1 files changed, 130 insertions, 106 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a92012a71702..cca80d96e509 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -211,24 +211,29 @@ static void put_huge_zero_page(void)
 	BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
 }
 
-static int shrink_huge_zero_page(struct shrinker *shrink,
-		struct shrink_control *sc)
+static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
+					struct shrink_control *sc)
 {
-	if (!sc->nr_to_scan)
-		/* we can free zero page only if last reference remains */
-		return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+	/* we can free zero page only if last reference remains */
+	return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+}
 
+static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
+				       struct shrink_control *sc)
+{
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
 		__free_page(zero_page);
+		return HPAGE_PMD_NR;
 	}
 
 	return 0;
 }
 
 static struct shrinker huge_zero_page_shrinker = {
-	.shrink = shrink_huge_zero_page,
+	.count_objects = shrink_huge_zero_page_count,
+	.scan_objects = shrink_huge_zero_page_scan,
 	.seeks = DEFAULT_SEEKS,
 };
 
@@ -417,7 +422,7 @@ static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
 	unsigned long msecs;
 	int err;
 
-	err = strict_strtoul(buf, 10, &msecs);
+	err = kstrtoul(buf, 10, &msecs);
 	if (err || msecs > UINT_MAX)
 		return -EINVAL;
 
@@ -444,7 +449,7 @@ static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
 	unsigned long msecs;
 	int err;
 
-	err = strict_strtoul(buf, 10, &msecs);
+	err = kstrtoul(buf, 10, &msecs);
 	if (err || msecs > UINT_MAX)
 		return -EINVAL;
 
@@ -470,7 +475,7 @@ static ssize_t pages_to_scan_store(struct kobject *kobj,
 	int err;
 	unsigned long pages;
 
-	err = strict_strtoul(buf, 10, &pages);
+	err = kstrtoul(buf, 10, &pages);
 	if (err || !pages || pages > UINT_MAX)
 		return -EINVAL;
 
@@ -538,7 +543,7 @@ static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj,
 	int err;
 	unsigned long max_ptes_none;
 
-	err = strict_strtoul(buf, 10, &max_ptes_none);
+	err = kstrtoul(buf, 10, &max_ptes_none);
 	if (err || max_ptes_none > HPAGE_PMD_NR-1)
 		return -EINVAL;
 
@@ -690,11 +695,10 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 	return pmd;
 }
 
-static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma)
+static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
 {
 	pmd_t entry;
-	entry = mk_pmd(page, vma->vm_page_prot);
-	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+	entry = mk_pmd(page, prot);
 	entry = pmd_mkhuge(entry);
 	return entry;
 }
@@ -727,7 +731,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		pte_free(mm, pgtable);
 	} else {
 		pmd_t entry;
-		entry = mk_huge_pmd(page, vma);
+		entry = mk_huge_pmd(page, vma->vm_page_prot);
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		page_add_new_anon_rmap(page, vma, haddr);
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
@@ -783,77 +788,57 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
-	pte_t *pte;
 
