Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  o Add +field argument support for --sort option (Jiri Olsa)

  o Do not access kallsyms when analyzing user binaries with 'probe' (Masami Hiramatsu)

  o Ignore stripped vmlinux and fallback to kallsyms (Anton Blanchard)

  o Add path to Ubuntu kernel debuginfo file (Anton Blanchard)

  o Disable kernel symbol demangling by default (Avi Kivity)

Infrastructure changes:

  o More intel PT prep work, from Adrian Hunter, including:

    - Let a user specify a PMU event without any config terms
    - Add perf-with-kcore script
    - Let default config be defined for a PMU
    - Add perf_pmu__scan_file()

  o "perf kvm stat report" improvements by Alexander Yarygin:
    o  Save pid string in opts.target.pid
    o  Enable the target.system_wide flag
    o  Unify the title bar output

  o Fix build issue on powerpc when DWARF support is disabled (Anton Blanchard)

  o Allow to specify lib compile variable for spec usage (Jiri Olsa)

  o Fix build on ARM (Stephane Eranian)

  o Fix build on powerpc when DWARF support is disabled (Anton Blanchard)

  o Don't include sys/poll.h directly (Arnaldo Carvalho de Melo)

  o Use ring buffer consume method to look like other tools (Arnaldo Carvalho de Melo)

  o Allow to specify lib compile variable for spec usage (Jiri Olsa)

  o Fix GNU-only grep usage in Makefile (John Spencer)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

31 files changed, 487 insertions, 60 deletions

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/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 1513935c399b..aaa869be3dc1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -104,6 +104,9 @@ OPTIONS
         Specify path to the executable or shared library file for user
         space tracing. Can also be used with --funcs option.
 
+--demangle-kernel::
+        Demangle kernel symbols.
+
 In absence of -m/-x options, perf probe checks if the first argument after
 the options is an absolute path name. If its an absolute path, perf probe
 uses it as a target module/target user space binary to probe.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d561e0214f52..0927bf4e6c2a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -276,6 +276,9 @@ OPTIONS
         Demangle symbol names to human readable form. It's enabled by default,
         disable with --no-demangle.
 
+--demangle-kernel::
+        Demangle kernel symbol names to human readable form (for C++ kernels).
+
 --mem-mode::
         Use the data addresses of samples in addition to instruction addresses
         to build the histograms.  To generate meaningful output, the perf.data
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 28fdee394880..3265b1070518 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -98,6 +98,9 @@ Default is to monitor all CPUS.
 --hide_user_symbols::
         Hide user symbols.
 
+--demangle-kernel::
+        Demangle kernel symbols.
+
 -D::
 --dump-symtab::
         Dump the symbol table used for profiling.
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/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 9f870d27cb39..62eff847f91c 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "thread.h"
 #include "map.h"
 #include "event.h"
+#include "debug.h"
 #include "tests/tests.h"
 
 #define STACK_SIZE 8192
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index 729ed69a6664..62c397ed3d97 100644
--- a/tools/perf/arch/arm/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index b92219b1900d..6f7782bea5dd 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,6 +1,6 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 52a56599a543..d7f281c2828d 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -26,7 +26,7 @@
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include <sys/time.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <limits.h>
 #include <err.h>
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 1a4ef9cd9d5f..f5d3ae483110 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -543,14 +543,12 @@ static void print_vcpu_info(struct perf_kvm_stat *kvm)
 
         pr_info("Analyze events for ");
 
-        if (kvm->live) {
-                if (kvm->opts.target.system_wide)
-                        pr_info("all VMs, ");
-                else if (kvm->opts.target.pid)
-                        pr_info("pid(s) %s, ", kvm->opts.target.pid);
-                else
-                        pr_info("dazed and confused on what is monitored, ");
-        }
+        if (kvm->opts.target.system_wide)
+                pr_info("all VMs, ");
+        else if (kvm->opts.target.pid)
+                pr_info("pid(s) %s, ", kvm->opts.target.pid);
+        else
+                pr_info("dazed and confused on what is monitored, ");
 
         if (vcpu == -1)
                 pr_info("all VCPUs:\n\n");
@@ -1085,8 +1083,8 @@ static int read_events(struct perf_kvm_stat *kvm)
 
 static int parse_target_str(struct perf_kvm_stat *kvm)
 {
-        if (kvm->pid_str) {
-                kvm->pid_list = intlist__new(kvm->pid_str);
+        if (kvm->opts.target.pid) {
+                kvm->pid_list = intlist__new(kvm->opts.target.pid);
                 if (kvm->pid_list == NULL) {
                         pr_err("Error parsing process id string\n");
                         return -EINVAL;
@@ -1188,7 +1186,7 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
                 OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
                             "key for sorting: sample(sort by samples number)"
                             " time (sort by avg time)"),
-                OPT_STRING('p', "pid", &kvm->pid_str, "pid",
+                OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
                            "analyze events only for given process id(s)"),
                 OPT_END()
         };
@@ -1207,6 +1205,9 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
                                            kvm_events_report_options);
         }
 
