Merge tag 'perf-core-for-mingo-5.5-20191011' 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:

perf trace:

  Arnaldo Carvalho de Melo:

  - Reuse the strace-like syscall_arg_fmt->scnprintf() beautification routines
    (convert integer arguments into strings, like open flags, etc) in tracepoint
    arguments.

    For now the type based scnprintf routines (pid_t, umode_t, etc) and the
    ones based in well known arg name based ("fd", etc) gets associated with
    tracepoint args of that type.

    A tracepoint only arg, "msr", for the msr:{write,read}_msr gets added as
    an initial step.

  - Introduce syscall_arg_fmt->strtoul() methods to be the reverse operation
    of ->scnprintf(), i.e. to go from a string to an integer.

  - Implement --filter, just like in 'perf record', that affects the tracepoint
    events specied thus far in the command line, use the ->strtoul() methods
    to allow strings in tables associated with beautifiers to the integers
    the in-kernel tracepoint (eBPF later) filters expect, e.g.:

     # perf trace --max-events 1 -e sched:*ipi --filter="cpu==1 || cpu==2"
      0.000 as/24630 sched:sched_wake_idle_without_ipi(cpu: 1)
     #

     # perf trace --max-events 1 --max-stack=32 -e msr:* --filter="msr==IA32_TSC_DEADLINE"
      207.000 cc1/19963 msr:write_msr(msr: IA32_TSC_DEADLINE, val: 5442316760822)
                                        do_trace_write_msr ([kernel.kallsyms])
                                        do_trace_write_msr ([kernel.kallsyms])
                                        lapic_next_deadline ([kernel.kallsyms])
                                        clockevents_program_event ([kernel.kallsyms])
                                        hrtimer_interrupt ([kernel.kallsyms])
                                        smp_apic_timer_interrupt ([kernel.kallsyms])
                                        apic_timer_interrupt ([kernel.kallsyms])
                                        [0x6ff66c] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x7047c3] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x707708] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        execute_one_pass (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x4f3d37] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x4f3d49] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        execute_pass_list (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        cgraph_node::expand (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x2625b4] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        symbol_table::finalize_compilation_unit (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x5ae8b9] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        toplev::main (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        main (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x26b6a] (/usr/lib/x86_64-linux-gnu/libc-2.29.so)
     #
     # perf trace --max-events 8 -e msr:* --filter="msr==IA32_SPEC_CTRL"
         0.000 :13281/13281 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.063 migration/3/25 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.217 kworker/u16:1-/4826 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.687 rcu_sched/11 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.696 :13280/13280 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.305 :13281/13281 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.355 :13274/13274 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         2.743 kworker/u16:0-/6711 msr:write_msr(msr: IA32_SPEC_CTRL)
     #
     # perf trace --max-events 8 --cpu 1 -e msr:* --filter="msr!=IA32_SPEC_CTRL && msr!=IA32_TSC_DEADLINE && msr != FS_BASE"
           0.000 mtr-packet/30819 msr:write_msr(msr: 0x830, val: 68719479037)
           0.096 :0/0 msr:read_msr(msr: IA32_TSC_ADJUST)
         238.925 mtr-packet/30819 msr:write_msr(msr: 0x830, val: 8589936893)
         511.010 :0/0 msr:write_msr(msr: 0x830, val: 68719479037)
        1005.052 :0/0 msr:read_msr(msr: IA32_TSC_ADJUST)
        1235.131 CPU 0/KVM/3750 msr:write_msr(msr: 0x830, val: 4294969595)
        1235.195 CPU 0/KVM/3750 msr:read_msr(msr: IA32_SYSENTER_ESP, val: -2199023037952)
        1235.201 CPU 0/KVM/3750 msr:read_msr(msr: IA32_APICBASE, val: 4276096000)
     #

  - Default to not using libtraceevent and its plugins for beautifying
    tracepoint arguments, since now we're reusing the strace-like beatufiers.
    Use --libtraceevent_print (using just --libtrace is unambiguous and can
    be used as a short hand) to go back to those beautifiers.