-	if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
-		if (unlikely(anon_vma_prepare(vma)))
-			return VM_FAULT_OOM;
-		if (unlikely(khugepaged_enter(vma)))
+	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+		return VM_FAULT_FALLBACK;
+	if (unlikely(anon_vma_prepare(vma)))
+		return VM_FAULT_OOM;
+	if (unlikely(khugepaged_enter(vma)))
+		return VM_FAULT_OOM;
+	if (!(flags & FAULT_FLAG_WRITE) &&
+			transparent_hugepage_use_zero_page()) {
+		pgtable_t pgtable;
+		struct page *zero_page;
+		bool set;
+		pgtable = pte_alloc_one(mm, haddr);
+		if (unlikely(!pgtable))
 			return VM_FAULT_OOM;
-		if (!(flags & FAULT_FLAG_WRITE) &&
-				transparent_hugepage_use_zero_page()) {
-			pgtable_t pgtable;
-			struct page *zero_page;
-			bool set;
-			pgtable = pte_alloc_one(mm, haddr);
-			if (unlikely(!pgtable))
-				return VM_FAULT_OOM;
-			zero_page = get_huge_zero_page();
-			if (unlikely(!zero_page)) {
-				pte_free(mm, pgtable);
-				count_vm_event(THP_FAULT_FALLBACK);
-				goto out;
-			}
-			spin_lock(&mm->page_table_lock);
-			set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
-					zero_page);
-			spin_unlock(&mm->page_table_lock);
-			if (!set) {
-				pte_free(mm, pgtable);
-				put_huge_zero_page();
-			}
-			return 0;
-		}
-		page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
-					  vma, haddr, numa_node_id(), 0);
-		if (unlikely(!page)) {
+		zero_page = get_huge_zero_page();
+		if (unlikely(!zero_page)) {
+			pte_free(mm, pgtable);
 			count_vm_event(THP_FAULT_FALLBACK);
-			goto out;
+			return VM_FAULT_FALLBACK;
 		}
-		count_vm_event(THP_FAULT_ALLOC);
-		if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
-			put_page(page);
-			goto out;
-		}
-		if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd,
-							  page))) {
-			mem_cgroup_uncharge_page(page);
-			put_page(page);
-			goto out;
+		spin_lock(&mm->page_table_lock);
+		set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
+				zero_page);
+		spin_unlock(&mm->page_table_lock);
+		if (!set) {
+			pte_free(mm, pgtable);
+			put_huge_zero_page();
 		}
-
 		return 0;
 	}
-out:
-	/*
-	 * Use __pte_alloc instead of pte_alloc_map, because we can't
-	 * run pte_offset_map on the pmd, if an huge pmd could
-	 * materialize from under us from a different thread.
-	 */
-	if (unlikely(pmd_none(*pmd)) &&
-	    unlikely(__pte_alloc(mm, vma, pmd, address)))
-		return VM_FAULT_OOM;
-	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd)))
-		return 0;
-	/*
-	 * A regular pmd is established and it can't morph into a huge pmd
-	 * from under us anymore at this point because we hold the mmap_sem
-	 * read mode and khugepaged takes it in write mode. So now it's
-	 * safe to run pte_offset_map().
-	 */
-	pte = pte_offset_map(pmd, address);
-	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
+	page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
+			vma, haddr, numa_node_id(), 0);
+	if (unlikely(!page)) {
+		count_vm_event(THP_FAULT_FALLBACK);
+		return VM_FAULT_FALLBACK;
+	}
+	if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
+		put_page(page);
+		count_vm_event(THP_FAULT_FALLBACK);
+		return VM_FAULT_FALLBACK;
+	}
+	if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
+		mem_cgroup_uncharge_page(page);
+		put_page(page);
+		count_vm_event(THP_FAULT_FALLBACK);
+		return VM_FAULT_FALLBACK;
+	}
+
+	count_vm_event(THP_FAULT_ALLOC);
+	return 0;
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -1165,7 +1150,6 @@ alloc:
 		new_page = NULL;
 
 	if (unlikely(!new_page)) {
-		count_vm_event(THP_FAULT_FALLBACK);
 		if (is_huge_zero_pmd(orig_pmd)) {
 			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
 					address, pmd, orig_pmd, haddr);
@@ -1176,9 +1160,9 @@ alloc:
 				split_huge_page(page);
 			put_page(page);
 		}
+		count_vm_event(THP_FAULT_FALLBACK);
 		goto out;
 	}
-	count_vm_event(THP_FAULT_ALLOC);
 
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
@@ -1186,10 +1170,13 @@ alloc:
 			split_huge_page(page);
 			put_page(page);
 		}
+		count_vm_event(THP_FAULT_FALLBACK);
 		ret |= VM_FAULT_OOM;
 		goto out;
 	}
 