+        if (!kvm->opts.target.pid)
+                kvm->opts.target.system_wide = true;
+
         return kvm_events_report_vcpu(kvm);
 }
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 347729e29a92..04412b4770a2 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -376,6 +376,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                         "target executable name or path", opt_set_target),
         OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
                     "Disable symbol demangling"),
+        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+                    "Enable kernel symbol demangling"),
         OPT_END()
         };
         int ret;
@@ -470,7 +472,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                         usage_with_options(probe_usage, options);
                 }
 
-                ret = show_line_range(&params.line_range, params.target);
+                ret = show_line_range(&params.line_range, params.target,
+                                      params.uprobes);
                 if (ret < 0)
                         pr_err_with_code("  Error: Failed to show lines.", ret);
                 return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 87e28a4e33ba..a1b040394170 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -65,8 +65,9 @@ static int process_synthesized_event(struct perf_tool *tool,
         return record__write(rec, event, event->header.size);
 }
 
-static int record__mmap_read(struct record *rec, struct perf_mmap *md)
+static int record__mmap_read(struct record *rec, int idx)
 {
+        struct perf_mmap *md = &rec->evlist->mmap[idx];
         unsigned int head = perf_mmap__read_head(md);
         unsigned int old = md->prev;
         unsigned char *data = md->base + page_size;
@@ -102,8 +103,7 @@ static int record__mmap_read(struct record *rec, struct perf_mmap *md)
         }
 
         md->prev = old;
-        perf_mmap__write_tail(md, old);
-
+        perf_evlist__mmap_consume(rec->evlist, idx);
 out:
         return rc;
 }
@@ -245,7 +245,7 @@ static int record__mmap_read_all(struct record *rec)
 
         for (i = 0; i < rec->evlist->nr_mmaps; i++) {
                 if (rec->evlist->mmap[i].base) {
-                        if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+                        if (record__mmap_read(rec, i) != 0) {
                                 rc = -1;
                                 goto out;
                         }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3da59a87ec7c..8c0b3f22412a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -680,6 +680,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                    "objdump binary to use for disassembly and annotations"),
         OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
                     "Disable symbol demangling"),
+        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+                    "Enable kernel symbol demangling"),
         OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
         OPT_CALLBACK(0, "percent-limit", &report, "percent",
                      "Don't show entries under that percent", parse_percent_limit),
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 9848e270b92c..e13864be2acb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -59,7 +59,7 @@
 
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <sys/prctl.h>
 #include <sys/wait.h>
 #include <sys/uio.h>
@@ -1142,6 +1142,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Interleave source code with assembly code (default)"),
         OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
                     "Display raw encoding of assembly instructions (default)"),
+        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+                    "Enable kernel symbol demangling"),
         OPT_STRING(0, "objdump", &objdump_path, "path",
                     "objdump binary to use for disassembly and annotations"),
         OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 75d4c237b03d..58f609198c6d 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -48,10 +48,6 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
-ifeq ($(ARCH),powerpc)
-  CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
-endif
-
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else
@@ -378,6 +374,12 @@ ifndef NO_LIBELF
   endif # NO_DWARF
 endif # NO_LIBELF
 
+ifeq ($(ARCH),powerpc)
+  ifndef NO_DWARF
+    CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
+  endif
+endif
+
 ifndef NO_LIBUNWIND
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
@@ -651,11 +653,13 @@ else
 sysconfdir = $(prefix)/etc
 ETC_PERFCONFIG = etc/perfconfig
 endif
+ifndef lib
 ifeq ($(IS_X86_64),1)
 lib = lib64
 else
 lib = lib
 endif
+endif # lib
 libdir = $(prefix)/$(lib)
 