    This will help in the transition, as can be seen in some of the sched tracepoints
    that still need some work in the libbeauty based mode:

    # trace --no-inherit -e msr:*,*sleep,sched:* sleep 1
         0.000 (         ): sched:sched_waking(comm: "trace", pid: 3319 (trace), prio: 120, success: 1)
         0.006 (         ): sched:sched_wakeup(comm: "trace", pid: 3319 (trace), prio: 120, success: 1)
         0.348 (         ): sched:sched_process_exec(filename: 140212596720100, pid: 3319 (sleep), old_pid: 3319 (sleep))
         0.490 (         ): msr:write_msr(msr: FS_BASE, val: 139631189321088)
         0.670 (         ): nanosleep(rqtp: 0x7ffc52c23bc0)                                    ...
         0.674 (         ): sched:sched_stat_runtime(comm: "sleep", pid: 3319 (sleep), runtime: 659259, vruntime: 78942418342)
         0.675 (         ): sched:sched_switch(prev_comm: "sleep", prev_pid: 3319 (sleep), prev_prio: 120, prev_state: 1, next_comm: "swapper/0", next_prio: 120)
      1001.059 (         ): sched:sched_waking(comm: "sleep", pid: 3319 (sleep), prio: 120, success: 1)
      1001.098 (         ): sched:sched_wakeup(comm: "sleep", pid: 3319 (sleep), prio: 120, success: 1)
         0.670 (1000.504 ms):  ... [continued]: nanosleep())                                        = 0
      1001.456 (         ): sched:sched_process_exit(comm: "sleep", pid: 3319 (sleep), prio: 120)
    # trace --libtrace --no-inherit -e msr:*,*sleep,sched:* sleep 1
    # trace --libtrace --no-inherit -e msr:*,*sleep,sched:* sleep 1
         0.000 (         ): sched:sched_waking(comm=trace pid=3323 prio=120 target_cpu=000)
         0.007 (         ): sched:sched_wakeup(comm=trace pid=3323 prio=120 target_cpu=000)
         0.382 (         ): sched:sched_process_exec(filename=/usr/bin/sleep pid=3323 old_pid=3323)
         0.525 (         ): msr:write_msr(c0000100, value 7f5d508a0580)
         0.713 (         ): nanosleep(rqtp: 0x7fff487fb4a0)                                    ...
         0.717 (         ): sched:sched_stat_runtime(comm=sleep pid=3323 runtime=617722 [ns] vruntime=78957731636 [ns])
         0.719 (         ): sched:sched_switch(prev_comm=sleep prev_pid=3323 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120)
      1001.117 (         ): sched:sched_waking(comm=sleep pid=3323 prio=120 target_cpu=000)
      1001.157 (         ): sched:sched_wakeup(comm=sleep pid=3323 prio=120 target_cpu=000)
         0.713 (1000.522 ms):  ... [continued]: nanosleep())                                        = 0
      1001.538 (         ): sched:sched_process_exit(comm=sleep pid=3323 prio=120)
    #

  - Make -v (verbose) mode be honoured for .perfconfig based trace.add_events,
    to help in diagnosing problems with building eBPF events (-e source.c).

  - When using eBPF syscall payload augmentation do not show strace-like
    syscalls when all the user specified was some tracepoint event, bringing
    the behaviour in line with that of when not using eBPF augmentation.

Intel PT:

  exported-sql-viewer GUI:

  Adrian Hunter:

  - Add LookupModel, HBoxLayout, VBoxLayout, global time range calculations
    so as to add a time chart by CPU.

perf script:

  Andi Kleen:

  - Allow --time (to specify a time span of interest) with --reltime

perf diff:

  Jin Yao:

  - Report noise for cycles diff, i.e. a histogram + stddev.
    (timestamps relative to start).

perf annotate:

  Arnaldo Carvalho de Melo:

  - Initialize env->cpuid when running in live mode (perf top), as it
    is used in some of the per arch annotation init routines.

samples bpf:

  Björn Töpel:

  - Fixup fallout of using tools/perf/perf-sys. from outside tools/perf.

Core:

  Ian Rogers:

  - Avoid 'sample_reg_masks' being const + weak, as this breaks with some
    compilers that constant-propagate from the weak symbol.

libperf:

  - First part of moving the perf_mmap class from tools/perf to libperf.

  - Propagate CFLAGS to libperf from the tools/perf Makefile.

Vendor events:

  John Garry:

  - Add entry in MAINTAINERS with reviewers for the for perf tool arm64
    pmu-events files.

