The routine set_max_huge_pages reduces the number of hugetlb_pages,
by calling free_pool_huge_page in a loop. It does this as long as
persistent_huge_pages() is above a calculated min_count value.
However, this loop can conditionally drop hugetlb_lock and in some
circumstances free_pool_huge_page can drop hugetlb_lock. If the
lock is dropped, counters could change the calculated min_count
value may no longer be valid.
The routine try_to_free_low has the same issue.
Recalculate min_count in each loop iteration as hugetlb_lock may have
been dropped.
Signed-off-by: Mike Kravetz <mike.krav...@oracle.com>
---
mm/hugetlb.c | 25 +++++++++++++++++++++----
1 file changed, 21 insertions(+), 4 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d5be25f910e8..c537274c2a38 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2521,11 +2521,20 @@ static void __init report_hugepages(void)
}
}
+static inline unsigned long min_hp_count(struct hstate *h, unsigned long count)
+{
+ unsigned long min_count;
+
+ min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
+ return max(count, min_count);
+}
+
#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count,
nodemask_t *nodes_allowed)
{
int i;
+ unsigned long min_count = min_hp_count(h, count);
if (hstate_is_gigantic(h))
return;
@@ -2534,7 +2543,7 @@ static void try_to_free_low(struct hstate *h, unsigned
long count,
struct page *page, *next;
struct list_head *freel = &h->hugepage_freelists[i];
list_for_each_entry_safe(page, next, freel, lru) {
- if (count >= h->nr_huge_pages)
+ if (min_count >= h->nr_huge_pages)
return;
if (PageHighMem(page))
continue;
@@ -2542,6 +2551,12 @@ static void try_to_free_low(struct hstate *h, unsigned
long count,
update_and_free_page(h, page);
h->free_huge_pages--;
h->free_huge_pages_node[page_to_nid(page)]--;
+
+ /*
+ * update_and_free_page could have dropped lock so
+ * recompute min_count.
+ */
+ min_count = min_hp_count(h, count);
}
}
}
@@ -2695,13 +2710,15 @@ static int set_max_huge_pages(struct hstate *h,
unsigned long count, int nid,
* and won't grow the pool anywhere else. Not until one of the
* sysctls are changed, or the surplus pages go out of use.
*/
- min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
- min_count = max(count, min_count);
- try_to_free_low(h, min_count, nodes_allowed);
+ min_count = min_hp_count(h, count);
+ try_to_free_low(h, count, nodes_allowed);
while (min_count < persistent_huge_pages(h)) {
if (!free_pool_huge_page(h, nodes_allowed, 0))
break;
cond_resched_lock(&hugetlb_lock);
+
+ /* Recompute min_count in case hugetlb_lock was dropped */
+ min_count = min_hp_count(h, count);
}
while (count < persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, 1))
--
2.30.2
