Merge tag 'perf-tools-for-v6.8-1-2024-01-09' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "Add Namhyung Kim as tools/perf/ co-maintainer, we're taking turns
  processing patches, switching roles from perf-tools to perf-tools-next
  at each Linux release.

  Data profiling:

   - Associate samples that identify loads and stores with data
     structures. This uses events available on Intel, AMD and others and
     DWARF info:

       # To get memory access samples in kernel for 1 second (on Intel)
       $ perf mem record -a -K --ldlat=4 -- sleep 1

       # Similar for the AMD (but it requires 6.3+ kernel for BPF filters)
       $ perf mem record -a --filter 'mem_op == load || mem_op == store, ip > 0x8000000000000000' -- sleep 1

     Then, amongst several modes of post processing, one can do things like:

       $ perf report -s type,typeoff --hierarchy --group --stdio
       ...
       #
       # Samples: 10K of events 'cpu/mem-loads,ldlat=4/P, cpu/mem-stores/P, dummy:u'
       # Event count (approx.): 602758064
       #
       #                    Overhead  Data Type / Data Type Offset
       # ...........................  ............................
       #
           26.09%   3.28%   0.00%     long unsigned int
              26.09%   3.28%   0.00%     long unsigned int +0 (no field)
           18.48%   0.73%   0.00%     struct page
              10.83%   0.02%   0.00%     struct page +8 (lru.next)
               3.90%   0.28%   0.00%     struct page +0 (flags)
               3.45%   0.06%   0.00%     struct page +24 (mapping)
               0.25%   0.28%   0.00%     struct page +48 (_mapcount.counter)
               0.02%   0.06%   0.00%     struct page +32 (index)
               0.02%   0.00%   0.00%     struct page +52 (_refcount.counter)
               0.02%   0.01%   0.00%     struct page +56 (memcg_data)
               0.00%   0.01%   0.00%     struct page +16 (lru.prev)
           15.37%  17.54%   0.00%     (stack operation)
              15.37%  17.54%   0.00%     (stack operation) +0 (no field)
           11.71%  50.27%   0.00%     (unknown)
              11.71%  50.27%   0.00%     (unknown) +0 (no field)

       $ perf annotate --data-type
       ...
       Annotate type: 'struct cfs_rq' in [kernel.kallsyms] (13 samples):
       ============================================================================
           samples     offset       size  field
                13          0        640  struct cfs_rq         {
                 2          0         16      struct load_weight       load {
                 2          0          8          unsigned long        weight;
                 0          8          4          u32  inv_weight;
                                              };
                 0         16          8      unsigned long    runnable_weight;
                 0         24          4      unsigned int     nr_running;
                 1         28          4      unsigned int     h_nr_running;
       ...

       $ perf annotate --data-type=page --group
       Annotate type: 'struct page' in [kernel.kallsyms] (480 samples):
        event[0] = cpu/mem-loads,ldlat=4/P
        event[1] = cpu/mem-stores/P
        event[2] = dummy:u
       ===================================================================================
                samples  offset  size  field
       447  33        0       0    64  struct page     {
       108   8        0       0     8	 long unsigned int  flags;
       319  13        0       8    40	 union       {
       319  13        0       8    40          struct          {
       236   2        0       8    16              union       {
       236   2        0       8    16                  struct list_head       lru {
       236   1        0       8     8                      struct list_head*  next;
         0   1        0      16     8                      struct list_head*  prev;
                                                       };
       236   2        0       8    16                  struct          {
       236   1        0       8     8                      void*      __filler;
         0   1        0      16     4                      unsigned int       mlock_count;
                                                       };
       236   2        0       8    16                  struct list_head       buddy_list {
       236   1        0       8     8                      struct list_head*  next;
         0   1        0      16     8                      struct list_head*  prev;
                                                       };
       236   2        0       8    16                  struct list_head       pcp_list {
       236   1        0       8     8                      struct list_head*  next;
         0   1        0      16     8                      struct list_head*  prev;
                                                       };
                                                   };
        82   4        0      24     8              struct address_space*      mapping;
         1   7        0      32     8              union       {
         1   7        0      32     8                  long unsigned int      index;
         1   7        0      32     8                  long unsigned int      share;
                                                   };
         0   0        0      40     8              long unsigned int  private;
                                                                 };

     This uses the existing annotate code, calling objdump to do the
     disassembly, with improvements to avoid having this take too long,
     but longer term a switch to a disassembler library, possibly
     reusing code in the kernel will be pursued.

