aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/cpuset.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/cpuset.c')
-rw-r--r--kernel/cpuset.c31
1 files changed, 16 insertions, 15 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index fc7f4748d34a..ee14e3a35a29 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -622,6 +622,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
int csn; /* how many cpuset ptrs in csa so far */
int i, j, k; /* indices for partition finding loops */
cpumask_var_t *doms; /* resulting partition; i.e. sched domains */
+ cpumask_var_t non_isolated_cpus; /* load balanced CPUs */
struct sched_domain_attr *dattr; /* attributes for custom domains */
int ndoms = 0; /* number of sched domains in result */
int nslot; /* next empty doms[] struct cpumask slot */
@@ -631,6 +632,10 @@ static int generate_sched_domains(cpumask_var_t **domains,
dattr = NULL;
csa = NULL;
+ if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL))
+ goto done;
+ cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+
/* Special case for the 99% of systems with one, full, sched domain */
if (is_sched_load_balance(&top_cpuset)) {
ndoms = 1;
@@ -643,7 +648,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
*dattr = SD_ATTR_INIT;
update_domain_attr_tree(dattr, &top_cpuset);
}
- cpumask_copy(doms[0], top_cpuset.effective_cpus);
+ cpumask_and(doms[0], top_cpuset.effective_cpus,
+ non_isolated_cpus);
goto done;
}
@@ -666,7 +672,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
* the corresponding sched domain.
*/
if (!cpumask_empty(cp->cpus_allowed) &&
- !is_sched_load_balance(cp))
+ !(is_sched_load_balance(cp) &&
+ cpumask_intersects(cp->cpus_allowed, non_isolated_cpus)))
continue;
if (is_sched_load_balance(cp))
@@ -748,6 +755,7 @@ restart:
if (apn == b->pn) {
cpumask_or(dp, dp, b->effective_cpus);
+ cpumask_and(dp, dp, non_isolated_cpus);
if (dattr)
update_domain_attr_tree(dattr + nslot, b);
@@ -760,6 +768,7 @@ restart:
BUG_ON(nslot != ndoms);
done:
+ free_cpumask_var(non_isolated_cpus);
kfree(csa);
/*
@@ -2444,20 +2453,12 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
* @node: is this an allowed node?
* @gfp_mask: memory allocation flags
*
- * If we're in interrupt, yes, we can always allocate. If __GFP_THISNODE is
- * set, yes, we can always allocate. If node is in our task's mems_allowed,
- * yes. If it's not a __GFP_HARDWALL request and this node is in the nearest
- * hardwalled cpuset ancestor to this task's cpuset, yes. If the task has been
- * OOM killed and has access to memory reserves as specified by the TIF_MEMDIE
- * flag, yes.
+ * If we're in interrupt, yes, we can always allocate. If @node is set in
+ * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this
+ * node is set in the nearest hardwalled cpuset ancestor to current's cpuset,
+ * yes. If current has access to memory reserves due to TIF_MEMDIE, yes.
* Otherwise, no.
*
- * The __GFP_THISNODE placement logic is really handled elsewhere,
- * by forcibly using a zonelist starting at a specified node, and by
- * (in get_page_from_freelist()) refusing to consider the zones for
- * any node on the zonelist except the first. By the time any such
- * calls get to this routine, we should just shut up and say 'yes'.
- *
* GFP_USER allocations are marked with the __GFP_HARDWALL bit,
* and do not allow allocations outside the current tasks cpuset
* unless the task has been OOM killed as is marked TIF_MEMDIE.
@@ -2493,7 +2494,7 @@ int __cpuset_node_allowed(int node, gfp_t gfp_mask)
int allowed; /* is allocation in zone z allowed? */
unsigned long flags;
- if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
+ if (in_interrupt())
return 1;
if (node_isset(node, current->mems_allowed))
return 1;