From d2785de15f1bd42d613d56bbac5a007e7293b874 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Mon, 12 Feb 2018 13:32:37 -0700 Subject: perf auxtrace arm: Fixing uninitialised variable When working natively on arm64 the compiler gets pesky and complains that variable 'i' is uninitialised, something that breaks the compilation. Here no further checks are needed since variable 'found_spe' can only be true if variable 'i' has been initialised as part of the for loop. Signed-off-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1518467557-18505-4-git-send-email-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/auxtrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 2323581b157d..fa639e3e52ac 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -68,7 +68,7 @@ struct auxtrace_record bool found_spe = false; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; - int i; + int i = 0; if (!evlist) return NULL; -- cgit From 796bfadd831bdef0de06cd0253398c3fe011e459 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Mon, 12 Feb 2018 16:38:57 -0700 Subject: perf cs-etm: Properly deal with cpu maps This patch allows the CoreSight AUX info section to fit topologies where only a subset of all available CPUs are present, avoiding at the same time accessing the ETM configuration areas of CPUs that have been offlined. Signed-off-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1518478737-24649-1-git-send-email-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 51 +++++++++++++++++++++++++++------------ 1 file changed, 36 insertions(+), 15 deletions(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index fbfc055d3f4d..5c655ad4621e 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -298,12 +298,17 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, { int i; int etmv3 = 0, etmv4 = 0; - const struct cpu_map *cpus = evlist->cpus; + struct cpu_map *event_cpus = evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); /* cpu map is not empty, we have specific CPUs to work with */ - if (!cpu_map__empty(cpus)) { - for (i = 0; i < cpu_map__nr(cpus); i++) { - if (cs_etm_is_etmv4(itr, cpus->map[i])) + if (!cpu_map__empty(event_cpus)) { + for (i = 0; i < cpu__max_cpu(); i++) { + if (!cpu_map__has(event_cpus, i) || + !cpu_map__has(online_cpus, i)) + continue; + + if (cs_etm_is_etmv4(itr, i)) etmv4++; else etmv3++; @@ -311,6 +316,9 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, } else { /* get configuration for all CPUs in the system */ for (i = 0; i < cpu__max_cpu(); i++) { + if (!cpu_map__has(online_cpus, i)) + continue; + if (cs_etm_is_etmv4(itr, i)) etmv4++; else @@ -318,6 +326,8 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, } } + cpu_map__put(online_cpus); + return (CS_ETM_HEADER_SIZE + (etmv4 * CS_ETMV4_PRIV_SIZE) + (etmv3 * CS_ETMV3_PRIV_SIZE)); @@ -447,7 +457,9 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, int i; u32 offset; u64 nr_cpu, type; - const struct cpu_map *cpus = session->evlist->cpus; + struct cpu_map *cpu_map; + struct cpu_map *event_cpus = session->evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; @@ -458,8 +470,21 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, if (!session->evlist->nr_mmaps) return -EINVAL; - /* If the cpu_map is empty all CPUs are involved */ - nr_cpu = cpu_map__empty(cpus) ? cpu__max_cpu() : cpu_map__nr(cpus); + /* If the cpu_map is empty all online CPUs are involved */ + if (cpu_map__empty(event_cpus)) { + cpu_map = online_cpus; + } else { + /* Make sure all specified CPUs are online */ + for (i = 0; i < cpu_map__nr(event_cpus); i++) { + if (cpu_map__has(event_cpus, i) && + !cpu_map__has(online_cpus, i)) + return -EINVAL; + } + + cpu_map = event_cpus; + } + + nr_cpu = cpu_map__nr(cpu_map); /* Get PMU type as dynamically assigned by the core */ type = cs_etm_pmu->type; @@ -472,15 +497,11 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, offset = CS_ETM_SNAPSHOT + 1; - /* cpu map is not empty, we have specific CPUs to work with */ - if (!cpu_map__empty(cpus)) { - for (i = 0; i < cpu_map__nr(cpus) && offset < priv_size; i++) - cs_etm_get_metadata(cpus->map[i], &offset, itr, info); - } else { - /* get configuration for