Re: [PATCH] Re: time() glitch on 2.4.18: solved

[Alan Cox]

On Wed, 2002-11-06 at 12:47, Richard B. Johnson wrote:
> udelay() would work memory/read/write is entirely different from I/O
> port read/write even though PWB traces are shared. But that might
> result in wasted CPU cycles.

udelay actually makes a lot lot more sense than the current _p stuff.
Legacy-free hardware might not do what is expected with port 0x80
eventually and still have stuff using _p
> 
> This works in all cases in machines I have tested. I can't test everything
> but, depending upon whether or not the forces a cache-line refill, the
> delay can be from 200 ns to over 800 ns. I have a single instance of this,
> and call it, rather than doing in-line. This adds a further delay.

Thats a call/return stack break. That does delay damage in excess of
what you actually want and the wrong places. udelay does the right thing