[PATCH v3 0/5] Optionally randomize kernel stack offset each syscall

[PATCH v3 0/5] Optionally randomize kernel stack offset each syscall

[Kees Cook]

v3:
- added review/ack tags (peterz, glider)
- further clarified commit logs and public attack references
- added -fstack-protector downgrades and details
v2: https://lore.kernel.org/lkml/20200324203231.64324-1-keescook@chromium.org/
rfc: https://lore.kernel.org/kernel-hardening/20190329081358.30497-1-elena.reshetova@intel.com/

Hi,

This is a continuation and refactoring of Elena's earlier effort to add
kernel stack base offset randomization. In the time since the previous
discussions, two attacks[1][2] were made public that depended on stack
determinism, so we're no longer in the position of "this is a good idea
but we have no examples of attacks". :)

Earlier discussions also devolved into debates on entropy sources, which
is mostly a red herring, given the already low entropy available due
to stack size. Regardless, entropy can be changed/improved separately
from this series as needed.

Earlier discussions also got stuck debating how much syscall overhead
was too much, but this is also a red herring since the feature itself
needs to be selectable at boot with no cost for those that don't want it:
this is solved here with static branches.

So, here is an improved version, made as arch-agnostic as possible,
with usage added for x86 and arm64. It also includes some small static
branch clean ups, and addresses some surprise performance issues due to
the stack canary[3].

Thanks!

-Kees

[1] https://a13xp0p0v.github.io/2020/02/15/CVE-2019-18683.html
[2] https://repositorio-aberto.up.pt/bitstream/10216/125357/2/374717.pdf
[3] https://lore.kernel.org/lkml/202003281520.A9BFF461@keescook/

Kees Cook (5):
  jump_label: Provide CONFIG-driven build state defaults
  init_on_alloc: Unpessimize default-on builds
  stack: Optionally randomize kernel stack offset each syscall
  x86/entry: Enable random_kstack_offset support
  arm64: entry: Enable random_kstack_offset support

 Makefile                         |  4 ++++
 arch/Kconfig                     | 23 ++++++++++++++++++
 arch/arm64/Kconfig               |  1 +
 arch/arm64/kernel/Makefile       |  4 ++++
 arch/arm64/kernel/syscall.c      | 10 ++++++++
 arch/x86/Kconfig                 |  1 +
 arch/x86/entry/Makefile          |  9 +++++++
 arch/x86/entry/common.c          | 12 +++++++++-
 include/linux/jump_label.h       | 19 +++++++++++++++
 include/linux/mm.h               | 18 +++++---------
 include/linux/randomize_kstack.h | 40 ++++++++++++++++++++++++++++++++
 init/main.c                      | 23 ++++++++++++++++++
 mm/page_alloc.c                  | 12 ++--------
 13 files changed, 153 insertions(+), 23 deletions(-)
 create mode 100644 include/linux/randomize_kstack.h

-- 
2.20.1

[PATCH v3 1/5] jump_label: Provide CONFIG-driven build state defaults

[Kees Cook]

Choosing the initial state of static branches changes the assembly
layout (if the condition is expected to be likely, inline, or unlikely,
out of line via a jump). A few places in the kernel use (or could be
using) a CONFIG to choose the default state, so provide the
infrastructure to do this and convert the existing cases (init_on_alloc
and init_on_free) to the new macros.

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/jump_label.h | 19 +++++++++++++++++++
 include/linux/mm.h         | 12 ++----------
 mm/page_alloc.c            | 12 ++----------
 3 files changed, 23 insertions(+), 20 deletions(-)

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 3526c0aee954..615fdfb871a3 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -382,6 +382,21 @@ struct static_key_false {
 		[0 ... (count) - 1] = STATIC_KEY_FALSE_INIT,	\
 	}
 
