diff options
Diffstat (limited to 'tools')
28 files changed, 258 insertions, 158 deletions
diff --git a/tools/Makefile b/tools/Makefile index 3ae43947a17..1f9a529fe54 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -31,44 +31,44 @@ help: @echo ' clean: a summary clean target to clean _all_ folders' cpupower: FORCE - $(QUIET_SUBDIR0)power/$@/ $(QUIET_SUBDIR1) + $(call descend,power/$@) firewire lguest perf usb virtio vm: FORCE - $(QUIET_SUBDIR0)$@/ $(QUIET_SUBDIR1) + $(call descend,$@) selftests: FORCE - $(QUIET_SUBDIR0)testing/$@/ $(QUIET_SUBDIR1) + $(call descend,testing/$@) turbostat x86_energy_perf_policy: FORCE - $(QUIET_SUBDIR0)power/x86/$@/ $(QUIET_SUBDIR1) + $(call descend,power/x86/$@) cpupower_install: - $(QUIET_SUBDIR0)power/$(@:_install=)/ $(QUIET_SUBDIR1) install + $(call descend,power/$(@:_install=),install) firewire_install lguest_install perf_install usb_install virtio_install vm_install: - $(QUIET_SUBDIR0)$(@:_install=)/ $(QUIET_SUBDIR1) install + $(call descend,$(@:_install=),install) selftests_install: - $(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) install + $(call descend,testing/$(@:_clean=),install) turbostat_install x86_energy_perf_policy_install: - $(QUIET_SUBDIR0)power/x86/$(@:_install=)/ $(QUIET_SUBDIR1) install + $(call descend,power/x86/$(@:_install=),install) install: cpupower_install firewire_install lguest_install perf_install \ selftests_install turbostat_install usb_install virtio_install \ vm_install x86_energy_perf_policy_install cpupower_clean: - $(QUIET_SUBDIR0)power/cpupower/ $(QUIET_SUBDIR1) clean + $(call descend,power/cpupower,clean) firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean: - $(QUIET_SUBDIR0)$(@:_clean=)/ $(QUIET_SUBDIR1) clean + $(call descend,$(@:_clean=),clean) selftests_clean: - $(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) clean + $(call descend,testing/$(@:_clean=),clean) turbostat_clean x86_energy_perf_policy_clean: - $(QUIET_SUBDIR0)power/x86/$(@:_clean=)/ $(QUIET_SUBDIR1) clean + $(call descend,power/x86/$(@:_clean=),clean) clean: cpupower_clean firewire_clean lguest_clean perf_clean selftests_clean \ turbostat_clean usb_clean virtio_clean vm_clean \ diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 00deed4d615..0a619af5be4 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -169,7 +169,34 @@ endif ### --- END CONFIGURATION SECTION --- -BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +ifneq ($(objtree),) +#$(info Determined 'objtree' to be $(objtree)) +endif + +ifneq ($(OUTPUT),) +#$(info Determined 'OUTPUT' to be $(OUTPUT)) +endif + +BASIC_CFLAGS = \ + -Iutil/include \ + -Iarch/$(ARCH)/include \ + $(if $(objtree),-I$(objtree)/arch/$(ARCH)/include/generated/uapi) \ + -I$(srctree)/arch/$(ARCH)/include/uapi \ + -I$(srctree)/arch/$(ARCH)/include \ + $(if $(objtree),-I$(objtree)/include/generated/uapi) \ + -I$(srctree)/include/uapi \ + -I$(srctree)/include \ + -I$(OUTPUT)util \ + -Iutil \ + -I. \ + -I$(TRACE_EVENT_DIR) \ + -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE BASIC_LDFLAGS = # Guard against environment variables diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index 46fc9f15c6b..7fcdcdbee91 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -3,7 +3,7 @@ #include <stdlib.h> #include "../../util/types.h" -#include "../../../../../arch/x86/include/asm/perf_regs.h" +#include <asm/perf_regs.h> #ifndef ARCH_X86_64 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 260abc535b5..283b4397e39 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -22,9 +22,10 @@ #include <pthread.h> #include <math.h> -#include "../../arch/x86/include/asm/svm.h" -#include "../../arch/x86/include/asm/vmx.h" -#include "../../arch/x86/include/asm/kvm.h" +#if defined(__i386__) || defined(__x86_64__) +#include <asm/svm.h> +#include <asm/vmx.h> +#include <asm/kvm.h> struct event_key { #define INVALID_KEY (~0ULL) @@ -58,7 +59,7 @@ struct kvm_event_key { }; -struct perf_kvm; +struct perf_kvm_stat; struct kvm_events_ops { bool (*is_begin_event)(struct perf_evsel *evsel, @@ -66,7 +67,7 @@ struct kvm_events_ops { struct event_key *key); bool (*is_end_event)(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key); - void (*decode_key)(struct perf_kvm *kvm, struct event_key *key, + void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, char decode[20]); const char *name; }; @@ -79,7 +80,7 @@ struct exit_reasons_table { #define EVENTS_BITS 12 #define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) -struct perf_kvm { +struct perf_kvm_stat { struct perf_tool tool; struct perf_session *session; @@ -146,7 +147,7 @@ static struct exit_reasons_table svm_exit_reasons[] = { SVM_EXIT_REASONS }; -static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code) +static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code) { int i = kvm->exit_reasons_size; struct exit_reasons_table *tbl = kvm->exit_reasons; @@ -162,7 +163,7 @@ static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code) return "UNKNOWN"; } -static void exit_event_decode_key(struct perf_kvm *kvm, +static void exit_event_decode_key(struct perf_kvm_stat *kvm, struct event_key *key, char decode[20]) { @@ -228,7 +229,7 @@ static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, return false; } -static void mmio_event_decode_key(struct perf_kvm *kvm __maybe_unused, +static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char decode[20]) { @@ -271,7 +272,7 @@ static bool ioport_event_end(struct perf_evsel *evsel, return kvm_entry_event(evsel); } -static void ioport_event_decode_key(struct perf_kvm *kvm __maybe_unused, +static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char decode[20]) { @@ -286,7 +287,7 @@ static struct kvm_events_ops ioport_events = { .name = "IO Port Access" }; -static bool register_kvm_events_ops(struct perf_kvm *kvm) +static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) { bool ret = true; @@ -311,7 +312,7 @@ struct vcpu_event_record { }; -static void init_kvm_event_record(struct perf_kvm *kvm) +static void init_kvm_event_record(struct perf_kvm_stat *kvm) { int i; @@ -360,7 +361,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key) return event; } -static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm, +static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, struct event_key *key) { struct kvm_event *event; @@ -381,7 +382,7 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm, return event; } -static bool handle_begin_event(struct perf_kvm *kvm, +static bool handle_begin_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, u64 timestamp) { @@ -425,7 +426,7 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id, return true; } -static bool handle_end_event(struct perf_kvm *kvm, +static bool handle_end_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, u64 timestamp) @@ -486,7 +487,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, return thread->priv; } -static bool handle_kvm_event(struct perf_kvm *kvm, +static bool handle_kvm_event(struct perf_kvm_stat *kvm, struct thread *thread, struct perf_evsel *evsel, struct perf_sample *sample) @@ -541,7 +542,7 @@ static struct kvm_event_key keys[] = { { NULL, NULL } }; -static bool select_key(struct perf_kvm *kvm) +static bool select_key(struct perf_kvm_stat *kvm) { int i; @@ -577,7 +578,8 @@ static void insert_to_result(struct rb_root *result, struct kvm_event *event, rb_insert_color(&event->rb, result); } -static void update_total_count(struct perf_kvm *kvm, struct kvm_event *event) +static void +update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event) { int vcpu = kvm->trace_vcpu; @@ -590,7 +592,7 @@ static bool event_is_valid(struct kvm_event *event, int vcpu) return !!get_event_count(event, vcpu); } -static void sort_result(struct perf_kvm *kvm) +static void sort_result(struct perf_kvm_stat *kvm) { unsigned int i; int vcpu = kvm->trace_vcpu; @@ -627,7 +629,7 @@ static void print_vcpu_info(int vcpu) pr_info("VCPU %d:\n\n", vcpu); } -static void print_result(struct perf_kvm *kvm) +static void print_result(struct perf_kvm_stat *kvm) { char decode[20]; struct kvm_event *event; @@ -670,7 +672,8 @@ static int process_sample_event(struct perf_tool *tool, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, sample->tid); - struct perf_kvm *kvm = container_of(tool, struct