 # Shell quote (do not use $(call) to accommodate ancient setups);
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 4d985e0f03f5..7076a62d0ff7 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -132,7 +132,7 @@ endef
 #
 # Usage: bool-value = $(call is-absolute,path)
 #
-is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+is-absolute = $(shell echo $(shell-sq) | grep -q ^/ && echo y)
 
 # lookup
 #
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
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 12b322fa3475..eeb68bb1972d 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,7 @@ int test__pmu(void)
                 if (ret)
                         break;
 
-                ret = perf_pmu__config_terms(&formats, &attr, terms);
+                ret = perf_pmu__config_terms(&formats, &attr, terms, false);
                 if (ret)
                         break;
 
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index 0b5a8cd2ee79..cf1d7913783b 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -92,7 +92,6 @@ struct perf_kvm_stat {
         u64 lost_events;
         u64 duration;
 
-        const char *pid_str;
         struct intlist *pid_list;
 
         struct rb_root result;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e34c81a0bcf3..61be3e695ec2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -643,7 +643,18 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
         if (!pmu)
                 return -EINVAL;
 
-        memset(&attr, 0, sizeof(attr));
+        if (pmu->default_config) {
+                memcpy(&attr, pmu->default_config,
+                       sizeof(struct perf_event_attr));
+        } else {
+                memset(&attr, 0, sizeof(attr));
+        }
+
+        if (!head_config) {
+                attr.type = pmu->type;
+                evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+                return evsel ? 0 : -ENOMEM;
+        }
 
         if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
                 return -EINVAL;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 0bc87ba46bf3..55fab6ad609a 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -210,6 +210,16 @@ PE_NAME '/' event_config '/'
         parse_events__free_terms($3);
         $$ = list;
 }
+|
+PE_NAME '/' '/'
+{
+        struct parse_events_evlist *data = _data;
+        struct list_head *list;
+
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+        $$ = list;
+}
 
 value_sym:
 PE_VALUE_SYM_HW
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9bf582750561..22a4ad5a927a 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,8 @@
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -387,6 +389,12 @@ static struct cpu_map *pmu_cpumask(const char *name)
         return cpus;
 }
 
+struct perf_event_attr *__attribute__((weak))
+perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+        return NULL;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
         struct perf_pmu *pmu;
@@ -421,6 +429,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
         pmu->name = strdup(name);
         pmu->type = type;
         list_add_tail(&pmu->list, &pmus);
+
+        pmu->default_config = perf_pmu__get_default_config(pmu);
+
         return pmu;
 }
 
@@ -479,28 +490,24 @@ pmu_find_format(struct list_head *formats, char *name)
 }
 
 /*
- * Returns value based on the format definition (format parameter)
+ * Sets value based on the format definition (format parameter)
  * and unformated value (value parameter).
- *
- * TODO maybe optimize a little ;)
  */
-static __u64 pmu_format_value(unsigned long *format, __u64 value)
+static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
+                             bool zero)
 {
         unsigned long fbit, vbit;
-        __u64 v = 0;
 
         for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
 
                 if (!test_bit(fbit, format))
                         continue;
 
-                if (!(value & (1llu << vbit++)))
-                        continue;
-
-                v |= (1llu << fbit);
+                if (value & (1llu << vbit++))
+                        *v |= (1llu << fbit);
+                else if (zero)
+                        *v &= ~(1llu << fbit);
         }
-
-        return v;
 }
 
 /*
@@ -509,7 +516,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
  */
 static int pmu_config_term(struct list_head *formats,
                            struct perf_event_attr *attr,
-                           struct parse_events_term *term)
+                           struct parse_events_term *term,
+                           bool zero)
 {
         struct perf_pmu_format *format;
         __u64 *vp;
@@ -548,18 +556,19 @@ static int pmu_config_term(struct list_head *formats,
          * non-hardcoded terms, here's the place to translate
          * them into value.
          */
-        *vp |= pmu_format_value(format->bits, term->val.num);
+        pmu_format_value(format->bits, term->val.num, vp, zero);
         return 0;
 }
 
 int perf_pmu__config_terms(struct list_head *formats,
                            struct perf_event_attr *attr,
-                           struct list_head *head_terms)
+                           struct list_head *head_terms,
+                           bool zero)
 {
         struct parse_events_term *term;
 
         list_for_each_entry(term, head_terms, list)
-                if (pmu_config_term(formats, attr, term))
+                if (pmu_config_term(formats, attr, term, zero))
                         return -EINVAL;
 
