Add a might_fault() check to validate that the perf sys_enter/sys_exit
probe callbacks are indeed called from a context where page faults can
be handled.

Signed-off-by: Mathieu Desnoyers <[email protected]>
Cc: Michael Jeanson <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Yonghong Song <[email protected]>
Cc: Paul E. McKenney <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Andrii Nakryiko <[email protected]>
Cc: [email protected]
Cc: Joel Fernandes <[email protected]>
---
 include/trace/perf.h          | 1 +
 kernel/trace/trace_syscalls.c | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/include/trace/perf.h b/include/trace/perf.h
index 5650c1bad088..321bfd7919f6 100644
--- a/include/trace/perf.h
+++ b/include/trace/perf.h
@@ -84,6 +84,7 @@ perf_trace_##call(void *__data, proto)                        
                \
        u64 __count __attribute__((unused));                            \
        struct task_struct *__task __attribute__((unused));             \
                                                                        \
+       might_fault();                                                  \
        guard(preempt_notrace)();                                       \
        do_perf_trace_##call(__data, args);                             \
 }
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 0430890cbb42..53faa791c735 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -600,6 +600,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs 
*regs, long id)
         * Syscall probe called with preemption enabled, but the ring
         * buffer and per-cpu data require preemption to be disabled.
         */
+       might_fault();
        guard(preempt_notrace)();
 
        syscall_nr = trace_get_syscall_nr(current, regs);
@@ -706,6 +707,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs 
*regs, long ret)
         * Syscall probe called with preemption enabled, but the ring
         * buffer and per-cpu data require preemption to be disabled.
         */
+       might_fault();
        guard(preempt_notrace)();
 
        syscall_nr = trace_get_syscall_nr(current, regs);
-- 
2.39.2


Reply via email to