mm/demotion: build demotion targets based on explicit memory tiers

This patch switch the demotion target building logic to use memory tiers
instead of NUMA distance.  All N_MEMORY NUMA nodes will be placed in the
default memory tier and additional memory tiers will be added by drivers
like dax kmem.

This patch builds the demotion target for a NUMA node by looking at all
memory tiers below the tier to which the NUMA node belongs.  The closest
node in the immediately following memory tier is used as a demotion
target.

Since we are now only building demotion target for N_MEMORY NUMA nodes the
CPU hotplug calls are removed in this patch.

Link: https://lkml.kernel.org/r/20220818131042.113280-6-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Wei Xu <weixugc@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hesham Almatary <hesham.almatary@huawei.com>
Cc: Jagdish Gediya <jvgediya.oss@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 0 insertions, 394 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 30477cf4868d..2a2329bf7c1a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2198,398 +2198,4 @@ out:
 	return 0;
 }
 #endif /* CONFIG_NUMA_BALANCING */
-
-/*
- * node_demotion[] example:
- *
- * Consider a system with two sockets.  Each socket has
- * three classes of memory attached: fast, medium and slow.
- * Each memory class is placed in its own NUMA node.  The
- * CPUs are placed in the node with the "fast" memory.  The
- * 6 NUMA nodes (0-5) might be split among the sockets like
- * this:
- *
- *	Socket A: 0, 1, 2
- *	Socket B: 3, 4, 5
- *
- * When Node 0 fills up, its memory should be migrated to
- * Node 1.  When Node 1 fills up, it should be migrated to
- * Node 2.  The migration path start on the nodes with the
- * processors (since allocations default to this node) and
- * fast memory, progress through medium and end with the
- * slow memory:
- *
- *	0 -> 1 -> 2 -> stop
- *	3 -> 4 -> 5 -> stop
- *
- * This is represented in the node_demotion[] like this:
- *
- *	{  nr=1, nodes[0]=1 }, // Node 0 migrates to 1
- *	{  nr=1, nodes[0]=2 }, // Node 1 migrates to 2
- *	{  nr=0, nodes[0]=-1 }, // Node 2 does not migrate
- *	{  nr=1, nodes[0]=4 }, // Node 3 migrates to 4
- *	{  nr=1, nodes[0]=5 }, // Node 4 migrates to 5
- *	{  nr=0, nodes[0]=-1 }, // Node 5 does not migrate
- *
- * Moreover some systems may have multiple slow memory nodes.
- * Suppose a system has one socket with 3 memory nodes, node 0
- * is fast memory type, and node 1/2 both are slow memory
- * type, and the distance between fast memory node and slow
- * memory node is same. So the migration path should be:
- *
- *	0 -> 1/2 -> stop
- *
- * This is represented in the node_demotion[] like this:
- *	{ nr=2, {nodes[0]=1, nodes[1]=2} }, // Node 0 migrates to node 1 and node 2
- *	{ nr=0, nodes[0]=-1, }, // Node 1 dose not migrate
- *	{ nr=0, nodes[0]=-1, }, // Node 2 does not migrate
- */
-
-/*
- * Writes to this array occur without locking.  Cycles are
- * not allowed: Node X demotes to Y which demotes to X...
- *
- * If multiple reads are performed, a single rcu_read_lock()
- * must be held over all reads to ensure that no cycles are
- * observed.
- */
-#define DEFAULT_DEMOTION_TARGET_NODES 15
-
-#if MAX_NUMNODES < DEFAULT_DEMOTION_TARGET_NODES
-#define DEMOTION_TARGET_NODES	(MAX_NUMNODES - 1)
-#else
-#define DEMOTION_TARGET_NODES	DEFAULT_DEMOTION_TARGET_NODES
-#endif
-
-struct demotion_nodes {
-	unsigned short nr;
-	short nodes[DEMOTION_TARGET_NODES];
-};
-
-static struct demotion_nodes *node_demotion __read_mostly;
-
-/**
- * next_demotion_node() - Get the next node in the demotion path
- * @node: The starting node to lookup the next node
- *
- * Return: node id for next memory node in the demotion path hierarchy
- * from @node; NUMA_NO_NODE if @node is terminal.  This does not keep
- * @node online or guarantee that it *continues* to be the next demotion
- * target.
