From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlb: change free_pool_huge_page to remove_pool_huge_page
free_pool_huge_page was called with hugetlb_lock held. It would remove a
hugetlb page, and then free the corresponding pages to the lower level
allocators such as buddy. free_pool_huge_page was called in a loop to
remove hugetlb pages and these loops could hold the hugetlb_lock for a
considerable time.
Create new routine remove_pool_huge_page to replace free_pool_huge_page.
remove_pool_huge_page will remove the hugetlb page, and it must be called
with the hugetlb_lock held. It will return the removed page and it is the
responsibility of the caller to free the page to the lower level
allocators. The hugetlb_lock is dropped before freeing to these
allocators which results in shorter lock hold times.
Add new helper routine to call update_and_free_page for a list of pages.
Note: Some changes to the routine return_unused_surplus_pages are in need
of explanation. Commit e5bbc8a6c992 ("mm/hugetlb.c: fix reservation race
when freeing surplus pages") modified this routine to address a race which
could occur when dropping the hugetlb_lock in the loop that removes pool
pages. Accounting changes introduced in that commit were subtle and took
some thought to understand. This commit removes the cond_resched_lock()
and the potential race. Therefore, remove the subtle code and restore the
more straight forward accounting effectively reverting the commit.
Link: https://lkml.kernel.org/r/20210409205254.242291-7-mike.kravetz@xxxxxxxxxx
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Reviewed-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Barry Song <song.bao.hua@xxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Hillf Danton <hdanton@xxxxxxxx>
Cc: HORIGUCHI NAOYA <naoya.horiguchi@xxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Mina Almasry <almasrymina@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hugetlb.c | 93 ++++++++++++++++++++++++++-----------------------
1 file changed, 51 insertions(+), 42 deletions(-)
--- a/mm/hugetlb.c~hugetlb-change-free_pool_huge_page-to-remove_pool_huge_page
+++ a/mm/hugetlb.c
@@ -1211,7 +1211,7 @@ static int hstate_next_node_to_alloc(str
}
/*
- * helper for free_pool_huge_page() - return the previously saved
+ * helper for remove_pool_huge_page() - return the previously saved
* node ["this node"] from which to free a huge page. Advance the
* next node id whether or not we find a free huge page to free so
* that the next attempt to free addresses the next node.
@@ -1391,6 +1391,16 @@ static void update_and_free_page(struct
}
}
+static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list)
+{
+ struct page *page, *t_page;
+
+ list_for_each_entry_safe(page, t_page, list, lru) {
+ update_and_free_page(h, page);
+ cond_resched();
+ }
+}
+
struct hstate *size_to_hstate(unsigned long size)
{
struct hstate *h;
@@ -1721,16 +1731,18 @@ static int alloc_pool_huge_page(struct h
}
/*
- * Free huge page from pool from next node to free.
- * Attempt to keep persistent huge pages more or less
- * balanced over allowed nodes.
+ * Remove huge page from pool from next node to free. Attempt to keep
+ * persistent huge pages more or less balanced over allowed nodes.
+ * This routine only 'removes' the hugetlb page. The caller must make
+ * an additional call to free the page to low level allocators.
* Called with hugetlb_lock locked.
*/
-static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
- bool acct_surplus)
+static struct page *remove_pool_huge_page(struct hstate *h,
+ nodemask_t *nodes_allowed,
+ bool acct_surplus)
{
int nr_nodes, node;
- int ret = 0;
+ struct page *page = NULL;
for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
/*
@@ -1739,23 +1751,14 @@ static int free_pool_huge_page(struct hs
*/
if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
!list_empty(&h->hugepage_freelists[node])) {
- struct page *page =
- list_entry(h->hugepage_freelists[node].next,
+ page = list_entry(h->hugepage_freelists[node].next,
struct page, lru);
remove_hugetlb_page(h, page, acct_surplus);
- /*
- * unlock/lock around update_and_free_page is temporary
- * and will be removed with subsequent patch.
