Merge branch 'edac-amd64' into edac-updates-for-v5.18

Signed-off-by: Borislav Petkov <bp@suse.de>

12 files changed, 109 insertions, 68 deletions

diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index a7ac97c76762..db2abd9e415b 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -171,6 +171,8 @@ static void __init pte_advanced_tests(struct pgtable_debug_args *args)
 	ptep_test_and_clear_young(args->vma, args->vaddr, args->ptep);
 	pte = ptep_get(args->ptep);
 	WARN_ON(pte_young(pte));
+
+	ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1);
 }
 
 static void __init pte_savedwrite_tests(struct pgtable_debug_args *args)
diff --git a/mm/gup.c b/mm/gup.c
index f0af462ac1e2..a9d4d724aef7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -124,8 +124,8 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
  * considered failure, and furthermore, a likely bug in the caller, so a warning
  * is also emitted.
  */
-struct page *try_grab_compound_head(struct page *page,
-				    int refs, unsigned int flags)
+__maybe_unused struct page *try_grab_compound_head(struct page *page,
+						   int refs, unsigned int flags)
 {
 	if (flags & FOLL_GET)
 		return try_get_compound_head(page, refs);
@@ -208,10 +208,35 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags)
  */
 bool __must_check try_grab_page(struct page *page, unsigned int flags)
 {
-	if (!(flags & (FOLL_GET | FOLL_PIN)))
-		return true;
+	WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
 
-	return try_grab_compound_head(page, 1, flags);
+	if (flags & FOLL_GET)
+		return try_get_page(page);
+	else if (flags & FOLL_PIN) {
+		int refs = 1;
+
+		page = compound_head(page);
+
+		if (WARN_ON_ONCE(page_ref_count(page) <= 0))
+			return false;
+
+		if (hpage_pincount_available(page))
+			hpage_pincount_add(page, 1);
+		else
+			refs = GUP_PIN_COUNTING_BIAS;
+
+		/*
+		 * Similar to try_grab_compound_head(): even if using the
+		 * hpage_pincount_add/_sub() routines, be sure to
+		 * *also* increment the normal page refcount field at least
+		 * once, so that the page really is pinned.
+		 */
+		page_ref_add(page, refs);
+
+		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1);
+	}
+
+	return true;
 }
 
 /**
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 5ad40e3add45..13128fa13062 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -47,7 +47,8 @@
 
 static bool kfence_enabled __read_mostly;
 
-static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL;
+unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL;
+EXPORT_SYMBOL_GPL(kfence_sample_interval); /* Export for test modules. */
 
 #ifdef MODULE_PARAM_PREFIX
 #undef MODULE_PARAM_PREFIX
diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c
index a22b1af85577..50dbb815a2a8 100644
--- a/mm/kfence/kfence_test.c
+++ b/mm/kfence/kfence_test.c
@@ -268,13 +268,13 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat
 	 * 100x the sample interval should be more than enough to ensure we get
 	 * a KFENCE allocation eventually.
 	 */
-	timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL);
+	timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval);
 	/*
 	 * Especially for non-preemption kernels, ensure the allocation-gate
 	 * timer can catch up: after @resched_after, every failed allocation
 	 * attempt yields, to ensure the allocation-gate timer is scheduled.
 	 */
-	resched_after = jiffies + msecs_to_jiffies(CONFIG_KFENCE_SAMPLE_INTERVAL);
+	resched_after = jiffies + msecs_to_jiffies(kfence_sample_interval);
 	do {
 		if (test_cache)
 			alloc = kmem_cache_alloc(test_cache, gfp);
@@ -608,7 +608,7 @@ static void test_gfpzero(struct kunit *test)
 	int i;
 
