Merge branch 'for-davem' into for-next

10 files changed, 58 insertions, 40 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 626e93d..6817b03 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1260,6 +1260,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int target_nid, last_cpupid = -1;
 	bool page_locked;
 	bool migrated = false;
+	bool was_writable;
 	int flags = 0;
 
 	/* A PROT_NONE fault should not end up here */
@@ -1291,17 +1292,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		flags |= TNF_FAULT_LOCAL;
 	}
 
-	/*
-	 * Avoid grouping on DSO/COW pages in specific and RO pages
-	 * in general, RO pages shouldn't hurt as much anyway since
-	 * they can be in shared cache state.
-	 *
-	 * FIXME! This checks "pmd_dirty()" as an approximation of
-	 * "is this a read-only page", since checking "pmd_write()"
-	 * is even more broken. We haven't actually turned this into
-	 * a writable page, so pmd_write() will always be false.
-	 */
-	if (!pmd_dirty(pmd))
+	/* See similar comment in do_numa_page for explanation */
+	if (!(vma->vm_flags & VM_WRITE))
 		flags |= TNF_NO_GROUP;
 
 	/*
@@ -1358,12 +1350,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (migrated) {
 		flags |= TNF_MIGRATED;
 		page_nid = target_nid;
-	}
+	} else
+		flags |= TNF_MIGRATE_FAIL;
 
 	goto out;
 clear_pmdnuma:
 	BUG_ON(!PageLocked(page));
+	was_writable = pmd_write(pmd);
 	pmd = pmd_modify(pmd, vma->vm_page_prot);
+	pmd = pmd_mkyoung(pmd);
+	if (was_writable)
+		pmd = pmd_mkwrite(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	update_mmu_cache_pmd(vma, addr, pmdp);
 	unlock_page(page);
@@ -1487,6 +1484,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 
 	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pmd_t entry;
+		bool preserve_write = prot_numa && pmd_write(*pmd);
 		ret = 1;
 
 		/*
@@ -1502,9 +1500,11 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		if (!prot_numa || !pmd_protnone(*pmd)) {
 			entry = pmdp_get_and_clear_notify(mm, addr, pmd);
 			entry = pmd_modify(entry, newprot);
+			if (preserve_write)
+				entry = pmd_mkwrite(entry);
 			ret = HPAGE_PMD_NR;
 			set_pmd_at(mm, addr, pmd, entry);
-			BUG_ON(pmd_write(entry));
+			BUG_ON(!preserve_write && pmd_write(entry));
 		}
 		spin_unlock(ptl);
 	}
diff --git a/mm/memory.c b/mm/memory.c
index 411144f..97839f5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3035,6 +3035,7 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
+	bool was_writable = pte_write(pte);
 	int flags = 0;
 
 	/* A PROT_NONE fault should not end up here */
@@ -3059,6 +3060,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Make it present again */
 	pte = pte_modify(pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
+	if (was_writable)
+		pte = pte_mkwrite(pte);
 	set_pte_at(mm, addr, ptep, pte);
 	update_mmu_cache(vma, addr, ptep);
 
@@ -3069,16 +3072,14 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	/*
-	 * Avoid grouping on DSO/COW pages in specific and RO pages
-	 * in general, RO pages shouldn't hurt as much anyway since
-	 * they can be in shared cache state.
-	 *
-	 * FIXME! This checks "pmd_dirty()" as an approximation of
-	 * "is this a read-only page", since checking "pmd_write()"
-	 * is even more broken. We haven't actually turned this into
-	 * a writable page, so pmd_write() will always be false.
+	 * Avoid grouping on RO pages in general. RO pages shouldn't hurt as
+	 * much anyway since they can be in shared cache state. This misses
+	 * the case where a mapping is writable but the process never writes
+	 * to it but pte_write gets cleared during protection updates and
+	 * pte_dirty has unpredictable behaviour between PTE scan updates,
+	 * background writeback, dirty balancing and application behaviour.
 	 */
-	if (!pte_dirty(pte))
+	if (!(vma->vm_flags & VM_WRITE))
 		flags |= TNF_NO_GROUP;
 
 	/*
@@ -3102,7 +3103,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (migrated) {
 		page_nid = target_nid;
 		flags |= TNF_MIGRATED;
-	}
+	} else
+		flags |= TNF_MIGRATE_FAIL;
 
 out:
 	if (page_nid != -1)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9fab107..65842d6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1092,6 +1092,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 			return NULL;
 
 		arch_refresh_nodedata(nid, pgdat);
+	} else {
+		/* Reset the nr_zones and classzone_idx to 0 before reuse */
+		pgdat->nr_zones = 0;
+		pgdat->classzone_idx = 0;
 	}
 