perf_kvm, tool); + struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, + tool); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", @@ -701,7 +704,7 @@ static int get_cpu_isa(struct perf_session *session) return isa; } -static int read_events(struct perf_kvm *kvm) +static int read_events(struct perf_kvm_stat *kvm) { int ret; @@ -750,7 +753,7 @@ static bool verify_vcpu(int vcpu) return true; } -static int kvm_events_report_vcpu(struct perf_kvm *kvm) +static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) { int ret = -EINVAL; int vcpu = kvm->trace_vcpu; @@ -798,7 +801,8 @@ static const char * const record_args[] = { _p; \ }) -static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv) +static int +kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) { unsigned int rec_argc, i, j; const char **rec_argv; @@ -821,7 +825,8 @@ static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -static int kvm_events_report(struct perf_kvm *kvm, int argc, const char **argv) +static int +kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) { const struct option kvm_events_report_options[] = { OPT_STRING(0, "event", &kvm->report_event, "report event", @@ -864,24 +869,37 @@ static void print_kvm_stat_usage(void) printf("\nOtherwise, it is the alias of 'perf stat':\n"); } -static int kvm_cmd_stat(struct perf_kvm *kvm, int argc, const char **argv) +static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) { + struct perf_kvm_stat kvm = { + .file_name = file_name, + + .trace_vcpu = -1, + .report_event = "vmexit", + .sort_key = "sample", + + .exit_reasons = svm_exit_reasons, + .exit_reasons_size = ARRAY_SIZE(svm_exit_reasons), + .exit_reasons_isa = "SVM", + }; + if (argc == 1) { print_kvm_stat_usage(); goto perf_stat; } if (!strncmp(argv[1], "rec", 3)) - return kvm_events_record(kvm, argc - 1, argv + 1); + return kvm_events_record(&kvm, argc - 1, argv + 1); if (!strncmp(argv[1], "rep", 3)) - return kvm_events_report(kvm, argc - 1 , argv + 1); + return kvm_events_report(&kvm, argc - 1 , argv + 1); perf_stat: return cmd_stat(argc, argv, NULL); } +#endif -static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv) +static int __cmd_record(const char *file_name, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -890,7 +908,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv) rec_argv = calloc(rec_argc + 1, sizeof(char *)); rec_argv[i++] = strdup("record"); rec_argv[i++] = strdup("-o"); - rec_argv[i++] = strdup(kvm->file_name); + rec_argv[i++] = strdup(file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -899,7 +917,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv) +static int __cmd_report(const char *file_name, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -908,7 +926,7 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv) rec_argv = calloc(rec_argc + 1, sizeof(char *)); rec_argv[i++] = strdup("report"); rec_argv[i++] = strdup("-i"); - rec_argv[i++] = strdup(kvm->file_name); + rec_argv[i++] = strdup(file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -917,7 +935,8 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv) return cmd_report(i, rec_argv, NULL); } -static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv) +static int +__cmd_buildid_list(const char *file_name, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -926,7 +945,7 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv) rec_argv = calloc(rec_argc + 1, sizeof(char *)); rec_argv[i++] = strdup("buildid-list"); rec_argv[i++] = strdup("-i"); - rec_argv[i++] = strdup(kvm->file_name); + rec_argv[i++] = strdup(file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -937,20 +956,12 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv) int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) { - struct perf_kvm kvm = { - .trace_vcpu = -1, - .report_event = "vmexit", - .sort_key = "sample", - - .exit_reasons = svm_exit_reasons, - .exit_reasons_size = ARRAY_SIZE(svm_exit_reasons), - .exit_reasons_isa = "SVM", - }; + const char *file_name; const struct option kvm_options[] = { - OPT_STRING('i', "input", &kvm.file_name, "file", + OPT_STRING('i', "input", &file_name, "file", "Input file