Linux-libre 4.3.2-gnu

1 files changed, 164 insertions, 79 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 097c7a4bf..bbac913f9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -16,6 +16,7 @@
 #include <linux/swap.h>
 #include <linux/shrinker.h>
 #include <linux/mm_inline.h>
+#include <linux/dax.h>
 #include <linux/kthread.h>
 #include <linux/khugepaged.h>
 #include <linux/freezer.h>
@@ -23,6 +24,8 @@
 #include <linux/pagemap.h>
 #include <linux/migrate.h>
 #include <linux/hashtable.h>
+#include <linux/userfaultfd_k.h>
+#include <linux/page_idle.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -104,7 +107,7 @@ static struct khugepaged_scan khugepaged_scan = {
 };
 
 
-static int set_recommended_min_free_kbytes(void)
+static void set_recommended_min_free_kbytes(void)
 {
 	struct zone *zone;
 	int nr_zones = 0;
@@ -139,7 +142,6 @@ static int set_recommended_min_free_kbytes(void)
 		min_free_kbytes = recommended_min;
 	}
 	setup_per_zone_wmarks();
-	return 0;
 }
 
 static int start_stop_khugepaged(void)
@@ -171,12 +173,7 @@ fail:
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
 
-static inline bool is_huge_zero_pmd(pmd_t pmd)
-{
-	return is_huge_zero_page(pmd_page(pmd));
-}
-
-static struct page *get_huge_zero_page(void)
+struct page *get_huge_zero_page(void)
 {
 	struct page *zero_page;
 retry:
@@ -716,21 +713,27 @@ static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
 
 static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					struct vm_area_struct *vma,
-					unsigned long haddr, pmd_t *pmd,
-					struct page *page, gfp_t gfp)
+					unsigned long address, pmd_t *pmd,
+					struct page *page, gfp_t gfp,
+					unsigned int flags)
 {
 	struct mem_cgroup *memcg;
 	pgtable_t pgtable;
 	spinlock_t *ptl;
+	unsigned long haddr = address & HPAGE_PMD_MASK;
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, mm, gfp, &memcg))
-		return VM_FAULT_OOM;
+	if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) {
+		put_page(page);
+		count_vm_event(THP_FAULT_FALLBACK);
+		return VM_FAULT_FALLBACK;
+	}
 
 	pgtable = pte_alloc_one(mm, haddr);
 	if (unlikely(!pgtable)) {
 		mem_cgroup_cancel_charge(page, memcg);
+		put_page(page);
 		return VM_FAULT_OOM;
 	}
 
@@ -750,6 +753,21 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		pte_free(mm, pgtable);
 	} else {
 		pmd_t entry;
+
+		/* Deliver the page fault to userland */
+		if (userfaultfd_missing(vma)) {
+			int ret;
+
+			spin_unlock(ptl);
+			mem_cgroup_cancel_charge(page, memcg);
+			put_page(page);
+			pte_free(mm, pgtable);
+			ret = handle_userfault(vma, address, flags,
+					       VM_UFFD_MISSING);
+			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
+			return ret;
+		}
+
 		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);
@@ -760,6 +778,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		atomic_long_inc(&mm->nr_ptes);
 		spin_unlock(ptl);
+		count_vm_event(THP_FAULT_ALLOC);
 	}
 
 	return 0;
@@ -806,6 +825,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pgtable_t pgtable;
 		struct page *zero_page;
 		bool set;
+		int ret;
 		pgtable = pte_alloc_one(mm, haddr);
 		if (unlikely(!pgtable))
 			return VM_FAULT_OOM;
@@ -816,14 +836,28 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			return VM_FAULT_FALLBACK;
 		}
 		ptl = pmd_lock(mm, pmd);
-		set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
-				zero_page);
-		spin_unlock(ptl);
+		ret = 0;
+		set = false;
+		if (pmd_none(*pmd)) {
+			if (userfaultfd_missing(vma)) {
+				spin_unlock(ptl);
+				ret = handle_userfault(vma, address, flags,
+						       VM_UFFD_MISSING);
+				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
+			} else {
+				set_huge_zero_page(pgtable, mm, vma,
+						   haddr, pmd,
+						   zero_page);
+				spin_unlock(ptl);
+				set = true;
+			}
+		} else
+			spin_unlock(ptl);
 		if (!set) {
 			pte_free(mm, pgtable);
 			put_huge_zero_page();
 		}
-		return 0;
+		return ret;
 	}
 	gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0);
 	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
@@ -831,14 +865,51 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
 	}
-	if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page, gfp))) {
-		put_page(page);
-		count_vm_event(THP_FAULT_FALLBACK);
-		return VM_FAULT_FALLBACK;
+	return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp,
+					    flags);
+}
+
+static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned long pfn, pgprot_t prot, bool write)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pmd_t entry;
+	spinlock_t *ptl;
+
+	ptl = pmd_lock(mm, pmd);
+	if (pmd_none(*pmd)) {
+		entry = pmd_mkhuge(pfn_pmd(pfn, prot));
+		if (write) {
+			entry = pmd_mkyoung(pmd_mkdirty(entry));
+			entry = maybe_pmd_mkwrite(entry, vma);
+		}
+		set_pmd_at(mm, addr, pmd, entry);
+		update_mmu_cache_pmd(vma, addr, pmd);
 	}
+	spin_unlock(ptl);
+}
 
