Messages in this thread Patch in this message | | | Date | Thu, 16 Jul 2009 13:05:31 -0700 (PDT) | From | David Rientjes <> | Subject | Re: [BUG] set_mempolicy(MPOL_INTERLEAV) cause kernel panic |
| |
On Wed, 15 Jul 2009, Lee Schermerhorn wrote:
> Interestingly, on ia64, the top cpuset mems_allowed gets set to all > possible nodes, while on x86_64, it gets set to on-line nodes [or nodes > with memory]. Maybe this is a to support hot-plug? >
numactl --interleave=all simply passes a nodemask with all bits set, so if cpuset_current_mems_allowed includes offline nodes from node_possible_map, then mpol_set_nodemask() doesn't mask them off.
Seems like we could handle this strictly in mempolicies without worrying about top_cpuset like in the following? --- diff --git a/mm/mempolicy.c b/mm/mempolicy.c --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -194,6 +194,7 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t cpuset_context_nmask; + nodemask_t mems_allowed; int ret; /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ @@ -201,20 +202,21 @@ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes) return 0; VM_BUG_ON(!nodes); + nodes_and(mems_allowed, cpuset_current_mems_allowed, + node_states[N_HIGH_MEMORY]); if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) nodes = NULL; /* explicit local allocation */ else { if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&cpuset_context_nmask, nodes, - &cpuset_current_mems_allowed); + &mems_allowed); else nodes_and(cpuset_context_nmask, *nodes, - cpuset_current_mems_allowed); + mems_allowed); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else - pol->w.cpuset_mems_allowed = - cpuset_current_mems_allowed; + pol->w.cpuset_mems_allowed = mems_allowed; } ret = mpol_ops[pol->mode].create(pol,
| |