all CPUs in the system */ - for (i = 0; i < cpu__max_cpu(); i++) + for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) + if (cpu_map__has(cpu_map, i)) cs_etm_get_metadata(i, &offset, itr, info); - } + + cpu_map__put(online_cpus); return 0; } -- cgit From 8e2ff72aa35e1a8a53894ae46751a83543338e14 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 29 Jan 2018 14:04:16 +0530 Subject: perf powerpc: Generate system call table from asm/unistd.h This should speed up accessing new system calls introduced with the kernel rather than waiting for libaudit updates to include them. Signed-off-by: Ravi Bangoria Cc: Alexander Shishkin Cc: Hendrik Brueckner Cc: Jiri Olsa Cc: Michael Ellerman Cc: Namhyung Kim Cc: Thomas Richter Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20180129083417.31240-3-ravi.bangoria@linux.vnet.ibm.com [ Made it generate syscall_32.c as well to fix the build on 32-bit ppc ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/powerpc/Makefile | 25 +++++++++++++++ .../perf/arch/powerpc/entry/syscalls/mksyscalltbl | 37 ++++++++++++++++++++++ 2 files changed, 62 insertions(+) create mode 100755 tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 42dab7c8f508..a111239df182 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -6,3 +6,28 @@ endif HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 PERF_HAVE_JITDUMP := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/powerpc/include/generated/asm +header32 := $(out)/syscalls_32.c +header64 := $(out)/syscalls_64.c +sysdef := $(srctree)/tools/arch/powerpc/include/uapi/asm/unistd.h +sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header64): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '64' '$(CC)' $(sysdef) > $@ + +$(header32): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '32' '$(CC)' $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64) + +archheaders: $(header32) $(header64) diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..ef52e1dd694b --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl @@ -0,0 +1,37 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# s390 script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner +# Changed by: Ravi Bangoria + +wordsize=$1 +gcc=$2 +input=$3 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table() +{ + local wordsize=$1 + local max_nr + + echo "static const char *syscalltbl_powerpc_${wordsize}[] = {" + while read sc nr; do + printf '\t[%d] = "%s",\n' $nr $sc + max_nr=$nr + done + echo '};' + echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr" +} + +$gcc -m${wordsize} -E -dM -x c $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -nu \ + |create_table ${wordsize} -- cgit From eca0fa28cd0df7369701dbee0e30ddce19c039b8 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 13 Feb 2018 16:14:16 +0100 Subject: perf record: Provide detailed information on s390 CPU When perf record ... is setup to record data, the s390 cpu information was a fixed string "IBM/S390". Replace this string with one containing more information about the machine. The information included in the cpuid is a comma separated list: manufacturer,type,model-capacity,model[,version,authorization] with - manufacturer: up to 16 byte name of the manufacturer (IBM). - type: a four digit number refering to the machine generation. - model-capacitiy: up to 16 characters describing number of cpus etc. - model: up to 16 characters describing model. - version: the CPU-MF counter facility version number, available on LPARs only, omitted on z/VM guests. - authorization: the CPU-MF counter facility authorization level, available on LPARs only, omitted on z/VM guests. Before: [root@s8360047 perf]# ./perf record -- sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (4 samples) ] [root@s8360047 perf]# ./perf report --header | fgrep cpuid # cpuid : IBM/S390 [root@s8360047 perf]# After: [root@s35lp76 perf]# ./perf report --header|fgrep cpuid # cpuid : IBM,3906,704,M03,3.5,002f [root@s35lp76 perf]# Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Cc: Heiko Carstens Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/20180213151419.80737-1-tmricht@linux.vnet.ibm.com [ Use scnprintf