summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLi Zhijian <lizhijian@fujitsu.com>2024-07-23 14:44:28 +0800
committerAndrew Morton <akpm@linux-foundation.org>2024-07-26 14:33:09 -0700
commit66eca1021a42856d6af2a9802c99e160278aed91 (patch)
treedaee39bda2758c63e77a152b238d468562799f77
parentf59adcf5933271ab7247c4c8938c67be8905b725 (diff)
downloadlwn-66eca1021a42856d6af2a9802c99e160278aed91.tar.gz
lwn-66eca1021a42856d6af2a9802c99e160278aed91.zip
mm/page_alloc: fix pcp->count race between drain_pages_zone() vs __rmqueue_pcplist()
It's expected that no page should be left in pcp_list after calling zone_pcp_disable() in offline_pages(). Previously, it's observed that offline_pages() gets stuck [1] due to some pages remaining in pcp_list. Cause: There is a race condition between drain_pages_zone() and __rmqueue_pcplist() involving the pcp->count variable. See below scenario: CPU0 CPU1 ---------------- --------------- spin_lock(&pcp->lock); __rmqueue_pcplist() { zone_pcp_disable() { /* list is empty */ if (list_empty(list)) { /* add pages to pcp_list */ alloced = rmqueue_bulk() mutex_lock(&pcp_batch_high_lock) ... __drain_all_pages() { drain_pages_zone() { /* read pcp->count, it's 0 here */ count = READ_ONCE(pcp->count) /* 0 means nothing to drain */ /* update pcp->count */ pcp->count += alloced << order; ... ... spin_unlock(&pcp->lock); In this case, after calling zone_pcp_disable() though, there are still some pages in pcp_list. And these pages in pcp_list are neither movable nor isolated, offline_pages() gets stuck as a result. Solution: Expand the scope of the pcp->lock to also protect pcp->count in drain_pages_zone(), to ensure no pages are left in the pcp list after zone_pcp_disable() [1] https://lore.kernel.org/linux-mm/6a07125f-e720-404c-b2f9-e55f3f166e85@fujitsu.com/ Link: https://lkml.kernel.org/r/20240723064428.1179519-1-lizhijian@fujitsu.com Fixes: 4b23a68f9536 ("mm/page_alloc: protect PCP lists with a spinlock") Signed-off-by: Li Zhijian <lizhijian@fujitsu.com> Reported-by: Yao Xingtao <yaoxt.fnst@fujitsu.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: David Hildenbrand <david@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r--mm/page_alloc.c18
1 files changed, 11 insertions, 7 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7ac8d61148fe..28f80daf5c04 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2343,16 +2343,20 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
static void drain_pages_zone(unsigned int cpu, struct zone *zone)
{
struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
- int count = READ_ONCE(pcp->count);
-
- while (count) {
- int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
- count -= to_drain;
+ int count;
+ do {
spin_lock(&pcp->lock);
- free_pcppages_bulk(zone, to_drain, pcp, 0);
+ count = pcp->count;
+ if (count) {
+ int to_drain = min(count,
+ pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
+
+ free_pcppages_bulk(zone, to_drain, pcp, 0);
+ count -= to_drain;
+ }
spin_unlock(&pcp->lock);
- }
+ } while (count);
}
/*