@@ -34,6 +34,8 @@
*/
extern struct static_key_false cpusets_pre_enable_key;
extern struct static_key_false cpusets_enabled_key;
+extern struct static_key_false cpusets_insane_config_key;
+
static inline bool cpusets_enabled(void)
{
return static_branch_unlikely(&cpusets_enabled_key);
@@ -51,6 +53,19 @@ static inline void cpuset_dec(void)
static_branch_dec_cpuslocked(&cpusets_pre_enable_key);
}
+/*
+ * This will get enabled whenever a cpuset configuration is considered
+ * unsupportable in general. E.g. movable only node which cannot satisfy
+ * any non movable allocations (see update_nodemask). Page allocator
+ * needs to make additional checks for those configurations and this
+ * check is meant to guard those checks without any overhead for sane
+ * configurations.
+ */
+static inline bool cpusets_insane_config(void)
+{
+ return static_branch_unlikely(&cpusets_insane_config_key);
+}
+
extern int cpuset_init(void);
extern void cpuset_init_smp(void);
extern void cpuset_force_rebuild(void);
@@ -167,6 +182,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
static inline bool cpusets_enabled(void) { return false; }
+static inline bool cpusets_insane_config(void) { return false; }
+
static inline int cpuset_init(void) { return 0; }
static inline void cpuset_init_smp(void) {}
@@ -1220,6 +1220,28 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
#define for_each_zone_zonelist(zone, z, zlist, highidx) \
for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL)
+/* Whether the 'nodes' are all movable nodes */
+static inline bool movable_only_nodes(nodemask_t *nodes)
+{
+ struct zonelist *zonelist;
+ struct zoneref *z;
+ int nid;
+
+ if (nodes_empty(*nodes))
+ return false;
+
+ /*
+ * We can chose arbitrary node from the nodemask to get a
+ * zonelist as they are interlinked. We just need to find
+ * at least one zone that can satisfy kernel allocations.
+ */
+ nid = first_node(*nodes);
+ zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK];
+ z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes);
+ return (!z->zone) ? true : false;
+}
+
+
#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif
@@ -69,6 +69,13 @@
DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
+/*
+ * There could be abnormal cpuset configurations for cpu or memory
+ * node binding, add this key to provide a quick low-cost judgement
+ * of the situation.
+ */
+DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key);
+
/* See "Frequency meter" comments, below. */
struct fmeter {
@@ -370,6 +377,17 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);
static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);
+static inline void check_insane_mems_config(nodemask_t *nodes)
+{
+ if (!cpusets_insane_config() &&
+ movable_only_nodes(nodes)) {
+ static_branch_enable(&cpusets_insane_config_key);
+ pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n"
+ "Cpuset allocations might fail even with a lot of memory available.\n",
+ nodemask_pr_args(nodes));
+ }
+}
+
/*
* Cgroup v2 behavior is used on the "cpus" and "mems" control files when
* on default hierarchy or when the cpuset_v2_mode flag is set by mounting
@@ -1868,6 +1886,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
if (retval < 0)
goto done;
+ check_insane_mems_config(&trialcs->mems_allowed);
+
spin_lock_irq(&callback_lock);
cs->mems_allowed = trialcs->mems_allowed;
spin_unlock_irq(&callback_lock);
@@ -3171,6 +3191,9 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
mems_updated = !nodes_equal(new_mems, cs->effective_mems);
+ if (mems_updated)
+ check_insane_mems_config(&new_mems);
+
if (is_in_v2_mode())
hotplug_update_tasks(cs, &new_cpus, &new_mems,
cpus_updated, mems_updated);
@@ -4914,6 +4914,19 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
if (!ac->preferred_zoneref->zone)
goto nopage;
+ /*
+ * Check for insane configurations where the cpuset doesn't contain
+ * any suitable zone to satisfy the request - e.g. non-movable
+ * GFP_HIGHUSER allocations from MOVABLE nodes only.
+ */
+ if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) {
+ struct zoneref *z = first_zones_zonelist(ac->zonelist,
+ ac->highest_zoneidx,
+ &cpuset_current_mems_allowed);
+ if (!z->zone)
+ goto nopage;
+ }
+
if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);