     This is the initial implementation, please use it and report
     impressions and bugs. Make sure the kernel-debuginfo packages match
     the running kernel. The 'perf report' phase for non short perf.data
     files may take a while.

     There is a great article about it on LWN:

       https://lwn.net/Articles/955709/ - "Data-type profiling for perf"

     One last test I did while writing this text, on a AMD Ryzen 5950X,
     using a distro kernel, while doing a simple 'find /' on an
     otherwise idle system resulted in:

     # uname -r
     6.6.9-100.fc38.x86_64
     # perf -vv | grep BPF_
                      bpf: [ on  ]  # HAVE_LIBBPF_SUPPORT
            bpf_skeletons: [ on  ]  # HAVE_BPF_SKEL
     # rpm -qa | grep kernel-debuginfo
     kernel-debuginfo-common-x86_64-6.6.9-100.fc38.x86_64
     kernel-debuginfo-6.6.9-100.fc38.x86_64
     #
     # perf mem record -a --filter 'mem_op == load || mem_op == store, ip > 0x8000000000000000'
     ^C[ perf record: Woken up 1 times to write data ]
     [ perf record: Captured and wrote 2.199 MB perf.data (2913 samples) ]
     #
     # ls -la perf.data
     -rw-------. 1 root root 2346486 Jan  9 18:36 perf.data
     # perf evlist
     ibs_op//
     dummy:u
     # perf evlist -v
     ibs_op//: type: 11, size: 136, config: 0, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CPU|PERIOD|IDENTIFIER|DATA_SRC|WEIGHT, read_format: ID, disabled: 1, inherit: 1, freq: 1, sample_id_all: 1
     dummy:u: type: 1 (PERF_TYPE_SOFTWARE), size: 136, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|ADDR|CPU|IDENTIFIER|DATA_SRC|WEIGHT, read_format: ID, inherit: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1
     #
     # perf report -s type,typeoff --hierarchy --group --stdio
     # Total Lost Samples: 0
     #
     # Samples: 2K of events 'ibs_op//, dummy:u'
     # Event count (approx.): 1904553038
     #
     #            Overhead  Data Type / Data Type Offset
     # ...................  ............................
     #
         73.70%   0.00%     (unknown)
            73.70%   0.00%     (unknown) +0 (no field)
          3.01%   0.00%     long unsigned int
             3.00%   0.00%     long unsigned int +0 (no field)
             0.01%   0.00%     long unsigned int +2 (no field)
          2.73%   0.00%     struct task_struct
             1.71%   0.00%     struct task_struct +52 (on_cpu)
             0.38%   0.00%     struct task_struct +2104 (rcu_read_unlock_special.b.blocked)
             0.23%   0.00%     struct task_struct +2100 (rcu_read_lock_nesting)
             0.14%   0.00%     struct task_struct +2384 ()
             0.06%   0.00%     struct task_struct +3096 (signal)
             0.05%   0.00%     struct task_struct +3616 (cgroups)
             0.05%   0.00%     struct task_struct +2344 (active_mm)
             0.02%   0.00%     struct task_struct +46 (flags)
             0.02%   0.00%     struct task_struct +2096 (migration_disabled)
             0.01%   0.00%     struct task_struct +24 (__state)
             0.01%   0.00%     struct task_struct +3956 (mm_cid_active)
             0.01%   0.00%     struct task_struct +1048 (cpus_ptr)
             0.01%   0.00%     struct task_struct +184 (se.group_node.next)
             0.01%   0.00%     struct task_struct +20 (thread_info.cpu)
             0.00%   0.00%     struct task_struct +104 (on_rq)
             0.00%   0.00%     struct task_struct +2456 (pid)
          1.36%   0.00%     struct module
             0.59%   0.00%     struct module +952 (kallsyms)
             0.42%   0.00%     struct module +0 (state)
             0.23%   0.00%     struct module +8 (list.next)
             0.12%   0.00%     struct module +216 (syms)
          0.95%   0.00%     struct inode
             0.41%   0.00%     struct inode +40 (i_sb)
             0.22%   0.00%     struct inode +0 (i_mode)
             0.06%   0.00%     struct inode +76 (i_rdev)
             0.06%   0.00%     struct inode +56 (i_security)
     <SNIP>