- */
- spin_unlock(&hugetlb_lock);
- update_and_free_page(h, page);
- spin_lock(&hugetlb_lock);
- ret = 1;
break;
}
}
- return ret;
+ return page;
}
/*
@@ -2075,17 +2078,16 @@ free:
* to the associated reservation map.
* 2) Free any unused surplus pages that may have been allocated to satisfy
* the reservation. As many as unused_resv_pages may be freed.
- *
- * Called with hugetlb_lock held. However, the lock could be dropped (and
- * reacquired) during calls to cond_resched_lock. Whenever dropping the lock,
- * we must make sure nobody else can claim pages we are in the process of
- * freeing. Do this by ensuring resv_huge_page always is greater than the
- * number of huge pages we plan to free when dropping the lock.
*/
static void return_unused_surplus_pages(struct hstate *h,
unsigned long unused_resv_pages)
{
unsigned long nr_pages;
+ struct page *page;
+ LIST_HEAD(page_list);
+
+ /* Uncommit the reservation */
+ h->resv_huge_pages -= unused_resv_pages;
/* Cannot return gigantic pages currently */
if (hstate_is_gigantic(h))
@@ -2102,24 +2104,21 @@ static void return_unused_surplus_pages(
* evenly across all nodes with memory. Iterate across these nodes
* until we can no longer free unreserved surplus pages. This occurs
* when the nodes with surplus pages have no free pages.
- * free_pool_huge_page() will balance the freed pages across the
+ * remove_pool_huge_page() will balance the freed pages across the
* on-line nodes with memory and will handle the hstate accounting.
- *
- * Note that we decrement resv_huge_pages as we free the pages. If
- * we drop the lock, resv_huge_pages will still be sufficiently large
- * to cover subsequent pages we may free.
*/
while (nr_pages--) {
- h->resv_huge_pages--;
- unused_resv_pages--;
- if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
+ page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1);
+ if (!page)
goto out;
- cond_resched_lock(&hugetlb_lock);
+
+ list_add(&page->lru, &page_list);
}
out:
- /* Fully uncommit the reservation */
- h->resv_huge_pages -= unused_resv_pages;
+ spin_unlock(&hugetlb_lock);
+ update_and_free_pages_bulk(h, &page_list);
+ spin_lock(&hugetlb_lock);
}
@@ -2572,7 +2571,6 @@ static void try_to_free_low(struct hstat
nodemask_t *nodes_allowed)
{
int i;
- struct page *page, *next;
LIST_HEAD(page_list);
if (hstate_is_gigantic(h))
@@ -2582,6 +2580,7 @@ static void try_to_free_low(struct hstat
* Collect pages to be freed on a list, and free after dropping lock
*/
for_each_node_mask(i, *nodes_allowed) {
+ 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)
@@ -2595,10 +2594,7 @@ static void try_to_free_low(struct hstat
out:
spin_unlock(&hugetlb_lock);
- list_for_each_entry_safe(page, next, &page_list, lru) {
- update_and_free_page(h, page);
- cond_resched();
- }
+ update_and_free_pages_bulk(h, &page_list);
spin_lock(&hugetlb_lock);
}
#else
@@ -2645,6 +2641,8 @@ static int set_max_huge_pages(struct hst
nodemask_t *nodes_allowed)
{
unsigned long min_count, ret;
+ struct page *page;
+ LIST_HEAD(page_list);
NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL);
/*
@@ -2757,11 +2755,22 @@ static int set_max_huge_pages(struct hst
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);
+
+ /*
+ * Collect pages to be removed on list without dropping lock
+ */
while (min_count < persistent_huge_pages(h)) {
- if (!free_pool_huge_page(h, nodes_allowed, 0))
+ page = remove_pool_huge_page(h, nodes_allowed, 0);
+ if (!page)
break;
- cond_resched_lock(&hugetlb_lock);
+
+ list_add(&page->lru, &page_list);
}
+ /* free the pages after dropping lock */
+ spin_unlock(&hugetlb_lock);
+ update_and_free_pages_bulk(h, &page_list);
+ spin_lock(&hugetlb_lock);
+
while (count < persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, 1))
break;
_