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

10 files changed, 48 insertions, 38 deletions

diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 338cd9faa835..a4cd30c0beb3 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -13,6 +13,7 @@
 #include "util/mmap.h"
 #include <errno.h>
 #include <linux/string.h>
+#include <perf/mmap.h>
 
 #define NR_ITERS 111
 
@@ -37,8 +38,8 @@ static int count_samples(struct evlist *evlist, int *sample_count,
 		struct mmap *map = &evlist->overwrite_mmap[i];
 		union perf_event *event;
 
-		perf_mmap__read_init(map);
-		while ((event = perf_mmap__read_event(map)) != NULL) {
+		perf_mmap__read_init(&map->core);
+		while ((event = perf_mmap__read_event(&map->core)) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
@@ -53,7 +54,7 @@ static int count_samples(struct evlist *evlist, int *sample_count,
 				return TEST_FAIL;
 			}
 		}
-		perf_mmap__read_done(map);
+		perf_mmap__read_done(&map->core);
 	}
 	return TEST_OK;
 }
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 1eb0bffaed6c..5d20bf8397f0 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -15,6 +15,7 @@
 #include <linux/string.h>
 #include <api/fs/fs.h>
 #include <bpf/bpf.h>
+#include <perf/mmap.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
@@ -184,16 +185,16 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 		struct mmap *md;
 
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md) < 0)
+		if (perf_mmap__read_init(&md->core) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md)) != NULL) {
+		while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 			const u32 type = event->header.type;
 
 			if (type == PERF_RECORD_SAMPLE)
 				count ++;
 		}
-		perf_mmap__read_done(md);
+		perf_mmap__read_done(&md->core);
 	}
 
 	if (count != expect) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index f5764a3890b9..1f017e1b2a55 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -10,6 +10,7 @@
 #include <sys/param.h>
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
+#include <perf/mmap.h>
 
 #include "debug.h"
 #include "dso.h"
@@ -425,16 +426,16 @@ static int process_events(struct machine *machine, struct evlist *evlist,
 
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md) < 0)
+		if (perf_mmap__read_init(&md->core) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md)) != NULL) {
+		while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
-			perf_mmap__consume(md);
+			perf_mmap__consume(&md->core);
 			if (ret < 0)
 				return ret;
 		}
-		perf_mmap__read_done(md);
+		perf_mmap__read_done(&md->core);
 	}
 	return 0;
 }
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 92c7d591bcac..50a0c9fcde7d 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -5,6 +5,7 @@
 #include <sys/prctl.h>
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
+#include <perf/mmap.h>
 
 #include "debug.h"
 #include "parse-events.h"
@@ -38,17 +39,17 @@ static int find_comm(struct evlist *evlist, const char *comm)
 	found = 0;
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md) < 0)
+		if (perf_mmap__read_init(&md->core) < 0)
 			continue;
-		while ((event = perf_mmap__read_event(md)) != NULL) {
+		while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 			if (event->header.type == PERF_RECORD_COMM &&
 			    (pid_t)event->comm.pid == getpid() &&
 			    (pid_t)event->comm.tid == getpid() &&
 			    strcmp(event->comm.comm, comm) == 0)
 				found += 1;
-			perf_mmap__consume(md);
+			perf_mmap__consume(&md->core);
 		}
-		perf_mmap__read_done(md);
+		perf_mmap__read_done(&md->core);
 	}
 	return found;
 }
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 3a22dce991ba..5f4c0dbb4715 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <perf/evlist.h>
+#include <perf/mmap.h>
 
 /*
  * This test will generate random numbers of calls to some getpid syscalls,
@@ -113,10 +114,10 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		}
 
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md) < 0)
+	if (perf_mmap__read_init(&md->core) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md)) != NULL) {
+	while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE) {
@@ -139,9 +140,9 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			goto out_delete_evlist;
 		}
 		nr_events[evsel->idx]++;
-		perf_mmap__consume(md);
+		perf_mmap__consume(&md->core);
 	}
-	perf_mmap__read_done(md);
+	perf_mmap__read_done(&md->core);
 
 out_init:
 	err = 0;
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 2b5c46813053..c6b2d7aab608 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -13,6 +13,7 @@
 #include "debug.h"
 #include "util/mmap.h"
 #include <errno.h>
+#include <perf/mmap.h>
 