instead of strncat to fix build errors on gcc GNU C99 5.4.0 20160609 -march=zEC12 -m64 -mzarch -ggdb3 -O6 -std=gnu99 -fPIC -fno-omit-frame-pointer -funwind-tables -fstack-protector-all ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/header.c | 130 +++++++++++++++++++++++++++++++++++-- 1 file changed, 125 insertions(+), 5 deletions(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index 9fa6c3e5782c..a78064c25ced 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -1,8 +1,9 @@ /* * Implementation of get_cpuid(). * - * Copyright 2014 IBM Corp. + * Copyright IBM Corp. 2014, 2018 * Author(s): Alexander Yarygin + * Thomas Richter * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -13,16 +14,135 @@ #include #include #include +#include #include "../../util/header.h" +#include "../../util/util.h" + +#define SYSINFO_MANU "Manufacturer:" +#define SYSINFO_TYPE "Type:" +#define SYSINFO_MODEL "Model:" +#define SRVLVL_CPUMF "CPU-MF:" +#define SRVLVL_VERSION "version=" +#define SRVLVL_AUTHORIZATION "authorization=" +#define SYSINFO "/proc/sysinfo" +#define SRVLVL "/proc/service_levels" int get_cpuid(char *buffer, size_t sz) { - const char *cpuid = "IBM/S390"; + char *cp, *line = NULL, *line2; + char type[8], model[33], version[8], manufacturer[32], authorization[8]; + int tpsize = 0, mdsize = 0, vssize = 0, mfsize = 0, atsize = 0; + int read; + unsigned long line_sz; + size_t nbytes; + FILE *sysinfo; + + /* + * Scan /proc/sysinfo line by line and read out values for + * Manufacturer:, Type: and Model:, for example: + * Manufacturer: IBM + * Type: 2964 + * Model: 702 N96 + * The first word is the Model Capacity and the second word is + * Model (can be omitted). Both words have a maximum size of 16 + * bytes. + */ + memset(manufacturer, 0, sizeof(manufacturer)); + memset(type, 0, sizeof(type)); + memset(model, 0, sizeof(model)); + memset(version, 0, sizeof(version)); + memset(authorization, 0, sizeof(authorization)); + + sysinfo = fopen(SYSINFO, "r"); + if (sysinfo == NULL) + return -1; + + while ((read = getline(&line, &line_sz, sysinfo)) != -1) { + if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) { + line2 = line + strlen(SYSINFO_MANU); + + while ((cp = strtok_r(line2, "\n ", &line2))) { + mfsize += scnprintf(manufacturer + mfsize, + sizeof(manufacturer) - mfsize, "%s", cp); + } + } + + if (!strncmp(line, SYSINFO_TYPE, strlen(SYSINFO_TYPE))) { + line2 = line + strlen(SYSINFO_TYPE); + + while ((cp = strtok_r(line2, "\n ", &line2))) { + tpsize += scnprintf(type + tpsize, + sizeof(type) - tpsize, "%s", cp); + } + } + + if (!strncmp(line, SYSINFO_MODEL, strlen(SYSINFO_MODEL))) { + line2 = line + strlen(SYSINFO_MODEL); + + while ((cp = strtok_r(line2, "\n ", &line2))) { + mdsize += scnprintf(model + mdsize, sizeof(type) - mdsize, + "%s%s", model[0] ? "," : "", cp); + } + break; + } + } + fclose(sysinfo); - if (strlen(cpuid) + 1 > sz) + /* Missing manufacturer, type or model information should not happen */ + if (!manufacturer[0] || !type[0] || !model[0]) return -1; - strcpy(buffer, cpuid); - return 0; + /* + * Scan /proc/service_levels and return the CPU-MF counter facility + * version number and authorization level. + * Optional, does not exist on z/VM guests. + */ + sysinfo = fopen(SRVLVL, "r"); + if (sysinfo == NULL) + goto skip_sysinfo; + while ((read = getline(&line, &line_sz, sysinfo)) != -1) { + if (strncmp(line, SRVLVL_CPUMF, strlen(SRVLVL_CPUMF))) + continue; + + line2 = line + strlen(SRVLVL_CPUMF); + while ((cp = strtok_r(line2, "\n ", &line2))) { + if (!strncmp(cp, SRVLVL_VERSION, + strlen(SRVLVL_VERSION))) { + char *sep = strchr(cp, '='); + + vssize += scnprintf(version + vssize, + sizeof(version) - vssize, "%s", sep + 1); + } + if (!strncmp(cp, SRVLVL_AUTHORIZATION, + strlen(SRVLVL_AUTHORIZATION))) { + char *sep = strchr(cp, '='); + + atsize += scnprintf(authorization + atsize, + sizeof(authorization) - atsize, "%s", sep + 1); + } + } + } + fclose(sysinfo); + +skip_sysinfo: + free(line); + + if (version[0] && authorization[0] ) + nbytes = snprintf(buffer, sz, "%s,%s,%s,%s,%s", + manufacturer, type, model, version, + authorization); + else + nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type, + model); + return (nbytes >= sz) ? -1 : 0; +} + +char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused) +{ + char *buf = malloc(128); + + if (buf && get_cpuid(buf, 128) < 0) + zfree(&buf); + return buf; } -- cgit From c59124fa59757fadc80ad881056a21f98c71b146 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 13 Feb 2018 16:14:17 +0100 Subject: perf annotate: Scan cpuid for s390 and save machine type Scan the cpuid string and extract the type number for later use. Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Cc: Heiko Carstens Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/20180213151419.80737-2-tmricht@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/annotate/instructions.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index 8c72b44444cb..01df9d8303e1 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -23,12 +23,37 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na return ops; } +static int s390__cpuid_parse(struct arch *arch, char *cpuid) +{ + unsigned int family; + char model[16], model_c[16], cpumf_v[16], cpumf_a[16]; + int ret; + + /* + * cpuid string format: + * "IBM,family,model-capacity,model[,cpum_cf-version,cpum_cf-authorization]" + */ + ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%s", &family, model_c, + model, cpumf_v, cpumf_a); + if (ret >= 2) { + arch->family = family; + arch->model = 0; + return 0; + } + + return -1; +} + static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused) { + int err = 0; + if (!arch->initialized) { arch->initialized = true; arch->associate_instruction_ops = s390__associate_ins_ops; + if (cpuid) + err = s390__cpuid_parse(arch, cpuid); } - return 0; + return err; } -- cgit From 4cb7d3ecfca90684ad00f893c34a2028fcc5f764 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 13 Feb 2018 16:14:18 +0100 Subject: perf cpuid: Introduce a platform specific cpuid compare function The function get_cpuid_str() is called by perf_pmu__getcpuid() and on s390 returns a complete description of the CPU and its capabilities, which is a comma separated list. To map the CPU type with the value defined in the pmu-events/arch/s390/mapfile.csv, introduce an architecture specific cpuid compare function named strcmp_cpuid_str() The currently used regex algorithm is defined as the weak default and will be used if no platform specific one is defined. This matches the current behavior. Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Cc: Heiko Carstens Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/20180213151419.80737-3-tmricht@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/header.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index a78064c25ced..231294b80dc4 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -146,3 +146,21 @@ char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused) zfree(&buf); return buf; } + +/* + * Compare the cpuid string returned by get_cpuid() function + * with the name generated by the jevents file read from + * pmu-events/arch/s390/mapfile.csv. + * + * Parameter mapcpuid is the cpuid as stored in the + * pmu-events/arch/s390/mapfile.csv. This is just the type number. + * Parameter cpuid is the cpuid returned by function get_cpuid(). + */ +int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) +{ + char *cp = strchr(cpuid, ','); + + if (cp == NULL) + return -1; + return strncmp(cp + 1, mapcpuid, strlen(mapcpuid)); +} -- cgit From 47812e00910407a0f14906c0a3bf2d803a616c6f Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 19 Feb 2018 11:24:44 +0100 Subject: perf s390: Fix reading cpuid model information Commit eca0fa28cd0d (perf record: Provide detailed information on s390 CPU") fixed a build error on Ubuntu. However the fix uses the wrong size to print the model information. Signed-off-by: Thomas Richter Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Martin Schwidefsky Fixes: eca0fa28cd0d ("perf record: Provide detailed information on s390 CPU") Link: http://lkml.kernel.org/r/20180219102444.96900-1-tmricht@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/header.