mm: hugetlb: eliminate memory-less nodes handling

The memory-notify-based approach aims to handle meory-less nodes, however,
it just adds the complexity of code as pointed by David in thread [1].
The handling of memory-less nodes is introduced by commit 4faf8d950ec4
("hugetlb: handle memory hot-plug events").  >From its commit message, we
cannot find any necessity of handling this case.  So, we can simply
register/unregister sysfs entries in register_node/unregister_node to
simlify the code.

BTW, hotplug callback added because in hugetlb_register_all_nodes() we
register sysfs nodes only for N_MEMORY nodes, seeing commit 9b5e5d0fdc91,
which said it was a preparation for handling memory-less nodes via memory
hotplug.  Since we want to remove memory hotplug, so make sure we only
register per-node sysfs for online (N_ONLINE) nodes in
hugetlb_register_all_nodes().

https://lore.kernel.org/linux-mm/60933ffc-b850-976c-78a0-0ee6e0ea9ef0@redhat.com/ [1]
Link: https://lkml.kernel.org/r/20220914072603.60293-3-songmuchun@bytedance.com
Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/drivers/base/node.c b/drivers/base/node.c
index ed391cb..80b1e91 100644 (file)
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -20,6 +20,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
+#include <linux/hugetlb.h>
 
 static struct bus_type node_subsys = {
        .name = "node",
@@ -608,10 +609,12 @@ static int register_node(struct node *node, int num)
        node->dev.groups = node_dev_groups;
        error = device_register(&node->dev);
 
-       if (error)
+       if (error) {
                put_device(&node->dev);
-       else
+       } else {
+               hugetlb_register_node(node);
                compaction_register_node(node);
+       }
 
        return error;
 }
@@ -625,6 +628,7 @@ static int register_node(struct node *node, int num)
  */
 void unregister_node(struct node *node)
 {
+       hugetlb_unregister_node(node);
        compaction_unregister_node(node);
        node_remove_accesses(node);
        node_remove_caches(node);

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 57e7295..6d7f397 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -16,6 +16,7 @@
 struct ctl_table;
 struct user_struct;
 struct mmu_gather;
+struct node;
 
 #ifndef is_hugepd
 typedef struct { unsigned long pd; } hugepd_t;
@@ -935,6 +936,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 }
 #endif
 
+#ifdef CONFIG_NUMA
+void hugetlb_register_node(struct node *node);
+void hugetlb_unregister_node(struct node *node);
+#endif
+
 #else  /* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
@@ -1109,6 +1115,14 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
                                   pte_t *ptep, pte_t pte)
 {
 }
+
+static inline void hugetlb_register_node(struct node *node)
+{
+}
+
+static inline void hugetlb_unregister_node(struct node *node)
+{
+}
 #endif /* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 397f298..0b1ab5a 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3871,24 +3871,8 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
        return 0;
 }
 
-static void __init hugetlb_sysfs_init(void)
-{
-       struct hstate *h;
-       int err;
-
-       hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
-       if (!hugepages_kobj)
-               return;
-
-       for_each_hstate(h) {
-               err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
-                                        hstate_kobjs, &hstate_attr_group);
-               if (err)
-                       pr_err("HugeTLB: Unable to add hstate %s", h->name);
-       }
-}
-
 #ifdef CONFIG_NUMA
+static bool hugetlb_sysfs_initialized __ro_after_init;
 
 /*
  * node_hstate/s - associate per node hstate attributes, via their kobjects,
@@ -3944,7 +3928,7 @@ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
  * Unregister hstate attributes from a single node device.
  * No-op if no hstate attributes attached.
  */
-static void hugetlb_unregister_node(struct node *node)
+void hugetlb_unregister_node(struct node *node)
 {
        struct hstate *h;
        struct node_hstate *nhs = &node_hstates[node->dev.id];
@@ -3974,12 +3958,15 @@ static void hugetlb_unregister_node(struct node *node)
  * Register hstate attributes for a single node device.
  * No-op if attributes already registered.
  */
-static void hugetlb_register_node(struct node *node)
+void hugetlb_register_node(struct node *node)
 {
        struct hstate *h;
        struct node_hstate *nhs = &node_hstates[node->dev.id];
        int err;
 
+       if (!hugetlb_sysfs_initialized)
+               return;
+
        if (nhs->hugepages_kobj)
                return;         /* already allocated */
 
@@ -4001,23 +3988,6 @@ static void hugetlb_register_node(struct node *node)
        }
 }
 
-static int __meminit hugetlb_memory_callback(struct notifier_block *self,
-                                            unsigned long action, void *arg)
-{
-       struct memory_notify *mnb = arg;
-       int nid = mnb->status_change_nid;
-
-       if (nid == NUMA_NO_NODE)
-               return NOTIFY_DONE;
-
-       if (action == MEM_GOING_ONLINE)
-               hugetlb_register_node(node_devices[nid]);
-       else if (action == MEM_CANCEL_ONLINE || action == MEM_OFFLINE)
-               hugetlb_unregister_node(node_devices[nid]);
-
-       return NOTIFY_OK;
-}
-
 /*
  * hugetlb init time:  register hstate attributes for all registered node
  * devices of nodes that have memory.  All on-line nodes should have
@@ -4027,11 +3997,8 @@ static void __init hugetlb_register_all_nodes(void)
 {
        int nid;
 
-       get_online_mems();
-       hotplug_memory_notifier(hugetlb_memory_callback, 0);
-       for_each_node_state(nid, N_MEMORY)
+       for_each_online_node(nid)
                hugetlb_register_node(node_devices[nid]);
-       put_online_mems();
 }
 #else  /* !CONFIG_NUMA */
 
@@ -4055,6 +4022,28 @@ static inline __init void hugetlb_cma_check(void)
 }
 #endif
 
+static void __init hugetlb_sysfs_init(void)
+{
+       struct hstate *h;
+       int err;
+
+       hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
+       if (!hugepages_kobj)
+               return;
+
+       for_each_hstate(h) {
+               err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
+                                        hstate_kobjs, &hstate_attr_group);
+               if (err)
+                       pr_err("HugeTLB: Unable to add hstate %s", h->name);
+       }
+
+#ifdef CONFIG_NUMA
+       hugetlb_sysfs_initialized = true;
+#endif
+       hugetlb_register_all_nodes();
+}
+
 static int __init hugetlb_init(void)
 {
        int i;
@@ -4109,7 +4098,6 @@ static int __init hugetlb_init(void)
        report_hugepages();
 
        hugetlb_sysfs_init();
-       hugetlb_register_all_nodes();
        hugetlb_cgroup_file_init();
 
 #ifdef CONFIG_SMP