[for-next][PATCH 17/27] function_graph: Move graph depth stored data to shadow stack global var

From: Steven Rostedt
Date: Tue Jun 04 2024 - 10:47:00 EST


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

The use of the task->trace_recursion for the logic used for the function
graph depth was a bit of an abuse of that variable. Now that there
exists global vars that are per stack for registered graph traces, use that
instead.

Link: https://lore.kernel.org/linux-trace-kernel/171509106728.162236.2398372644430125344.stgit@devnote2
Link: https://lore.kernel.org/linux-trace-kernel/20240603190823.634870264@xxxxxxxxxxx

Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Alexei Starovoitov <alexei.starovoitov@xxxxxxxxx>
Cc: Florent Revest <revest@xxxxxxxxxxxx>
Cc: Martin KaFai Lau <martin.lau@xxxxxxxxx>
Cc: bpf <bpf@xxxxxxxxxxxxxxx>
Cc: Sven Schnelle <svens@xxxxxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Cc: Alan Maguire <alan.maguire@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Guo Ren <guoren@xxxxxxxxxx>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
---
include/linux/trace_recursion.h | 29 ----------------------------
kernel/trace/trace.h | 34 +++++++++++++++++++++++++++++++--
2 files changed, 32 insertions(+), 31 deletions(-)

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index 02e6afc6d7fe..fdfb6f66718a 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -44,25 +44,6 @@ enum {
*/
TRACE_IRQ_BIT,

- /*
- * In the very unlikely case that an interrupt came in
- * at a start of graph tracing, and we want to trace
- * the function in that interrupt, the depth can be greater
- * than zero, because of the preempted start of a previous
- * trace. In an even more unlikely case, depth could be 2
- * if a softirq interrupted the start of graph tracing,
- * followed by an interrupt preempting a start of graph
- * tracing in the softirq, and depth can even be 3
- * if an NMI came in at the start of an interrupt function
- * that preempted a softirq start of a function that
- * preempted normal context!!!! Luckily, it can't be
- * greater than 3, so the next two bits are a mask
- * of what the depth is when we set TRACE_GRAPH_FL
- */
-
- TRACE_GRAPH_DEPTH_START_BIT,
- TRACE_GRAPH_DEPTH_END_BIT,
-
/*
* To implement set_graph_notrace, if this bit is set, we ignore
* function graph tracing of called functions, until the return
@@ -78,16 +59,6 @@ enum {
#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit)))

-#define trace_recursion_depth() \
- (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3)
-#define trace_recursion_set_depth(depth) \
- do { \
- current->trace_recursion &= \
- ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \
- current->trace_recursion |= \
- ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \
- } while (0)
-
#define TRACE_CONTEXT_BITS 4

#define TRACE_FTRACE_START TRACE_FTRACE_BIT
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 73919129e57c..82d879dc63ff 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -900,8 +900,38 @@ extern void free_fgraph_ops(struct trace_array *tr);

enum {
TRACE_GRAPH_FL = 1,
+
+ /*
+ * In the very unlikely case that an interrupt came in
+ * at a start of graph tracing, and we want to trace
+ * the function in that interrupt, the depth can be greater
+ * than zero, because of the preempted start of a previous
+ * trace. In an even more unlikely case, depth could be 2
+ * if a softirq interrupted the start of graph tracing,
+ * followed by an interrupt preempting a start of graph
+ * tracing in the softirq, and depth can even be 3
+ * if an NMI came in at the start of an interrupt function
+ * that preempted a softirq start of a function that
+ * preempted normal context!!!! Luckily, it can't be
+ * greater than 3, so the next two bits are a mask
+ * of what the depth is when we set TRACE_GRAPH_FL
+ */
+
+ TRACE_GRAPH_DEPTH_START_BIT,
+ TRACE_GRAPH_DEPTH_END_BIT,
};

+static inline unsigned long ftrace_graph_depth(unsigned long *task_var)
+{
+ return (*task_var >> TRACE_GRAPH_DEPTH_START_BIT) & 3;
+}
+
+static inline void ftrace_graph_set_depth(unsigned long *task_var, int depth)
+{
+ *task_var &= ~(3 << TRACE_GRAPH_DEPTH_START_BIT);
+ *task_var |= (depth & 3) << TRACE_GRAPH_DEPTH_START_BIT;
+}
+
#ifdef CONFIG_DYNAMIC_FTRACE
extern struct ftrace_hash __rcu *ftrace_graph_hash;
extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash;
@@ -934,7 +964,7 @@ ftrace_graph_addr(unsigned long *task_var, struct ftrace_graph_ent *trace)
* when the depth is zero.
*/
*task_var |= TRACE_GRAPH_FL;
- trace_recursion_set_depth(trace->depth);
+ ftrace_graph_set_depth(task_var, trace->depth);

/*
* If no irqs are to be traced, but a set_graph_function
@@ -959,7 +989,7 @@ ftrace_graph_addr_finish(struct fgraph_ops *gops, struct ftrace_graph_ret *trace
unsigned long *task_var = fgraph_get_task_var(gops);

if ((*task_var & TRACE_GRAPH_FL) &&
- trace->depth == trace_recursion_depth())
+ trace->depth == ftrace_graph_depth(task_var))
*task_var &= ~TRACE_GRAPH_FL;
}

--
2.43.0