Re: [RFC PATCH v4 7/7] mm/demotion: Demote pages according to allocation fallback order

[Aneesh Kumar K.V]

Ying Huang <ying.huang@xxxxxxxxx> writes:

.....

> > > > 
>> > > > https://lore.kernel.org/lkml/69f2d063a15f8c4afb4688af7b7890f32af55391.camel@xxxxxxxxx/
>> > > > 
>> > > > That is, something like below,
>> > > > 
>> > > > static struct page *alloc_demote_page(struct page *page, unsigned long node)
>> > > > {
>> > > > 	struct page *page;
>> > > > 	nodemask_t allowed_mask;
>> > > > 	struct migration_target_control mtc = {
>> > > > 		/*
>> > > > 		 * Allocate from 'node', or fail quickly and quietly.
>> > > > 		 * When this happens, 'page' will likely just be discarded
>> > > > 		 * instead of migrated.
>> > > > 		 */
>> > > > 		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
>> > > > 			    __GFP_THISNODE  | __GFP_NOWARN |
>> > > > 			    __GFP_NOMEMALLOC | GFP_NOWAIT,
>> > > > 		.nid = node
>> > > > 	};
>> > > > 
>> > > > 	page = alloc_migration_target(page, (unsigned long)&mtc);
>> > > > 	if (page)
>> > > > 		return page;
>> > > > 
>> > > > 	mtc.gfp_mask &= ~__GFP_THISNODE;
>> > > > 	mtc.nmask = &allowed_mask;
>> > > > 
>> > > > 	return alloc_migration_target(page, (unsigned long)&mtc);
>> > > > }
>> > > 
>> > > I skipped doing this in v5 because I was not sure this is really what we
>> > > want.
>> > 
>> > I think so.  And this is the original behavior.  We should keep the
>> > original behavior as much as possible, then make changes if necessary.
>> > 
>> 
>> That is the reason I split the new page allocation as a separate patch. 
>> Previous discussion on this topic didn't conclude on whether we really 
>> need to do the above or not
>> https://lore.kernel.org/lkml/CAAPL-u9endrWf_aOnPENDPdvT-2-YhCAeJ7ONGckGnXErTLOfQ@xxxxxxxxxxxxxx/
>
> Please check the later email in the thread you referenced.  Both Wei and
> me agree that the use case needs to be supported.  We just didn't reach
> concensus about how to implement it.  If you think Wei's solution is
> better (referenced as below), you can try to do that too.  Although I
> think my proposed implementation is much simpler.

How about the below details

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 79bd8d26feb2..cd6e71f702ad 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -21,6 +21,7 @@ void node_remove_from_memory_tier(int node);
 int node_get_memory_tier_id(int node);
 int node_set_memory_tier(int node, int tier);
 int node_reset_memory_tier(int node, int tier);
+void node_get_allowed_targets(int node, nodemask_t *targets);
 #else
 #define numa_demotion_enabled	false
 static inline int next_demotion_node(int node)
@@ -28,6 +29,10 @@ static inline int next_demotion_node(int node)
 	return NUMA_NO_NODE;
 }
 
+static inline void node_get_allowed_targets(int node, nodemask_t *targets)
+{
+	*targets = NODE_MASK_NONE;
+}
 #endif	/* CONFIG_TIERED_MEMORY */
 
 #endif
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index b4e72b672d4d..592d939ec28d 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -18,6 +18,7 @@ struct memory_tier {
 
 struct demotion_nodes {
 	nodemask_t preferred;
+	nodemask_t allowed;
 };
 
 #define to_memory_tier(device) container_of(device, struct memory_tier, dev)
@@ -378,6 +379,25 @@ int node_set_memory_tier(int node, int tier)
 }
 EXPORT_SYMBOL_GPL(node_set_memory_tier);
 
+void node_get_allowed_targets(int node, nodemask_t *targets)
+{
+	/*
+	 * node_demotion[] is updated without excluding this
+	 * function from running.
+	 *
+	 * If any node is moving to lower tiers then modifications
+	 * in node_demotion[] are still valid for this node, if any
+	 * node is moving to higher tier then moving node may be
+	 * used once for demotion which should be ok so rcu should
+	 * be enough here.
+	 */
+	rcu_read_lock();
+
+	*targets = node_demotion[node].allowed;
+
+	rcu_read_unlock();
+}
+
 /**
  * next_demotion_node() - Get the next node in the demotion path
  * @node: The starting node to lookup the next node
@@ -437,8 +457,10 @@ static void __disable_all_migrate_targets(void)
 {
 	int node;
 
