On Mon, 5 Jan 2015, Andreas Mohr wrote: > These thoughts also mean that I'm unsure (difficult to determine) > of whether this change is good (i.e. a clean step in the right direction), > or whether instead the implementation could easily directly be made > fully independent from IRQ constraints. We have thought a couple of times about making it independent of interrupts. We can do that if there is guarantee that no slab operations are going to be performed from an interrupt context. That in turn will simplify allocator design significantly. Regarding this patchset: I think this has the character of an RFC at this point. There are some good ideas here but this needs to mature a bit and get lots of feedback. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>