name"), - OPT_STRING('o', "output", &kvm.file_name, "file", + OPT_STRING('o', "output", &file_name, "file", "Output file name"), OPT_BOOLEAN(0, "guest", &perf_guest, "Collect guest os data"), @@ -985,32 +996,34 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) if (!perf_host) perf_guest = 1; - if (!kvm.file_name) { + if (!file_name) { if (perf_host && !perf_guest) - kvm.file_name = strdup("perf.data.host"); + file_name = strdup("perf.data.host"); else if (!perf_host && perf_guest) - kvm.file_name = strdup("perf.data.guest"); + file_name = strdup("perf.data.guest"); else - kvm.file_name = strdup("perf.data.kvm"); + file_name = strdup("perf.data.kvm"); - if (!kvm.file_name) { + if (!file_name) { pr_err("Failed to allocate memory for filename\n"); return -ENOMEM; } } if (!strncmp(argv[0], "rec", 3)) - return __cmd_record(&kvm, argc, argv); + return __cmd_record(file_name, argc, argv); else if (!strncmp(argv[0], "rep", 3)) - return __cmd_report(&kvm, argc, argv); + return __cmd_report(file_name, argc, argv); else if (!strncmp(argv[0], "diff", 4)) return cmd_diff(argc, argv, NULL); else if (!strncmp(argv[0], "top", 3)) return cmd_top(argc, argv, NULL); else if (!strncmp(argv[0], "buildid-list", 12)) - return __cmd_buildid_list(&kvm, argc, argv); + return __cmd_buildid_list(file_name, argc, argv); +#if defined(__i386__) || defined(__x86_64__) else if (!strncmp(argv[0], "stat", 4)) - return kvm_cmd_stat(&kvm, argc, argv); + return kvm_cmd_stat(file_name, argc, argv); +#endif else usage_with_options(kvm_usage, kvm_options); diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 484f26cc0c0..5acd6e8e658 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -15,7 +15,7 @@ #include "util/thread_map.h" #include "util/pmu.h" #include "event-parse.h" -#include "../../include/linux/hw_breakpoint.h" +#include <linux/hw_breakpoint.h> #include <sys/mman.h> diff --git a/tools/perf/perf.h b/tools/perf/perf.h index c50985eaec4..238f923f221 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -5,8 +5,9 @@ struct winsize; void get_term_dimensions(struct winsize *ws); +#include <asm/unistd.h> + #if defined(__i386__) -#include "../../arch/x86/include/asm/unistd.h" #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); #define CPUINFO_PROC "model name" @@ -16,7 +17,6 @@ void get_term_dimensions(struct winsize *ws); #endif #if defined(__x86_64__) -#include "../../arch/x86/include/asm/unistd.h" #define rmb() asm volatile("lfence" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); #define CPUINFO_PROC "model name" @@ -26,20 +26,17 @@ void get_term_dimensions(struct winsize *ws); #endif #ifdef __powerpc__ -#include "../../arch/powerpc/include/asm/unistd.h" #define rmb() asm volatile ("sync" ::: "memory") #define cpu_relax() asm volatile ("" ::: "memory"); #define CPUINFO_PROC "cpu" #endif #ifdef __s390__ -#include "../../arch/s390/include/asm/unistd.h" #define rmb() asm volatile("bcr 15,0" ::: "memory") #define cpu_relax() asm volatile("" ::: "memory"); #endif #ifdef __sh__ -#include "../../arch/sh/include/asm/unistd.h" #if defined(__SH4A__) || defined(__SH5__) # define rmb() asm volatile("synco" ::: "memory") #else @@ -50,35 +47,30 @@ void get_term_dimensions(struct winsize *ws); #endif #ifdef __hppa__ -#include "../../arch/parisc/include/asm/unistd.h" #define rmb() asm volatile("" ::: "memory") #define cpu_relax() asm volatile("" ::: "memory"); #define CPUINFO_PROC "cpu" #endif #ifdef __sparc__ -#include "../../arch/sparc/include/uapi/asm/unistd.h" #define rmb() asm volatile("":::"memory") #define cpu_relax() asm volatile("":::"memory") #define CPUINFO_PROC "cpu" #endif #ifdef __alpha__ -#include "../../arch/alpha/include/asm/unistd.h" #define rmb() asm volatile("mb" ::: "memory") #define cpu_relax() asm volatile("" ::: "memory") #define CPUINFO_PROC "cpu model" #endif #ifdef __ia64__ -#include "../../arch/ia64/include/asm/unistd.h" #define rmb() asm volatile ("mf" ::: "memory") #define cpu_relax() asm volatile ("hint @pause" ::: "memory") #define CPUINFO_PROC "model name" #endif #ifdef __arm__ -#include "../../arch/arm/include/asm/unistd.h" /* * Use the __kuser_memory_barrier helper in the CPU helper page. See * arch/arm/kernel/entry-armv.S in the kernel