mm: larger stack guard gap, between vmas

[ Upstream commit 1be7107f ]

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>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

Documentation/kernel-parameters.txt

@@ -3453,6 +3453,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	spia_pedr=
 	spia_peddr=
 
+	stack_guard_gap=	[MM]
+			override the default stack gap protection. The value
+			is in page units and it defines how many pages prior
+			to (for stacks growing down) resp. after (for stacks
+			growing up) the main stack are reserved for no other
+			mapping. Default value is 256 pages.
+
 	stacktrace	[FTRACE]
 			Enabled the stack tracer on boot up.
 

arch/arc/mm/mmap.c

@@ -64,7 +64,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		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;
 	}
 

arch/arm/mm/mmap.c

@@ -89,7 +89,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		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;
 	}
 
@@ -140,7 +140,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			addr = PAGE_ALIGN(addr);
 		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;
 	}
 

arch/frv/mm/elf-fdpic.c

@@ -74,7 +74,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(current->mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			goto success;
 	}
 

arch/mips/mm/mmap.c

@@ -92,7 +92,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 
 		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;
 	}
 

arch/parisc/kernel/sys_parisc.c

@@ -88,7 +88,7 @@ unsigned long 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;
+	struct vm_area_struct *vma, *prev;
 	unsigned long task_size = TASK_SIZE;
 	int do_color_align, last_mmap;
 	struct vm_unmapped_area_info info;
@@ -115,9 +115,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		else
 			addr = PAGE_ALIGN(addr);
 
-		vma = find_vma(mm, addr);
+		vma = find_vma_prev(mm, addr, &prev);
 		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			goto found_addr;
 	}
 
@@ -141,7 +142,7 @@ 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;
 	int do_color_align, last_mmap;
@@ -175,9 +176,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			addr = COLOR_ALIGN(addr, last_mmap, pgoff);
 		else
 			addr = PAGE_ALIGN(addr);
-		vma = find_vma(mm, addr);
+
+		vma = find_vma_prev(mm, addr, &prev);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)) &&
+		    (!prev || addr >= vm_end_gap(prev)))
 			goto found_addr;
 	}
 

arch/powerpc/mm/slice.c

@@ -105,7 +105,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
 	if ((mm->task_size - len) < addr)
 		return 0;
 	vma = find_vma(mm, addr);
-	return (!vma || (addr + len) <= vma->vm_start);
+	return (!vma || (addr + len) <= vm_start_gap(vma));
 }
 
 static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)

arch/s390/mm/mmap.c

@@ -104,7 +104,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -144,7 +144,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-				(!vma || addr + len <= vma->vm_start))
+				(!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 

arch/sh/mm/mmap.c

@@ -63,7 +63,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 
 		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;
 	}
 
@@ -113,7 +113,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 		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;
 	}
 

arch/sparc/kernel/sys_sparc_64.c

@@ -118,7 +118,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 
 		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;
 	}
 
@@ -181,7 +181,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 		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;
 	}
 

arch/sparc/mm/hugetlbpage.c

@@ -115,7 +115,7 @@ 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)

arch/tile/mm/hugetlbpage.c

@@ -237,7 +237,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		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 (current->mm->get_unmapped_area == arch_get_unmapped_area)

arch/x86/kernel/sys_x86_64.c

@@ -143,7 +143,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
 		if (end - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -186,7 +186,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		addr = PAGE_ALIGN(addr);
 		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;
 	}
 

arch/x86/mm/hugetlbpage.c

@@ -144,7 +144,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		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)

arch/xtensa/kernel/syscall.c

@@ -87,7 +87,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		/* At this point:  (!vmm || addr < vmm->vm_end). */
 		if (TASK_SIZE - len < addr)
 			return -ENOMEM;
-		if (!vmm || addr + len <= vmm->vm_start)
+		if (!vmm || addr + len <= vm_start_gap(vmm))
 			return addr;
 		addr = vmm->vm_end;
 		if (flags & MAP_SHARED)

fs/hugetlbfs/inode.c

@@ -168,7 +168,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		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;
 	}
 

fs/proc/task_mmu.c

@@ -287,11 +287,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	/* We don't show the stack guard page in /proc/maps */
 	start = vma->vm_start;
-	if (stack_guard_page_start(vma, start))
-		start += PAGE_SIZE;
 	end = vma->vm_end;
-	if (stack_guard_page_end(vma, end))
-		end -= PAGE_SIZE;
 
 	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
 	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",

include/linux/mm.h

@@ -1247,34 +1247,6 @@ int clear_page_dirty_for_io(struct page *page);
 
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 
-/* Is the vma a continuation of the stack vma above it? */
-static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
-{
-	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
-}
-
-static inline int stack_guard_page_start(struct vm_area_struct *vma,
-					     unsigned long addr)
-{
-	return (vma->vm_flags & VM_GROWSDOWN) &&
-		(vma->vm_start == addr) &&
-		!vma_growsdown(vma->vm_prev, addr);
-}
-
-/* Is the vma a continuation of the stack vma below it? */
-static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr)
-{
-	return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP);
-}
-
-static inline int stack_guard_page_end(struct vm_area_struct *vma,
-					   unsigned long addr)
-{
-	return (vma->vm_flags & VM_GROWSUP) &&
-		(vma->vm_end == addr) &&
-		!vma_growsup(vma->vm_next, addr);
-}
-
 extern struct task_struct *task_of_stack(struct task_struct *task,
 				struct vm_area_struct *vma, bool in_group);
 
@@ -1965,6 +1937,7 @@ void page_cache_async_readahead(struct address_space *mapping,
 
 unsigned long max_sane_readahead(unsigned long nr);
 
+extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 
@@ -1993,6 +1966,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m
 	return vma;
 }
 
+static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
+{
+	unsigned long vm_start = vma->vm_start;
+
+	if (vma->vm_flags & VM_GROWSDOWN) {
+		vm_start -= stack_guard_gap;
+		if (vm_start > vma->vm_start)
+			vm_start = 0;
+	}
+	return vm_start;
+}
+
+static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
+{
+	unsigned long vm_end = vma->vm_end;
+
+	if (vma->vm_flags & VM_GROWSUP) {
+		vm_end += stack_guard_gap;
+		if (vm_end < vma->vm_end)
+			vm_end = -PAGE_SIZE;
+	}
+	return vm_end;
+}
+
 static inline unsigned long vma_pages(struct vm_area_struct *vma)
 {
 	return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;

mm/gup.c

@@ -275,11 +275,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	unsigned int fault_flags = 0;
 	int ret;
 
-	/* For mm_populate(), just skip the stack guard page. */
-	if ((*flags & FOLL_POPULATE) &&
-			(stack_guard_page_start(vma, address) ||
-			 stack_guard_page_end(vma, address + PAGE_SIZE)))
-		return -ENOENT;
 	if (*flags & FOLL_WRITE)
 		fault_flags |= FAULT_FLAG_WRITE;
 	if (nonblocking)

mm/memory.c

@@ -2619,40 +2619,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	return ret;
 }
 
-/*
- * 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.
@@ -2673,10 +2639,6 @@ 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) && !mm_forbids_zeropage(mm)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),