[fuse-devel] Re: [parisc-linux] [PATCH] Fixs to work on ARM and PARIC platforms.

[Miklos Szeredi]

> >   flush_dcache_page():
> >      - The kernel address is flushed regardless whether the page is
> >        anonymous or not
> 
> Not quite ... if the page is file backed but has no user mappings, on
> the page dirty bit will be set (the kernel view won't be flushed).

Yes, but in this case (page obtained from get_user_pages()) it
obviously does have a user mapping.

> >      - If the page is file backed, then all user addresses refering to
> >        the page are flushed
> 
> Yes, that's what it does.
> 
> > Why this discrepancy between anonymous and file backed pages?
> > Wounldn't it be enough for file backed pages too to flush only one
> > user address?
> 
> Not necessarily ... you're getting deep into how VIPT and VIVT caches
> work.  VIVT and non-CAM based VIPT caches need every alias flushed
> (well, that's not congruent, anyway ... we try to keep congruence in
> parisc, but it's not always possible).  Usually a page is either file
> backed or anonymous, so for an anonymous page, we wouldn't know the user
> address to flush even if it were congruent.

I still don't see _why_ you need all aliases flushed from
get_user_pages() when you are only accessing the page through a single
address.

Think of it this way: 

get_user_pages(... write=0 ...) + memcpy() is equivalent to
copy_from_user()

get_user_pages(... write=1 ...) + memcpy() + flush_kernel_dcache_page()
is equivalent to copy_to_user()

copy_from_user() and copy_to_user() don't care about aliases, do they?

> > Added to the mix are copy_to/from_user_page() which already seem to do
> > the above, and are used in combination with get_user_pages() which
> > results in multiple redundant cache flushes.  Not too clean, is it?
> 
> I don't see that they do.  If flush_dcache_page() also does anon pages,
> then the arch implementation of flush_anon_page() will be empty.  If it
> doesn't, then the flush_anon_page() and flush_dcache_page() are mutually
> exclusive, anyway (because they both check the anon flag).

No, I was thinking of 

  get_user_pages()
  copy_to_user_page()/copy_from_user_page()

copy_to/from_user_page are defined as:

	  flush_cache_page(vma, vaddr, page_to_pfn(page)); \
	  memcpy(dst, src, len); \
	  ...

So they do flush the caches _once more_ after get_user_pages() should
have already done so.  OK, I see it flushes the icache as well, but
then only an icache flush should be needed, no?

Miklos