Re: [PATCH] change name of rep_nop

[Alan Cox]

> While we're on the subject of stupidly named routines and x86-isms, I'm 
> having trouble reconciling this text in Documentation/cachetlb.txt:
> 
> 	1) void flush_cache_all(void)
> 
> 	        The most severe flush of all.  After this interface runs,
> 	        the entire cpu cache is flushed.

I suspect the real definition should be

	"After this interface runs the device and other views of 
	 memory includes all dirty cache lines on the processor. On 
	 processors with cache coherent bus interfaces this may well
	 be a no operation

	 Footnote: AGP tends to have its own coherency and caching setup
	 so the AGP drivers use their own interfaces to avoid needless
	 overhead"