Merge tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "perf record:

   - Enable leader sampling for inherited task events. It was supported
     only for system-wide events but the kernel started to support such
     a setup since v6.12.

     This is to reduce the number of PMU interrupts. The samples of the
     leader event will contain counts of other events and no samples
     will be generated for the other member events.

       $ perf record -e '{cycles,instructions}:S'  ${MYPROG}

  perf report:

   - Fix --branch-history option to display more branch-related
     information like prediction, abort and cycles which is available
     on Intel machines.

       $ perf record -bg -- perf test -w brstack

       $ perf report --branch-history
       ...
       #
       # Overhead  Source:Line               Symbol          Shared Object         Predicted  Abort  Cycles  IPC   [IPC Coverage]
       # ........  ........................  ..............  ....................  .........  .....  ......  ....................
       #
            8.17%  copy_page_64.S:19         [k] copy_page   [kernel.kallsyms]     50.0%      0      5       -      -
                   |
                   ---xas_load xarray.h:171
                      |
                      |--5.68%--xas_load xarray.c:245 (cycles:1)
                      |          xas_load xarray.c:242
                      |          xas_load xarray.h:1260 (cycles:1)
                      |          xas_descend xarray.c:146
                      |          xas_load xarray.c:244 (cycles:2)
                      |          xas_load xarray.c:245
                      |          xas_descend xarray.c:218 (cycles:10)
       ...

  perf stat:

   - Add HWMON PMU support.

     The HWMON provides various system information like CPU/GPU
     temperature, fan speed and so on. Expose them as PMU events so that
     users can see the values using perf stat commands.

       $ perf stat -e temp_cpu,fan1 true

        Performance counter stats for 'true':

                    60.00 'C   temp_cpu
                        0 rpm  fan1

              0.000745382 seconds time elapsed

              0.000883000 seconds user
              0.000000000 seconds sys

   - Display metric threshold in JSON output.

     Some metrics define thresholds to classify value ranges. It used to
     be in a different color but it won't work for JSON.

     Add "metric-threshold" field to the JSON that can be one of "good",
     "less good", "nearly bad" and "bad".

       # perf stat -a -M TopdownL1 -j true
       {"counter-value" : "18693525.000000", "unit" : "", "event" : "TOPDOWN.SLOTS", "event-runtime" : 5552708, "pcnt-running" : 100.00, "metric-value" : "43.226002", "metric-unit" : "%  tma_backend_bound", "metric-threshold" : "bad"}
       {"metric-value" : "29.212267", "metric-unit" : "%  tma_frontend_bound", "metric-threshold" : "bad"}
       {"metric-value" : "7.138972", "metric-unit" : "%  tma_bad_speculation", "metric-threshold" : "good"}
       {"metric-value" : "20.422759", "metric-unit" : "%  tma_retiring", "metric-threshold" : "good"}
       {"counter-value" : "3817732.000000", "unit" : "", "event" : "topdown-retiring", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "5472824.000000", "unit" : "", "event" : "topdown-fe-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "7984780.000000", "unit" : "", "event" : "topdown-be-bound", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       {"counter-value" : "1418181.000000", "unit" : "", "event" : "topdown-bad-spec", "event-runtime" : 5552708, "pcnt-running" : 100.00, }
       ...

  perf sched:

   - Add -P/--pre-migrations option for 'timehist' sub-command to track
     time a task waited on a run-queue before migrating to a different
     CPU.

       $ perf sched timehist -P
                  time    cpu  task name                       wait time  sch delay   run time  pre-mig time
                               [tid/pid]                          (msec)     (msec)     (msec)     (msec)
       --------------- ------  ------------------------------  ---------  ---------  ---------  ---------
         585940.535527 [0000]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535535 [0000]  migration/0[20]                     0.000      0.002      0.008      0.000
         585940.535559 [0001]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535563 [0001]  migration/1[25]                     0.000      0.001      0.004      0.000
         585940.535678 [0002]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.535686 [0002]  migration/2[31]                     0.000      0.002      0.008      0.000
         585940.535905 [0001]  <idle>                              0.000      0.000      0.342      0.000
         585940.535938 [0003]  perf[584885]                        0.000      0.000      0.000      0.000
         585940.537048 [0001]  sleep[584886]                       0.000      0.019      1.142      0.001
         585940.537749 [0002]  <idle>                              0.000      0.000      2.062      0.000
       ...

