@@ -492,6 +492,9 @@ struct hstate {
unsigned int nr_huge_pages_node[MAX_NUMNODES];
unsigned int free_huge_pages_node[MAX_NUMNODES];
unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+ unsigned int nr_free_vmemmap_pages;
+#endif
#ifdef CONFIG_CGROUP_HUGETLB
/* cgroup control files */
struct cftype cgroup_files_dfl[7];
@@ -71,6 +71,7 @@ obj-$(CONFIG_FRONTSWAP) += frontswap.o
obj-$(CONFIG_ZSWAP) += zswap.o
obj-$(CONFIG_HAS_DMA) += dmapool.o
obj-$(CONFIG_HUGETLBFS) += hugetlb.o
+obj-$(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP) += hugetlb_vmemmap.o
obj-$(CONFIG_NUMA) += mempolicy.o
obj-$(CONFIG_SPARSEMEM) += sparse.o
obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
@@ -42,6 +42,7 @@
#include <linux/userfaultfd_k.h>
#include <linux/page_owner.h>
#include "internal.h"
+#include "hugetlb_vmemmap.h"
int hugetlb_max_hstate __read_mostly;
unsigned int default_hstate_idx;
@@ -3285,6 +3286,8 @@ void __init hugetlb_add_hstate(unsigned int order)
snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
huge_page_size(h)/1024);
+ hugetlb_vmemmap_init(h);
+
parsed_hstate = h;
}
new file mode 100644
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Free some vmemmap pages of HugeTLB
+ *
+ * Copyright (c) 2020, Bytedance. All rights reserved.
+ *
+ * Author: Muchun Song <songmuchun@bytedance.com>
+ *
+ * The struct page structures (page structs) are used to describe a physical
+ * page frame. By default, there is a one-to-one mapping from a page frame to
+ * it's corresponding page struct.
+ *
+ * The HugeTLB pages consist of multiple base page size pages and is supported
+ * by many architectures. See hugetlbpage.rst in the Documentation directory
+ * for more details. On the x86 architecture, HugeTLB pages of size 2MB and 1GB
+ * are currently supported. Since the base page size on x86 is 4KB, a 2MB
+ * HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of
+ * 4096 base pages. For each base page, there is a corresponding page struct.
+ *
+ * Within the HugeTLB subsystem, only the first 4 page structs are used to
+ * contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER
+ * provides this upper limit. The only 'useful' information in the remaining
+ * page structs is the compound_head field, and this field is the same for all
+ * tail pages.
+ *
+ * By removing redundant page structs for HugeTLB pages, memory can returned to
+ * the buddy allocator for other uses.
+ *
+ * When the system boot up, every 2M HugeTLB has 512 struct page structs which
+ * size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE).
+ *
+ * HugeTLB struct pages(8 pages) page frame(8 pages)
+ * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+
+ * | | | 0 | -------------> | 0 |
+ * | | +-----------+ +-----------+
+ * | | | 1 | -------------> | 1 |
+ * | | +-----------+ +-----------+
+ * | | | 2 | -------------> | 2 |
+ * | | +-----------+ +-----------+
+ * | | | 3 | -------------> | 3 |
+ * | | +-----------+ +-----------+
+ * | | | 4 | -------------> | 4 |
+ * | 2MB | +-----------+ +-----------+
+ * | | | 5 | -------------> | 5 |
+ * | | +-----------+ +-----------+
+ * | | | 6 | -------------> | 6 |
+ * | | +-----------+ +-----------+
+ * | | | 7 | -------------> | 7 |
+ * | | +-----------+ +-----------+
+ * | |
+ * | |
+ * | |
+ * +-----------+
+ *
+ * The value of page->compound_head is the same for all tail pages. The first
+ * page of page structs (page 0) associated with the HugeTLB page contains the 4
+ * page structs necessary to describe the HugeTLB. The only use of the remaining
+ * pages of page structs (page 1 to page 7) is to point to page->compound_head.
+ * Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs
+ * will be used for each HugeTLB page. This will allow us to free the remaining
+ * 6 pages to the buddy allocator.
+ *
+ * Here is how things look after remapping.
+ *
+ * HugeTLB struct pages(8 pages) page frame(8 pages)
+ * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+
+ * | | | 0 | -------------> | 0 |
+ * | | +-----------+ +-----------+
+ * | | | 1 | -------------> | 1 |
+ * | | +-----------+ +-----------+
+ * | | | 2 | ----------------^ ^ ^ ^ ^ ^
+ * | | +-----------+ | | | | |
+ * | | | 3 | ------------------+ | | | |
+ * | | +-----------+ | | | |
+ * | | | 4 | --------------------+ | | |
+ * | 2MB | +-----------+ | | |
+ * | | | 5 | ----------------------+ | |
+ * | | +-----------+ | |
+ * | | | 6 | ------------------------+ |
+ * | | +-----------+ |
+ * | | | 7 | --------------------------+
+ * | | +-----------+
+ * | |
+ * | |
+ * | |
+ * +-----------+
+ *
+ * When a HugeTLB is freed to the buddy system, we should allocate 6 pages for
+ * vmemmap pages and restore the previous mapping relationship.
+ *
+ * Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar
+ * to the 2MB HugeTLB page. We also can use this approach to free the vmemmap
+ * pages.
+ */
+#define pr_fmt(fmt) "HugeTLB Vmemmap: " fmt
+
+#include "hugetlb_vmemmap.h"
+
+/*
+ * There are a lot of struct page structures(8 page frames for 2MB HugeTLB page
+ * and 4096 page frames for 1GB HugeTLB page) associated with each HugeTLB page.
+ * For tail pages, the value of compound_head is the same. So we can reuse first
+ * page of tail page structures. We map the virtual addresses of the remaining
+ * pages of tail page structures to the first tail page struct, and then free
+ * these page frames. Therefore, we need to reserve two pages as vmemmap areas.
+ */
+#define RESERVE_VMEMMAP_NR 2U
+
+void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+ unsigned int order = huge_page_order(h);
+ unsigned int vmemmap_pages;
+
+ vmemmap_pages = ((1 << order) * sizeof(struct page)) >> PAGE_SHIFT;
+ /*
+ * The head page and the first tail page are not to be freed to buddy
+ * system, the others page will map to the first tail page. So there
+ * are the remaining pages that can be freed.
+ *
+ * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? This is
+ * not expected to happen unless the system is corrupted. So on the
+ * safe side, it is only a safety net.
+ */
+ if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+ h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+
+ pr_debug("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
+ h->name);
+}
new file mode 100644
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Free some vmemmap pages of HugeTLB
+ *
+ * Copyright (c) 2020, Bytedance. All rights reserved.
+ *
+ * Author: Muchun Song <songmuchun@bytedance.com>
+ */
+#ifndef _LINUX_HUGETLB_VMEMMAP_H
+#define _LINUX_HUGETLB_VMEMMAP_H
+#include <linux/hugetlb.h>
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+void __init hugetlb_vmemmap_init(struct hstate *h);
+#else
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
+#endif /* _LINUX_HUGETLB_VMEMMAP_H */