function_graph: Handle tail calls for stack unwinding

For the tail-call, there would be 2 or more ftrace_ret_stacks on the
ret_stack, which records "return_to_handler" as the return address except
for the last one.  But on the real stack, there should be 1 entry because
tail-call reuses the return address on the stack and jump to the next
function.

In ftrace_graph_ret_addr() that is used for stack unwinding, skip tail
calls as a real stack unwinder would do.

Link: https://lore.kernel.org/linux-trace-kernel/171509096221.162236.8806372072523195752.stgit@devnote2
Link: https://lore.kernel.org/linux-trace-kernel/20240603190821.717065217@goodmis.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: bpf <bpf@vger.kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Guo Ren <guoren@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index aae51f746828d58a6bb309d19794b79be36268cf..8de2a2662281dedc6ec3a08015b159beec380d5a 100644 (file)
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -594,16 +594,26 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
                                    unsigned long ret, unsigned long *retp)
 {
        struct ftrace_ret_stack *ret_stack;
+       unsigned long return_handler = (unsigned long)dereference_kernel_function_descriptor(return_to_handler);
        int i = task->curr_ret_stack;
 
-       if (ret != (unsigned long)dereference_kernel_function_descriptor(return_to_handler))
+       if (ret != return_handler)
                return ret;
 
        while (i > 0) {
                ret_stack = get_ret_stack(current, i, &i);
                if (!ret_stack)
                        break;
-               if (ret_stack->retp == retp)
+               /*
+                * For the tail-call, there would be 2 or more ftrace_ret_stacks on
+                * the ret_stack, which records "return_to_handler" as the return
+                * address except for the last one.
+                * But on the real stack, there should be 1 entry because tail-call
+                * reuses the return address on the stack and jump to the next function.
+                * Thus we will continue to find real return address.
+                */
+               if (ret_stack->retp == retp &&
+                   ret_stack->ret != return_handler)
                        return ret_stack->ret;
        }
 
@@ -614,10 +624,11 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
                                    unsigned long ret, unsigned long *retp)
 {
        struct ftrace_ret_stack *ret_stack;
+       unsigned long return_handler = (unsigned long)dereference_kernel_function_descriptor(return_to_handler);
        int offset = task->curr_ret_stack;
        int i;
 
-       if (ret != (unsigned long)dereference_kernel_function_descriptor(return_to_handler))
+       if (ret != return_handler)
                return ret;
 
        if (!idx)
@@ -626,6 +637,8 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
        i = *idx;
        do {
                ret_stack = get_ret_stack(task, offset, &offset);
+               if (ret_stack && ret_stack->ret == return_handler)
+                       continue;
                i--;
        } while (i >= 0 && ret_stack);