perf/urgent fixes

Hi Ingo,

Please consider pulling,

- Arnaldo

Test results at the end of this message, as usual.

The following changes since commit 874d48f2af91efc38c720e7c6450547f6ea8c843:

Merge tag 'perf-urgent-for-mingo-4.14-20171005' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2017-10-05 20:07:08 +0200)

are available in the git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo-4.14-20171010

for you to fetch changes up to aa7b4e02b328f0589b6133e72aafb1289f614a79:

tools include uapi bpf.h: Sync kernel ABI header with tooling header (2017-10-09 15:55:45 -0300)

----------------------------------------------------------------
perf/urgent fixes:

- Unbreak 'perf record' for arm/arm64 with events with explicit PMU (Mark Rutland)

- Add missing separator for "perf script -F ip,brstack" (and brstackoff) (Mark Santaniello)

- One line, comment only, sync kernel ABI header with tooling header (Arnaldo Carvalho de Melo)

----------------------------------------------------------------
Arnaldo Carvalho de Melo (1):
tools include uapi bpf.h: Sync kernel ABI header with tooling header

Mark Rutland (1):
perf pmu: Unbreak perf record for arm/arm64 with events with explicit PMU

Mark Santaniello (1):
perf script: Add missing separator for "-F ip,brstack" (and brstackoff)

 tools/include/uapi/linux/bpf.h |  2 +-
 tools/perf/builtin-script.c    |  4 +--
 tools/perf/util/parse-events.c |  9 ++++---
 tools/perf/util/pmu.c          | 56 +++++++++++++++++++++++++++++++-----------
 tools/perf/util/pmu.h          |  1 +
 5 files changed, 50 insertions(+), 22 deletions(-)

Test results:

The first ones are container (docker) based builds of tools/perf with and without libelf support. Where clang is available, it is also used to build perf with/without libelf.

The objtool and samples/bpf/ builds are disabled now that I'm switching from using the sources in a local volume to fetching them from a http server to build it inside the container, to make it easier to build in a container cluster. Those will come back later.

Several are cross builds, the ones with -x-ARCH and the android one, and those may not have all the features built, due to lack of multi-arch devel packages, available and being used so far on just a few, like debian:experimental-x-{arm64,mipsel}.

The 'perf test' one will perform a variety of tests exercising tools/perf/util/, tools/lib/{bpf,traceevent,etc}, as well as run perf commands with a variety of command line event specifications to then intercept the sys_perf_event syscall to check that the perf_event_attr fields are set up as expected, among a variety of other unit tests.

Then there is the 'make -C tools/perf build-test' ones, that build tools/perf/ with a variety of feature sets, exercising the build with an incomplete set of features as well as with a complete one. It is planned to have it run on each of the containers mentioned above, using some container orchestration infrastructure. Get in contact if interested in helping having this in place.

  # dm
   1 alpine:3.4: Ok
   2 alpine:3.5: Ok
   3 alpine:3.6: Ok
   4 alpine:edge: Ok
   5 android-ndk:r12b-arm: Ok
   6 android-ndk:r15c-arm: Ok
   7 centos:5: Ok
   8 centos:6: Ok
   9 centos:7: Ok
  10 debian:7: Ok
  11 debian:8: Ok
  12 debian:9: Ok
  13 debian:experimental: Ok
  14 debian:experimental-x-arm64: Ok
  15 debian:experimental-x-mips: Ok
  16 debian:experimental-x-mips64: Ok
  17 debian:experimental-x-mipsel: Ok
  18 fedora:20: Ok
  19 fedora:21: Ok
  20 fedora:22: Ok
  21 fedora:23: Ok
  22 fedora:24: Ok
  23 fedora:24-x-ARC-uClibc: FAIL

builtin-sched.c: In function 'timehist_sched_switch_event':
builtin-sched.c:2580:1: internal compiler error: in change_address_1, at emit-rtl.c:2150
}
^
util/db-export.c: In function 'db_export__sample':
util/db-export.c:429:1: internal compiler error: in change_address_1, at emit-rtl.c:2150
}
^
Please submit a full bug report,
with preprocessed source if appropriate.
See <https://github.com/foss-for-synopsys-dwc-arc-processors/toolchain/issues> for instructions.

