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>

2 files changed, 99 insertions, 125 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 2917e9b2e4d4..6325103db6f3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1605,12 +1605,6 @@ no_page_table:
 	return page;
 }
 
-static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr)
-{
-	return stack_guard_page_start(vma, addr) ||
-	       stack_guard_page_end(vma, addr+PAGE_SIZE);
-}
-
 /**
  * __get_user_pages() - pin user pages in memory
  * @tsk:	task_struct of target task
@@ -1761,11 +1755,6 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				int ret;
 				unsigned int fault_flags = 0;
 
-				/* For mlock, just skip the stack guard page. */
-				if (foll_flags & FOLL_MLOCK) {
-					if (stack_guard_page(vma, start))
-						goto next_page;
-				}
 				if (foll_flags & FOLL_WRITE)
 					fault_flags |= FAULT_FLAG_WRITE;
 				if (nonblocking)
@@ -3122,40 +3111,6 @@ out_release:
 }
 
 /*
- * This is like a special single-page "expand_{down|up}wards()",
- * except we must first make sure that 'address{-|+}PAGE_SIZE'
- * doesn't hit another vma.
- */
-static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
-{
-	address &= PAGE_MASK;
-	if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
-		struct vm_area_struct *prev = vma->vm_prev;
-
-		/*
-		 * Is there a mapping abutting this one below?
-		 *
-		 * That's only ok if it's the same stack mapping
-		 * that has gotten split..
-		 */
-		if (prev && prev->vm_end == address)
-			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
-
-		return expand_downwards(vma, address - PAGE_SIZE);
-	}
-	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
-		struct vm_area_struct *next = vma->vm_next;
-
-		/* As VM_GROWSDOWN but s/below/above/ */
-		if (next && next->vm_start == address + PAGE_SIZE)
-			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
-
-		return expand_upwards(vma, address + PAGE_SIZE);
-	}
-	return 0;
-}
-
-/*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
@@ -3174,10 +3129,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vma->vm_flags & VM_SHARED)
 		return VM_FAULT_SIGBUS;
 
-	/* Check if we need to add a guard page to the stack */
-	if (check_stack_guard_page(vma, address) < 0)
-		return VM_FAULT_SIGSEGV;
-
 	/* Use the zero-page for reads */
 	if (!(flags & FAULT_FLAG_WRITE)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
diff --git a/mm/mmap.c b/mm/mmap.c
index e949a2026a72..cbcf486cef8e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -245,6 +245,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	unsigned long rlim, retval;
 	unsigned long newbrk, oldbrk;
 	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *next;
 	unsigned long min_brk;
 
 	down_write(&mm->mmap_sem);
@@ -289,7 +290,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	}
 
 	/* Check against existing mmap mappings. */
-	if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
+	next = find_vma(mm, oldbrk);
+	if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
 		goto out;
 
 	/* Ok, looks good - let it rip. */
@@ -1368,8 +1370,8 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long start_addr;
+	struct vm_area_struct *vma, *prev;
+	unsigned long start_addr, vm_start, prev_end;
 
 	if (len > TASK_SIZE - mmap_min_addr)
 		return -ENOMEM;
@@ -1379,9 +1381,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			return addr;
 	}
 	if (len > mm->cached_hole_size) {
@@ -1392,7 +1395,17 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	}
 
 full_search:
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
+	for (vma = find_vma_prev(mm, addr, &prev); ; prev = vma,
+						vma = vma->vm_next) {
+		if (prev) {
+			prev_end = vm_end_gap(prev);
+			if (addr < prev_end) {
+				addr = prev_end;
+				/* If vma already violates gap, forget it */
+				if (vma && addr > vma->vm_start)
+					addr = vma->vm_start;
+			}
+		}
 		/* At this point:  (!vma || addr < vma->vm_end). */
 		if (TASK_SIZE - len < addr) {
 			/*
@@ -1407,16 +1420,16 @@ full_search:
 			}
 			return -ENOMEM;
 		}
-		if (!vma || addr + len <= vma->vm_start) {
+		vm_start = vma ? vm_start_gap(vma) : TASK_SIZE;
+		if (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;
-		addr = vma->vm_end;
+		if (addr + mm->cached_hole_size < vm_start)
+			mm->cached_hole_size = vm_start - addr;
 	}
 }
 #endif	
@@ -1442,9 +1455,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			  const unsigned long len, const unsigned long pgoff,
 			  const unsigned long flags)
 {
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = addr0;
+	unsigned long vm_start, prev_end;
 	unsigned long low_limit = max(PAGE_SIZE, mmap_min_addr);
 
 	/* requested length too big for entire address space */
@@ -1457,9 +1471,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* requesting a specific address */
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)) &&
+				(!prev || addr >= vm_end_gap(prev)))
 			return addr;
 	}
 