  perf top/report:

   - Don't ignore job control, allowing control+Z + bg to work.

   - Add s390 raw data interpretation for PAI (Processor Activity
     Instrumentation) counters.

  perf archive:

   - Add new option '--all' to pack perf.data with DSOs.

   - Add new option '--unpack' to expand tarballs.

  Initialization speedups:

   - Lazily initialize zstd streams to save memory when not using it.

   - Lazily allocate/size mmap event copy.

   - Lazy load kernel symbols in 'perf record'.

   - Be lazier in allocating lost samples buffer in 'perf record'.

   - Don't synthesize BPF events when disabled via the command line
     (perf record --no-bpf-event).

  Assorted improvements:

   - Show note on AMD systems that the :p, :pp, :ppp and :P are all the
     same, as IBS (Instruction Based Sampling) is used and it is
     inherentely precise, not having levels of precision like in Intel
     systems.

   - When 'cycles' isn't available, fall back to the "task-clock" event
     when not system wide, not to 'cpu-clock'.

   - Add --debug-file option to redirect debug output, e.g.:

       $ perf --debug-file /tmp/perf.log record -v true

   - Shrink 'struct map' to under one cacheline by avoiding function
     pointers for selecting if addresses are identity or DSO relative,
     and using just a byte for some boolean struct members.

   - Resolve the arch specific strerrno just once to use in
     perf_env__arch_strerrno().

   - Reduce memory for recording PERF_RECORD_LOST_SAMPLES event.

  Assorted fixes:

   - Fix the default 'perf top' usage on Intel hybrid systems, now it
     starts with a browser showing the number of samples for Efficiency
     (cpu_atom/cycles/P) and Performance (cpu_core/cycles/P). This
     behaviour is similar on ARM64, with its respective set of
     big.LITTLE processors.

   - Fix segfault on build_mem_topology() error path.

   - Fix 'perf mem' error on hybrid related to availability of mem event
     in a PMU.

   - Fix missing reference count gets (map, maps) in the db-export code.

   - Avoid recursively taking env->bpf_progs.lock in the 'perf_env'
     code.

   - Use the newly introduced maps__for_each_map() to add missing
     locking around iteration of 'struct map' entries.

   - Parse NOTE segments until the build id is found, don't stop on the
     first one, ELF files may have several such NOTE segments.

   - Remove 'egrep' usage, its deprecated, use 'grep -E' instead.

   - Warn first about missing libelf, not libbpf, that depends on
     libelf.

   - Use alternative to 'find ... -printf' as this isn't supported in
     busybox.

   - Address python 3.6 DeprecationWarning for string scapes.

   - Fix memory leak in uniq() in libsubcmd.

   - Fix man page formatting for 'perf lock'

   - Fix some spelling mistakes.

  perf tests:

   - Fail shell tests that needs some symbol in perf itself if it is
     stripped. These tests check if a symbol is resolved, if some hot
     function is indeed detected by profiling, etc.

