mm/hugetlb: add mempolicy check in the reservation routine

In the reservation routine, we only check whether the cpuset meets the
memory allocation requirements.  But we ignore the mempolicy of MPOL_BIND
case.  If someone mmap hugetlb succeeds, but the subsequent memory
allocation may fail due to mempolicy restrictions and receives the SIGBUS
signal.  This can be reproduced by the follow steps.

 1) Compile the test case.
    cd tools/testing/selftests/vm/
    gcc map_hugetlb.c -o map_hugetlb

 2) Pre-allocate huge pages. Suppose there are 2 numa nodes in the
    system. Each node will pre-allocate one huge page.
    echo 2 > /proc/sys/vm/nr_hugepages

 3) Run test case(mmap 4MB). We receive the SIGBUS signal.
    numactl --membind=3D0 ./map_hugetlb 4

With this patch applied, the mmap will fail in the step 3) and throw
"mmap: Cannot allocate memory".

[akpm@linux-foundation.org: include sched.h for `current']
Reported-by: Jianchao Guo <guojianchao@bytedance.com>
Suggested-by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michel Lespinasse <walken@google.com>
Cc: Baoquan He <bhe@redhat.com>
Link: http://lkml.kernel.org/r/20200728034938.14993-1-songmuchun@bytedance.comSigned-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/mempolicy.h

@@ -6,7 +6,7 @@
 #ifndef _LINUX_MEMPOLICY_H
 #define _LINUX_MEMPOLICY_H 1
 
-
+#include <linux/sched.h>
 #include <linux/mmzone.h>
 #include <linux/dax.h>
 #include <linux/slab.h>
@@ -152,6 +152,15 @@ extern int huge_node(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				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;
@@ -281,5 +290,10 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
 static inline void mpol_put_task_policy(struct task_struct *task)
 {
 }
+
+static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
+{
+	return NULL;
+}
 #endif /* CONFIG_NUMA */
 #endif

mm/hugetlb.c

@@ -3458,13 +3458,21 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
-static unsigned int cpuset_mems_nr(unsigned int *array)
+static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;
 	unsigned int nr = 0;
+	nodemask_t *mpol_allowed;
+	unsigned int *array = h->free_huge_pages_node;
+	gfp_t gfp_mask = htlb_alloc_mask(h);
+
+	mpol_allowed = policy_nodemask_current(gfp_mask);
 
-	for_each_node_mask(node, cpuset_current_mems_allowed)
+	for_each_node_mask(node, cpuset_current_mems_allowed) {
+		if (!mpol_allowed ||
+		    (mpol_allowed && node_isset(node, *mpol_allowed)))
 			nr += array[node];
+	}
 
 	return nr;
 }
@@ -3643,12 +3651,18 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
 	 * we fall back to check against current free page availability as
 	 * a best attempt and hopefully to minimize the impact of changing
 	 * semantics that cpuset has.
+	 *
+	 * Apart from cpuset, we also have memory policy mechanism that
+	 * also determines from which node the kernel will allocate memory
+	 * in a NUMA system. So similar to cpuset, we also should consider
+	 * the memory policy of the current task. Similar to the description
+	 * above.
 	 */
 	if (delta > 0) {
 		if (gather_surplus_pages(h, delta) < 0)
 			goto out;
 
-		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+		if (delta > allowed_mems_nr(h)) {
 			return_unused_surplus_pages(h, delta);
 			goto out;
 		}

mm/mempolicy.c

@@ -1890,7 +1890,7 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
  * Return a nodemask representing a mempolicy for filtering nodes for
  * page allocation
  */
-static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
+nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 {
 	/* Lower zones don't get a nodemask applied for MPOL_BIND */
 	if (unlikely(policy->mode == MPOL_BIND) &&