Bug reported: https://github.com/foss-for-synopsys-dwc-arc-processors/toolchain/issues/137

24 fedora:25: Ok
25 fedora:26: Ok
26 fedora:rawhide: Ok
27 mageia:5: Ok
28 opensuse:42.1: Ok
29 opensuse:42.2: Ok
30 opensuse:42.3: Ok
31 opensuse:tumbleweed: Ok
32 oraclelinux:6: Ok
33 oraclelinux:7: O
34 ubuntu:12.04.5: Ok
35 ubuntu:14.04.4: Ok
36 ubuntu:14.04.4-x-linaro-arm64: Ok
37 ubuntu:15.04: Ok
38 ubuntu:15.10: Ok
39 ubuntu:16.04: Ok
40 ubuntu:16.04-x-arm: Ok
41 ubuntu:16.04-x-arm64: Ok
42 ubuntu:16.04-x-powerpc: Ok
43 ubuntu:16.04-x-powerpc64: Ok
44 ubuntu:16.04-x-powerpc64el: Ok
45 ubuntu:16.04-x-s390: Ok
46 ubuntu:16.10: Ok
47 ubuntu:17.04: Ok
48 ubuntu:17.10: Ok

  # uname -a
  Linux jouet 4.13.0+ #3 SMP Mon Sep 25 11:51:22 -03 2017 x86_64 x86_64 x86_64 GNU/Linux
  # perf test
   1: vmlinux symtab matches kallsyms                       : Ok
   2: Detect openat syscall event                           : Ok
   3: Detect openat syscall event on all cpus               : Ok
   4: Read samples using the mmap interface                 : Ok
   5: Test data source output                               : Ok
   6: Parse event definition strings                        : Ok
   7: Simple expression parser                              : Ok
   8: PERF_RECORD_* events & perf_sample fields             : Ok
   9: Parse perf pmu format                                 : Ok
  10: DSO data read                                         : Ok
  11: DSO data cache                                        : Ok
  12: DSO data reopen                                       : Ok
  13: Roundtrip evsel->name                                 : Ok
  14: Parse sched tracepoints fields                        : Ok
  15: syscalls:sys_enter_openat event fields                : Ok
  16: Setup struct perf_event_attr                          : Ok
  17: Match and link multiple hists                         : Ok
  18: 'import perf' in python                               : Ok
  19: Breakpoint overflow signal handler                    : Ok
  20: Breakpoint overflow sampling                          : Ok
  21: Number of exit events of a simple workload            : Ok
  22: Software clock events period values                   : Ok
  23: Object code reading                                   : Ok
  24: Sample parsing                                        : Ok
  25: Use a dummy software event to keep tracking           : Ok
  26: Parse with no sample_id_all bit set                   : Ok
  27: Filter hist entries                                   : Ok
  28: Lookup mmap thread                                    : Ok
  29: Share thread mg                                       : Ok
  30: Sort output of hist entries                           : Ok
  31: Cumulate child hist entries                           : Ok
  32: Track with sched_switch                               : Ok
  33: Filter fds with revents mask in a fdarray             : Ok
  34: Add fd to a fdarray, making it autogrow               : Ok
  35: kmod_path__parse                                      : Ok
  36: Thread map                                            : Ok
  37: LLVM search and compile                               :
  37.1: Basic BPF llvm compile                              : Ok
  37.2: kbuild searching                                    : Ok
  37.3: Compile source for BPF prologue generation          : Ok
  37.4: Compile source for BPF relocation                   : Ok
  38: Session topology                                      : Ok
  39: BPF filter                                            :
  39.1: Basic BPF filtering                                 : Ok
  39.2: BPF pinning                                         : Ok
  39.3: BPF prologue generation                             : Ok
  39.4: BPF relocation checker                              : Ok
  40: Synthesize thread map                                 : Ok
  41: Remove thread map                                     : Ok
  42: Synthesize cpu map                                    : Ok
  43: Synthesize stat config                                : Ok
  44: Synthesize stat                                       : Ok
  45: Synthesize stat round                                 : Ok
  46: Synthesize attr update                                : Ok
  47: Event times                                           : Ok
  48: Read backward ring buffer                             : Ok
  49: Print cpu map                                         : Ok
  50: Probe SDT events                                      : Ok
  51: is_printable_array                                    : Ok
  52: Print bitmap                                          : Ok
  53: perf hooks                                            : Ok
  54: builtin clang support                                 : Skip (not compiled in)
  55: unit_number__scnprintf                                : Ok
  56: x86 rdpmc                                             : Ok
  57: Convert perf time to TSC                              : Ok
  58: DWARF unwind                                          : Ok
  59: x86 instruction decoder - new instructions            : Ok
  60: Intel cqm nmi context read                            : Skip
  61: Use vfs_getname probe to get syscall args filenames   : Ok
  62: probe libc's inet_pton & backtrace it with ping       : Ok
  63: Check open filename arg using perf trace + vfs_getname: Ok
  64: Add vfs_getname probe to get syscall args filenames   : Ok
  #

