Currently, if a tracer changes a syscall nr to __NR_future_enosys,
behavior will differ between kernels that know about
__NR_future_enosys (and return -ENOSYS) and older kernels (which
return the value from pt_regs).  This is silly; we should just
return -ENOSYS.

This is unlikely to ever happen on x86 because the return value in
pt_regs starts out as -ENOSYS, but a silly tracer can change that.

Signed-off-by: Andy Lutomirski <l...@amacapital.net>
Cc: Will Drewry <w...@chromium.org>
---
 arch/x86/include/asm/syscall.h |   11 +++++++++++
 kernel/seccomp.c               |   15 +++++++++++++++
 2 files changed, 26 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 1ace47b..8191e057 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -70,6 +70,17 @@ static inline void syscall_set_return_value(struct 
task_struct *task,
        regs->ax = (long) error ?: val;
 }
 
+static inline bool syscall_is_nr_future(struct task_struct *task,
+                                       struct pt_regs *regs)
+{
+#ifdef CONFIG_IA32_EMULATION
+       if (task_thread_info(task)->status & TS_COMPAT)
+               return syscall_get_nr(task, regs) > __NR_ia32_syscall_max;
+#endif
+
+       return syscall_get_nr(task, regs) > __NR_syscall_max;
+}
+
 #ifdef CONFIG_X86_32
 
 static inline void syscall_get_arguments(struct task_struct *task,
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 5af44b5..bd7527d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -429,6 +429,21 @@ int __secure_computing(int this_syscall)
                         */
                        if (fatal_signal_pending(current))
                                break;
+
+                       if (syscall_is_nr_future(current, regs)) {
+                               /*
+                                * If the tracer selects a system call that
+                                * only future kernels know about, we still need
+                                * to execute that syscall by returning
+                                * -ENOSYS.  (On x86, this only matters if the
+                                * tracer changed the return value, which would
+                                * be silly, but user code can be silly.)
+                                */
+                               syscall_set_return_value(current, regs,
+                                                        -ENOSYS, 0);
+                               goto skip;
+                       }
+
                        if (syscall_get_nr(current, regs) < 0)
                                goto skip;  /* Explicit request to skip. */
 
-- 
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to