From 0cb0b507d7eaff090b2607799de3acad464fa446 Mon Sep 17 00:00:00 2001 From: David Abdurachmanov Date: Mon, 24 Jun 2019 18:58:45 +0300 Subject: [PATCH] riscv: add SECCOMP support Signed-off-by: David Abdurachmanov diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 0c4b12205632..6f89a83c1e9c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -30,6 +30,7 @@ config RISCV select GENERIC_SMP_IDLE_THREAD select GENERIC_ATOMIC64 if !64BIT select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_SECCOMP_FILTER select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_CONTIGUOUS select HAVE_FUTEX_CMPXCHG if FUTEX @@ -223,6 +224,19 @@ menu "Kernel features" source "kernel/Kconfig.hz" +config SECCOMP + bool "Enable seccomp to safely compute untrusted bytecode" + help + This kernel feature is useful for number crunching applications + that may need to compute untrusted bytecode during their + execution. By using pipes or other transports made available to + the process as file descriptors supporting the read/write + syscalls, it's possible to isolate those applications in + their own address space using seccomp. Once seccomp is + enabled via prctl(PR_SET_SECCOMP), it cannot be disabled + and the task is only allowed to execute a few safe syscalls + defined by each seccomp mode. + endmenu menu "Boot options" diff --git a/arch/riscv/include/asm/seccomp.h b/arch/riscv/include/asm/seccomp.h new file mode 100644 index 000000000000..bf7744ee3b3d --- /dev/null +++ b/arch/riscv/include/asm/seccomp.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_SECCOMP_H +#define _ASM_SECCOMP_H + +#include + +#include + +#endif /* _ASM_SECCOMP_H */ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 905372d7eeb8..a0b2a29a0da1 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -75,6 +75,7 @@ struct thread_info { #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing */ +#define TIF_SECCOMP 8 /* syscall secure computing */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -82,11 +83,13 @@ struct thread_info { #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_WORK_MASK \ (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED) #define _TIF_SYSCALL_WORK \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT) + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \ + _TIF_SECCOMP ) #endif /* _ASM_RISCV_THREAD_INFO_H */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index bc7a56e1ca6f..0bbedfa3e47d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -203,8 +203,25 @@ check_syscall_nr: /* Check to make sure we don't jump to a bogus syscall number. */ li t0, __NR_syscalls la s0, sys_ni_syscall - /* Syscall number held in a7 */ - bgeu a7, t0, 1f + /* + * The tracer can change syscall number to valid/invalid value. + * We use syscall_set_nr helper in syscall_trace_enter thus we + * cannot trust the current value in a7 and have to reload from + * the current task pt_regs. + */ + REG_L a7, PT_A7(sp) + /* + * Syscall number held in a7. + * If syscall number is above allowed value, redirect to ni_syscall. + */ + bge a7, t0, 1f + /* + * Check if syscall is rejected by tracer or seccomp, i.e., a7 == -1. + * If yes, we pretend it was executed. + */ + li t1, -1 + beq a7, t1, ret_from_syscall_rejected + /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR add s0, s0, t0 @@ -215,6 +232,12 @@ check_syscall_nr: ret_from_syscall: /* Set user a0 to kernel a0 */ REG_S a0, PT_A0(sp) + /* + * We didn't execute the actual syscall. + * Seccomp already set return value for the current task pt_regs. + * (If it was configured with SECCOMP_RET_ERRNO/TRACE) + */ +ret_from_syscall_rejected: /* Trace syscalls, but only if requested by the user. */ REG_L t0, TASK_TI_FLAGS(tp) andi t0, t0, _TIF_SYSCALL_WORK diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 368751438366..63e47c9f85f0 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -154,6 +154,16 @@ void do_syscall_trace_enter(struct pt_regs *regs) if (tracehook_report_syscall_entry(regs)) syscall_set_nr(current, regs, -1); + /* + * Do the secure computing after ptrace; failures should be fast. + * If this fails we might have return value in a0 from seccomp + * (via SECCOMP_RET_ERRNO/TRACE). + */ + if (secure_computing(NULL) == -1) { + syscall_set_nr(current, regs, -1); + return; + } + #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, syscall_get_nr(current, regs)); diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index dc66fe852768..e30864b25fb5 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -112,6 +112,8 @@ struct seccomp_data { # define __NR_seccomp 383 # elif defined(__aarch64__) # define __NR_seccomp 277 +# elif defined(__riscv) +# define __NR_seccomp 277 # elif defined(__hppa__) # define __NR_seccomp 338 # elif defined(__powerpc__) @@ -1582,6 +1584,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) # define ARCH_REGS struct user_pt_regs # define SYSCALL_NUM regs[8] # define SYSCALL_RET regs[0] +#elif defined(__riscv) && __riscv_xlen == 64 +# define ARCH_REGS struct user_regs_struct +# define SYSCALL_NUM a7 +# define SYSCALL_RET a0 #elif defined(__hppa__) # define ARCH_REGS struct user_regs_struct # define SYSCALL_NUM gr[20] @@ -1671,7 +1677,7 @@ void change_syscall(struct __test_metadata *_metadata, EXPECT_EQ(0, ret) {} #if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \ - defined(__s390__) || defined(__hppa__) + defined(__s390__) || defined(__hppa__) || defined(__riscv) { regs.SYSCALL_NUM = syscall; } -- 2.21.0