@@ -1474,8 +1489,9 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 	/* make sure it can fit in the remaining address space */
 	if (addr >= low_limit + len) {
-		vma = find_vma(mm, addr-len);
-		if (!vma || addr <= vma->vm_start)
+		vma = find_vma_prev(mm, addr-len, &prev);
+		if ((!vma || addr <= vm_start_gap(vma)) &&
+		    (!prev || addr-len >= vm_end_gap(prev)))
 			/* remember the address as a hint for next time */
 			return (mm->free_area_cache = addr-len);
 	}
@@ -1491,18 +1507,21 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		 * else if new region fits below vma->vm_start,
 		 * return with success:
 		 */
-		vma = find_vma(mm, addr);
-		if (!vma || addr+len <= vma->vm_start)
+		vma = find_vma_prev(mm, addr, &prev);
+		vm_start = vma ? vm_start_gap(vma) : mm->mmap_base;
+		prev_end = prev ? vm_end_gap(prev) : low_limit;
+
+		if (addr + len <= vm_start && addr >= prev_end)
 			/* 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;
-	} while (vma->vm_start >= low_limit + len);
+		addr = vm_start - len;
+	} while (vm_start >= low_limit + len);
 
 bottomup:
 	/*
@@ -1647,21 +1666,19 @@ out:
  * update accounting. This is shared with both the
  * grow-up and grow-down cases.
  */
-static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
+static int acct_stack_growth(struct vm_area_struct *vma,
+			     unsigned long size, unsigned long grow)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
-	unsigned long new_start, actual_size;
+	unsigned long new_start;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
-	actual_size = size;
-	if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
-		actual_size -= PAGE_SIZE;
-	if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+	if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
 		return -ENOMEM;
 
 	/* mlock limit tests */
@@ -1703,32 +1720,40 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
  */
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
-	int error;
+	struct vm_area_struct *next;
+	unsigned long gap_addr;
+	int error = 0;
 
 	if (!(vma->vm_flags & VM_GROWSUP))
 		return -EFAULT;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
+	/* Guard against wrapping around to address 0. */
+	address &= PAGE_MASK;
+	address += PAGE_SIZE;
+	if (!address)
+		return -ENOMEM;
+
+	/* Enforce stack_guard_gap */
+	gap_addr = address + stack_guard_gap;
+	if (gap_addr < address)
+		return -ENOMEM;
+	next = vma->vm_next;
+	if (next && next->vm_start < gap_addr) {
+		if (!(next->vm_flags & VM_GROWSUP))
+			return -ENOMEM;
+		/* Check that both stack segments have the same anon_vma? */
+	}
+
+	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
-	vma_lock_anon_vma(vma);
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
-	 * Also guard against wrapping around to address 0.
 	 */
-	if (address < PAGE_ALIGN(address+4))
-		address = PAGE_ALIGN(address+4);
-	else {
-		vma_unlock_anon_vma(vma);
-		return -ENOMEM;
-	}
-	error = 0;
+	vma_lock_anon_vma(vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address > vma->vm_end) {
@@ -1758,27 +1783,36 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 int expand_downwards(struct vm_area_struct *vma,
 				   unsigned long address)
 {
+	struct vm_area_struct *prev;
+	unsigned long gap_addr;
 	int error;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
-	if (unlikely(anon_vma_prepare(vma)))
-		return -ENOMEM;
-
 	address &= PAGE_MASK;
 	error = security_file_mmap(NULL, 0, 0, 0, address, 1);
 	if (error)
 		return error;
 
-	vma_lock_anon_vma(vma);
+	/* Enforce stack_guard_gap */
+	gap_addr = address - stack_guard_gap;
+	if (gap_addr > address)
+		return -ENOMEM;
+	prev = vma->vm_prev;
+	if (prev && prev->vm_end > gap_addr) {
+		if (!(prev->vm_flags & VM_GROWSDOWN))
+			return -ENOMEM;
+		/* Check that both stack segments have the same anon_vma? */
+	}
+
+	/* We must make sure the anon_vma is allocated. */
+	if (unlikely(anon_vma_prepare(vma)))
+		return -ENOMEM;
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
 	 */
+	vma_lock_anon_vma(vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address < vma->vm_start) {
@@ -1802,28 +1836,25 @@ 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.
- */
+/* enforced gap between the expanding stack and other mappings. */
+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
+
+static int __init cmdline_parse_stack_guard_gap(char *p)
+{
+	unsigned long val;
+	char *endptr;
+
+	val = simple_strtoul(p, &endptr, 10);
+	if (!*endptr)
+		stack_guard_gap = val << PAGE_SHIFT;
+
+	return 0;
+}
+__setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);
+
 #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);
 }
 
@@ -1846,14 +1877,6 @@ 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);
 }