1 files changed, 38 insertions, 6 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index f54b235f29a9..e6beac4805a4 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1296,15 +1296,20 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		file = fget(fd);
 		if (!file)
 			goto out;
+		if (is_file_hugepages(file))
+			len = ALIGN(len, huge_page_size(hstate_file(file)));
 	} else if (flags & MAP_HUGETLB) {
 		struct user_struct *user = NULL;
+
+		len = ALIGN(len, huge_page_size(hstate_sizelog(
+			(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK)));
 		/*
 		 * VM_NORESERVE is used because the reservations will be
 		 * taken when vm_ops->mmap() is called
 		 * A dummy user value is used because we are not locking
 		 * memory so no accounting is necessary
 		 */
-		file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
+		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len,
 				VM_NORESERVE,
 				&user, HUGETLB_ANONHUGE_INODE,
 				(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
@@ -1922,7 +1927,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 
 	/* Check the cache first. */
 	/* (Cache hit rate is typically around 35%.) */
-	vma = mm->mmap_cache;
+	vma = ACCESS_ONCE(mm->mmap_cache);
 	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
 		struct rb_node *rb_node;
 
@@ -2169,9 +2174,28 @@ int expand_downwards(struct vm_area_struct *vma,
 	return error;
 }
 
+/*
+ * Note how expand_stack() refuses to expand the stack all the way to
+ * abut the next virtual mapping, *unless* that mapping itself is also
+ * a stack mapping. We want to leave room for a guard page, after all
+ * (the guard page itself is not added here, that is done by the
+ * actual page faulting logic)
+ *
+ * This matches the behavior of the guard page logic (see mm/memory.c:
+ * check_stack_guard_page()), which only allows the guard page to be
+ * removed under these circumstances.
+ */
 #ifdef CONFIG_STACK_GROWSUP
 int expand_stack(struct vm_area_struct *vma, unsigned long address)
 {
+	struct vm_area_struct *next;
+
+	address &= PAGE_MASK;
+	next = vma->vm_next;
+	if (next && next->vm_start == address + PAGE_SIZE) {
+		if (!(next->vm_flags & VM_GROWSUP))
+			return -ENOMEM;
+	}
 	return expand_upwards(vma, address);
 }
 
@@ -2194,6 +2218,14 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 #else
 int expand_stack(struct vm_area_struct *vma, unsigned long address)
 {
+	struct vm_area_struct *prev;
+
+	address &= PAGE_MASK;
+	prev = vma->vm_prev;
+	if (prev && prev->vm_end == address) {
+		if (!(prev->vm_flags & VM_GROWSDOWN))
+			return -ENOMEM;
+	}
 	return expand_downwards(vma, address);
 }
 
@@ -2262,7 +2294,7 @@ static void unmap_region(struct mm_struct *mm,
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
-				 next ? next->vm_start : 0);
+				 next ? next->vm_start : USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, start, end);
 }
 
@@ -2640,7 +2672,7 @@ void exit_mmap(struct mm_struct *mm)
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
 
-	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
+	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, 0, -1);
 
 	/*
@@ -2886,7 +2918,7 @@ static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		down_write(&anon_vma->root->rwsem);
+		down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
 		 * anon_vma->root->rwsem. If some other vma in this mm shares
@@ -2943,7 +2975,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never
+ * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *