[PATCH 08/20] perf tools: Add perf-with-kcore script

[Arnaldo Carvalho de Melo <acme@kernel.org>]

From: Adrian Hunter <adrian.hunter@intel.com>

Decoding an Intel PT trace of the kernel requires an accurate kernel
object image.  This is provided by making a copy of kcore.  However the
copy needs to be made under the same conditions as the original
recording, and then it needs to be associated with the perf.data file.
The perf-with-kcore script does that.

The script also checks the permissions on the buildid cache and can be
used to fix them.  That is needed for distributions where root does not
have a home directory and consequently writes to the same buildid cache
as the user, resulting in cached files that the user does not have
access to.

Example:

$ ./perf-with-kcore
Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]
       <perf sub-command> can be record, script, report or inject
   or: perf-with-kcore fix_buildid_cache_permissions
$ ./perf-with-kcore record pt_uname -e intel_pt// -- uname
Recording
Using /home/ahunter/bin/perf
perf version 3.15.rc3.g4549ba
/home/ahunter/bin/perf record -o pt_uname/perf.data -e intel_pt//  -- uname
Linux
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.023 MB pt_uname/perf.data ]
Copying kcore
[sudo] password for ahunter:
Done
$ tools/perf/perf-with-kcore.sh script pt_uname | head
Using /home/ahunter/bin/perf
perf version 3.15.rc3.g4549ba
/home/ahunter/bin/perf script -i pt_uname/perf.data --kallsyms=pt_uname/kcore_dir/kallsyms
         swapper     0 [002] 161533.969666: sched:sched_switch: swapper/2:0 [120] R ==> perf:11316 [120]
          :11315 11315 [003] 161533.969704: sched:sched_switch: perf:11315 [120] S ==> swapper/3:0 [120]
          :11316 11316 [002] 161533.969783: sched:sched_switch: perf:11316 [120] R ==> migration/2:33 [0]
             :33    33 [002] 161533.969791: sched:sched_switch: migration/2:33 [0] S ==> swapper/2:0 [120]
         swapper     0 [003] 161533.969792: sched:sched_switch: swapper/3:0 [120] R ==> perf:11316 [120]
          :11316 11316 [003] 161533.970062: branches:                 0 [unknown] ([unknown]) => ffffffff810532fa native_write_msr_safe ([kernel.kallsyms])
          :11316 11316 [003] 161533.970062: branches:  ffffffff810532fd native_write_msr_safe ([kernel.kallsyms]) => ffffffff81035b31 pt_config_start ([kernel.kallsyms])

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1406786474-9306-30-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/.gitignore         |   1 +
 tools/perf/Makefile.perf      |   5 +-
 tools/perf/perf-with-kcore.sh | 259 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 264 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/perf-with-kcore.sh

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 782d86e961b9..717221e98450 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -15,6 +15,7 @@ perf.data
 perf.data.old
 output.svg
 perf-archive
+perf-with-kcore
 tags
 TAGS
 cscope*
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 95e832b1bc3c..171f4e65601b 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -126,6 +126,7 @@ PYRF_OBJS =
 SCRIPT_SH =
 