+#define _DEFINE_STATIC_KEY_1(name)	DEFINE_STATIC_KEY_TRUE(name)
+#define _DEFINE_STATIC_KEY_0(name)	DEFINE_STATIC_KEY_FALSE(name)
+#define DEFINE_STATIC_KEY_MAYBE(cfg, name)			\
+	__PASTE(_DEFINE_STATIC_KEY_, IS_ENABLED(cfg))(name)
+
+#define _DEFINE_STATIC_KEY_RO_1(name)	DEFINE_STATIC_KEY_TRUE_RO(name)
+#define _DEFINE_STATIC_KEY_RO_0(name)	DEFINE_STATIC_KEY_FALSE_RO(name)
+#define DEFINE_STATIC_KEY_MAYBE_RO(cfg, name)			\
+	__PASTE(_DEFINE_STATIC_KEY_RO_, IS_ENABLED(cfg))(name)
+
+#define _DECLARE_STATIC_KEY_1(name)	DECLARE_STATIC_KEY_TRUE(name)
+#define _DECLARE_STATIC_KEY_0(name)	DECLARE_STATIC_KEY_FALSE(name)
+#define DECLARE_STATIC_KEY_MAYBE(cfg, name)			\
+	__PASTE(_DECLARE_STATIC_KEY_, IS_ENABLED(cfg))(name)
+
 extern bool ____wrong_branch_error(void);
 
 #define static_key_enabled(x)							\
@@ -482,6 +497,10 @@ extern bool ____wrong_branch_error(void);
 
 #endif /* CONFIG_JUMP_LABEL */
 
+#define static_branch_maybe(config, x)					\
+	(IS_ENABLED(config) ? static_branch_likely(x)			\
+			    : static_branch_unlikely(x))
+
 /*
  * Advanced usage; refcount, branch is enabled when: count != 0
  */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c54fb96cb1e6..059658604dd6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2662,11 +2662,7 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 					int enable) { }
 #endif
 
-#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON
-DECLARE_STATIC_KEY_TRUE(init_on_alloc);
-#else
-DECLARE_STATIC_KEY_FALSE(init_on_alloc);
-#endif
+DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
 static inline bool want_init_on_alloc(gfp_t flags)
 {
 	if (static_branch_unlikely(&init_on_alloc) &&
@@ -2675,11 +2671,7 @@ static inline bool want_init_on_alloc(gfp_t flags)
 	return flags & __GFP_ZERO;
 }
 
-#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON
-DECLARE_STATIC_KEY_TRUE(init_on_free);
-#else
-DECLARE_STATIC_KEY_FALSE(init_on_free);
-#endif
+DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
 static inline bool want_init_on_free(void)
 {
 	return static_branch_unlikely(&init_on_free) &&
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c4eb750a199..1f625e5a03c0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -135,18 +135,10 @@ unsigned long totalcma_pages __read_mostly;
 
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
-#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON
-DEFINE_STATIC_KEY_TRUE(init_on_alloc);
-#else
-DEFINE_STATIC_KEY_FALSE(init_on_alloc);
-#endif
+DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
 EXPORT_SYMBOL(init_on_alloc);
 
-#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON
-DEFINE_STATIC_KEY_TRUE(init_on_free);
-#else
-DEFINE_STATIC_KEY_FALSE(init_on_free);
-#endif
+DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
 EXPORT_SYMBOL(init_on_free);
 
 static int __init early_init_on_alloc(char *buf)
-- 
2.20.1

[PATCH v3 2/5] init_on_alloc: Unpessimize default-on builds

[Kees Cook]

Right now, the state of CONFIG_INIT_ON_ALLOC_DEFAULT_ON (and
...ON_FREE...) did not change the assembly ordering of the static branch
tests. Use the new jump_label macro to check CONFIG settings to default
to the "expected" state, unpessimizes the resulting assembly code.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Alexander Potapenko <glider@google.com>
---
 include/linux/mm.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 059658604dd6..64e911159ffa 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2665,7 +2665,8 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
 static inline bool want_init_on_alloc(gfp_t flags)
 {
-	if (static_branch_unlikely(&init_on_alloc) &&
+	if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+				&init_on_alloc) &&
 	    !page_poisoning_enabled())
 		return true;
 	return flags & __GFP_ZERO;
@@ -2674,7 +2675,8 @@ static inline bool want_init_on_alloc(gfp_t flags)
 DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
 static inline bool want_init_on_free(void)
 {
-	return static_branch_unlikely(&init_on_free) &&
+	return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
+				   &init_on_free) &&
 	       !page_poisoning_enabled();
 }
 
-- 
2.20.1

[PATCH v3 3/5] stack: Optionally randomize kernel stack offset each syscall

[Kees Cook]

This provides the ability for architectures to enable kernel stack base
address offset randomization. This feature is controlled by the boot
param "randomize_kstack_offset=on/off", with its default value set by
CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT.

