diff options
62 files changed, 2348 insertions, 1462 deletions
diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt new file mode 100644 index 000000000000..a39dbbb44c4c --- /dev/null +++ b/tools/perf/Documentation/android.txt @@ -0,0 +1,75 @@ +How to compile perf for Android +========================================= + +I. Set the Android NDK environment +------------------------------------------------ + +(a). Use the Android NDK +------------------------------------------------ +1. You need to download and install the Android Native Development Kit (NDK). +Set the NDK variable to point to the path where you installed the NDK: + export NDK=/path/to/android-ndk + +2. Set cross-compiling environment variables for NDK toolchain and sysroot. +For arm: + export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi- + export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm +For x86: + export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android- + export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86 + +This method is not working for Android NDK versions up to Revision 8b. +perf uses some bionic enhancements that are not included in these NDK versions. +You can use method (b) described below instead. + +(b). Use the Android source tree +----------------------------------------------- +1. Download the master branch of the Android source tree. +Set the environment for the target you want using: + source build/envsetup.sh + lunch + +2. Build your own NDK sysroot to contain latest bionic changes and set the +NDK sysroot environment variable. + cd ${ANDROID_BUILD_TOP}/ndk +For arm: + ./build/tools/build-ndk-sysroot.sh --abi=arm + export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-arm +For x86: + ./build/tools/build-ndk-sysroot.sh --abi=x86 + export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-x86 + +3. Set the NDK toolchain environment variable. +For arm: + export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/arm-linux-androideabi- +For x86: + export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/i686-linux-android- + +II. Compile perf for Android +------------------------------------------------ +You need to run make with the NDK toolchain and sysroot defined above: + make CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}" + +III. Install perf +----------------------------------------------- +You need to connect to your Android device/emulator using adb. +Install perf using: + adb push perf /data/perf + +If you also want to use perf-archive you need busybox tools for Android. +For installing perf-archive, you first need to replace #!/bin/bash with #!/system/bin/sh: + sed 's/#!\/bin\/bash/#!\/system\/bin\/sh/g' perf-archive >> /tmp/perf-archive + chmod +x /tmp/perf-archive + adb push /tmp/perf-archive /data/perf-archive + +IV. Environment settings for running perf +------------------------------------------------ +Some perf features need environment variables to run properly. +You need to set these before running perf on the target: + adb shell + # PERF_PAGER=cat + +IV. Run perf +------------------------------------------------ +Run perf on your device/emulator to which you previously connected using adb: + # ./data/perf diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index ab7f667de1b1..194f37d635df 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -72,6 +72,66 @@ OPTIONS --symfs=<directory>:: Look for files with symbols relative to this directory. +-b:: +--baseline-only:: + Show only items with match in baseline. + +-c:: +--compute:: + Differential computation selection - delta,ratio,wdiff (default is delta). + If '+' is specified as a first character, the output is sorted based + on the computation results. + See COMPARISON METHODS section for more info. + +-p:: +--period:: + Show period values for both compared hist entries. + +-F:: +--formula:: + Show formula for given computation. + +COMPARISON METHODS +------------------ +delta +~~~~~ +If specified the 'Delta' column is displayed with value 'd' computed as: + + d = A->period_percent - B->period_percent + +with: + - A/B being matching hist entry from first/second file specified + (or perf.data/perf.data.old) respectively. + + - period_percent being the % of the hist entry period value within + single data file + +ratio +~~~~~ +If specified the 'Ratio' column is displayed with value 'r' computed as: + + r = A->period / B->period + +with: + - A/B being matching hist entry from first/second file specified + (or perf.data/perf.data.old) respectively. + + - period being the hist entry period value + +wdiff +~~~~~ +If specified the 'Weighted diff' column is displayed with value 'd' computed as: + + d = B->period * WEIGHT-A - A->period * WEIGHT-B + + - A/B being matching hist entry from first/second file specified + (or perf.data/perf.data.old) respectively. + + - period being the hist entry period value + + - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option + behind ':' separator like '-c wdiff:1,2'. + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Makefile b/tools/perf/Makefile index e5e71e7d95a0..318bec8e14e4 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -45,6 +45,8 @@ include config/utilities.mak # # Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf # backtrace post unwind. +# +# Define NO_BACKTRACE if you do not want stack backtrace debug feature $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) @@ -153,15 +155,15 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ -include config/feature-tests.mak -ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y) +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all),y) CFLAGS := $(CFLAGS) -fstack-protector-all endif -ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wstack-protector),y) +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector),y) CFLAGS := $(CFLAGS) -Wstack-protector endif -ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wvolatile-register-var),y) +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var),y) CFLAGS := $(CFLAGS) -Wvolatile-register-var endif @@ -170,6 +172,13 @@ endif BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE BASIC_LDFLAGS = +ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS)),y) + BIONIC := 1 + EXTLIBS := $(filter-out -lrt,$(EXTLIBS)) + EXTLIBS := $(filter-out -lpthread,$(EXTLIBS)) + BASIC_CFLAGS += -I. +endif + # Guard against environment variables BUILTIN_OBJS = LIB_H = @@ -185,7 +194,7 @@ strip-libs = $(filter-out -l%,$(1)) PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources) PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py -$(OUTPUT)python/perf.so: $(PYRF_OBJS) $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) +$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ mkdir -p $(OUTPUT)python && \ @@ -298,6 +307,7 @@ LIB_H += util/evlist.h LIB_H += util/exec_cmd.h LIB_H += util/types.h LIB_H += util/levenshtein.h +LIB_H += util/machine.h LIB_H += util/map.h LIB_H += util/parse-options.h LIB_H += util/parse-events.h @@ -381,6 +391,7 @@ LIB_OBJS += $(OUTPUT)util/header.o LIB_OBJS += $(OUTPUT)util/callchain.o LIB_OBJS += $(OUTPUT)util/values.o LIB_OBJS += $(OUTPUT)util/debug.o +LIB_OBJS += $(OUTPUT)util/machine.o LIB_OBJS += $(OUTPUT)util/map.o LIB_OBJS += $(OUTPUT)util/pstack.o LIB_OBJS += $(OUTPUT)util/session.o @@ -446,20 +457,6 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT) -# Files needed for the python binding, perf.so -# pyrf is just an internal name needed for all those wrappers. -# This has to be in sync with what is in the 'sources' variable in -# tools/perf/util/setup.py - -PYRF_OBJS += $(OUTPUT)util/cpumap.o -PYRF_OBJS += $(OUTPUT)util/ctype.o -PYRF_OBJS += $(OUTPUT)util/evlist.o -PYRF_OBJS += $(OUTPUT)util/evsel.o -PYRF_OBJS += $(OUTPUT)util/python.o -PYRF_OBJS += $(OUTPUT)util/thread_map.o -PYRF_OBJS += $(OUTPUT)util/util.o -PYRF_OBJS += $(OUTPUT)util/xyarray.o - # # Platform specific tweaks # @@ -479,14 +476,26 @@ else FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y) FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS) - ifneq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y) - msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); - else + ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y) + LIBC_SUPPORT := 1 + endif + ifeq ($(BIONIC),1) + LIBC_SUPPORT := 1 + endif + ifeq ($(LIBC_SUPPORT),1) NO_LIBELF := 1 NO_DWARF := 1 NO_DEMANGLE := 1 + else + msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); endif -endif +else + FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS) + ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y) + msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); + NO_DWARF := 1 + endif # Dwarf support +endif # SOURCE_LIBELF endif # NO_LIBELF ifndef NO_LIBUNWIND @@ -511,8 +520,6 @@ ifneq ($(OUTPUT),) endif ifdef NO_LIBELF -BASIC_CFLAGS += -DNO_LIBELF_SUPPORT - EXTLIBS := $(filter-out -lelf,$(EXTLIBS)) # Remove ELF/DWARF dependent codes @@ -527,17 +534,12 @@ BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS)) LIB_OBJS += $(OUTPUT)util/symbol-minimal.o else # NO_LIBELF +BASIC_CFLAGS += -DLIBELF_SUPPORT -ifneq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON)),y) - BASIC_CFLAGS += -DLIBELF_NO_MMAP +ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON)),y) + BASIC_CFLAGS += -DLIBELF_MMAP endif -FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS) -ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y) - msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); - NO_DWARF := 1 -endif # Dwarf support - ifndef NO_DWARF ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); @@ -550,38 +552,33 @@ endif # PERF_HAVE_DWARF_REGS endif # NO_DWARF endif # NO_LIBELF -ifdef NO_LIBUNWIND - BASIC_CFLAGS += -DNO_LIBUNWIND_SUPPORT -else +ifndef NO_LIBUNWIND + BASIC_CFLAGS += -DLIBUNWIND_SUPPORT EXTLIBS += $(LIBUNWIND_LIBS) BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS) BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS) LIB_OBJS += $(OUTPUT)util/unwind.o endif -ifdef NO_LIBAUDIT - BASIC_CFLAGS += -DNO_LIBAUDIT_SUPPORT -else +ifndef NO_LIBAUDIT FLAGS_LIBAUDIT = $(ALL_CFLAGS) $(ALL_LDFLAGS) -laudit ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT)),y) msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev); - BASIC_CFLAGS += -DNO_LIBAUDIT_SUPPORT else + BASIC_CFLAGS += -DLIBAUDIT_SUPPORT BUILTIN_OBJS += $(OUTPUT)builtin-trace.o EXTLIBS += -laudit endif endif -ifdef NO_NEWT - BASIC_CFLAGS += -DNO_NEWT_SUPPORT -else +ifndef NO_NEWT FLAGS_NEWT=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lnewt ifneq ($(call try-cc,$(SOURCE_NEWT),$(FLAGS_NEWT)),y) msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev); - BASIC_CFLAGS += -DNO_NEWT_SUPPORT else # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h BASIC_CFLAGS += -I/usr/include/slang + BASIC_CFLAGS += -DNEWT_SUPPORT EXTLIBS += -lnewt -lslang LIB_OBJS += $(OUTPUT)ui/setup.o LIB_OBJS += $(OUTPUT)ui/browser.o @@ -603,17 +600,15 @@ else endif endif -ifdef NO_GTK2 - BASIC_CFLAGS += -DNO_GTK2_SUPPORT -else +ifndef NO_GTK2 FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y) msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); - BASIC_CFLAGS += -DNO_GTK2_SUPPORT else ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y) BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR endif + BASIC_CFLAGS += -DGTK2_SUPPORT BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null) EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null) LIB_OBJS += $(OUTPUT)ui/gtk/browser.o @@ -621,7 +616,7 @@ else LIB_OBJS += $(OUTPUT)ui/gtk/util.o LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o # Make sure that it'd be included only once. - ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),) + ifeq ($(findstring -DNEWT_SUPPORT,$(BASIC_CFLAGS)),) LIB_OBJS += $(OUTPUT)ui/setup.o LIB_OBJS += $(OUTPUT)ui/util.o endif @@ -762,23 +757,24 @@ ifeq ($(NO_PERF_REGS),0) ifeq ($(ARCH),x86) LIB_H += arch/x86/include/perf_regs.h endif -else - BASIC_CFLAGS += -DNO_PERF_REGS + BASIC_CFLAGS += -DHAVE_PERF_REGS endif -ifdef NO_STRLCPY - BASIC_CFLAGS += -DNO_STRLCPY -else - ifneq ($(call try-cc,$(SOURCE_STRLCPY),),y) - BASIC_CFLAGS += -DNO_STRLCPY +ifndef NO_STRLCPY + ifeq ($(call try-cc,$(SOURCE_STRLCPY),),y) + BASIC_CFLAGS += -DHAVE_STRLCPY endif endif -ifdef NO_BACKTRACE - BASIC_CFLAGS += -DNO_BACKTRACE -else - ifneq ($(call try-cc,$(SOURCE_BACKTRACE),),y) - BASIC_CFLAGS += -DNO_BACKTRACE +ifndef NO_ON_EXIT + ifeq ($(call try-cc,$(SOURCE_ON_EXIT),),y) + BASIC_CFLAGS += -DHAVE_ON_EXIT + endif +endif + +ifndef NO_BACKTRACE + ifeq ($(call try-cc,$(SOURCE_BACKTRACE),),y) + BASIC_CFLAGS += -DBACKTRACE_SUPPORT endif endif diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion index 1958fa539d0f..56e6a12aab59 100644 --- a/tools/perf/bash_completion +++ b/tools/perf/bash_completion @@ -1,23 +1,59 @@ # perf completion +function_exists() +{ + declare -F $1 > /dev/null + return $? +} + +function_exists __ltrim_colon_completions || +__ltrim_colon_completions() +{ + if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then + # Remove colon-word prefix from COMPREPLY items + local colon_word=${1%${1##*:}} + local i=${#COMPREPLY[*]} + while [[ $((--i)) -ge 0 ]]; do + COMPREPLY[$i]=${COMPREPLY[$i]#"$colon_word"} + done + fi +} + have perf && _perf() { - local cur cmd + local cur prev cmd COMPREPLY=() - _get_comp_words_by_ref cur prev + if function_exists _get_comp_words_by_ref; then + _get_comp_words_by_ref -n : cur prev + else + cur=$(_get_cword :) + prev=${COMP_WORDS[COMP_CWORD-1]} + fi cmd=${COMP_WORDS[0]} - # List perf subcommands + # List perf subcommands or long options if [ $COMP_CWORD -eq 1 ]; then - cmds=$($cmd --list-cmds) - COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) ) + if [[ $cur == --* ]]; then + COMPREPLY=( $( compgen -W '--help --version \ + --exec-path --html-path --paginate --no-pager \ + --perf-dir --work-tree --debugfs-dir' -- "$cur" ) ) + else + cmds=$($cmd --list-cmds) + COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) ) + fi # List possible events for -e option elif [[ $prev == "-e" && "${COMP_WORDS[1]}" == @(record|stat|top) ]]; then - cmds=$($cmd list --raw-dump) - COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) ) + evts=$($cmd list --raw-dump) + COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) ) + __ltrim_colon_completions $cur + # List long option names + elif [[ $cur == --* ]]; then + subcmd=${COMP_WORDS[1]} + opts=$($cmd $subcmd --list-opts) + COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) ) # Fall down to list regular files else _filedir diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 9ea38540b873..690fa9a54657 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -246,7 +246,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) .sample = process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .ordered_samples = true, .ordering_requires_timestamps = true, }, diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 83654557e108..d37e077f4b14 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -15,22 +15,6 @@ #include "util/strlist.h" #include "util/symbol.h" -static char const *add_name_list_str, *remove_name_list_str; - -static const char * const buildid_cache_usage[] = { - "perf buildid-cache [<options>]", - NULL -}; - -static const struct option buildid_cache_options[] = { - OPT_STRING('a', "add", &add_name_list_str, - "file list", "file(s) to add"), - OPT_STRING('r', "remove", &remove_name_list_str, "file list", - "file(s) to remove"), - OPT_INCR('v', "verbose", &verbose, "be more verbose"), - OPT_END() -}; - static int build_id_cache__add_file(const char *filename, const char *debugdir) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; @@ -51,8 +35,8 @@ static int build_id_cache__add_file(const char *filename, const char *debugdir) return err; } -static int build_id_cache__remove_file(const char *filename __maybe_unused, - const char *debugdir __maybe_unused) +static int build_id_cache__remove_file(const char *filename, + const char *debugdir) { u8 build_id[BUILD_ID_SIZE]; char sbuild_id[BUILD_ID_SIZE * 2 + 1]; @@ -73,11 +57,34 @@ static int build_id_cache__remove_file(const char *filename __maybe_unused, return err; } -static int __cmd_buildid_cache(void) +int cmd_buildid_cache(int argc, const char **argv, + const char *prefix __maybe_unused) { struct strlist *list; struct str_node *pos; char debugdir[PATH_MAX]; + char const *add_name_list_str = NULL, + *remove_name_list_str = NULL; + const struct option buildid_cache_options[] = { + OPT_STRING('a', "add", &add_name_list_str, + "file list", "file(s) to add"), + OPT_STRING('r', "remove", &remove_name_list_str, "file list", + "file(s) to remove"), + OPT_INCR('v', "verbose", &verbose, "be more verbose"), + OPT_END() + }; + const char * const buildid_cache_usage[] = { + "perf buildid-cache [<options>]", + NULL + }; + + argc = parse_options(argc, argv, buildid_cache_options, + buildid_cache_usage, 0); + + if (symbol__init() < 0) + return -1; + + setup_pager(); snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); @@ -119,16 +126,3 @@ static int __cmd_buildid_cache(void) return 0; } - -int cmd_buildid_cache(int argc, const char **argv, - const char *prefix __maybe_unused) -{ - argc = parse_options(argc, argv, buildid_cache_options, - buildid_cache_usage, 0); - - if (symbol__init() < 0) - return -1; - - setup_pager(); - return __cmd_buildid_cache(); -} diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 1159feeebb19..a0e94fffa03e 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -16,27 +16,6 @@ #include "util/session.h" #include "util/symbol.h" -static const char *input_name; -static bool force; -static bool show_kernel; -static bool with_hits; - -static const char * const buildid_list_usage[] = { - "perf buildid-list [<options>]", - NULL -}; - -static const struct option options[] = { - OPT_BOOLEAN('H', "with-hits", &with_hits, "Show only DSOs with hits"), - OPT_STRING('i', "input", &input_name, "file", - "input file name"), - OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), - OPT_BOOLEAN('k', "kernel", &show_kernel, "Show current kernel build id"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose"), - OPT_END() -}; - static int sysfs__fprintf_build_id(FILE *fp) { u8 kallsyms_build_id[BUILD_ID_SIZE]; @@ -65,7 +44,8 @@ static int filename__fprintf_build_id(const char *name, FILE *fp) return fprintf(fp, "%s\n", sbuild_id); } -static int perf_session__list_build_ids(void) +static int perf_session__list_build_ids(const char *input_name, + bool force, bool with_hits) { struct perf_session *session; @@ -95,18 +75,31 @@ out: return 0; } -static int __cmd_buildid_list(void) -{ - if (show_kernel) - return sysfs__fprintf_build_id(stdout); - - return perf_session__list_build_ids(); -} - int cmd_buildid_list(int argc, const char **argv, const char *prefix __maybe_unused) { + bool show_kernel = false; + bool with_hits = false; + bool force = false; + const char *input_name = NULL; + const struct option options[] = { + OPT_BOOLEAN('H', "with-hits", &with_hits, "Show only DSOs with hits"), + OPT_STRING('i', "input", &input_name, "file", "input file name"), + OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), + OPT_BOOLEAN('k', "kernel", &show_kernel, "Show current kernel build id"), + OPT_INCR('v', "verbose", &verbose, "be more verbose"), + OPT_END() + }; + const char * const buildid_list_usage[] = { + "perf buildid-list [<options>]", + NULL + }; + argc = parse_options(argc, argv, options, buildid_list_usage, 0); setup_pager(); - return __cmd_buildid_list(); + + if (show_kernel) + return sysfs__fprintf_build_id(stdout); + + return perf_session__list_build_ids(input_name, force, with_hits); } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 761f4197a9e2..380683de1df3 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -24,6 +24,228 @@ static char const *input_old = "perf.data.old", static char diff__default_sort_order[] = "dso,symbol"; static bool force; static bool show_displacement; +static bool show_period; +static bool show_formula; +static bool show_baseline_only; +static bool sort_compute; + +static s64 compute_wdiff_w1; +static s64 compute_wdiff_w2; + +enum { + COMPUTE_DELTA, + COMPUTE_RATIO, + COMPUTE_WEIGHTED_DIFF, + COMPUTE_MAX, +}; + +const char *compute_names[COMPUTE_MAX] = { + [COMPUTE_DELTA] = "delta", + [COMPUTE_RATIO] = "ratio", + [COMPUTE_WEIGHTED_DIFF] = "wdiff", +}; + +static int compute; + +static int setup_compute_opt_wdiff(char *opt) +{ + char *w1_str = opt; + char *w2_str; + + int ret = -EINVAL; + + if (!opt) + goto out; + + w2_str = strchr(opt, ','); + if (!w2_str) + goto out; + + *w2_str++ = 0x0; + if (!*w2_str) + goto out; + + compute_wdiff_w1 = strtol(w1_str, NULL, 10); + compute_wdiff_w2 = strtol(w2_str, NULL, 10); + + if (!compute_wdiff_w1 || !compute_wdiff_w2) + goto out; + + pr_debug("compute wdiff w1(%" PRId64 ") w2(%" PRId64 ")\n", + compute_wdiff_w1, compute_wdiff_w2); + + ret = 0; + + out: + if (ret) + pr_err("Failed: wrong weight data, use 'wdiff:w1,w2'\n"); + + return ret; +} + +static int setup_compute_opt(char *opt) +{ + if (compute == COMPUTE_WEIGHTED_DIFF) + return setup_compute_opt_wdiff(opt); + + if (opt) { + pr_err("Failed: extra option specified '%s'", opt); + return -EINVAL; + } + + return 0; +} + +static int setup_compute(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + int *cp = (int *) opt->value; + char *cstr = (char *) str; + char buf[50]; + unsigned i; + char *option; + + if (!str) { + *cp = COMPUTE_DELTA; + return 0; + } + + if (*str == '+') { + sort_compute = true; + cstr = (char *) ++str; + if (!