Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 69 insertions, 70 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 88433cc25d..0646547178 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -91,7 +91,7 @@ static unsigned int khugepaged_max_ptes_shared __read_mostly;
 #define MM_SLOTS_HASH_BITS 10
 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
 
-static struct kmem_cache *mm_slot_cache __read_mostly;
+static struct kmem_cache *mm_slot_cache __ro_after_init;
 
 struct collapse_control {
 	bool is_khugepaged;
@@ -524,15 +524,15 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte,
 	}
 }
 
-static bool is_refcount_suitable(struct page *page)
+static bool is_refcount_suitable(struct folio *folio)
 {
 	int expected_refcount;
 
-	expected_refcount = total_mapcount(page);
-	if (PageSwapCache(page))
-		expected_refcount += compound_nr(page);
+	expected_refcount = folio_mapcount(folio);
+	if (folio_test_swapcache(folio))
+		expected_refcount += folio_nr_pages(folio);
 
-	return page_count(page) == expected_refcount;
+	return folio_ref_count(folio) == expected_refcount;
 }
 
 static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
@@ -542,6 +542,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					struct list_head *compound_pagelist)
 {
 	struct page *page = NULL;
+	struct folio *folio = NULL;
 	pte_t *_pte;
 	int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
 	bool writable = false;
@@ -576,7 +577,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			goto out;
 		}
 
-		VM_BUG_ON_PAGE(!PageAnon(page), page);
+		folio = page_folio(page);
+		VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio);
 
 		if (page_mapcount(page) > 1) {
 			++shared;
@@ -588,16 +590,15 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			}
 		}
 
-		if (PageCompound(page)) {
-			struct page *p;
-			page = compound_head(page);
+		if (folio_test_large(folio)) {
+			struct folio *f;
 
 			/*
 			 * Check if we have dealt with the compound page
 			 * already
 			 */
-			list_for_each_entry(p, compound_pagelist, lru) {
-				if (page == p)
+			list_for_each_entry(f, compound_pagelist, lru) {
+				if (folio == f)
 					goto next;
 			}
 		}
@@ -608,7 +609,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 * is needed to serialize against split_huge_page
 		 * when invoked from the VM.
 		 */
-		if (!trylock_page(page)) {
+		if (!folio_trylock(folio)) {
 			result = SCAN_PAGE_LOCK;
 			goto out;
 		}
@@ -624,8 +625,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 * but not from this process. The other process cannot write to
 		 * the page, only trigger CoW.
 		 */
-		if (!is_refcount_suitable(page)) {
-			unlock_page(page);
+		if (!is_refcount_suitable(folio)) {
+			folio_unlock(folio);
 			result = SCAN_PAGE_COUNT;
 			goto out;
 		}
@@ -634,27 +635,27 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 * Isolate the page to avoid collapsing an hugepage
 		 * currently in use by the VM.
 		 */
-		if (!isolate_lru_page(page)) {
-			unlock_page(page);
+		if (!folio_isolate_lru(folio)) {
+			folio_unlock(folio);
 			result = SCAN_DEL_PAGE_LRU;
 			goto out;
 		}
-		mod_node_page_state(page_pgdat(page),
-				NR_ISOLATED_ANON + page_is_file_lru(page),
-				compound_nr(page));
-		VM_BUG_ON_PAGE(!PageLocked(page), page);
-		VM_BUG_ON_PAGE(PageLRU(page), page);
+		node_stat_mod_folio(folio,
+				NR_ISOLATED_ANON + folio_is_file_lru(folio),
+				folio_nr_pages(folio));
+		VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+		VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
-		if (PageCompound(page))
-			list_add_tail(&page->lru, compound_pagelist);
+		if (folio_test_large(folio))
+			list_add_tail(&folio->lru, compound_pagelist);
 next:
 		/*
 		 * If collapse was initiated by khugepaged, check that there is
 		 * enough young pte to justify collapsing the page
 		 */
 		if (cc->is_khugepaged &&
-		    (pte_young(pteval) || page_is_young(page) ||
-		     PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm,
+		    (pte_young(pteval) || folio_test_young(folio) ||
+		     folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
 								     address)))
 			referenced++;
 
