linux/kernel/scs.c
Yee Lee 528a4ab453 scs: Release kasan vmalloc poison in scs_free process
Since scs allocation is moved to vmalloc region, the
shadow stack is protected by kasan_posion_vmalloc.
However, the vfree_atomic operation needs to access
its context for scs_free process and causes kasan error
as the dump info below.

This patch Adds kasan_unpoison_vmalloc() before vfree_atomic,
which aligns to the prior flow as using kmem_cache.
The vmalloc region will go back posioned in the following
vumap() operations.

 ==================================================================
 BUG: KASAN: vmalloc-out-of-bounds in llist_add_batch+0x60/0xd4
 Write of size 8 at addr ffff8000100b9000 by task kthreadd/2

 CPU: 0 PID: 2 Comm: kthreadd Not tainted 5.15.0-rc2-11681-g92477dd1faa6-dirty #1
 Hardware name: linux,dummy-virt (DT)
 Call trace:
  dump_backtrace+0x0/0x43c
  show_stack+0x1c/0x2c
  dump_stack_lvl+0x68/0x84
  print_address_description+0x80/0x394
  kasan_report+0x180/0x1dc
  __asan_report_store8_noabort+0x48/0x58
  llist_add_batch+0x60/0xd4
  vfree_atomic+0x60/0xe0
  scs_free+0x1dc/0x1fc
  scs_release+0xa4/0xd4
  free_task+0x30/0xe4
  __put_task_struct+0x1ec/0x2e0
  delayed_put_task_struct+0x5c/0xa0
  rcu_do_batch+0x62c/0x8a0
  rcu_core+0x60c/0xc14
  rcu_core_si+0x14/0x24
  __do_softirq+0x19c/0x68c
  irq_exit+0x118/0x2dc
  handle_domain_irq+0xcc/0x134
  gic_handle_irq+0x7c/0x1bc
  call_on_irq_stack+0x40/0x70
  do_interrupt_handler+0x78/0x9c
  el1_interrupt+0x34/0x60
  el1h_64_irq_handler+0x1c/0x2c
  el1h_64_irq+0x78/0x7c
  _raw_spin_unlock_irqrestore+0x40/0xcc
  sched_fork+0x4f0/0xb00
  copy_process+0xacc/0x3648
  kernel_clone+0x168/0x534
  kernel_thread+0x13c/0x1b0
  kthreadd+0x2bc/0x400
  ret_from_fork+0x10/0x20

 Memory state around the buggy address:
  ffff8000100b8f00: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
  ffff8000100b8f80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
 >ffff8000100b9000: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
                    ^
  ffff8000100b9080: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
  ffff8000100b9100: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
 ==================================================================

Suggested-by: Kuan-Ying Lee <kuan-ying.lee@mediatek.com>
Acked-by: Will Deacon <will@kernel.org>
Tested-by: Will Deacon <will@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Yee Lee <yee.lee@mediatek.com>
Fixes: a2abe7cbd8 ("scs: switch to vmapped shadow stacks")
Link: https://lore.kernel.org/r/20210930081619.30091-1-yee.lee@mediatek.com
Signed-off-by: Will Deacon <will@kernel.org>
2021-09-30 09:37:27 +01:00

155 lines
2.8 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Shadow Call Stack support.
*
* Copyright (C) 2019 Google LLC
*/
#include <linux/cpuhotplug.h>
#include <linux/kasan.h>
#include <linux/mm.h>
#include <linux/scs.h>
#include <linux/vmalloc.h>
#include <linux/vmstat.h>
static void __scs_account(void *s, int account)
{
struct page *scs_page = vmalloc_to_page(s);
mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
account * (SCS_SIZE / SZ_1K));
}
/* Matches NR_CACHED_STACKS for VMAP_STACK */
#define NR_CACHED_SCS 2
static DEFINE_PER_CPU(void *, scs_cache[NR_CACHED_SCS]);
static void *__scs_alloc(int node)
{
int i;
void *s;
for (i = 0; i < NR_CACHED_SCS; i++) {
s = this_cpu_xchg(scs_cache[i], NULL);
if (s) {
kasan_unpoison_vmalloc(s, SCS_SIZE);
memset(s, 0, SCS_SIZE);
return s;
}
}
return __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
GFP_SCS, PAGE_KERNEL, 0, node,
__builtin_return_address(0));
}
void *scs_alloc(int node)
{
void *s;
s = __scs_alloc(node);
if (!s)
return NULL;
*__scs_magic(s) = SCS_END_MAGIC;
/*
* Poison the allocation to catch unintentional accesses to
* the shadow stack when KASAN is enabled.
*/
kasan_poison_vmalloc(s, SCS_SIZE);
__scs_account(s, 1);
return s;
}
void scs_free(void *s)
{
int i;
__scs_account(s, -1);
/*
* We cannot sleep as this can be called in interrupt context,
* so use this_cpu_cmpxchg to update the cache, and vfree_atomic
* to free the stack.
*/
for (i = 0; i < NR_CACHED_SCS; i++)
if (this_cpu_cmpxchg(scs_cache[i], 0, s) == NULL)
return;
kasan_unpoison_vmalloc(s, SCS_SIZE);
vfree_atomic(s);
}
static int scs_cleanup(unsigned int cpu)
{
int i;
void **cache = per_cpu_ptr(scs_cache, cpu);
for (i = 0; i < NR_CACHED_SCS; i++) {
vfree(cache[i]);
cache[i] = NULL;
}
return 0;
}
void __init scs_init(void)
{
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "scs:scs_cache", NULL,
scs_cleanup);
}
int scs_prepare(struct task_struct *tsk, int node)
{
void *s = scs_alloc(node);
if (!s)
return -ENOMEM;
task_scs(tsk) = task_scs_sp(tsk) = s;
return 0;
}
static void scs_check_usage(struct task_struct *tsk)
{
static unsigned long highest;
unsigned long *p, prev, curr = highest, used = 0;
if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE))
return;
for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) {
if (!READ_ONCE_NOCHECK(*p))
break;
used += sizeof(*p);
}
while (used > curr) {
prev = cmpxchg_relaxed(&highest, curr, used);
if (prev == curr) {
pr_info("%s (%d): highest shadow stack usage: %lu bytes\n",
tsk->comm, task_pid_nr(tsk), used);
break;
}
curr = prev;
}
}
void scs_release(struct task_struct *tsk)
{
void *s = task_scs(tsk);
if (!s)
return;
WARN(task_scs_end_corrupted(tsk),
"corrupted shadow stack detected when freeing task\n");
scs_check_usage(tsk);
scs_free(s);
}