1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
linux/arch/arm64/kernel/syscall.c
Kees Cook 6db1208bf9 randomize_kstack: Remove non-functional per-arch entropy filtering
An unintended consequence of commit 9c573cd313 ("randomize_kstack:
Improve entropy diffusion") was that the per-architecture entropy size
filtering reduced how many bits were being added to the mix, rather than
how many bits were being used during the offsetting. All architectures
fell back to the existing default of 0x3FF (10 bits), which will consume
at most 1KiB of stack space. It seems that this is working just fine,
so let's avoid the confusion and update everything to use the default.

The prior intent of the per-architecture limits were:

  arm64: capped at 0x1FF (9 bits), 5 bits effective
  powerpc: uncapped (10 bits), 6 or 7 bits effective
  riscv: uncapped (10 bits), 6 bits effective
  x86: capped at 0xFF (8 bits), 5 (x86_64) or 6 (ia32) bits effective
  s390: capped at 0xFF (8 bits), undocumented effective entropy

Current discussion has led to just dropping the original per-architecture
filters. The additional entropy appears to be safe for arm64, x86,
and s390. Quoting Arnd, "There is no point pretending that 15.75KB is
somehow safe to use while 15.00KB is not."

Co-developed-by: Yuntao Liu <liuyuntao12@huawei.com>
Signed-off-by: Yuntao Liu <liuyuntao12@huawei.com>
Fixes: 9c573cd313 ("randomize_kstack: Improve entropy diffusion")
Link: https://lore.kernel.org/r/20240617133721.377540-1-liuyuntao12@huawei.com
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com> # s390
Link: https://lore.kernel.org/r/20240619214711.work.953-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
2024-06-28 08:54:56 -07:00

159 lines
4.6 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
#include <linux/context_tracking.h>
#include <linux/errno.h>
#include <linux/nospec.h>
#include <linux/ptrace.h>
#include <linux/randomize_kstack.h>
#include <linux/syscalls.h>
#include <asm/debug-monitors.h>
#include <asm/exception.h>
#include <asm/fpsimd.h>
#include <asm/syscall.h>
#include <asm/thread_info.h>
#include <asm/unistd.h>
long compat_arm_syscall(struct pt_regs *regs, int scno);
long sys_ni_syscall(void);
static long do_ni_syscall(struct pt_regs *regs, int scno)
{
if (is_compat_task()) {
long ret = compat_arm_syscall(regs, scno);
if (ret != -ENOSYS)
return ret;
}
return sys_ni_syscall();
}
static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn)
{
return syscall_fn(regs);
}
static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
unsigned int sc_nr,
const syscall_fn_t syscall_table[])
{
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)];
ret = __invoke_syscall(regs, syscall_fn);
} else {
ret = do_ni_syscall(regs, scno);
}
syscall_set_return_value(current, regs, 0, ret);
/*
* This value will get limited by KSTACK_OFFSET_MAX(), which is 10
* bits. The actual entropy will be further reduced by the compiler
* when applying stack alignment constraints: the AAPCS mandates a
* 16-byte aligned SP at function boundaries, which will remove the
* 4 low bits from any entropy chosen here.
*
* The resulting 6 bits of entropy is seen in SP[9:4].
*/
choose_random_kstack_offset(get_random_u16());
}
static inline bool has_syscall_work(unsigned long flags)
{
return unlikely(flags & _TIF_SYSCALL_WORK);
}
static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
const syscall_fn_t syscall_table[])
{
unsigned long flags = read_thread_flags();
regs->orig_x0 = regs->regs[0];
regs->syscallno = scno;
/*
* BTI note:
* The architecture does not guarantee that SPSR.BTYPE is zero
* on taking an SVC, so we could return to userspace with a
* non-zero BTYPE after the syscall.
*
* This shouldn't matter except when userspace is explicitly
* doing something stupid, such as setting PROT_BTI on a page
* that lacks conforming BTI/PACIxSP instructions, falling
* through from one executable page to another with differing
* PROT_BTI, or messing with BTYPE via ptrace: in such cases,
* userspace should not be surprised if a SIGILL occurs on
* syscall return.
*
* So, don't touch regs->pstate & PSR_BTYPE_MASK here.
* (Similarly for HVC and SMC elsewhere.)
*/
if (flags & _TIF_MTE_ASYNC_FAULT) {
/*
* Process the asynchronous tag check fault before the actual
* syscall. do_notify_resume() will send a signal to userspace
* before the syscall is restarted.
*/
syscall_set_return_value(current, regs, -ERESTARTNOINTR, 0);
return;
}
if (has_syscall_work(flags)) {
/*
* The de-facto standard way to skip a system call using ptrace
* is to set the system call to -1 (NO_SYSCALL) and set x0 to a
* suitable error code for consumption by userspace. However,
* this cannot be distinguished from a user-issued syscall(-1)
* and so we must set x0 to -ENOSYS here in case the tracer doesn't
* issue the skip and we fall into trace_exit with x0 preserved.
*
* This is slightly odd because it also means that if a tracer
* sets the system call number to -1 but does not initialise x0,
* then x0 will be preserved for all system calls apart from a
* user-issued syscall(-1). However, requesting a skip and not
* setting the return value is unlikely to do anything sensible
* anyway.
*/
if (scno == NO_SYSCALL)
syscall_set_return_value(current, regs, -ENOSYS, 0);
scno = syscall_trace_enter(regs);
if (scno == NO_SYSCALL)
goto trace_exit;
}
invoke_syscall(regs, scno, sc_nr, syscall_table);
/*
* The tracing status may have changed under our feet, so we have to
* check again. However, if we were tracing entry, then we always trace
* exit regardless, as the old entry assembly did.
*/
if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
flags = read_thread_flags();
if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
return;
}
trace_exit:
syscall_trace_exit(regs);
}
void do_el0_svc(struct pt_regs *regs)
{
el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
}
#ifdef CONFIG_COMPAT
void do_el0_svc_compat(struct pt_regs *regs)
{
el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
compat_sys_call_table);
}
#endif