linux-kernel - [PATCH -V3 6/8] hugetlbfs: Add a list for tracking in-use HugeTLB pages

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: <1331622432-24683-7-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
Date:	Tue, 13 Mar 2012 12:37:10 +0530
From:	"Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>
To:	linux-mm@...ck.org, mgorman@...e.de,
	kamezawa.hiroyu@...fujitsu.com, dhillf@...il.com,
	aarcange@...hat.com, mhocko@...e.cz, akpm@...ux-foundation.org,
	hannes@...xchg.org
Cc:	linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
	"Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>
Subject: [PATCH -V3 6/8] hugetlbfs: Add a list for tracking in-use HugeTLB pages

From: "Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>

hugepage_activelist will be used to track currently used HugeTLB pages.
We need to find the in-use HugeTLB pages to support memcg removal.
On memcg removal we update the page's memory cgroup to point to
parent cgroup.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@...ux.vnet.ibm.com>
---
 include/linux/hugetlb.h |    1 +
 mm/hugetlb.c            |   23 ++++++++++++++++++-----
 2 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8c1e855..e62eee7 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -217,6 +217,7 @@ struct hstate {
 	unsigned long resv_huge_pages;
 	unsigned long surplus_huge_pages;
 	unsigned long nr_overcommit_huge_pages;
+	struct list_head hugepage_activelist;
 	struct list_head hugepage_freelists[MAX_NUMNODES];
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 30f66f1..e038fdc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -433,7 +433,7 @@ void copy_huge_page(struct page *dst, struct page *src)
 static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
 	int nid = page_to_nid(page);
-	list_add(&page->lru, &h->hugepage_freelists[nid]);
+	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
 }
@@ -445,7 +445,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 	if (list_empty(&h->hugepage_freelists[nid]))
 		return NULL;
 	page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
-	list_del(&page->lru);
+	list_move(&page->lru, &h->hugepage_activelist);
 	set_page_refcounted(page);
 	h->free_huge_pages--;
 	h->free_huge_pages_node[nid]--;
@@ -542,13 +542,14 @@ static void free_huge_page(struct page *page)
 	page->mapping = NULL;
 	BUG_ON(page_count(page));
 	BUG_ON(page_mapcount(page));
-	INIT_LIST_HEAD(&page->lru);
 
 	if (mapping)
 		mem_cgroup_hugetlb_uncharge_page(h - hstates,
 						 pages_per_huge_page(h), page);
 	spin_lock(&hugetlb_lock);
 	if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
+		/* remove the page from active list */
+		list_del(&page->lru);
 		update_and_free_page(h, page);
 		h->surplus_huge_pages--;
 		h->surplus_huge_pages_node[nid]--;
@@ -562,6 +563,7 @@ static void free_huge_page(struct page *page)
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
+	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, free_huge_page);
 	spin_lock(&hugetlb_lock);
 	h->nr_huge_pages++;
@@ -1866,6 +1868,7 @@ void __init hugetlb_add_hstate(unsigned order)
 	h->free_huge_pages = 0;
 	for (i = 0; i < MAX_NUMNODES; ++i)
 		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
+	INIT_LIST_HEAD(&h->hugepage_activelist);
 	h->next_nid_to_alloc = first_node(node_states[N_HIGH_MEMORY]);
 	h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]);
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
@@ -2324,14 +2327,24 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 		page = pte_page(pte);
 		if (pte_dirty(pte))
 			set_page_dirty(page);
-		list_add(&page->lru, &page_list);
+
+		spin_lock(&hugetlb_lock);
+		list_move(&page->lru, &page_list);
+		spin_unlock(&hugetlb_lock);
 	}
 	spin_unlock(&mm->page_table_lock);
 	flush_tlb_range(vma, start, end);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 	list_for_each_entry_safe(page, tmp, &page_list, lru) {
 		page_remove_rmap(page);
-		list_del(&page->lru);
+		/*
+		 * We need to move it back huge page active list. If we are
+		 * holding the last reference, below put_page will move it
+		 * back to free list.
+		 */
+		spin_lock(&hugetlb_lock);
+		list_move(&page->lru, &h->hugepage_activelist);
+		spin_unlock(&hugetlb_lock);
 		put_page(page);
 	}
 }
-- 
1.7.9

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/