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index 231294b80dc4..a4c30f1c70be 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -81,7 +81,7 @@ int get_cpuid(char *buffer, size_t sz) line2 = line + strlen(SYSINFO_MODEL); while ((cp = strtok_r(line2, "\n ", &line2))) { - mdsize += scnprintf(model + mdsize, sizeof(type) - mdsize, + mdsize += scnprintf(model + mdsize, sizeof(model) - mdsize, "%s%s", model[0] ? "," : "", cp); } break; -- cgit From 9dfb85dfaffe6bc38f0c9f8a8622e2a7ca333e58 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 1 Mar 2018 18:09:07 -0500 Subject: perf test: Switch to new perf_mmap__read_event() interface for time-to-tsc The perf test 'time-to-tsc' still use the legacy interface. No functional change. Commiter notes: Testing it: # perf test tsc 57: Convert perf time to TSC : Ok # Signed-off-by: Kan Liang Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/r/1519945751-37786-10-git-send-email-kan.liang@linux.intel.com [ Changed bool parameters from 0 to 'false', as per Jiri comment ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/perf-time-to-tsc.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 06abe8108b33..7f82d91ef473 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -60,6 +60,8 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe union perf_event *event; u64 test_tsc, comm1_tsc, comm2_tsc; u64 test_time, comm1_time = 0, comm2_time = 0; + struct perf_mmap *md; + u64 end, start; threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -109,7 +111,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe perf_evlist__disable(evlist); for (i = 0; i < evlist->nr_mmaps; i++) { - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md, false, &start, &end) < 0) + continue; + + while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_COMM || @@ -128,8 +134,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe comm2_time = sample.time; } next_event: - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md, false); } + perf_mmap__read_done(md); } if (!comm1_time || !comm2_time) -- cgit From d6ace3df43049a46aa1f5596c0c8d75433321437 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 6 Mar 2018 10:36:05 -0500 Subject: perf mmap: Simplify perf_mmap__consume() It isn't necessary to pass the 'overwrite' argument to perf_mmap__consume(). Discard it. Signed-off-by: Kan Liang Suggested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/r/1520350567-80082-6-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 7f82d91ef473..a9bc77df6a65 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -134,7 +134,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe comm2_time = sample.time; } next_event: - perf_mmap__consume(md, false); + perf_mmap__consume(md); } perf_mmap__read_done(md); } -- cgit From 0019dc87b928380e2c85fcd8694e512079d7b580 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 6 Mar 2018 10:36:06 -0500 Subject: perf mmap: Simplify perf_mmap__read_event() It isn't necessary to pass the 'overwrite', 'start' and 'end' argument to perf_mmap__read_event(). Discard them. Signed-off-by: Kan Liang Suggested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/r/1520350567-80082-7-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/perf-time-to-tsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index a9bc77df6a65..17cf7fc3c7d5 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -115,7 +115,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe if (perf_mmap__read_init(md, false, &start, &end) < 0) continue; - while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) { + while ((event = perf_mmap__read_event(md)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_COMM || -- cgit From b9bae2c841b73eac6bfed510bc24a3051754ff51 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 6 Mar 2018 10:36:07 -0500 Subject: perf mmap: Simplify perf_mmap__read_init() It isn't necessary to pass the 'start', 'end' and 'overwrite' arguments to perf_mmap__read_init(). The data is stored in the struct perf_mmap. Discard the parameters. Signed-off-by: Kan Liang Suggested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/r/1520350567-80082-8-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/perf-time-to-tsc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 