*str) + return 0; + } + + option = strchr(str, ':'); + if (option) { + unsigned len = option++ - str; + + /* + * The str data are not writeable, so we need + * to use another buffer. + */ + + /* No option value is longer. */ + if (len >= sizeof(buf)) + return -EINVAL; + + strncpy(buf, str, len); + buf[len] = 0x0; + cstr = buf; + } + + for (i = 0; i < COMPUTE_MAX; i++) + if (!strcmp(cstr, compute_names[i])) { + *cp = i; + return setup_compute_opt(option); + } + + pr_err("Failed: '%s' is not computation method " + "(use 'delta','ratio' or 'wdiff')\n", str); + return -EINVAL; +} + +static double get_period_percent(struct hist_entry *he, u64 period) +{ + u64 total = he->hists->stats.total_period; + return (period * 100.0) / total; +} + +double perf_diff__compute_delta(struct hist_entry *he) +{ + struct hist_entry *pair = he->pair; + double new_percent = get_period_percent(he, he->stat.period); + double old_percent = pair ? get_period_percent(pair, pair->stat.period) : 0.0; + + he->diff.period_ratio_delta = new_percent - old_percent; + he->diff.computed = true; + return he->diff.period_ratio_delta; +} + +double perf_diff__compute_ratio(struct hist_entry *he) +{ + struct hist_entry *pair = he->pair; + double new_period = he->stat.period; + double old_period = pair ? pair->stat.period : 0; + + he->diff.computed = true; + he->diff.period_ratio = pair ? (new_period / old_period) : 0; + return he->diff.period_ratio; +} + +s64 perf_diff__compute_wdiff(struct hist_entry *he) +{ + struct hist_entry *pair = he->pair; + u64 new_period = he->stat.period; + u64 old_period = pair ? pair->stat.period : 0; + + he->diff.computed = true; + + if (!pair) + he->diff.wdiff = 0; + else + he->diff.wdiff = new_period * compute_wdiff_w2 - + old_period * compute_wdiff_w1; + + return he->diff.wdiff; +} + +static int formula_delta(struct hist_entry *he, char *buf, size_t size) +{ + struct hist_entry *pair = he->pair; + + if (!pair) + return -1; + + return scnprintf(buf, size, + "(%" PRIu64 " * 100 / %" PRIu64 ") - " + "(%" PRIu64 " * 100 / %" PRIu64 ")", + he->stat.period, he->hists->stats.total_period, + pair->stat.period, pair->hists->stats.total_period); +} + +static int formula_ratio(struct hist_entry *he, char *buf, size_t size) +{ + struct hist_entry *pair = he->pair; + double new_period = he->stat.period; + double old_period = pair ? pair->stat.period : 0; + + if (!pair) + return -1; + + return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period); +} + +static int formula_wdiff(struct hist_entry *he, char *buf, size_t size) +{ + struct hist_entry *pair = he->pair; + u64 new_period = he->stat.period; + u64 old_period = pair ? pair->stat.period : 0; + + if (!pair) + return -1; + + return scnprintf(buf, size, + "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")", + new_period, compute_wdiff_w2, old_period, compute_wdiff_w1); +} + +int perf_diff__formula(char *buf, size_t size, struct hist_entry *he) +{ + switch (compute) { + case COMPUTE_DELTA: + return formula_delta(he, buf, size); + case COMPUTE_RATIO: + return formula_ratio(he, buf, size); + case COMPUTE_WEIGHTED_DIFF: + return formula_wdiff(he, buf, size); + default: + BUG_ON(1); + } + + return -1; +} static int hists__add_entry(struct hists *self, struct addr_location *al, u64 period) @@ -47,7 +269,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (al.filtered || al.sym == NULL) + if (al.filtered) return 0; if (hists__add_entry(&evsel->hists, &al, sample->period)) { @@ -63,15 +285,15 @@ static struct perf_tool tool = { .sample = diff__process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .lost = perf_event__process_lost, .ordered_samples = true, .ordering_requires_timestamps = true, }; -static void perf_session__insert_hist_entry_by_name(struct rb_root *root, - struct hist_entry *he) +static void insert_hist_entry_by_name(struct rb_root *root, + struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -90,7 +312,7 @@ static void perf_session__insert_hist_entry_by_name(struct rb_root *root, rb_insert_color(&he->rb_node, root); } -static void hists__resort_entries(struct hists *self) +static void hists__name_resort(struct hists *self, bool sort) { unsigned long position = 1; struct rb_root tmp = RB_ROOT; @@ -100,12 +322,16 @@ static void hists__resort_entries(struct hists *self) struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - rb_erase(&n->rb_node, &self->entries); n->position = position++; - perf_session__insert_hist_entry_by_name(&tmp, n); + + if (sort) { + rb_erase(&n->rb_node, &self->entries); + insert_hist_entry_by_name(&tmp, n); + } } - self->entries = tmp; + if (sort) + self->entries = tmp; } static struct hist_entry *hists__find_entry(struct hists *self, @@ -121,7 +347,7 @@ static struct hist_entry *hists__find_entry(struct hists *self, n = n->rb_left; else if (cmp > 0) n = n->rb_right; - else + else return iter; } @@ -150,6 +376,160 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel, return NULL; } +static void perf_evlist__resort_hists(struct perf_evlist *evlist, bool name) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + struct hists *hists = &evsel->hists; + + hists__output_resort(hists); + + /* + * The hists__name_resort only sets possition + * if name is false. + */ + if (name || ((!name) && show_displacement)) + hists__name_resort(hists, name); + } +} + +static void hists__baseline_only(struct hists *hists) +{ + struct rb_node *next = rb_first(&hists->entries); + + while (next != NULL) { + struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + + next = rb_next(&he->rb_node); + if (!he->pair) { + rb_erase(&he->rb_node, &hists->entries); + hist_entry__free(he); + } + } +} + +static void hists__precompute(struct hists *hists) +{ + struct rb_node *next = rb_first(&hists->entries); + + while (next != NULL) { + struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + + next = rb_next(&he->rb_node); + + switch (compute) { + case COMPUTE_DELTA: + perf_diff__compute_delta(he); + break; + case COMPUTE_RATIO: + perf_diff__compute_ratio(he); + break; + case COMPUTE_WEIGHTED_DIFF: + perf_diff__compute_wdiff(he); + break; + default: + BUG_ON(1); + } + } +} + +static int64_t cmp_doubles(double l, double r) +{ + if (l > r) + return -1; + else if (l < r) + return 1; + else + return 0; +} + +static int64_t +hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, + int c) +{ + switch (c) { + case COMPUTE_DELTA: + { + double l = left->diff.period_ratio_delta; + double r = right->diff.period_ratio_delta; + + return cmp_doubles(l, r); + } + case COMPUTE_RATIO: + { + double l = left->diff.period_ratio; + double r = right->diff.period_ratio; + + return cmp_doubles(l, r); + } + case COMPUTE_WEIGHTED_DIFF: + { + s64 l = left->diff.wdiff; + s64 r = right->diff.wdiff; + + return r - l; + } + default: + BUG_ON(1); + } + + return 0; +} + +static void insert_hist_entry_by_compute(struct rb_root *root, + struct hist_entry *he, + int c) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + if (hist_entry__cmp_compute(he, iter, c) < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, root); +} + +static void hists__compute_resort(struct hists *hists) +{ + struct rb_root tmp = RB_ROOT; + struct rb_node *next = rb_first(&hists->entries); + + while (next != NULL) { + struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + + next = rb_next(&he->rb_node); + + rb_erase(&he->rb_node, &hists->entries); + insert_hist_entry_by_compute(&tmp, he, compute); + } + + hists->entries = tmp; +} + +static void hists__process(struct hists *old, struct hists *new) +{ + hists__match(old, new); + + if (show_baseline_only) + hists__baseline_only(new); + + if (sort_compute) { + hists__precompute(new); + hists__compute_resort(new); + } + + hists__fprintf(new, true, 0, 0, stdout); +} + static int __cmd_diff(void) { int ret, i; @@ -176,15 +556,8 @@ static int __cmd_diff(void) evlist_old = older->evlist; evlist_new = newer->evlist; - list_for_each_entry(evsel, &evlist_new->entries, node) - hists__output_resort(&evsel->hists); - - list_for_each_entry(evsel, &evlist_old->entries, node) { - hists__output_resort(&evsel->hists); - - if (show_displacement) - hists__resort_entries(&evsel->hists); - } + perf_evlist__resort_hists(evlist_old, true); + perf_evlist__resort_hists(evlist_new, false); list_for_each_entry(evsel, &evlist_new->entries, node) { struct perf_evsel *evsel_old; @@ -198,9 +571,7 @@ static int __cmd_diff(void) first = false; - hists__match(&evsel_old->hists, &evsel->hists); - hists__fprintf(&evsel->hists, &evsel_old->hists, - show_displacement, true, 0, 0, stdout); + hists__process(&evsel_old->hists, &evsel->hists); } out_delete: @@ -221,6 +592,16 @@ static const struct option options[] = { "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('M', "displacement", &show_displacement, "Show position displacement relative to baseline"), + OPT_BOOLEAN('b', "baseline-only", &show_baseline_only, + "Show only items with match in baseline"), + OPT_CALLBACK('c', "compute", &compute, + "delta,ratio,wdiff:w1,w2 (default delta)", + "Entries differential computation selection", + setup_compute), + OPT_BOOLEAN('p', "period", &show_period, + "Show period values."), + OPT_BOOLEAN('F', "formula", &show_formula, + "Show formula."), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), @@ -242,6 +623,45 @@ static const struct option options[] = { OPT_END() }; +static void ui_init(void) +{ + perf_hpp__init(); + + /* No overhead column. */ + perf_hpp__column_enable(PERF_HPP__OVERHEAD, false); + + /* + * Display baseline/delta/ratio/displacement/ + * formula/periods columns. + */ + perf_hpp__column_enable(PERF_HPP__BASELINE, true); + + switch (compute) { + case COMPUTE_DELTA: + perf_hpp__column_enable(PERF_HPP__DELTA, true); + break; + case COMPUTE_RATIO: + perf_hpp__column_enable(PERF_HPP__RATIO, true); + break; + case COMPUTE_WEIGHTED_DIFF: + perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF, true); + break; + default: + BUG_ON(1); + }; + + if (show_displacement) + perf_hpp__column_enable(PERF_HPP__DISPL, true); + + if (show_formula) + perf_hpp__column_enable(PERF_HPP__FORMULA, true); + + if (show_period) { + perf_hpp__column_enable(PERF_HPP__PERIOD, true); + perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE, true); + } +} + int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) { sort_order = diff__default_sort_order; @@ -264,7 +684,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) if (symbol__init() < 0) return -1; - perf_hpp__init(true, show_displacement); + ui_init(); + setup_sorting(diff_usage, options); setup_pager(); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 1fb164164fd0..997afb82691b 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -108,23 +108,20 @@ static int __cmd_evlist(const char *input_name, struct perf_attr_details *detail return 0; } -static const char * const evlist_usage[] = { - "perf evlist [<options>]", - NULL -}; - int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_attr_details details = { .verbose = false, }; const char *input_name = NULL; const struct option options[] = { - OPT_STRING('i', "input", &input_name, "file", - "Input file name"), - OPT_BOOLEAN('F', "freq", &details.freq, - "Show the sample frequency"), - OPT_BOOLEAN('v', "verbose", &details.verbose, - "Show all event attr details"), - OPT_END() + OPT_STRING('i', "input", &input_name, "file", "Input file name"), + OPT_BOOLEAN('F', "freq", &details.freq, "Show the sample frequency"), + OPT_BOOLEAN('v', "verbose", &details.verbose, + "Show all event attr details"), + OPT_END() + }; + const char * const evlist_usage[] = { + "perf evlist [<options>]", + NULL }; argc = parse_options(argc, argv, options, evlist_usage, 0); diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 25c8b942ff85..411ee5664e98 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -30,23 +30,6 @@ enum help_format { HELP_FORMAT_WEB, }; -static bool show_all = false; -static enum help_format help_format = HELP_FORMAT_NONE; -static struct option builtin_help_options[] = { - OPT_BOOLEAN('a', "all", &show_all, "print all available commands"), - OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN), - OPT_SET_UINT('w', "web", &help_format, "show manual in web browser", - HELP_FORMAT_WEB), - OPT_SET_UINT('i', "info", &help_format, "show info page", - HELP_FORMAT_INFO), - OPT_END(), -}; - -static const char * const builtin_help_usage[] = { - "perf help [--all] [--man|--web|--info] [command]", - NULL -}; - static enum help_format parse_help_format(const char *format) { if (!strcmp(format, "man")) @@ -258,11 +241,13 @@ static int add_man_viewer_info(const char *var, const char *value) static int perf_help_config(const char *var, const char *value, void *cb) { + enum help_format *help_formatp = cb; + if (!strcmp(var, "help.format")) { if (!value) return config_error_nonbool(var); - help_format = parse_help_format(value); - if (help_format == HELP_FORMAT_NONE) + *help_formatp = parse_help_format(value); + if (*help_formatp == HELP_FORMAT_NONE) return -1; return 0; } @@ -428,12 +413,27 @@ static int show_html_page(const char *perf_cmd) int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) { + bool show_all = false; + enum help_format help_format = HELP_FORMAT_NONE; + struct option builtin_help_options[] = { + OPT_BOOLEAN('a', "all", &show_all, "print all available commands"), + OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN), + OPT_SET_UINT('w', "web", &help_format, "show manual in web browser", + HELP_FORMAT_WEB), + OPT_SET_UINT('i', "info", &help_format, "show info page", + HELP_FORMAT_INFO), + OPT_END(), + }; + const char * const builtin_help_usage[] = { + "perf help [--all] [--man|--web|--info] [command]", + NULL + }; const char *alias; int rc = 0; load_command_list("perf-", &main_cmds, &other_cmds); - perf_config(perf_help_config, NULL); + perf_config(perf_help_config, &help_format); argc = parse_options(argc, argv, builtin_help_options, builtin_help_usage, 0); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 1eaa6617c814..386a5c0013ff 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -14,8 +14,10 @@ #include "util/parse-options.h" -static char const *input_name = "-"; -static bool inject_build_ids; +struct perf_inject { + struct perf_tool tool; + bool build_ids; +}; static int perf_event__repipe_synth(struct perf_tool *tool __maybe_unused, union perf_event *event, @@ -100,14 +102,14 @@ static int perf_event__repipe_mmap(struct perf_tool *tool, return err; } -static int perf_event__repipe_task(struct perf_tool *tool, +static int perf_event__repipe_fork(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { int err; - err = perf_event__process_task(tool, event, sample, machine); + err = perf_event__process_fork(tool, event, sample, machine); perf_event__repipe(tool, event, sample, machine); return err; @@ -194,7 +196,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, * account this as unresolved. */ } else { -#ifndef NO_LIBELF_SUPPORT +#ifdef LIBELF_SUPPORT pr_warning("no symbols found in %s, maybe " "install a debug package?\n", al.map->dso->long_name); @@ -208,22 +210,6 @@ repipe: return 0; } -struct perf_tool perf_inject = { - .sample = perf_event__repipe_sample, - .mmap = perf_event__repipe, - .comm = perf_event__repipe, - .fork = perf_event__repipe, - .exit = perf_event__repipe, - .lost = perf_event__repipe, - .read = perf_event__repipe_sample, - .throttle = perf_event__repipe, - .unthrottle = perf_event__repipe, - .attr = perf_event__repipe_attr, - .event_type = perf_event__repipe_event_type_synth, - .tracing_data = perf_event__repipe_tracing_data_synth, - .build_id = perf_event__repipe_op2_synth, -}; - extern volatile int session_done; static void sig_handler(int sig __maybe_unused) @@ -231,56 +217,72 @@ static void sig_handler(int sig __maybe_unused) session_done = 1; } -static int __cmd_inject(void) +static int __cmd_inject(struct perf_inject *inject) { struct perf_session *session; int ret = -EINVAL; signal(SIGINT, sig_handler); - if (inject_build_ids) { - perf_inject.sample = perf_event__inject_buildid; - perf_inject.mmap = perf_event__repipe_mmap; - perf_inject.fork = perf_event__repipe_task; - perf_inject.tracing_data = perf_event__repipe_tracing_data; + if (inject->build_ids) { + inject->tool.sample = perf_event__inject_buildid; + inject->tool.mmap = perf_event__repipe_mmap; + inject->tool.fork = perf_event__repipe_fork; + inject->tool.tracing_data = perf_event__repipe_tracing_data; } - session = perf_session__new(input_name, O_RDONLY, false, true, &perf_inject); + session = perf_session__new("-", O_RDONLY, false, true, &inject->tool); if (session == NULL) return -ENOMEM; - ret = perf_session__process_events(session, &perf_inject); + ret = perf_session__process_events(session, &inject->tool); perf_session__delete(session); return ret; } -static const char * const report_usage[] = { - "perf inject [<options>]", - NULL -}; - -static const struct option options[] = { - OPT_BOOLEAN('b', "build-ids", &inject_build_ids, - "Inject build-ids into the output stream"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show build ids, etc)"), - OPT_END() -}; - int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) { - argc = parse_options(argc, argv, options, report_usage, 0); + struct perf_inject inject = { + .tool = { + .sample = perf_event__repipe_sample, + .mmap = perf_event__repipe, + .comm = perf_event__repipe, + .fork = perf_event__repipe, + .exit = perf_event__repipe, + .lost = perf_event__repipe, + .read = perf_event__repipe_sample, + .throttle = perf_event__repipe, + .unthrottle = perf_event__repipe, + .attr = perf_event__repipe_attr, + .event_type = perf_event__repipe_event_type_synth, + .tracing_data = perf_event__repipe_tracing_data_synth, + .build_id = perf_event__repipe_op2_synth, + }, + }; + const struct option options[] = { + OPT_BOOLEAN('b', "build-ids", &inject.build_ids, + "Inject build-ids into the output stream"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show build ids, etc)"), + OPT_END() + }; + const char * const inject_usage[] = { + "perf inject [<options>]", + NULL + }; + + argc = parse_options(argc, argv, options, inject_usage, 0); /* * Any (unrecognized) arguments left? */ if (argc) - usage_with_options(report_usage, options); + usage_with_options(inject_usage, options); if (symbol__init() < 0) return -1; - return __cmd_inject(); + return __cmd_inject(&inject); } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index bc912c68f49a..14bf82f63659 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -21,8 +21,6 @@ struct alloc_stat; typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *); -static const char *input_name; - static int alloc_flag; static int caller_flag; @@ -31,8 +29,6 @@ static int caller_lines = -1; static bool raw_ip; -static char default_sort_order[] = "frag,hit,bytes"; - static int *cpunode_map; static int max_cpu_num; @@ -481,7 +477,7 @@ static void sort_result(void) __sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort); } -static int __cmd_kmem(void) +static int __cmd_kmem(const char *input_name) { int err = -EINVAL; struct perf_session *session; @@ -520,11 +516,6 @@ out_delete: return err; } -static const char * const kmem_usage[] = { - "perf kmem [<options>] {record|stat}", - NULL -}; - static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r) { if (l->ptr < r->ptr) @@ -720,41 +711,17 @@ static int parse_line_opt(const struct option *opt __maybe_unused, return 0; } -static const struct option kmem_options[] = { - OPT_STRING('i', "input", &input_name, "file", - "input file name"), - OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL, - "show per-callsite statistics", - parse_caller_opt), - OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL, - "show per-allocation statistics", - parse_alloc_opt), - OPT_CALLBACK('s', "sort", NULL, "key[,key2...]", - "sort by keys: ptr, call_site, bytes, hit, pingpong, frag", - parse_sort_opt), - OPT_CALLBACK('l', "line", NULL, "num", - "show n lines", - parse_line_opt), - OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"), - OPT_END() -}; - -static const char *record_args[] = { - "record", - "-a", - "-R", - "-f", - "-c", "1", +static int __cmd_record(int argc, const char **argv) +{ + const char * const record_args[] = { + "record", "-a", "-R", "-f", "-c", "1", "-e", "kmem:kmalloc", "-e", "kmem:kmalloc_node", "-e", "kmem:kfree", "-e", "kmem:kmem_cache_alloc", "-e", "kmem:kmem_cache_alloc_node", "-e", "kmem:kmem_cache_free", -}; - -static int __cmd_record(int argc, const char **argv) -{ + }; unsigned int rec_argc, i, j; const char **rec_argv; @@ -775,6 +742,25 @@ static int __cmd_record(int argc, const char **argv) int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) { + const char * const default_sort_order = "frag,hit,bytes"; + const char *input_name = NULL; + const struct option kmem_options[] = { + OPT_STRING('i', "input", &input_name, "file", "input file name"), + OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL, + "show per-callsite