Merge branch 'linus' into perf/core

Merge reason: merge the latest fixes, update to latest -rc.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

6 files changed, 118 insertions, 56 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0e8ca034770..f13e067e146 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -227,6 +227,9 @@ static struct device_attribute bdi_dev_attrs[] = {
 static __init int bdi_class_init(void)
 {
 	bdi_class = class_create(THIS_MODULE, "bdi");
+	if (IS_ERR(bdi_class))
+		return PTR_ERR(bdi_class);
+
 	bdi_class->dev_attrs = bdi_dev_attrs;
 	bdi_debug_init();
 	return 0;
diff --git a/mm/mmap.c b/mm/mmap.c
index 75557c639ad..f90ea92f755 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -507,11 +507,12 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	struct address_space *mapping = NULL;
 	struct prio_tree_root *root = NULL;
 	struct file *file = vma->vm_file;
-	struct anon_vma *anon_vma = NULL;
 	long adjust_next = 0;
 	int remove_next = 0;
 
 	if (next && !insert) {
+		struct vm_area_struct *exporter = NULL;
+
 		if (end >= next->vm_end) {
 			/*
 			 * vma expands, overlapping all the next, and
@@ -519,7 +520,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 			 */
 again:			remove_next = 1 + (end > next->vm_end);
 			end = next->vm_end;
-			anon_vma = next->anon_vma;
+			exporter = next;
 			importer = vma;
 		} else if (end > next->vm_start) {
 			/*
@@ -527,7 +528,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 			 * mprotect case 5 shifting the boundary up.
 			 */
 			adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
-			anon_vma = next->anon_vma;
+			exporter = next;
 			importer = vma;
 		} else if (end < vma->vm_end) {
 			/*
@@ -536,28 +537,19 @@ again:			remove_next = 1 + (end > next->vm_end);
 			 * mprotect case 4 shifting the boundary down.
 			 */
 			adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
-			anon_vma = next->anon_vma;
+			exporter = vma;
 			importer = next;
 		}
-	}
 
-	/*
-	 * When changing only vma->vm_end, we don't really need anon_vma lock.
-	 */
-	if (vma->anon_vma && (insert || importer || start != vma->vm_start))
-		anon_vma = vma->anon_vma;
-	if (anon_vma) {
 		/*
 		 * Easily overlooked: when mprotect shifts the boundary,
 		 * make sure the expanding vma has anon_vma set if the
 		 * shrinking vma had, to cover any anon pages imported.
 		 */
-		if (importer && !importer->anon_vma) {
-			/* Block reverse map lookups until things are set up. */
-			if (anon_vma_clone(importer, vma)) {
+		if (exporter && exporter->anon_vma && !importer->anon_vma) {
+			if (anon_vma_clone(importer, exporter))
 				return -ENOMEM;
-			}
-			importer->anon_vma = anon_vma;
+			importer->anon_vma = exporter->anon_vma;
 		}
 	}
 
@@ -825,6 +817,61 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 }
 
 /*
+ * Rough compatbility check to quickly see if it's even worth looking
+ * at sharing an anon_vma.
+ *
+ * They need to have the same vm_file, and the flags can only differ
+ * in things that mprotect may change.
+ *
+ * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that
+ * we can merge the two vma's. For example, we refuse to merge a vma if
+ * there is a vm_ops->close() function, because that indicates that the
+ * driver is doing some kind of reference counting. But that doesn't
+ * really matter for the anon_vma sharing case.
+ */
+static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b)
+{
+	return a->vm_end == b->vm_start &&
+		mpol_equal(vma_policy(a), vma_policy(b)) &&
+		a->vm_file == b->vm_file &&
+		!((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) &&
+		b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
+}
+
+/*
+ * Do some basic sanity checking to see if we can re-use the anon_vma
+ * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be
+ * the same as 'old', the other will be the new one that is trying
+ * to share the anon_vma.
+ *
+ * NOTE! This runs with mm_sem held for reading, so it is possible that
+ * the anon_vma of 'old' is concurrently in the process of being set up
+ * by another page fault trying to merge _that_. But that's ok: if it
+ * is being set up, that automatically means that it will be a singleton
+ * acceptable for merging, so we can do all of this optimistically. But
+ * we do that ACCESS_ONCE() to make sure that we never re-load the pointer.
+ *
+ * IOW: that the "list_is_singular()" test on the anon_vma_chain only
+ * matters for the 'stable anon_vma' case (ie the thing we want to avoid
+ * is to return an anon_vma that is "complex" due to having gone through
+ * a fork).
+ *
+ * We also make sure that the two vma's are compatible (adjacent,
+ * and with the same memory policies). That's all stable, even with just
+ * a read lock on the mm_sem.
+ */
+static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b)
+{
+	if (anon_vma_compatible(a, b)) {
+		struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma);
+
+		if (anon_vma && list_is_singular(&old->anon_vma_chain))
+			return anon_vma;
+	}
+	return NULL;
+}
+
+/*
  * find_mergeable_anon_vma is used by anon_vma_prepare, to check
  * neighbouring vmas for a suitable anon_vma, before it goes off
  * to allocate a new anon_vma.  It checks because a repetitive
@@ -834,28 +881,16 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
  */
 struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
 {
+	struct anon_vma *anon_vma;
 	struct vm_area_struct *near;
-	unsigned long vm_flags;
 
 	near = vma->vm_next;
 	if (!near)
 		goto try_prev;
 
