Re: [PATCH v2] openvswitch: allocate nr_node_ids flow_stats instead of num_possible_nodes

2015-07-21 Thread David Miller
From: Chris J Arges Date: Tue, 21 Jul 2015 12:36:33 -0500 > Some architectures like POWER can have a NUMA node_possible_map that > contains sparse entries. This causes memory corruption with openvswitch > since it allocates flow_cache with a multiple of num_possible_nodes() and > assumes the node

Re: [PATCH v2] openvswitch: allocate nr_node_ids flow_stats instead of num_possible_nodes

2015-07-21 Thread Nishanth Aravamudan
On 21.07.2015 [12:36:33 -0500], Chris J Arges wrote: > Some architectures like POWER can have a NUMA node_possible_map that > contains sparse entries. This causes memory corruption with openvswitch > since it allocates flow_cache with a multiple of num_possible_nodes() and > assumes the node variab

Re: [PATCH v2] openvswitch: allocate nr_node_ids flow_stats instead of num_possible_nodes

2015-07-21 Thread Pravin Shelar
On Tue, Jul 21, 2015 at 10:36 AM, Chris J Arges wrote: > Some architectures like POWER can have a NUMA node_possible_map that > contains sparse entries. This causes memory corruption with openvswitch > since it allocates flow_cache with a multiple of num_possible_nodes() and > assumes the node var

[PATCH v2] openvswitch: allocate nr_node_ids flow_stats instead of num_possible_nodes

2015-07-21 Thread Chris J Arges
Some architectures like POWER can have a NUMA node_possible_map that contains sparse entries. This causes memory corruption with openvswitch since it allocates flow_cache with a multiple of num_possible_nodes() and assumes the node variable returned by for_each_node will index into flow->stats[node