statistics", parse_caller_opt), + OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL, + "show per-allocation statistics", parse_alloc_opt), + OPT_CALLBACK('s', "sort", NULL, "key[,key2...]", + "sort by keys: ptr, call_site, bytes, hit, pingpong, frag", + parse_sort_opt), + OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt), + OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"), + OPT_END() + }; + const char * const kmem_usage[] = { + "perf kmem [<options>] {record|stat}", + NULL + }; argc = parse_options(argc, argv, kmem_options, kmem_usage, 0); if (!argc) @@ -793,7 +779,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (list_empty(&alloc_sort)) setup_sorting(&alloc_sort, default_sort_order); - return __cmd_kmem(); + return __cmd_kmem(input_name); } else usage_with_options(kmem_usage, kmem_options); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index a28c9cad9048..836c82f01371 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -32,16 +32,76 @@ struct event_key { int info; }; +struct kvm_event_stats { + u64 time; + struct stats stats; +}; + +struct kvm_event { + struct list_head hash_entry; + struct rb_node rb; + + struct event_key key; + + struct kvm_event_stats total; + + #define DEFAULT_VCPU_NUM 8 + int max_vcpu; + struct kvm_event_stats *vcpu; +}; + +typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); + +struct kvm_event_key { + const char *name; + key_cmp_fun key; +}; + + +struct perf_kvm; + struct kvm_events_ops { bool (*is_begin_event)(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key); bool (*is_end_event)(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key); - void (*decode_key)(struct event_key *key, char decode[20]); + void (*decode_key)(struct perf_kvm *kvm, struct event_key *key, + char decode[20]); const char *name; }; +struct exit_reasons_table { + unsigned long exit_code; + const char *reason; +}; + +#define EVENTS_BITS 12 +#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) + +struct perf_kvm { + struct perf_tool tool; + struct perf_session *session; + + const char *file_name; + const char *report_event; + const char *sort_key; + int trace_vcpu; + + struct exit_reasons_table *exit_reasons; + int exit_reasons_size; + const char *exit_reasons_isa; + + struct kvm_events_ops *events_ops; + key_cmp_fun compare; + struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; + u64 total_time; + u64 total_count; + + struct rb_root result; +}; + + static void exit_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) @@ -78,45 +138,35 @@ static bool exit_event_end(struct perf_evsel *evsel, return kvm_entry_event(evsel); } -struct exit_reasons_table { - unsigned long exit_code; - const char *reason; -}; - -struct exit_reasons_table vmx_exit_reasons[] = { +static struct exit_reasons_table vmx_exit_reasons[] = { VMX_EXIT_REASONS }; -struct exit_reasons_table svm_exit_reasons[] = { +static struct exit_reasons_table svm_exit_reasons[] = { SVM_EXIT_REASONS }; -static int cpu_isa; - -static const char *get_exit_reason(u64 exit_code) +static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code) { - int table_size = ARRAY_SIZE(svm_exit_reasons); - struct exit_reasons_table *table = svm_exit_reasons; - - if (cpu_isa == 1) { - table = vmx_exit_reasons; - table_size = ARRAY_SIZE(vmx_exit_reasons); - } + int i = kvm->exit_reasons_size; + struct exit_reasons_table *tbl = kvm->exit_reasons; - while (table_size--) { - if (table->exit_code == exit_code) - return table->reason; - table++; + while (i--) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; } pr_err("unknown kvm exit code:%lld on %s\n", - (unsigned long long)exit_code, cpu_isa ? "VMX" : "SVM"); + (unsigned long long)exit_code, kvm->exit_reasons_isa); return "UNKNOWN"; } -static void exit_event_decode_key(struct event_key *key, char decode[20]) +static void exit_event_decode_key(struct perf_kvm *kvm, + struct event_key *key, + char decode[20]) { - const char *exit_reason = get_exit_reason(key->key); + const char *exit_reason = get_exit_reason(kvm, key->key); scnprintf(decode, 20, "%s", exit_reason); } @@ -128,11 +178,11 @@ static struct kvm_events_ops exit_events = { .name = "VM-EXIT" }; - /* - * For the mmio events, we treat: - * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry - * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). - */ +/* + * For the mmio events, we treat: + * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry + * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). + */ static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -178,7 +228,9 @@ static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, return false; } -static void mmio_event_decode_key(struct event_key *key, char decode[20]) +static void mmio_event_decode_key(struct perf_kvm *kvm __maybe_unused, + struct event_key *key, + char decode[20]) { scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key, key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); @@ -219,7 +271,9 @@ static bool ioport_event_end(struct perf_evsel *evsel, return kvm_entry_event(evsel); } -static void ioport_event_decode_key(struct event_key *key, char decode[20]) +static void ioport_event_decode_key(struct perf_kvm *kvm __maybe_unused, + struct event_key *key, + char decode[20]) { scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key, key->info ? "POUT" : "PIN"); @@ -232,64 +286,37 @@ static struct kvm_events_ops ioport_events = { .name = "IO Port Access" }; -static const char *report_event = "vmexit"; -struct kvm_events_ops *events_ops; - -static bool register_kvm_events_ops(void) +static bool register_kvm_events_ops(struct perf_kvm *kvm) { bool ret = true; - if (!strcmp(report_event, "vmexit")) - events_ops = &exit_events; - else if (!strcmp(report_event, "mmio")) - events_ops = &mmio_events; - else if (!strcmp(report_event, "ioport")) - events_ops = &ioport_events; + if (!strcmp(kvm->report_event, "vmexit")) + kvm->events_ops = &exit_events; + else if (!strcmp(kvm->report_event, "mmio")) + kvm->events_ops = &mmio_events; + else if (!strcmp(kvm->report_event, "ioport")) + kvm->events_ops = &ioport_events; else { - pr_err("Unknown report event:%s\n", report_event); + pr_err("Unknown report event:%s\n", kvm->report_event); ret = false; } return ret; } -struct kvm_event_stats { - u64 time; - struct stats stats; -}; - -struct kvm_event { - struct list_head hash_entry; - struct rb_node rb; - - struct event_key key; - - struct kvm_event_stats total; - - #define DEFAULT_VCPU_NUM 8 - int max_vcpu; - struct kvm_event_stats *vcpu; -}; - struct vcpu_event_record { int vcpu_id; u64 start_time; struct kvm_event *last_event; }; -#define EVENTS_BITS 12 -#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) - -static u64 total_time; -static u64 total_count; -static struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; -static void init_kvm_event_record(void) +static void init_kvm_event_record(struct perf_kvm *kvm) { - int i; + unsigned int i; - for (i = 0; i < (int)EVENTS_CACHE_SIZE; i++) - INIT_LIST_HEAD(&kvm_events_cache[i]); + for (i = 0; i < EVENTS_CACHE_SIZE; i++) + INIT_LIST_HEAD(&kvm->kvm_events_cache[i]); } static int kvm_events_hash_fn(u64 key) @@ -333,17 +360,19 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key) return event; } -static struct kvm_event *find_create_kvm_event(struct event_key *key) +static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm, + struct event_key *key) { struct kvm_event *event; struct list_head *head; BUG_ON(key->key == INVALID_KEY); - head = &kvm_events_cache[kvm_events_hash_fn(key->key)]; - list_for_each_entry(event, head, hash_entry) + head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)]; + list_for_each_entry(event, head, hash_entry) { if (event->key.key == key->key && event->key.info == key->info) return event; + } event = kvm_alloc_init_event(key); if (!event) @@ -353,13 +382,14 @@ static struct kvm_event *find_create_kvm_event(struct event_key *key) return event; } -static bool handle_begin_event(struct vcpu_event_record *vcpu_record, +static bool handle_begin_event(struct perf_kvm *kvm, + struct vcpu_event_record *vcpu_record, struct event_key *key, u64 timestamp) { struct kvm_event *event = NULL; if (key->key != INVALID_KEY) - event = find_create_kvm_event(key); + event = find_create_kvm_event(kvm, key); vcpu_record->last_event = event; vcpu_record->start_time = timestamp; @@ -387,7 +417,10 @@ static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event) static bool update_kvm_event(struct kvm_event *event, int vcpu_id, u64 time_diff) { - kvm_update_event_stats(&event->total, time_diff); + if (vcpu_id == -1) { + kvm_update_event_stats(&event->total, time_diff); + return true; + } if (!kvm_event_expand(event, vcpu_id)) return false; @@ -396,11 +429,19 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id, return true; } -static bool handle_end_event(struct vcpu_event_record *vcpu_record, - struct event_key *key, u64 timestamp) +static bool handle_end_event(struct perf_kvm *kvm, + struct vcpu_event_record *vcpu_record, + struct event_key *key, + u64 timestamp) { struct kvm_event *event; u64 time_begin, time_diff; + int vcpu; + + if (kvm->trace_vcpu == -1) + vcpu = -1; + else + vcpu = vcpu_record->vcpu_id; event = vcpu_record->last_event; time_begin = vcpu_record->start_time; @@ -419,7 +460,7 @@ static bool handle_end_event(struct vcpu_event_record *vcpu_record, return true; if (!event) - event = find_create_kvm_event(key); + event = find_create_kvm_event(kvm, key); if (!event) return false; @@ -430,7 +471,7 @@ static bool handle_end_event(struct vcpu_event_record *vcpu_record, BUG_ON(timestamp < time_begin); time_diff = timestamp - time_begin; - return update_kvm_event(event, vcpu_record->vcpu_id, time_diff); + return update_kvm_event(event, vcpu, time_diff); } static @@ -455,7 +496,9 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, return thread->priv; } -static bool handle_kvm_event(struct thread *thread, struct perf_evsel *evsel, +static bool handle_kvm_event(struct perf_kvm *kvm, + struct thread *thread, + struct perf_evsel *evsel, struct perf_sample *sample) { struct vcpu_event_record *vcpu_record; @@ -465,22 +508,20 @@ static bool handle_kvm_event(struct thread *thread, struct perf_evsel *evsel, if (!vcpu_record) return true; - if (events_ops->is_begin_event(evsel, sample, &key)) - return handle_begin_event(vcpu_record, &key, sample->time); + /* only process events for vcpus user cares about */ + if ((kvm->trace_vcpu != -1) && + (kvm->trace_vcpu != vcpu_record->vcpu_id)) + return true; + + if (kvm->events_ops->is_begin_event(evsel, sample, &key)) + return handle_begin_event(kvm, vcpu_record, &key, sample->time); - if (events_ops->is_end_event(evsel, sample, &key)) - return handle_end_event(vcpu_record, &key, sample->time); + if (kvm->events_ops->is_end_event(evsel, sample, &key)) + return handle_end_event(kvm, vcpu_record, &key, sample->time); return true; } -typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); -struct kvm_event_key { - const char *name; - key_cmp_fun key; -}; - -static int trace_vcpu = -1; #define GET_EVENT_KEY(func, field) \ static u64 get_event_ ##func(struct kvm_event *event, int vcpu) \ { \ @@ -515,29 +556,25 @@ static struct kvm_event_key keys[] = { { NULL, NULL } }; -static const char *sort_key = "sample"; -static key_cmp_fun compare; - -static bool select_key(void) +static bool select_key(struct perf_kvm *kvm) { int i; for (i = 0; keys[i].name; i++) { - if (!strcmp(keys[i].name, sort_key)) { - compare = keys[i].key; + if (!strcmp(keys[i].name, kvm->sort_key)) { + kvm->compare = keys[i].key; return true; } } - pr_err("Unknown compare key:%s\n", sort_key); + pr_err("Unknown compare key:%s\n", kvm->sort_key); return false; } -static struct rb_root result; -static void insert_to_result(struct kvm_event *event, key_cmp_fun bigger, - int vcpu) +static void insert_to_result(struct rb_root *result, struct kvm_event *event, + key_cmp_fun bigger, int vcpu) { - struct rb_node **rb = &result.rb_node; + struct rb_node **rb = &result->rb_node; struct rb_node *parent = NULL; struct kvm_event *p; @@ -552,13 +589,15 @@ static void insert_to_result(struct kvm_event *event, key_cmp_fun bigger, } rb_link_node(&event->rb, parent, rb); - rb_insert_color(&event->rb, &result); + rb_insert_color(&event->rb, result); } -static void update_total_count(struct kvm_event *event, int vcpu) +static void update_total_count(struct perf_kvm *kvm, struct kvm_event *event) { - total_count += get_event_count(event, vcpu); - total_time += get_event_time(event, vcpu); + int vcpu = kvm->trace_vcpu; + + kvm->total_count += get_event_count(event, vcpu); + kvm->total_time += get_event_time(event, vcpu); } static bool event_is_valid(struct kvm_event *event, int vcpu) @@ -566,28 +605,32 @@ static bool event_is_valid(struct kvm_event *event, int vcpu) return !!get_event_count(event, vcpu); } -static void sort_result(int vcpu) +static void sort_result(struct perf_kvm *kvm) { unsigned int i; + int vcpu = kvm->trace_vcpu; struct kvm_event *event; - for (i = 0; i < EVENTS_CACHE_SIZE; i++) - list_for_each_entry(event, &kvm_events_cache[i], hash_entry) + for (i = 0; i < EVENTS_CACHE_SIZE; i++) { + list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) { if (event_is_valid(event, vcpu)) { - update_total_count(event, vcpu); - insert_to_result(event, compare, vcpu); + update_total_count(kvm, event); + insert_to_result(&kvm->result, event, + kvm->compare, vcpu); } + } + } } /* returns left most element of result, and erase it */ -static struct kvm_event *pop_from_result(void) +static struct kvm_event *pop_from_result(struct rb_root *result) { - struct rb_node *node = rb_first(&result); + struct rb_node *node = rb_first(result); if (!node) return NULL; - rb_erase(node, &result); + rb_erase(node, result); return container_of(node, struct kvm_event, rb); } @@ -601,14 +644,15 @@ static void print_vcpu_info(int vcpu) pr_info("VCPU %d:\n\n", vcpu); } -static void print_result(int vcpu) +static void print_result(struct perf_kvm *kvm) { char decode[20]; struct kvm_event *event; + int vcpu = kvm->trace_vcpu; pr_info("\n\n"); print_vcpu_info(vcpu); - pr_info("%20s ", events_ops->name); + pr_info("%20s ", kvm->events_ops->name); pr_info("%10s ", "Samples"); pr_info("%9s ", "Samples%"); @@ -616,33 +660,34 @@ static void print_result(int vcpu) pr_info("%16s ", "Avg time"); pr_info("\n\n"); - while ((event = pop_from_result())) { + while ((event = pop_from_result(&kvm->result))) { u64 ecount, etime; ecount = get_event_count(event, vcpu); etime = get_event_time(event, vcpu); - events_ops->decode_key(&event->key, decode); + kvm->events_ops->decode_key(kvm, &event->key, decode); pr_info("%20s ", decode); pr_info("%10llu ", (unsigned long long)ecount); - pr_info("%8.2f%% ", (double)ecount / total_count * 100); - pr_info("%8.2f%% ", (double)etime / total_time * 100); + pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100); + pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100); pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3, kvm_event_rel_stddev(vcpu, event)); pr_info("\n"); } - pr_info("\nTotal Samples:%lld, Total events handled time:%.2fus.\n\n", - (unsigned long long)total_count, total_time / 1e3); + pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n", + kvm->total_count, kvm->total_time / 1e3); } -static int process_sample_event(struct perf_tool *tool __maybe_unused, +static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, sample->tid); + struct perf_kvm *kvm = container_of(tool, struct perf_kvm, tool); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", @@ -650,18 +695,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (!handle_kvm_event(thread, evsel, sample)) + if (!handle_kvm_event(kvm, thread, evsel, sample)) return -1; return 0; } -static struct perf_tool eops = { - .sample = process_sample_event, - .comm = perf_event__process_comm, - .ordered_samples = true, -}; - static int get_cpu_isa(struct perf_session *session) { char *cpuid = session->header.env.cpuid; @@ -679,34 +718,43 @@ static int get_cpu_isa(struct perf_session *session) return isa; } -static const char *file_name; - -static int read_events(void) +static int read_events(struct perf_kvm *kvm) { - struct perf_session *kvm_session; int ret; - kvm_session = perf_session__new(file_name, O_RDONLY, 0, false, &eops); - if (!kvm_session) { + struct perf_tool eops = { + .sample = process_sample_event, + .comm = perf_event__process_comm, + .ordered_samples = true, + }; + + kvm->tool = eops; + kvm->session = perf_session__new(kvm->file_name, O_RDONLY, 0, false, + &kvm->tool); + if (!kvm->session) { pr_err("Initializing perf session failed\n"); return -EINVAL; } - if (!perf_session__has_traces(kvm_session, "kvm record")) + if (!perf_session__has_traces(kvm->session, "kvm record")) return -EINVAL; /* * Do not use 'isa' recorded in kvm_exit tracepoint since it is not * traced in the old kernel. */ - ret = get_cpu_isa(kvm_session); + ret = get_cpu_isa(kvm->session); if (ret < 0) return ret; - cpu_isa = ret; + if (ret == 1) { + kvm->exit_reasons = vmx_exit_reasons; + kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons); + kvm->exit_reasons_isa = "VMX"; + } - return perf_session__process_events(kvm_session, &eops); + return perf_session__process_events(kvm->session, &kvm->tool); } static bool verify_vcpu(int vcpu) @@ -719,28 +767,30 @@ static bool verify_vcpu(int vcpu) return true; } -static int kvm_events_report_vcpu(int vcpu) +static int kvm_events_report_vcpu(struct perf_kvm *kvm) { int ret = -EINVAL; + int vcpu = kvm->trace_vcpu; if (!verify_vcpu(vcpu)) goto exit; - if (!select_key()) + if (!select_key(kvm)) goto exit; - if (!register_kvm_events_ops()) + if (!register_kvm_events_ops(kvm)) goto exit; - init_kvm_event_record(); + init_kvm_event_record(kvm); setup_pager(); - ret = read_events(); + ret = read_events(kvm); if (ret) goto exit; - sort_result(vcpu); - print_result(vcpu); + sort_result(kvm); + print_result(kvm); + exit: return ret; } @@ -765,7 +815,7 @@ static const char * const record_args[] = { _p; \ }) -static int kvm_events_record(int argc, const char **argv) +static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv) { unsigned int rec_argc, i, j; const char **rec_argv; @@ -780,7 +830,7 @@ static int kvm_events_record(int argc, const char **argv) rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]); rec_argv[i++] = STRDUP_FAIL_EXIT("-o"); - rec_argv[i++] = STRDUP_FAIL_EXIT(file_name); + rec_argv[i++] = STRDUP_FAIL_EXIT(kvm->file_name); for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; @@ -788,24 +838,24 @@ static int kvm_events_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -static const char * const kvm_events_report_usage[] = { - "perf kvm stat report [<options>]", - NULL -}; - -static const struct option kvm_events_report_options[] = { - OPT_STRING(0, "event", &report_event, "report event", - "event for reporting: vmexit, mmio, ioport"), - OPT_INTEGER(0, "vcpu", &trace_vcpu, - "vcpu id to report"), - OPT_STRING('k', "key", &sort_key, "sort-key", - "key for sorting: sample(sort by samples number)" - " time (sort by avg time)"), - OPT_END() -}; - -static int kvm_events_report(int argc, const char **argv) +static int kvm_events_report(struct perf_kvm *kvm, int argc, const char **argv) { + const struct option kvm_events_report_options[] = { + OPT_STRING(0, "event", &kvm->report_event, "report event", + "event for reporting: vmexit, mmio, ioport"), + OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu, + "vcpu id to report"), + OPT_STRING('k', "key", &kvm->sort_key, "sort-key", + "key for sorting: sample(sort by samples number)" + " time (sort by avg time)"), + OPT_END() + }; + + const char * const kvm_events_report_usage[] = { + "perf kvm stat report [<options>]", + NULL + }; + symbol__init(); if (argc) { @@ -817,7 +867,7 @@ static int kvm_events_report(int argc, const char **argv) kvm_events_report_options); } - return kvm_events_report_vcpu(trace_vcpu); + return kvm_events_report_vcpu(kvm); } static void print_kvm_stat_usage(void) @@ -831,7 +881,7 @@ static void print_kvm_stat_usage(void) printf("\nOtherwise, it is the alias of 'perf stat':\n"); } -static int kvm_cmd_stat(int argc, const char **argv) +static int kvm_cmd_stat(struct perf_kvm *kvm, int argc, const char **argv) { if (argc == 1) { print_kvm_stat_usage(); @@ -839,44 +889,16 @@ static int kvm_cmd_stat(int argc, const char **argv) } if (!strncmp(argv[1], "rec", 3)) - return kvm_events_record(argc - 1, argv + 1); + return kvm_events_record(kvm, argc - 1, argv + 1); if (!strncmp(argv[1], "rep", 3)) - return kvm_events_report(argc - 1 , argv + 1); + return kvm_events_report(kvm, argc - 1 , argv + 1); perf_stat: return cmd_stat(argc, argv, NULL); } -static char name_buffer[256]; - -static const char * const kvm_usage[] = { - "perf kvm [<options>] {top|record|report|diff|buildid-list|stat}", - NULL -}; - -static const struct option kvm_options[] = { - OPT_STRING('i', "input", &file_name, "file", - "Input file name"), - OPT_STRING('o', "output", &file_name, "file", - "Output file name"), - OPT_BOOLEAN(0, "guest", &perf_guest, - "Collect guest os data"), - OPT_BOOLEAN(0, "host", &perf_host, - "Collect host os data"), - OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory", - "guest mount directory under