mm: make drop_caches keep reclaiming on all nodes

Currently, drop_caches are reclaiming node-by-node, looping on each node
until reclaim could not make progress.  This can however leave quite some
slab entries (such as filesystem inodes) unreclaimed if objects say on
node 1 keep objects on node 0 pinned.  So move the "loop until no
progress" loop to the node-by-node iteration to retry reclaim also on
other nodes if reclaim on some nodes made progress.  This fixes problem
when drop_caches was not reclaiming lots of otherwise perfectly fine to
reclaim inodes.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Jan Kara <[email protected]>
Reported-by: You Zhou <[email protected]>
Reported-by: Pengfei Xu <[email protected]>
Tested-by: Pengfei Xu <[email protected]>
Reviewed-by: Shakeel Butt <[email protected]>
Cc: Vladimir Davydov <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

0 files changed, 0 insertions, 0 deletions