/* Returns the syscall nr to run (which should match regs->orig_ax). */ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, unsigned long phase1_result) { struct thread_info *ti = pt_regs_to_thread_info(regs); long ret = 0; u32 work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); /* * If we stepped into a sysenter/syscall insn, it trapped in * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. * If user-mode had set TF itself, then it's still clear from * do_debug() and we need to set it again to restore the user * state. If we entered on the slow path, TF was already set. */ if (work & _TIF_SINGLESTEP) regs->flags |= X86_EFLAGS_TF; #ifdef CONFIG_SECCOMP /* * Call seccomp_phase2 before running the other hooks so that * they can see any changes made by a seccomp tracer. */ if (phase1_result > 1 && seccomp_phase2(phase1_result)) { /* seccomp failures shouldn't expose any additional code. */ return -1; } #endif if (unlikely(work & _TIF_SYSCALL_EMU)) ret = -1L; if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && tracehook_report_syscall_entry(regs)) ret = -1L; if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); do_audit_syscall_entry(regs, arch); return ret ?: regs->orig_ax; }
/* * Returns the syscall nr to run (which should match regs->orig_ax) or -1 * to skip the syscall. */ static long syscall_trace_enter(struct pt_regs *regs) { u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; struct thread_info *ti = current_thread_info(); unsigned long ret = 0; bool emulated = false; u32 work; if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; if (unlikely(work & _TIF_SYSCALL_EMU)) emulated = true; if ((emulated || (work & _TIF_SYSCALL_TRACE)) && tracehook_report_syscall_entry(regs)) return -1L; if (emulated) return -1L; #ifdef CONFIG_SECCOMP /* * Do seccomp after ptrace, to catch any tracer changes. */ 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; } ret = __secure_computing(&sd); if (ret == -1) return ret; } #endif if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); do_audit_syscall_entry(regs, arch); return ret ?: regs->orig_ax; }
/* * 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 */ }