Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> writes:
> +/*
> + * Find an automatic demotion target for 'node'.
> + * Failing here is OK. It might just indicate
> + * being at the end of a chain.
> + */
> +static int establish_migrate_target(int node, nodemask_t *used)
> +{
> + int migration_target;
> +
> + /*
> + * Can not set a migration target on a
> + * node with it already set.
> + *
> + * No need for READ_ONCE() here since this
> + * in the write path for node_demotion[].
> + * This should be the only thread writing.
> + */
> + if (node_demotion[node] != NUMA_NO_NODE)
> + return NUMA_NO_NODE;
> +
> + migration_target = find_next_best_node(node, used);
> + if (migration_target == NUMA_NO_NODE)
> + return NUMA_NO_NODE;
> +
> + node_demotion[node] = migration_target;
> +
> + return migration_target;
> +}
> +
> +/*
> + * When memory fills up on a node, memory contents can be
> + * automatically migrated to another node instead of
> + * discarded at reclaim.
> + *
> + * Establish a "migration path" which will start at nodes
> + * with CPUs and will follow the priorities used to build the
> + * page allocator zonelists.
> + *
> + * The difference here is that cycles must be avoided. If
> + * node0 migrates to node1, then neither node1, nor anything
> + * node1 migrates to can migrate to node0.
> + *
> + * This function can run simultaneously with readers of
> + * node_demotion[]. However, it can not run simultaneously
> + * with itself. Exclusion is provided by memory hotplug events
> + * being single-threaded.
> + */
> +void set_migration_target_nodes(void)
> +{
> + nodemask_t next_pass = NODE_MASK_NONE;
> + nodemask_t this_pass = NODE_MASK_NONE;
> + nodemask_t used_targets = NODE_MASK_NONE;
> + int node;
> +
> + get_online_mems();
> + /*
> + * Avoid any oddities like cycles that could occur
> + * from changes in the topology. This will leave
> + * a momentary gap when migration is disabled.
> + */
> + disable_all_migrate_targets();
> +
> + /*
> + * Ensure that the "disable" is visible across the system.
> + * Readers will see either a combination of before+disable
> + * state or disable+after. They will never see before and
> + * after state together.
> + *
> + * The before+after state together might have cycles and
> + * could cause readers to do things like loop until this
> + * function finishes. This ensures they can only see a
> + * single "bad" read and would, for instance, only loop
> + * once.
> + */
> + smp_wmb();
> +
> + /*
> + * Allocations go close to CPUs, first. Assume that
> + * the migration path starts at the nodes with CPUs.
> + */
> + next_pass = node_states[N_CPU];
> +again:
> + this_pass = next_pass;
> + next_pass = NODE_MASK_NONE;
> + /*
> + * To avoid cycles in the migration "graph", ensure
> + * that migration sources are not future targets by
> + * setting them in 'used_targets'.
> + *
> + * But, do this only once per pass so that multiple
> + * source nodes can share a target node.
establish_migrate_target() calls find_next_best_node(), which will set
target_node in used_targets. So it seems that the nodes_or() below is
only necessary to initialize used_targets, and multiple source nodes
cannot share one target node in current implementation.
Best Regards,
Huang, Ying
> + */
> + nodes_or(used_targets, used_targets, this_pass);
> + for_each_node_mask(node, this_pass) {
> + int target_node = establish_migrate_target(node, &used_targets);
> +
> + if (target_node == NUMA_NO_NODE)
> + continue;
> +
> + /* Visit targets from this pass in the next pass: */
> + node_set(target_node, next_pass);
> + }
> + /* Is another pass necessary? */
> + if (!nodes_empty(next_pass))
> + goto again;
> +
> + put_online_mems();
> +}