   - The 'perf test sigtrap' test is currently failing on PREEMPT_RT,
     skip it if sleeping spinlocks are detected (using BTF) and point to
     the mailing list discussion about it. This test is also being
     skipped on several architectures (powerpc, s390x, arm and aarch64)
     due to other pending issues with intruction breakpoints.

   - Adjust test case perf record offcpu profiling tests for s390.

   - Fix 'Setup struct perf_event_attr' fails on s390 on z/VM guest,
     addressing issues caused by the fallback from cycles to task-clock
     done in this release.

   - Fix mask for VG register in the user-regs test.

   - Use shellcheck on 'perf test' shell scripts automatically to make
     sure changes don't introduce things it flags as problematic.

   - Add option to change objdump binary and allow it to be set via
     'perf config'.

   - Add basic 'perf script', 'perf list --json" and 'perf diff' tests.

   - Basic branch counter support.

   - Make DSO tests a suite rather than individual.

   - Remove atomics from test_loop to avoid test failures.

   - Fix call chain match on powerpc for the record+probe_libc_inet_pton
     test.

   - Improve Intel hybrid tests.

  Vendor event files (JSON):

  powerpc:

   - Update datasource event name to fix duplicate events on IBM's
     Power10.

   - Add PVN for HX-C2000 CPU with Power8 Architecture.

  Intel:

   - Alderlake/rocketlake metric fixes.

   - Update emeraldrapids events to v1.02.

   - Update icelakex events to v1.23.

   - Update sapphirerapids events to v1.17.

   - Add skx, clx, icx and spr upi bandwidth metric.

  AMD:

   - Add Zen 4 memory controller events.

  RISC-V:

   - Add StarFive Dubhe-80 and Dubhe-90 JSON files.
       https://www.starfivetech.com/en/site/cpu-u

   - Add T-HEAD C9xx JSON file.
       https://github.com/riscv-software-src/opensbi/blob/master/docs/platform/thead-c9xx.md

  ARM64:

   - Remove UTF-8 characters from cmn.json, that were causing build
     failure in some distros.

   - Add core PMU events and metrics for Ampere One X.

   - Rename Ampere One's BPU_FLUSH_MEM_FAULT to GPC_FLUSH_MEM_FAULT

  libperf:

   - Rename several perf_cpu_map constructor names to clarify what they
     really do.

   - Ditto for some other methods, coping with some issues in their
     semantics, like perf_cpu_map__empty() ->
     perf_cpu_map__has_any_cpu_or_is_empty().

   - Document perf_cpu_map__nr()'s behavior

  perf stat:

   - Exit if parse groups fails.

   - Combine the -A/--no-aggr and --no-merge options.

   - Fix help message for --metric-no-threshold option.

  Hardware tracing:

  ARM64 CoreSight:

   - Bump minimum OpenCSD version to ensure a bugfix is present.

   - Add 'T' itrace option for timestamp trace

   - Set start vm addr of exectable file to 0 and don't ignore first
     sample on the arm-cs-trace-disasm.py 'perf script'"

* tag 'perf-tools-for-v6.8-1-2024-01-09' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (179 commits)
  MAINTAINERS: Add Namhyung as tools/perf/ co-maintainer
  perf test: test case 'Setup struct perf_event_attr' fails on s390 on z/vm
  perf db-export: Fix missing reference count get in call_path_from_sample()
  perf tests: Add perf script test
  libsubcmd: Fix memory leak in uniq()
  perf TUI: Don't ignore job control
  perf vendor events intel: Update sapphirerapids events to v1.17
  perf vendor events intel: Update icelakex events to v1.23
  perf vendor events intel: Update emeraldrapids events to v1.02
  perf vendor events intel: Alderlake/rocketlake metric fixes
  perf x86 test: Add hybrid test for conflicting legacy/sysfs event
  perf x86 test: Update hybrid expectations
  perf vendor events amd: Add Zen 4 memory controller events
  perf stat: Fix hard coded LL miss units
  perf record: Reduce memory for recording PERF_RECORD_LOST_SAMPLES event
  perf env: Avoid recursively taking env->bpf_progs.lock
  perf annotate: Add --insn-stat option for debugging
  perf annotate: Add --type-stat option for debugging
  perf annotate: Support event group display
  perf annotate: Add --data-type option
  ...

