Merge tag 'perf-core-for-mingo-5.4-20190920-2' of git://git.kernel.or…

…g/pub/scm/linux/kernel/git/acme/linux into perf/urgent

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

perf stat:

  Srikar Dronamraju:

  - Fix a segmentation fault when using repeat forever.

  - Reset previous counts on repeat with interval.

aarch64:

  James Clark:

  - Add PMU event JSON files for Cortex-A76 and Neoverse N1.

PowerPC:

  Anju T Sudhakar:

  - Make 'trace_cycles' the default event for 'perf kvm record' in PowerPC.

S/390:

  - Link libjvmti to tools/lib/string.o to have a weak strlcpy()
    implementation, providing previously unresolved symbol on s/390.

perf test:

  Jiri Olsa:

  - Add libperf automated tests to 'make -C tools/perf build-test'.

  Colin Ian King:

  - Fix spelling mistake.

Tree wide:

  Arnaldo Carvalho de Melo:

  - Some more header file sanitization.

libperf:

  Jiri Olsa:

  - Add dependency on libperf for python.so binding.

libtraceevent:

  Sakari Ailus:

  - Convert remaining %p[fF] users to %p[sS].

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

tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt

@@ -59,12 +59,12 @@ parser context.
 
 The _tep_register_function()_ function registers a function name mapped to an
 address and (optional) module. This mapping is used in case the function tracer
-or events have "%pF" or "%pS" parameter in its format string. It is common to
-pass in the kallsyms function names with their corresponding addresses with this
+or events have "%pS" parameter in its format string. It is common to pass in
+the kallsyms function names with their corresponding addresses with this
 function. The _tep_ argument is the trace event parser context. The _name_ is
-the name of the function, the string is copied internally. The _addr_ is
-the start address of the function. The _mod_ is the kernel module
-the function may be in (NULL for none).
+the name of the function, the string is copied internally. The _addr_ is the
+start address of the function. The _mod_ is the kernel module the function may
+be in (NULL for none).
 
 The _tep_register_print_string()_ function  registers a string by the address
 it was stored in the kernel. Some strings internal to the kernel with static

tools/lib/traceevent/event-parse.c

@@ -4367,10 +4367,20 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					switch (*ptr) {
 					case 's':
 					case 'S':
-					case 'f':
-					case 'F':
 					case 'x':
 						break;
+					case 'f':
+					case 'F':
+						/*
+						 * Pre-5.5 kernels use %pf and
+						 * %pF for printing symbols
+						 * while kernels since 5.5 use
+						 * %pfw for fwnodes. So check
+						 * %p[fF] isn't followed by 'w'.
+						 */
+						if (ptr[1] != 'w')
+							break;
+						/* fall through */
 					default:
 						/*
 						 * Older kernels do not process
@@ -4487,12 +4497,12 @@ get_bprint_format(void *data, int size __maybe_unused,
 
 	printk = find_printk(tep, addr);
 	if (!printk) {
-		if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
+		if (asprintf(&format, "%%ps: (NO FORMAT FOUND at %llx)\n", addr) < 0)
 			return NULL;
 		return format;
 	}
 
-	if (asprintf(&format, "%s: %s", "%pf", printk->printk) < 0)
+	if (asprintf(&format, "%s: %s", "%ps", printk->printk) < 0)
 		return NULL;
 
 	return format;

tools/perf/Makefile.perf

@@ -567,7 +567,7 @@ all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 # Create python binding output directory if not already present
 _dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python')
 
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST) $(LIBPERF)
 	$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
         CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
 	  $(PYTHON_WORD) util/setup.py \

tools/perf/arch/arm/util/cs-etm.c

@@ -25,7 +25,7 @@
 #include "../../util/evsel.h"
 #include "../../util/pmu.h"
 #include "../../util/cs-etm.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/session.h"
 
 #include <errno.h>

tools/perf/arch/arm64/util/arm-spe.c

@@ -16,7 +16,7 @@
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
 #include "../../util/session.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
 #include "../../util/auxtrace.h"

tools/perf/arch/arm64/util/dwarf-regs.c

@@ -11,7 +11,6 @@
 #include <dwarf-regs.h>
 #include <linux/ptrace.h> /* for struct user_pt_regs */
 #include <linux/stringify.h>
-#include "util.h"
 
 struct pt_regs_dwarfnum {
 	const char *name;

tools/perf/arch/arm64/util/header.c

@@ -1,5 +1,7 @@
 #include <stdio.h>
 #include <stdlib.h>
+#include <perf/cpumap.h>
+#include <internal/cpumap.h>
 #include <api/fs/fs.h>
 #include "debug.h"
 #include "header.h"
@@ -29,7 +31,7 @@ char *get_cpuid_str(struct perf_pmu *pmu)
 
 	/* read midr from list of cpus mapped to this pmu */
 	cpus = perf_cpu_map__get(pmu->cpus);
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
 		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
 				sysfs, cpus->map[cpu]);
 

tools/perf/arch/arm64/util/unwind-libunwind.c

@@ -5,8 +5,8 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-#include "../../util/debug.h"
 #endif
+#include "../../util/debug.h"
 
 int LIBUNWIND__ARCH_REG_ID(int regnum)
 {

tools/perf/arch/powerpc/util/dwarf-regs.c

@@ -12,7 +12,6 @@
 #include <linux/ptrace.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
-#include "util.h"
 
 struct pt_regs_dwarfnum {
 	const char *name;

tools/perf/arch/powerpc/util/header.c

@@ -6,7 +6,6 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
-#include "util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \

tools/perf/arch/powerpc/util/kvm-stat.c

@@ -5,9 +5,11 @@
 #include "util/debug.h"
 #include "util/evsel.h"
 #include "util/evlist.h"
+#include "util/pmu.h"
 
