[RFC,v2,13/31] function_graph: Add "task variables" per task for fgraph_ops

Commit Message

Masami Hiramatsu (Google) Nov. 8, 2023, 2:26 p.m. UTC

From: Steven Rostedt (VMware) <[e-mail]>

Add a "task variables" array on the tasks shadow ret_stack that is the
size of longs for each possible registered fgraph_ops. That's a total
of 16, taking up 8 * 16 = 128 bytes (out of a page size 4k).

This will allow for fgraph_ops to do specific features on a per task basis
having a way to maintain state for each task.

Signed-off-by: Steven Rostedt (VMware) <[e-mail]>
Signed-off-by: Masami Hiramatsu (Google) <[e-mail]>
---
 Changes in v2:
  - Make description lines shorter than 76 chars.
---
 include/linux/ftrace.h |    2 +
 kernel/trace/fgraph.c  |   73 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 74 insertions(+), 1 deletion(-)

Patch

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index d30eb8a97a50..3f9f1f48e8fd 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1071,6 +1071,7 @@  struct fgraph_ops {
 	trace_func_graph_ret_t		retfunc;
 	struct ftrace_ops		ops; /* for the hash lists */
 	void				*private;
+	int				idx;
 };
 
 /*
@@ -1109,6 +1110,7 @@  ftrace_graph_get_ret_stack(struct task_struct *task, int idx);
 
 unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp);
+unsigned long *fgraph_get_task_var(struct fgraph_ops *gops);
 
 /*
  * Sometimes we don't want to trace a function with the function
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 97cf320d20a8..79bdd3c775dd 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -92,10 +92,18 @@  enum {
 #define SHADOW_STACK_SIZE (PAGE_SIZE)
 #define SHADOW_STACK_INDEX (SHADOW_STACK_SIZE / sizeof(long))
 /* Leave on a buffer at the end */
-#define SHADOW_STACK_MAX_INDEX (SHADOW_STACK_INDEX - (FGRAPH_RET_INDEX + 1))
+#define SHADOW_STACK_MAX_INDEX				\
+	(SHADOW_STACK_INDEX - (FGRAPH_RET_INDEX + 1 + FGRAPH_ARRAY_SIZE))
 
 #define RET_STACK(t, index) ((struct ftrace_ret_stack *)(&(t)->ret_stack[index]))
 
+/*
+ * Each fgraph_ops has a reservered unsigned long at the end (top) of the
+ * ret_stack to store task specific state.
+ */
+#define SHADOW_STACK_TASK_VARS(ret_stack) \
+	((unsigned long *)(&(ret_stack)[SHADOW_STACK_INDEX - FGRAPH_ARRAY_SIZE]))
+
 DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
 int ftrace_graph_active;
 
@@ -131,6 +139,44 @@  static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops)
 {
 }
 
+static void ret_stack_set_task_var(struct task_struct *t, int idx, long val)
+{
+	unsigned long *gvals = SHADOW_STACK_TASK_VARS(t->ret_stack);
+
+	gvals[idx] = val;
+}
+
+static unsigned long *
+ret_stack_get_task_var(struct task_struct *t, int idx)
+{
+	unsigned long *gvals = SHADOW_STACK_TASK_VARS(t->ret_stack);
+
+	return &gvals[idx];
+}
+
+static void ret_stack_init_task_vars(unsigned long *ret_stack)
+{
+	unsigned long *gvals = SHADOW_STACK_TASK_VARS(ret_stack);
+
+	memset(gvals, 0, sizeof(*gvals) * FGRAPH_ARRAY_SIZE);
+}
+
+/**
+ * fgraph_get_task_var - retrieve a task specific state variable
+ * @gops: The ftrace_ops that owns the task specific variable
+ *
+ * Every registered fgraph_ops has a task state variable
+ * reserved on the task's ret_stack. This function returns the
+ * address to that variable.
+ *
+ * Returns the address to the fgraph_ops @gops tasks specific
+ * unsigned long variable.
+ */
+unsigned long *fgraph_get_task_var(struct fgraph_ops *gops)
+{
+	return ret_stack_get_task_var(current, gops->idx);
+}
+
 /*
  * @offset: The index into @t->ret_stack to find the ret_stack entry
  * @index: Where to place the index into @t->ret_stack of that entry
@@ -708,6 +754,7 @@  static int alloc_retstack_tasklist(unsigned long **ret_stack_list)
 
 		if (t->ret_stack == NULL) {
 			atomic_set(&t->trace_overrun, 0);
+			ret_stack_init_task_vars(ret_stack_list[start]);
 			t->curr_ret_stack = 0;
 			t->curr_ret_depth = -1;
 			/* Make sure the tasks see the 0 first: */
@@ -768,6 +815,7 @@  static void
 graph_init_task(struct task_struct *t, unsigned long *ret_stack)
 {
 	atomic_set(&t->trace_overrun, 0);
+	ret_stack_init_task_vars(ret_stack);
 	t->ftrace_timestamp = 0;
 	t->curr_ret_stack = 0;
 	t->curr_ret_depth = -1;
@@ -866,6 +914,24 @@  static int start_graph_tracing(void)
 	return ret;
 }
 
+static void init_task_vars(int idx)
+{
+	struct task_struct *g, *t;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		if (idle_task(cpu)->ret_stack)
+			ret_stack_set_task_var(idle_task(cpu), idx, 0);
+	}
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, t) {
+		if (t->ret_stack)
+			ret_stack_set_task_var(t, idx, 0);
+	}
+	read_unlock(&tasklist_lock);
+}
+
 int register_ftrace_graph(struct fgraph_ops *gops)
 {
 	int command = 0;
@@ -901,6 +967,7 @@  int register_ftrace_graph(struct fgraph_ops *gops)
 	fgraph_array[i] = gops;
 	if (i + 1 > fgraph_array_cnt)
 		fgraph_array_cnt = i + 1;
+	gops->idx = i;
 
 	ftrace_graph_active++;
 
@@ -918,6 +985,8 @@  int register_ftrace_graph(struct fgraph_ops *gops)
 		ftrace_graph_return = return_run;
 		ftrace_graph_entry = entry_run;
 		command = FTRACE_START_FUNC_RET;
+	} else {
+		init_task_vars(gops->idx);
 	}
 
 	ret = ftrace_startup(&gops->ops, command);
@@ -942,6 +1011,8 @@  void unregister_ftrace_graph(struct fgraph_ops *gops)
 	if (i >= fgraph_array_cnt)
 		goto out;
 
+	WARN_ON_ONCE(gops->idx != i);
+
 	fgraph_array[i] = &fgraph_stub;
 	if (i + 1 == fgraph_array_cnt) {
 		for (; i >= 0; i--)