  $ make -C tools/perf build-test
  make: Entering directory '/home/acme/git/linux/tools/perf'
  - tarpkg: ./tests/perf-targz-src-pkg .
              make_no_libbpf_O: make NO_LIBBPF=1
               make_no_slang_O: make NO_SLANG=1
            make_no_auxtrace_O: make NO_AUXTRACE=1
                   make_tags_O: make tags
        make_with_babeltrace_O: make LIBBABELTRACE=1
                 make_perf_o_O: make perf.o
  make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1
            make_no_libaudit_O: make NO_LIBAUDIT=1
                  make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
           make_no_backtrace_O: make NO_BACKTRACE=1
         make_install_prefix_O: make install prefix=/tmp/krava
             make_no_libnuma_O: make NO_LIBNUMA=1
                  make_debug_O: make DEBUG=1
                make_no_gtk2_O: make NO_GTK2=1
           make_no_libunwind_O: make NO_LIBUNWIND=1
       make_util_pmu_bison_o_O: make util/pmu-bison.o
             make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1
                   make_pure_O: make
                 make_static_O: make LDFLAGS=-static
                make_minimal_O: make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1
            make_no_demangle_O: make NO_DEMANGLE=1
                   make_help_O: make help
                make_install_O: make install
             make_util_map_o_O: make util/map.o
                make_no_newt_O: make NO_NEWT=1
           make_no_libbionic_O: make NO_LIBBIONIC=1
         make_with_clangllvm_O: make LIBCLANGLLVM=1
             make_no_libperl_O: make NO_LIBPERL=1
           make_no_libpython_O: make NO_LIBPYTHON=1
                    make_doc_O: make doc
              make_no_libelf_O: make NO_LIBELF=1
            make_install_bin_O: make install-bin
              make_clean_all_O: make clean all
   make_install_prefix_slash_O: make install prefix=/tmp/krava/
  OK
  make: Leaving directory '/home/acme/git/linux/tools/perf'
$

From: Mark Santaniello <[email protected]>

Prior to commit 55b9b50811ca ("perf script: Support -F brstack,dso and brstacksym,dso"), we were printing a space before the brstack data. It seems that this space was important. Without it, parsing is difficult.

Very sorry for the mistake.

Notice here how the "ip" and "brstack" run together:

$ perf script -F ip,brstack | head -n 1
          22e18c40x22e19e2/0x22e190b/P/-/-/0 0x22e19a1/0x22e19d0/P/-/-/0 0x22e195d/0x22e1990/P/-/-/0 0x22e18e9/0x22e1943/P/-/-/0 0x22e1a69/0x22e18c0/P/-/-/0 0x22e19f7/0x22e1a20/P/-/-/0 0x22e1910/0x22e19ee/P/-/-/0 0x22e19e2/0x22e190b/P/-/-/0 0x22e19a1/0x22e19d0/P/-/-/0 0x22e195d/0x22e1990/P/-/-/0 0x22e18e9/0x22e1943/P/-/-/0 0x22e1a69/0x22e18c0/P/-/-/0 0x22e19f7/0x22e1a20/P/-/-/0 0x22e1910/0x22e19ee/P/-/-/0 0x22e19e2/0x22e190b/P/-/-/0 0x22e19a1/0x22e19d0/P/-/-/0

After this diff, sanity is restored:

