Re: [PATCH bpf-next 2/4] x86/fgraph,bpf: Switch kprobe_multi program stack unwind to hw_regs path

[Jiri Olsa <olsajiri@gmail.com>]

On Mon, Jan 12, 2026 at 05:07:57PM -0500, Steven Rostedt wrote:
> On Mon, 12 Jan 2026 22:49:38 +0100
> Jiri Olsa <jolsa@kernel.org> wrote:
> 
> > To recreate same stack setup for return probe as we have for entry
> > probe, we set the instruction pointer to the attached function address,
> > which gets us the same unwind setup and same stack trace.
> > 
> > With the fix, entry probe:
> > 
> >   # bpftrace -e 'kprobe:__x64_sys_newuname* { print(kstack)}'
> >   Attaching 1 probe...
> > 
> >         __x64_sys_newuname+9
> >         do_syscall_64+134
> >         entry_SYSCALL_64_after_hwframe+118
> > 
> > return probe:
> > 
> >   # bpftrace -e 'kretprobe:__x64_sys_newuname* { print(kstack)}'
> >   Attaching 1 probe...
> > 
> >         __x64_sys_newuname+4
> >         do_syscall_64+134
> >         entry_SYSCALL_64_after_hwframe+118
> 
> But is this really correct?
> 
> The stack trace of the return from __x86_sys_newuname is from offset "+4".
> 
> The stack trace from entry is offset "+9". Isn't it confusing that the
> offset is likely not from the return portion of that function?

right, makes sense.. so standard kprobe actualy skips attached function
(__x86_sys_newuname) on return probe stacktrace.. perhaps we should do
the same for kprobe_multi

I managed to get that with the change below, but it's wrong wrt arch code,
note the ftrace_regs_set_stack_pointer(fregs, stack + 8) .. will try to
figure out better way when we agree on the solution

thanks,
jirka


---
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index c56e1e63b893..b0e8ce4934e7 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -71,6 +71,9 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 #define ftrace_regs_set_instruction_pointer(fregs, _ip)	\
 	do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0)
 
+#define ftrace_regs_set_stack_pointer(fregs, _sp)	\
+	do { arch_ftrace_regs(fregs)->regs.sp = (_sp); } while (0)
+
 
 static __always_inline unsigned long
 ftrace_regs_get_return_address(struct ftrace_regs *fregs)
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 6279e0a753cf..b1510c412dcb 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -717,7 +717,8 @@ int function_graph_enter_regs(unsigned long ret, unsigned long func,
 /* Retrieve a function return address to the trace stack on thread info.*/
 static struct ftrace_ret_stack *
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
-			unsigned long frame_pointer, int *offset)
+			unsigned long *stack, unsigned long frame_pointer,
+			int *offset)
 {
 	struct ftrace_ret_stack *ret_stack;
 
@@ -762,6 +763,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 
 	*offset += FGRAPH_FRAME_OFFSET;
 	*ret = ret_stack->ret;
+	*stack = (unsigned long) ret_stack->retp;
 	trace->func = ret_stack->func;
 	trace->overrun = atomic_read(&current->trace_overrun);
 	trace->depth = current->curr_ret_depth;
@@ -810,12 +812,13 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
 	struct ftrace_ret_stack *ret_stack;
 	struct ftrace_graph_ret trace;
 	unsigned long bitmap;
+	unsigned long stack;
 	unsigned long ret;
 	int offset;
 	int bit;
 	int i;
 
-	ret_stack = ftrace_pop_return_trace(&trace, &ret, frame_pointer, &offset);
+	ret_stack = ftrace_pop_return_trace(&trace, &ret, &stack, frame_pointer, &offset);
 
 	if (unlikely(!ret_stack)) {
 		ftrace_graph_stop();
@@ -824,8 +827,11 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
 		return (unsigned long)panic;
 	}
 
-	if (fregs)
-		ftrace_regs_set_instruction_pointer(fregs, trace.func);
+	if (fregs) {
+		ftrace_regs_set_instruction_pointer(fregs, ret);
+		ftrace_regs_set_stack_pointer(fregs, stack + 8);
+	}
+
 
 	bit = ftrace_test_recursion_trylock(trace.func, ret);
 	/*
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
index e1a9b55e07cb..852830536109 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
@@ -74,12 +74,20 @@ static void test_stacktrace_ips_kprobe_multi(bool retprobe)
 
 	load_kallsyms();
 
-	check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 5,
-			     ksym_get_addr("bpf_testmod_stacktrace_test"),
-			     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
-			     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
-			     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
-			     ksym_get_addr("bpf_testmod_test_read"));
+	if (retprobe) {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4,
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	} else {
+		check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 5,
+				     ksym_get_addr("bpf_testmod_stacktrace_test"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+				     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+				     ksym_get_addr("bpf_testmod_test_read"));
+	}
 
 cleanup:
 	stacktrace_ips__destroy(skel);