This feature is based on the original idea from the last public release
of PaX's RANDKSTACK feature: https://pax.grsecurity.net/docs/randkstack.txt
All the credit for the original idea goes to the PaX team. Note that
the design and implementation of this upstream randomize_kstack_offset
feature differs greatly from the RANDKSTACK feature (see below).

Reasoning for the feature:

This feature aims to make harder the various stack-based attacks that
rely on deterministic stack structure. We have had many such attacks in
past (just to name few):

https://jon.oberheide.org/files/infiltrate12-thestackisback.pdf
https://jon.oberheide.org/files/stackjacking-infiltrate11.pdf
https://googleprojectzero.blogspot.com/2016/06/exploiting-recursion-in-linux-kernel_20.html

As Linux kernel stack protections have been constantly improving
(vmap-based stack allocation with guard pages, removal of thread_info,
STACKLEAK), attackers have had to find new ways for their exploits
to work. They have done so, continuing to rely on the kernel's stack
determinism, in situations where VMAP_STACK and THREAD_INFO_IN_TASK_STRUCT
were not relevant. For example, the following recent attacks would have
been hampered if the stack offset was non-deterministic between syscalls:

https://repositorio-aberto.up.pt/bitstream/10216/125357/2/374717.pdf
(page 70: targeting the pt_regs copy with linear stack overflow)

https://a13xp0p0v.github.io/2020/02/15/CVE-2019-18683.html
(leaked stack address from one syscall as a target during next syscall)

The main idea is that since the stack offset is randomized on each system
call, it is harder for an attack to reliably land in any particular place
on the thread stack, even with address exposures, as the stack base will
change on the next syscall. Also, since randomization is performed after
placing pt_regs, the ptrace-based approach[1] to discover the randomized
offset during a long-running syscall should not be possible.

Design description:

During most of the kernel's execution, it runs on the "thread stack",
which is pretty deterministic in its structure: it is fixed in size,
and on every entry from userspace to kernel on a syscall the thread
stack starts construction from an address fetched from the per-cpu
cpu_current_top_of_stack variable. The first element to be pushed to the
thread stack is the pt_regs struct that stores all required CPU registers
and syscall parameters. Finally the specific syscall function is called,
with the stack being used as the kernel executes the resulting request.

The goal of randomize_kstack_offset feature is to add a random offset
after the pt_regs has been pushed to the stack and before the rest of the
thread stack is used during the syscall processing, and to change it every
time a process issues a syscall. The source of randomness is currently
architecture-defined (but x86 is using the low byte of rdtsc()). Future
improvements for different entropy sources is possible, but out of scope
for this patch. As suggested by Andy Lutomirski, the offset is added
using alloca() and an empty asm() statement with an output constraint,
since it avoid changes to assembly syscall entry code, to the unwinder,
and provides correct stack alignment as defined by the compiler.

In order to make this available by default with zero performance impact
for those that don't want it, it is boot-time selectable with static
branches. This way, if the overhead is not wanted, it can just be
left turned off with no performance impact.

The generated assembly for x86_64 with GCC looks like this:

...
ffffffff81003977: 65 8b 05 02 ea 00 7f  mov %gs:0x7f00ea02(%rip),%eax
					    # 12380 <kstack_offset>
ffffffff8100397e: 25 ff 03 00 00        and $0x3ff,%eax
ffffffff81003983: 48 83 c0 0f           add $0xf,%rax
ffffffff81003987: 25 f8 07 00 00        and $0x7f8,%eax
ffffffff8100398c: 48 29 c4              sub %rax,%rsp
ffffffff8100398f: 48 8d 44 24 0f        lea 0xf(%rsp),%rax
ffffffff81003994: 48 83 e0 f0           and $0xfffffffffffffff0,%rax
...

As a result of the above stack alignment, this patch introduces about
5 bits of randomness after pt_regs is spilled to the thread stack on
x86_64, and 6 bits on x86_32 (since its has 1 fewer bit required for
stack alignment). The amount of entropy could be adjusted based on how
much of the stack space we wish to trade for security.

My measure of syscall performance overhead (on x86_64):

lmbench: /usr/lib/lmbench/bin/x86_64-linux-gnu/lat_syscall -N 10000 null
    randomize_kstack_offset=y	Simple syscall: 0.7082 microseconds
    randomize_kstack_offset=n	Simple syscall: 0.7016 microseconds

So, roughly 0.9% overhead growth for a no-op syscall, which is very
manageable. And for people that don't want this, it's off by default.

