@@ -56,6 +56,43 @@ TRACE_EVENT(task_rename,
__entry->newcomm, __entry->oom_score_adj)
);
+/**
+ * task_prctl_unknown - called on unknown prctl() option
+ * @option: option passed
+ * @arg2: arg2 passed
+ * @arg3: arg3 passed
+ * @arg4: arg4 passed
+ * @arg5: arg5 passed
+ *
+ * Called on an unknown prctl() option.
+ */
+TRACE_EVENT(task_prctl_unknown,
+
+ TP_PROTO(int option, unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5),
+
+ TP_ARGS(option, arg2, arg3, arg4, arg5),
+
+ TP_STRUCT__entry(
+ __field( int, option)
+ __field( unsigned long, arg2)
+ __field( unsigned long, arg3)
+ __field( unsigned long, arg4)
+ __field( unsigned long, arg5)
+ ),
+
+ TP_fast_assign(
+ __entry->option = option;
+ __entry->arg2 = arg2;
+ __entry->arg3 = arg3;
+ __entry->arg4 = arg4;
+ __entry->arg5 = arg5;
+ ),
+
+ TP_printk("option=%d arg2=%ld arg3=%ld arg4=%ld arg5=%ld",
+ __entry->option, __entry->arg2, __entry->arg3, __entry->arg4, __entry->arg5)
+);
+
#endif
/* This part must be outside protection */
@@ -75,6 +75,8 @@
#include <asm/io.h>
#include <asm/unistd.h>
+#include <trace/events/task.h>
+
#include "uid16.h"
#ifndef SET_UNALIGN_CTL
@@ -2785,6 +2787,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3);
break;
default:
+ trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5);
error = -EINVAL;
break;
}
prctl() is a complex syscall which multiplexes its functionality based on a large set of PR_* options. Currently we count 64 such options. The return value of unknown options is -EINVAL, and doesn't distinguish from known options that were passed invalid args that also return -EINVAL. To understand if programs are attempting to use prctl() options not yet available on the running kernel, provide the task_prctl_unknown tracepoint. Note, this tracepoint is in an unlikely cold path, and would therefore be suitable for continuous monitoring (e.g. via perf_event_open). While the above is likely the simplest usecase, additionally this tracepoint can help unlock some testing scenarios (where probing sys_enter or sys_exit causes undesirable performance overheads): a. unprivileged triggering of a test module: test modules may register a probe to be called back on task_prctl_unknown, and pick a very large unknown prctl() option upon which they perform a test function for an unprivileged user; b. unprivileged triggering of an eBPF program function: similar as idea (a). Example trace_pipe output: test-380 [001] ..... 78.142904: task_prctl_unknown: option=1234 arg2=101 arg3=102 arg4=103 arg5=104 Signed-off-by: Marco Elver <elver@google.com> --- v3: * Remove "comm". v2: * Remove "pid" in trace output (suggested by Steven). --- include/trace/events/task.h | 37 +++++++++++++++++++++++++++++++++++++ kernel/sys.c | 3 +++ 2 files changed, 40 insertions(+)