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.
Change-Id: I611023b0bfe1cab7b3e5da13e331a7baaaaf6eb0
Original-patch-by: Oleg Nesterov <oleg@redhat.com>
Original-patch-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
[wt: backport to 4.11: adjust context]
[wt: backport to 4.9: adjust context ; kernel doc was not in admin-guide]
[wt: backport to 4.4: adjust context ; drop ppc hugetlb_radix changes]
[wt: backport to 3.18: adjust context ; no FOLL_POPULATE ;
s390 uses generic arch_get_unmapped_area()]
[wt: backport to 3.16: adjust context]
[wt: backport to 3.10: adjust context ; code logic in PARISC's
arch_get_unmapped_area() wasn't found ; code inserted into
expand_upwards() and expand_downwards() runs under anon_vma lock;
changes for gup.c:faultin_page go to memory.c:__get_user_pages();
included Hugh Dickins' fixes]
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Flex1911 <dedsa2002@gmail.com>
diff --git a/mm/mmap.c b/mm/mmap.c
index 964223d..bf664b9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -247,6 +247,7 @@
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);
@@ -291,7 +292,8 @@
}
/* 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. */
@@ -1414,8 +1416,8 @@
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)
return -ENOMEM;
@@ -1425,9 +1427,10 @@
if (addr) {
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)))
return addr;
}
if (len > mm->cached_hole_size) {
@@ -1438,7 +1441,17 @@
}
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) {
/*
@@ -1453,16 +1466,16 @@
}
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
@@ -1486,9 +1499,10 @@
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, start_addr;
+ unsigned long vm_start, prev_end;
/* requested length too big for entire address space */
if (len > TASK_SIZE)
@@ -1500,9 +1514,10 @@
/* 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 &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)) &&
+ (!prev || addr >= vm_end_gap(prev)))
return addr;
}
@@ -1526,18 +1541,21 @@
* 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 = vm_end_gap(prev);
+
+ 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 (len < vma->vm_start);
+ addr = vm_start - len;
+ } while (len < vm_start);
fail:
/*
@@ -1737,7 +1755,9 @@
*/
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;
@@ -1746,23 +1766,33 @@
* 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) {
@@ -1792,27 +1822,36 @@
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) {
@@ -1836,6 +1875,23 @@
return error;
}
+/* 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)
{