which every guest os" - " instance has a subdir"), - OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name, - "file", "file saving guest os vmlinux"), - OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms, - "file", "file saving guest os /proc/kallsyms"), - OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, - "file", "file saving guest os /proc/modules"), - OPT_END() -}; - -static int __cmd_record(int argc, const char **argv) +static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -885,7 +907,7 @@ static int __cmd_record(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(file_name); + rec_argv[i++] = strdup(kvm->file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -894,7 +916,7 @@ static int __cmd_record(int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -static int __cmd_report(int argc, const char **argv) +static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -903,7 +925,7 @@ static int __cmd_report(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(file_name); + rec_argv[i++] = strdup(kvm->file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -912,7 +934,7 @@ static int __cmd_report(int argc, const char **argv) return cmd_report(i, rec_argv, NULL); } -static int __cmd_buildid_list(int argc, const char **argv) +static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -921,7 +943,7 @@ static int __cmd_buildid_list(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(file_name); + rec_argv[i++] = strdup(kvm->file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -932,6 +954,43 @@ static int __cmd_buildid_list(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 struct option kvm_options[] = { + OPT_STRING('i', "input", &kvm.file_name, "file", + "Input file name"), + OPT_STRING('o', "output", &kvm.file_name, "file", + "Output file name"), + OPT_BOOLEAN(0, "guest", &perf_guest, + "Collect guest os data"), + OPT_BOOLEAN(0, "host", &perf_host, + "Collect host os data"), + OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory", + "guest mount directory under which every guest os" + " instance has a subdir"), + OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name, + "file", "file saving guest os vmlinux"), + OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms, + "file", "file saving guest os /proc/kallsyms"), + OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, + "file", "file saving guest os /proc/modules"), + OPT_END() + }; + + + const char * const kvm_usage[] = { + "perf kvm [<options>] {top|record|report|diff|buildid-list|stat}", + NULL + }; + perf_host = 0; perf_guest = 1; @@ -943,28 +1002,32 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) if (!perf_host) perf_guest = 1; - if (!file_name) { + if (!kvm.file_name) { if (perf_host && !perf_guest) - sprintf(name_buffer, "perf.data.host"); + kvm.file_name = strdup("perf.data.host"); else if (!perf_host && perf_guest) - sprintf(name_buffer, "perf.data.guest"); + kvm.file_name = strdup("perf.data.guest"); else - sprintf(name_buffer, "perf.data.kvm"); - file_name = name_buffer; + kvm.file_name = strdup("perf.data.kvm"); + + if (!kvm.file_name) { + pr_err("Failed to allocate memory for filename\n"); + return -ENOMEM; + } } if (!strncmp(argv[0], "rec", 3)) - return __cmd_record(argc, argv); + return __cmd_record(&kvm, argc, argv); else if (!strncmp(argv[0], "rep", 3)) - return __cmd_report(argc, argv); + return __cmd_report(&kvm, 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(argc, argv); + return __cmd_buildid_list(&kvm, argc, argv); else if (!strncmp(argv[0], "stat", 4)) - return kvm_cmd_stat(argc, argv); + return kvm_cmd_stat(&kvm, argc, argv); else usage_with_options(kvm_usage, kvm_options); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 7d6e09949880..6f5f328157aa 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -823,12 +823,6 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, return 0; } -static struct perf_tool eops = { - .sample = process_sample_event, - .comm = perf_event__process_comm, - .ordered_samples = true, -}; - static const struct perf_evsel_str_handler lock_tracepoints[] = { { "lock:lock_acquire", perf_evsel__process_lock_acquire, }, /* CONFIG_LOCKDEP */ { "lock:lock_acquired", perf_evsel__process_lock_acquired, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */ @@ -838,6 +832,11 @@ static const struct perf_evsel_str_handler lock_tracepoints[] = { static int read_events(void) { + struct perf_tool eops = { + .sample = process_sample_event, + .comm = perf_event__process_comm, + .ordered_samples = true, + }; session = perf_session__new(input_name, O_RDONLY, 0, false, &eops); if (!session) { pr_err("Initializing perf session failed\n"); @@ -878,53 +877,11 @@ static int __cmd_report(void) return 0; } -static const char * const report_usage[] = { - "perf lock report [<options>]", - NULL -}; - -static const struct option report_options[] = { - OPT_STRING('k', "key", &sort_key, "acquired", - "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"), - /* TODO: type */ - OPT_END() -}; - -static const char * const info_usage[] = { - "perf lock info [<options>]", - NULL -}; - -static const struct option info_options[] = { - OPT_BOOLEAN('t', "threads", &info_threads, - "dump thread list in perf.data"), - OPT_BOOLEAN('m', "map", &info_map, - "map of lock instances (address:name table)"), - OPT_END() -}; - -static const char * const lock_usage[] = { - "perf lock [<options>] {record|report|script|info}", - NULL -}; - -static const struct option lock_options[] = { - OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), - OPT_END() -}; - -static const char *record_args[] = { - "record", - "-R", - "-f", - "-m", "1024", - "-c", "1", -}; - static int __cmd_record(int argc, const char **argv) { + const char *record_args[] = { + "record", "-R", "-f", "-m", "1024", "-c", "1", + }; unsigned int rec_argc, i, j; const char **rec_argv; @@ -963,6 +920,37 @@ static int __cmd_record(int argc, const char **argv) int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) { + const struct option info_options[] = { + OPT_BOOLEAN('t', "threads", &info_threads, + "dump thread list in perf.data"), + OPT_BOOLEAN('m', "map", &info_map, + "map of lock instances (address:name table)"), + OPT_END() + }; + const struct option lock_options[] = { + OPT_STRING('i', "input", &input_name, "file", "input file name"), + OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_END() + }; + const struct option report_options[] = { + OPT_STRING('k', "key", &sort_key, "acquired", + "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"), + /* TODO: type */ + OPT_END() + }; + const char * const info_usage[] = { + "perf lock info [<options>]", + NULL + }; + const char * const lock_usage[] = { + "perf lock [<options>] {record|report|script|info}", + NULL + }; + const char * const report_usage[] = { + "perf lock report [<options>]", + NULL + }; unsigned int i; int rc = 0; diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 118aa8946573..de38a034b129 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -250,19 +250,20 @@ static int opt_set_filter(const struct option *opt __maybe_unused, return 0; } -static const char * const probe_usage[] = { - "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]", - "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]", - "perf probe [<options>] --del '[GROUP:]EVENT' ...", - "perf probe --list", +int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) +{ + const char * const probe_usage[] = { + "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]", + "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]", + "perf probe [<options>] --del '[GROUP:]EVENT' ...", + "perf probe --list", #ifdef DWARF_SUPPORT - "perf probe [<options>] --line 'LINEDESC'", - "perf probe [<options>] --vars 'PROBEPOINT'", + "perf probe [<options>] --line 'LINEDESC'", + "perf probe [<options>] --vars 'PROBEPOINT'", #endif - NULL + NULL }; - -static const struct option options[] = { + const struct option options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show parsed arguments, etc)"), OPT_BOOLEAN('l', "list", ¶ms.list_events, @@ -325,10 +326,7 @@ static const struct option options[] = { OPT_CALLBACK('x', "exec", NULL, "executable|path", "target executable name or path", opt_set_target), OPT_END() -}; - -int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) -{ + }; int ret; argc = parse_options(argc, argv, options, probe_usage, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f14cb5fdb91f..73b5d7f91194 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -31,13 +31,36 @@ #include <sched.h> #include <sys/mman.h> -#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " +#ifndef HAVE_ON_EXIT +#ifndef ATEXIT_MAX +#define ATEXIT_MAX 32 +#endif +static int __on_exit_count = 0; +typedef void (*on_exit_func_t) (int, void *); +static on_exit_func_t __on_exit_funcs[ATEXIT_MAX]; +static void *__on_exit_args[ATEXIT_MAX]; +static int __exitcode = 0; +static void __handle_on_exit_funcs(void); +static int on_exit(on_exit_func_t function, void *arg); +#define exit(x) (exit)(__exitcode = (x)) + +static int on_exit(on_exit_func_t function, void *arg) +{ + if (__on_exit_count == ATEXIT_MAX) + return -ENOMEM; + else if (__on_exit_count == 0) + atexit(__handle_on_exit_funcs); + __on_exit_funcs[__on_exit_count] = function; + __on_exit_args[__on_exit_count++] = arg; + return 0; +} -#ifdef NO_LIBUNWIND_SUPPORT -static char callchain_help[] = CALLCHAIN_HELP "[fp]"; -#else -static unsigned long default_stack_dump_size = 8192; -static char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +static void __handle_on_exit_funcs(void) +{ + int i; + for (i = 0; i < __on_exit_count; i++) + __on_exit_funcs[i] (__exitcode, __on_exit_args[i]); +} #endif enum write_mode_t { @@ -800,7 +823,7 @@ error: return ret; } -#ifndef NO_LIBUNWIND_SUPPORT +#ifdef LIBUNWIND_SUPPORT static int get_stack_size(char *str, unsigned long *_size) { char *endptr; @@ -826,7 +849,7 @@ static int get_stack_size(char *str, unsigned long *_size) max_size, str); return -1; } -#endif /* !NO_LIBUNWIND_SUPPORT */ +#endif /* LIBUNWIND_SUPPORT */ static int parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, @@ -865,9 +888,11 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, "needed for -g fp\n"); break; -#ifndef NO_LIBUNWIND_SUPPORT +#ifdef LIBUNWIND_SUPPORT /* Dwarf style */ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + const unsigned long default_stack_dump_size = 8192; + ret = 0; rec->opts.call_graph = CALLCHAIN_DWARF; rec->opts.stack_dump_size = default_stack_dump_size; @@ -883,7 +908,7 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, if (!ret) pr_debug("callchain: