+ mm-hugetlb-add-dedicated-func-to-get-allowed-nodemask-for-current-process.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: mm/hugetlb: add dedicated func to get 'allowed' nodemask for current process
has been added to the -mm mm-unstable branch.  Its filename is
     mm-hugetlb-add-dedicated-func-to-get-allowed-nodemask-for-current-process.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-hugetlb-add-dedicated-func-to-get-allowed-nodemask-for-current-process.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: Feng Tang <feng.tang@intel.com>
Subject: mm/hugetlb: add dedicated func to get 'allowed' nodemask for current process
Date: Fri, 5 Aug 2022 08:59:03 +0800

Muchun Song found that after MPOL_PREFERRED_MANY policy was introduced in
commit b27abaccf8e8 ("mm/mempolicy: add MPOL_PREFERRED_MANY for multiple
preferred nodes"), the policy_nodemask_current()'s semantics for this new
policy has been changed, which returns 'preferred' nodes instead of
'allowed' nodes.

With the changed semantic of policy_nodemask_current, a task with
MPOL_PREFERRED_MANY policy could fail to get its reservation even though
it can fall back to other nodes (either defined by cpusets or all online
nodes) for that reservation failing mmap calles unnecessarily early.

The fix is to not consider MPOL_PREFERRED_MANY for reservations at all
because they, unlike MPOL_MBIND, do not pose any actual hard constrain.

Michal suggested the policy_nodemask_current() is only used by hugetlb,
and could be moved to hugetlb code with more explicit name to enforce the
'allowed' semantics for which only MPOL_BIND policy matters.

apply_policy_zone() is made extern to be called in hugetlb code and its
return value is changed to bool.

[1]. https://lore.kernel.org/lkml/20220801084207.39086-1-songmuchun@bytedance.com/t/

Link: https://lkml.kernel.org/r/20220805005903.95563-1-feng.tang@intel.com
Fixes: b27abaccf8e8 ("mm/mempolicy: add MPOL_PREFERRED_MANY for multiple preferred nodes")
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reported-by: Muchun Song <songmuchun@bytedance.com>
Suggested-by: Michal Hocko <mhocko@suse.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ben Widawsky <bwidawsk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/mempolicy.h |   13 +------------
 mm/hugetlb.c              |   24 ++++++++++++++++++++----
 mm/mempolicy.c            |    2 +-
 3 files changed, 22 insertions(+), 17 deletions(-)

--- a/include/linux/mempolicy.h~mm-hugetlb-add-dedicated-func-to-get-allowed-nodemask-for-current-process
+++ a/include/linux/mempolicy.h
@@ -151,13 +151,6 @@ extern bool mempolicy_in_oom_domain(stru
 				const nodemask_t *mask);
 extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy);
 
-static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
-{
-	struct mempolicy *mpol = get_task_policy(current);
-
-	return policy_nodemask(gfp, mpol);
-}
-
 extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
@@ -189,6 +182,7 @@ static inline bool mpol_is_preferred_man
 	return  (pol->mode == MPOL_PREFERRED_MANY);
 }
 
+extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone);
 
 #else
 
@@ -294,11 +288,6 @@ static inline void mpol_put_task_policy(
 {
 }
 
-static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
-{
-	return NULL;
-}
-
 static inline bool mpol_is_preferred_many(struct mempolicy *pol)
 {
 	return  false;
--- a/mm/hugetlb.c~mm-hugetlb-add-dedicated-func-to-get-allowed-nodemask-for-current-process
+++ a/mm/hugetlb.c
@@ -4330,18 +4330,34 @@ 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;
 	unsigned int nr = 0;
-	nodemask_t *mpol_allowed;
+	nodemask_t *mbind_nodemask;
 	unsigned int *array = h->free_huge_pages_node;
 	gfp_t gfp_mask = htlb_alloc_mask(h);
 
-	mpol_allowed = policy_nodemask_current(gfp_mask);
-
+	mbind_nodemask = policy_mbind_nodemask(gfp_mask);
 	for_each_node_mask(node, cpuset_current_mems_allowed) {
-		if (!mpol_allowed || node_isset(node, *mpol_allowed))
+		if (!mbind_nodemask || node_isset(node, *mbind_nodemask))
 			nr += array[node];
 	}
 
--- a/mm/mempolicy.c~mm-hugetlb-add-dedicated-func-to-get-allowed-nodemask-for-current-process
+++ a/mm/mempolicy.c
@@ -1805,7 +1805,7 @@ bool vma_policy_mof(struct vm_area_struc
 	return pol->flags & MPOL_F_MOF;
 }
 
-static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
+bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
 {
 	enum zone_type dynamic_policy_zone = policy_zone;
 
_

Patches currently in -mm which might be from feng.tang@intel.com are

mm-hugetlb-add-dedicated-func-to-get-allowed-nodemask-for-current-process.patch