source for details. @@ -89,13 +81,11 @@ void get_term_dimensions(struct winsize *ws); #endif #ifdef __aarch64__ -#include "../../arch/arm64/include/asm/unistd.h" #define rmb() asm volatile("dmb ld" ::: "memory") #define cpu_relax() asm volatile("yield" ::: "memory") #endif #ifdef __mips__ -#include "../../arch/mips/include/asm/unistd.h" #define rmb() asm volatile( \ ".set mips2\n\t" \ "sync\n\t" \ @@ -112,7 +102,7 @@ void get_term_dimensions(struct winsize *ws); #include <sys/types.h> #include <sys/syscall.h> -#include "../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> #include "util/types.h" #include <stdbool.h> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 618d41140ab..d144d464ce3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -18,8 +18,8 @@ #include "cpumap.h" #include "thread_map.h" #include "target.h" -#include "../../../include/linux/hw_breakpoint.h" -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/hw_breakpoint.h> +#include <linux/perf_event.h> #include "perf_regs.h" #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 6f94d6dea00..d99b476ef37 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -3,7 +3,8 @@ #include <linux/list.h> #include <stdbool.h> -#include "../../../include/uapi/linux/perf_event.h" +#include <stddef.h> +#include <linux/perf_event.h> #include "types.h" #include "xyarray.h" #include "cgroup.h" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 7daad237dea..566b84c695c 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1378,6 +1378,8 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, str = tmp + 1; fprintf(fp, "# node%u cpu list : %s\n", c, str); + + str += strlen(str) + 1; } return; error: diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 879d215cdac..9bc00783f24 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -1,7 +1,7 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> #include "types.h" diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c index 516ecd9ddd6..6ef213b35ec 100644 --- a/tools/perf/util/parse-events-test.c +++ b/tools/perf/util/parse-events-test.c @@ -3,7 +3,7 @@ #include "evsel.h" #include "evlist.h" #include "sysfs.h" -#include "../../../include/linux/hw_breakpoint.h" +#include <linux/hw_breakpoint.h> #define TEST_ASSERT_VAL(text, cond) \ do { \ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 75c7b0fca6d..6b6d03e93c3 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,4 +1,4 @@ -#include "../../../include/linux/hw_breakpoint.h" +#include <linux/hw_breakpoint.h> #include "util.h" #include "../perf.h" #include "evlist.h" diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 839230ceb18..2820c407adb 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -7,7 +7,7 @@ #include <linux/list.h> #include <stdbool.h> #include "types.h" -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> #include "types.h" struct list_head; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 39f3abac774..fdeb8ac7c5d 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -2,7 +2,7 @@ #define __PMU_H #include <linux/bitops.h> -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> enum { PERF_PMU_FORMAT_VALUE_CONFIG, diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index dd6426163ba..0eae00ad5fe 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -7,7 +7,7 @@ #include "symbol.h" #include "thread.h" #include <linux/rbtree.h> -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> struct sample_queue; struct ip_callchain; diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 2eeb51baf07..cfa906882e2 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -90,17 +90,17 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...) if (!strbuf_avail(sb)) strbuf_grow(sb, 64); va_start(ap, fmt); - len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); va_end(ap); if (len < 0) - die("your vscnprintf is broken"); + die("your vsnprintf is broken"); if (len > strbuf_avail(sb)) { strbuf_grow(sb, len); va_start(ap, fmt); - len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); va_end(ap); if (len > strbuf_avail(sb)) { - die("this should not happen, your snprintf is broken"); + die("this should not happen, your vsnprintf is