 SCRIPT_SH += perf-archive.sh
+SCRIPT_SH += perf-with-kcore.sh
 
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
@@ -878,6 +879,8 @@ install-bin: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(call QUIET_INSTALL, perf-with-kcore) \
+		$(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
 	$(call QUIET_INSTALL, perl-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
@@ -923,7 +926,7 @@ config-clean:
 	@$(MAKE) -C config/feature-checks clean >/dev/null
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
-	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/perf-with-kcore.sh b/tools/perf/perf-with-kcore.sh
new file mode 100644
index 000000000000..c7ff90a90e4e
--- /dev/null
+++ b/tools/perf/perf-with-kcore.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# perf-with-kcore: use perf with a copy of kcore
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+set -e
+
+usage()
+{
+        echo "Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]" >&2
+        echo "       <perf sub-command> can be record, script, report or inject" >&2
+        echo "   or: perf-with-kcore fix_buildid_cache_permissions" >&2
+        exit 1
+}
+
+find_perf()
+{
+	if [ -n "$PERF" ] ; then
+		return
+	fi
+	PERF=`which perf || true`
+	if [ -z "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	if [ ! -x "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	echo "Using $PERF"
+	"$PERF" version
+}
+
+copy_kcore()
+{
+	echo "Copying kcore"
+
+	if [ $EUID -eq 0 ] ; then
+		SUDO=""
+	else
+		SUDO="sudo"
+	fi
+
+	rm -f perf.data.junk
+	("$PERF" record -o perf.data.junk $PERF_OPTIONS -- sleep 60) >/dev/null 2>/dev/null &
+	PERF_PID=$!
+
+	# Need to make sure that perf has started
+	sleep 1
+
+	KCORE=$(($SUDO "$PERF" buildid-cache -v -f -k /proc/kcore >/dev/null) 2>&1)
+	case "$KCORE" in
+	"kcore added to build-id cache directory "*)
+		KCORE_DIR=${KCORE#"kcore added to build-id cache directory "}
+	;;
+	*)
+		kill $PERF_PID
+		wait >/dev/null 2>/dev/null || true
+		rm perf.data.junk
+		echo "$KCORE"
+		echo "Failed to find kcore" >&2
+		exit 1
+	;;
+	esac
+
+	kill $PERF_PID
+	wait >/dev/null 2>/dev/null || true
+	rm perf.data.junk
+
+	$SUDO cp -a "$KCORE_DIR" "$(pwd)/$PERF_DATA_DIR"
+	$SUDO rm -f "$KCORE_DIR/kcore"
+	$SUDO rm -f "$KCORE_DIR/kallsyms"
+	$SUDO rm -f "$KCORE_DIR/modules"
+	$SUDO rmdir "$KCORE_DIR"
+
+	KCORE_DIR_BASENAME=$(basename "$KCORE_DIR")
+	KCORE_DIR="$(pwd)/$PERF_DATA_DIR/$KCORE_DIR_BASENAME"
+
+	$SUDO chown $UID "$KCORE_DIR"
+	$SUDO chown $UID "$KCORE_DIR/kcore"
+	$SUDO chown $UID "$KCORE_DIR/kallsyms"
+	$SUDO chown $UID "$KCORE_DIR/modules"
+
+	$SUDO chgrp $GROUPS "$KCORE_DIR"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kcore"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kallsyms"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/modules"
+
+	ln -s "$KCORE_DIR_BASENAME" "$PERF_DATA_DIR/kcore_dir"
+}
+
+fix_buildid_cache_permissions()
+{
+	if [ $EUID -ne 0 ] ; then
+		echo "This script must be run as root via sudo " >&2
+		exit 1
+	fi
+
+	if [ -z "$SUDO_USER" ] ; then
+		echo "This script must be run via sudo" >&2
+		exit 1
+	fi
+
+	USER_HOME=$(bash <<< "echo ~$SUDO_USER")
+
+	if [ "$HOME" != "$USER_HOME" ] ; then
+		echo "Fix unnecessary because root has a home: $HOME" >&2
+		exit 1
+	fi
+
+	echo "Fixing buildid cache permissions"
+
