Messages in this thread | | | Subject | Re: [PATCH] Define flush_wc, a way to flush write combining store buffers | From | Alan Cox <> | Date | Wed, 08 Mar 2006 22:06:31 +0000 |
| |
On Mer, 2006-03-08 at 13:31 -0800, Bryan O'Sullivan wrote: > flush_wc() says nothing about whether {A,B,C} may be reordered with > respect to each other, or whether {D,E} may, but it guarantees that > {A,B,C} will make it off-CPU before {D,E}. An arch that implements > flush_wc() should make the stores occur immediately, if possible.
How is this different to mmiowb() ?
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |