mirror of
https://github.com/torvalds/linux
synced 2024-09-06 18:01:05 +00:00
ef1a840934
The stackleak_erase() function is called on the trampoline stack at the
end of syscall. This stack is not big enough for ftrace and kprobes
operations, e.g. it can be exhausted if we use kprobe_events for
stackleak_erase().
So let's disable function tracing and kprobes of stackleak_erase().
Reported-by: kernel test robot <lkp@intel.com>
Fixes: 10e9ae9fab ("gcc-plugins: Add STACKLEAK plugin for tracking the kernel stack")
Signed-off-by: Alexander Popov <alex.popov@linux.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
135 lines
3.9 KiB
C
135 lines
3.9 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>
|
|
|
|
static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
|
|
|
|
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;
|
|
}
|
|
|
|
#define skip_erasing() static_branch_unlikely(&stack_erasing_bypass)
|
|
#else
|
|
#define skip_erasing() false
|
|
#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */
|
|
|
|
asmlinkage void notrace stackleak_erase(void)
|
|
{
|
|
/* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */
|
|
unsigned long kstack_ptr = current->lowest_stack;
|
|
unsigned long boundary = (unsigned long)end_of_stack(current);
|
|
unsigned int poison_count = 0;
|
|
const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
|
|
|
|
if (skip_erasing())
|
|
return;
|
|
|
|
/* Check that 'lowest_stack' value is sane */
|
|
if (unlikely(kstack_ptr - boundary >= THREAD_SIZE))
|
|
kstack_ptr = boundary;
|
|
|
|
/* Search for the poison value in the kernel stack */
|
|
while (kstack_ptr > boundary && poison_count <= depth) {
|
|
if (*(unsigned long *)kstack_ptr == STACKLEAK_POISON)
|
|
poison_count++;
|
|
else
|
|
poison_count = 0;
|
|
|
|
kstack_ptr -= sizeof(unsigned long);
|
|
}
|
|
|
|
/*
|
|
* One 'long int' at the bottom of the thread stack is reserved and
|
|
* should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y).
|
|
*/
|
|
if (kstack_ptr == boundary)
|
|
kstack_ptr += sizeof(unsigned long);
|
|
|
|
#ifdef CONFIG_STACKLEAK_METRICS
|
|
current->prev_lowest_stack = kstack_ptr;
|
|
#endif
|
|
|
|
/*
|
|
* Now write the poison value to the kernel stack. Start from
|
|
* 'kstack_ptr' and move up till the new 'boundary'. We assume that
|
|
* the stack pointer doesn't change when we write poison.
|
|
*/
|
|
if (on_thread_stack())
|
|
boundary = current_stack_pointer;
|
|
else
|
|
boundary = current_top_of_stack();
|
|
|
|
while (kstack_ptr < boundary) {
|
|
*(unsigned long *)kstack_ptr = STACKLEAK_POISON;
|
|
kstack_ptr += sizeof(unsigned long);
|
|
}
|
|
|
|
/* Reset the 'lowest_stack' value for the next syscall */
|
|
current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64;
|
|
}
|
|
NOKPROBE_SYMBOL(stackleak_erase);
|
|
|
|
void __used stackleak_track_stack(void)
|
|
{
|
|
/*
|
|
* N.B. stackleak_erase() fills the kernel stack with the poison value,
|
|
* which has the register width. That code assumes that the value
|
|
* of 'lowest_stack' is aligned on the register width boundary.
|
|
*
|
|
* That is true for x86 and x86_64 because of the kernel stack
|
|
* alignment on these platforms (for details, see 'cc_stack_align' in
|
|
* arch/x86/Makefile). Take care of that when you port STACKLEAK to
|
|
* new platforms.
|
|
*/
|
|
unsigned long sp = (unsigned long)&sp;
|
|
|
|
/*
|
|
* 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);
|
|
|
|
if (sp < current->lowest_stack &&
|
|
sp >= (unsigned long)task_stack_page(current) +
|
|
sizeof(unsigned long)) {
|
|
current->lowest_stack = sp;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(stackleak_track_stack);
|