+	find "$USER_HOME/.debug" -xdev -type d          ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type f -links 1 ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type l          ! -user "$SUDO_USER" -ls -exec chown -h "$SUDO_USER" \{\} \;
+
+	if [ -n "$SUDO_GID" ] ; then
+		find "$USER_HOME/.debug" -xdev -type d          ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type f -links 1 ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type l          ! -group "$SUDO_GID" -ls -exec chgrp -h "$SUDO_GID" \{\} \;
+	fi
+
+	echo "Done"
+}
+
+check_buildid_cache_permissions()
+{
+	if [ $EUID -eq 0 ] ; then
+		return
+	fi
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -user "$USER" -print -quit)
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -group "$GROUPS" -print -quit)
+
+	if [ -n "$PERMISSIONS_OK" ] ; then
+		echo "*** WARNING *** buildid cache permissions may need fixing" >&2
+	fi
+}
+
+record()
+{
+	echo "Recording"
+
+	if [ $EUID -ne 0 ] ; then
+
+		if [ "$(cat /proc/sys/kernel/kptr_restrict)" -ne 0 ] ; then
+			echo "*** WARNING *** /proc/sys/kernel/kptr_restrict prevents access to kernel addresses" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q ' -a \|^-a \| -a$\|^-a$\| --all-cpus \|^--all-cpus \| --all-cpus$\|^--all-cpus$' ; then
+			echo "*** WARNING *** system-wide tracing without root access will not be able to read all necessary information from /proc" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q 'intel_pt\|intel_bts\| -I\|^-I' ; then
+			if [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt -1 ] ; then
+				echo "*** WARNING *** /proc/sys/kernel/perf_event_paranoid restricts buffer size and tracepoint (sched_switch) use" >&2
+			fi
+
+			if echo "$PERF_OPTIONS" | grep -q ' --per-thread \|^--per-thread \| --per-thread$\|^--per-thread$' ; then
+				true
+			elif echo "$PERF_OPTIONS" | grep -q ' -t \|^-t \| -t$\|^-t$' ; then
+				true
+			elif [ ! -r /sys/kernel/debug -o ! -x /sys/kernel/debug ] ; then
+				echo "*** WARNING *** /sys/kernel/debug permissions prevent tracepoint (sched_switch) use" >&2
+			fi
+		fi
+	fi
+
+	if [ -z "$1" ] ; then
+		echo "Workload is required for recording" >&2
+		usage
+	fi
+
+	if [ -e "$PERF_DATA_DIR" ] ; then
+		echo "'$PERF_DATA_DIR' exists" >&2
+		exit 1
+	fi
+
+	find_perf
+
+	mkdir "$PERF_DATA_DIR"
+
+	echo "$PERF record -o $PERF_DATA_DIR/perf.data $PERF_OPTIONS -- $*"
+	"$PERF" record -o "$PERF_DATA_DIR/perf.data" $PERF_OPTIONS -- $* || true
+
+	if rmdir "$PERF_DATA_DIR" > /dev/null 2>/dev/null ; then
+		exit 1
+	fi
+
+	copy_kcore
+
+	echo "Done"
+}
+
+subcommand()
+{
+	find_perf
+	check_buildid_cache_permissions
+	echo "$PERF $PERF_SUB_COMMAND -i $PERF_DATA_DIR/perf.data --kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms $*"
+	"$PERF" $PERF_SUB_COMMAND -i "$PERF_DATA_DIR/perf.data" "--kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms" $*
+}
+
+if [ "$1" = "fix_buildid_cache_permissions" ] ; then
+	fix_buildid_cache_permissions
+	exit 0
+fi
+
+PERF_SUB_COMMAND=$1
+PERF_DATA_DIR=$2
+shift || true
+shift || true
+
+if [ -z "$PERF_SUB_COMMAND" ] ; then
+	usage
+fi
+
+if [ -z "$PERF_DATA_DIR" ] ; then
+	usage
+fi
+
+case "$PERF_SUB_COMMAND" in
+"record")
+	while [ "$1" != "--" ] ; do
+		PERF_OPTIONS+="$1 "
+		shift || break
+	done
+	if [ "$1" != "--" ] ; then
+		echo "Options and workload are required for recording" >&2
+		usage
+	fi
+	shift
+	record $*
+;;
+"script")
+	subcommand $*
+;;
+"report")
+	subcommand $*
+;;
+"inject")
+	subcommand $*
+;;
+*)
+	usage
+;;
+esac
-- 
1.9.3