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, 16 insertions, 37 deletions

diff --git a/mm/sparse.c b/mm/sparse.c
index 952f06d8f373..cb3bfae64036 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -427,7 +427,8 @@ static unsigned long __init section_map_size(void)
 }
 
 struct page __init *__populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long size = section_map_size();
 	struct page *map = sparse_buffer_alloc(size);
@@ -524,7 +525,7 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 			break;
 
 		map = __populate_section_memmap(pfn, PAGES_PER_SECTION,
-				nid, NULL);
+				nid, NULL, NULL);
 		if (!map) {
 			pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.",
 			       __func__, nid);
@@ -629,9 +630,10 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 static struct page * __meminit populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
-	return __populate_section_memmap(pfn, nr_pages, nid, altmap);
+	return __populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 }
 
 static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
@@ -700,7 +702,8 @@ static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
 }
 #else
 struct page * __meminit populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	return kvmalloc_node(array_size(sizeof(struct page),
 					PAGES_PER_SECTION), GFP_KERNEL, nid);
@@ -823,7 +826,8 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 }
 
 static struct page * __meminit section_activate(int nid, unsigned long pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	struct mem_section *ms = __pfn_to_section(pfn);
 	struct mem_section_usage *usage = NULL;
@@ -855,7 +859,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
 	if (nr_pages < PAGES_PER_SECTION && early_section(ms))
 		return pfn_to_page(pfn);
 
-	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap);
+	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 	if (!memmap) {
 		section_deactivate(pfn, nr_pages, altmap);
 		return ERR_PTR(-ENOMEM);
@@ -869,7 +873,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
  * @nid: The node to add section on
  * @start_pfn: start pfn of the memory range
  * @nr_pages: number of pfns to add in the section
- * @altmap: device page map
+ * @altmap: alternate pfns to allocate the memmap backing store
+ * @pgmap: alternate compound page geometry for devmap mappings
  *
  * This is only intended for hotplug.
  *
@@ -883,7 +888,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
  * * -ENOMEM	- Out of memory.
  */
 int __meminit sparse_add_section(int nid, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct mem_section *ms;
@@ -894,7 +900,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 	if (ret < 0)
 		return ret;
 
-	memmap = section_activate(nid, start_pfn, nr_pages, altmap);
+	memmap = section_activate(nid, start_pfn, nr_pages, altmap, pgmap);
 	if (IS_ERR(memmap))
 		return PTR_ERR(memmap);
 
@@ -916,33 +922,6 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 	return 0;
 }
 
-#ifdef CONFIG_MEMORY_FAILURE
-static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-	int i;
-
-	/*
-	 * A further optimization is to have per section refcounted
-	 * num_poisoned_pages.  But that would need more space per memmap, so
-	 * for now just do a quick global check to speed up this routine in the
-	 * absence of bad pages.
-	 */
-	if (atomic_long_read(&num_poisoned_pages) == 0)
-		return;
-
-	for (i = 0; i < nr_pages; i++) {
-		if (PageHWPoison(&memmap[i])) {
-			num_poisoned_pages_dec();
-			ClearPageHWPoison(&memmap[i]);
-		}
-	}
-}
-#else
-static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-}
-#endif
-
 void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
 		unsigned long nr_pages, unsigned long map_offset,
 		struct vmem_altmap *altmap)