Merge tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Most of the MM queue. A few things are still pending.

  Liam's maple tree rework didn't make it. This has resulted in a few
  other minor patch series being held over for next time.

  Multi-gen LRU still isn't merged as we were waiting for mapletree to
  stabilize. The current plan is to merge MGLRU into -mm soon and to
  later reintroduce mapletree, with a view to hopefully getting both
  into 6.1-rc1.

  Summary:

   - The usual batches of cleanups from Baoquan He, Muchun Song, Miaohe
     Lin, Yang Shi, Anshuman Khandual and Mike Rapoport

   - Some kmemleak fixes from Patrick Wang and Waiman Long

   - DAMON updates from SeongJae Park

   - memcg debug/visibility work from Roman Gushchin

   - vmalloc speedup from Uladzislau Rezki

   - more folio conversion work from Matthew Wilcox

   - enhancements for coherent device memory mapping from Alex Sierra

   - addition of shared pages tracking and CoW support for fsdax, from
     Shiyang Ruan

   - hugetlb optimizations from Mike Kravetz

   - Mel Gorman has contributed some pagealloc changes to improve
     latency and realtime behaviour.

   - mprotect soft-dirty checking has been improved by Peter Xu

   - Many other singleton patches all over the place"

 [ XFS merge from hell as per Darrick Wong in

   https://lore.kernel.org/all/YshKnxb4VwXycPO8@magnolia/ ]

* tag 'mm-stable-2022-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (282 commits)
  tools/testing/selftests/vm/hmm-tests.c: fix build
  mm: Kconfig: fix typo
  mm: memory-failure: convert to pr_fmt()
  mm: use is_zone_movable_page() helper
  hugetlbfs: fix inaccurate comment in hugetlbfs_statfs()
  hugetlbfs: cleanup some comments in inode.c
  hugetlbfs: remove unneeded header file
  hugetlbfs: remove unneeded hugetlbfs_ops forward declaration
  hugetlbfs: use helper macro SZ_1{K,M}
  mm: cleanup is_highmem()
  mm/hmm: add a test for cross device private faults
  selftests: add soft-dirty into run_vmtests.sh
  selftests: soft-dirty: add test for mprotect
  mm/mprotect: fix soft-dirty check in can_change_pte_writable()
  mm: memcontrol: fix potential oom_lock recursion deadlock
  mm/gup.c: fix formatting in check_and_migrate_movable_page()
  xfs: fail dax mount if reflink is enabled on a partition
  mm/memcontrol.c: remove the redundant updating of stats_flush_threshold
  userfaultfd: don't fail on unrecognized features
  hugetlb_cgroup: fix wrong hugetlb cgroup numa stat
  ...

1 files changed, 59 insertions, 9 deletions

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 1089ea8a9c98..1362feb3c6c9 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -6,11 +6,11 @@
  *
  *     Author: Muchun Song <songmuchun@bytedance.com>
  *
- * See Documentation/vm/vmemmap_dedup.rst
+ * See Documentation/mm/vmemmap_dedup.rst
  */
 #define pr_fmt(fmt)	"HugeTLB: " fmt
 
-#include <linux/memory_hotplug.h>
+#include <linux/memory.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -97,18 +97,68 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
 	return ret;
 }
 
+static unsigned int vmemmap_optimizable_pages(struct hstate *h,
+					      struct page *head)
+{
+	if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) {
+		pmd_t *pmdp, pmd;
+		struct page *vmemmap_page;
+		unsigned long vaddr = (unsigned long)head;
+
+		/*
+		 * Only the vmemmap page's vmemmap page can be self-hosted.
+		 * Walking the page tables to find the backing page of the
+		 * vmemmap page.
+		 */
+		pmdp = pmd_off_k(vaddr);
+		/*
+		 * The READ_ONCE() is used to stabilize *pmdp in a register or
+		 * on the stack so that it will stop changing under the code.
+		 * The only concurrent operation where it can be changed is
+		 * split_vmemmap_huge_pmd() (*pmdp will be stable after this
+		 * operation).
+		 */
+		pmd = READ_ONCE(*pmdp);
+		if (pmd_leaf(pmd))
+			vmemmap_page = pmd_page(pmd) + pte_index(vaddr);
+		else
+			vmemmap_page = pte_page(*pte_offset_kernel(pmdp, vaddr));
+		/*
+		 * Due to HugeTLB alignment requirements and the vmemmap pages
+		 * being at the start of the hotplugged memory region in
+		 * memory_hotplug.memmap_on_memory case. Checking any vmemmap
+		 * page's vmemmap page if it is marked as VmemmapSelfHosted is
+		 * sufficient.
+		 *
+		 * [                  hotplugged memory                  ]
+		 * [        section        ][...][        section        ]
+		 * [ vmemmap ][              usable memory               ]
+		 *   ^   |     |                                        |
+		 *   +---+     |                                        |
+		 *     ^       |                                        |
+		 *     +-------+                                        |
+		 *          ^                                           |
+		 *          +-------------------------------------------+
+		 */
+		if (PageVmemmapSelfHosted(vmemmap_page))
+			return 0;
+	}
+
+	return hugetlb_optimize_vmemmap_pages(h);
+}
+
 void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
 {
 	unsigned long vmemmap_addr = (unsigned long)head;
 	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
 
-	vmemmap_pages = hugetlb_optimize_vmemmap_pages(h);
+	vmemmap_pages = vmemmap_optimizable_pages(h, head);
 	if (!vmemmap_pages)
 		return;
 
-	if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF)
-		return;
-
 	static_branch_inc(&hugetlb_optimize_vmemmap_key);
 
 	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
@@ -199,10 +249,10 @@ static struct ctl_table hugetlb_vmemmap_sysctls[] = {
 static __init int hugetlb_vmemmap_sysctls_init(void)
 {
 	/*
-	 * If "memory_hotplug.memmap_on_memory" is enabled or "struct page"
-	 * crosses page boundaries, the vmemmap pages cannot be optimized.
+	 * If "struct page" crosses page boundaries, the vmemmap pages cannot
+	 * be optimized.
 	 */
-	if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page)))
+	if (is_power_of_2(sizeof(struct page)))
 		register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
 
 	return 0;