linux/arch/arm64/kernel/syscall.c
Will Deacon 139dbe5d8e arm64: syscall: Expand the comment about ptrace and syscall(-1)
If a task executes syscall(-1), we intercept this early and force x0 to
be -ENOSYS so that we don't need to distinguish this scenario from one
where the scno is -1 because a tracer wants to skip the system call
using ptrace. With the return value set, the return path is the same as
the skip case.

Although there is a one-line comment noting this in el0_svc_common(), it
misses out most of the detail. Expand the comment to describe a bit more
about what is going on.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Keno Fischer <keno@juliacomputing.com>
Cc: Luis Machado <luis.machado@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
2020-07-16 11:41:58 +01:00

205 lines
5.5 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/syscalls.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.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)
{
#ifdef CONFIG_COMPAT
long ret;
if (is_compat_task()) {
ret = compat_arm_syscall(regs, scno);
if (ret != -ENOSYS)
return ret;
}
#endif
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;
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);
}
if (is_compat_task())
ret = lower_32_bits(ret);
regs->regs[0] = ret;
}
static inline bool has_syscall_work(unsigned long flags)
{
return unlikely(flags & _TIF_SYSCALL_WORK);
}
int syscall_trace_enter(struct pt_regs *regs);
void syscall_trace_exit(struct pt_regs *regs);
#ifdef CONFIG_ARM64_ERRATUM_1463225
DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
static void cortex_a76_erratum_1463225_svc_handler(void)
{
u32 reg, val;
if (!unlikely(test_thread_flag(TIF_SINGLESTEP)))
return;
if (!unlikely(this_cpu_has_cap(ARM64_WORKAROUND_1463225)))
return;
__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 1);
reg = read_sysreg(mdscr_el1);
val = reg | DBG_MDSCR_SS | DBG_MDSCR_KDE;
write_sysreg(val, mdscr_el1);
asm volatile("msr daifclr, #8");
isb();
/* We will have taken a single-step exception by this point */
write_sysreg(reg, mdscr_el1);
__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0);
}
#else
static void cortex_a76_erratum_1463225_svc_handler(void) { }
#endif /* CONFIG_ARM64_ERRATUM_1463225 */
static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
const syscall_fn_t syscall_table[])
{
unsigned long flags = current_thread_info()->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.)
*/
cortex_a76_erratum_1463225_svc_handler();
local_daif_restore(DAIF_PROCCTX);
user_exit();
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)
regs->regs[0] = -ENOSYS;
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)) {
local_daif_mask();
flags = current_thread_info()->flags;
if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
/*
* We're off to userspace, where interrupts are
* always enabled after we restore the flags from
* the SPSR.
*/
trace_hardirqs_on();
return;
}
local_daif_restore(DAIF_PROCCTX);
}
trace_exit:
syscall_trace_exit(regs);
}
static inline void sve_user_discard(void)
{
if (!system_supports_sve())
return;
clear_thread_flag(TIF_SVE);
/*
* task_fpsimd_load() won't be called to update CPACR_EL1 in
* ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
* happens if a context switch or kernel_neon_begin() or context
* modification (sigreturn, ptrace) intervenes.
* So, ensure that CPACR_EL1 is already correct for the fast-path case.
*/
sve_user_disable();
}
void do_el0_svc(struct pt_regs *regs)
{
sve_user_discard();
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