__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
{
struct thread_info *ti;
enter_from_user_mode();
local_irq_enable();
ti = current_thread_info();
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
nr = syscall_trace_enter(regs);
/*
* NB: Native and x32 syscalls are dispatched from the same
* table. The only functional difference is the x32 bit in
* regs->orig_ax, which changes the behavior of some syscalls.
*/
nr &= __SYSCALL_MASK;
if (likely(nr < NR_syscalls)) {
nr = array_index_nospec(nr, NR_syscalls);
regs->ax = sys_call_table[nr](regs);
}
syscall_return_slowpath(regs);
}
/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
__visible long do_fast_syscall_32(struct pt_regs *regs)
{
/*
* Called using the internal vDSO SYSENTER/SYSCALL32 calling
* convention. Adjust regs so it looks like we entered using int80.
*/
unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
vdso_image_32.sym_int80_landing_pad;
/*
* SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
* so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
* Fix it up.
*/
regs->ip = landing_pad;
enter_from_user_mode();
local_irq_enable();
/* Fetch EBP from where the vDSO stashed it. */
if (
#ifdef CONFIG_X86_64
/*
* Micro-optimization: the pointer we're following is explicitly
* 32 bits, so it can't be out of range.
*/
__get_user(*(u32 *)®s->bp,
(u32 __user __force *)(unsigned long)(u32)regs->sp)
#else
get_user(*(u32 *)®s->bp,
(u32 __user __force *)(unsigned long)(u32)regs->sp)
#endif
) {
/* User code screwed up. */
local_irq_disable();
regs->ax = -EFAULT;
prepare_exit_to_usermode(regs);
return 0; /* Keep it simple: use IRET. */
}
/* Now this is just like a normal syscall. */
do_syscall_32_irqs_on(regs);
#ifdef CONFIG_X86_64
/*
* Opportunistic SYSRETL: if possible, try to return using SYSRETL.
* SYSRETL is available on all 64-bit CPUs, so we don't need to
* bother with SYSEXIT.
*
* Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
* because the ECX fixup above will ensure that this is essentially
* never the case.
*/
return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
regs->ip == landing_pad &&
(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
#else
/*
* Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
*
* Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
* because the ECX fixup above will ensure that this is essentially
* never the case.
*
* We don't allow syscalls at all from VM86 mode, but we still
* need to check VM, because we might be returning from sys_vm86.
*/
return static_cpu_has(X86_FEATURE_SEP) &&
regs->cs == __USER_CS && regs->ss == __USER_DS &&
regs->ip == landing_pad &&
(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
#endif
}
/* Handles int $0x80 */
__visible void do_int80_syscall_32(struct pt_regs *regs)
{
enter_from_user_mode();
local_irq_enable();
do_syscall_32_irqs_on(regs);
}
/*
* We can return 0 to resume the syscall or anything else to go to phase
* 2. If we resume the syscall, we need to put something appropriate in
* regs->orig_ax.
*
* NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax
* are fully functional.
*
* For phase 2's benefit, our return value is:
* 0: resume the syscall
* 1: go to phase 2; no seccomp phase 2 needed
* anything else: go to phase 2; pass return value to seccomp
*/
unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
{
struct thread_info *ti = pt_regs_to_thread_info(regs);
unsigned long ret = 0;
u32 work;
if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
BUG_ON(regs != task_pt_regs(current));
work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
#ifdef CONFIG_CONTEXT_TRACKING
/*
* If TIF_NOHZ is set, we are required to call user_exit() before
* doing anything that could touch RCU.
*/
if (work & _TIF_NOHZ) {
enter_from_user_mode();
work &= ~_TIF_NOHZ;
}
#endif
#ifdef CONFIG_SECCOMP
/*
* Do seccomp first -- it should minimize exposure of other
* code, and keeping seccomp fast is probably more valuable
* than the rest of this.
*/
if (work & _TIF_SECCOMP) {
struct seccomp_data sd;
sd.arch = arch;
sd.nr = regs->orig_ax;
sd.instruction_pointer = regs->ip;
#ifdef CONFIG_X86_64
if (arch == AUDIT_ARCH_X86_64) {
sd.args[0] = regs->di;
sd.args[1] = regs->si;
sd.args[2] = regs->dx;
sd.args[3] = regs->r10;
sd.args[4] = regs->r8;
sd.args[5] = regs->r9;
} else
#endif
{
sd.args[0] = regs->bx;
sd.args[1] = regs->cx;
sd.args[2] = regs->dx;
sd.args[3] = regs->si;
sd.args[4] = regs->di;
sd.args[5] = regs->bp;
}
BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0);
BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1);
ret = seccomp_phase1(&sd);
if (ret == SECCOMP_PHASE1_SKIP) {
regs->orig_ax = -1;
ret = 0;
} else if (ret != SECCOMP_PHASE1_OK) {
return ret; /* Go directly to phase 2 */
}
work &= ~_TIF_SECCOMP;
}
#endif
/* Do our best to finish without phase 2. */
if (work == 0)
return ret; /* seccomp and/or nohz only (ret == 0 here) */
#ifdef CONFIG_AUDITSYSCALL
if (work == _TIF_SYSCALL_AUDIT) {
/*
* If there is no more work to be done except auditing,
* then audit in phase 1. Phase 2 always audits, so, if
* we audit here, then we can't go on to phase 2.
*/
do_audit_syscall_entry(regs, arch);
return 0;
}
#endif
return 1; /* Something is enabled that we can't handle in phase 1 */
}