RE: [parisc-linux] Fwd: Problems with raw interface.

["Santosh Abraham" <santosha@india.hp.com>]

hmm.. why is map_user_kiobuf () calling flush_dcache_page () then ?
should it not be calling flush_cache_{range,page} ?

map_user_kiobuf () called from the raw I/O path should ,in the
write case, be flushing user data out, so that its visible to
the kernel VA.
This is not being done in flush_dcache_page () when page->mapping is
NULL.

-----Original Message-----
From: Randolph Chung [mailto:randolph@tausq.org]
Sent: Thursday, September 25, 2003 4:20 PM
To: santosh.abraham@hp.com
Cc: parisc-linux@lists.parisc-linux.org
Subject: Re: [parisc-linux] Fwd: Problems with raw interface.


> Also, does'nt __flush_dcache_page () need to have a for loop for "i_mmap"
> similar to the one for "i_mmap_shared" ?
>

no, this was discussed recently on this list.

see jejb's message:
http://lists.parisc-linux.org/pipermail/parisc-linux/2003-August/020791.html

and the corresponding thread for more info.

i thought flush_dcache_page is for making kernel mapping visible to
user, if you are trying to make user data visible to the kernel, you
should not be relying on flush_dcache_page.

randolph
--
Randolph Chung
Debian GNU/Linux Developer, hppa/ia64 ports
http://www.tausq.org/