48AM +0000, Al Viro wrote:
> On Fri, Jan 20, 2023 at 04:54:51AM +0000, Matthew Wilcox wrote:
>
> > > Sure, but... there's also this:
> > >
> > > static inline void __kunmap_local(const void *addr)
> > > {
> > > #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
> > > kunmap_flush_on_unmap(addr);
> > > #endif
> > > }
> > >
> > > Are you sure that the guts of that thing will be happy with address that is not
> > > page-aligned? I've looked there at some point, got scared of parisc (IIRC)
> > > MMU details and decided not to rely upon that...
> >
> > Ugh, PA-RISC (the only implementor) definitely will flush the wrong
> > addresses. I think we should do this, as having bugs that only manifest
> > on one not-well-tested architecture seems Bad.
> >
> > static inline void __kunmap_local(const void *addr)
> > {
> > #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
> > - kunmap_flush_on_unmap(addr);
> > + kunmap_flush_on_unmap(PAGE_ALIGN_DOWN(addr));
> > #endif
> > }
>
> PTR_ALIGN_DOWN(addr, PAGE_SIZE), perhaps?
Anyway, that's a question to parisc folks; I _think_ pdtlb
quietly ignores the lower bits of address, so that part seems
to be safe, but I wouldn't bet upon that. And when I got to
flush_kernel_dcache_page_asm I gave up - it's been a long time
since I've dealt with parisc assembler.
