On Fri, 30 Jul 2004 13:16:28 -0400
Jeff Garzik <jgarzik@xxxxxxxxx> wrote:
1) Changing from GFP_ATOMIC to <something else> may break code
x86-64 did it for a long time and I am not aware of problems with it
(however I don't know how widespread CONFIG_PREEMPT use on x86-64 is)
2) Conversely from #1, I also worry why GFP_ATOMIC would be needed at all. I code all my drivers to require that pci_alloc_consistent() be called from somewhere that is allowed to sleep.
Maybe you do, but others don't.