The patch titled
Subject: hugetlb: force allocating surplus hugepages on mempolicy allowed nodes
has been added to the -mm mm-unstable branch. Its filename is
hugetlb-force-allocating-surplus-hugepages-on-mempolicy-allowed-nodes.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hugetlb-force-allocating-surplus-hugepages-on-mempolicy-allowed-nodes.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Aristeu Rozanski <aris@xxxxxxxxxx>
Subject: hugetlb: force allocating surplus hugepages on mempolicy allowed nodes
Date: Fri, 21 Jun 2024 15:00:50 -0400
allowed_mems_nr() only accounts for the number of free hugepages in the
nodes the current process belongs to. In case one or more of the
requested surplus hugepages are allocated in a different node, the whole
allocation will fail due allowed_mems_nr() returning a lower value.
So allocate surplus hugepages in one of the nodes the current process belongs to.
Easy way to reproduce this issue is to use a 2+ NUMA nodes system:
# echo 0 >/proc/sys/vm/nr_hugepages
# echo 1 >/proc/sys/vm/nr_overcommit_hugepages
# numactl -m0 ./tools/testing/selftests/mm/map_hugetlb 2
will eventually fail when the hugepage ends up allocated in a different node.
Link: https://lkml.kernel.org/r/20240621190050.mhxwb65zn37doegp@xxxxxxxxxx
Signed-off-by: Aristeu Rozanski <aris@xxxxxxxxxx>
Cc: Muchun Song <muchun.song@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/hugetlb.c | 46 +++++++++++++++++++++++++++-------------------
1 file changed, 27 insertions(+), 19 deletions(-)
--- a/mm/hugetlb.c~hugetlb-force-allocating-surplus-hugepages-on-mempolicy-allowed-nodes
+++ a/mm/hugetlb.c
@@ -2620,6 +2620,23 @@ struct folio *alloc_hugetlb_folio_nodema
return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask);
}
+static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
+{
+#ifdef CONFIG_NUMA
+ struct mempolicy *mpol = get_task_policy(current);
+
+ /*
+ * Only enforce MPOL_BIND policy which overlaps with cpuset policy
+ * (from policy_nodemask) specifically for hugetlb case
+ */
+ if (mpol->mode == MPOL_BIND &&
+ (apply_policy_zone(mpol, gfp_zone(gfp)) &&
+ cpuset_nodemask_valid_mems_allowed(&mpol->nodes)))
+ return &mpol->nodes;
+#endif
+ return NULL;
+}
+
/*
* Increase the hugetlb pool such that it can accommodate a reservation
* of size 'delta'.
@@ -2633,6 +2650,8 @@ static int gather_surplus_pages(struct h
long i;
long needed, allocated;
bool alloc_ok = true;
+ int node;
+ nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
lockdep_assert_held(&hugetlb_lock);
needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
@@ -2647,8 +2666,14 @@ static int gather_surplus_pages(struct h
retry:
spin_unlock_irq(&hugetlb_lock);
for (i = 0; i < needed; i++) {
- folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
- NUMA_NO_NODE, NULL);
+ for_each_node_mask(node, cpuset_current_mems_allowed) {
+ if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) {
+ folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
+ node, NULL);
+ if (folio)
+ break;
+ }
+ }
if (!folio) {
alloc_ok = false;
break;
@@ -4878,23 +4903,6 @@ static int __init default_hugepagesz_set
}
__setup("default_hugepagesz=", default_hugepagesz_setup);
-static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
-{
-#ifdef CONFIG_NUMA
- struct mempolicy *mpol = get_task_policy(current);
-
- /*
- * Only enforce MPOL_BIND policy which overlaps with cpuset policy
- * (from policy_nodemask) specifically for hugetlb case
- */
- if (mpol->mode == MPOL_BIND &&
- (apply_policy_zone(mpol, gfp_zone(gfp)) &&
- cpuset_nodemask_valid_mems_allowed(&mpol->nodes)))
- return &mpol->nodes;
-#endif
- return NULL;
-}
-
static unsigned int allowed_mems_nr(struct hstate *h)
{
int node;
_
Patches currently in -mm which might be from aris@xxxxxxxxxx are
hugetlb-force-allocating-surplus-hugepages-on-mempolicy-allowed-nodes.patch
