linux-stable/kernel/stackleak.c
Mark Rutland 0cfa2ccd28 stackleak: rework stack high bound handling
Prior to returning to userspace, we reset current->lowest_stack to a
reasonable high bound. Currently we do this by subtracting the arbitrary
value `THREAD_SIZE/64` from the top of the stack, for reasons lost to
history.

Looking at configurations today:

* On i386 where THREAD_SIZE is 8K, the bound will be 128 bytes. The
  pt_regs at the top of the stack is 68 bytes (with 0 to 16 bytes of
  padding above), and so this covers an additional portion of 44 to 60
  bytes.

* On x86_64 where THREAD_SIZE is at least 16K (up to 32K with KASAN) the
  bound will be at least 256 bytes (up to 512 with KASAN). The pt_regs
  at the top of the stack is 168 bytes, and so this cover an additional
  88 bytes of stack (up to 344 with KASAN).

* On arm64 where THREAD_SIZE is at least 16K (up to 64K with 64K pages
  and VMAP_STACK), the bound will be at least 256 bytes (up to 1024 with
  KASAN). The pt_regs at the top of the stack is 336 bytes, so this can
  fall within the pt_regs, or can cover an additional 688 bytes of
  stack.

Clearly the `THREAD_SIZE/64` value doesn't make much sense -- in the
worst case, this will cause more than 600 bytes of stack to be erased
for every syscall, even if actual stack usage were substantially
smaller.

This patches makes this slightly less nonsensical by consistently
resetting current->lowest_stack to the base of the task pt_regs. For
clarity and for consistency with the handling of the low bound, the
generation of the high bound is split into a helper with commentary
explaining why.

Since the pt_regs at the top of the stack will be clobbered upon the
next exception entry, we don't need to poison these at exception exit.
By using task_pt_regs() as the high stack boundary instead of
current_top_of_stack() we avoid some redundant poisoning, and the
compiler can share the address generation between the poisoning and
resetting of `current->lowest_stack`, making the generated code more
optimal.

It's not clear to me whether the existing `THREAD_SIZE/64` offset was a
dodgy heuristic to skip the pt_regs, or whether it was attempting to
minimize the number of times stackleak_check_stack() would have to
update `current->lowest_stack` when stack usage was shallow at the cost
of unconditionally poisoning a small portion of the stack for every exit
to userspace.

For now I've simply removed the offset, and if we need/want to minimize
updates for shallow stack usage it should be easy to add a better
heuristic atop, with appropriate commentary so we know what's going on.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-7-mark.rutland@arm.com
2022-05-08 01:33:08 -07:00

150 lines
4.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* This code fills the used part of the kernel stack with a poison value
* before returning to userspace. It's part of the STACKLEAK feature
* ported from grsecurity/PaX.
*
* Author: Alexander Popov <alex.popov@linux.com>
*
* STACKLEAK reduces the information which kernel stack leak bugs can
* reveal and blocks some uninitialized stack variable attacks.
*/
#include <linux/stackleak.h>
#include <linux/kprobes.h>
#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
#include <linux/jump_label.h>
#include <linux/sysctl.h>
#include <linux/init.h>
static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
#ifdef CONFIG_SYSCTL
static int stack_erasing_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int ret = 0;
int state = !static_branch_unlikely(&stack_erasing_bypass);
int prev_state = state;
table->data = &state;
table->maxlen = sizeof(int);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
state = !!state;
if (ret || !write || state == prev_state)
return ret;
if (state)
static_branch_disable(&stack_erasing_bypass);
else
static_branch_enable(&stack_erasing_bypass);
pr_warn("stackleak: kernel stack erasing is %s\n",
state ? "enabled" : "disabled");
return ret;
}
static struct ctl_table stackleak_sysctls[] = {
{
.procname = "stack_erasing",
.data = NULL,
.maxlen = sizeof(int),
.mode = 0600,
.proc_handler = stack_erasing_sysctl,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{}
};
static int __init stackleak_sysctls_init(void)
{
register_sysctl_init("kernel", stackleak_sysctls);
return 0;
}
late_initcall(stackleak_sysctls_init);
#endif /* CONFIG_SYSCTL */
#define skip_erasing() static_branch_unlikely(&stack_erasing_bypass)
#else
#define skip_erasing() false
#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */
static __always_inline void __stackleak_erase(void)
{
const unsigned long task_stack_low = stackleak_task_low_bound(current);
const unsigned long task_stack_high = stackleak_task_high_bound(current);
unsigned long erase_low = current->lowest_stack;
unsigned long erase_high;
unsigned int poison_count = 0;
const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
/* Search for the poison value in the kernel stack */
while (erase_low > task_stack_low && poison_count <= depth) {
if (*(unsigned long *)erase_low == STACKLEAK_POISON)
poison_count++;
else
poison_count = 0;
erase_low -= sizeof(unsigned long);
}
#ifdef CONFIG_STACKLEAK_METRICS
current->prev_lowest_stack = erase_low;
#endif
/*
* Write poison to the task's stack between 'erase_low' and
* 'erase_high'.
*
* If we're running on a different stack (e.g. an entry trampoline
* stack) we can erase everything below the pt_regs at the top of the
* task stack.
*
* If we're running on the task stack itself, we must not clobber any
* stack used by this function and its caller. We assume that this
* function has a fixed-size stack frame, and the current stack pointer
* doesn't change while we write poison.
*/
if (on_thread_stack())
erase_high = current_stack_pointer;
else
erase_high = task_stack_high;
while (erase_low < erase_high) {
*(unsigned long *)erase_low = STACKLEAK_POISON;
erase_low += sizeof(unsigned long);
}
/* Reset the 'lowest_stack' value for the next syscall */
current->lowest_stack = task_stack_high;
}
asmlinkage void noinstr stackleak_erase(void)
{
if (skip_erasing())
return;
__stackleak_erase();
}
void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
{
unsigned long sp = current_stack_pointer;
/*
* Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than
* STACKLEAK_SEARCH_DEPTH makes the poison search in
* stackleak_erase() unreliable. Let's prevent that.
*/
BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH);
/* 'lowest_stack' should be aligned on the register width boundary */
sp = ALIGN(sp, sizeof(unsigned long));
if (sp < current->lowest_stack &&
sp >= stackleak_task_low_bound(current)) {
current->lowest_stack = sp;
}
}
EXPORT_SYMBOL(stackleak_track_stack);