perf annotate: Add --code-with-type option.

This option is to show data type info in the regular (code) annotation.
It tries to find data type for each (memory) instruction in the
function.  It'd be useful to see function-level memory access pattern
and also to debug the data type profiling result.

The output would be added at the end of the line and have "# data-type:"
prefix.

For now, it only works with --stdio mode for simplicity.  I can work on
enabling it for TUI later.

  $ perf annotate --stdio --code-with-type
   Percent |      Source code & Disassembly of vmlinux for cpu/mem-loads/ppk (253 samples, percent: local period)
  ---------------------------------------------------------------------------------------------------------------
           : 0                0xffffffff81baa000 <check_preemption_disabled>:
      0.00 :   ffffffff81baa000:        pushq   %r12              # data-type: (stack operation)
      0.00 :   ffffffff81baa002:        pushq   %rbp              # data-type: (stack operation)
      0.00 :   ffffffff81baa003:        pushq   %rbx              # data-type: (stack operation)
      0.00 :   ffffffff81baa004:        subq    $0x8, %rsp
     18.00 :   ffffffff81baa008:        movl    %gs:0x7e48893d(%rip), %ebx  # 0x3294c <pcpu_hot+0xc>              # data-type: struct pcpu_hot +0xc (cpu_number)
     12.58 :   ffffffff81baa00f:        movl    %gs:0x7e488932(%rip), %eax  # 0x32948 <pcpu_hot+0x8>              # data-type: struct pcpu_hot +0x8 (preempt_count)
      0.00 :   ffffffff81baa016:        testl   $0x7fffffff, %eax
      0.00 :   ffffffff81baa01b:        je      0xffffffff81baa02c <check_preemption_disabled+0x2c>
      0.00 :   ffffffff81baa01d:        addq    $0x8, %rsp
      0.00 :   ffffffff81baa021:        movl    %ebx, %eax
     14.19 :   ffffffff81baa023:        popq    %rbx              # data-type: (stack operation)
     18.86 :   ffffffff81baa024:        popq    %rbp              # data-type: (stack operation)
     12.10 :   ffffffff81baa025:        popq    %r12              # data-type: (stack operation)
     17.78 :   ffffffff81baa027:        jmp     0xffffffff81bc1170 <__x86_return_thunk>
      6.49 :   ffffffff81baa02c:        callq   *0xc9139e(%rip)  # 0xffffffff8283b3d0 <pv_ops+0xf0>               # data-type: (stack operation)
      0.00 :   ffffffff81baa032:        testb   $0x2, %ah
      0.00 :   ffffffff81baa035:        je      0xffffffff81baa01d <check_preemption_disabled+0x1d>
      0.00 :   ffffffff81baa037:        movq    %rdi, %rbp
      0.00 :   ffffffff81baa03a:        movq    %gs:0x32940, %rax         # data-type: struct pcpu_hot +0 (current_task)
      0.00 :   ffffffff81baa043:        testb   $0x4, 0x2f(%rax)          # data-type: struct task_struct +0x2f (flags)
      0.00 :   ffffffff81baa047:        je      0xffffffff81baa052 <check_preemption_disabled+0x52>
      0.00 :   ffffffff81baa049:        cmpl    $0x1, 0x3d0(%rax)         # data-type: struct task_struct +0x3d0 (nr_cpus_allowed)
      0.00 :   ffffffff81baa050:        je      0xffffffff81baa01d <check_preemption_disabled+0x1d>
      0.00 :   ffffffff81baa052:        movq    %gs:0x32940, %r12         # data-type: struct pcpu_hot +0 (current_task)
      0.00 :   ffffffff81baa05b:        cmpw    $0x0, 0x7f0(%r12)         # data-type: struct task_struct +0x7f0 (migration_disabled)
      0.00 :   ffffffff81baa065:        movq    %rsi, (%rsp)
      0.00 :   ffffffff81baa069:        jne     0xffffffff81baa01d <check_preemption_disabled+0x1d>
      0.00 :   ffffffff81baa06b:        movl    0xe8dd13(%rip), %eax  # 0xffffffff82a37d84 <system_state>         # data-type: enum system_states +0
      0.00 :   ffffffff81baa071:        testl   %eax, %eax
      0.00 :   ffffffff81baa073:        je      0xffffffff81baa01d <check_preemption_disabled+0x1d>
      0.00 :   ffffffff81baa075:        incl    %gs:0x7e4888cc(%rip)  # 0x32948 <pcpu_hot+0x8>            # data-type: struct pcpu_hot +0x8 (preempt_count)
      0.00 :   ffffffff81baa07c:        movq    $-0x7e14a100, %rdi
      0.00 :   ffffffff81baa083:        callq   0xffffffff81148c40 <__printk_ratelimit>           # data-type: (stack operation)
      0.00 :   ffffffff81baa088:        testl   %eax, %eax
      0.00 :   ffffffff81baa08a:        je      0xffffffff81baa0d5 <check_preemption_disabled+0xd5>
      0.00 :   ffffffff81baa08c:        movl    0x958(%r12), %r9d         # data-type: struct task_struct +0x958 (pid)
      0.00 :   ffffffff81baa094:        movq    (%rsp), %rdx              # data-type: char* +0
      0.00 :   ffffffff81baa098:        movq    %rbp, %rsi
      0.00 :   ffffffff81baa09b:        leaq    0xb88(%r12), %r8          # data-type: struct task_struct +0xb88 (comm)
      0.00 :   ffffffff81baa0a3:        movl    %gs:0x7e48889e(%rip), %ecx  # 0x32948 <pcpu_hot+0x8>              # data-type: struct pcpu_hot +0x8 (preempt_count)
      0.00 :   ffffffff81baa0aa:        andl    $0x7fffffff, %ecx
      0.00 :   ffffffff81baa0b0:        movq    $-0x7dd3cdf0, %rdi
      0.00 :   ffffffff81baa0b7:        subl    $0x1, %ecx
      0.00 :   ffffffff81baa0ba:        callq   0xffffffff81149340 <_printk>              # data-type: (stack operation)
      0.00 :   ffffffff81baa0bf:        movq    0x20(%rsp), %rsi
      0.00 :   ffffffff81baa0c4:        movq    $-0x7ddb8c7e, %rdi
      0.00 :   ffffffff81baa0cb:        callq   0xffffffff81149340 <_printk>              # data-type: (stack operation)
      0.00 :   ffffffff81baa0d0:        callq   0xffffffff81b7ab60 <dump_stack>           # data-type: (stack operation)
      0.00 :   ffffffff81baa0d5:        decl    %gs:0x7e48886c(%rip)  # 0x32948 <pcpu_hot+0x8>            # data-type: struct pcpu_hot +0x8 (preempt_count)
      0.00 :   ffffffff81baa0dc:        jmp     0xffffffff81baa01d <check_preemption_disabled+0x1d>

Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250310224925.799005-8-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

2 files changed, 13 insertions, 0 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 156c5f37b051..46090c5b42b4 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -168,6 +168,10 @@ include::itrace.txt[]
 --skip-empty::
 	Do not display empty (or dummy) events.
 
+--code-with-type::
+	Show data type info in code annotation (for memory instructions only).
+	Currently it only works with --stdio option.
+
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 966950c38306..9833c2c82a2f 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -788,6 +788,8 @@ int cmd_annotate(int argc, const char **argv)
 		    "Show instruction stats for the data type annotation"),
 	OPT_BOOLEAN(0, "skip-empty", &symbol_conf.skip_empty,
 		    "Do not display empty (or dummy) events in the output"),
+	OPT_BOOLEAN(0, "code-with-type", &annotate_opts.code_with_type,
+		    "Show data type info in code annotation (memory instructions only)"),
 	OPT_END()
 	};
 	int ret;
@@ -913,6 +915,13 @@ int cmd_annotate(int argc, const char **argv)
 		annotate_opts.annotate_src = false;
 		symbol_conf.annotate_data_member = true;
 		symbol_conf.annotate_data_sample = true;
+	} else if (annotate_opts.code_with_type) {
+		symbol_conf.annotate_data_member = true;
+
+		if (!annotate.use_stdio) {
+			pr_err("--code-with-type only works with --stdio.\n");
+			goto out_delete;
+		}
 	}
 
 	setup_browser(true);