17cf7fc3c7d5..7a7721604b86 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -61,7 +61,6 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe u64 test_tsc, comm1_tsc, comm2_tsc; u64 test_time, comm1_time = 0, comm2_time = 0; struct perf_mmap *md; - u64 end, start; threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -112,7 +111,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe for (i = 0; i < evlist->nr_mmaps; i++) { md = &evlist->mmap[i]; - if (perf_mmap__read_init(md, false, &start, &end) < 0) + if (perf_mmap__read_init(md) < 0) continue; while ((event = perf_mmap__read_event(md)) != NULL) { -- cgit From 15d599a25c7649807a2b66f7100efcf030665068 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 7 Mar 2018 16:02:25 +0200 Subject: perf intel-pt/bts: In auxtrace_record__init_intel() evlist is never NULL Tidy auxtrace_record__init_intel() slightly by recognizing that evlist is never NULL. Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1520431349-30689-6-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/auxtrace.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index 6aa3f2a38321..b135af62011c 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -37,15 +37,11 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); - if (evlist) { - evlist__for_each_entry(evlist, evsel) { - if (intel_pt_pmu && - evsel->attr.type == intel_pt_pmu->type) - found_pt = true; - if (intel_bts_pmu && - evsel->attr.type == intel_bts_pmu->type) - found_bts = true; - } + evlist__for_each_entry(evlist, evsel) { + if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type) + found_pt = true; + if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type) + found_bts = true; } if (found_pt && found_bts) { -- cgit From 0b58a77ca8792bd7798ef3a4d865c57694ec74fc Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 7 Mar 2018 14:43:25 +0100 Subject: perf annotate: Fix s390 target function disassembly 'perf annotate' displays function call assembler instructions with a right arrow. Hitting enter on this line/instruction causes the browser to disassemble this target function and show it on the screen. On s390 this results in an error message 'The called function was not found.' The function call assembly line parsing does not handle the s390 bras and brasl instructions. Function call__parse expects the target as first operand: callq e9140 <__fxstat> S390 has a register number as first operand: brasl %r14,41d60 Therefore the target addresses on s390 are always zero which is an invalid address. Introduce a s390 specific call parsing function which skips the first operand on s390. Signed-off-by: Thomas Richter Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/20180307134325.96106-1-tmricht@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/annotate/instructions.c | 53 +++++++++++++++++++++++++++- 1 file changed, 52 insertions(+), 1 deletion(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index 01df9d8303e1..e80589fc5b58 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -1,6 +1,57 @@ // SPDX-License-Identifier: GPL-2.0 #include +static int s390_call__parse(struct arch *arch, struct ins_operands *ops, + struct map *map) +{ + char *endptr, *tok, *name; + struct addr_map_symbol target = { + .map = map, + }; + + tok = strchr(ops->raw, ','); + if (!tok) + return -1; + + ops->target.addr = strtoull(tok + 1, &endptr, 16); + + name = strchr(endptr, '<'); + if (name == NULL) + return -1; + + name++; + + if (arch->objdump.skip_functions_char && + strchr(name, arch->objdump.skip_functions_char)) + return -1; + + tok = strchr(name, '>'); + if (tok == NULL) + return -1; + + *tok = '\0'; + ops->target.name = strdup(name); + *tok = '>'; + + if (ops->target.name == NULL) + return -1; + target.addr = map__objdump_2mem(map, ops->target.addr); + + if (map_groups__find_ams(&target) == 0 && + map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) + ops->target.sym = target.sym; + + return 0; +} + +static int call__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops); + +static struct ins_ops s390_call_ops = { + .parse = s390_call__parse, + .scnprintf = call__scnprintf, +}; + static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name) { struct