5 files changed, 88 insertions, 21 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 827fb9a0bf0d..2f72af0357e5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8611,6 +8611,7 @@ ftrace_pid_follow_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 
@@ -8624,6 +8625,7 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f16f053ef77d..17d0ea0cc3e6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	return err;
 }
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask)))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	guard(mutex)(&cpu_buffer->mapping_lock);
+
+	if (cpu_buffer->user_mapped)
+		__rb_inc_dec_mapped(cpu_buffer, true);
+	else
+		WARN(1, "Unexpected buffer stat, it should be mapped");
+}
+
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 23de3719f495..1e7c032a72d2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
 static inline void put_snapshot_map(struct trace_array *tr) { }
 #endif
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+static void tracing_buffers_mmap_open(struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = vma->vm_file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file);
+}
+
 static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
 {
 	struct ftrace_buffer_info *info = vma->vm_file->private_data;
@@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a
 }
 
 static const struct vm_operations_struct tracing_buffers_vmops = {
+	.open		= tracing_buffers_mmap_open,
 	.close		= tracing_buffers_mmap_close,
 	.may_split      = tracing_buffers_may_split,
 };
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9928da636c9d..b7343fdfd7b0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_raw(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 
@@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 
@@ -4668,26 +4670,22 @@ static __init int event_trace_memsetup(void)
 	return 0;
 }
 
-__init void
-early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+/*
+ * Helper function to enable or disable a comma-separated list of events
+ * from the bootup buffer.
+ */
+static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable)
 {
 	char *token;
-	int ret;
-
-	while (true) {
-		token = strsep(&buf, ",");
-
-		if (!token)
-			break;
 
+	while ((token = strsep(&buf, ","))) {
 		if (*token) {
-			/* Restarting syscalls requires that we stop them first */
-			if (disable_first)
+			if (enable) {
+				if (ftrace_set_clr_event(tr, token, 1))
+					pr_warn("Failed to enable trace event: %s\n", token);
+			} else {
 				ftrace_set_clr_event(tr, token, 0);
-
-			ret = ftrace_set_clr_event(tr, token, 1);
-			if (ret)
-				pr_warn("Failed to enable trace event: %s\n", token);
+			}
 		}
 
 		/* Put back the comma to allow this to be called again */
@@ -4696,6 +4694,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
 	}
 }
 
+/**
+ * early_enable_events - enable events from the bootup buffer
+ * @tr: The trace array to enable the events in
+ * @buf: The buffer containing the comma separated list of events
+ * @disable_first: If true, disable all events in @buf before enabling them
+ *
+ * This function enables events from the bootup buffer. If @disable_first
+ * is true, it will first disable all events in the buffer before enabling
+ * them.
+ *
+ * For syscall events, which rely on a global refcount to register the
+ * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must
+ * ensure the refcount hits zero before re-enabling them. A simple
+ * "disable then enable" per-event is not enough if multiple syscalls are
+ * used, as the refcount will stay above zero. Thus, we need a two-phase
+ * approach: disable all, then enable all.
+ */
+__init void
+early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+{
+	if (disable_first)
+		__early_set_events(tr, buf, false);
+
+	__early_set_events(tr, buf, true);
+}
+
 static __init int event_trace_enable(void)
 {
 	struct trace_array *tr = top_trace_array();
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3d8239fee004..0d2d3a2ea7dd 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -400,14 +400,19 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 				      struct fgraph_ops *gops,
 				      struct ftrace_regs *fregs)
 {
+	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct fgraph_times *ftimes;
 	struct trace_array *tr;
+	unsigned int trace_ctx;
+	u64 calltime, rettime;
 	int size;
 
+	rettime = trace_clock_local();
+
 	ftrace_graph_addr_finish(gops, trace);
 
-	if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
-		trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
+	if (*task_var & TRACE_GRAPH_NOTRACE) {
+		*task_var &= ~TRACE_GRAPH_NOTRACE;
 		return;
 	}
 
@@ -418,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	tr = gops->private;
 	handle_nosleeptime(tr, trace, ftimes, size);
 
-	if (tracing_thresh &&
-	    (trace_clock_local() - ftimes->calltime < tracing_thresh))
+	calltime = ftimes->calltime;
+
+	if (tracing_thresh && (rettime - calltime < tracing_thresh))
 		return;
-	else
-		trace_graph_return(trace, gops, fregs);
+
+	trace_ctx = tracing_gen_ctx();
+	__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
 }
 
 static struct fgraph_ops funcgraph_ops = {