mm: numa: Add fault driven placement and migration
NOTE: This patch is based on "sched, numa, mm: Add fault driven
placement and migration policy" but as it throws away all the policy
to just leave a basic foundation I had to drop the signed-offs-by.
This patch creates a bare-bones method for setting PTEs pte_numa in the
context of the scheduler that when faulted later will be faulted onto the
node the CPU is running on. In itself this does nothing useful but any
placement policy will fundamentally depend on receiving hints on placement
from fault context and doing something intelligent about it.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 31f8a3a..ed8638c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -398,6 +398,17 @@
#ifdef CONFIG_CPUMASK_OFFSTACK
struct cpumask cpumask_allocation;
#endif
+#ifdef CONFIG_NUMA_BALANCING
+ /*
+ * numa_next_scan is the next time when the PTEs will me marked
+ * pte_numa to gather statistics and migrate pages to new nodes
+ * if necessary
+ */
+ unsigned long numa_next_scan;
+
+ /* numa_scan_seq prevents two threads setting pte_numa */
+ int numa_scan_seq;
+#endif
struct uprobes_state uprobes_state;
};
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a0..844af5b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1479,6 +1479,14 @@
short il_next;
short pref_node_fork;
#endif
+#ifdef CONFIG_NUMA_BALANCING
+ int numa_scan_seq;
+ int numa_migrate_seq;
+ unsigned int numa_scan_period;
+ u64 node_stamp; /* migration stamp */
+ struct callback_head numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
+
struct rcu_head rcu;
/*
@@ -1553,6 +1561,14 @@
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
+#ifdef CONFIG_NUMA_BALANCING
+extern void task_numa_fault(int node, int pages);
+#else
+static inline void task_numa_fault(int node, int pages)
+{
+}
+#endif
+
/*
* Priority of a process goes from 0..MAX_PRIO-1, valid RT
* priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
@@ -1990,6 +2006,10 @@
};
extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_settle_count;
+
#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;