  Build:

   - Make libunwind opt-in (LIBUNWIND=1) rather than opt-out.

     The perf tools are generally built with libelf and libdw which has
     unwinder functionality. The libunwind support predates it and no
     need to have duplicate unwinders by default.

   - Rename NO_DWARF=1 build option to NO_LIBDW=1 in order to clarify
     it's using libdw for handling DWARF information.

  Internals:

   - Do not set exclude_guest bit in the perf_event_attr by default.

     This was causing a trouble in AMD IBS PMU as it doesn't support the
     bit. The bit will be set when it's needed later by the fallback
     logic. Also update the missing feature detection logic to make sure
     not clear supported bits unnecessarily.

   - Run perf test in parallel by default and mark flaky tests
     "exclusive" to run them serially at the end. Some test numbers are
     changed but the test can complete in less than half the time.

  JSON vendor events:

   - Add AMD Zen 5 events and metrics.

   - Add i.MX91 and i.MX95 DDR metrics

   - Fix HiSilicon HIP08 Topdown metric name.

   - Support compat events on PowerPC"

* tag 'perf-tools-for-v6.13-2024-11-24' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (232 commits)
  perf tests: Fix hwmon parsing with PMU name test
  perf hwmon_pmu: Ensure hwmon key union is zeroed before use
  perf tests hwmon_pmu: Remove double evlist__delete()
  perf/test: fix perf ftrace test on s390
  perf bpf-filter: Return -ENOMEM directly when pfi allocation fails
  perf test: Correct hwmon test PMU detection
  perf: Remove unused del_perf_probe_events()
  perf pmu: Move pmu_metrics_table__find and remove ARM override
  perf jevents: Add map_for_cpu()
  perf header: Pass a perf_cpu rather than a PMU to get_cpuid_str
  perf header: Avoid transitive PMU includes
  perf arm64 header: Use cpu argument in get_cpuid
  perf header: Refactor get_cpuid to take a CPU for ARM
  perf header: Move is_cpu_online to numa bench
  perf jevents: fix breakage when do perf stat on system metric
  perf test: Add missing __exit calls in tool/hwmon tests
  perf tests: Make leader sampling test work without branch event
  perf util: Remove kernel version deadcode
  perf test shell trace_exit_race: Use --no-comm to avoid cases where COMM isn't resolved
  perf test shell trace_exit_race: Show what went wrong in verbose mode
  ...

9 files changed, 69 insertions, 87 deletions

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 2ebfb826dcea..bca47d136f05 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -30,9 +30,7 @@ endef
 #
 FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
-        dwarf                           \
-        dwarf_getlocations              \
-        dwarf_getcfi                    \
+        libdw                           \
         eventfd                         \
         fortify-source                  \
         get_current_dir_name            \
@@ -61,7 +59,6 @@ FEATURE_TESTS_BASIC :=                  \
         reallocarray                    \
         stackprotector-all              \
         timerfd                         \
-        libdw-dwarf-unwind              \
         zlib                            \
         lzma                            \
         get_cpuid                       \
@@ -121,8 +118,7 @@ ifeq ($(FEATURE_TESTS),all)
 endif
 
 FEATURE_DISPLAY ?=              \
-         dwarf                  \
-         dwarf_getlocations     \
+         libdw                  \
          glibc                  \
          libbfd                 \
          libbfd-buildid		\
@@ -134,7 +130,6 @@ FEATURE_DISPLAY ?=              \
          libpython              \
          libcrypto              \
          libunwind              \
-         libdw-dwarf-unwind     \
          libcapstone            \
          llvm-perf              \
          zlib                   \
@@ -234,7 +229,7 @@ endef
 
