diff mbox series

[v2,03/19] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP

Message ID 20201026145114.59424-4-songmuchun@bytedance.com (mailing list archive)
State New, archived
Headers show
Series Free some vmemmap pages of hugetlb page | expand

Commit Message

Muchun Song Oct. 26, 2020, 2:50 p.m. UTC
The purpose of introducing HUGETLB_PAGE_FREE_VMEMMAP is to configure
whether to enable the feature of freeing unused vmemmap associated
with HugeTLB pages. Now only support x86.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/mm/init_64.c |  2 +-
 fs/Kconfig            | 16 ++++++++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

Comments

Oscar Salvador Oct. 29, 2020, 10:29 a.m. UTC | #1
On Mon, Oct 26, 2020 at 10:50:58PM +0800, Muchun Song wrote:
> The purpose of introducing HUGETLB_PAGE_FREE_VMEMMAP is to configure
> whether to enable the feature of freeing unused vmemmap associated
> with HugeTLB pages. Now only support x86.

Why this needs to be a config thing?
If this space-memory-optimization does not come with a trade-off,
why does the user have to set this instead of coming by default?
Muchun Song Oct. 29, 2020, 1:34 p.m. UTC | #2
On Thu, Oct 29, 2020 at 6:29 PM Oscar Salvador <osalvador@suse.de> wrote:
>
> On Mon, Oct 26, 2020 at 10:50:58PM +0800, Muchun Song wrote:
> > The purpose of introducing HUGETLB_PAGE_FREE_VMEMMAP is to configure
> > whether to enable the feature of freeing unused vmemmap associated
> > with HugeTLB pages. Now only support x86.
>
> Why this needs to be a config thing?
> If this space-memory-optimization does not come with a trade-off,
> why does the user have to set this instead of coming by default?

Now we only support x86_64. If we want to support other archs. We
need some arch special code to support this feature. In the future,
if this patch series is merged to mainline, I will implement this
optimization for other archs. At that time we can remove the
HUGETLB_PAGE_FREE_VMEMMAP.

Thanks.

>
>
> --
> Oscar Salvador
> SUSE L3
diff mbox series

Patch

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0a45f062826e..0435bee2e172 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1225,7 +1225,7 @@  static struct kcore_list kcore_vsyscall;
 
 static void __init register_page_bootmem_info(void)
 {
-#ifdef CONFIG_NUMA
+#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)
 	int i;
 
 	for_each_online_node(i)
diff --git a/fs/Kconfig b/fs/Kconfig
index 976e8b9033c4..5a4265ff2a86 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -245,6 +245,22 @@  config HUGETLBFS
 config HUGETLB_PAGE
 	def_bool HUGETLBFS
 
+config HUGETLB_PAGE_FREE_VMEMMAP
+	bool "Free unused vmemmap associated with HugeTLB pages"
+	default n
+	depends on X86
+	depends on HUGETLB_PAGE
+	depends on SPARSEMEM_VMEMMAP
+	depends on HAVE_BOOTMEM_INFO_NODE
+	help
+	  There are many struct page structures associated with each HugeTLB
+	  page. But we only use a few struct page structures. In this case,
+	  it wastes some memory. It is better to free the unused struct page
+	  structures to buddy system which can save some memory. For
+	  architectures that support it, say Y here.
+
+	  If unsure, say N.
+
 config MEMFD_CREATE
 	def_bool TMPFS || HUGETLBFS