SECCOMP_RET_TRAP:
Results in the kernel sending a SIGSYS signal to the triggering
- task without executing the system call. The kernel will
- rollback the register state to just before the system call
- entry such that a signal handler in the task will be able to
- inspect the ucontext_t->uc_mcontext registers and emulate
- system call success or failure upon return from the signal
- handler.
+ task without executing the system call. siginfo->si_call_addr
+ will show the address of the system call instruction, and
+ siginfo->si_syscall and siginfo->si_arch will indicate which
+ syscall was attempted. The program counter will be as though
+ the syscall happened (i.e. it will not point to the syscall
+ instruction). The return value register will contain an arch-
+ dependent value -- if resuming execution, set it to something
+ sensible. (The architecture dependency is because replacing
+ it with -ENOSYS could overwrite some useful information.)
The SECCOMP_RET_DATA portion of the return value will be passed
as si_errno.
the BPF program return value will be available to the tracer
via PTRACE_GETEVENTMSG.
+ The tracer can skip the system call by changing the syscall number
+ to -1. Alternatively, the tracer can change the system call
+ requested by changing the system call to a valid syscall number. If
+ the tracer asks to skip the system call, then the system call will
+ appear to return the value that the tracer puts in the return value
+ register.
+
+ The seccomp check will not be run again after the tracer is
+ notified. (This means that seccomp-based sandboxes MUST NOT
+ allow use of ptrace, even of other sandboxed processes, without
+ extreme care; ptracers can use this mechanism to escape.)
+
SECCOMP_RET_ALLOW:
Results in the system call being executed.
support seccomp filter with minor fixup: SIGSYS support and seccomp return
value checking. Then it must just add CONFIG_HAVE_ARCH_SECCOMP_FILTER
to its arch-specific Kconfig.
+
+
+
+Caveats
+-------
+
+The vDSO can cause some system calls to run entirely in userspace,
+leading to surprises when you run programs on different machines that
+fall back to real syscalls. To minimize these surprises on x86, make
+sure you test with
+/sys/devices/system/clocksource/clocksource0/current_clocksource set to
+something like acpi_pm.
+
+On x86-64, vsyscall emulation is enabled by default. (vsyscalls are
+legacy variants on vDSO calls.) Currently, emulated vsyscalls will honor seccomp, with a few oddities:
+
+- A return value of SECCOMP_RET_TRAP will set a si_call_addr pointing to
+ the vsyscall entry for the given call and not the address after the
+ 'syscall' instruction. Any code which wants to restart the call
+ should be aware that (a) a ret instruction has been emulated and (b)
+ trying to resume the syscall will again trigger the standard vsyscall
+ emulation security checks, making resuming the syscall mostly
+ pointless.
+
+- A return value of SECCOMP_RET_TRACE will signal the tracer as usual,
+ but the syscall may not be changed to another system call using the
+ orig_rax register. It may only be changed to -1 order to skip the
+ currently emulated call. Any other change MAY terminate the process.
+ The rip value seen by the tracer will be the syscall entry address;
+ this is different from normal behavior. The tracer MUST NOT modify
+ rip or rsp. (Do not rely on other changes terminating the process.
+ They might work. For example, on some kernels, choosing a syscall
+ that only exists in future kernels will be correctly emulated (by
+ returning -ENOSYS).
+
+To detect this quirky behavior, check for addr & ~0x0C00 ==
+0xFFFFFFFFFF600000. (For SECCOMP_RET_TRACE, use rip. For
+SECCOMP_RET_TRAP, use siginfo->si_call_addr.) Do not check any other
+condition: future kernels may improve vsyscall emulation and current
+kernels in vsyscall=native mode will behave differently, but the
+instructions at 0xF...F600{0,4,8,C}00 will not be system calls in these
+cases.
+
+Note that modern systems are unlikely to use vsyscalls at all -- they
+are a legacy feature and they are considerably slower than standard
+syscalls. New code will use the vDSO, and vDSO-issued system calls
+are indistinguishable from normal system calls.
return nr;
}
-#ifdef CONFIG_SECCOMP
-static int vsyscall_seccomp(struct task_struct *tsk, int syscall_nr)
-{
- if (!seccomp_mode(&tsk->seccomp))
- return 0;
- task_pt_regs(tsk)->orig_ax = syscall_nr;
- task_pt_regs(tsk)->ax = syscall_nr;
- return __secure_computing(syscall_nr);
-}
-#else
-#define vsyscall_seccomp(_tsk, _nr) 0
-#endif
-
static bool write_ok_or_segv(unsigned long ptr, size_t size)
{
/*
{
struct task_struct *tsk;
unsigned long caller;
- int vsyscall_nr;
+ int vsyscall_nr, syscall_nr, tmp;
int prev_sig_on_uaccess_error;
long ret;
- int skip;
/*
* No point in checking CS -- the only way to get here is a user mode
}
tsk = current;
- /*
- * With a real vsyscall, page faults cause SIGSEGV. We want to
- * preserve that behavior to make writing exploits harder.