broken"); } } strbuf_setlen(sb, sb->len + len); diff --git a/tools/power/cpupower/.gitignore b/tools/power/cpupower/.gitignore index 8a83dd2ffc1..d42073f1260 100644 --- a/tools/power/cpupower/.gitignore +++ b/tools/power/cpupower/.gitignore @@ -20,3 +20,10 @@ utils/cpufreq-set.o utils/cpufreq-aperf.o cpupower bench/cpufreq-bench +debug/kernel/Module.symvers +debug/i386/centrino-decode +debug/i386/dump_psb +debug/i386/intel_gsic +debug/i386/powernow-k8-decode +debug/x86_64/centrino-decode +debug/x86_64/powernow-k8-decode diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index cf397bd26d0..d875a74a3bd 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -253,7 +253,8 @@ clean: | xargs rm -f -rm -f $(OUTPUT)cpupower -rm -f $(OUTPUT)libcpupower.so* - -rm -rf $(OUTPUT)po/*.{gmo,pot} + -rm -rf $(OUTPUT)po/*.gmo + -rm -rf $(OUTPUT)po/*.pot $(MAKE) -C bench O=$(OUTPUT) clean diff --git a/tools/power/cpupower/debug/i386/Makefile b/tools/power/cpupower/debug/i386/Makefile index 3ba158f0e28..c05cc0ac80c 100644 --- a/tools/power/cpupower/debug/i386/Makefile +++ b/tools/power/cpupower/debug/i386/Makefile @@ -26,7 +26,10 @@ $(OUTPUT)powernow-k8-decode: powernow-k8-decode.c all: $(OUTPUT)centrino-decode $(OUTPUT)dump_psb $(OUTPUT)intel_gsic $(OUTPUT)powernow-k8-decode clean: - rm -rf $(OUTPUT){centrino-decode,dump_psb,intel_gsic,powernow-k8-decode} + rm -rf $(OUTPUT)centrino-decode + rm -rf $(OUTPUT)dump_psb + rm -rf $(OUTPUT)intel_gsic + rm -rf $(OUTPUT)powernow-k8-decode install: $(INSTALL) -d $(DESTDIR)${bindir} diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1 index 1141c207371..e01c35d13b6 100644 --- a/tools/power/cpupower/man/cpupower-monitor.1 +++ b/tools/power/cpupower/man/cpupower-monitor.1 @@ -7,11 +7,11 @@ cpupower\-monitor \- Report processor frequency and idle statistics .RB "\-l" .B cpupower monitor -.RB [ "\-m <mon1>," [ "<mon2>,..." ] ] +.RB [ -c ] [ "\-m <mon1>," [ "<mon2>,..." ] ] .RB [ "\-i seconds" ] .br .B cpupower monitor -.RB [ "\-m <mon1>," [ "<mon2>,..." ] ] +.RB [ -c ][ "\-m <mon1>," [ "<mon2>,..." ] ] .RB command .br .SH DESCRIPTION @@ -64,6 +64,17 @@ Only display specific monitors. Use the monitor string(s) provided by \-l option Measure intervall. .RE .PP +\-c +.RS 4 +Schedule the process on every core before starting and ending measuring. +This could be needed for the Idle_Stats monitor when no other MSR based +monitor (has to be run on the core that is measured) is run in parallel. +This is to wake up the processors from deeper sleep states and let the +kernel re +-account its cpuidle (C-state) information before reading the +cpuidle timings from sysfs. +.RE +.PP command .RS 4 Measure idle and frequency characteristics of an arbitrary command/workload. diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 906895d21cc..93b0aa74ca0 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -158,6 +158,8 @@ out: cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO; case 0x2A: /* SNB */ case 0x2D: /* SNB Xeon */ + case 0x3A: /* IVB */ + case 0x3E: /* IVB Xeon */ cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO; cpu_info->caps |= CPUPOWER_CAP_IS_SNB; break; diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 2eb584cf2f5..aa9e95486a2 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -92,6 +92,14 @@ extern int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info); extern struct cpupower_cpu_info cpupower_cpu_info; /* cpuid and cpuinfo helpers **************************/ +struct cpuid_core_info { + int pkg; + int core; + int cpu; + + /* flags */ + unsigned int is_online:1; +}; /* CPU topology/hierarchy parsing ******************/ struct cpupower_topology { @@ -101,18 +109,12 @@ struct cpupower_topology { unsigned int threads; /* per core */ /* Array gets mallocated with cores entries, holding per core info */ - struct { - int pkg; - int core; - int cpu; - - /* flags */ - unsigned int is_online:1; - } *core_info; + struct cpuid_core_info *core_info; }; extern int get_cpu_topology(struct cpupower_topology *cpu_top); extern void cpu_topology_release(struct cpupower_topology cpu_top); + /* CPU topology/hierarchy parsing ******************/ /* X86 ONLY ****************************************/ diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c index 96e28c124b5..38ab9162946 100644 --- a/tools/power/cpupower/utils/helpers/sysfs.c +++ b/tools/power/cpupower/utils/helpers/sysfs.c @@ -37,25 +37,6 @@ unsigned int sysfs_read_file(const char *path, char *buf, size_t buflen) return (unsigned int) numread; } -static unsigned int sysfs_write_file(const char *path, - const char *value, size_t len) -{ - int fd; - ssize_t numwrite; - - fd = open(path, O_WRONLY); - if (fd == -1) - return 0; - - numwrite = write(fd, value, len); - if (numwrite < 1) { - close(fd); - return 0; - } - close(fd); - return (unsigned int) numwrite; -} - /* * Detect whether a CPU is online * diff --git a/tools/power/cpupower/utils/helpers/topology.c b/tools/power/cpupower/utils/helpers/topology.c index 4eae2c47ba4..c13120af519 100644 --- a/tools/power/cpupower/utils/helpers/topology.c +++ b/tools/power/cpupower/utils/helpers/topology.c @@ -20,9 +20,8 @@ #include <helpers/sysfs.h> /* returns -1 on failure, 0 on success */ -int sysfs_topology_read_file(unsigned int cpu, const char *fname) +static int sysfs_topology_read_file(unsigned int cpu, const char *fname, int *result) { - unsigned long value; char linebuf[MAX_LINE_LEN]; char *endp; char path[SYSFS_PATH_MAX]; @@ -31,20 +30,12 @@ int sysfs_topology_read_file(unsigned int cpu, const char *fname) cpu, fname); if (sysfs_read_file(path, linebuf, MAX_LINE_LEN) == 0) return -1; - value = strtoul(linebuf, &endp, 0); + *result = strtol(linebuf, &endp, 0); if (endp == linebuf || errno == ERANGE) return -1; - return value; + return 0; } -struct cpuid_core_info { - unsigned int pkg; - unsigned int thread; - unsigned int cpu; - /* flags */ - unsigned int is_online:1; -}; - static int __compare(const void *t1, const void *t2) { struct cpuid_core_info *top1 = (struct cpuid_core_info *)t1; @@ -53,9 +44,9 @@ static int __compare(const void *t1, const void *t2) return -1; else if (top1->pkg > top2->pkg) return 1; - else if (top1->thread < top2->thread) + else if (top1->core < top2->core) return -1; - else if (top1->thread > top2->thread) + else if (top1->core > top2->core) return 1; else if (top1->cpu < top2->cpu) return -1; @@ -73,28 +64,42 @@ static int __compare(const void *t1, const void *t2) */ int get_cpu_topology(struct cpupower_topology *cpu_top) { - int cpu, cpus = sysconf(_SC_NPROCESSORS_CONF); + int cpu, last_pkg, cpus = sysconf(_SC_NPROCESSORS_CONF); - cpu_top->core_info = malloc(sizeof(struct cpupower_topology) * cpus); + cpu_top->core_info = malloc(sizeof(struct cpuid_core_info) * cpus); if (cpu_top->core_info == NULL) return -ENOMEM; cpu_top->pkgs = cpu_top->cores = 0; for (cpu = 0; cpu < cpus; cpu++) { cpu_top->core_info[cpu].cpu = cpu; cpu_top->core_info[cpu].is_online = sysfs_is_cpu_online(cpu); - cpu_top->core_info[cpu].pkg = - sysfs_topology_read_file(cpu, "physical_package_id"); - if ((int)cpu_top->core_info[cpu].pkg != -1 && - cpu_top->core_info[cpu].pkg > cpu_top->pkgs) - cpu_top->pkgs = cpu_top->core_info[cpu].pkg; - cpu_top->core_info[cpu].core = - sysfs_topology_read_file(cpu, "core_id"); + if(sysfs_topology_read_file( + cpu, + "physical_package_id", + &(cpu_top->core_info[cpu].pkg)) < 0) + return -1; + if(sysfs_topology_read_file( + cpu, + "core_id", + &(cpu_top->core_info[cpu].core)) < 0) + return -1; } - cpu_top->pkgs++; qsort(cpu_top->core_info, cpus, sizeof(struct cpuid_core_info), __compare); + /* Count the number of distinct pkgs values. This works + because the primary sort of the core_info struct was just + done by pkg value. */ + last_pkg = cpu_top->core_info[0].pkg; + for(cpu = 1; cpu < cpus; cpu++) { + if(cpu_top->core_info[cpu].pkg != last_pkg) { + last_pkg = cpu_top->core_info[cpu].pkg; + cpu_top->pkgs++; + } + } + cpu_top->pkgs++; + /* Intel's cores count is not consecutively numbered, there may * be a core_id of 3, but none of 2. Assume there always is 0 * Get amount of cores by counting duplicates in a package diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c index 0d6571e418d..c4bae9203a6 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c @@ -39,6 +39,7 @@ static int mode; static int interval = 