         return 0;
@@ -573,8 +582,10 @@ int perf_pmu__config_terms(struct list_head *formats,
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
                      struct list_head *head_terms)
 {
+        bool zero = !!pmu->default_config;
+
         attr->type = pmu->type;
-        return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+        return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -794,3 +805,39 @@ bool pmu_have_event(const char *pname, const char *name)
         }
         return false;
 }
+
+static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+{
+        struct stat st;
+        char path[PATH_MAX];
+        const char *sysfs;
+
+        sysfs = sysfs__mountpoint();
+        if (!sysfs)
+                return NULL;
+
+        snprintf(path, PATH_MAX,
+                 "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
+
+        if (stat(path, &st) < 0)
+                return NULL;
+
+        return fopen(path, "r");
+}
+
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+                        ...)
+{
+        va_list args;
+        FILE *file;
+        int ret = EOF;
+
+        va_start(args, fmt);
+        file = perf_pmu__open_file(pmu, name);
+        if (file) {
+                ret = vfscanf(file, fmt, args);
+                fclose(file);
+        }
+        va_end(args);
+        return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1c1e2eecbe1f..0f5c0a88fdc8 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -13,9 +13,12 @@ enum {
 
 #define PERF_PMU_FORMAT_BITS 64
 
+struct perf_event_attr;
+
 struct perf_pmu {
         char *name;
         __u32 type;
+        struct perf_event_attr *default_config;
         struct cpu_map *cpus;
         struct list_head format;  /* HEAD struct perf_pmu_format -> list */
         struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
@@ -27,7 +30,8 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
                      struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,
                            struct perf_event_attr *attr,
-                           struct list_head *head_terms);
+                           struct list_head *head_terms,
+                           bool zero);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
                           const char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
@@ -45,5 +49,11 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+                        ...) __attribute__((format(scanf, 3, 4)));
+
 int perf_pmu__test(void);
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index f73595fc0627..be37b5aca335 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -697,11 +697,11 @@ end:
         return ret;
 }
 
-int show_line_range(struct line_range *lr, const char *module)
+int show_line_range(struct line_range *lr, const char *module, bool user)
 {
         int ret;
 
-        ret = init_symbol_maps(false);
+        ret = init_symbol_maps(user);
         if (ret < 0)
                 return ret;
         ret = __show_line_range(lr, module);
@@ -776,7 +776,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
         int i, ret = 0;
         struct debuginfo *dinfo;
 
-        ret = init_symbol_maps(false);
+        ret = init_symbol_maps(pevs->uprobes);
         if (ret < 0)
                 return ret;
 
@@ -822,7 +822,8 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 }
 
 int show_line_range(struct line_range *lr __maybe_unused,
-                    const char *module __maybe_unused)
+                    const char *module __maybe_unused,
+                    bool user __maybe_unused)
 {
         pr_warning("Debuginfo-analysis is not supported.\n");
         return -ENOSYS;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 776c9347a3b6..e01e9943139f 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -128,7 +128,8 @@ extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
                                  bool force_add);
 extern int del_perf_probe_events(struct strlist *dellist);
 extern int show_perf_probe_events(void);
-extern int show_line_range(struct line_range *lr, const char *module);
+extern int show_line_range(struct line_range *lr, const char *module,
+                           bool user);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
                                int max_probe_points, const char *module,
                                struct strfilter *filter, bool externs);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 9c593561aa71..c7918f83b300 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -609,14 +609,18 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
                 return -EINVAL;
         }
 
-        /* Get an appropriate symbol from symtab */
-        symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+        symbol = dwarf_diename(sp_die);
         if (!symbol) {
-                pr_warning("Failed to find symbol at 0x%lx\n",
-                           (unsigned long)paddr);
-                return -ENOENT;
+                /* Try to get the symbol name from symtab */
+                symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+                if (!symbol) {
+                        pr_warning("Failed to find symbol at 0x%lx\n",
+                                   (unsigned long)paddr);
+                        return -ENOENT;
+                }
+                eaddr = sym.st_value;
         }
-        tp->offset = (unsigned long)(paddr - sym.st_value);
+        tp->offset = (unsigned long)(paddr - eaddr);
         tp->address = (unsigned long)paddr;
         tp->symbol = strdup(symbol);
         if (!tp->symbol)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 1958637cf136..289df9d1e65a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1446,12 +1446,47 @@ static const char *get_default_sort_order(void)
         return default_sort_orders[sort__mode];
 }
 
