On 09/10, Kees Cook wrote:
>
> I've looked more closely now. So, while I agree with you about
> resource limits, there's a corner case that is better handled here:
> once we've called flush_old_exec(), we can no longer send errors back
> to the parent. We just segfault. So, I think it's better to give a
> resource limit error early, since it is able to do the math early.
>
> If we move acct_arg_size() earlier, then the "immediate" resource
> utilization is checked, but it means it can just segfault later. If we
> leave it as-is, we account for later memory allocations "too early",
> but we'll still not be able to run: but we can tell the parent why.
I don't follow. Could you spell please?
AFAICS, the trivial patch I proposed changes nothing except it fixes the
bprm->pages accounting. The problem is really minor, but this looks confusing
and wrong anyway.
> I prefer leave it as-is.
After this discussion, I strongly disagree.
And now I think we should remove this rlim crap from get_arg_page() altogether
to make the things more clear.
> > Please forget. I meant that _if_ we actually wanted to account this
> > additional
> > memory in bprm->pages, than we would probably need something like
> > acct_arg_size(size/PAGE_SIZE + DIV_ROUND_UP(ptr_size, PAGE_SIZE)).
>
> I'd need to study that more, but that change seems reasonable. :)
Please forget. Not that it matters, but we simply can't account ptr_size
100% correctly if we do this in get_arg_page().
See the patch below. Completely untested, quite possibly wrong, but I think
this is what we should do.
Oleg.
diff --git a/fs/exec.c b/fs/exec.c
index 1ebf6e5..7804a5c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -218,55 +218,10 @@ static struct page *get_arg_page(struct linux_binprm
*bprm, unsigned long pos,
if (ret <= 0)
return NULL;
- if (write) {
- unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
- unsigned long ptr_size, limit;
-
- /*
- * Since the stack will hold pointers to the strings, we
- * must account for them as well.
- *
- * The size calculation is the entire vma while each arg page is
- * built, so each time we get here it's calculating how far it
- * is currently (rather than each call being just the newly
- * added size from the arg page). As a result, we need to
- * always add the entire size of the pointers, so that on the
- * last call to get_arg_page() we'll actually have the entire
- * correct size.
- */
- ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
- if (ptr_size > ULONG_MAX - size)
- goto fail;
- size += ptr_size;
-
- acct_arg_size(bprm, size / PAGE_SIZE);
-
- /*
- * We've historically supported up to 32 pages (ARG_MAX)
- * of argument strings even with small stacks
- */
- if (size <= ARG_MAX)
- return page;
-
- /*
- * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
- * (whichever is smaller) for the argv+env strings.
- * This ensures that:
- * - the remaining binfmt code will not run out of stack space,
- * - the program will have a reasonable amount of stack left
- * to work from.
- */
- limit = _STK_LIM / 4 * 3;
- limit = min(limit, bprm->rlim_stack.rlim_cur / 4);
- if (size > limit)
- goto fail;
- }
+ if (write)
+ acct_arg_size(bprm, vma_pages(bprm->vma));
return page;
-
-fail:
- put_page(page);
- return NULL;
}
static void put_arg_page(struct page *page)
@@ -410,11 +365,6 @@ static int bprm_mm_init(struct linux_binprm *bprm)
if (!mm)
goto err;
- /* Save current stack limit for all calculations made during exec. */
- task_lock(current->group_leader);
- bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK];
- task_unlock(current->group_leader);
-
err = __bprm_mm_init(bprm);
if (err)
goto err;
@@ -492,6 +442,27 @@ static int count(struct user_arg_ptr argv, int max)
return i;
}
+static int prepare_rlim_stack(struct linux_binprm *bprm)
+{
+ unsigned long limit, ptr_size;
+
+ task_lock(current->group_leader);
+ bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK];
+ task_unlock(current->group_leader);
+
+ limit = _STK_LIM / 4 * 3;
+ limit = min(limit, bprm->rlim_stack.rlim_cur / 4);
+ limit = max(limit, (unsigned long)ARG_MAX);
+ /* COMMENT */
+ ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+ if (limit <= ptr_size)
+ return -E2BIG;
+ limit -= ptr_size;
+
+ bprm->p_min = bprm->p - limit;
+ return 0;
+}
+
/*
* 'copy_strings()' copies argument/environment strings from the old
* processes's memory to the new process's stack. The call to get_user_pages()
@@ -527,6 +498,8 @@ static int copy_strings(int argc, struct user_arg_ptr argv,
pos = bprm->p;
str += len;
bprm->p -= len;
+ if (bprm->p <= bprm->p_min)
+ goto out;
while (len > 0) {
int offset, bytes_to_copy;
@@ -1801,6 +1774,10 @@ static int __do_execve_file(int fd, struct filename
*filename,
if (retval < 0)
goto out;
+ retval = prepare_rlim_stack(bprm);
+ if (retval < 0)
+ goto out;
+
retval = copy_strings_kernel(1, &bprm->filename, bprm);
if (retval < 0)
goto out;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index c05f24f..423e8c1 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -24,7 +24,7 @@ struct linux_binprm {
struct page *page[MAX_ARG_PAGES];
#endif
struct mm_struct *mm;
- unsigned long p; /* current top of mem */
+ unsigned long p, p_min; /* current top of mem */
unsigned int
/*
* True after the bprm_set_creds hook has been called once
