Merge tag 'perf-tools-for-v6.14-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf-tools updates from Namhyung Kim:
 "There are a lot of changes in the perf tools in this cycle.

  build:

   - Use generic syscall table to generate syscall numbers on supported
     archs

   - This also enables to get rid of libaudit which was used for syscall
     numbers

   - Remove python2 support as it's deprecated for years

   - Fix issues on static build with libzstd

  perf record:

   - Intel-PT supports "aux-action" config term to pause or resume
     tracing in the aux-buffer. Users can start the intel_pt event as
     "started-paused" and configure other events to control the Intel-PT
     tracing:

         # perf record --kcore -e intel_pt/aux-action=start-paused/   \
             -e syscalls:sys_enter_newuname/aux-action=resume/        \
             -e syscalls:sys_exit_newuname/aux-action=pause/ -- uname

     This requires kernel support (which was added in v6.13)

  perf lock:

   - 'perf lock contention' command has an ability to symbolize locks in
     dynamically allocated objects using slab cache name when it runs
     with BPF. Those dynamic locks would have "&" prefix in the name to
     distinguish them from ordinary (static) locks

        # perf lock con -abl -E 5 sleep 1
           contended   total wait     max wait     avg wait            address   symbol

                   2      1.95 us      1.77 us       975 ns   ffff9d5e852d3498   &task_struct (mutex)
                   1      1.18 us      1.18 us      1.18 us   ffff9d5e852d3538   &task_struct (mutex)
                   4      1.12 us       354 ns       279 ns   ffff9d5e841ca800   &kmalloc-cg-512 (mutex)
                   2       859 ns       617 ns       429 ns   ffffffffa41c3620   delayed_uprobe_lock (mutex)
                   3       691 ns       388 ns       230 ns   ffffffffa41c0940   pack_mutex (mutex)

     This also requires kernel/BPF support (which was added in v6.13)

  perf ftrace:

   - 'perf ftrace latency' command gets a couple of options to support
     linear buckets instead of exponential. Also it's possible to
     specify max and min latency for the linear buckets:

        # perf ftrace latency -abn -T switch_mm_irqs_off --bucket-range=100   \
            --min-latency=200 --max-latency=800 -- sleep 1
        #   DURATION     |      COUNT | GRAPH                                  |
             0 -  200 ns |        186 | ###                                    |
           200 -  300 ns |        256 | #####                                  |
           300 -  400 ns |        364 | #######                                |
           400 -  500 ns |        223 | ####                                   |
           500 -  600 ns |        111 | ##                                     |
           600 -  700 ns |         41 |                                        |
           700 -  800 ns |        141 | ##                                     |
           800 -  ... ns |        169 | ###                                    |

        # statistics  (in nsec)
          total time:              2162212
            avg time:                  967
            max time:                16817
            min time:                  132
               count:                 2236

   - As you can see in the above example, it nows shows the statistics
     at the end so that users can see the avg/max/min latencies easily

   - 'perf ftrace profile' command has --graph-opts option like 'perf
     ftrace trace' so that it can control the tracing behaviors in the
     same way. For example, it can limit the function call depth or
     threshold

  perf script:

   - Improve physical memory resolution in 'mem-phys-addr' script by
     parsing /proc/iomem file

        # perf script mem-phys-addr -- find /
        ...
        Event: mem_inst_retired.all_loads:P
        Memory type                                    count  percentage
        ----------------------------------------  ----------  ----------
        100000000-85f7fffff : System RAM                8929        69.7
          547600000-54785d23f : Kernel data             1240         9.7
          546a00000-5474bdfff : Kernel rodata            490         3.8
          5480ce000-5485fffff : Kernel bss               121         0.9
        0-fff : Reserved                                3860        30.1
        100000-89c01fff : System RAM                      18         0.1
        8a22c000-8df6efff : System RAM                     5         0.0

  Others:

   - 'perf test' gets --runs-per-test option to run the test cases
     repeatedly. This would be helpful to see if it's flaky