 	/* Skip if we think it'd take too long. */
-	KFENCE_TEST_REQUIRES(test, CONFIG_KFENCE_SAMPLE_INTERVAL <= 100);
+	KFENCE_TEST_REQUIRES(test, kfence_sample_interval <= 100);
 
 	setup_test_cache(test, size, 0, NULL);
 	buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY);
@@ -739,7 +739,7 @@ static void test_memcache_alloc_bulk(struct kunit *test)
 	 * 100x the sample interval should be more than enough to ensure we get
 	 * a KFENCE allocation eventually.
 	 */
-	timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL);
+	timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval);
 	do {
 		void *objects[100];
 		int i, num = kmem_cache_alloc_bulk(test_cache, GFP_ATOMIC, ARRAY_SIZE(objects),
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 35f14d0a00a6..131492fd1148 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -16,6 +16,7 @@
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
+#include <linux/page_table_check.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 
@@ -1416,6 +1417,21 @@ static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm,
 	return 0;
 }
 
+static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+				  unsigned long addr, pmd_t *pmdp)
+{
+	spinlock_t *ptl;
+	pmd_t pmd;
+
+	mmap_assert_write_locked(mm);
+	ptl = pmd_lock(vma->vm_mm, pmdp);
+	pmd = pmdp_collapse_flush(vma, addr, pmdp);
+	spin_unlock(ptl);
+	mm_dec_nr_ptes(mm);
+	page_table_check_pte_clear_range(mm, addr, pmd);
+	pte_free(mm, pmd_pgtable(pmd));
+}
+
 /**
  * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at
  * address haddr.
@@ -1433,7 +1449,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma = find_vma(mm, haddr);
 	struct page *hpage;
 	pte_t *start_pte, *pte;
-	pmd_t *pmd, _pmd;
+	pmd_t *pmd;
 	spinlock_t *ptl;
 	int count = 0;
 	int i;
@@ -1509,12 +1525,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	}
 
 	/* step 4: collapse pmd */
-	ptl = pmd_lock(vma->vm_mm, pmd);
-	_pmd = pmdp_collapse_flush(vma, haddr, pmd);
-	spin_unlock(ptl);
-	mm_dec_nr_ptes(mm);
-	pte_free(mm, pmd_pgtable(_pmd));
-
+	collapse_and_free_pmd(mm, vma, haddr, pmd);
 drop_hpage:
 	unlock_page(hpage);
 	put_page(hpage);
@@ -1552,7 +1563,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
 	unsigned long addr;
-	pmd_t *pmd, _pmd;
+	pmd_t *pmd;
 
 	i_mmap_lock_write(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -1591,14 +1602,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		 * reverse order. Trylock is a way to avoid deadlock.
 		 */
 		if (mmap_write_trylock(mm)) {
-			if (!khugepaged_test_exit(mm)) {
-				spinlock_t *ptl = pmd_lock(mm, pmd);
-				/* assume page table is clear */
-				_pmd = pmdp_collapse_flush(vma, addr, pmd);
-				spin_unlock(ptl);
-				mm_dec_nr_ptes(mm);
-				pte_free(mm, pmd_pgtable(_pmd));
-			}
+			if (!khugepaged_test_exit(mm))
+				collapse_and_free_pmd(mm, vma, addr, pmd);
 			mmap_write_unlock(mm);
 		} else {
 			/* Try again later */
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index dc3758fdba68..7580baa76af1 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1410,7 +1410,8 @@ static void kmemleak_scan(void)
 {
 	unsigned long flags;
 	struct kmemleak_object *object;
-	int i;
+	struct zone *zone;
+	int __maybe_unused i;
 	int new_leaks = 0;
 
 	jiffies_last_scan = jiffies;
@@ -1450,9 +1451,9 @@ static void kmemleak_scan(void)
 	 * Struct page scanning for each node.
 	 */
 	get_online_mems();
-	for_each_online_node(i) {
-		unsigned long start_pfn = node_start_pfn(i);
-		unsigned long end_pfn = node_end_pfn(i);
+	for_each_populated_zone(zone) {
+		unsigned long start_pfn = zone->zone_start_pfn;
+		unsigned long end_pfn = zone_end_pfn(zone);
 		unsigned long pfn;
 
 		for (pfn = start_pfn; pfn < end_pfn; pfn++) {
@@ -1461,8 +1462,8 @@ static void kmemleak_scan(void)
 			if (!page)
 				continue;
 