$ perf script -F ip,brstack | head -n 1
          22e18c4 0x22e19e2/0x22e190b/P/-/-/0  0x22e19a1/0x22e19d0/P/-/-/0  0x22e195d/0x22e1990/P/-/-/0  0x22e18e9/0x22e1943/P/-/-/0  0x22e1a69/0x22e18c0/P/-/-/0  0x22e19f7/0x22e1a20/P/-/-/0  0x22e1910/0x22e19ee/P/-/-/0  0x22e19e2/0x22e190b/P/-/-/0  0x22e19a1/0x22e19d0/P/-/-/0  0x22e195d/0x22e1990/P/-/-/0  0x22e18e9/0x22e1943/P/-/-/0  0x22e1a69/0x22e18c0/P/-/-/0  0x22e19f7/0x22e1a20/P/-/-/0  0x22e1910/0x22e19ee/P/-/-/0  0x22e19e2/0x22e190b/P/-/-/0  0x22e19a1/0x22e19d0/P/-/-/0

---
 tools/perf/builtin-script.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 3d4c3b5e1868..0c977b6e0f8b 100644
@@ -586,7 +586,7 @@ static void print_sample_brstack(struct perf_sample *sample,
 			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		}
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);

@@ -681,7 +681,7 @@ static void print_sample_brstackoff(struct perf_sample *sample,
 		if (alt.map && !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);

2.13.6

From: Mark Rutland <[email protected]>

Currently, perf record is broken on arm/arm64 systems when the PMU is specified explicitly as part of the event, e.g.

$ ./perf record -e armv8_cortex_a53/cpu_cycles/u true

In such cases, perf record fails to open events unless perf_event_paranoid is set to -1, even if the PMU in question supports mode exclusion. Further, even when perf_event_paranoid is toggled, no samples are recorded.

This is an unintended side effect of commit:

e3ba76deef23064f ("perf tools: Force uncore events to system wide monitoring)

... which assumes that if a PMU has an associated cpu_map, it is an uncore PMU, and forces events for such PMUs to be system-wide.

This is not true for arm/arm64 systems, which can have heterogeneous CPUs. To account for this, multiple CPU PMUs are exposed, each with a "cpus" field under sysfs, which the perf tool parses into a cpu_map. ARM PMUs do not have a "cpumask" file, and only have a "cpus" file. For the gory details as to why, see commit:

7e3fcffe95544010 ("perf pmu: Support alternative sysfs cpumask")

Given all of this, we can instead identify uncore PMUs by explicitly checking for a "cpumask" file, and restore arm/arm64 PMU support back to a working state. This patch does so, adding a new perf_pmu::is_uncore field, and splitting the existing cpumask parsing so that it can be reused.

Tested-by Will Deacon <[email protected]>

---
 tools/perf/util/parse-events.c |  9 ++++---
 tools/perf/util/pmu.c          | 56 +++++++++++++++++++++++++++++++-----------
 tools/perf/util/pmu.h          |  1 +
 3 files changed, 47 insertions(+), 19 deletions(-)

index f6257fb4f08c..39b15968eab1 100644
@@ -309,10 +309,11 @@ static char *get_config_name(struct list_head *head_terms)
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
-	    char *name, struct cpu_map *cpus,
+	    char *name, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats)
 {
 	struct perf_evsel *evsel;
+	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
 
 	event_attr_init(attr);
 

@@ -323,7 +324,7 @@ __add_event(struct list_head *list, int *idx,
 	(*idx)++;
 	evsel->cpus        = cpu_map__get(cpus);
 	evsel->own_cpus    = cpu_map__get(cpus);
-	evsel->system_wide = !!cpus;
+	evsel->system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)

@@ -1233,7 +1234,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		return evsel ? 0 : -ENOMEM;
 	}
 

@@ -1254,7 +1255,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
-			    get_config_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats);
 	if (evsel) {
 		evsel->unit = info.unit;

index 389e9729331f..fe0de0502ce2 100644
@@ -22,6 +22,7 @@ struct perf_pmu {
 	char *name;
 	__u32 type;
 	bool selectable;
+	bool is_uncore;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */

2.13.6

From: Arnaldo Carvalho de Melo <[email protected]>

Silences the checker:

Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'

The 90caccdd8cc0 ("bpf: fix bpf_tail_call() x64 JIT") cset only updated a comment in uapi/bpf.h.

---
 tools/include/uapi/linux/bpf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 43ab5c402f98..f90860d1f897 100644
@@ -312,7 +312,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)

2.13.6

Pulled, thanks a lot Arnaldo!

Ingo