 #
 # generates feature value assignment for name, like:
-#   $(call feature_assign,dwarf) == feature-dwarf=1
+#   $(call feature_assign,libdw) == feature-libdw=1
 #
 feature_assign = feature-$(1)=$(feature-$(1))
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 28cdfb11a755..043dfd00fce7 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -5,9 +5,7 @@ FILES=                                          \
          test-all.bin                           \
          test-backtrace.bin                     \
          test-bionic.bin                        \
-         test-dwarf.bin                         \
-         test-dwarf_getlocations.bin            \
-         test-dwarf_getcfi.bin                  \
+         test-libdw.bin                         \
          test-eventfd.bin                       \
          test-fortify-source.bin                \
          test-get_current_dir_name.bin          \
@@ -53,7 +51,6 @@ FILES=                                          \
          test-pthread-barrier.bin		\
          test-stackprotector-all.bin            \
          test-timerfd.bin                       \
-         test-libdw-dwarf-unwind.bin            \
          test-libbabeltrace.bin                 \
          test-libcapstone.bin			\
          test-compile-32.bin                    \
@@ -169,9 +166,9 @@ $(OUTPUT)test-libopencsd.bin:
 	$(BUILD) # -lopencsd_c_api -lopencsd provided by
 		 # $(FEATURE_CHECK_LDFLAGS-libopencsd)
 
-DWARFLIBS := -ldw
+DWLIBS := -ldw
 ifeq ($(findstring -static,${LDFLAGS}),-static)
-  DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd
+  DWLIBS += -lelf -lz -llzma -lbz2 -lzstd
 
   LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0
   LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION)))
@@ -180,21 +177,15 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
   # Elfutils merged libebl.a into libdw.a starting from version 0.177,
   # Link libebl.a only if libdw is older than this version.
   ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0)
-    DWARFLIBS += -lebl
+    DWLIBS += -lebl
   endif
 
   # Must put -ldl after -lebl for dependency
   DWARFLIBS += -ldl
 endif
 
-$(OUTPUT)test-dwarf.bin:
-	$(BUILD) $(DWARFLIBS)
-
-$(OUTPUT)test-dwarf_getlocations.bin:
-	$(BUILD) $(DWARFLIBS)
-
-$(OUTPUT)test-dwarf_getcfi.bin:
-	$(BUILD) $(DWARFLIBS)
+$(OUTPUT)test-libdw.bin:
+	$(BUILD) $(DWLIBS)
 
 $(OUTPUT)test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
@@ -321,9 +312,6 @@ $(OUTPUT)test-backtrace.bin:
 $(OUTPUT)test-timerfd.bin:
 	$(BUILD)
 
-$(OUTPUT)test-libdw-dwarf-unwind.bin:
-	$(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind)
-
 $(OUTPUT)test-libbabeltrace.bin:
 	$(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 6f4bf386a3b5..59ef3d7fe6a4 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -38,12 +38,8 @@
 # include "test-glibc.c"
 #undef main
 
-#define main main_test_dwarf
-# include "test-dwarf.c"
-#undef main
-
-#define main main_test_dwarf_getlocations
-# include "test-dwarf_getlocations.c"
+#define main main_test_libdw
+# include "test-libdw.c"
 #undef main
 
 #define main main_test_eventfd
@@ -98,10 +94,6 @@
 # include "test-stackprotector-all.c"
 #undef main
 