-	/*
-	 * Since only mprotect tries to remerge vmas, match flags
-	 * which might be mprotected into each other later on.
-	 * Neither mlock nor madvise tries to remerge at present,
-	 * so leave their flags as obstructing a merge.
-	 */
-	vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
-	vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
-
-	if (near->anon_vma && vma->vm_end == near->vm_start &&
- 			mpol_equal(vma_policy(vma), vma_policy(near)) &&
-			can_vma_merge_before(near, vm_flags,
-				NULL, vma->vm_file, vma->vm_pgoff +
-				((vma->vm_end - vma->vm_start) >> PAGE_SHIFT)))
-		return near->anon_vma;
+	anon_vma = reusable_anon_vma(near, vma, near);
+	if (anon_vma)
+		return anon_vma;
 try_prev:
 	/*
 	 * It is potentially slow to have to call find_vma_prev here.
@@ -868,14 +903,9 @@ try_prev:
 	if (!near)
 		goto none;
 
-	vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
-	vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
-
-	if (near->anon_vma && near->vm_end == vma->vm_start &&
-  			mpol_equal(vma_policy(near), vma_policy(vma)) &&
-			can_vma_merge_after(near, vm_flags,
-				NULL, vma->vm_file, vma->vm_pgoff))
-		return near->anon_vma;
+	anon_vma = reusable_anon_vma(near, near, vma);
+	if (anon_vma)
+		return anon_vma;
 none:
 	/*
 	 * There's no absolute need to look only at touching neighbours:
diff --git a/mm/rmap.c b/mm/rmap.c
index eaa7a09eb72..526704e8215 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -182,7 +182,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
 	struct anon_vma_chain *avc, *pavc;
 
-	list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) {
+	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
 		avc = anon_vma_chain_alloc();
 		if (!avc)
 			goto enomem_failure;
@@ -730,13 +730,29 @@ void page_move_anon_rmap(struct page *page,
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
+ * @exclusive:	the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address)
+	struct vm_area_struct *vma, unsigned long address, int exclusive)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 
 	BUG_ON(!anon_vma);
+
+	/*
+	 * If the page isn't exclusively mapped into this vma,
+	 * we must use the _oldest_ possible anon_vma for the
+	 * page mapping!
+	 *
+	 * So take the last AVC chain entry in the vma, which is
+	 * the deepest ancestor, and use the anon_vma from that.
+	 */
+	if (!exclusive) {
+		struct anon_vma_chain *avc;
+		avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma);
+		anon_vma = avc->anon_vma;
+	}
+
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	page->mapping = (struct address_space *) anon_vma;
 	page->index = linear_page_index(vma, address);
@@ -791,7 +807,7 @@ void page_add_anon_rmap(struct page *page,
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	if (first)
-		__page_set_anon_rmap(page, vma, address);
+		__page_set_anon_rmap(page, vma, address, 0);
 	else
 		__page_check_anon_rmap(page, vma, address);
 }
@@ -813,7 +829,7 @@ void page_add_new_anon_rmap(struct page *page,
 	SetPageSwapBacked(page);
 	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
 	__inc_zone_page_state(page, NR_ANON_PAGES);
-	__page_set_anon_rmap(page, vma, address);
+	__page_set_anon_rmap(page, vma, address, 1);
 	if (page_evictable(page, vma))
 		lru_cache_add_lru(page, LRU_ACTIVE_ANON);
 	else
diff --git a/mm/slab.c b/mm/slab.c
index a9f325b28be..bac0f4fcc21 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3602,21 +3602,10 @@ EXPORT_SYMBOL(kmem_cache_alloc_notrace);
  */
 int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr)
 {
-	unsigned long addr = (unsigned long)ptr;
-	unsigned long min_addr = PAGE_OFFSET;
-	unsigned long align_mask = BYTES_PER_WORD - 1;
 	unsigned long size = cachep->buffer_size;
 	struct page *page;
 
-	if (unlikely(addr < min_addr))
-		goto out;
-	if (unlikely(addr > (unsigned long)high_memory - size))
-		goto out;
-	if (unlikely(addr & align_mask))
-		goto out;
-	if (unlikely(!kern_addr_valid(addr)))
-		goto out;
-	if (unlikely(!kern_addr_valid(addr + size - 1)))
+	if (unlikely(!kern_ptr_validate(ptr, size)))
 		goto out;
 	page = virt_to_page(ptr);
 	if (unlikely(!PageSlab(page)))
diff --git a/mm/slub.c b/mm/slub.c
index b364844a106..7d6c8b1ccf6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2386,6 +2386,9 @@ int kmem_ptr_validate(struct kmem_cache *s, const void *object)
 {
 	struct page *page;
 
+	if (!kern_ptr_validate(object, s->size))
+		return 0;
+
 	page = get_object_page(object);
 
 	if (!page || s != page->slab)
diff --git a/mm/util.c b/mm/util.c
index 834db7be240..f5712e8964b 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -186,6 +186,27 @@ void kzfree(const void *p)
 }
 EXPORT_SYMBOL(kzfree);
 
+int kern_ptr_validate(const void *ptr, unsigned long size)
+{
+	unsigned long addr = (unsigned long)ptr;
+	unsigned long min_addr = PAGE_OFFSET;
+	unsigned long align_mask = sizeof(void *) - 1;
+
+	if (unlikely(addr < min_addr))
+		goto out;
+	if (unlikely(addr > (unsigned long)high_memory - size))
+		goto out;
+	if (unlikely(addr & align_mask))
+		goto out;
+	if (unlikely(!kern_addr_valid(addr)))
+		goto out;
+	if (unlikely(!kern_addr_valid(addr + size - 1)))
+		goto out;
+	return 1;
+out:
+	return 0;
+}
+
 /*
  * strndup_user - duplicate an existing string from user space
  * @s: The string to duplicate