linux-kernel - [PATCH v8 10/12] 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: <20201210035526.38938-11-songmuchun@bytedance.com>
Date:   Thu, 10 Dec 2020 11:55:24 +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, song.bao.hua@...ilicon.com,
        david@...hat.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 v8 10/12] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate

All the infrastructure is ready, so we introduce 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 allocator. And initialize it
in the hugetlb_vmemmap_init(). This patch is actual enablement of the
feature.

Signed-off-by: Muchun Song <songmuchun@...edance.com>
Acked-by: Mike Kravetz <mike.kravetz@...cle.com>
---
 include/linux/hugetlb.h |  3 +++
 mm/hugetlb.c            |  1 +
 mm/hugetlb_vmemmap.c    | 29 +++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h    | 10 ++++++----
 4 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 7f47f0eeca3b..66d82ae7b712 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 2e7a59b44364..6440367a71b6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3327,6 +3327,7 @@ void __init hugetlb_add_hstate(unsigned int order)
 	h->next_nid_to_free = first_memory_node;
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
+	hugetlb_vmemmap_init(h);
 
 	parsed_hstate = h;
 }
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index f0926b382338..36a2e2db7913 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -421,3 +421,32 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 
 	free_vmemmap_page_list(&vmemmap_pages);
 }
+
+void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+	unsigned int nr_pages = pages_per_huge_page(h);
+	unsigned int vmemmap_pages;
+
+	/* We cannot optimize if a "struct page" crosses page boundaries. */
+	if (!is_power_of_2(sizeof(struct page)))
+		return;
+
+	if (!hugetlb_free_vmemmap_enabled)
+		return;
+
+	vmemmap_pages = (nr_pages * 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? It is true
+	 * on some architectures (e.g. aarch64). See Documentation/arm64/
+	 * hugetlbpage.rst for more details.
+	 */
+	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+
+	pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
+		h->name);
+}
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 8fd57c49e230..0a1c0d33a316 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -11,21 +11,23 @@
 #include <linux/hugetlb.h>
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+void hugetlb_vmemmap_init(struct hstate *h);
 void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 
 /*
  * How many vmemmap pages associated with a HugeTLB page that can be freed
  * to the buddy allocator.
- *
- * Todo: Now it is zero, because all infrastructure is not ready. Once all the
- * infrastructure is ready, we will rework this function to support the feature.
  */
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
-	return 0;
+	return h->nr_free_vmemmap_pages;
 }
 #else
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+
 static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
-- 
2.11.0