mm: larger stack guard gap, between vmas

commit 1be7107fbe18eed3e319a6c3e83c78254b693acb upstream.

Stack guard page is a useful feature to reduce a risk of stack smashing
into a different mapping. We have been using a single page gap which
is sufficient to prevent having stack adjacent to a different mapping.
But this seems to be insufficient in the light of the stack usage in
userspace. E.g. glibc uses as large as 64kB alloca() in many commonly
used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX]
which is 256kB or stack strings with MAX_ARG_STRLEN.

This will become especially dangerous for suid binaries and the default
no limit for the stack size limit because those applications can be
tricked to consume a large portion of the stack and a single glibc call
could jump over the guard page. These attacks are not theoretical,
unfortunatelly.

Make those attacks less probable by increasing the stack guard gap
to 1MB (on systems with 4k pages; but make it depend on the page size
because systems with larger base pages might cap stack allocations in
the PAGE_SIZE units) which should cover larger alloca() and VLA stack
allocations. It is obviously not a full fix because the problem is
somehow inherent, but it should reduce attack space a lot.

One could argue that the gap size should be configurable from userspace,
but that can be done later when somebody finds that the new 1MB is wrong
for some special case applications.  For now, add a kernel command line
option (stack_guard_gap) to specify the stack gap size (in page units).

Implementation wise, first delete all the old code for stack guard page:
because although we could get away with accounting one extra page in a
stack vma, accounting a larger gap can break userspace - case in point,
a program run with "ulimit -S -v 20000" failed when the 1MB gap was
counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK
and strict non-overcommit mode.

Instead of keeping gap inside the stack vma, maintain the stack guard
gap as a gap between vmas: using vm_start_gap() in place of vm_start
(or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few
places which need to respect the gap - mainly arch_get_unmapped_area(),
and and the vma tree's subtree_gap support for that.

Original-patch-by: Oleg Nesterov <oleg@redhat.com>
Original-patch-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Tested-by: Helge Deller <deller@gmx.de> # parisc
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[Hugh Dickins: Backported to 3.2]
[bwh: Fix more instances of vma->vm_start in sparc64 impl. of
 arch_get_unmapped_area_topdown() and generic impl. of
 hugetlb_get_unmapped_area()]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

1 files changed, 16 insertions, 11 deletions

diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 07e14535375c..e13e85dbfcd9 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -33,7 +33,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct * vma;
 	unsigned long task_size = TASK_SIZE;
-	unsigned long start_addr;
+	unsigned long start_addr, vm_start;
 
 	if (test_thread_flag(TIF_32BIT))
 		task_size = STACK_TOP32;
@@ -67,15 +67,17 @@ full_search:
 			}
 			return -ENOMEM;
 		}
-		if (likely(!vma || addr + len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/*
 			 * Remember the place where we stopped the search:
 			 */
 			mm->free_area_cache = addr + len;
 			return addr;
 		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
 	}
@@ -90,6 +92,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
+	unsigned long vm_start;
 
 	/* This should only ever run for 32-bit processes.  */
 	BUG_ON(!test_thread_flag(TIF_32BIT));
@@ -106,7 +109,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* make sure it can fit in the remaining address space */
 	if (likely(addr > len)) {
 		vma = find_vma(mm, addr-len);
-		if (!vma || addr <= vma->vm_start) {
+		if (!vma || addr <= vm_start_gap(vma)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr-len);
 		}
@@ -124,18 +127,20 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		 * return with success:
 		 */
 		vma = find_vma(mm, addr);
-		if (likely(!vma || addr+len <= vma->vm_start)) {
+		if (vma)
+			vm_start = vm_start_gap(vma);
+		if (likely(!vma || addr + len <= vm_start)) {
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr);
 		}
 
  		/* remember the largest hole we saw so far */
- 		if (addr + mm->cached_hole_size < vma->vm_start)
- 		        mm->cached_hole_size = vma->vm_start - addr;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = (vma->vm_start-len) & HPAGE_MASK;
-	} while (likely(len < vma->vm_start));
+		addr = (vm_start - len) & HPAGE_MASK;
+	} while (likely(len < vm_start));
 
 bottomup:
 	/*
@@ -182,7 +187,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, HPAGE_SIZE);
 		vma = find_vma(mm, addr);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 	if (mm->get_unmapped_area == arch_get_unmapped_area)