[PATCH v2 3/3] mm: hugetlb: add hugetlb_free_vmemmap sysctl

[Muchun Song]

We must add "hugetlb_free_vmemmap=on" to boot cmdline and reboot the
server to enable the feature of freeing vmemmap pages of HugeTLB
pages. Rebooting usually taske a long time. Add a sysctl to enable
the feature at runtime and do not need to reboot.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
 Documentation/admin-guide/sysctl/vm.rst | 13 ++++++++++
 include/linux/memory_hotplug.h          |  9 +++++++
 mm/hugetlb_vmemmap.c                    | 42 ++++++++++++++++++++++++++++-----
 mm/hugetlb_vmemmap.h                    |  4 +++-
 mm/memory_hotplug.c                     |  5 ++++
 5 files changed, 66 insertions(+), 7 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index f4804ce37c58..01f18e6cc227 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -561,6 +561,19 @@ Change the minimum size of the hugepage pool.
 See Documentation/admin-guide/mm/hugetlbpage.rst
 
 
+hugetlb_free_vmemmap
+====================
+
+A toggle value indicating if vmemmap pages are allowed to be optimized.
+If it is off (0), then it can be set true (1).  Once true, the vmemmap
+pages associated with each HugeTLB page will be optimized, and the toggle
+cannot be set back to false.  It only optimizes the subsequent allocation
+of HugeTLB pages from buddy system, while already allocated HugeTLB pages
+will not be optimized.
+
+See Documentation/admin-guide/mm/hugetlbpage.rst
+
+
 nr_hugepages_mempolicy
 ======================
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index e0b2209ab71c..20d7edf62a6a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -351,4 +351,13 @@ void arch_remove_linear_mapping(u64 start, u64 size);
 extern bool mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+bool mhp_memmap_on_memory(void);
+#else
+static inline bool mhp_memmap_on_memory(void)
+{
+	return false;
+}
+#endif
+
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 836d1117f08b..3bcc8f25bd50 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -10,6 +10,7 @@
 
 #define pr_fmt(fmt)	"HugeTLB: " fmt
 
+#include <linux/memory_hotplug.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -118,17 +119,14 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	BUILD_BUG_ON(__NR_USED_SUBPAGE >=
 		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
 
-	if (!hugetlb_free_vmemmap_enabled())
-		return;
-
-	if (IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON) &&
-	    !is_power_of_2(sizeof(struct page))) {
+	if (!is_power_of_2(sizeof(struct page))) {
 		/*
 		 * The hugetlb_free_vmemmap_enabled_key can be enabled when
 		 * CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON. It should
 		 * be disabled if "struct page" crosses page boundaries.
 		 */
-		static_branch_disable(&hugetlb_free_vmemmap_enabled_key);
+		if (IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON))
+			static_branch_disable(&hugetlb_free_vmemmap_enabled_key);
 		return;
 	}
 
@@ -147,3 +145,35 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
 		h->name);
 }
+
+static struct ctl_table hugetlb_vmemmap_sysctls[] = {
+	{
+		.procname	= "hugetlb_free_vmemmap",
+		.data		= &hugetlb_free_vmemmap_enabled_key.key,
+		.mode		= 0644,
+		/* only handle a transition from default "0" to "1" */
+		.proc_handler	= proc_do_static_key,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+
+static __init int hugetlb_vmemmap_sysctls_init(void)
+{
+	/*
+	 * The vmemmap pages cannot be optimized if
+	 * "memory_hotplug.memmap_on_memory" is enabled unless
+	 * "hugetlb_free_vmemmap" is enabled as well since
+	 * "hugetlb_free_vmemmap" takes precedence over
+	 * "memory_hotplug.memmap_on_memory".
+	 */
+	if (mhp_memmap_on_memory() && !hugetlb_free_vmemmap_enabled())
+		return 0;
+
+	if (is_power_of_2(sizeof(struct page)))
+		register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
+
+	return 0;
+}
+late_initcall(hugetlb_vmemmap_sysctls_init);
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index cb2bef8f9e73..b67a159027f4 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -21,7 +21,9 @@ void hugetlb_vmemmap_init(struct hstate *h);
  */
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
-	return h->nr_free_vmemmap_pages;
+	if (hugetlb_free_vmemmap_enabled())
+		return h->nr_free_vmemmap_pages;
+	return 0;
 }
 #else
 static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c226a337c1ef..c2115e566abc 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -50,6 +50,11 @@ static bool memmap_on_memory __ro_after_init;
 #ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
 module_param(memmap_on_memory, bool, 0444);
 MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
+
+bool mhp_memmap_on_memory(void)
+{
+	return memmap_on_memory;
+}
 #endif
 
 enum {
-- 
2.11.0