Re: patch: highmem zero-bounce

[Andrea Arcangeli]

On Tue, Jun 26, 2001 at 06:22:15PM +0200, Jens Axboe wrote:
> Hi,
> 
> I updated the patches to 2.4.6-pre5, and removed the zone-dma32
> addition. This means that machines with > 4GB of RAM will need to go all

good, we can relax the ZONE_NORMAL later, that's a separate problem with
skipping the bounces.

I can see one mm corruption race condition in the patch, you missed
nested irq in the for kmap_irq_bh (PIO).  You must _always_
__cli/__save_flags before accessing the KMAP_IRQ_BH slot, in case the
remapping is required (so _only_ when the page is in the highmem zone).
Otherwise memory corruption will happen when the race triggers (for
example two ide disks in PIO mode doing I/O at the same time connected
to different irq sources).

Andrea