Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

1 files changed, 8 insertions, 10 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index cadfbb5155ea..07db42455dd4 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -389,18 +389,15 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 {
 	p4d_t *p4d;
 	unsigned long next;
-	int cleared;
 
 	p4d = p4d_offset(pgd, addr);
 	do {
 		next = p4d_addr_end(addr, end);
 
-		cleared = p4d_clear_huge(p4d);
-		if (cleared || p4d_bad(*p4d))
+		p4d_clear_huge(p4d);
+		if (p4d_bad(*p4d))
 			*mask |= PGTBL_P4D_MODIFIED;
 
-		if (cleared)
-			continue;
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
 		vunmap_pud_range(p4d, addr, next, mask);
@@ -478,6 +475,9 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 			return -EBUSY;
 		if (WARN_ON(!page))
 			return -ENOMEM;
+		if (WARN_ON(!pfn_valid(page_to_pfn(page))))
+			return -EINVAL;
+
 		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
 		(*nr)++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
@@ -1938,11 +1938,10 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
 		return ERR_PTR(err);
 	}
 
-	vbq = &get_cpu_var(vmap_block_queue);
+	vbq = raw_cpu_ptr(&vmap_block_queue);
 	spin_lock(&vbq->lock);
 	list_add_tail_rcu(&vb->free_list, &vbq->free);
 	spin_unlock(&vbq->lock);
-	put_cpu_var(vmap_block_queue);
 
 	return vaddr;
 }
@@ -2021,7 +2020,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 	order = get_order(size);
 
 	rcu_read_lock();
-	vbq = &get_cpu_var(vmap_block_queue);
+	vbq = raw_cpu_ptr(&vmap_block_queue);
 	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
 		unsigned long pages_off;
 
@@ -2044,7 +2043,6 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 		break;
 	}
 
-	put_cpu_var(vmap_block_queue);
 	rcu_read_unlock();
 
 	/* Allocate new block if nothing was found */
@@ -2895,7 +2893,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			/* memory allocation should consider mempolicy, we can't
 			 * wrongly use nearest node when nid == NUMA_NO_NODE,
 			 * otherwise memory may be allocated in only one node,
-			 * but mempolcy want to alloc memory by interleaving.
+			 * but mempolicy wants to alloc memory by interleaving.
 			 */
 			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
 				nr = alloc_pages_bulk_array_mempolicy(bulk_gfp,