[RFC,v3,5/5] tracing: convert sys_enter/exit to faultable tracepoints

Commit Message

Mathieu Desnoyers Oct. 2, 2023, 8:25 p.m. UTC

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

This allows tracers to fault-in userspace system call arguments such as
path strings within their probe callbacks.

Co-developed-by: Michael Jeanson <[e-mail]>
Signed-off-by: Mathieu Desnoyers <[e-mail]>
Signed-off-by: Michael Jeanson <[e-mail]>
Cc: Steven Rostedt (VMware) <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Alexei Starovoitov <[e-mail]>
Cc: Yonghong Song <[e-mail]>
Cc: Paul E. McKenney <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: [e-mail]
Cc: Joel Fernandes <[e-mail]>
---
 include/trace/events/syscalls.h |  4 +-
 kernel/trace/trace_syscalls.c   | 92 +++++++++++++++++++++++----------
 2 files changed, 68 insertions(+), 28 deletions(-)

Patch

diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index b6e0cbc2c71f..dc30e3004818 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_MAY_FAULT(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_MAY_FAULT(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 942ddbdace4a..e4414f7bdbe7 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -299,27 +299,33 @@  static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int syscall_nr;
 	int size;
 
+	/*
+	 * Probe called with preemption enabled (may_fault), 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;
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
 	if (!entry)
-		return;
+		goto end;
 
 	entry = ring_buffer_event_data(fbuffer.event);
 	entry->nr = syscall_nr;
@@ -327,6 +333,8 @@  static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	trace_event_buffer_commit(&fbuffer);
+end:
+	preempt_enable_notrace();
 }
 
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -338,31 +346,39 @@  static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct trace_event_buffer fbuffer;
 	int syscall_nr;
 
+	/*
+	 * Probe called with preemption enabled (may_fault), 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;
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry));
 	if (!entry)
-		return;
+		goto end;
 
 	entry = ring_buffer_event_data(fbuffer.event);
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
 	trace_event_buffer_commit(&fbuffer);
+end:
+	preempt_enable_notrace();
 }
 
 static int reg_event_syscall_enter(struct trace_event_file *file,
@@ -377,7 +393,9 @@  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_prio_flags_sys_enter(ftrace_syscall_enter, tr,
+							  TRACEPOINT_DEFAULT_PRIO,
+							  TRACEPOINT_MAY_FAULT);
 	if (!ret) {
 		rcu_assign_pointer(tr->enter_syscall_files[num], file);
 		tr->sys_refcount_enter++;
@@ -415,7 +433,9 @@  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_prio_flags_sys_exit(ftrace_syscall_exit, tr,
+							 TRACEPOINT_DEFAULT_PRIO,
+							 TRACEPOINT_MAY_FAULT);
 	if (!ret) {
 		rcu_assign_pointer(tr->exit_syscall_files[num], file);
 		tr->sys_refcount_exit++;
@@ -579,20 +599,26 @@  static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int rctx;
 	int size;
 
+	/*
+	 * Probe called with preemption enabled (may_fault), 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);
@@ -601,7 +627,7 @@  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);
@@ -611,12 +637,14 @@  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)
@@ -628,7 +656,9 @@  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_prio_flags_sys_enter(perf_syscall_enter, NULL,
+							  TRACEPOINT_DEFAULT_PRIO,
+							  TRACEPOINT_MAY_FAULT);
 	if (ret) {
 		pr_info("event trace: Could not activate syscall entry trace point");
 	} else {
@@ -678,20 +708,26 @@  static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int rctx;
 	int size;
 
+	/*
+	 * Probe called with preemption enabled (may_fault), 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));
@@ -699,7 +735,7 @@  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);
@@ -708,11 +744,13 @@  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)
@@ -724,7 +762,9 @@  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_prio_flags_sys_exit(perf_syscall_exit, NULL,
+							 TRACEPOINT_DEFAULT_PRIO,
+							 TRACEPOINT_MAY_FAULT);
 	if (ret) {
 		pr_info("event trace: Could not activate syscall exit trace point");
 	} else {