-#define main main_test_libdw_dwarf_unwind
-# include "test-libdw-dwarf-unwind.c"
-#undef main
-
 #define main main_test_zlib
 # include "test-zlib.c"
 #undef main
@@ -187,8 +179,7 @@ int main(int argc, char *argv[])
 	main_test_get_current_dir_name();
 	main_test_gettid();
 	main_test_glibc();
-	main_test_dwarf();
-	main_test_dwarf_getlocations();
+	main_test_libdw();
 	main_test_eventfd();
 	main_test_libelf_getphdrnum();
 	main_test_libelf_gelf_getnote();
@@ -202,7 +193,6 @@ int main(int argc, char *argv[])
 	main_test_numa_num_possible_cpus();
 	main_test_timerfd();
 	main_test_stackprotector_all();
-	main_test_libdw_dwarf_unwind();
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
 	main_test_pthread_barrier();
diff --git a/tools/build/feature/test-dwarf.c b/tools/build/feature/test-dwarf.c
deleted file mode 100644
index 8d474bd7371b..000000000000
--- a/tools/build/feature/test-dwarf.c
+++ /dev/null
@@ -1,11 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <dwarf.h>
-#include <elfutils/libdw.h>
-#include <elfutils/version.h>
-
-int main(void)
-{
-	Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
-
-	return (long)dbg;
-}
diff --git a/tools/build/feature/test-dwarf_getcfi.c b/tools/build/feature/test-dwarf_getcfi.c
deleted file mode 100644
index 50e7d7cb7bdf..000000000000
--- a/tools/build/feature/test-dwarf_getcfi.c
+++ /dev/null
@@ -1,9 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include <elfutils/libdw.h>
-
-int main(void)
-{
-	Dwarf *dwarf = NULL;
-	return dwarf_getcfi(dwarf) == NULL;
-}
diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c
deleted file mode 100644
index 78fb4a1fa68c..000000000000
--- a/tools/build/feature/test-dwarf_getlocations.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdlib.h>
-#include <elfutils/libdw.h>
-
-int main(void)
-{
-	Dwarf_Addr base, start, end;
-	Dwarf_Attribute attr;
-	Dwarf_Op *op;
-        size_t nops;
-	ptrdiff_t offset = 0;
-        return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
-}
diff --git a/tools/build/feature/test-libdw-dwarf-unwind.c b/tools/build/feature/test-libdw-dwarf-unwind.c
deleted file mode 100644
index ed03d9505609..000000000000
--- a/tools/build/feature/test-libdw-dwarf-unwind.c
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <elfutils/libdwfl.h>
-
-int main(void)
-{
-	/*
-	 * This function is guarded via: __nonnull_attribute__ (1, 2).
-	 * Passing '1' as arguments value. This code is never executed,
-	 * only compiled.
-	 */
-	dwfl_thread_getframes((void *) 1, (void *) 1, NULL);
-	return 0;
-}
diff --git a/tools/build/feature/test-libdw.c b/tools/build/feature/test-libdw.c
new file mode 100644
index 000000000000..2fb59479ab77
--- /dev/null
+++ b/tools/build/feature/test-libdw.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <elfutils/version.h>
+
+int test_libdw(void)
+{
+	Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
+
+	return (long)dbg;
+}
+
+int test_libdw_unwind(void)
+{
+	/*
+	 * This function is guarded via: __nonnull_attribute__ (1, 2).
+	 * Passing '1' as arguments value. This code is never executed,
+	 * only compiled.
+	 */
+	dwfl_thread_getframes((void *) 1, (void *) 1, NULL);
+	return 0;
+}
+
+int test_libdw_getlocations(void)
+{
+	Dwarf_Addr base, start, end;
+	Dwarf_Attribute attr;
+	Dwarf_Op *op;
+	size_t nops;
+	ptrdiff_t offset = 0;
+
+	return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops);
+}
+
+int test_libdw_getcfi(void)
+{
+	Dwarf *dwarf = NULL;
+
+	return dwarf_getcfi(dwarf) == NULL;
+}
+
+int test_elfutils(void)
+{
+	Dwarf_CFI *cfi = NULL;
+
+	dwarf_cfi_end(cfi);
+	return 0;
+}
+
+int main(void)
+{
+	return test_libdw() + test_libdw_unwind() + test_libdw_getlocations() +
+	       test_libdw_getcfi() + test_elfutils();
+}
diff --git a/tools/build/feature/test-libtraceevent.c b/tools/build/feature/test-libtraceevent.c
index 416b11ffd4b4..804ad80dbbd9 100644
--- a/tools/build/feature/test-libtraceevent.c
+++ b/tools/build/feature/test-libtraceevent.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <traceevent/trace-seq.h>
+#include <trace-seq.h>
 
 int main(void)
 {