There are two gotchas with using the alloca() trick. First,
compilers that have Stack Clash protection (-fstack-clash-protection)
enabled by default (e.g. Ubuntu[3]) add pagesize stack probes to
any dynamic stack allocations. While the randomization offset is
always less than a page, the resulting assembly would still contain
(unreachable!) probing routines, bloating the resulting assembly. To
avoid this, -fno-stack-clash-protection is unconditionally added to
the kernel Makefile since this is the only dynamic stack allocation in
the kernel (now that VLAs have been removed) and it is provably safe
from Stack Clash style attacks.

The second gotcha with alloca() is a negative interaction with
-fstack-protector-strong, in that it see the alloca() as an array
allocation, which triggers the unconditional addition of the stack
canary function pre/post-amble which slows down syscalls regardless of
the static branch. In order to avoid adding this unneeded check and its
associated performance impact, architectures need to downgrade uses of
-fstack-protector-strong to -fstack-protector (which only triggers for
char arrays) in the compilation units that use the add_random_kstack()
macro and to audit the resulting stack mitigation coverage (to make sure
no desired coverage disappears). This is done in the next patches for
x86 and arm64. There is, unfortunately, no attribute that can be used
to disable stack protector for specific functions.

Comparison to PaX RANDKSTACK feature:

The RANDKSTACK feature randomizes the location of the stack start
(cpu_current_top_of_stack), i.e. including the location of pt_regs
structure itself on the stack. Initially this patch followed the same
approach, but during the recent discussions[2], it has been determined
to be of a little value since, if ptrace functionality is available for
an attacker, they can use PTRACE_PEEKUSR/PTRACE_POKEUSR to read/write
different offsets in the pt_regs struct, observe the cache behavior of
the pt_regs accesses, and figure out the random stack offset. Another
difference is that the random offset is stored in a per-cpu variable,
rather than having it be per-thread. As a result, these implementations
differ a fair bit in their implementation details and results, though
obviously the intent is similar.

[1] https://lore.kernel.org/kernel-hardening/2236FBA76BA1254E88B949DDB74E612BA4BC57C1@IRSMSX102.ger.corp.intel.com/
[2] https://lore.kernel.org/kernel-hardening/20190329081358.30497-1-elena.reshetova@intel.com/
[3] https://lists.ubuntu.com/archives/ubuntu-devel/2019-June/040741.html

Co-developed-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Link: https://lore.kernel.org/r/20190415060918.3766-1-elena.reshetova@intel.com
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 Makefile                         |  4 ++++
 arch/Kconfig                     | 23 ++++++++++++++++++
 include/linux/randomize_kstack.h | 40 ++++++++++++++++++++++++++++++++
 init/main.c                      | 23 ++++++++++++++++++
 4 files changed, 90 insertions(+)
 create mode 100644 include/linux/randomize_kstack.h

diff --git a/Makefile b/Makefile
index 4d0711f54047..1d4a8b9a6b02 100644
--- a/Makefile
+++ b/Makefile
@@ -779,6 +779,10 @@ ifdef CONFIG_INIT_STACK_ALL
 KBUILD_CFLAGS	+= -ftrivial-auto-var-init=pattern
 endif
 
+# While VLAs have been removed, GCC produces unreachable stack probes
+# for the randomize_kstack_offset feature. Disable it for all compilers.
+KBUILD_CFLAGS	+= $(call cc-option,-fno-stack-clash-protection,)
+
 DEBUG_CFLAGS	:= $(call cc-option, -fno-var-tracking-assignments)
 
 ifdef CONFIG_DEBUG_INFO
diff --git a/arch/Kconfig b/arch/Kconfig
index 17fe351cdde0..701c7d842714 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -854,6 +854,29 @@ config VMAP_STACK
 	  virtual mappings with real shadow memory, and KASAN_VMALLOC must
 	  be enabled.
 