- */
-int next_demotion_node(int node)
-{
-	struct demotion_nodes *nd;
-	unsigned short target_nr, index;
-	int target;
-
-	if (!node_demotion)
-		return NUMA_NO_NODE;
-
-	nd = &node_demotion[node];
-
-	/*
-	 * node_demotion[] is updated without excluding this
-	 * function from running.  RCU doesn't provide any
-	 * compiler barriers, so the READ_ONCE() is required
-	 * to avoid compiler reordering or read merging.
-	 *
-	 * Make sure to use RCU over entire code blocks if
-	 * node_demotion[] reads need to be consistent.
-	 */
-	rcu_read_lock();
-	target_nr = READ_ONCE(nd->nr);
-
-	switch (target_nr) {
-	case 0:
-		target = NUMA_NO_NODE;
-		goto out;
-	case 1:
-		index = 0;
-		break;
-	default:
-		/*
-		 * If there are multiple target nodes, just select one
-		 * target node randomly.
-		 *
-		 * In addition, we can also use round-robin to select
-		 * target node, but we should introduce another variable
-		 * for node_demotion[] to record last selected target node,
-		 * that may cause cache ping-pong due to the changing of
-		 * last target node. Or introducing per-cpu data to avoid
-		 * caching issue, which seems more complicated. So selecting
-		 * target node randomly seems better until now.
-		 */
-		index = get_random_int() % target_nr;
-		break;
-	}
-
-	target = READ_ONCE(nd->nodes[index]);
-
-out:
-	rcu_read_unlock();
-	return target;
-}
-
-/* Disable reclaim-based migration. */
-static void __disable_all_migrate_targets(void)
-{
-	int node, i;
-
-	if (!node_demotion)
-		return;
-
-	for_each_online_node(node) {
-		node_demotion[node].nr = 0;
-		for (i = 0; i < DEMOTION_TARGET_NODES; i++)
-			node_demotion[node].nodes[i] = NUMA_NO_NODE;
-	}
-}
-
-static void disable_all_migrate_targets(void)
-{
-	__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.
-	 */
-	synchronize_rcu();
-}
-
-/*
- * 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 best_distance)
-{
-	int migration_target, index, val;
-	struct demotion_nodes *nd;
-
-	if (!node_demotion)
-		return NUMA_NO_NODE;
-
-	nd = &node_demotion[node];
-
-	migration_target = find_next_best_node(node, used);
-	if (migration_target == NUMA_NO_NODE)
-		return NUMA_NO_NODE;
-
-	/*
-	 * If the node has been set a migration target node before,
-	 * which means it's the best distance between them. Still
-	 * check if this node can be demoted to other target nodes
-	 * if they have a same best distance.
-	 */
-	if (best_distance != -1) {
-		val = node_distance(node, migration_target);
-		if (val > best_distance)
-			goto out_clear;
-	}
-
-	index = nd->nr;
-	if (WARN_ONCE(index >= DEMOTION_TARGET_NODES,
-		      "Exceeds maximum demotion target nodes\n"))
-		goto out_clear;
-
-	nd->nodes[index] = migration_target;
-	nd->nr++;
-
-	return migration_target;
-out_clear:
-	node_clear(migration_target, *used);
-	return NUMA_NO_NODE;
-}
-
-/*
- * 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. Also one node can
- * be migrated to multiple nodes if the target nodes all have
- * a same best-distance against the source node.
- *
- * 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.
- */
-static void __set_migration_target_nodes(void)
-{
-	nodemask_t next_pass;
-	nodemask_t this_pass;
-	nodemask_t used_targets = NODE_MASK_NONE;
-	int node, best_distance;
-
-	/*
-	 * 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();
-
-	/*
-	 * 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'.  Do this only
-	 * once per pass so that multiple source nodes can
-	 * share a target node.