@@ -668,13 +669,13 @@ next:
 		result = SCAN_LACK_REFERENCED_PAGE;
 	} else {
 		result = SCAN_SUCCEED;
-		trace_mm_collapse_huge_page_isolate(page, none_or_zero,
+		trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero,
 						    referenced, writable, result);
 		return result;
 	}
 out:
 	release_pte_pages(pte, _pte, compound_pagelist);
-	trace_mm_collapse_huge_page_isolate(page, none_or_zero,
+	trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero,
 					    referenced, writable, result);
 	return result;
 }
@@ -887,16 +888,16 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc)
 }
 #endif
 
-static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node,
+static bool hpage_collapse_alloc_folio(struct folio **folio, gfp_t gfp, int node,
 				      nodemask_t *nmask)
 {
-	*hpage = __alloc_pages(gfp, HPAGE_PMD_ORDER, node, nmask);
-	if (unlikely(!*hpage)) {
+	*folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, nmask);
+
+	if (unlikely(!*folio)) {
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 		return false;
 	}
 
-	folio_prep_large_rmappable((struct folio *)*hpage);
 	count_vm_event(THP_COLLAPSE_ALLOC);
 	return true;
 }
@@ -1063,17 +1064,20 @@ static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm,
 	int node = hpage_collapse_find_target_node(cc);
 	struct folio *folio;
 
-	if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask))
+	if (!hpage_collapse_alloc_folio(&folio, gfp, node, &cc->alloc_nmask)) {
+		*hpage = NULL;
 		return SCAN_ALLOC_HUGE_PAGE_FAIL;
+	}
 
-	folio = page_folio(*hpage);
 	if (unlikely(mem_cgroup_charge(folio, mm, gfp))) {
 		folio_put(folio);
 		*hpage = NULL;
 		return SCAN_CGROUP_CHARGE_FAIL;
 	}
-	count_memcg_page_event(*hpage, THP_COLLAPSE_ALLOC);
 
+	count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1);
+
+	*hpage = folio_page(folio, 0);
 	return SCAN_SUCCEED;
 }
 
@@ -1247,6 +1251,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 	int result = SCAN_FAIL, referenced = 0;
 	int none_or_zero = 0, shared = 0;
 	struct page *page = NULL;
+	struct folio *folio = NULL;
 	unsigned long _address;
 	spinlock_t *ptl;
 	int node = NUMA_NO_NODE, unmapped = 0;
@@ -1333,29 +1338,28 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 			}
 		}
 
-		page = compound_head(page);
-
+		folio = page_folio(page);
 		/*
 		 * Record which node the original page is from and save this
 		 * information to cc->node_load[].
 		 * Khugepaged will allocate hugepage from the node has the max
 		 * hit record.
 		 */
-		node = page_to_nid(page);
+		node = folio_nid(folio);
 		if (hpage_collapse_scan_abort(node, cc)) {
 			result = SCAN_SCAN_ABORT;
 			goto out_unmap;
 		}
 		cc->node_load[node]++;
-		if (!PageLRU(page)) {
+		if (!folio_test_lru(folio)) {
 			result = SCAN_PAGE_LRU;
 			goto out_unmap;
 		}
-		if (PageLocked(page)) {
+		if (folio_test_locked(folio)) {
 			result = SCAN_PAGE_LOCK;
 			goto out_unmap;
 		}
-		if (!PageAnon(page)) {
+		if (!folio_test_anon(folio)) {
 			result = SCAN_PAGE_ANON;
 			goto out_unmap;
 		}
@@ -1370,7 +1374,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 		 * has excessive GUP pins (i.e. 512).  Anyway the same check
 		 * will be done again later the risk seems low.
 		 */
-		if (!is_refcount_suitable(page)) {
+		if (!is_refcount_suitable(folio)) {
 			result = SCAN_PAGE_COUNT;
 			goto out_unmap;
 		}
@@ -1380,8 +1384,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 		 * enough young pte to justify collapsing the page
 		 */
 		if (cc->is_khugepaged &&
-		    (pte_young(pteval) || page_is_young(page) ||
-		     PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm,
+		    (pte_young(pteval) || folio_test_young(folio) ||
+		     folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
 								     address)))
 			referenced++;
 	}
@@ -1403,7 +1407,7 @@ out_unmap:
 		*mmap_locked = false;
 	}
 out:
-	trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
+	trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced,
 				     none_or_zero, result, unmapped);
 	return result;
 }
@@ -1473,7 +1477,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	bool notified = false;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	struct vm_area_struct *vma = vma_lookup(mm, haddr);
-	struct page *hpage;
+	struct folio *folio;
 	pte_t *start_pte, *pte;
 	pmd_t *pmd, pgt_pmd;
 	spinlock_t *pml = NULL, *ptl;
@@ -1506,19 +1510,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	if (userfaultfd_wp(vma))
 		return SCAN_PTE_UFFD_WP;
 