1; static char *show_monitors_param; static struct cpupower_topology cpu_top; +static unsigned int wake_cpus; /* ToDo: Document this in the manpage */ static char range_abbr[RANGE_MAX] = { 'T', 'C', 'P', 'M', }; @@ -84,7 +85,7 @@ int fill_string_with_spaces(char *s, int n) void print_header(int topology_depth) { int unsigned mon; - int state, need_len, pr_mon_len; + int state, need_len; cstate_t s; char buf[128] = ""; int percent_width = 4; @@ -93,7 +94,6 @@ void print_header(int topology_depth) printf("%s|", buf); for (mon = 0; mon < avail_monitors; mon++) { - pr_mon_len = 0; need_len = monitors[mon]->hw_states_num * (percent_width + 3) - 1; if (mon != 0) { @@ -315,16 +315,28 @@ int fork_it(char **argv) int do_interval_measure(int i) { unsigned int num; + int cpu; + + if (wake_cpus) + for (cpu = 0; cpu < cpu_count; cpu++) + bind_cpu(cpu); for (num = 0; num < avail_monitors; num++) { dprint("HW C-state residency monitor: %s - States: %d\n", monitors[num]->name, monitors[num]->hw_states_num); monitors[num]->start(); } + sleep(i); + + if (wake_cpus) + for (cpu = 0; cpu < cpu_count; cpu++) + bind_cpu(cpu); + for (num = 0; num < avail_monitors; num++) monitors[num]->stop(); + return 0; } @@ -333,7 +345,7 @@ static void cmdline(int argc, char *argv[]) int opt; progname = basename(argv[0]); - while ((opt = getopt(argc, argv, "+li:m:")) != -1) { + while ((opt = getopt(argc, argv, "+lci:m:")) != -1) { switch (opt) { case 'l': if (mode) @@ -352,6 +364,9 @@ static void cmdline(int argc, char *argv[]) mode = show; show_monitors_param = optarg; break; + case 'c': + wake_cpus = 1; + break; default: print_wrong_arg_exit(); } diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h index 9312ee1f2db..9e43f3371fb 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h @@ -65,4 +65,21 @@ extern long long timespec_diff_us(struct timespec start, struct timespec end); "could be inaccurate\n"), mes, ov); \ } + +/* Taken over from x86info project sources -> return 0 on success */ +#include <sched.h> +#include <sys/types.h> +#include <unistd.h> +static inline int bind_cpu(int cpu) +{ + cpu_set_t set; + + if (sched_getaffinity(getpid(), sizeof(set), &set) == 0) { + CPU_ZERO(&set); + CPU_SET(cpu, &set); + return sched_setaffinity(getpid(), sizeof(set), &set); + } + return 1; +} + #endif /* __CPUIDLE_INFO_HW__ */ diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c index a1bc07cd53e..a99b43b97d6 100644 --- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c @@ -150,9 +150,15 @@ static struct cpuidle_monitor *snb_register(void) || cpupower_cpu_info.family != 6) return NULL; - if (cpupower_cpu_info.model != 0x2A - && cpupower_cpu_info.model != 0x2D) + switch (cpupower_cpu_info.model) { + case 0x2A: /* SNB */ + case 0x2D: /* SNB Xeon */ + case 0x3A: /* IVB */ + case 0x3E: /* IVB Xeon */ + break; + default: return NULL; + } is_valid = calloc(cpu_count, sizeof(int)); for (num = 0; num < SNB_CSTATE_COUNT; num++) { diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 96ce80a3743..2964b96aa55 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -1,8 +1,11 @@ -ifeq ("$(origin O)", "command line") +ifeq ($(origin O), command line) dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),) ABSOLUTE_O := $(shell cd $(O) ; pwd) - OUTPUT := $(ABSOLUTE_O)/ + OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/) COMMAND_O := O=$(ABSOLUTE_O) +ifeq ($(objtree),) + objtree := $(O) +endif endif ifneq ($(OUTPUT),) @@ -41,7 +44,16 @@ else NO_SUBDIR = : endif -QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +# +# Define a callable command for descending to a new directory +# +# Call by doing: $(call descend,directory[,target]) +# +descend = \ + +mkdir -p $(OUTPUT)$(1) && \ + $(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2) + +QUIET_SUBDIR0 = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir QUIET_SUBDIR1 = ifneq ($(findstring $(MAKEFLAGS),s),s) @@ -56,5 +68,10 @@ ifndef V $(MAKE) $(PRINT_DIR) -C $$subdir QUIET_FLEX = @echo ' ' FLEX $@; QUIET_BISON = @echo ' ' BISON $@; + + descend = \ + @echo ' ' DESCEND $(1); \ + mkdir -p $(OUTPUT)$(1) && \ + $(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2) endif endif |