Re: Memory-mapped I/O barriers, state of affairs?

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Leon Woestenberg
Date: Monday, March 22, 2010 - 3:12 pm

Hello Andreas, all,

On Mon, Mar 22, 2010 at 9:16 PM, Andreas Bombe <aeb@debian.org> wrote:
The mapping makes the memory cache-coherent. I already use that.

But does that mean that this coherency is guaranteed to occur before I
start MMIO access to a device, i.e. is there a guaranteed ordering
between the writes?

Regards,
-- 
Leon
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Memory-mapped I/O barriers, state of affairs?, Leon Woestenberg, (Mon Mar 22, 12:18 pm)
Re: Memory-mapped I/O barriers, state of affairs?, Andreas Bombe, (Mon Mar 22, 1:16 pm)
Re: Memory-mapped I/O barriers, state of affairs?, Leon Woestenberg, (Mon Mar 22, 3:12 pm)
Re: Memory-mapped I/O barriers, state of affairs?, Robert Hancock, (Mon Mar 22, 5:14 pm)