linux-kernel - [PATCH v3 04/21] mm/hugetlb: Introduce nr_free_vmemmap

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20201108141113.65450-5-songmuchun@bytedance.com>
Date:   Sun,  8 Nov 2020 22:10:56 +0800
From:   Muchun Song <songmuchun@...edance.com>
To:     corbet@....net, mike.kravetz@...cle.com, tglx@...utronix.de,
        mingo@...hat.com, bp@...en8.de, x86@...nel.org, hpa@...or.com,
        dave.hansen@...ux.intel.com, luto@...nel.org, peterz@...radead.org,
        viro@...iv.linux.org.uk, akpm@...ux-foundation.org,
        paulmck@...nel.org, mchehab+huawei@...nel.org,
        pawan.kumar.gupta@...ux.intel.com, rdunlap@...radead.org,
        oneukum@...e.com, anshuman.khandual@....com, jroedel@...e.de,
        almasrymina@...gle.com, rientjes@...gle.com, willy@...radead.org,
        osalvador@...e.de, mhocko@...e.com
Cc:     duanxiongchun@...edance.com, linux-doc@...r.kernel.org,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        linux-fsdevel@...r.kernel.org,
        Muchun Song <songmuchun@...edance.com>
Subject: [PATCH v3 04/21] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate

If the size of hugetlb page is 2MB, we need 512 struct page structures
(8 pages) to be associated with it. As far as I know, we only use the
first 4 struct page structures. Use of first 4 struct page structures
comes from HUGETLB_CGROUP_MIN_ORDER.

For tail pages, the value of compound_head is the same. So we can reuse
first page of tail page structs. We map the virtual addresses of the
remaining 6 pages of tail page structs to the first tail page struct,
and then free these 6 pages. Therefore, we need to reserve at least 2
pages as vmemmap areas.

So we introduce a new nr_free_vmemmap_pages field in the hstate to
indicate how many vmemmap pages associated with a hugetlb page that we
can free to buddy system.

Signed-off-by: Muchun Song <songmuchun@...edance.com>
Acked-by: Mike Kravetz <mike.kravetz@...cle.com>
---
 include/linux/hugetlb.h |  3 +++
 mm/hugetlb.c            | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d5cc5f802dd4..eed3dd3bd626 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -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];
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 81a41aa080a5..a0007902fafb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1292,6 +1292,42 @@ static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
 #endif
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+/*
+ * There are 512 struct page structs(8 pages) associated with each 2MB
+ * hugetlb page. For tail pages, the value of compound_dtor is the same.
+ * So we can reuse first page of tail page structs. We map the virtual
+ * addresses of the remaining 6 pages of tail page structs to the first
+ * tail page struct, and then free these 6 pages. Therefore, we need to
+ * reserve at least 2 pages as vmemmap areas.
+ */
+#define RESERVE_VMEMMAP_NR	2U
+
+static 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 not free to buddy system,
+	 * the others page will map to the first tail page. So there are
+	 * (@vmemmap_pages - RESERVE_VMEMMAP_NR) pages can be freed.
+	 */
+	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+	else
+		h->nr_free_vmemmap_pages = 0;
+
+	pr_debug("HugeTLB: can free %d vmemmap pages for %s\n",
+		 h->nr_free_vmemmap_pages, h->name);
+}
+#else
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+#endif
+
 static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
@@ -3285,6 +3321,8 @@ 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;
 }
 
-- 
2.11.0