@@ -44,10 +44,12 @@
SYSCALL_WORK_SYSCALL_TRACE | \
SYSCALL_WORK_SYSCALL_EMU | \
SYSCALL_WORK_SYSCALL_AUDIT | \
+ SYSCALL_WORK_SYSCALL_USER_DISPATCH | \
ARCH_SYSCALL_WORK_ENTER)
#define SYSCALL_WORK_EXIT (SYSCALL_WORK_SYSCALL_TRACEPOINT | \
SYSCALL_WORK_SYSCALL_TRACE | \
SYSCALL_WORK_SYSCALL_AUDIT | \
+ SYSCALL_WORK_SYSCALL_USER_DISPATCH | \
ARCH_SYSCALL_WORK_EXIT)
/*
@@ -5,6 +5,8 @@
#include <linux/livepatch.h>
#include <linux/audit.h>
+#include "common.h"
+
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
@@ -46,6 +48,16 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
{
long ret = 0;
+ /*
+ * Handle Syscall User Dispatch. This must comes first, since
+ * the ABI here can be something that doesn't make sense for
+ * other syscall_work features.
+ */
+ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+ if (do_syscall_user_dispatch(regs))
+ return -1L;
+ }
+
/* Handle ptrace */
if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
ret = arch_syscall_enter_tracehook(regs);
@@ -230,6 +242,11 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
{
bool step;
+ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+ if (on_syscall_dispatch())
+ return;
+ }
+
audit_syscall_exit(regs);
if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
Syscall User Dispatch (SUD) must take precedence over seccomp and ptrace, since the use case is emulation (it can be invoked with a different ABI) such that seccomp filtering by syscall number doesn't make sense in the first place. In addition, either the syscall is dispatched back to userspace, in which case there is no resource for to trace, or the syscall will be executed, and seccomp/ptrace will execute next. Since SUD runs before tracepoints, it needs to be a SYSCALL_WORK_EXIT as well, just to prevent a trace exit event when dispatch was triggered. For that, the on_syscall_dispatch() examines context to skip the tracepoint, audit and other work. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> --- Changes since v6: - Update do_syscall_intercept signature (Christian Brauner) - Move it to before tracepoints - Use SYSCALL_WORK flags --- include/linux/entry-common.h | 2 ++ kernel/entry/common.c | 17 +++++++++++++++++ 2 files changed, 19 insertions(+)