 #include "book3s_hv_exits.h"
 #include "book3s_hcalls.h"
+#include <subcmd/parse-options.h>
 
 #define NR_TPS 4
 
@@ -172,3 +174,46 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
 
 	return ret;
 }
+
+/*
+ * Incase of powerpc architecture, pmu registers are programmable
+ * by guest kernel. So monitoring guest via host may not provide
+ * valid samples with default 'cycles' event. It is better to use
+ * 'trace_imc/trace_cycles' event for guest profiling, since it
+ * can track the guest instruction pointer in the trace-record.
+ *
+ * Function to parse the arguments and return appropriate values.
+ */
+int kvm_add_default_arch_event(int *argc, const char **argv)
+{
+	const char **tmp;
+	bool event = false;
+	int i, j = *argc;
+
+	const struct option event_options[] = {
+		OPT_BOOLEAN('e', "event", &event, NULL),
+		OPT_END()
+	};
+
+	tmp = calloc(j + 1, sizeof(char *));
+	if (!tmp)
+		return -EINVAL;
+
+	for (i = 0; i < j; i++)
+		tmp[i] = argv[i];
+
+	parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN);
+	if (!event) {
+		if (pmu_have_event("trace_imc", "trace_cycles")) {
+			argv[j++] = strdup("-e");
+			argv[j++] = strdup("trace_imc/trace_cycles/");
+			*argc += 2;
+		} else {
+			free(tmp);
+			return -EINVAL;
+		}
+	}
+
+	free(tmp);
+	return 0;
+}

tools/perf/arch/powerpc/util/skip-callchain-idx.c

@@ -13,6 +13,7 @@
 #include "util/callchain.h"
 #include "util/debug.h"
 #include "util/dso.h"
+#include "util/event.h" // struct ip_callchain
 #include "util/map.h"
 #include "util/symbol.h"
 

tools/perf/arch/powerpc/util/sym-handling.c

@@ -4,7 +4,6 @@
  * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
  */
 
-#include "debug.h"
 #include "dso.h"
 #include "symbol.h"
 #include "map.h"

tools/perf/arch/s390/util/machine.c

@@ -2,7 +2,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
-#include "util.h"
+#include "util.h" // page_size
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"

tools/perf/arch/x86/tests/intel-cqm.c

@@ -5,7 +5,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "arch-tests.h"
-#include "util.h"
 
 #include <signal.h>
 #include <sys/mman.h>

tools/perf/arch/x86/tests/perf-time-to-tsc.c

@@ -15,7 +15,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "record.h"
 #include "tsc.h"
 #include "tests/tests.h"

tools/perf/arch/x86/tests/rdpmc.c

@@ -13,7 +13,7 @@
 #include "tests/tests.h"
 #include "cloexec.h"
 #include "event.h"
-#include "util.h"
+#include "util.h" // page_size
 #include "arch-tests.h"
 
 static u64 rdpmc(unsigned int counter)

tools/perf/arch/x86/util/archinsn.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../../../../arch/x86/include/asm/insn.h"
 #include "archinsn.h"
+#include "event.h"
 #include "machine.h"
 #include "thread.h"
 #include "symbol.h"

tools/perf/arch/x86/util/event.c

@@ -3,6 +3,8 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 
+#include "../../util/event.h"
+#include "../../util/synthetic-events.h"
 #include "../../util/machine.h"
 #include "../../util/tool.h"
 #include "../../util/map.h"

tools/perf/arch/x86/util/intel-bts.c

@@ -22,7 +22,7 @@
 #include "../../util/tsc.h"
 #include "../../util/auxtrace.h"
 #include "../../util/intel-bts.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)

tools/perf/arch/x86/util/intel-pt.c

@@ -26,7 +26,7 @@
 #include "../../util/record.h"
 #include "../../util/target.h"
 #include "../../util/tsc.h"
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/intel-pt.h"
 
 #define KiB(x) ((x) * 1024)

tools/perf/arch/x86/util/machine.c

@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/string.h>
+#include <limits.h>
 #include <stdlib.h>
 
-#include "../../util/util.h"
+#include "../../util/util.h" // page_size
 #include "../../util/machine.h"
 #include "../../util/map.h"
 #include "../../util/symbol.h"

tools/perf/arch/x86/util/tsc.c

@@ -8,6 +8,8 @@
 #include <linux/types.h>
 #include <asm/barrier.h>
 #include "../../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
 #include "../../../util/tsc.h"
 
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,

tools/perf/bench/epoll-ctl.c

@@ -21,12 +21,12 @@
 #include <sys/resource.h>
 #include <sys/epoll.h>
 #include <sys/eventfd.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
-#include "cpumap.h"
 
 #include <err.h>
 

tools/perf/bench/epoll-wait.c

@@ -76,12 +76,12 @@
 #include <sys/epoll.h>
 #include <sys/eventfd.h>
 #include <sys/types.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
-#include "cpumap.h"
 
 #include <err.h>
 

tools/perf/bench/futex-hash.c

@@ -20,13 +20,13 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <sys/time.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 

tools/perf/bench/futex-lock-pi.c

@@ -14,10 +14,10 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/futex-requeue.c

@@ -20,10 +20,10 @@
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/futex-wake-parallel.c

@@ -29,7 +29,8 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe
 #include <linux/time64.h>
 #include <errno.h>
 #include "futex.h"
-#include "cpumap.h"
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/futex-wake.c

@@ -20,10 +20,10 @@
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/numa.c

@@ -9,7 +9,6 @@
 /* For the CLR_() macros */
 #include <pthread.h>
 
-#include "../builtin.h"
 #include <subcmd/parse-options.h>
 #include "../util/cloexec.h"