19 files changed, 318 insertions, 44 deletions

diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
index a7e169d1bf64..5f886cd09e6b 100644
--- a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
+++ b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
@@ -42,7 +42,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned long i, len, size, thr;
-	pthread_t threads[256];
 	struct args args[256];
 	long long v;
 
diff --git a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
index c0158fac7d0b..e05a559253ca 100644
--- a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
+++ b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
@@ -57,7 +57,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned int i, len, thr;
-	pthread_t threads[256];
 	struct args args[256];
 
 	if (argc < 3) {
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
index 8f6d384208ed..0fc7bf1a25af 100644
--- a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
@@ -51,7 +51,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
 int main(int argc, char **argv)
 {
 	unsigned int i, thr;
-	pthread_t threads[256];
 	struct args args[256];
 
 	if (argc < 2) {
diff --git a/tools/perf/tests/shell/diff.sh b/tools/perf/tests/shell/diff.sh
new file mode 100755
index 000000000000..14b87af88703
--- /dev/null
+++ b/tools/perf/tests/shell/diff.sh
@@ -0,0 +1,108 @@
+#!/bin/sh
+# perf diff tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata1=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+perfdata2=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+perfdata3=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+testprog="perf test -w thloop"
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+testsym="test_loop"
+
+skip_test_missing_symbol ${testsym}
+
+cleanup() {
+  rm -rf "${perfdata1}"
+  rm -rf "${perfdata1}".old
+  rm -rf "${perfdata2}"
+  rm -rf "${perfdata2}".old
+  rm -rf "${perfdata3}"
+  rm -rf "${perfdata3}".old
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+make_data() {
+  file="$1"
+  if ! perf record -o "${file}" ${testprog} 2> /dev/null
+  then
+    echo "Workload record [Failed record]"
+    echo 1
+    return
+  fi
+  if ! perf report -i "${file}" -q | grep -q "${testsym}"
+  then
+    echo "Workload record [Failed missing output]"
+    echo 1
+    return
+  fi
+  echo 0
+}
+
+test_two_files() {
+  echo "Basic two file diff test"
+  err=$(make_data "${perfdata1}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata2}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+
+  if ! perf diff "${perfdata1}" "${perfdata2}" | grep -q "${testsym}"
+  then
+    echo "Basic two file diff test [Failed diff]"
+    err=1
+    return
+  fi
+  echo "Basic two file diff test [Success]"
+}
+
+test_three_files() {
+  echo "Basic three file diff test"
+  err=$(make_data "${perfdata1}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata2}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+  err=$(make_data "${perfdata3}")
+  if [ $err != 0 ]
+  then
+    return
+  fi
+
+  if ! perf diff "${perfdata1}" "${perfdata2}" "${perfdata3}" | grep -q "${testsym}"
+  then
+    echo "Basic three file diff test [Failed diff]"
+    err=1
+    return
+  fi
+  echo "Basic three file diff test [Success]"
+}
+
+test_two_files
+test_three_files
+
+cleanup
+exit $err
diff --git a/tools/perf/tests/shell/lib/perf_has_symbol.sh b/tools/perf/tests/shell/lib/perf_has_symbol.sh
new file mode 100644
index 000000000000..5d59c32ae3e7
--- /dev/null
+++ b/tools/perf/tests/shell/lib/perf_has_symbol.sh
@@ -0,0 +1,21 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+perf_has_symbol()
+{
+	if perf test -vv "Symbols" 2>&1 | grep "[[:space:]]$1$"; then
+		echo "perf does have symbol '$1'"
+		return 0
+	fi
+	echo "perf does not have symbol '$1'"
+	return 1
+}
+
+skip_test_missing_symbol()
+{
+	if ! perf_has_symbol "$1" ; then
+		echo "perf is missing symbols - skipping test"
+		exit 2
+	fi
+	return 0
+}
diff --git a/tools/perf/tests/shell/lib/setup_python.sh b/tools/perf/tests/shell/lib/setup_python.sh
new file mode 100644
index 000000000000..c2fce1793538
--- /dev/null
+++ b/tools/perf/tests/shell/lib/setup_python.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+if [ "x$PYTHON" = "x" ]
+then
+  python3 --version >/dev/null 2>&1 && PYTHON=python3
+fi
+if [ "x$PYTHON" = "x" ]
+then
+  python --version >/dev/null 2>&1 && PYTHON=python
+fi
+if [ "x$PYTHON" = "x" ]
+then
+  echo Skipping test, python not detected please set environment variable PYTHON.
+  exit 2
+fi
diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh
new file mode 100755
index 000000000000..22b004f2b23e
--- /dev/null
+++ b/tools/perf/tests/shell/list.sh
@@ -0,0 +1,19 @@
+#!/bin/sh
+# perf list tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+err=0
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
+
+test_list_json() {
+  echo "Json output test"
+  perf list -j | $PYTHON -m json.tool
+  echo "Json output test [Success]"
+}
+
+test_list_json
+exit $err
diff --git a/tools/perf/tests/shell/pipe_test.sh b/tools/perf/tests/shell/pipe_test.sh
index 8dd115dd35a7..a78d35d2cff0 100755
--- a/tools/perf/tests/shell/pipe_test.sh
+++ b/tools/perf/tests/shell/pipe_test.sh
@@ -2,10 +2,17 @@
 # perf pipe recording and injection test
 # SPDX-License-Identifier: GPL-2.0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+sym="noploop"
+
+skip_test_missing_symbol ${sym}
+
 data=$(mktemp /tmp/perf.data.XXXXXX)
 prog="perf test -w noploop"
 task="perf"
-sym="noploop"
 