-	for_each_node_mask(node, node_states[N_MEMORY])
+	for_each_node_mask(node, node_states[N_MEMORY]) {
 		node_demotion[node].preferred = NODE_MASK_NONE;
+		node_demotion[node].allowed = NODE_MASK_NONE;
+	}
 }
 
 static void disable_all_migrate_targets(void)
@@ -465,7 +487,7 @@ static void establish_migration_targets(void)
 	struct demotion_nodes *nd;
 	int target = NUMA_NO_NODE, node;
 	int distance, best_distance;
-	nodemask_t used;
+	nodemask_t used, allowed = NODE_MASK_NONE;
 
 	if (!node_demotion)
 		return;
@@ -511,6 +533,29 @@ static void establish_migration_targets(void)
 			}
 		} while (1);
 	}
+	/*
+	 * Now build the allowed mask for each node collecting node mask from
+	 * all memory tier below it. This allows us to fallback demotion page
+	 * allocation to a set of nodes that is closer the above selected
+	 * perferred node.
+	 */
+	list_for_each_entry(memtier, &memory_tiers, list)
+		nodes_or(allowed, allowed, memtier->nodelist);
+	/*
+	 * Removes nodes not yet in N_MEMORY.
+	 */
+	nodes_and(allowed, node_states[N_MEMORY], allowed);
+
+	list_for_each_entry(memtier, &memory_tiers, list) {
+		/*
+		 * Keep removing current tier from allowed nodes,
+		 * This will remove all nodes in current and above
+		 * memory tier from the allowed mask.
+		 */
+		nodes_andnot(allowed, allowed, memtier->nodelist);
+		for_each_node_mask(node, memtier->nodelist)
+			node_demotion[node].allowed = allowed;
+	}
 }
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3a8f78277f99..b0792d838efb 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1460,19 +1460,32 @@ static void folio_check_dirty_writeback(struct folio *folio,
 		mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
 }
 
-static struct page *alloc_demote_page(struct page *page, unsigned long node)
+static struct page *alloc_demote_page(struct page *page, unsigned long private)
 {
-	struct migration_target_control mtc = {
-		/*
-		 * Allocate from 'node', or fail quickly and quietly.
-		 * When this happens, 'page' will likely just be discarded
-		 * instead of migrated.
-		 */
-		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
-			    __GFP_THISNODE  | __GFP_NOWARN |
-			    __GFP_NOMEMALLOC | GFP_NOWAIT,
-		.nid = node
-	};
+	struct page *target_page;
+	nodemask_t *allowed_mask;
+	struct migration_target_control *mtc;
+
+	mtc = (struct migration_target_control *)private;
+
+	allowed_mask = mtc->nmask;
+	/*
+	 * make sure we allocate from the target node first also trying to
+	 * reclaim pages from the target node via kswapd if we are low on
+	 * free memory on target node. If we don't do this and if we have low
+	 * free memory on the target memtier, we would start allocating pages
+	 * from higher memory tiers without even forcing a demotion of cold
+	 * pages from the target memtier. This can result in the kernel placing
+	 * hotpages in higher memory tiers.
+	 */
+	mtc->nmask = NULL;
+	mtc->gfp_mask |= __GFP_THISNODE;
+	target_page = alloc_migration_target(page, (unsigned long)&mtc);
+	if (target_page)
+		return target_page;
+
+	mtc->gfp_mask &= ~__GFP_THISNODE;
+	mtc->nmask = allowed_mask;
 
 	return alloc_migration_target(page, (unsigned long)&mtc);
 }
@@ -1487,6 +1500,19 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
 {
 	int target_nid = next_demotion_node(pgdat->node_id);
 	unsigned int nr_succeeded;
+	nodemask_t allowed_mask;
+
+	struct migration_target_control mtc = {
+		/*
+		 * Allocate from 'node', or fail quickly and quietly.
+		 * When this happens, 'page' will likely just be discarded
+		 * instead of migrated.
+		 */
+		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN |
+			__GFP_NOMEMALLOC | GFP_NOWAIT,
+		.nid = target_nid,
+		.nmask = &allowed_mask
+	};
 
 	if (list_empty(demote_pages))
 		return 0;
@@ -1494,10 +1520,12 @@ static unsigned int demote_page_list(struct list_head *demote_pages,
 	if (target_nid == NUMA_NO_NODE)
 		return 0;
 
+	node_get_allowed_targets(pgdat->node_id, &allowed_mask);
+
 	/* Demotion ignores all cpuset and mempolicy settings */
 	migrate_pages(demote_pages, alloc_demote_page, NULL,
-			    target_nid, MIGRATE_ASYNC, MR_DEMOTION,
-			    &nr_succeeded);
+		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
+		      &nr_succeeded);
 
 	if (current_is_kswapd())
 		__count_vm_events(PGDEMOTE_KSWAPD, nr_succeeded);