aboutsummaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>2008-04-08 17:41:54 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-04-08 18:25:53 -0700
commit41e3355de052693c7a0cad74b845148d262edadf (patch)
tree7d40851015f1a90a9c6386c3e880ed23ac5127cb /mm/page_alloc.c
parentbb070e43497d4fcfea7d8b52003fe1376c218343 (diff)
downloadkernel_samsung_aries-41e3355de052693c7a0cad74b845148d262edadf.zip
kernel_samsung_aries-41e3355de052693c7a0cad74b845148d262edadf.tar.gz
kernel_samsung_aries-41e3355de052693c7a0cad74b845148d262edadf.tar.bz2
memcg: fix node_state handling
This should be N_NORMAL_MEMORY. N_NORMAL_MEMORY is "true" if a node has memory for the kernel. N_HIGH_MEMORY is "true" if a node has memory for HIGHMEM. (If CONFIG_HIGHMEM=n, always "true") This check is used for testing whether we can use kmalloc_node() on a node. Then, if there is a node which only contains HIGHMEM, the system will call kmalloc_node() which doesn't contain memory for the kernel. If it happens under SLUB, the kernel will panic. I think this only happens on x86_32-numa. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
0 files changed, 0 insertions, 0 deletions