   - Add 'parse_events' method to Python perf extension module, so that
     users can use the same event parsing logic in the python code. One
     more step towards implementing perf tools in Python. :)

   - Support opening tracepoint events without libtraceevent. This will
     be helpful if it won't use the tracing data like in 'perf stat'

   - Update ARM Neoverse N2/V2 JSON events and metrics"

* tag 'perf-tools-for-v6.14-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (176 commits)
  perf test: Update event_groups test to use instructions
  perf bench: Fix undefined behavior in cmpworker()
  perf annotate: Prefer passing evsel to evsel->core.idx
  perf lock: Rename fields in lock_type_table
  perf lock: Add percpu-rwsem for type filter
  perf lock: Fix parse_lock_type which only retrieve one lock flag
  perf lock: Fix return code for functions in __cmd_contention
  perf hist: Fix width calculation in hpp__fmt()
  perf hist: Fix bogus profiles when filters are enabled
  perf hist: Deduplicate cmp/sort/collapse code
  perf test: Improve verbose documentation
  perf test: Add a runs-per-test flag
  perf test: Fix parallel/sequential option documentation
  perf test: Send list output to stdout rather than stderr
  perf test: Rename functions and variables for better clarity
  perf tools: Expose quiet/verbose variables in Makefile.perf
  perf config: Add a function to set one variable in .perfconfig
  perf test perftool_testsuite: Return correct value for skipping
  perf test perftool_testsuite: Add missing description
  perf test record+probe_libc_inet_pton: Make test resilient
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-bus-event_source-devices

@@ -0,0 +1,24 @@
+What: /sys/bus/event_source/devices/<pmu>
+Date: 2014/02/24
+Contact:	Linux kernel mailing list <[email protected]>
+Description:	Performance Monitoring Unit (<pmu>)
+
+		Each <pmu> directory, for a PMU device, is a name
+		optionally followed by an underscore and then either a
+		decimal or hexadecimal number. For example, cpu is a
+		PMU name without a suffix as is intel_bts,
+		uncore_imc_0 is a PMU name with a 0 numeric suffix,
+		ddr_pmu_87e1b0000000 is a PMU name with a hex
+		suffix. The hex suffix must be more than two
+		characters long to avoid ambiguity with PMUs like the
+		S390 cpum_cf.
+
+		Tools can treat PMUs with the same name that differ by
+		suffix as instances of the same PMU for the sake of,
+		for example, opening an event. For example, the PMUs
+		uncore_imc_free_running_0 and
+		uncore_imc_free_running_1 have an event data_read;
+		opening the data_read event on a PMU specified as
+		uncore_imc_free_running should be treated as opening
+		the data_read event on PMU uncore_imc_free_running_0
+		and PMU uncore_imc_free_running_1.

Documentation/ABI/testing/sysfs-bus-event_source-devices-events

@@ -37,11 +37,13 @@ Description:	Per-pmu performance monitoring events specific to the running syste
 		performance monitoring event supported by the <pmu>. The name
 		of the file is the name of the event.
 
-		As performance monitoring event names are case
-		insensitive in the perf tool, the perf tool only looks
-		for lower or upper case event names in sysfs to avoid
+		As performance monitoring event names are case insensitive
+		in the perf tool, the perf tool only looks for all lower
+		case or all upper case event names in sysfs to avoid
 		scanning the directory. It is therefore required the
-		name of the event here is either lower or upper case.
+		name of the event here is either completely lower or upper
+		case, with no mixed-case characters. Numbers, '.', '_', and
+		'-' are also allowed.
 
