Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few MM hotfixes

 - kthread, tools, scripts, ntfs and ocfs2

 - some of MM

Subsystems affected by this patch series: kthread, tools, scripts, ntfs,
ocfs2 and mm (hofixes, pagealloc, slab-generic, slab, slub, kcsan,
debug, pagecache, gup, swap, shmem, memcg, pagemap, mremap, mincore,
sparsemem, vmalloc, kasan, pagealloc, hugetlb and vmscan).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits)
  mm: vmscan: consistent update to pgrefill
  mm/vmscan.c: fix typo
  khugepaged: khugepaged_test_exit() check mmget_still_valid()
  khugepaged: retract_page_tables() remember to test exit
  khugepaged: collapse_pte_mapped_thp() protect the pmd lock
  khugepaged: collapse_pte_mapped_thp() flush the right range
  mm/hugetlb: fix calculation of adjust_range_if_pmd_sharing_possible
  mm: thp: replace HTTP links with HTTPS ones
  mm/page_alloc: fix memalloc_nocma_{save/restore} APIs
  mm/page_alloc.c: skip setting nodemask when we are in interrupt
  mm/page_alloc: fallbacks at most has 3 elements
  mm/page_alloc: silence a KASAN false positive
  mm/page_alloc.c: remove unnecessary end_bitidx for [set|get]_pfnblock_flags_mask()
  mm/page_alloc.c: simplify pageblock bitmap access
  mm/page_alloc.c: extract the common part in pfn_to_bitidx()
  mm/page_alloc.c: replace the definition of NR_MIGRATETYPE_BITS with PB_migratetype_bits
  mm/shuffle: remove dynamic reconfiguration
  mm/memory_hotplug: document why shuffle_zone() is relevant
  mm/page_alloc: remove nr_free_pagecache_pages()
  mm: remove vm_total_pages
  ...

1 files changed, 49 insertions, 3 deletions

diff --git a/mm/util.c b/mm/util.c
index c63c8e47be57..5ef378a2a038 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -503,8 +503,8 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	if (!ret) {
 		if (mmap_write_lock_killable(mm))
 			return -EINTR;
-		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
-				    &populate, &uf);
+		ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate,
+			      &uf);
 		mmap_write_unlock(mm);
 		userfaultfd_unmap_complete(mm, &uf);
 		if (populate)
@@ -746,6 +746,47 @@ int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
 	return ret;
 }
 
+static void sync_overcommit_as(struct work_struct *dummy)
+{
+	percpu_counter_sync(&vm_committed_as);
+}
+
+int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int new_policy;
+	int ret;
+
+	/*
+	 * The deviation of sync_overcommit_as could be big with loose policy
+	 * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to
+	 * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply
+	 * with the strict "NEVER", and to avoid possible race condtion (even
+	 * though user usually won't too frequently do the switching to policy
+	 * OVERCOMMIT_NEVER), the switch is done in the following order:
+	 *	1. changing the batch
+	 *	2. sync percpu count on each CPU
+	 *	3. switch the policy
+	 */
+	if (write) {
+		t = *table;
+		t.data = &new_policy;
+		ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+		if (ret)
+			return ret;
+
+		mm_compute_batch(new_policy);
+		if (new_policy == OVERCOMMIT_NEVER)
+			schedule_on_each_cpu(sync_overcommit_as);
+		sysctl_overcommit_memory = new_policy;
+	} else {
+		ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	}
+
+	return ret;
+}
+
 int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
@@ -787,10 +828,15 @@ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
  * balancing memory across competing virtual machines that are hosted.
  * Several metrics drive this policy engine including the guest reported
  * memory commitment.
+ *
+ * The time cost of this is very low for small platforms, and for big
+ * platform like a 2S/36C/72T Skylake server, in worst case where
+ * vm_committed_as's spinlock is under severe contention, the time cost
+ * could be about 30~40 microseconds.
  */
 unsigned long vm_memory_committed(void)
 {
-	return percpu_counter_read_positive(&vm_committed_as);
+	return percpu_counter_sum_positive(&vm_committed_as);
 }
 EXPORT_SYMBOL_GPL(vm_memory_committed);