 if ! perf record -e task-clock:u -o - ${prog} | perf report -i - --task | grep ${task}; then
 	echo "cannot find the test file in the perf report"
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index eebeea6bdc76..72c65570db37 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -45,7 +45,10 @@ trace_libc_inet_pton_backtrace() {
 		;;
 	ppc64|ppc64le)
 		eventattr='max-stack=4'
-		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		# Add gaih_inet to expected backtrace only if it is part of libc.
+		if nm $libc | grep -F -q gaih_inet.; then
+			echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		fi
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
 		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 29443b8e8876..3d1a7759a7b2 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -8,10 +8,19 @@ shelldir=$(dirname "$0")
 # shellcheck source=lib/waiting.sh
 . "${shelldir}"/lib/waiting.sh
 
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+testsym="test_loop"
+
+skip_test_missing_symbol ${testsym}
+
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 testprog="perf test -w thloop"
-testsym="test_loop"
+cpu_pmu_dir="/sys/bus/event_source/devices/cpu*"
+br_cntr_file="/caps/branch_counter_nr"
+br_cntr_output="branch stack counters"
 
 cleanup() {
   rm -rf "${perfdata}"
@@ -155,10 +164,37 @@ test_workload() {
   echo "Basic target workload test [Success]"
 }
 
+test_branch_counter() {
+  echo "Basic branch counter test"
+  # Check if the branch counter feature is supported
+  for dir in $cpu_pmu_dir
+  do
+    if [ ! -e "$dir$br_cntr_file" ]
+    then
+      echo "branch counter feature not supported on all core PMUs ($dir) [Skipped]"
+      return
+    fi
+  done
+  if ! perf record -o "${perfdata}" -j any,counter ${testprog} 2> /dev/null
+  then
+    echo "Basic branch counter test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf report -i "${perfdata}" -D -q | grep -q "$br_cntr_output"
+  then
+    echo "Basic branch record test [Failed missing output]"
+    err=1
+    return
+  fi
+  echo "Basic branch counter test [Success]"
+}
+
 test_per_thread
 test_register_capture
 test_system_wide
 test_workload
+test_branch_counter
 