 		File contents:
 

Documentation/admin-guide/workload-tracing.rst

@@ -83,7 +83,7 @@ scripts/ver_linux is a good way to check if your system already has
 the necessary tools::
 
   sudo apt-get build-essentials flex bison yacc
-  sudo apt install libelf-dev systemtap-sdt-dev libaudit-dev libslang2-dev libperl-dev libdw-dev
+  sudo apt install libelf-dev systemtap-sdt-dev libslang2-dev libperl-dev libdw-dev
 
 cscope is a good tool to browse kernel sources. Let's install it now::
 

tools/bpf/bpftool/Makefile

@@ -106,6 +106,7 @@ FEATURE_TESTS += libbfd-liberty
 FEATURE_TESTS += libbfd-liberty-z
 FEATURE_TESTS += disassembler-four-args
 FEATURE_TESTS += disassembler-init-styled
+FEATURE_TESTS += libelf-zstd
 
 FEATURE_DISPLAY := clang-bpf-co-re
 FEATURE_DISPLAY += llvm
@@ -132,6 +133,12 @@ endif
 
 LIBS = $(LIBBPF) -lelf -lz
 LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz
+
+ifeq ($(feature-libelf-zstd),1)
+LIBS += -lzstd
+LIBS_BOOTSTRAP += -lzstd
+endif
+
 ifeq ($(feature-libcap), 1)
 CFLAGS += -DUSE_LIBCAP
 LIBS += -lcap

tools/build/Build.include

@@ -13,6 +13,8 @@
 comma   := ,
 squote  := '
 pound   := \#
+empty   :=
+space   := $(empty) $(empty)
 
 ###
 # Name of target with a '.' as filename prefix. foo/bar.o => foo/.bar.o

tools/build/Makefile.build

@@ -12,26 +12,6 @@
 PHONY := __build
 __build:
 
-ifeq ($(V),1)
-  quiet =
-  Q =
-else
-  quiet=quiet_
-  Q=@
-endif
-
-# If the user is running make -s (silent mode), suppress echoing of commands
-# make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS.
-ifeq ($(filter 3.%,$(MAKE_VERSION)),)
-short-opts := $(firstword -$(MAKEFLAGS))
-else
-short-opts := $(filter-out --%,$(MAKEFLAGS))
-endif
-
-ifneq ($(findstring s,$(short-opts)),)
-  quiet=silent_
-endif
-
 build-dir := $(srctree)/tools/build
 
 # Define $(fixdep) for dep-cmd function

tools/build/Makefile.feature

@@ -28,6 +28,41 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
+# These + the ones in FEATURE_TESTS_EXTRA are included in
+# tools/build/feature/test-all.c and we try to build it all together
+# then setting all those features to '1' meaning they are all enabled.
+#
+# There are things like fortify-source that will be set to 1 because test-all
+# is built with the flags needed to test if its enabled, resulting in
+#
+#   $ rm -rf /tmp/b ; mkdir /tmp/b ; make -C tools/perf O=/tmp/b feature-dump
+#   $ grep fortify-source /tmp/b/FEATURE-DUMP
+#   feature-fortify-source=1
+#   $
+#
+#   All the others should have lines in tools/build/feature/test-all.c like:
+#
+#    #define main main_test_disassembler_init_styled
+#    # include "test-disassembler-init-styled.c"
+#    #undef main
+#
+#    #define main main_test_libzstd
+#    # include "test-libzstd.c"
+#    #undef main
+#
+#    int main(int argc, char *argv[])
+#    {
+#      main_test_disassembler_four_args();
+#      main_test_libzstd();
+#      return 0;
+#    }
+#
+#    If the sample above works, then we end up with these lines in the FEATURE-DUMP
+#    file:
+#
+#    feature-disassembler-four-args=1
+#    feature-libzstd=1
+#
 FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         libdw                           \
@@ -38,17 +73,16 @@ FEATURE_TESTS_BASIC :=                  \
         glibc                           \
         libbfd                          \
         libbfd-buildid			\
-        libcap                          \
         libelf                          \
         libelf-getphdrnum               \
         libelf-gelf_getnote             \
         libelf-getshdrstrndx            \
+        libelf-zstd                     \
         libnuma                         \
         numa_num_possible_cpus          \
         libperl                         \
         libpython                       \
         libslang                        \
-        libslang-include-subdir         \
         libtraceevent                   \
         libtracefs                      \
         libcpupower                     \
@@ -89,13 +123,6 @@ FEATURE_TESTS_EXTRA :=                  \
          libbfd-liberty                 \
          libbfd-liberty-z               \
          libopencsd                     \
-         libunwind-x86                  \
-         libunwind-x86_64               \
-         libunwind-arm                  \
-         libunwind-aarch64              \
-         libunwind-debug-frame          \
-         libunwind-debug-frame-arm      \
-         libunwind-debug-frame-aarch64  \
          cxx                            \
          llvm                           \
          clang                          \
@@ -122,7 +149,6 @@ FEATURE_DISPLAY ?=              \
          glibc                  \
          libbfd                 \
          libbfd-buildid		\
-         libcap                 \
          libelf                 \
          libnuma                \
          numa_num_possible_cpus \

