2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 06:34:11 +08:00
linux-next/arch/riscv/kernel/ptrace.c
Tycho Andersen af33d2433b
riscv: fix seccomp reject syscall code path
If secure_computing() rejected a system call, we were previously setting
the system call number to -1, to indicate to later code that the syscall
failed. However, if something (e.g. a user notification) was sleeping, and
received a signal, we may set a0 to -ERESTARTSYS and re-try the system call
again.

In this case, seccomp "denies" the syscall (because of the signal), and we
would set a7 to -1, thus losing the value of the system call we want to
restart.

Instead, let's return -1 from do_syscall_trace_enter() to indicate that the
syscall was rejected, so we don't clobber the value in case of -ERESTARTSYS
or whatever.

This commit fixes the user_notification_signal seccomp selftest on riscv to
no longer hang. That test expects the system call to be re-issued after the
signal, and it wasn't due to the above bug. Now that it is, everything
works normally.

Note that in the ptrace (tracer) case, the tracer can set the register
values to whatever they want, so we still need to keep the code that
handles out-of-bounds syscalls. However, we can drop the comment.

We can also drop syscall_set_nr(), since it is no longer used anywhere, and
the code that re-loads the value in a7 because of it.

Reported in: https://lore.kernel.org/bpf/CAEn-LTp=ss0Dfv6J00=rCAy+N78U2AmhqJNjfqjr2FDpPYjxEQ@mail.gmail.com/

Reported-by: David Abdurachmanov <david.abdurachmanov@gmail.com>
Signed-off-by: Tycho Andersen <tycho@tycho.ws>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
2020-03-05 13:58:15 -08:00

186 lines
4.4 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright 2010 Tilera Corporation. All Rights Reserved.
* Copyright 2015 Regents of the University of California
* Copyright 2017 SiFive
*
* Copied from arch/tile/kernel/ptrace.c
*/
#include <asm/ptrace.h>
#include <asm/syscall.h>
#include <asm/thread_info.h>
#include <linux/audit.h>
#include <linux/ptrace.h>
#include <linux/elf.h>
#include <linux/regset.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/tracehook.h>
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
enum riscv_regset {
REGSET_X,
#ifdef CONFIG_FPU
REGSET_F,
#endif
};
static int riscv_gpr_get(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
struct pt_regs *regs;
regs = task_pt_regs(target);
return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
}
static int riscv_gpr_set(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
int ret;
struct pt_regs *regs;
regs = task_pt_regs(target);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
return ret;
}
#ifdef CONFIG_FPU
static int riscv_fpr_get(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
int ret;
struct __riscv_d_ext_state *fstate = &target->thread.fstate;
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0,
offsetof(struct __riscv_d_ext_state, fcsr));
if (!ret) {
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0,
offsetof(struct __riscv_d_ext_state, fcsr) +
sizeof(fstate->fcsr));
}
return ret;
}
static int riscv_fpr_set(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
int ret;
struct __riscv_d_ext_state *fstate = &target->thread.fstate;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
offsetof(struct __riscv_d_ext_state, fcsr));
if (!ret) {
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0,
offsetof(struct __riscv_d_ext_state, fcsr) +
sizeof(fstate->fcsr));
}
return ret;
}
#endif
static const struct user_regset riscv_user_regset[] = {
[REGSET_X] = {
.core_note_type = NT_PRSTATUS,
.n = ELF_NGREG,
.size = sizeof(elf_greg_t),
.align = sizeof(elf_greg_t),
.get = &riscv_gpr_get,
.set = &riscv_gpr_set,
},
#ifdef CONFIG_FPU
[REGSET_F] = {
.core_note_type = NT_PRFPREG,
.n = ELF_NFPREG,
.size = sizeof(elf_fpreg_t),
.align = sizeof(elf_fpreg_t),
.get = &riscv_fpr_get,
.set = &riscv_fpr_set,
},
#endif
};
static const struct user_regset_view riscv_user_native_view = {
.name = "riscv",
.e_machine = EM_RISCV,
.regsets = riscv_user_regset,
.n = ARRAY_SIZE(riscv_user_regset),
};
const struct user_regset_view *task_user_regset_view(struct task_struct *task)
{
return &riscv_user_native_view;
}
void ptrace_disable(struct task_struct *child)
{
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
}
long arch_ptrace(struct task_struct *child, long request,
unsigned long addr, unsigned long data)
{
long ret = -EIO;
switch (request) {
default:
ret = ptrace_request(child, request, addr, data);
break;
}
return ret;
}
/*
* Allows PTRACE_SYSCALL to work. These are called from entry.S in
* {handle,ret_from}_syscall.
*/
__visible int do_syscall_trace_enter(struct pt_regs *regs)
{
if (test_thread_flag(TIF_SYSCALL_TRACE))
if (tracehook_report_syscall_entry(regs))
return -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() == -1)
return -1;
#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
trace_sys_enter(regs, syscall_get_nr(current, regs));
#endif
audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
return 0;
}
__visible void do_syscall_trace_exit(struct pt_regs *regs)
{
audit_syscall_exit(regs);
if (test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, 0);
#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
trace_sys_exit(regs, regs_return_value(regs));
#endif
}