 #ifndef O_DIRECTORY
 #define O_DIRECTORY    00200000
@@ -92,10 +93,10 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 			struct mmap *md;
 
 			md = &evlist->mmap[i];
-			if (perf_mmap__read_init(md) < 0)
+			if (perf_mmap__read_init(&md->core) < 0)
 				continue;
 
-			while ((event = perf_mmap__read_event(md)) != NULL) {
+			while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 				const u32 type = event->header.type;
 				int tp_flags;
 				struct perf_sample sample;
@@ -103,7 +104,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 				++nr_events;
 
 				if (type != PERF_RECORD_SAMPLE) {
-					perf_mmap__consume(md);
+					perf_mmap__consume(&md->core);
 					continue;
 				}
 
@@ -123,7 +124,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 
 				goto out_ok;
 			}
-			perf_mmap__read_done(md);
+			perf_mmap__read_done(&md->core);
 		}
 
 		if (nr_events == before)
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 437426be29e9..2195fc205e72 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -6,6 +6,7 @@
 #include <pthread.h>
 
 #include <sched.h>
+#include <perf/mmap.h>
 #include "evlist.h"
 #include "evsel.h"
 #include "debug.h"
@@ -170,10 +171,10 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 			struct mmap *md;
 
 			md = &evlist->mmap[i];
-			if (perf_mmap__read_init(md) < 0)
+			if (perf_mmap__read_init(&md->core) < 0)
 				continue;
 
-			while ((event = perf_mmap__read_event(md)) != NULL) {
+			while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 				const u32 type = event->header.type;
 				const char *name = perf_event__name(type);
 
@@ -276,9 +277,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 					++errs;
 				}
 
-				perf_mmap__consume(md);
+				perf_mmap__consume(&md->core);
 			}
-			perf_mmap__read_done(md);
+			perf_mmap__read_done(&md->core);
 		}
 
 		/*
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 84519df87f30..bfb9986093d8 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -15,6 +15,7 @@
 #include "util/mmap.h"
 #include "util/thread_map.h"
 #include <perf/evlist.h>
+#include <perf/mmap.h>
 
 #define NR_LOOPS  10000000
 
@@ -99,10 +100,10 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	evlist__disable(evlist);
 
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md) < 0)
+	if (perf_mmap__read_init(&md->core) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md)) != NULL) {
+	while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE)
@@ -117,9 +118,9 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		total_periods += sample.period;
 		nr_samples++;
 next_event:
-		perf_mmap__consume(md);
+		perf_mmap__consume(&md->core);
 	}
-	perf_mmap__read_done(md);
+	perf_mmap__read_done(&md->core);
 
 out_init:
 	if ((u64) nr_samples == total_periods) {
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index ffa592e0020e..fcb0d03dba4e 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -8,6 +8,7 @@
 #include <linux/zalloc.h>
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
+#include <perf/mmap.h>
 
 #include "debug.h"
 #include "parse-events.h"
@@ -269,17 +270,17 @@ static int process_events(struct evlist *evlist,
 
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md) < 0)
+		if (perf_mmap__read_init(&md->core) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md)) != NULL) {
+		while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 			cnt += 1;
 			ret = add_event(evlist, &events, event);
-			 perf_mmap__consume(md);
+			 perf_mmap__consume(&md->core);
 			if (ret < 0)
 				goto out_free_nodes;
 		}
-		perf_mmap__read_done(md);
+		perf_mmap__read_done(&md->core);
 	}
 
 	events_array = calloc(cnt, sizeof(struct event_node));
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index bce3a4cb4c89..4965f8b9055b 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <perf/cpumap.h>
 #include <perf/evlist.h>
+#include <perf/mmap.h>
 
 static int exited;
 static int nr_exit;
@@ -117,16 +118,16 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
 retry:
 	md = &evlist->mmap[0];
-	if (perf_mmap__read_init(md) < 0)
+	if (perf_mmap__read_init(&md->core) < 0)
 		goto out_init;
 
-	while ((event = perf_mmap__read_event(md)) != NULL) {
+	while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 		if (event->header.type == PERF_RECORD_EXIT)
 			nr_exit++;
 
-		perf_mmap__consume(md);
+		perf_mmap__consume(&md->core);
 	}
-	perf_mmap__read_done(md);
+	perf_mmap__read_done(&md->core);
 
 out_init:
 	if (!exited || !nr_exit) {