[PATCH -mm] mm, compaction: properly signal and act upon lock and need_sched() contention - fix

[David Rientjes]

On Mon, 2 Jun 2014, Vlastimil Babka wrote:

> compact_should_abort() returns true instead of false and vice versa
> due to changes between v1 and v2 of the patch. This makes both async
> and sync compaction abort with high probability, and has been reported
> to cause e.g. soft lockups on some ARM boards, or drivers calling
> dma_alloc_coherent() fail to probe with CMA enabled on different boards.
> 
> This patch fixes the return value to match comments and callers expecations.
> 
> Reported-and-tested-by: Kevin Hilman <khilman at linaro.org>
> Reported-and-tested-by: Shawn Guo <shawn.guo at linaro.org>
> Tested-by: Stephen Warren <swarren at nvidia.com>
> Signed-off-by: Vlastimil Babka <vbabka at suse.cz>

Acked-by: David Rientjes <rientjes at google.com>