linux/kernel/scs.c
Andrey Konovalov f6e39794f4 kasan, vmalloc: only tag normal vmalloc allocations
The kernel can use to allocate executable memory.  The only supported
way to do that is via __vmalloc_node_range() with the executable bit set
in the prot argument.  (vmap() resets the bit via pgprot_nx()).

Once tag-based KASAN modes start tagging vmalloc allocations, executing
code from such allocations will lead to the PC register getting a tag,
which is not tolerated by the kernel.

Only tag the allocations for normal kernel pages.

[andreyknvl@google.com: pass KASAN_VMALLOC_PROT_NORMAL to kasan_unpoison_vmalloc()]
  Link: https://lkml.kernel.org/r/9230ca3d3e40ffca041c133a524191fd71969a8d.1646233925.git.andreyknvl@google.com
[andreyknvl@google.com: support tagged vmalloc mappings]
  Link: https://lkml.kernel.org/r/2f6605e3a358cf64d73a05710cb3da356886ad29.1646233925.git.andreyknvl@google.com
[andreyknvl@google.com: don't unintentionally disabled poisoning]
  Link: https://lkml.kernel.org/r/de4587d6a719232e83c760113e46ed2d4d8da61e.1646757322.git.andreyknvl@google.com

Link: https://lkml.kernel.org/r/fbfd9939a4dc375923c9a5c6b9e7ab05c26b8c6b.1643047180.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-24 19:06:48 -07:00

159 lines
2.9 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) {
s = kasan_unpoison_vmalloc(s, SCS_SIZE,
KASAN_VMALLOC_PROT_NORMAL);
memset(s, 0, SCS_SIZE);
goto out;
}
}
s = __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
GFP_SCS, PAGE_KERNEL, 0, node,
__builtin_return_address(0));
out:
return kasan_reset_tag(s);
}
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, KASAN_VMALLOC_PROT_NORMAL);
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);
}