RE: ordered memory access

Bret Indrelee (bindrelee@sbs-cp.com)
Thu, 30 Sep 1999 10:31:00 -0500

> The case that Manfred brought up was perfectly valid - we could do
> __raw_atomic_foo() functions to do it if there is a need. We could
> also just decide that atomic_foo() does not guarantee ordering.

Since you already have separate functions for memory barriers, I would think
not guarenteeing ordering would be the sensible thing to do. Keep it simple.

IFF it is shown that almost every time you do the atomic_xxx() functions the
code also needs the memory barrier, then you can consider adding this to the
function.

-Bret

-------------------------------------------------------------
SBS Technologies, Connectivity Products
... solutions for real-time connectivity

Bret Indrelee, Engineer
SBS Technologies, Inc., Connectivity Products
1284 Corporate Center Drive, St. Paul MN 55121
Direct: (651) 905-4731
Main: (651) 905-4700 Fax: (651) 905-4701
E-mail: bindrelee@sbs-cp.com http://www.sbs.com
-------------------------------------------------------------

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/