linux-kernel - [PATCH -next] mm, proc: collect percpu free pages into the free 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-next>] [day] [month] [year] [list]

Date:   Mon, 22 Aug 2022 10:33:11 +0800
From:   Liu Shixin <liushixin2@...wei.com>
To:     Andrew Morton <akpm@...ux-foundation.org>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        huang ying <huang.ying.caritas@...il.com>,
        Aaron Lu <aaron.lu@...el.com>,
        Dave Hansen <dave.hansen@...el.com>,
        "Michal Hocko" <mhocko@...e.com>,
        Jesper Dangaard Brouer <brouer@...hat.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Kemi Wang <kemi.wang@...el.com>,
        "Kefeng Wang" <wangkefeng.wang@...wei.com>
CC:     <linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>,
        Liu Shixin <liushixin2@...wei.com>
Subject: [PATCH -next] mm, proc: collect percpu free pages into the free pages

The page on pcplist could be used, but not counted into memory free or
avaliable, and pcp_free is only showed by show_mem() for now. Since commit
d8a759b57035 ("mm, page_alloc: double zone's batchsize"), there is a
significant decrease in the display of free memory, with a large number
of cpus and zones, the number of pages in the percpu list can be very
large, so it is better to let user to know the pcp count.

On a machine with 3 zones and 72 CPUs. Before commit d8a759b57035, the
maximum amount of pages in the pcp lists was theoretically 162MB(3*72*768KB).
After the patch, the lists can hold 324MB. It has been observed to be 114MB
in the idle state after system startup in practice(increased 80 MB).

Signed-off-by: Liu Shixin <liushixin2@...wei.com>
---
 mm/page_alloc.c | 47 +++++++++++++++++++++++++++++++++--------------
 1 file changed, 33 insertions(+), 14 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 033f1e26d15b..f8b46ac2c2a0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5853,6 +5853,26 @@ static unsigned long nr_free_zone_pages(int offset)
 	return sum;
 }
 
+static unsigned long nr_free_zone_pcplist_pages(struct zone *zone)
+{
+	unsigned long sum = 0;
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		sum += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count;
+	return sum;
+}
+
+static unsigned long nr_free_pcplist_pages(void)
+{
+	unsigned long sum = 0;
+	struct zone *zone;
+
+	for_each_zone(zone)
+		sum += nr_free_zone_pcplist_pages(zone);
+	return sum;
+}
+
 /**
  * nr_free_buffer_pages - count number of pages beyond high watermark
  *
@@ -5894,7 +5914,8 @@ long si_mem_available(void)
 	 * Estimate the amount of memory available for userspace allocations,
 	 * without causing swapping or OOM.
 	 */
-	available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages;
+	available = global_zone_page_state(NR_FREE_PAGES) +
+		    nr_free_pcplist_pages() - totalreserve_pages;
 
 	/*
 	 * Not all the page cache can be freed, otherwise the system will
@@ -5924,7 +5945,8 @@ void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages();
 	val->sharedram = global_node_page_state(NR_SHMEM);
-	val->freeram = global_zone_page_state(NR_FREE_PAGES);
+	val->freeram = global_zone_page_state(NR_FREE_PAGES) +
+		       nr_free_pcplist_pages();
 	val->bufferram = nr_blockdev_pages();
 	val->totalhigh = totalhigh_pages();
 	val->freehigh = nr_free_highpages();
@@ -5938,30 +5960,28 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 {
 	int zone_type;		/* needs to be signed */
 	unsigned long managed_pages = 0;
+	unsigned long free_pages = sum_zone_node_page_state(nid, NR_FREE_PAGES);
 	unsigned long managed_highpages = 0;
 	unsigned long free_highpages = 0;
 	pg_data_t *pgdat = NODE_DATA(nid);
 
-	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
-		managed_pages += zone_managed_pages(&pgdat->node_zones[zone_type]);
-	val->totalram = managed_pages;
-	val->sharedram = node_page_state(pgdat, NR_SHMEM);
-	val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
-#ifdef CONFIG_HIGHMEM
 	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
 		struct zone *zone = &pgdat->node_zones[zone_type];
 
+		managed_pages += zone_managed_pages(zone);
+		free_pages += nr_free_zone_pcplist_pages(zone);
+#ifdef CONFIG_HIGHMEM
 		if (is_highmem(zone)) {
 			managed_highpages += zone_managed_pages(zone);
 			free_highpages += zone_page_state(zone, NR_FREE_PAGES);
 		}
+#endif
 	}
+	val->totalram = managed_pages;
+	val->sharedram = node_page_state(pgdat, NR_SHMEM);
+	val->freeram = free_pages;
 	val->totalhigh = managed_highpages;
 	val->freehigh = free_highpages;
-#else
-	val->totalhigh = managed_highpages;
-	val->freehigh = free_highpages;
-#endif
 	val->mem_unit = PAGE_SIZE;
 }
 #endif
@@ -6035,8 +6055,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
 			continue;
 
-		for_each_online_cpu(cpu)
-			free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count;
+		free_pcp += nr_free_zone_pcplist_pages(zone);
 	}
 
 	printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
-- 
2.25.1