ins_ops *ops = NULL; @@ -14,7 +65,7 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na if (!strcmp(name, "bras") || !strcmp(name, "brasl") || !strcmp(name, "basr")) - ops = &call_ops; + ops = &s390_call_ops; if (!strcmp(name, "br")) ops = &ret_ops; -- cgit From 0b4b6b78a3ce07023052e44b967f5d42fa3d802c Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 8 Mar 2018 13:09:13 +0100 Subject: perf annotate: Handle s390 PC relative load and store instruction. S390 has several load and store instructions with target operand addressing relative to the program counter, for example lrl, lgrl, strl, stgrl. These instructions are handled similar to x86. Objdump output displays those instructions as: 9595c: c4 2d 00 09 9c 54 lgrl %r7,1c8540 This output is parsed (like on x86) and perf annotate shows those lines as: lgrl %r7,mp_+0x60 This patch handles the s390 specific instruction parsing for PC relative load and store instructions. Signed-off-by: Thomas Richter Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/20180308120913.14802-1-tmricht@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/annotate/instructions.c | 63 ++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index e80589fc5b58..46c21831f2ac 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -52,6 +52,61 @@ static struct ins_ops s390_call_ops = { .scnprintf = call__scnprintf, }; +static int s390_mov__parse(struct arch *arch __maybe_unused, + struct ins_operands *ops, + struct map *map __maybe_unused) +{ + char *s = strchr(ops->raw, ','), *target, *endptr; + + if (s == NULL) + return -1; + + *s = '\0'; + ops->source.raw = strdup(ops->raw); + *s = ','; + + if (ops->source.raw == NULL) + return -1; + + target = ++s; + ops->target.raw = strdup(target); + if (ops->target.raw == NULL) + goto out_free_source; + + ops->target.addr = strtoull(target, &endptr, 16); + if (endptr == target) + goto out_free_target; + + s = strchr(endptr, '<'); + if (s == NULL) + goto out_free_target; + endptr = strchr(s + 1, '>'); + if (endptr == NULL) + goto out_free_target; + + *endptr = '\0'; + ops->target.name = strdup(s + 1); + *endptr = '>'; + if (ops->target.name == NULL) + goto out_free_target; + + return 0; + +out_free_target: + zfree(&ops->target.raw); +out_free_source: + zfree(&ops->source.raw); + return -1; +} + +static int mov__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops); + +static struct ins_ops s390_mov_ops = { + .parse = s390_mov__parse, + .scnprintf = mov__scnprintf, +}; + static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name) { struct ins_ops *ops = NULL; @@ -68,6 +123,14 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na ops = &s390_call_ops; if (!strcmp(name, "br")) ops = &ret_ops; + /* override load/store relative to PC */ + if (!strcmp(name, "lrl") || + !strcmp(name, "lgrl") || + !strcmp(name, "lgfrl") || + !strcmp(name, "llgfrl") || + !strcmp(name, "strl") || + !strcmp(name, "stgrl")) + ops = &s390_mov_ops; if (ops) arch__associate_ins_ops(arch, name, ops); -- cgit From 744e9a91cf898bf027dbe65cc61a5d7565335cba Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Thu, 8 Mar 2018 21:10:30 -0600 Subject: perf tools arm64: Add libdw DWARF post unwind support for ARM64 Based on prior work: https://lkml.org/lkml/2014/5/6/395 and on how other arches add libdw unwind support. Includes support for running the unwind test, e.g., on a system with only elfutils' libdw 0.170, the test now runs, and successfully: $ ./perf test unwind 56: Test dwarf unwind : Ok Originally-by: Jean Pihet Reported-by: Christian Hansen Signed-off-by: Kim Phillips Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180308211030.4ee4a0d6ff6dc5cda1b567d4@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/include/arch-tests.h | 12 ++++++ tools/perf/arch/arm64/tests/Build | 2 + tools/perf/arch/arm64/tests/arch-tests.c | 16 ++++++++ tools/perf/arch/arm64/util/Build | 1 + tools/perf/arch/arm64/util/unwind-libdw.c | 60 ++++++++++++++++++++++++++++++ 5 files changed, 91 insertions(+) create mode 100644 tools/perf/arch/arm64/include/arch-tests.h create mode 100644 tools/perf/arch/arm64/tests/arch-tests.c create mode 100644 tools/perf/arch/arm64/util/unwind-libdw.c (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h new file mode 100644 index 000000000000..90ec4c8cb880 --- /dev/null +++ b/tools/perf/arch/arm64/include/arch-tests.