[RFC PATCH 5/6] tracing: convert sys_enter/exit to faultable tracepoints

[Michael Jeanson]

Convert the definition of the system call enter/exit tracepoints to
faultable tracepoints now that all upstream tracers handle it.

Co-developed-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Signed-off-by: Michael Jeanson <mjeanson@xxxxxxxxxxxx>
Cc: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Yonghong Song <yhs@xxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: bpf@xxxxxxxxxxxxxxx
Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
---
 include/trace/events/syscalls.h |  4 +-
 kernel/trace/trace_syscalls.c   | 84 +++++++++++++++++++++++----------
 2 files changed, 60 insertions(+), 28 deletions(-)

diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index b6e0cbc2c71f..2bd2d94563a2 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -15,7 +15,7 @@
 
 #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
 
-TRACE_EVENT_FN(sys_enter,
+TRACE_EVENT_FN_MAYFAULT(sys_enter,
 
 	TP_PROTO(struct pt_regs *regs, long id),
 
@@ -41,7 +41,7 @@ TRACE_EVENT_FN(sys_enter,
 
 TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY)
 
-TRACE_EVENT_FN(sys_exit,
+TRACE_EVENT_FN_MAYFAULT(sys_exit,
 
 	TP_PROTO(struct pt_regs *regs, long ret),
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index d85a2f0f316b..4ca9190e26b2 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -304,21 +304,27 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int syscall_nr;
 	int size;
 
+	/*
+	 * Probe called with preemption enabled (mayfault), but ring buffer and
+	 * per-cpu data require preemption to be disabled.
+	 */
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
 	trace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
 	if (!trace_file)
-		return;
+		goto end;
 
 	if (trace_trigger_soft_disabled(trace_file))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
@@ -329,7 +335,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	event = trace_buffer_lock_reserve(buffer,
 			sys_data->enter_event->event.type, size, irq_flags, pc);
 	if (!event)
-		return;
+		goto end;
 
 	entry = ring_buffer_event_data(event);
 	entry->nr = syscall_nr;
@@ -338,6 +344,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	event_trigger_unlock_commit(trace_file, buffer, event, entry,
 				    irq_flags, pc);
+end:
+	preempt_enable_notrace();
 }
 
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -352,21 +360,27 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	int pc;
 	int syscall_nr;
 
+	/*
+	 * Probe called with preemption enabled (mayfault), but ring buffer and
+	 * per-cpu data require preemption to be disabled.
+	 */
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
 	trace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
 	if (!trace_file)
-		return;
+		goto end;
 
 	if (trace_trigger_soft_disabled(trace_file))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	local_save_flags(irq_flags);
 	pc = preempt_count();
@@ -376,7 +390,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 			sys_data->exit_event->event.type, sizeof(*entry),
 			irq_flags, pc);
 	if (!event)
-		return;
+		goto end;
 
 	entry = ring_buffer_event_data(event);
 	entry->nr = syscall_nr;
@@ -384,6 +398,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 
 	event_trigger_unlock_commit(trace_file, buffer, event, entry,
 				    irq_flags, pc);
+end:
+	preempt_enable_notrace();
 }
 
 static int reg_event_syscall_enter(struct trace_event_file *file,
@@ -398,7 +414,7 @@ static int reg_event_syscall_enter(struct trace_event_file *file,
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!tr->sys_refcount_enter)
-		ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
+		ret = register_trace_mayfault_sys_enter(ftrace_syscall_enter, tr);
 	if (!ret) {
 		rcu_assign_pointer(tr->enter_syscall_files[num], file);
 		tr->sys_refcount_enter++;
@@ -436,7 +452,7 @@ static int reg_event_syscall_exit(struct trace_event_file *file,
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!tr->sys_refcount_exit)
-		ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
+		ret = register_trace_mayfault_sys_exit(ftrace_syscall_exit, tr);
 	if (!ret) {
 		rcu_assign_pointer(tr->exit_syscall_files[num], file);
 		tr->sys_refcount_exit++;
@@ -600,20 +616,26 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int rctx;
 	int size;
 
+	/*
+	 * Probe called with preemption enabled (mayfault), but ring buffer and
+	 * per-cpu data require preemption to be disabled.
+	 */
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	head = this_cpu_ptr(sys_data->enter_event->perf_events);
 	valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
 	if (!valid_prog_array && hlist_empty(head))
-		return;
+		goto end;
 
 	/* get the size after alignment with the u32 buffer size field */
 	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
@@ -622,7 +644,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 
 	rec = perf_trace_buf_alloc(size, NULL, &rctx);
 	if (!rec)
-		return;
+		goto end;
 
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, args);
@@ -632,12 +654,14 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
-		return;
+		goto end;
 	}
 
 	perf_trace_buf_submit(rec, size, rctx,
 			      sys_data->enter_event->event.type, 1, regs,
 			      head, NULL);
+end:
+	preempt_enable_notrace();
 }
 
 static int perf_sysenter_enable(struct trace_event_call *call)
@@ -649,7 +673,7 @@ static int perf_sysenter_enable(struct trace_event_call *call)
 
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_perf_refcount_enter)
-		ret = register_trace_sys_enter(perf_syscall_enter, NULL);
+		ret = register_trace_mayfault_sys_enter(perf_syscall_enter, NULL);
 	if (ret) {
 		pr_info("event trace: Could not activate syscall entry trace point");
 	} else {
@@ -699,20 +723,26 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int rctx;
 	int size;
 
+	/*
+	 * Probe called with preemption enabled (mayfault), but ring buffer and
+	 * per-cpu data require preemption to be disabled.
+	 */
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	head = this_cpu_ptr(sys_data->exit_event->perf_events);
 	valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
 	if (!valid_prog_array && hlist_empty(head))
-		return;
+		goto end;
 
 	/* We can probably do that at build time */
 	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
@@ -720,7 +750,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
 	rec = perf_trace_buf_alloc(size, NULL, &rctx);
 	if (!rec)
-		return;
+		goto end;
 
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
@@ -729,11 +759,13 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	     !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
-		return;
+		goto end;
 	}
 
 	perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
 			      1, regs, head, NULL);
+end:
+	preempt_enable_notrace();
 }
 
 static int perf_sysexit_enable(struct trace_event_call *call)
@@ -745,7 +777,7 @@ static int perf_sysexit_enable(struct trace_event_call *call)
 
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_perf_refcount_exit)
-		ret = register_trace_sys_exit(perf_syscall_exit, NULL);
+		ret = register_trace_mayfault_sys_exit(perf_syscall_exit, NULL);
 	if (ret) {
 		pr_info("event trace: Could not activate syscall exit trace point");
 	} else {
-- 
2.25.1