-	count_vm_event(THP_FAULT_ALLOC);
-	return 0;
+int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+			pmd_t *pmd, unsigned long pfn, bool write)
+{
+	pgprot_t pgprot = vma->vm_page_prot;
+	/*
+	 * If we had pmd_special, we could avoid all these restrictions,
+	 * but we need to be consistent with PTEs and architectures that
+	 * can't support a 'special' bit.
+	 */
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+						(VM_PFNMAP|VM_MIXEDMAP));
+	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return VM_FAULT_SIGBUS;
+	if (track_pfn_insert(vma, &pgprot, pfn))
+		return VM_FAULT_SIGBUS;
+	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
+	return VM_FAULT_NOPAGE;
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -873,16 +944,14 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 */
 	if (is_huge_zero_pmd(pmd)) {
 		struct page *zero_page;
-		bool set;
 		/*
 		 * get_huge_zero_page() will never allocate a new page here,
 		 * since we already have a zero page to copy. It just takes a
 		 * reference.
 		 */
 		zero_page = get_huge_zero_page();
-		set = set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
+		set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
 				zero_page);
-		BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */
 		ret = 0;
 		goto out_unlock;
 	}
@@ -1387,41 +1456,41 @@ out:
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
+	pmd_t orig_pmd;
 	spinlock_t *ptl;
-	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		struct page *page;
-		pgtable_t pgtable;
-		pmd_t orig_pmd;
-		/*
-		 * For architectures like ppc64 we look at deposited pgtable
-		 * when calling pmdp_huge_get_and_clear. So do the
-		 * pgtable_trans_huge_withdraw after finishing pmdp related
-		 * operations.
-		 */
-		orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
-							tlb->fullmm);
-		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
-		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
-		if (is_huge_zero_pmd(orig_pmd)) {
-			atomic_long_dec(&tlb->mm->nr_ptes);
-			spin_unlock(ptl);
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) != 1)
+		return 0;
+	/*
+	 * For architectures like ppc64 we look at deposited pgtable
+	 * when calling pmdp_huge_get_and_clear. So do the
+	 * pgtable_trans_huge_withdraw after finishing pmdp related
+	 * operations.
+	 */
+	orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
+			tlb->fullmm);
+	tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+	if (vma_is_dax(vma)) {
+		spin_unlock(ptl);
+		if (is_huge_zero_pmd(orig_pmd))
 			put_huge_zero_page();
-		} else {
-			page = pmd_page(orig_pmd);
-			page_remove_rmap(page);
-			VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
-			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
-			VM_BUG_ON_PAGE(!PageHead(page), page);
-			atomic_long_dec(&tlb->mm->nr_ptes);
-			spin_unlock(ptl);
-			tlb_remove_page(tlb, page);
-		}
-		pte_free(tlb->mm, pgtable);
-		ret = 1;
+	} else if (is_huge_zero_pmd(orig_pmd)) {
+		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
+		atomic_long_dec(&tlb->mm->nr_ptes);
+		spin_unlock(ptl);
+		put_huge_zero_page();
+	} else {
+		struct page *page = pmd_page(orig_pmd);
+		page_remove_rmap(page);
+		VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
+		add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
+		VM_BUG_ON_PAGE(!PageHead(page), page);
+		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
+		atomic_long_dec(&tlb->mm->nr_ptes);
+		spin_unlock(ptl);
+		tlb_remove_page(tlb, page);
 	}
-	return ret;
+	return 1;
 }
 
 int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
@@ -1689,6 +1758,11 @@ static void __split_huge_page_refcount(struct page *page,
 		/* clear PageTail before overwriting first_page */
 		smp_wmb();
 
