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, 37 insertions, 37 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 8c74107a2b15..d39b01fd52fe 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -104,6 +104,7 @@
 #include <linux/swapops.h>
 
 #include <asm/tlbflush.h>
+#include <asm/tlb.h>
 #include <linux/uaccess.h>
 
 #include "internal.h"
@@ -350,7 +351,7 @@ static void mpol_rebind_preferred(struct mempolicy *pol,
  */
 static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
 {
-	if (!pol)
+	if (!pol || pol->mode == MPOL_LOCAL)
 		return;
 	if (!mpol_store_user_nodemask(pol) &&
 	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
@@ -440,12 +441,11 @@ static inline bool queue_pages_required(struct page *page,
 }
 
 /*
- * queue_pages_pmd() has four possible return values:
+ * queue_pages_pmd() has three possible return values:
  * 0 - pages are placed on the right node or queued successfully, or
  *     special page is met, i.e. huge zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
- * 2 - THP was split.
  * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
  *        existing page was already on a node that does not follow the
  *        policy.
@@ -507,18 +507,13 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 	struct queue_pages *qp = walk->private;
 	unsigned long flags = qp->flags;
-	int ret;
 	bool has_unmovable = false;
 	pte_t *pte, *mapped_pte;
 	spinlock_t *ptl;
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
-	if (ptl) {
-		ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
-		if (ret != 2)
-			return ret;
-	}
-	/* THP was split, fall through to pte walk */
+	if (ptl)
+		return queue_pages_pmd(pmd, ptl, addr, end, walk);
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
@@ -636,12 +631,18 @@ unlock:
 unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long addr, unsigned long end)
 {
+	struct mmu_gather tlb;
 	int nr_updated;
 
-	nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA);
+	tlb_gather_mmu(&tlb, vma->vm_mm);
+
+	nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE,
+				       MM_CP_PROT_NUMA);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 
+	tlb_finish_mmu(&tlb);
+
 	return nr_updated;
 }
 #else
@@ -2135,44 +2136,55 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
 }
 
 /**
- * alloc_pages_vma - Allocate a page for a VMA.
+ * vma_alloc_folio - Allocate a folio for a VMA.
  * @gfp: GFP flags.
- * @order: Order of the GFP allocation.
+ * @order: Order of the folio.
  * @vma: Pointer to VMA or NULL if not available.
  * @addr: Virtual address of the allocation.  Must be inside @vma.
  * @hugepage: For hugepages try only the preferred node if possible.
  *
- * Allocate a page for a specific address in @vma, using the appropriate
+ * Allocate a folio for a specific address in @vma, using the appropriate
  * NUMA policy.  When @vma is not NULL the caller must hold the mmap_lock
  * of the mm_struct of the VMA to prevent it from going away.  Should be
- * used for all allocations for pages that will be mapped into user space.
+ * used for all allocations for folios that will be mapped into user space.
  *
- * Return: The page on success or NULL if allocation fails.
+ * Return: The folio on success or NULL if allocation fails.
  */
-struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
+struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, bool hugepage)
 {
 	struct mempolicy *pol;
 	int node = numa_node_id();
-	struct page *page;
+	struct folio *folio;
 	int preferred_nid;
 	nodemask_t *nmask;
 
 	pol = get_vma_policy(vma, addr);
 
 	if (pol->mode == MPOL_INTERLEAVE) {
+		struct page *page;
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
+		gfp |= __GFP_COMP;
 		page = alloc_page_interleave(gfp, order, nid);
+		if (page && order > 1)
+			prep_transhuge_page(page);
+		folio = (struct folio *)page;
 		goto out;
 	}
 
 	if (pol->mode == MPOL_PREFERRED_MANY) {
+		struct page *page;
+
 		node = policy_node(gfp, pol, node);
+		gfp |= __GFP_COMP;
 		page = alloc_pages_preferred_many(gfp, order, node, pol);
 		mpol_cond_put(pol);
+		if (page && order > 1)
+			prep_transhuge_page(page);
+		folio = (struct folio *)page;
 		goto out;
 	}
 
@@ -2199,8 +2211,8 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 			 * First, try to allocate THP only on local node, but
 			 * don't reclaim unnecessarily, just compact.
 			 */
-			page = __alloc_pages_node(hpage_node,
-				gfp | __GFP_THISNODE | __GFP_NORETRY, order);
+			folio = __folio_alloc_node(gfp | __GFP_THISNODE |
+					__GFP_NORETRY, order, hpage_node);
 
 			/*
 			 * If hugepage allocations are configured to always
@@ -2208,8 +2220,9 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 			 * to prefer hugepage backing, retry allowing remote
 			 * memory with both reclaim and compact as well.
 			 */
-			if (!page && (gfp & __GFP_DIRECT_RECLAIM))
-				page = __alloc_pages(gfp, order, hpage_node, nmask);
+			if (!folio && (gfp & __GFP_DIRECT_RECLAIM))
+				folio = __folio_alloc(gfp, order, hpage_node,
+						      nmask);
 
 			goto out;
 		}
@@ -2217,25 +2230,12 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 	nmask = policy_nodemask(gfp, pol);
 	preferred_nid = policy_node(gfp, pol, node);
-	page = __alloc_pages(gfp, order, preferred_nid, nmask);
+	folio = __folio_alloc(gfp, order, preferred_nid, nmask);
 	mpol_cond_put(pol);
 out:
-	return page;
-}
-EXPORT_SYMBOL(alloc_pages_vma);
-
-struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, bool hugepage)
-{
-	struct folio *folio;
-
-	folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr,
-			hugepage);
-	if (folio && order > 1)
-		prep_transhuge_page(&folio->page);
-
 	return folio;
 }
+EXPORT_SYMBOL(vma_alloc_folio);
 
 /**
  * alloc_pages - Allocate pages.