[PATCH 2/6] timers/migration: Abstract out hierarchy to prepare for CPU capacity awareness

[Frederic Weisbecker <frederic@kernel.org>]

In order to prepare for separating out CPUs from different capacities in
distinct hierarchies, create a hierarchy structure that group setup
must rely upon.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 kernel/time/timer_migration.c | 100 +++++++++++++++++++++-------------
 kernel/time/timer_migration.h |  10 ++++
 2 files changed, 72 insertions(+), 38 deletions(-)

diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 1d0d3a4058d5..52e97b880b1c 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -102,7 +102,7 @@
  * active CPU/group information atomic_try_cmpxchg() is used instead and only
  * the per CPU tmigr_cpu->lock is held.
  *
- * During the setup of groups tmigr_level_list is required. It is protected by
+ * During the setup of groups, hier->level_list is required. It is protected by
  * @tmigr_mutex.
  *
  * When @timer_base->lock as well as tmigr related locks are required, the lock
@@ -416,13 +416,12 @@
  */
 
 static DEFINE_MUTEX(tmigr_mutex);
-static struct list_head *tmigr_level_list __read_mostly;
+
+static struct tmigr_hierarchy *hierarchy;
 
 static unsigned int tmigr_hierarchy_levels __read_mostly;
 static unsigned int tmigr_crossnode_level __read_mostly;
 
-static struct tmigr_group *tmigr_root;
-
 static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu);
 
 /*
@@ -1653,14 +1652,15 @@ static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
 	group->groupevt.ignore = true;
 }
 
-static struct tmigr_group *tmigr_get_group(int node, unsigned int lvl)
+static struct tmigr_group *tmigr_get_group(struct tmigr_hierarchy *hier,
+					   int node, unsigned int lvl)
 {
 	struct tmigr_group *tmp, *group = NULL;
 
 	lockdep_assert_held(&tmigr_mutex);
 
 	/* Try to attach to an existing group first */
-	list_for_each_entry(tmp, &tmigr_level_list[lvl], list) {
+	list_for_each_entry(tmp, &hier->level_list[lvl], list) {
 		/*
 		 * If @lvl is below the cross NUMA node level, check whether
 		 * this group belongs to the same NUMA node.
@@ -1694,14 +1694,15 @@ static struct tmigr_group *tmigr_get_group(int node, unsigned int lvl)
 	tmigr_init_group(group, lvl, node);
 
 	/* Setup successful. Add it to the hierarchy */
-	list_add(&group->list, &tmigr_level_list[lvl]);
+	list_add(&group->list, &hier->level_list[lvl]);
 	trace_tmigr_group_set(group);
 	return group;
 }
 
-static bool tmigr_init_root(struct tmigr_group *group, bool activate)
+static bool tmigr_init_root(struct tmigr_hierarchy *hier,
+			    struct tmigr_group *group, bool activate)
 {
-	if (!group->parent && group != tmigr_root) {
+	if (!group->parent && group != hier->root) {
 		/*
 		 * This is the new top-level, prepare its groupmask in advance
 		 * to avoid accidents where yet another new top-level is
@@ -1717,11 +1718,12 @@ static bool tmigr_init_root(struct tmigr_group *group, bool activate)
 
 }
 
-static void tmigr_connect_child_parent(struct tmigr_group *child,
+static void tmigr_connect_child_parent(struct tmigr_hierarchy *hier,
+				       struct tmigr_group *child,
 				       struct tmigr_group *parent,
 				       bool activate)
 {
-	if (tmigr_init_root(parent, activate)) {
+	if (tmigr_init_root(hier, parent, activate)) {
 		/*
 		 * The previous top level had prepared its groupmask already,
 		 * simply account it in advance as the first child. If some groups
@@ -1757,10 +1759,10 @@ static void tmigr_connect_child_parent(struct tmigr_group *child,
 	trace_tmigr_connect_child_parent(child);
 }
 
-static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
-			      struct tmigr_group *start, bool activate)
+static int tmigr_setup_groups(struct tmigr_hierarchy *hier, unsigned int cpu,
+			      unsigned int node, struct tmigr_group *start, bool activate)
 {
-	struct tmigr_group *group, *child, **stack;
+	struct tmigr_group *root = hier->root, *group, *child, **stack;
 	int i, top = 0, err = 0, start_lvl = 0;
 	bool root_mismatch = false;
 
@@ -1773,11 +1775,11 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 		start_lvl = start->level + 1;
 	}
 
-	if (tmigr_root)
-		root_mismatch = tmigr_root->numa_node != node;
+	if (root)
+		root_mismatch = root->numa_node != node;
 
 	for (i = start_lvl; i < tmigr_hierarchy_levels; i++) {
-		group = tmigr_get_group(node, i);
+		group = tmigr_get_group(hier, node, i);
 		if (IS_ERR(group)) {
 			err = PTR_ERR(group);
 			i--;
@@ -1799,7 +1801,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 		if (group->parent)
 			break;
 		if ((!root_mismatch || i >= tmigr_crossnode_level) &&
-		    list_is_singular(&tmigr_level_list[i]))
+		    list_is_singular(&hier->level_list[i]))
 			break;
 	}
 
@@ -1827,7 +1829,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 			tmc->tmgroup = group;
 			tmc->groupmask = BIT(group->num_children++);
 
