[PATCH v6 15/36] function_graph: Add "task variables" per task for fgraph_ops

From: Masami Hiramatsu (Google)
Date: Fri Jan 12 2024 - 05:16:28 EST


From: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>

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) <rostedt@xxxxxxxxxxx>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
---
Changes in v3:
- Move fgraph_ops::idx to previous patch in the series.
Changes in v2:
- Make description lines shorter than 76 chars.
---
include/linux/ftrace.h | 1 +
kernel/trace/fgraph.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 70 insertions(+), 1 deletion(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 3d9e74ea6065..737f84104577 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1116,6 +1116,7 @@ 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 ad4ea196b76e..4ff5d2864fd2 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;

@@ -182,6 +190,44 @@ 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
@@ -791,6 +837,7 @@ 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: */
@@ -851,6 +898,7 @@ 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;
@@ -949,6 +997,24 @@ 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;
@@ -998,6 +1064,8 @@ 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);