+		if (page_is_young(page))
+			set_page_young(page_tail);
+		if (page_is_idle(page))
+			set_page_idle(page_tail);
+
 		/*
 		 * __split_huge_page_splitting() already set the
 		 * splitting bit in all pmd that could map this
@@ -2132,8 +2206,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 	for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
-		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
-			if (++none_or_zero <= khugepaged_max_ptes_none)
+		if (pte_none(pteval) || (pte_present(pteval) &&
+				is_zero_pfn(pte_pfn(pteval)))) {
+			if (!userfaultfd_armed(vma) &&
+			    ++none_or_zero <= khugepaged_max_ptes_none)
 				continue;
 			else
 				goto out;
@@ -2193,7 +2269,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 
 		/* If there is no mapped pte young don't collapse the page */
-		if (pte_young(pteval) || PageReferenced(page) ||
+		if (pte_young(pteval) ||
+		    page_is_young(page) || PageReferenced(page) ||
 		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = true;
 	}
@@ -2257,8 +2334,12 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 
 static void khugepaged_alloc_sleep(void)
 {
-	wait_event_freezable_timeout(khugepaged_wait, false,
-			msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
+	DEFINE_WAIT(wait);
+
+	add_wait_queue(&khugepaged_wait, &wait);
+	freezable_schedule_timeout_interruptible(
+		msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
+	remove_wait_queue(&khugepaged_wait, &wait);
 }
 
 static int khugepaged_node_load[MAX_NUMNODES];
@@ -2345,7 +2426,7 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm,
 	 */
 	up_read(&mm->mmap_sem);
 
-	*hpage = alloc_pages_exact_node(node, gfp, HPAGE_PMD_ORDER);
+	*hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER);
 	if (unlikely(!*hpage)) {
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 		*hpage = ERR_PTR(-ENOMEM);
@@ -2586,7 +2667,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	     _pte++, _address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
-			if (++none_or_zero <= khugepaged_max_ptes_none)
+			if (!userfaultfd_armed(vma) &&
+			    ++none_or_zero <= khugepaged_max_ptes_none)
 				continue;
 			else
 				goto out_unmap;
@@ -2619,7 +2701,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		 */
 		if (page_count(page) != 1 + !!PageSwapCache(page))
 			goto out_unmap;
-		if (pte_young(pteval) || PageReferenced(page) ||
+		if (pte_young(pteval) ||
+		    page_is_young(page) || PageReferenced(page) ||
 		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = true;
 	}
@@ -2882,7 +2965,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd)
 {
 	spinlock_t *ptl;
-	struct page *page;
+	struct page *page = NULL;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
 	unsigned long mmun_start;	/* For mmu_notifiers */
@@ -2895,25 +2978,27 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 again:
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	ptl = pmd_lock(mm, pmd);
-	if (unlikely(!pmd_trans_huge(*pmd))) {
-		spin_unlock(ptl);
-		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-		return;
-	}
-	if (is_huge_zero_pmd(*pmd)) {
+	if (unlikely(!pmd_trans_huge(*pmd)))
+		goto unlock;
+	if (vma_is_dax(vma)) {
+		pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+		if (is_huge_zero_pmd(_pmd))
+			put_huge_zero_page();
+	} else if (is_huge_zero_pmd(*pmd)) {
 		__split_huge_zero_page_pmd(vma, haddr, pmd);
-		spin_unlock(ptl);
-		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-		return;
+	} else {
+		page = pmd_page(*pmd);
+		VM_BUG_ON_PAGE(!page_count(page), page);
+		get_page(page);
 	}
-	page = pmd_page(*pmd);
-	VM_BUG_ON_PAGE(!page_count(page), page);
-	get_page(page);
+ unlock:
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
-	split_huge_page(page);
+	if (!page)
+		return;
 
+	split_huge_page(page);
 	put_page(page);
 
 	/*
@@ -2962,7 +3047,7 @@ static void split_huge_page_address(struct mm_struct *mm,
 	split_huge_page_pmd_mm(mm, address, pmd);
 }
 
-void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+void vma_adjust_trans_huge(struct vm_area_struct *vma,
 			     unsigned long start,
 			     unsigned long end,
 			     long adjust_next)