 	/* we can use NODE_DATA(nid) from here */
@@ -1977,15 +1981,6 @@ void try_offline_node(int nid)
 		if (is_vmalloc_addr(zone->wait_table))
 			vfree(zone->wait_table);
 	}
-
-	/*
-	 * Since there is no way to guarentee the address of pgdat/zone is not
-	 * on stack of any kernel threads or used by other kernel objects
-	 * without reference counting or other symchronizing method, do not
-	 * reset node_data and free pgdat here. Just reset it to 0 and reuse
-	 * the memory when the node is online again.
-	 */
-	memset(pgdat, 0, sizeof(*pgdat));
 }
 EXPORT_SYMBOL(try_offline_node);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index da9990a..9ec50a3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -774,10 +774,8 @@ again:			remove_next = 1 + (end > next->vm_end);
 
 			importer->anon_vma = exporter->anon_vma;
 			error = anon_vma_clone(importer, exporter);
-			if (error) {
-				importer->anon_vma = NULL;
+			if (error)
 				return error;
-			}
 		}
 	}
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 4472781..8858483 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -75,6 +75,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		oldpte = *pte;
 		if (pte_present(oldpte)) {
 			pte_t ptent;
+			bool preserve_write = prot_numa && pte_write(oldpte);
 
 			/*
 			 * Avoid trapping faults against the zero or KSM
@@ -94,6 +95,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 			ptent = ptep_modify_prot_start(mm, addr, pte);
 			ptent = pte_modify(ptent, newprot);
+			if (preserve_write)
+				ptent = pte_mkwrite(ptent);
 
 			/* Avoid taking write faults for known dirty pages */
 			if (dirty_accountable && pte_dirty(ptent) &&
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 45e187b..644bcb6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
 	 *                   bw * elapsed + write_bandwidth * (period - elapsed)
 	 * write_bandwidth = ---------------------------------------------------
 	 *                                          period
+	 *
+	 * @written may have decreased due to account_page_redirty().
+	 * Avoid underflowing @bw calculation.
 	 */
-	bw = written - bdi->written_stamp;
+	bw = written - min(written, bdi->written_stamp);
 	bw *= HZ;
 	if (unlikely(elapsed > period)) {
 		do_div(bw, elapsed);
@@ -922,7 +925,7 @@ static void global_update_bandwidth(unsigned long thresh,
 				    unsigned long now)
 {
 	static DEFINE_SPINLOCK(dirty_lock);
-	static unsigned long update_time;
+	static unsigned long update_time = INITIAL_JIFFIES;
 
 	/*
 	 * check locklessly first to optimize away locking for the most time
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 72f5ac3..755a42c 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -103,6 +103,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 
 			if (!is_migrate_isolate_page(buddy)) {
 				__isolate_free_page(page, order);
+				kernel_map_pages(page, (1 << order), 1);
 				set_page_refcounted(page);
 				isolated_page = page;
 			}
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 75c1f28..29f2f8b 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -265,8 +265,15 @@ int walk_page_range(unsigned long start, unsigned long end,
 			vma = vma->vm_next;
 
 			err = walk_page_test(start, next, walk);
-			if (err > 0)
+			if (err > 0) {
+				/*
+				 * positive return values are purely for
+				 * controlling the pagewalk, so should never
+				 * be passed to the callers.
+				 */
+				err = 0;
 				continue;
+			}
 			if (err < 0)
 				break;
 		}
diff --git a/mm/rmap.c b/mm/rmap.c
index 5e3e090..c161a14 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -287,6 +287,13 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 	return 0;
 
  enomem_failure:
+	/*
+	 * dst->anon_vma is dropped here otherwise its degree can be incorrectly
+	 * decremented in unlink_anon_vmas().
+	 * We can safely do this because callers of anon_vma_clone() don't care
+	 * about dst->anon_vma if anon_vma_clone() failed.
+	 */
+	dst->anon_vma = NULL;
 	unlink_anon_vmas(dst);
 	return -ENOMEM;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 6832c4e..82c4737 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2449,7 +2449,8 @@ redo:
 	do {
 		tid = this_cpu_read(s->cpu_slab->tid);
 		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
+	} while (IS_ENABLED(CONFIG_PREEMPT) &&
+		 unlikely(tid != READ_ONCE(c->tid)));
 
 	/*
 	 * Irqless object alloc/free algorithm used here depends on sequence
@@ -2718,7 +2719,8 @@ redo:
 	do {
 		tid = this_cpu_read(s->cpu_slab->tid);
 		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
+	} while (IS_ENABLED(CONFIG_PREEMPT) &&
+		 unlikely(tid != READ_ONCE(c->tid)));
 
 	/* Same with comment on barrier() in slab_alloc_node() */
 	barrier();