+	count_vm_event(THP_FAULT_ALLOC);
+
 	if (is_huge_zero_pmd(orig_pmd))
 		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
 	else
@@ -1210,7 +1197,8 @@ alloc:
 		goto out_mn;
 	} else {
 		pmd_t entry;
-		entry = mk_huge_pmd(new_page, vma);
+		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 		pmdp_clear_flush(vma, haddr, pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
@@ -1290,64 +1278,90 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	int page_nid = -1, this_nid = numa_node_id();
 	int target_nid;
-	int current_nid = -1;
-	bool migrated;
+	bool page_locked;
+	bool migrated = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
-	get_page(page);
-	current_nid = page_to_nid(page);
+	page_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
+	/*
+	 * Acquire the page lock to serialise THP migrations but avoid dropping
+	 * page_table_lock if at all possible
+	 */
+	page_locked = trylock_page(page);
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1) {
-		put_page(page);
-		goto clear_pmdnuma;
+		/* If the page was locked, there are no parallel migrations */
+		if (page_locked)
+			goto clear_pmdnuma;
+
+		/*
+		 * Otherwise wait for potential migrations and retry. We do
+		 * relock and check_same as the page may no longer be mapped.
+		 * As the fault is being retried, do not account for it.
+		 */
+		spin_unlock(&mm->page_table_lock);
+		wait_on_page_locked(page);
+		page_nid = -1;
+		goto out;
 	}
 
-	/* Acquire the page lock to serialise THP migrations */
+	/* Page is misplaced, serialise migrations and parallel THP splits */
+	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	lock_page(page);
+	if (!page_locked)
+		lock_page(page);
+	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
+		page_nid = -1;
 		goto out_unlock;
 	}
-	spin_unlock(&mm->page_table_lock);
 
-	/* Migrate the THP to the requested node */
+	/*
+	 * Migrate the THP to the requested node, returns with page unlocked
+	 * and pmd_numa cleared.
+	 */
+	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
-	if (!migrated)
-		goto check_same;
+	if (migrated)
+		page_nid = target_nid;
 
-	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
-	return 0;
-
-check_same:
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
-		goto out_unlock;
+	goto out;
 clear_pmdnuma:
+	BUG_ON(!PageLocked(page));
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	unlock_page(page);
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+
+out:
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
+
+	if (page_nid != -1)
+		task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+
 	return 0;
 }
 
@@ -1661,7 +1675,6 @@ static void __split_huge_page_refcount(struct page *page,
 	BUG_ON(atomic_read(&page->_count) <= 0);
 
 	__mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1);
-	__mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);
 
 	ClearPageCompound(page);
 	compound_unlock(page);
@@ -2296,6 +2309,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out;
 
 	vma = find_vma(mm, address);
+	if (!vma)
+		goto out;
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (address < hstart || address + HPAGE_PMD_SIZE > hend)
@@ -2357,7 +2372,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 	__SetPageUptodate(new_page);
 	pgtable = pmd_pgtable(_pmd);
 
-	_pmd = mk_huge_pmd(new_page, vma);
+	_pmd = mk_huge_pmd(new_page, vma->vm_page_prot);
+	_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
 
 	/*
 	 * spin_lock() below is not the equivalent of smp_wmb(), so
@@ -2707,6 +2723,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 
 	mmun_start = haddr;
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
+again:
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_trans_huge(*pmd))) {
@@ -2729,7 +2746,14 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 	split_huge_page(page);
 
 	put_page(page);
-	BUG_ON(pmd_trans_huge(*pmd));
+
+	/*
+	 * We don't always have down_write of mmap_sem here: a racing
+	 * do_huge_pmd_wp_page() might have copied-on-write to another
+	 * huge page before our split_huge_page() got the anon_vma lock.
+	 */
+	if (unlikely(pmd_trans_huge(*pmd)))
+		goto again;
 }
 
 void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,