-			/* only scan pages belonging to this node */
-			if (page_to_nid(page) != i)
+			/* only scan pages belonging to this zone */
+			if (page_zone(page) != zone)
 				continue;
 			/* only scan if page is in use */
 			if (page_count(page) == 0)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 09d342c7cbd0..36e9f38c919d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -254,7 +254,7 @@ struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-extern spinlock_t css_set_lock;
+static DEFINE_SPINLOCK(objcg_lock);
 
 bool mem_cgroup_kmem_disabled(void)
 {
@@ -298,9 +298,9 @@ static void obj_cgroup_release(struct percpu_ref *ref)
 	if (nr_pages)
 		obj_cgroup_uncharge_pages(objcg, nr_pages);
 
-	spin_lock_irqsave(&css_set_lock, flags);
+	spin_lock_irqsave(&objcg_lock, flags);
 	list_del(&objcg->list);
-	spin_unlock_irqrestore(&css_set_lock, flags);
+	spin_unlock_irqrestore(&objcg_lock, flags);
 
 	percpu_ref_exit(ref);
 	kfree_rcu(objcg, rcu);
@@ -332,7 +332,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
 
 	objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
 
-	spin_lock_irq(&css_set_lock);
+	spin_lock_irq(&objcg_lock);
 
 	/* 1) Ready to reparent active objcg. */
 	list_add(&objcg->list, &memcg->objcg_list);
@@ -342,7 +342,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
 	/* 3) Move already reparented objcgs to the parent's list */
 	list_splice(&memcg->objcg_list, &parent->objcg_list);
 
-	spin_unlock_irq(&css_set_lock);
+	spin_unlock_irq(&objcg_lock);
 
 	percpu_ref_kill(&objcg->refcnt);
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 14ae5c18e776..97a9ed8f87a9 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1596,6 +1596,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	}
 
 	/*
+	 * Pages instantiated by device-dax (not filesystem-dax)
+	 * may be compound pages.
+	 */
+	page = compound_head(page);
+
+	/*
 	 * Prevent the inode from being freed while we are interrogating
 	 * the address_space, typically this would be handled by
 	 * lock_page(), but dax pages do not use the page lock. This
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 0138dfcdb1d8..5ca3fbcb1495 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -94,7 +94,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 				/* Also skip shared copy-on-write pages */
 				if (is_cow_mapping(vma->vm_flags) &&
-				    page_mapcount(page) != 1)
+				    page_count(page) != 1)
 					continue;
 
 				/*
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 6a0ddda6b3c5..f67c4c70f17f 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -115,7 +115,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 	 * onlining - just onlined memory won't immediately be considered for
 	 * allocation.
 	 */
-	if (!isolated_page && PageBuddy(page)) {
+	if (!isolated_page) {
 		nr_pages = move_freepages_block(zone, page, migratetype, NULL);
 		__mod_zone_freepage_state(zone, nr_pages, migratetype);
 	}
diff --git a/mm/page_table_check.c b/mm/page_table_check.c
index 7504e7caa2a1..3763bd077861 100644
--- a/mm/page_table_check.c
+++ b/mm/page_table_check.c
@@ -86,8 +86,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr,
 {
 	struct page_ext *page_ext;
 	struct page *page;
+	unsigned long i;
 	bool anon;
-	int i;
 
 	if (!pfn_valid(pfn))
 		return;
@@ -121,8 +121,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr,
 {
 	struct page_ext *page_ext;
 	struct page *page;
+	unsigned long i;
 	bool anon;
-	int i;
 
 	if (!pfn_valid(pfn))
 		return;
@@ -152,10 +152,10 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr,
 void __page_table_check_zero(struct page *page, unsigned int order)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
-	int i;
+	unsigned long i;
 