 cleanup
 exit $err
diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index a1ef8f0d2b5c..67c925f3a15a 100755
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -77,9 +77,9 @@ test_offcpu_child() {
     err=1
     return
   fi
-  # each process waits for read and write, so it should be more than 800 events
+  # each process waits at least for poll, so it should be more than 400 events
   if ! perf report -i ${perfdata} -s comm -q -n -t ';' --percent-limit=90 | \
-    awk -F ";" '{ if (NF > 3 && int($3) < 800) exit 1; }'
+    awk -F ";" '{ if (NF > 3 && int($3) < 400) exit 1; }'
   then
     echo "Child task off-cpu test [Failed invalid output]"
     err=1
diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
new file mode 100755
index 000000000000..5ae7bd0031a8
--- /dev/null
+++ b/tools/perf/tests/shell/script.sh
@@ -0,0 +1,66 @@
+#!/bin/sh
+# perf script tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+temp_dir=$(mktemp -d /tmp/perf-test-script.XXXXXXXXXX)
+
+perfdatafile="${temp_dir}/perf.data"
+db_test="${temp_dir}/db_test.py"
+
+err=0
+
+cleanup()
+{
+	trap - EXIT TERM INT
+	sane=$(echo "${temp_dir}" | cut -b 1-21)
+	if [ "${sane}" = "/tmp/perf-test-script" ] ; then
+		echo "--- Cleaning up ---"
+		rm -f "${temp_dir}/"*
+		rmdir "${temp_dir}"
+	fi
+}
+
+trap_cleanup()
+{
+	cleanup
+	exit 1
+}
+
+trap trap_cleanup EXIT TERM INT
+
+
+test_db()
+{
+	echo "DB test"
+
+	# Check if python script is supported
+	libpython=$(perf version --build-options | grep python | grep -cv OFF)
+	if [ "${libpython}" != "1" ] ; then
+		echo "SKIP: python scripting is not supported"
+		err=2
+		return
+	fi
+
+	cat << "_end_of_file_" > "${db_test}"
+perf_db_export_mode = True
+perf_db_export_calls = False
+perf_db_export_callchains = True
+
+def sample_table(*args):
+    print(f'sample_table({args})')
+
+def call_path_table(*args):
+    print(f'call_path_table({args}')
+_end_of_file_
+	perf record -g -o "${perfdatafile}" true
+	perf script -i "${perfdatafile}" -s "${db_test}"
+	echo "DB test [Success]"
+}
+
+test_db
+
+cleanup
+
+exit $err
diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
index 196e22672c50..3bc900533a5d 100755
--- a/tools/perf/tests/shell/stat+json_output.sh
+++ b/tools/perf/tests/shell/stat+json_output.sh
@@ -8,20 +8,10 @@ set -e
 
 skip_test=0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py
-if [ "x$PYTHON" == "x" ]
-then
-	if which python3 > /dev/null
-	then
-		PYTHON=python3
-	elif which python > /dev/null
-	then
-		PYTHON=python
-	else
-		echo Skipping test, python not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
 
 stat_output=$(mktemp /tmp/__perf_test.stat_output.json.XXXXX)
 
