perf mem: Add 'dtlb' output field

This is a breakdown of perf_mem_data_src.mem_dtlb values.  It assumes
PMU drivers would set PERF_MEM_TLB_HIT bit with an appropriate level.

And having PERF_MEM_TLB_MISS means that it failed to find one in any
levels of TLB.  For now, it doesn't use PERF_MEM_TLB_{WK,OS} bits.

Also it seems Intel machines don't distinguish L1 or L2 precisely.  So I
added ANY_HIT (printed as "L?-Hit") to handle the case.

  $ perf mem report -F overhead,dtlb,dso --stdio
  ...
  #           --- D-TLB ----
  # Overhead   L?-Hit   Miss  Shared Object
  # ........  ..............  .................
  #
      67.03%    99.5%   0.5%  [unknown]
      31.23%    99.2%   0.8%  [kernel.kallsyms]
       1.08%    97.8%   2.2%  [i915]
       0.36%   100.0%   0.0%  [JIT] tid 6853
       0.12%   100.0%   0.0%  [drm]
       0.05%   100.0%   0.0%  [drm_kms_helper]
       0.05%   100.0%   0.0%  [ext4]
       0.02%   100.0%   0.0%  [aesni_intel]
       0.02%   100.0%   0.0%  [crc32c_intel]
       0.02%   100.0%   0.0%  [dm_crypt]
       ...

Committer testing:

  # perf report --header | grep cpudesc
  # cpudesc : AMD Ryzen 9 9950X3D 16-Core Processor
  # perf mem report -F overhead,dtlb,dso --stdio | head -20
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 2K of event 'cycles:P'
  # Total weight : 2637
  # Sort order   : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc
  #
  #           ---------- D-TLB -----------
  # Overhead   L1-Hit L2-Hit   Miss  Other  Shared Object
  # ........  ............................  .................................
  #
      77.47%    18.4%   0.1%   0.6%  80.9%  [kernel.kallsyms]
       5.61%    36.5%   0.7%   1.4%  61.5%  libxul.so
       2.77%    39.7%   0.0%  12.3%  47.9%  libc.so.6
       2.01%    34.0%   1.9%   1.9%  62.3%  libglib-2.0.so.0.8400.1
       1.93%    31.4%   2.0%   2.0%  64.7%  [amdgpu]
       1.63%    48.8%   0.0%   0.0%  51.2%  [JIT] tid 60168
       1.14%     3.3%   0.0%   0.0%  96.7%  [vdso]
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250430205548.789750-12-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 8 insertions, 0 deletions

diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 5b080f506244..d26b925e3d7f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1288,6 +1288,7 @@ __HPP_COLOR_MEM_STAT_FN(op, OP)
 __HPP_COLOR_MEM_STAT_FN(cache, CACHE)
 __HPP_COLOR_MEM_STAT_FN(memory, MEMORY)
 __HPP_COLOR_MEM_STAT_FN(snoop, SNOOP)
+__HPP_COLOR_MEM_STAT_FN(dtlb, DTLB)
 
 #undef __HPP_COLOR_PERCENT_FN
 #undef __HPP_COLOR_ACC_PERCENT_FN
@@ -1319,6 +1320,8 @@ void hist_browser__init_hpp(void)
 				hist_browser__hpp_color_mem_stat_memory;
 	perf_hpp__format[PERF_HPP__MEM_STAT_SNOOP].color =
 				hist_browser__hpp_color_mem_stat_snoop;
+	perf_hpp__format[PERF_HPP__MEM_STAT_DTLB].color =
+				hist_browser__hpp_color_mem_stat_dtlb;
 
 	res_sample_init();
 }
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 94024dfa8dcc..ed5c40ebd906 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -354,6 +354,8 @@ static enum mem_stat_type hpp__mem_stat_type(struct perf_hpp_fmt *fmt)
 		return PERF_MEM_STAT_MEMORY;
 	case PERF_HPP__MEM_STAT_SNOOP:
 		return PERF_MEM_STAT_SNOOP;
+	case PERF_HPP__MEM_STAT_DTLB:
+		return PERF_MEM_STAT_DTLB;
 	default:
 		break;
 	}
@@ -653,6 +655,7 @@ HPP_MEM_STAT_FNS(op, OP)
 HPP_MEM_STAT_FNS(cache, CACHE)
 HPP_MEM_STAT_FNS(memory, MEMORY)
 HPP_MEM_STAT_FNS(snoop, SNOOP)
+HPP_MEM_STAT_FNS(dtlb, DTLB)
 
 static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			    struct hist_entry *a __maybe_unused,
@@ -760,6 +763,7 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__MEM_STAT_PRINT_FNS("Cache", cache, CACHE),
 	HPP__MEM_STAT_PRINT_FNS("Memory", memory, MEMORY),
 	HPP__MEM_STAT_PRINT_FNS("Snoop", snoop, SNOOP),
+	HPP__MEM_STAT_PRINT_FNS("D-TLB", dtlb, DTLB),
 };
 
 struct perf_hpp_list perf_hpp_list = {
@@ -1118,6 +1122,7 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 	case PERF_HPP__MEM_STAT_CACHE:
 	case PERF_HPP__MEM_STAT_MEMORY:
 	case PERF_HPP__MEM_STAT_SNOOP:
+	case PERF_HPP__MEM_STAT_DTLB:
 		fmt->len = MEM_STAT_LEN * MEM_STAT_PRINT_LEN;
 		break;