-			tmigr_init_root(group, activate);
+			tmigr_init_root(hier, group, activate);
 
 			trace_tmigr_connect_cpu_parent(tmc);
 
@@ -1835,7 +1837,7 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 			continue;
 		} else {
 			child = stack[i - 1];
-			tmigr_connect_child_parent(child, group, activate);
+			tmigr_connect_child_parent(hier, child, group, activate);
 		}
 	}
 
@@ -1894,15 +1896,15 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 	}
 
 	/* Root update */
-	if (list_is_singular(&tmigr_level_list[top])) {
-		group = list_first_entry(&tmigr_level_list[top],
+	if (list_is_singular(&hier->level_list[top])) {
+		group = list_first_entry(&hier->level_list[top],
 					 typeof(*group), list);
 		WARN_ON_ONCE(group->parent);
-		if (tmigr_root) {
+		if (root) {
 			/* Old root should be the same or below */
-			WARN_ON_ONCE(tmigr_root->level > top);
+			WARN_ON_ONCE(root->level > top);
 		}
-		tmigr_root = group;
+		hier->root = group;
 	}
 out:
 	kfree(stack);
@@ -1910,18 +1912,48 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node,
 	return err;
 }
 
+static struct tmigr_hierarchy *tmigr_get_hierarchy(void)
+{
+	if (hierarchy)
+		return hierarchy;
+
+	hierarchy = kzalloc(sizeof(*hierarchy), GFP_KERNEL);
+	if (!hierarchy)
+		return ERR_PTR(-ENOMEM);
+
+	hierarchy->level_list = kzalloc_objs(struct list_head,
+					     tmigr_hierarchy_levels);
+	if (!hierarchy->level_list) {
+		kfree(hierarchy);
+		hierarchy = NULL;
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (int i = 0; i < tmigr_hierarchy_levels; i++)
+		INIT_LIST_HEAD(&hierarchy->level_list[i]);
+
+	return hierarchy;
+}
+
 static int tmigr_add_cpu(unsigned int cpu)
 {
-	struct tmigr_group *old_root = tmigr_root;
+	struct tmigr_hierarchy *hier;
+	struct tmigr_group *old_root;
 	int node = cpu_to_node(cpu);
 	int ret;
 
 	guard(mutex)(&tmigr_mutex);
 
-	ret = tmigr_setup_groups(cpu, node, NULL, false);
+	hier = tmigr_get_hierarchy();
+	if (IS_ERR(hier))
+		return PTR_ERR(hier);
+
+	old_root = hier->root;
+
+	ret = tmigr_setup_groups(hier, cpu, node, NULL, false);
 
 	/* Root has changed? Connect the old one to the new */
-	if (ret >= 0 && old_root && old_root != tmigr_root) {
+	if (ret >= 0 && old_root && old_root != hier->root) {
 		/*
 		 * The target CPU must never do the prepare work, except
 		 * on early boot when the boot CPU is the target. Otherwise
@@ -1935,7 +1967,7 @@ static int tmigr_add_cpu(unsigned int cpu)
 		 * otherwise the old root may not be active as expected.
 		 */
 		WARN_ON_ONCE(!per_cpu_ptr(&tmigr_cpu, raw_smp_processor_id())->available);
-		ret = tmigr_setup_groups(-1, old_root->numa_node, old_root, true);
+		ret = tmigr_setup_groups(hier, -1, old_root->numa_node, old_root, true);
 	}
 
 	return ret;
@@ -1970,7 +2002,7 @@ static int tmigr_cpu_prepare(unsigned int cpu)
 
 static int __init tmigr_init(void)
 {
-	unsigned int cpulvl, nodelvl, cpus_per_node, i;
+	unsigned int cpulvl, nodelvl, cpus_per_node;
 	unsigned int nnodes = num_possible_nodes();
 	unsigned int ncpus = num_possible_cpus();
 	int ret = -ENOMEM;
@@ -2017,14 +2049,6 @@ static int __init tmigr_init(void)
 	 */
 	tmigr_crossnode_level = cpulvl;
 
-	tmigr_level_list = kzalloc_objs(struct list_head,
-					tmigr_hierarchy_levels);
-	if (!tmigr_level_list)
-		goto err;
-
-	for (i = 0; i < tmigr_hierarchy_levels; i++)
-		INIT_LIST_HEAD(&tmigr_level_list[i]);
-
 	pr_info("Timer migration: %d hierarchy levels; %d children per group;"
 		" %d crossnode level\n",
 		tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP,
diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h
index 70879cde6fdd..77df422e5f9a 100644
--- a/kernel/time/timer_migration.h
+++ b/kernel/time/timer_migration.h
@@ -5,6 +5,16 @@
 /* Per group capacity. Must be a power of 2! */
 #define TMIGR_CHILDREN_PER_GROUP 8
 
+/**
+ * struct tmigr_hierarchy - a hierarchy associated to a given CPU capacity.
+ * @level_list:	Per level lists of tmigr groups
+ * @root:	The current root of the hierarchy
+ */
+struct tmigr_hierarchy {
+	struct list_head	*level_list;
+	struct tmigr_group	*root;
+};
+
 /**
  * struct tmigr_event - a timer event associated to a CPU
  * @nextevt:	The node to enqueue an event in the parent group queue
-- 
2.53.0