WSL2-Linux-Kernel/arch/arm64/kernel/syscall.c

170 строки
4.1 KiB
C
Исходник Обычный вид История

// 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);
arm64: implement syscall wrappers To minimize the risk of userspace-controlled values being used under speculation, this patch adds pt_regs based syscall wrappers for arm64, which pass the minimum set of required userspace values to syscall implementations. For each syscall, a wrapper which takes a pt_regs argument is automatically generated, and this extracts the arguments before calling the "real" syscall implementation. Each syscall has three functions generated: * __do_<compat_>sys_<name> is the "real" syscall implementation, with the expected prototype. * __se_<compat_>sys_<name> is the sign-extension/narrowing wrapper, inherited from common code. This takes a series of long parameters, casting each to the requisite types required by the "real" syscall implementation in __do_<compat_>sys_<name>. This wrapper *may* not be necessary on arm64 given the AAPCS rules on unused register bits, but it seemed safer to keep the wrapper for now. * __arm64_<compat_>_sys_<name> takes a struct pt_regs pointer, and extracts *only* the relevant register values, passing these on to the __se_<compat_>sys_<name> wrapper. The syscall invocation code is updated to handle the calling convention required by __arm64_<compat_>_sys_<name>, and passes a single struct pt_regs pointer. The compiler can fold the syscall implementation and its wrappers, such that the overhead of this approach is minimized. Note that we play games with sys_ni_syscall(). It can't be defined with SYSCALL_DEFINE0() because we must avoid the possibility of error injection. Additionally, there are a couple of locations where we need to call it from C code, and we don't (currently) have a ksys_ni_syscall(). While it has no wrapper, passing in a redundant pt_regs pointer is benign per the AAPCS. When ARCH_HAS_SYSCALL_WRAPPER is selected, no prototype is defines for sys_ni_syscall(). Since we need to treat it differently for in-kernel calls and the syscall tables, the prototype is defined as-required. The wrappers are largely the same as their x86 counterparts, but simplified as we don't have a variety of compat calling conventions that require separate stubs. Unlike x86, we have some zero-argument compat syscalls, and must define COMPAT_SYSCALL_DEFINE0() to ensure that these are also given an __arm64_compat_sys_ prefix. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-07-11 16:56:56 +03:00
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)
{
arm64: implement syscall wrappers To minimize the risk of userspace-controlled values being used under speculation, this patch adds pt_regs based syscall wrappers for arm64, which pass the minimum set of required userspace values to syscall implementations. For each syscall, a wrapper which takes a pt_regs argument is automatically generated, and this extracts the arguments before calling the "real" syscall implementation. Each syscall has three functions generated: * __do_<compat_>sys_<name> is the "real" syscall implementation, with the expected prototype. * __se_<compat_>sys_<name> is the sign-extension/narrowing wrapper, inherited from common code. This takes a series of long parameters, casting each to the requisite types required by the "real" syscall implementation in __do_<compat_>sys_<name>. This wrapper *may* not be necessary on arm64 given the AAPCS rules on unused register bits, but it seemed safer to keep the wrapper for now. * __arm64_<compat_>_sys_<name> takes a struct pt_regs pointer, and extracts *only* the relevant register values, passing these on to the __se_<compat_>sys_<name> wrapper. The syscall invocation code is updated to handle the calling convention required by __arm64_<compat_>_sys_<name>, and passes a single struct pt_regs pointer. The compiler can fold the syscall implementation and its wrappers, such that the overhead of this approach is minimized. Note that we play games with sys_ni_syscall(). It can't be defined with SYSCALL_DEFINE0() because we must avoid the possibility of error injection. Additionally, there are a couple of locations where we need to call it from C code, and we don't (currently) have a ksys_ni_syscall(). While it has no wrapper, passing in a redundant pt_regs pointer is benign per the AAPCS. When ARCH_HAS_SYSCALL_WRAPPER is selected, no prototype is defines for sys_ni_syscall(). Since we need to treat it differently for in-kernel calls and the syscall tables, the prototype is defined as-required. The wrappers are largely the same as their x86 counterparts, but simplified as we don't have a variety of compat calling conventions that require separate stubs. Unlike x86, we have some zero-argument compat syscalls, and must define COMPAT_SYSCALL_DEFINE0() to ensure that these are also given an __arm64_compat_sys_ prefix. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-07-11 16:56:56 +03:00
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);
}
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;
cortex_a76_erratum_1463225_svc_handler();
local_daif_restore(DAIF_PROCCTX);
user_exit();
if (has_syscall_work(flags)) {
/* set default errno for user-issued syscall(-1) */
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)) {
/*
* 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();
}
asmlinkage void el0_svc_handler(struct pt_regs *regs)
{
sve_user_discard();
el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
}
#ifdef CONFIG_COMPAT
asmlinkage void el0_svc_compat_handler(struct pt_regs *regs)
{
el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
compat_sys_call_table);
}
#endif