Merge tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - cgroup improvements for 'perf stat', allowing for compact
   specification of events and cgroups in the command line.

 - Support per thread topdown metrics in 'perf stat'.

 - Support sample-read topdown metric group in 'perf record'

 - Show start of latency in addition to its start in 'perf sched
   latency'.

 - Add min, max to 'perf script' futex-contention output, in addition to
   avg.

 - Allow usage of 'perf_event_attr->exclusive' attribute via the new
   ':e' event modifier.

 - Add 'snapshot' command to 'perf record --control', using it with
   Intel PT.

 - Support FIFO file names as alternative options to 'perf record
   --control'.

 - Introduce branch history "streams", to compare 'perf record' runs
   with 'perf diff' based on branch records and report hot streams.

 - Support PE executable symbol tables using libbfd, to profile, for
   instance, wine binaries.

 - Add filter support for option 'perf ftrace -F/--funcs'.

 - Allow configuring the 'disassembler_style' 'perf annotate' knob via
   'perf config'

 - Update CascadelakeX and SkylakeX JSON vendor events files.

 - Add support for parsing perchip/percore JSON vendor events.

 - Add power9 hv_24x7 core level metric events.

 - Add L2 prefetch, ITLB instruction fetch hits JSON events for AMD
   zen1.

 - Enable Family 19h users by matching Zen2 AMD vendor events.

 - Use debuginfod in 'perf probe' when required debug files not found
   locally.

 - Display negative tid in non-sample events in 'perf script'.

 - Make GTK2 support opt-in

 - Add build test with GTK+

 - Add missing -lzstd to the fast path feature detection

 - Add scripts to auto generate 'mmap', 'mremap' string<->id tables for
   use in 'perf trace'.

 - Show python test script in verbose mode.

 - Fix uncore metric expressions

 - Msan uninitialized use fixes.

 - Use condition variables in 'perf bench numa'

 - Autodetect python3 binary in systems without python2.

 - Support md5 build ids in addition to sha1.

 - Add build id 'perf test' regression test.

 - Fix printable strings in python3 scripts.

 - Fix off by ones in 'perf trace' in arches using libaudit.

 - Fix JSON event code for events referencing std arch events.

 - Introduce 'perf test' shell script for Arm CoreSight testing.

 - Add rdtsc() for Arm64 for used in the PERF_RECORD_TIME_CONV metadata
   event and in 'perf test tsc'.

 - 'perf c2c' improvements: Add "RMT Load Hit" metric, "Total Stores",
   fixes and documentation update.

 - Fix usage of reloc_sym in 'perf probe' when using both kallsyms and
   debuginfo files.

 - Do not print 'Metric Groups:' unnecessarily in 'perf list'

 - Refcounting fixes in the event parsing code.

 - Add expand cgroup event 'perf test' entry.

 - Fix out of bounds CPU map access when handling armv8_pmu events in
   'perf stat'.

 - Add build-id injection 'perf bench' benchmark.

 - Enter namespace when reading build-id in 'perf inject'.

 - Do not load map/dso when injecting build-id speeding up the 'perf
   inject' process.

 - Add --buildid-all option to avoid processing all samples, just the
   mmap metadata events.

 - Add feature test to check if libbfd has buildid support

 - Add 'perf test' entry for PE binary format support.

 - Fix typos in power8 PMU vendor events JSON files.

 - Hide libtraceevent non API functions.

* tag 'perf-tools-for-v5.10-2020-10-15' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (113 commits)
  perf c2c: Update documentation for metrics reorganization
  perf c2c: Add metrics "RMT Load Hit"
  perf c2c: Correct LLC load hit metrics
  perf c2c: Change header for LLC local hit
  perf c2c: Use more explicit headers for HITM
  perf c2c: Change header from "LLC Load Hitm" to "Load Hitm"
  perf c2c: Organize metrics based on memory hierarchy
  perf c2c: Display "Total Stores" as a standalone metrics
  perf c2c: Display the total numbers continuously
  perf bench: Use condition variables in numa.
  perf jevents: Fix event code for events referencing std arch events
  perf diff: Support hot streams comparison
  perf streams: Report hot streams
  perf streams: Calculate the sum of total streams hits
  perf streams: Link stream pair
  perf streams: Compare two streams
  perf streams: Get the evsel_streams by evsel_idx
  perf streams: Introduce branch history "streams"
  perf intel-pt: Improve PT documentation slightly
  perf tools: Add support for exclusive groups/events
  ...