tools/build/feature/Makefile

@@ -13,7 +13,6 @@ FILES=                                          \
          test-gtk2.bin                          \
          test-gtk2-infobar.bin                  \
          test-hello.bin                         \
-         test-libaudit.bin                      \
          test-libbfd.bin                        \
          test-libbfd-buildid.bin		\
          test-disassembler-four-args.bin        \
@@ -28,6 +27,7 @@ FILES=                                          \
          test-libelf-getphdrnum.bin             \
          test-libelf-gelf_getnote.bin           \
          test-libelf-getshdrstrndx.bin          \
+         test-libelf-zstd.bin                   \
          test-libdebuginfod.bin                 \
          test-libnuma.bin                       \
          test-numa_num_possible_cpus.bin        \
@@ -110,7 +110,7 @@ all: $(FILES)
 __BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
   BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1
   BUILD_BFD = $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
-  BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap
+  BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd
 
 __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS)
   BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1
@@ -196,6 +196,9 @@ $(OUTPUT)test-libelf-gelf_getnote.bin:
 $(OUTPUT)test-libelf-getshdrstrndx.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-libelf-zstd.bin:
+	$(BUILD) -lelf -lz -lzstd
+
 $(OUTPUT)test-libdebuginfod.bin:
 	$(BUILD) -ldebuginfod
 
@@ -228,9 +231,6 @@ $(OUTPUT)test-libunwind-debug-frame-arm.bin:
 $(OUTPUT)test-libunwind-debug-frame-aarch64.bin:
 	$(BUILD) -lelf -llzma -lunwind-aarch64
 
-$(OUTPUT)test-libaudit.bin:
-	$(BUILD) -laudit
-
 $(OUTPUT)test-libslang.bin:
 	$(BUILD) -lslang
 

tools/build/feature/test-all.c

@@ -58,8 +58,8 @@
 # include "test-libelf-getshdrstrndx.c"
 #undef main
 
-#define main main_test_libunwind
-# include "test-libunwind.c"
+#define main main_test_libelf_zstd
+# include "test-libelf-zstd.c"
 #undef main
 
 #define main main_test_libslang
@@ -170,6 +170,14 @@
 # include "test-libzstd.c"
 #undef main
 
+#define main main_test_libtraceevent
+# include "test-libtraceevent.c"
+#undef main
+
+#define main main_test_libtracefs
+# include "test-libtracefs.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -184,7 +192,6 @@ int main(int argc, char *argv[])
 	main_test_libelf_getphdrnum();
 	main_test_libelf_gelf_getnote();
 	main_test_libelf_getshdrstrndx();
-	main_test_libunwind();
 	main_test_libslang();
 	main_test_libbfd();
 	main_test_libbfd_buildid();
@@ -208,6 +215,8 @@ int main(int argc, char *argv[])
 	main_test_reallocarray();
 	main_test_disassembler_four_args();
 	main_test_libzstd();
+	main_test_libtraceevent();
+	main_test_libtracefs();
 
 	return 0;
 }