linux-kernel - [RFC PATCH 1/4] mm/swap.c: pre-sort pages in pagevec for pagevec_lru_move

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]

Date:   Fri, 25 Dec 2020 17:59:47 +0800
From:   Alex Shi <alex.shi@...ux.alibaba.com>
To:     willy@...radead.org
Cc:     tim.c.chen@...ux.intel.com,
        Konstantin Khlebnikov <koct9i@...il.com>,
        Hugh Dickins <hughd@...gle.com>, Yu Zhao <yuzhao@...gle.com>,
        Michal Hocko <mhocko@...e.com>,
        Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org
Subject: [RFC PATCH 1/4] mm/swap.c: pre-sort pages in pagevec for pagevec_lru_move_fn

Pages in pagevec may have different lruvec, so we have to do relock in
function pagevec_lru_move_fn(), but a relock may cause current cpu wait
for long time on the same lock for spinlock fairness reason.

Before per memcg lru_lock, we have to bear the relock since the spinlock
is the only way to serialize page's memcg/lruvec. Now TestClearPageLRU
could be used to isolate pages exculsively, and stable the page's
lruvec/memcg. So it gives us a chance to sort the page's lruvec before
moving action in pagevec_lru_move_fn. Then we don't suffer from the
spinlock's fairness wait.

Signed-off-by: Alex Shi <alex.shi@...ux.alibaba.com>
Cc: Konstantin Khlebnikov <koct9i@...il.com>
Cc: Hugh Dickins <hughd@...gle.com>
Cc: Yu Zhao <yuzhao@...gle.com>
Cc: Michal Hocko <mhocko@...e.com>
Cc: Matthew Wilcox (Oracle) <willy@...radead.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org
---
 mm/swap.c | 92 +++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 79 insertions(+), 13 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index c5363bdebe67..994641331bf7 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -201,29 +201,95 @@ int get_kernel_page(unsigned long start, int write, struct page **pages)
 }
 EXPORT_SYMBOL_GPL(get_kernel_page);
 
+/* Pratt's gaps for shell sort, https://en.wikipedia.org/wiki/Shellsort */
+static int gaps[] = { 6, 4, 3, 2, 1, 0};
+
+/* Shell sort pagevec[] on page's lruvec.*/
+static void shell_sort(struct pagevec *pvec, unsigned long *lvaddr)
+{
+	int g, i, j, n = pagevec_count(pvec);
+
+	for (g=0; gaps[g] > 0 && gaps[g] <= n/2; g++) {
+		int gap = gaps[g];
+
+		for (i = gap; i < n; i++) {
+			unsigned long tmp = lvaddr[i];
+			struct page *page = pvec->pages[i];
+
+			for (j = i - gap; j >= 0 && lvaddr[j] > tmp; j -= gap) {
+				lvaddr[j + gap] = lvaddr[j];
+				pvec->pages[j + gap] = pvec->pages[j];
+			}
+			lvaddr[j + gap] = tmp;
+			pvec->pages[j + gap] = page;
+		}
+	}
+}
+
+/* Get lru bit cleared page and their lruvec address, release the others */
+void sort_isopv(struct pagevec *pvec, struct pagevec *isopv,
+		unsigned long *lvaddr)
+{
+	int i, j;
+	struct pagevec busypv;
+
+	pagevec_init(&busypv);
+
+	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+
+		pvec->pages[i] = NULL;
+
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page)) {
+			pagevec_add(&busypv, page);
+			continue;
+		}
+		lvaddr[j++] = (unsigned long)
+				mem_cgroup_page_lruvec(page, page_pgdat(page));
+		pagevec_add(isopv, page);
+	}
+	pagevec_reinit(pvec);
+	if (pagevec_count(&busypv))
+		release_pages(busypv.pages, busypv.nr);
+
+	shell_sort(isopv, lvaddr);
+}
+
 static void pagevec_lru_move_fn(struct pagevec *pvec,
 	void (*move_fn)(struct page *page, struct lruvec *lruvec))
 {
-	int i;
+	int i, n;
 	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
+	unsigned long lvaddr[PAGEVEC_SIZE];
+	struct pagevec isopv;
 
-	for (i = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
+	pagevec_init(&isopv);
 
-		/* block memcg migration during page moving between lru */
-		if (!TestClearPageLRU(page))
-			continue;
+	sort_isopv(pvec, &isopv, lvaddr);
 
-		lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
-		(*move_fn)(page, lruvec);
+	n = pagevec_count(&isopv);
+	if (!n)
+		return;
 
-		SetPageLRU(page);
+	lruvec = (struct lruvec *)lvaddr[0];
+	spin_lock_irqsave(&lruvec->lru_lock, flags);
+
+	for (i = 0; i < n; i++) {
+		/* lock new lruvec if lruvec changes, we have sorted them */
+		if (lruvec != (struct lruvec *)lvaddr[i]) {
+			spin_unlock_irqrestore(&lruvec->lru_lock, flags);
+			lruvec = (struct lruvec *)lvaddr[i];
+			spin_lock_irqsave(&lruvec->lru_lock, flags);
+		}
+
+		(*move_fn)(isopv.pages[i], lruvec);
+
+		SetPageLRU(isopv.pages[i]);
 	}
-	if (lruvec)
-		unlock_page_lruvec_irqrestore(lruvec, flags);
-	release_pages(pvec->pages, pvec->nr);
-	pagevec_reinit(pvec);
+	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
+	release_pages(isopv.pages, isopv.nr);
 }
 
 static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
-- 
2.29.GIT