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_TESTS_H +#define ARCH_TESTS_H + +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +#endif + +extern struct test arch_tests[]; + +#endif diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build index b30eff9bcc83..883c57ff0c08 100644 --- a/tools/perf/arch/arm64/tests/Build +++ b/tools/perf/arch/arm64/tests/Build @@ -1,2 +1,4 @@ libperf-y += regs_load.o libperf-y += dwarf-unwind.o + +libperf-y += arch-tests.o diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c new file mode 100644 index 000000000000..5b1543c98022 --- /dev/null +++ b/tools/perf/arch/arm64/tests/arch-tests.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "tests/tests.h" +#include "arch-tests.h" + +struct test arch_tests[] = { +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "DWARF unwind", + .func = test__dwarf_unwind, + }, +#endif + { + .func = NULL, + }, +}; diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index c0b8dfef98ba..68f8a8eb3ad0 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -2,6 +2,7 @@ libperf-y += header.o libperf-y += sym-handling.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ ../../arm/util/auxtrace.o \ diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c new file mode 100644 index 000000000000..7623d85e77f3 --- /dev/null +++ b/tools/perf/arch/arm64/util/unwind-libdw.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/event.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX], dwarf_pc; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_ARM64_##r); \ + val; \ +}) + + dwarf_regs[0] = REG(X0); + dwarf_regs[1] = REG(X1); + dwarf_regs[2] = REG(X2); + dwarf_regs[3] = REG(X3); + dwarf_regs[4] = REG(X4); + dwarf_regs[5] = REG(X5); + dwarf_regs[6] = REG(X6); + dwarf_regs[7] = REG(X7); + dwarf_regs[8] = REG(X8); + dwarf_regs[9] = REG(X9); + dwarf_regs[10] = REG(X10); + dwarf_regs[11] = REG(X11); + dwarf_regs[12] = REG(X12); + dwarf_regs[13] = REG(X13); + dwarf_regs[14] = REG(X14); + dwarf_regs[15] = REG(X15); + dwarf_regs[16] = REG(X16); + dwarf_regs[17] = REG(X17); + dwarf_regs[18] = REG(X18); + dwarf_regs[19] = REG(X19); + dwarf_regs[20] = REG(X20); + dwarf_regs[21] = REG(X21); + dwarf_regs[22] = REG(X22); + dwarf_regs[23] = REG(X23); + dwarf_regs[24] = REG(X24); + dwarf_regs[25] = REG(X25); + dwarf_regs[26] = REG(X26); + dwarf_regs[27] = REG(X27); + dwarf_regs[28] = REG(X28); + dwarf_regs[29] = REG(X29); + dwarf_regs[30] = REG(LR); + dwarf_regs[31] = REG(SP); + + if (!dwfl_thread_state_registers(thread, 0, PERF_REG_ARM64_MAX, + dwarf_regs)) + return false; + + dwarf_pc = REG(PC); + dwfl_thread_state_register_pc(thread, dwarf_pc); + + return true; +} -- cgit From 85a84e4f813912ab77d872ff6882dd7b435fbf4e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 20 Mar 2018 16:19:08 -0300 Subject: perf annotate: Pass function descriptor to its instruction parsing routines We need that to figure out if jumps have targets in a different function. E.g. _cpp_lex_token(), in /usr/libexec/gcc/x86_64-redhat-linux/5.3.1/cc1 has a line like this: jne c469be Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-ris0ioziyp469pofpzix2atb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/annotate/instructions.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'tools/perf/arch') diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index 46c21831f2ac..cee4e2f7c057 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -2,9 +2,10 @@ #include static int s390_call__parse(struct arch *arch, struct ins_operands *ops, - struct map *map) + struct map_symbol *ms) { char *endptr, *tok, *name; + struct map *map = ms->map; struct addr_map_symbol target = { .map = map, }; @@ -54,7 +55,7 @@ static struct ins_ops s390_call_ops = { static int s390_mov__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, - struct map *map __maybe_unused) + struct map_symbol *ms __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *endptr; -- cgit