+static int setup_sort_order(void)
+{
+        char *new_sort_order;
+
+        /*
+         * Append '+'-prefixed sort order to the default sort
+         * order string.
+         */
+        if (!sort_order || is_strict_order(sort_order))
+                return 0;
+
+        if (sort_order[1] == '\0') {
+                error("Invalid --sort key: `+'");
+                return -EINVAL;
+        }
+
+        /*
+         * We allocate new sort_order string, but we never free it,
+         * because it's checked over the rest of the code.
+         */
+        if (asprintf(&new_sort_order, "%s,%s",
+                     get_default_sort_order(), sort_order + 1) < 0) {
+                error("Not enough memory to set up --sort");
+                return -ENOMEM;
+        }
+
+        sort_order = new_sort_order;
+        return 0;
+}
+
 static int __setup_sorting(void)
 {
         char *tmp, *tok, *str;
-        const char *sort_keys = sort_order;
+        const char *sort_keys;
         int ret = 0;
 
+        ret = setup_sort_order();
+        if (ret)
+                return ret;
+
+        sort_keys = sort_order;
         if (sort_keys == NULL) {
                 if (is_strict_order(field_order)) {
                         /*
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 9fb5e9e9f161..2a92e10317c5 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -680,6 +680,11 @@ static u64 ref_reloc(struct kmap *kmap)
         return 0;
 }
 
+static bool want_demangle(bool is_kernel_sym)
+{
+        return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map,
                   struct symsrc *syms_ss, struct symsrc *runtime_ss,
                   symbol_filter_t filter, int kmodule)
@@ -712,6 +717,14 @@ int dso__load_sym(struct dso *dso, struct map *map,
                 symbols__delete(&dso->symbols[map->type]);
 
         if (!syms_ss->symtab) {
+                /*
+                 * If the vmlinux is stripped, fail so we will fall back
+                 * to using kallsyms. The vmlinux runtime symbols aren't
+                 * of much use.
+                 */
+                if (dso->kernel)
+                        goto out_elf_end;
+
                 syms_ss->symtab  = syms_ss->dynsym;
                 syms_ss->symshdr = syms_ss->dynshdr;
         }
@@ -938,7 +951,7 @@ new_symbol:
                  * DWARF DW_compile_unit has this, but we don't always have access
                  * to it...
                  */
-                if (symbol_conf.demangle) {
+                if (want_demangle(dso->kernel || kmodule)) {
                         int demangle_flags = DMGL_NO_OPTS;
                         if (verbose)
                                 demangle_flags = DMGL_PARAMS | DMGL_ANSI;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ac098a3c2a31..be84f7a9838b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -34,6 +34,7 @@ struct symbol_conf symbol_conf = {
         .try_vmlinux_path       = true,
         .annotate_src           = true,
         .demangle               = true,
+        .demangle_kernel        = false,
         .cumulate_callchain     = true,
         .show_hist_headers      = true,
         .symfs                  = "",
@@ -1756,7 +1757,7 @@ static int vmlinux_path__init(struct perf_session_env *env)
         char bf[PATH_MAX];
         char *kernel_version;
 
-        vmlinux_path = malloc(sizeof(char *) * 5);
+        vmlinux_path = malloc(sizeof(char *) * 6);
         if (vmlinux_path == NULL)
                 return -1;
 
@@ -1787,6 +1788,12 @@ static int vmlinux_path__init(struct perf_session_env *env)
         if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
                 goto out_fail;
         ++vmlinux_path__nr_entries;
+        snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
+                 kernel_version);
+        vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
+        if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+                goto out_fail;
+        ++vmlinux_path__nr_entries;
         snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
         vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
         if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 3f95ea0357e3..bec4b7bd09de 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -120,6 +120,7 @@ struct symbol_conf {
                         annotate_src,
                         event_group,
                         demangle,
+                        demangle_kernel,
                         filter_relative,
                         show_hist_headers;
         const char      *vmlinux_name,
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index d6a79b1fb28c..80bfdaa0e2a4 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,6 +39,8 @@
 
 #define _ALL_SOURCE 1
 #define _BSD_SOURCE 1
+/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
+#define _DEFAULT_SOURCE 1
 #define HAS_BOOL
 
 #include <unistd.h>
@@ -64,7 +66,7 @@
 #include <regex.h>
 #include <utime.h>
 #include <sys/wait.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <inttypes.h>