- */
- prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
- current_thread_info()->sig_on_uaccess_error = 1;
/*
+ * Check for access_ok violations and find the syscall nr.
+ *
* NULL is a valid user pointer (in the access_ok sense) on 32-bit and
* 64-bit, so we don't need to special-case it here. For all the
* vsyscalls, NULL means "don't write anything" not "write it at
* address 0".
*/
- ret = -EFAULT;
- skip = 0;
switch (vsyscall_nr) {
case 0:
- skip = vsyscall_seccomp(tsk, __NR_gettimeofday);
- if (skip)
- break;
-
if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
- !write_ok_or_segv(regs->si, sizeof(struct timezone)))
- break;
+ !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_gettimeofday;
+ break;
+
+ case 1:
+ if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_time;
+ break;
+
+ case 2:
+ if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
+ !write_ok_or_segv(regs->si, sizeof(unsigned))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_getcpu;
+ break;
+ }
+
+ /*
+ * Handle seccomp. regs->ip must be the original value.
+ * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt.
+ *
+ * We could optimize the seccomp disabled case, but performance
+ * here doesn't matter.
+ */
+ regs->orig_ax = syscall_nr;
+ regs->ax = -ENOSYS;
+ tmp = secure_computing(syscall_nr);
+ if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
+ warn_bad_vsyscall(KERN_DEBUG, regs,
+ "seccomp tried to change syscall nr or ip");
+ do_exit(SIGSYS);
+ }
+ if (tmp)
+ goto do_ret; /* skip requested */
+ /*
+ * With a real vsyscall, page faults cause SIGSEGV. We want to
+ * preserve that behavior to make writing exploits harder.
+ */
+ prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
+ current_thread_info()->sig_on_uaccess_error = 1;
+
+ ret = -EFAULT;
+ switch (vsyscall_nr) {
+ case 0:
ret = sys_gettimeofday(
(struct timeval __user *)regs->di,
(struct timezone __user *)regs->si);
break;
case 1:
- skip = vsyscall_seccomp(tsk, __NR_time);
- if (skip)
- break;
-
- if (!write_ok_or_segv(regs->di, sizeof(time_t)))
- break;
-
ret = sys_time((time_t __user *)regs->di);
break;
case 2:
- skip = vsyscall_seccomp(tsk, __NR_getcpu);
- if (skip)
- break;
-
- if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
- !write_ok_or_segv(regs->si, sizeof(unsigned)))
- break;
-
ret = sys_getcpu((unsigned __user *)regs->di,
(unsigned __user *)regs->si,
NULL);
current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error;
- if (skip) {
- if ((long)regs->ax <= 0L) /* seccomp errno emulation */
- goto do_ret;
- goto done; /* seccomp trace/trap */
- }
-
+check_fault:
if (ret == -EFAULT) {
/* Bad news -- userspace fed a bad pointer to a vsyscall. */
warn_bad_vsyscall(KERN_INFO, regs,
/* Emulate a ret instruction. */
regs->ip = caller;
regs->sp += 8;
-done:
return true;
sigsegv:
#ifdef CONFIG_SECCOMP_FILTER
case SECCOMP_MODE_FILTER: {
int data;
+ struct pt_regs *regs = task_pt_regs(current);
ret = seccomp_run_filters(this_syscall);
data = ret & SECCOMP_RET_DATA;
ret &= SECCOMP_RET_ACTION;
switch (ret) {
case SECCOMP_RET_ERRNO:
/* Set the low-order 16-bits as a errno. */
- syscall_set_return_value(current, task_pt_regs(current),
+ syscall_set_return_value(current, regs,
-data, 0);
goto skip;
case SECCOMP_RET_TRAP:
/* Show the handler the original registers. */
- syscall_rollback(current, task_pt_regs(current));
+ syscall_rollback(current, regs);
/* Let the filter pass back 16 bits of data. */
seccomp_send_sigsys(this_syscall, data);
goto skip;
case SECCOMP_RET_TRACE:
/* Skip these calls if there is no tracer. */
- if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP))
+ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
+ syscall_set_return_value(current, regs,
+ -ENOSYS, 0);
goto skip;
+ }
/* Allow the BPF to provide the event message */
ptrace_event(PTRACE_EVENT_SECCOMP, data);
/*
*/
if (fatal_signal_pending(current))
break;
+ if (syscall_get_nr(current, regs) < 0)
+ goto skip; /* Explicit request to skip. */
+
return 0;
case SECCOMP_RET_ALLOW:
return 0;
git.openpandora.org / pandora-kernel.git / commitdiff