-	hpage = find_lock_page(vma->vm_file->f_mapping,
+	folio = filemap_lock_folio(vma->vm_file->f_mapping,
 			       linear_page_index(vma, haddr));
-	if (!hpage)
+	if (IS_ERR(folio))
 		return SCAN_PAGE_NULL;
 
-	if (!PageHead(hpage)) {
-		result = SCAN_FAIL;
-		goto drop_hpage;
-	}
-
-	if (compound_order(hpage) != HPAGE_PMD_ORDER) {
+	if (folio_order(folio) != HPAGE_PMD_ORDER) {
 		result = SCAN_PAGE_COMPOUND;
-		goto drop_hpage;
+		goto drop_folio;
 	}
 
 	result = find_pmd_or_thp_or_none(mm, haddr, &pmd);
@@ -1532,13 +1531,13 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		 */
 		goto maybe_install_pmd;
 	default:
-		goto drop_hpage;
+		goto drop_folio;
 	}
 
 	result = SCAN_FAIL;
 	start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
 	if (!start_pte)		/* mmap_lock + page lock should prevent this */
-		goto drop_hpage;
+		goto drop_folio;
 
 	/* step 1: check all mapped PTEs are to the right huge page */
 	for (i = 0, addr = haddr, pte = start_pte;
@@ -1563,7 +1562,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		 * Note that uprobe, debugger, or MAP_PRIVATE may change the
 		 * page table, but the new page will not be a subpage of hpage.
 		 */
-		if (hpage + i != page)
+		if (folio_page(folio, i) != page)
 			goto abort;
 	}
 
@@ -1578,7 +1577,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	 * page_table_lock) ptl nests inside pml. The less time we hold pml,
 	 * the better; but userfaultfd's mfill_atomic_pte() on a private VMA
 	 * inserts a valid as-if-COWed PTE without even looking up page cache.
-	 * So page lock of hpage does not protect from it, so we must not drop
+	 * So page lock of folio does not protect from it, so we must not drop
 	 * ptl before pgt_pmd is removed, so uffd private needs pml taken now.
 	 */
 	if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED))
@@ -1602,7 +1601,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 			continue;
 		/*
 		 * We dropped ptl after the first scan, to do the mmu_notifier:
-		 * page lock stops more PTEs of the hpage being faulted in, but
+		 * page lock stops more PTEs of the folio being faulted in, but
 		 * does not stop write faults COWing anon copies from existing
 		 * PTEs; and does not stop those being swapped out or migrated.
 		 */
@@ -1611,7 +1610,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 			goto abort;
 		}
 		page = vm_normal_page(vma, addr, ptent);
-		if (hpage + i != page)
+		if (folio_page(folio, i) != page)
 			goto abort;
 
 		/*
@@ -1630,8 +1629,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 
 	/* step 3: set proper refcount and mm_counters. */
 	if (nr_ptes) {
-		page_ref_sub(hpage, nr_ptes);
-		add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes);
+		folio_ref_sub(folio, nr_ptes);
+		add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes);
 	}
 
 	/* step 4: remove empty page table */
@@ -1655,14 +1654,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 maybe_install_pmd:
 	/* step 5: install pmd entry */
 	result = install_pmd
-			? set_huge_pmd(vma, haddr, pmd, hpage)
+			? set_huge_pmd(vma, haddr, pmd, &folio->page)
 			: SCAN_SUCCEED;
-	goto drop_hpage;
+	goto drop_folio;
 abort:
 	if (nr_ptes) {
 		flush_tlb_mm(mm);
-		page_ref_sub(hpage, nr_ptes);
-		add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes);
+		folio_ref_sub(folio, nr_ptes);
+		add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes);
 	}
 	if (start_pte)
 		pte_unmap_unlock(start_pte, ptl);
@@ -1670,9 +1669,9 @@ abort:
 		spin_unlock(pml);
 	if (notified)
 		mmu_notifier_invalidate_range_end(&range);
-drop_hpage:
-	unlock_page(hpage);
-	put_page(hpage);
+drop_folio:
+	folio_unlock(folio);
+	folio_put(folio);
 	return result;
 }