1 files changed, 74 insertions, 22 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index f7cd9cb..6c04292 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -191,16 +191,19 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long retval;
-	unsigned long newbrk, oldbrk;
+	unsigned long newbrk, oldbrk, origbrk;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *next;
 	unsigned long min_brk;
 	bool populate;
+	bool downgraded = false;
 	LIST_HEAD(uf);
 
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
+	origbrk = mm->brk;
+
 #ifdef CONFIG_COMPAT_BRK
 	/*
 	 * CONFIG_COMPAT_BRK can still be overridden by setting
@@ -229,14 +232,32 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 
 	newbrk = PAGE_ALIGN(brk);
 	oldbrk = PAGE_ALIGN(mm->brk);
-	if (oldbrk == newbrk)
-		goto set_brk;
+	if (oldbrk == newbrk) {
+		mm->brk = brk;
+		goto success;
+	}
 
-	/* Always allow shrinking brk. */
+	/*
+	 * Always allow shrinking brk.
+	 * __do_munmap() may downgrade mmap_sem to read.
+	 */
 	if (brk <= mm->brk) {
-		if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf))
-			goto set_brk;
-		goto out;
+		int ret;
+
+		/*
+		 * mm->brk must to be protected by write mmap_sem so update it
+		 * before downgrading mmap_sem. When __do_munmap() fails,
+		 * mm->brk will be restored from origbrk.
+		 */
+		mm->brk = brk;
+		ret = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true);
+		if (ret < 0) {
+			mm->brk = origbrk;
+			goto out;
+		} else if (ret == 1) {
+			downgraded = true;
+		}
+		goto success;
 	}
 
 	/* Check against existing mmap mappings. */
@@ -247,18 +268,21 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	/* Ok, looks good - let it rip. */
 	if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
 		goto out;
-
-set_brk:
 	mm->brk = brk;
+
+success:
 	populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
-	up_write(&mm->mmap_sem);
+	if (downgraded)
+		up_read(&mm->mmap_sem);
+	else
+		up_write(&mm->mmap_sem);
 	userfaultfd_unmap_complete(mm, &uf);
 	if (populate)
 		mm_populate(oldbrk, newbrk - oldbrk);
 	return brk;
 
 out:
-	retval = mm->brk;
+	retval = origbrk;
 	up_write(&mm->mmap_sem);
 	return retval;
 }
@@ -2687,8 +2711,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
  * work.  This now handles partial unmappings.
  * Jeremy Fitzhardinge <jeremy@goop.org>
  */
-int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
-	      struct list_head *uf)
+int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
+		struct list_head *uf, bool downgrade)
 {
 	unsigned long end;
 	struct vm_area_struct *vma, *prev, *last;
@@ -2770,25 +2794,38 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
 				mm->locked_vm -= vma_pages(tmp);
 				munlock_vma_pages_all(tmp);
 			}
+
 			tmp = tmp->vm_next;
 		}
 	}
 
-	/*
-	 * Remove the vma's, and unmap the actual pages
-	 */
+	/* Detach vmas from rbtree */
 	detach_vmas_to_be_unmapped(mm, vma, prev, end);
-	unmap_region(mm, vma, prev, start, end);
 
+	/*
+	 * mpx unmap needs to be called with mmap_sem held for write.
+	 * It is safe to call it before unmap_region().
+	 */
 	arch_unmap(mm, vma, start, end);
 
+	if (downgrade)
+		downgrade_write(&mm->mmap_sem);
+
+	unmap_region(mm, vma, prev, start, end);
+
 	/* Fix up all other VM information */
 	remove_vma_list(mm, vma);
 
-	return 0;
+	return downgrade ? 1 : 0;
 }
 
-int vm_munmap(unsigned long start, size_t len)
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
+	      struct list_head *uf)
+{
+	return __do_munmap(mm, start, len, uf, false);
+}
+
+static int __vm_munmap(unsigned long start, size_t len, bool downgrade)
 {
 	int ret;
 	struct mm_struct *mm = current->mm;
@@ -2797,17 +2834,32 @@ int vm_munmap(unsigned long start, size_t len)
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
-	ret = do_munmap(mm, start, len, &uf);
-	up_write(&mm->mmap_sem);
+	ret = __do_munmap(mm, start, len, &uf, downgrade);
+	/*
+	 * Returning 1 indicates mmap_sem is downgraded.
+	 * But 1 is not legal return value of vm_munmap() and munmap(), reset
+	 * it to 0 before return.
+	 */
+	if (ret == 1) {
+		up_read(&mm->mmap_sem);
+		ret = 0;
+	} else
+		up_write(&mm->mmap_sem);
+
 	userfaultfd_unmap_complete(mm, &uf);
 	return ret;
 }
+
+int vm_munmap(unsigned long start, size_t len)
+{
+	return __vm_munmap(start, len, false);
+}
 EXPORT_SYMBOL(vm_munmap);
 
 SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
 	profile_munmap(addr);
-	return vm_munmap(addr, len);
+	return __vm_munmap(addr, len, true);
 }