linux/kernel/entry/syscall_user_dispatch.c
Eric W. Biederman 941edc5bf1 exit/syscall_user_dispatch: Send ordinary signals on failure
Use force_fatal_sig instead of calling do_exit directly.  This ensures
the ordinary signal handling path gets invoked, core dumps as
appropriate get created, and for multi-threaded processes all of the
threads are terminated not just a single thread.

When asked Gabriel Krisman Bertazi <krisman@collabora.com> said [1]:
> ebiederm@xmission.com (Eric W. Biederman) asked:
>
> > Why does do_syscal_user_dispatch call do_exit(SIGSEGV) and
> > do_exit(SIGSYS) instead of force_sig(SIGSEGV) and force_sig(SIGSYS)?
> >
> > Looking at the code these cases are not expected to happen, so I would
> > be surprised if userspace depends on any particular behaviour on the
> > failure path so I think we can change this.
>
> Hi Eric,
>
> There is not really a good reason, and the use case that originated the
> feature doesn't rely on it.
>
> Unless I'm missing yet another problem and others correct me, I think
> it makes sense to change it as you described.
>
> > Is using do_exit in this way something you copied from seccomp?
>
> I'm not sure, its been a while, but I think it might be just that.  The
> first prototype of SUD was implemented as a seccomp mode.

If at some point it becomes interesting we could relax
"force_fatal_sig(SIGSEGV)" to instead say
"force_sig_fault(SIGSEGV, SEGV_MAPERR, sd->selector)".

I avoid doing that in this patch to avoid making it possible
to catch currently uncatchable signals.

Cc: Gabriel Krisman Bertazi <krisman@collabora.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
[1] https://lkml.kernel.org/r/87mtr6gdvi.fsf@collabora.com
Link: https://lkml.kernel.org/r/20211020174406.17889-14-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2021-10-29 14:31:33 -05:00

109 lines
2.4 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2020 Collabora Ltd.
*/
#include <linux/sched.h>
#include <linux/prctl.h>
#include <linux/syscall_user_dispatch.h>
#include <linux/uaccess.h>
#include <linux/signal.h>
#include <linux/elf.h>
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <asm/syscall.h>
#include "common.h"
static void trigger_sigsys(struct pt_regs *regs)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = SIGSYS;
info.si_code = SYS_USER_DISPATCH;
info.si_call_addr = (void __user *)KSTK_EIP(current);
info.si_errno = 0;
info.si_arch = syscall_get_arch(current);
info.si_syscall = syscall_get_nr(current, regs);
force_sig_info(&info);
}
bool syscall_user_dispatch(struct pt_regs *regs)
{
struct syscall_user_dispatch *sd = &current->syscall_dispatch;
char state;
if (likely(instruction_pointer(regs) - sd->offset < sd->len))
return false;
if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
return false;
if (likely(sd->selector)) {
/*
* access_ok() is performed once, at prctl time, when
* the selector is loaded by userspace.
*/
if (unlikely(__get_user(state, sd->selector))) {
force_fatal_sig(SIGSEGV);
return true;
}
if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW))
return false;
if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
force_fatal_sig(SIGSYS);
return true;
}
}
sd->on_dispatch = true;
syscall_rollback(current, regs);
trigger_sigsys(regs);
return true;
}
int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
unsigned long len, char __user *selector)
{
switch (mode) {
case PR_SYS_DISPATCH_OFF:
if (offset || len || selector)
return -EINVAL;
break;
case PR_SYS_DISPATCH_ON:
/*
* Validate the direct dispatcher region just for basic
* sanity against overflow and a 0-sized dispatcher
* region. If the user is able to submit a syscall from
* an address, that address is obviously valid.
*/
if (offset && offset + len <= offset)
return -EINVAL;
if (selector && !access_ok(selector, sizeof(*selector)))
return -EFAULT;
break;
default:
return -EINVAL;
}
current->syscall_dispatch.selector = selector;
current->syscall_dispatch.offset = offset;
current->syscall_dispatch.len = len;
current->syscall_dispatch.on_dispatch = false;
if (mode == PR_SYS_DISPATCH_ON)
set_syscall_work(SYSCALL_USER_DISPATCH);
else
clear_syscall_work(SYSCALL_USER_DISPATCH);
return 0;
}