+config HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+	def_bool n
+	help
+	  An arch should select this symbol if it can support kernel stack
+	  offset randomization with calls to add_random_kstack_offset()
+	  during syscall entry and choose_random_kstack_offset() during
+	  syscall exit. Downgrading of -fstack-protector-strong to
+	  -fstack-protector should also be applied to the entry code and
+	  closely examined, as the artificial stack bump looks like an array
+	  to the compiler, so it will attempt to add canary checks regardless
+	  of the static branch state.
+
+config RANDOMIZE_KSTACK_OFFSET_DEFAULT
+	bool "Randomize kernel stack offset on syscall entry"
+	depends on HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+	help
+	  The kernel stack offset can be randomized (after pt_regs) by
+	  roughly 5 bits of entropy, frustrating memory corruption
+	  attacks that depend on stack address determinism or
+	  cross-syscall address exposures. This feature is controlled
+	  by kernel boot param "randomize_kstack_offset=on/off", and this
+	  config chooses the default boot state.
+
 config ARCH_OPTIONAL_KERNEL_RWX
 	def_bool n
 
diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h
new file mode 100644
index 000000000000..1df0dc52cadc
--- /dev/null
+++ b/include/linux/randomize_kstack.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LINUX_RANDOMIZE_KSTACK_H
+#define _LINUX_RANDOMIZE_KSTACK_H
+
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+#include <linux/percpu-defs.h>
+
+DECLARE_STATIC_KEY_MAYBE(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
+			 randomize_kstack_offset);
+DECLARE_PER_CPU(u32, kstack_offset);
+
+/*
+ * Do not use this anywhere else in the kernel. This is used here because
+ * it provides an arch-agnostic way to grow the stack with correct
+ * alignment. Also, since this use is being explicitly masked to a max of
+ * 10 bits, stack-clash style attacks are unlikely. For more details see
+ * "VLAs" in Documentation/process/deprecated.rst
+ */
+void *__builtin_alloca(size_t size);
+
+#define add_random_kstack_offset() do {					\
+	if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,	\
+				&randomize_kstack_offset)) {		\
+		u32 offset = this_cpu_read(kstack_offset);		\
+		u8 *ptr = __builtin_alloca(offset & 0x3FF);		\
+		asm volatile("" : "=m"(*ptr));				\
+	}								\
+} while (0)
+
+#define choose_random_kstack_offset(rand) do {				\
+	if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,	\
+				&randomize_kstack_offset)) {		\
+		u32 offset = this_cpu_read(kstack_offset);		\
+		offset ^= (rand);					\
+		this_cpu_write(kstack_offset, offset);			\
+	}								\
+} while (0)
+
+#endif
diff --git a/init/main.c b/init/main.c
index ee4947af823f..78fe3aea00b0 100644
--- a/init/main.c
+++ b/init/main.c
@@ -777,6 +777,29 @@ static void __init mm_init(void)
 	pti_init();
 }
 
+#ifdef CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
+			   randomize_kstack_offset);
+DEFINE_PER_CPU(u32, kstack_offset);
+
+static int __init early_randomize_kstack_offset(char *buf)
+{
+	int ret;
+	bool bool_result;
+
+	ret = kstrtobool(buf, &bool_result);
+	if (ret)
+		return ret;
+
+	if (bool_result)
+		static_branch_enable(&randomize_kstack_offset);
+	else
+		static_branch_disable(&randomize_kstack_offset);
+	return 0;
+}
+early_param("randomize_kstack_offset", early_randomize_kstack_offset);
+#endif
+
 void __init __weak arch_call_rest_init(void)
 {
 	rest_init();
-- 
2.20.1

[PATCH v3 4/5] x86/entry: Enable random_kstack_offset support

[Kees Cook]

Allow for a randomized stack offset on a per-syscall basis, with roughly
5 bits of entropy.

In order to avoid unconditional stack canaries on syscall entry, also
downgrade from -fstack-protector-strong to -fstack-protector to avoid
triggering checks due to alloca(). Examining the resulting canary coverage
changes to common.o, this also removes canaries in other functions,
due to a handful of declarations of "__u64 args[6]" (from seccomp) and
"unsigned long args[6]" (from tracepoints), but their accesses are indexed
(instead of via dynamically sized linear reads/writes) so the risk of
removing useful mitigation coverage here is very low.