-	 *
-	 * 'used_targets' will become unavailable in future
-	 * passes.  This limits some opportunities for
-	 * multiple source nodes to share a destination.
-	 */
-	nodes_or(used_targets, used_targets, this_pass);
-
-	for_each_node_mask(node, this_pass) {
-		best_distance = -1;
-
-		/*
-		 * Try to set up the migration path for the node, and the target
-		 * migration nodes can be multiple, so doing a loop to find all
-		 * the target nodes if they all have a best node distance.
-		 */
-		do {
-			int target_node =
-				establish_migrate_target(node, &used_targets,
-							 best_distance);
-
-			if (target_node == NUMA_NO_NODE)
-				break;
-
-			if (best_distance == -1)
-				best_distance = node_distance(node, target_node);
-
-			/*
-			 * Visit targets from this pass in the next pass.
-			 * Eventually, every node will have been part of
-			 * a pass, and will become set in 'used_targets'.
-			 */
-			node_set(target_node, next_pass);
-		} while (1);
-	}
-	/*
-	 * 'next_pass' contains nodes which became migration
-	 * targets in this pass.  Make additional passes until
-	 * no more migrations targets are available.
-	 */
-	if (!nodes_empty(next_pass))
-		goto again;
-}
-
-/*
- * For callers that do not hold get_online_mems() already.
- */
-void set_migration_target_nodes(void)
-{
-	get_online_mems();
-	__set_migration_target_nodes();
-	put_online_mems();
-}
-
-/*
- * This leaves migrate-on-reclaim transiently disabled between
- * the MEM_GOING_OFFLINE and MEM_OFFLINE events.  This runs
- * whether reclaim-based migration is enabled or not, which
- * ensures that the user can turn reclaim-based migration at
- * any time without needing to recalculate migration targets.
- *
- * These callbacks already hold get_online_mems().  That is why
- * __set_migration_target_nodes() can be used as opposed to
- * set_migration_target_nodes().
- */
-#ifdef CONFIG_MEMORY_HOTPLUG
-static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
-						 unsigned long action, void *_arg)
-{
-	struct memory_notify *arg = _arg;
-
-	/*
-	 * Only update the node migration order when a node is
-	 * changing status, like online->offline.  This avoids
-	 * the overhead of synchronize_rcu() in most cases.
-	 */
-	if (arg->status_change_nid < 0)
-		return notifier_from_errno(0);
-
-	switch (action) {
-	case MEM_GOING_OFFLINE:
-		/*
-		 * Make sure there are not transient states where
-		 * an offline node is a migration target.  This
-		 * will leave migration disabled until the offline
-		 * completes and the MEM_OFFLINE case below runs.
-		 */
-		disable_all_migrate_targets();
-		break;
-	case MEM_OFFLINE:
-	case MEM_ONLINE:
-		/*
-		 * Recalculate the target nodes once the node
-		 * reaches its final state (online or offline).
-		 */
-		__set_migration_target_nodes();
-		break;
-	case MEM_CANCEL_OFFLINE:
-		/*
-		 * MEM_GOING_OFFLINE disabled all the migration
-		 * targets.  Reenable them.
-		 */
-		__set_migration_target_nodes();
-		break;
-	case MEM_GOING_ONLINE:
-	case MEM_CANCEL_ONLINE:
-		break;
-	}
-
-	return notifier_from_errno(0);
-}
-#endif
-
-void __init migrate_on_reclaim_init(void)
-{
-	node_demotion = kcalloc(nr_node_ids,
-				sizeof(struct demotion_nodes),
-				GFP_KERNEL);
-	WARN_ON(!node_demotion);
-#ifdef CONFIG_MEMORY_HOTPLUG
-	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
-#endif
-	/*
-	 * At this point, all numa nodes with memory/CPus have their state
-	 * properly set, so we can build the demotion order now.
-	 * Let us hold the cpu_hotplug lock just, as we could possibily have
-	 * CPU hotplug events during boot.
-	 */
-	cpus_read_lock();
-	set_migration_target_nodes();
-	cpus_read_unlock();
-}
 #endif /* CONFIG_NUMA */
-
-