1 files changed, 183 insertions, 0 deletions

diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
new file mode 100755
index 000000000000..8d84fdbed6a6
--- /dev/null
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -0,0 +1,183 @@
+#!/bin/sh
+# Check Arm CoreSight trace data recording and synthesized samples
+
+# Uses the 'perf record' to record trace data with Arm CoreSight sinks;
+# then verify if there have any branch samples and instruction samples
+# are generated by CoreSight with 'perf script' and 'perf report'
+# commands.
+
+# SPDX-License-Identifier: GPL-2.0
+# Leo Yan <leo.yan@linaro.org>, 2020
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+skip_if_no_cs_etm_event() {
+	perf list | grep -q 'cs_etm//' && return 0
+
+	# cs_etm event doesn't exist
+	return 2
+}
+
+skip_if_no_cs_etm_event || exit 2
+
+cleanup_files()
+{
+	rm -f ${perfdata}
+	rm -f ${file}
+}
+
+trap cleanup_files exit
+
+record_touch_file() {
+	echo "Recording trace (only user mode) with path: CPU$2 => $1"
+	rm -f $file
+	perf record -o ${perfdata} -e cs_etm/@$1/u --per-thread \
+		-- taskset -c $2 touch $file
+}
+
+perf_script_branch_samples() {
+	echo "Looking at perf.data file for dumping branch samples:"
+
+	# Below is an example of the branch samples dumping:
+	#   touch  6512          1         branches:u:      ffffb220824c strcmp+0xc (/lib/aarch64-linux-gnu/ld-2.27.so)
+	#   touch  6512          1         branches:u:      ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so)
+	#   touch  6512          1         branches:u:      ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so)
+	perf script -F,-time -i ${perfdata} | \
+		egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +"
+}
+
+perf_report_branch_samples() {
+	echo "Looking at perf.data file for reporting branch samples:"
+
+	# Below is an example of the branch samples reporting:
+	#   73.04%    73.04%  touch    libc-2.27.so      [.] _dl_addr
+	#    7.71%     7.71%  touch    libc-2.27.so      [.] getenv
+	#    2.59%     2.59%  touch    ld-2.27.so        [.] strcmp
+	perf report --stdio -i ${perfdata} | \
+		egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 "
+}
+
+perf_report_instruction_samples() {
+	echo "Looking at perf.data file for instruction samples:"
+
+	# Below is an example of the instruction samples reporting:
+	#   68.12%  touch    libc-2.27.so   [.] _dl_addr
+	#    5.80%  touch    libc-2.27.so   [.] getenv
+	#    4.35%  touch    ld-2.27.so     [.] _dl_fixup
+	perf report --itrace=i1000i --stdio -i ${perfdata} | \
+		egrep " +[0-9]+\.[0-9]+% +$1"
+}
+
+is_device_sink() {
+	# If the node of "enable_sink" is existed under the device path, this
+	# means the device is a sink device.  Need to exclude 'tpiu' since it
+	# cannot support perf PMU.
+	echo "$1" | egrep -q -v "tpiu"
+
+	if [ $? -eq 0 -a -e "$1/enable_sink" ]; then
+
+		pmu_dev="/sys/bus/event_source/devices/cs_etm/sinks/$2"
+
+		# Warn if the device is not supported by PMU
+		if ! [ -f $pmu_dev ]; then
+			echo "PMU doesn't support $pmu_dev"
+		fi
+
+		return 0
+	fi
+
+	# Otherwise, it's not a sink device
+	return 1
+}
+
+arm_cs_iterate_devices() {
+	for dev in $1/connections/out\:*; do
+
+		# Skip testing if it's not a directory
+		! [ -d $dev ] && continue;
+
+		# Read out its symbol link file name
+		path=`readlink -f $dev`
+
+		# Extract device name from path, e.g.
+		#   path = '/sys/devices/platform/20010000.etf/tmc_etf0'
+		#     `> device_name = 'tmc_etf0'
+		device_name=$(basename $path)
+
+		if is_device_sink $path $devce_name; then
+
+			record_touch_file $device_name $2 &&
+			perf_script_branch_samples touch &&
+			perf_report_branch_samples touch &&
+			perf_report_instruction_samples touch
+
+			err=$?
+
+			# Exit when find failure
+			[ $err != 0 ] && exit $err
+		fi
+
+		arm_cs_iterate_devices $dev $2
+	done
+}
+
+arm_cs_etm_traverse_path_test() {
+	# Iterate for every ETM device
+	for dev in /sys/bus/coresight/devices/etm*; do
+
+		# Find the ETM device belonging to which CPU
+		cpu=`cat $dev/cpu`
+
+		echo $dev
+		echo $cpu
+
+		# Use depth-first search (DFS) to iterate outputs
+		arm_cs_iterate_devices $dev $cpu
+	done
+}
+
+arm_cs_etm_system_wide_test() {
+	echo "Recording trace with system wide mode"
+	perf record -o ${perfdata} -e cs_etm// -a -- ls
+
+	perf_script_branch_samples perf &&
+	perf_report_branch_samples perf &&
+	perf_report_instruction_samples perf
+
+	err=$?
+
+	# Exit when find failure
+	[ $err != 0 ] && exit $err
+}
+
+arm_cs_etm_snapshot_test() {
+	echo "Recording trace with snapshot mode"
+	perf record -o ${perfdata} -e cs_etm// -S \
+		-- dd if=/dev/zero of=/dev/null &
+	PERFPID=$!
+
+	# Wait for perf program
+	sleep 1
+
+	# Send signal to snapshot trace data
+	kill -USR2 $PERFPID
+
+	# Stop perf program
+	kill $PERFPID
+	wait $PERFPID
+
+	perf_script_branch_samples dd &&
+	perf_report_branch_samples dd &&
+	perf_report_instruction_samples dd
+
+	err=$?
+
+	# Exit when find failure
+	[ $err != 0 ] && exit $err
+}
+
+arm_cs_etm_traverse_path_test
+arm_cs_etm_system_wide_test
+arm_cs_etm_snapshot_test
+exit 0