Signed-off-by: Kees Cook <keescook@chromium.org>
---
 arch/x86/Kconfig        |  1 +
 arch/x86/entry/Makefile |  9 +++++++++
 arch/x86/entry/common.c | 12 +++++++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index beea77046f9b..b9d449581eb6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -150,6 +150,7 @@ config X86
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
 	select HAVE_ARCH_VMAP_STACK		if X86_64
+	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_WITHIN_STACK_FRAMES
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 06fc70cf5433..7b40e6ae2618 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -7,6 +7,15 @@ OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
 
 CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
+
+# Downgrade to -fstack-protector to avoid triggering unneeded stack canary
+# checks due to randomize_kstack_offset. This also removes canaries in
+# other places as well, due to a handful of declarations of __u64 args[6]
+# (seccomp) and unsigned long args[6] (tracepoints), but their accesses
+# are indexed (instead of via dynamically sized linear reads/writes) so
+# the risk of removing useful mitigation coverage here is very low.
+CFLAGS_common.o			+= $(subst -fstack-protector-strong,-fstack-protector,$(filter -fstack-protector-strong,$(KBUILD_CFLAGS)))
+
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 9747876980b5..086d7af570af 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -26,6 +26,7 @@
 #include <linux/livepatch.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/randomize_kstack.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -189,6 +190,13 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	lockdep_assert_irqs_disabled();
 	lockdep_sys_exit();
 
+	/*
+	 * x86_64 stack alignment means 3 bits are ignored, so keep
+	 * the top 5 bits. x86_32 needs only 2 bits of alignment, so
+	 * the top 6 bits will be used.
+	 */
+	choose_random_kstack_offset(rdtsc() & 0xFF);
+
 	cached_flags = READ_ONCE(ti->flags);
 
 	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
@@ -283,6 +291,7 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 {
 	struct thread_info *ti;
 
+	add_random_kstack_offset();
 	enter_from_user_mode();
 	local_irq_enable();
 	ti = current_thread_info();
@@ -355,6 +364,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 /* Handles int $0x80 */
 __visible void do_int80_syscall_32(struct pt_regs *regs)
 {
+	add_random_kstack_offset();
 	enter_from_user_mode();
 	local_irq_enable();
 	do_syscall_32_irqs_on(regs);
@@ -378,8 +388,8 @@ __visible long do_fast_syscall_32(struct pt_regs *regs)
 	 */
 	regs->ip = landing_pad;
 
+	add_random_kstack_offset();
 	enter_from_user_mode();
-
 	local_irq_enable();
 
 	/* Fetch EBP from where the vDSO stashed it. */
-- 
2.20.1

[PATCH v3 5/5] arm64: entry: Enable random_kstack_offset support

[Kees Cook]

Allow for a randomized stack offset on a per-syscall basis, with roughly
5 bits of entropy.

In order to avoid unconditional stack canaries on syscall entry, also
downgrade from -fstack-protector-strong to -fstack-protector to avoid
triggering checks due to alloca(). Examining the resulting syscall.o,
sees no changes in canary coverage (none before, none now).

Signed-off-by: Kees Cook <keescook@chromium.org>
---
 arch/arm64/Kconfig          |  1 +
 arch/arm64/kernel/Makefile  |  4 ++++
 arch/arm64/kernel/syscall.c | 10 ++++++++++
 3 files changed, 15 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0b30e884e088..4d5aa4959f72 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -127,6 +127,7 @@ config ARM64
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_PREL32_RELOCATIONS
+	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index fc6488660f64..b89005f125d6 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -11,6 +11,10 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_insn.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
+# Downgrade to -fstack-protector to avoid triggering unneeded stack canary
+# checks due to randomize_kstack_offset.
+CFLAGS_syscall.o	+= $(subst -fstack-protector-strong,-fstack-protector,$(filter -fstack-protector-strong,$(KBUILD_CFLAGS)))
+
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-common.o entry-fpsimd.o process.o ptrace.o	\
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index a12c0c88d345..238dbd753b44 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -5,6 +5,7 @@
 #include <linux/errno.h>
 #include <linux/nospec.h>
 #include <linux/ptrace.h>
+#include <linux/randomize_kstack.h>
 #include <linux/syscalls.h>
 
 #include <asm/daifflags.h>
@@ -42,6 +43,8 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 {
 	long ret;
 
+	add_random_kstack_offset();
+
 	if (scno < sc_nr) {
 		syscall_fn_t syscall_fn;
 		syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];
@@ -51,6 +54,13 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 	}
 
 	regs->regs[0] = ret;
+
+	/*
+	 * Since the compiler chooses a 4 bit alignment for the stack,
+	 * let's save one additional bit (9 total), which gets us up
+	 * near 5 bits of entropy.
+	 */
+	choose_random_kstack_offset(get_random_int() & 0x1FF);
 }
 
 static inline bool has_syscall_work(unsigned long flags)
-- 
2.20.1