 	BUG_ON(!page_ext);
-	for (i = 0; i < (1 << order); i++) {
+	for (i = 0; i < (1ul << order); i++) {
 		struct page_table_check *ptc = get_page_table_check(page_ext);
 
 		BUG_ON(atomic_read(&ptc->anon_map_count));
@@ -206,17 +206,10 @@ EXPORT_SYMBOL(__page_table_check_pud_clear);
 void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, pte_t pte)
 {
-	pte_t old_pte;
-
 	if (&init_mm == mm)
 		return;
 
-	old_pte = *ptep;
-	if (pte_user_accessible_page(old_pte)) {
-		page_table_check_clear(mm, addr, pte_pfn(old_pte),
-				       PAGE_SIZE >> PAGE_SHIFT);
-	}
-
+	__page_table_check_pte_clear(mm, addr, *ptep);
 	if (pte_user_accessible_page(pte)) {
 		page_table_check_set(mm, addr, pte_pfn(pte),
 				     PAGE_SIZE >> PAGE_SHIFT,
@@ -228,17 +221,10 @@ EXPORT_SYMBOL(__page_table_check_pte_set);
 void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr,
 				pmd_t *pmdp, pmd_t pmd)
 {
-	pmd_t old_pmd;
-
 	if (&init_mm == mm)
 		return;
 
-	old_pmd = *pmdp;
-	if (pmd_user_accessible_page(old_pmd)) {
-		page_table_check_clear(mm, addr, pmd_pfn(old_pmd),
-				       PMD_PAGE_SIZE >> PAGE_SHIFT);
-	}
-
+	__page_table_check_pmd_clear(mm, addr, *pmdp);
 	if (pmd_user_accessible_page(pmd)) {
 		page_table_check_set(mm, addr, pmd_pfn(pmd),
 				     PMD_PAGE_SIZE >> PAGE_SHIFT,
@@ -250,17 +236,10 @@ EXPORT_SYMBOL(__page_table_check_pmd_set);
 void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr,
 				pud_t *pudp, pud_t pud)
 {
-	pud_t old_pud;
-
 	if (&init_mm == mm)
 		return;
 
-	old_pud = *pudp;
-	if (pud_user_accessible_page(old_pud)) {
-		page_table_check_clear(mm, addr, pud_pfn(old_pud),
-				       PUD_PAGE_SIZE >> PAGE_SHIFT);
-	}
-
+	__page_table_check_pud_clear(mm, addr, *pudp);
 	if (pud_user_accessible_page(pud)) {
 		page_table_check_set(mm, addr, pud_pfn(pud),
 				     PUD_PAGE_SIZE >> PAGE_SHIFT,
@@ -268,3 +247,23 @@ void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr,
 	}
 }
 EXPORT_SYMBOL(__page_table_check_pud_set);
+
+void __page_table_check_pte_clear_range(struct mm_struct *mm,
+					unsigned long addr,
+					pmd_t pmd)
+{
+	if (&init_mm == mm)
+		return;
+
+	if (!pmd_bad(pmd) && !pmd_leaf(pmd)) {
+		pte_t *ptep = pte_offset_map(&pmd, addr);
+		unsigned long i;
+
+		pte_unmap(ptep);
+		for (i = 0; i < PTRS_PER_PTE; i++) {
+			__page_table_check_pte_clear(mm, addr, *ptep);
+			addr += PAGE_SIZE;
+			ptep++;
+		}
+	}
+}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 090bfb605ecf..59b14e0d696c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1066,8 +1066,10 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
 	 * forward progress (e.g. journalling workqueues or kthreads).
 	 */
 	if (!current_is_kswapd() &&
-	    current->flags & (PF_IO_WORKER|PF_KTHREAD))
+	    current->flags & (PF_IO_WORKER|PF_KTHREAD)) {
+		cond_resched();
 		return;
+	}
 
 	/*
 	 * These figures are pulled out of thin air.