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index c77955419173..d2a3506e0d19 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -4,7 +4,7 @@
 
 set -e
 
-# Test all PMU events; however exclude parametrized ones (name contains '?')
+# Test all PMU events; however exclude parameterized ones (name contains '?')
 for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g'); do
   echo "Testing $p"
   result=$(perf stat -e "$p" true 2>&1)
diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh
index ad94c936de7e..7ca172599aa6 100755
--- a/tools/perf/tests/shell/stat_metrics_values.sh
+++ b/tools/perf/tests/shell/stat_metrics_values.sh
@@ -1,16 +1,10 @@
 #!/bin/bash
 # perf metrics value validation
 # SPDX-License-Identifier: GPL-2.0
-if [ "x$PYTHON" == "x" ]
-then
-	if which python3 > /dev/null
-	then
-		PYTHON=python3
-	else
-		echo Skipping test, python3 not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
+
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 
 grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; }
 
diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
index 66dfdfdad553..e342e6c8aa50 100755
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -2,8 +2,14 @@
 # Check Arm64 callgraphs are complete in fp mode
 # SPDX-License-Identifier: GPL-2.0
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 lscpu | grep -q "aarch64" || exit 2
 
+skip_test_missing_symbol leafloop
+
 PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 TEST_PROGRAM="perf test -w leafloop"
 
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index 09908d71c994..5f14d0cb013f 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -4,6 +4,10 @@
 # SPDX-License-Identifier: GPL-2.0
 # German Gomez <german.gomez@arm.com>, 2022
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 # skip the test if the hardware doesn't support branch stack sampling
 # and if the architecture doesn't support filter types: any,save_type,u
 if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev/null 2>&1 ; then
@@ -11,6 +15,8 @@ if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev
 	exit 2
 fi
 
+skip_test_missing_symbol brstack_bench
+
 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
 TESTPROG="perf test -w brstack"
 
diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh
index 69bb6fe86c50..3dfa91832aa8 100755
--- a/tools/perf/tests/shell/test_data_symbol.sh
+++ b/tools/perf/tests/shell/test_data_symbol.sh
@@ -4,6 +4,13 @@
 # SPDX-License-Identifier: GPL-2.0
 # Leo Yan <leo.yan@linaro.org>, 2022
 
+shelldir=$(dirname "$0")
+# shellcheck source=lib/waiting.sh
+. "${shelldir}"/lib/waiting.sh
+
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
 skip_if_no_mem_event() {
 	perf mem record -e list 2>&1 | grep -E -q 'available' && return 0
 	return 2
@@ -11,8 +18,11 @@ skip_if_no_mem_event() {
 
 skip_if_no_mem_event || exit 2
 
+skip_test_missing_symbol buf1
+
 TEST_PROGRAM="perf test -w datasym"
 PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+ERR_FILE=$(mktemp /tmp/__perf_test.stderr.XXXXX)
 
 check_result() {
 	# The memory report format is as below:
@@ -50,13 +60,15 @@ echo "Recording workload..."
 # specific CPU and test in per-CPU mode.
 is_amd=$(grep -E -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo)
 if (($is_amd >= 1)); then
-	perf mem record -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM &
+	perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}" &
 else
-	perf mem record --all-user -o ${PERF_DATA} -- $TEST_PROGRAM &
+	perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}" &
 fi
 
 PERFPID=$!
 
+wait_for_perf_to_start ${PERFPID} "${ERR_FILE}"
+
 sleep 1
 
 kill $PERFPID
diff --git a/tools/perf/tests/shell/test_perf_data_converter_json.sh b/tools/perf/tests/shell/test_perf_data_converter_json.sh
index 6ded58f98f55..c4f1b59d116f 100755
--- a/tools/perf/tests/shell/test_perf_data_converter_json.sh
+++ b/tools/perf/tests/shell/test_perf_data_converter_json.sh
@@ -6,16 +6,9 @@ set -e
 
 err=0
 
-if [ "$PYTHON" = "" ] ; then
-	if which python3 > /dev/null ; then
-		PYTHON=python3
-	elif which python > /dev/null ; then
-		PYTHON=python
-	else
-		echo Skipping test, python not detected please set environment variable PYTHON.
-		exit 2
-	fi
-fi
+shelldir=$(dirname "$0")
+# shellcheck source=lib/setup_python.sh
+. "${shelldir}"/lib/setup_python.sh
 
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 result=$(mktemp /tmp/__perf_test.output.json.XXXXX)