stack dump size %d\n", rec->opts.stack_dump_size); -#endif /* !NO_LIBUNWIND_SUPPORT */ +#endif /* LIBUNWIND_SUPPORT */ } else { pr_err("callchain: Unknown -g option " "value: %s\n", arg); @@ -930,6 +955,14 @@ static struct perf_record record = { .file_new = true, }; +#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " + +#ifdef LIBUNWIND_SUPPORT +static const char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +#else +static const char callchain_help[] = CALLCHAIN_HELP "[fp]"; +#endif + /* * XXX Will stay a global variable till we fix builtin-script.c to stop messing * with it and switch to use the library functions in perf_evlist that came diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1da243dfbc3e..5104a40af563 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -320,7 +320,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, const char *evname = perf_evsel__name(pos); hists__fprintf_nr_sample_events(hists, evname, stdout); - hists__fprintf(hists, NULL, false, true, 0, 0, stdout); + hists__fprintf(hists, true, 0, 0, stdout); fprintf(stdout, "\n\n"); } @@ -556,8 +556,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .sample = process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .lost = perf_event__process_lost, .read = process_read_event, .attr = perf_event__process_attr, @@ -691,7 +691,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) setup_browser(true); else { use_browser = 0; - perf_hpp__init(false, false); + perf_hpp__init(); } setup_sorting(report_usage, options); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 9b9e32eaa805..30e53360d3c2 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1426,7 +1426,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_ struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->pid); + struct thread *thread = machine__findnew_thread(machine, sample->tid); int err = 0; if (thread == NULL) { @@ -1672,7 +1672,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, .lost = perf_event__process_lost, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .ordered_samples = true, }, .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 1be843aa1546..04ceb0779d39 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -24,7 +24,6 @@ static u64 last_timestamp; static u64 nr_unordered; extern const struct option record_options[]; static bool no_callchain; -static bool show_full_info; static bool system_wide; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -473,8 +472,6 @@ static int cleanup_scripting(void) return scripting_ops->stop_script(); } -static const char *input_name; - static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -523,8 +520,8 @@ static struct perf_tool perf_script = { .sample = process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .attr = perf_event__process_attr, .event_type = perf_event__process_event_type, .tracing_data = perf_event__process_tracing_data, @@ -1156,20 +1153,40 @@ out: return n_args; } -static const char * const script_usage[] = { - "perf script [<options>]", - "perf script [<options>] record <script> [<record-options>] <command>", - "perf script [<options>] report <script> [script-args]", - "perf script [<options>] <script> [<record-options>] <command>", - "perf script [<options>] <top-script> [script-args]", - NULL -}; +static int have_cmd(int argc, const char **argv) +{ + char **__argv = malloc(sizeof(const char *) * argc); + + if (!__argv) { + pr_err("malloc failed\n"); + return -1; + } + + memcpy(__argv, argv, sizeof(const char *) * argc); + argc = parse_options(argc, (const char **)__argv, record_options, + NULL, PARSE_OPT_STOP_AT_NON_OPTION); + free(__argv); -static const struct option options[] = { + system_wide = (argc == 0); + + return 0; +} + +int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) +{ + bool show_full_info = false; + const char *input_name = NULL; + char *rec_script_path = NULL; + char *rep_script_path = NULL; + struct perf_session *session; + char *script_path = NULL; + const char **__argv; + int i, j, err; + const struct option options[] = { OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_INCR('v', "verbose", &verbose, - "be more verbose (show symbol address, etc)"), + "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('L', "Latency", &latency_format, "show latency attributes (irqs/preemption disabled, etc)"), OPT_CALLBACK_NOOPT('l', "list", NULL, NULL, "list available scripts", @@ -1179,8 +1196,7 @@ static const struct option options[] = { parse_scriptname), OPT_STRING('g', "gen-script", &generate_script_lang, "lang", "generate perf-script.xx script in specified language"), - OPT_STRING('i', "input", &input_name, "file", - "input file name"), + OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_BOOLEAN('d', "debug-mode", &debug_mode, "do various checks like samples ordering and lost events"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, @@ -1195,10 +1211,9 @@ static const struct option options[] = { "comma separated output fields prepend with 'type:'. " "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff", - parse_output_fields), + "addr,symoff", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, - "system-wide collection from all CPUs"), + "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"), @@ -1208,37 +1223,16 @@ static const struct option options[] = { "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, "Show the path of [kernel.kallsyms]"), - OPT_END() -}; - -static int have_cmd(int argc, const char **argv) -{ - char **__argv = malloc(sizeof(const char *) * argc); - - if (!__argv) { - pr_err("malloc failed\n"); - return -1; - } - - memcpy(__argv, argv, sizeof(const char *) * argc); - argc = parse_options(argc, (const char **)__argv, record_options, - NULL, PARSE_OPT_STOP_AT_NON_OPTION); - free(__argv); - - system_wide = (argc == 0); - - return 0; -} - -int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) -{ - char *rec_script_path = NULL; - char *rep_script_path = NULL; - struct perf_session *session; - char *script_path = NULL; - const char **__argv; - int i, j, err; + }; + const char * const script_usage[] = { + "perf script [<options>]", + "perf script [<options>] record <script> [<record-options>] <command>", + "perf script [<options>] report <script> [script-args]", + "perf script [<options>] <script> [<record-options>] <command>", + "perf script [<options>] <top-script> [script-args]", + NULL + }; setup_scripting(); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index e8cd4d81b06e..93b9011fa3e2 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -64,122 +64,12 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" -static struct perf_event_attr default_attrs[] = { - - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, - { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, - - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, - -}; - -/* - * Detailed stats (-d), covering the L1 and last level data caches: - */ -static struct perf_event_attr detailed_attrs[] = { - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_L1D << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_L1D << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_LL << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_LL << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, -}; - -/* - * Very detailed stats (-d -d), covering the instruction cache and the TLB caches: - */ -static struct perf_event_attr very_detailed_attrs[] = { - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_L1I << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_L1I << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_DTLB << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_DTLB << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_ITLB << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_ITLB << 0 | - (PERF_COUNT_HW_CACHE_OP_READ << 8) | - (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, - -}; - -/* - * Very, very detailed stats (-d -d -d), adding prefetch events: - */ -static struct perf_event_attr very_very_detailed_attrs[] = { - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_L1D << 0 | - (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | - (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, - - { .type = PERF_TYPE_HW_CACHE, - .config = - PERF_COUNT_HW_CACHE_L1D << 0 | - (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | - (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, -}; - - - static struct perf_evlist *evsel_list; static struct perf_target target = { .uid = UINT_MAX, }; -static int run_idx = 0; static int run_count = 1; static bool no_inherit = false; static bool scale = true; @@ -187,15 +77,12 @@ static bool no_aggr = false; static pid_t child_pid = -1; static bool null_run = false; static int detailed_run = 0; -static bool sync_run = false; static bool big_num = true; static int big_num_opt = -1; static const char *csv_sep = NULL; static bool csv_output = false; static bool group = false; -static const char *output_name = NULL; static FILE *output = NULL; -static int output_fd; static volatile int done = 0; @@ -1028,11 +915,6 @@ static void sig_atexit(void) kill(getpid(), signr); } -static const char * const stat_usage[] = { - "perf stat [<options>] [<command>]", - NULL -}; - static int stat__set_big_num(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset) { @@ -1040,62 +922,119 @@ static int stat__set_big_num(const struct option *opt __maybe_unused, return 0; } -static bool append_file; - -static const struct option options[] = { - OPT_CALLBACK('e', "event", &evsel_list, "event", - "event selector. use 'perf list' to list available events", - parse_events_option), - OPT_CALLBACK(0, "filter", &evsel_list, "filter", - "event filter", parse_filter), - OPT_BOOLEAN('i', "no-inherit", &no_inherit, - "child tasks do not inherit counters"), - OPT_STRING('p', "pid", &target.pid, "pid", - "stat events on existing process id"), - OPT_STRING('t', "tid", &target.tid, "tid", - "stat events on existing thread id"), - OPT_BOOLEAN('a', "all-cpus", &target.system_wide, - "system-wide collection from all CPUs"), - OPT_BOOLEAN('g', "group", &group, - "put the counters into a counter group"), - OPT_BOOLEAN('c', "scale", &scale, - "scale/normalize counters"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show counter open errors, etc)"), - OPT_INTEGER('r', "repeat", &run_count, - "repeat command and print average + stddev (max: 100)"), - OPT_BOOLEAN('n', "null", &null_run, - "null run - dont start any counters"), - OPT_INCR('d', "detailed", &detailed_run, - "detailed run - start a lot of events"), - OPT_BOOLEAN('S', "sync", &sync_run, - "call sync() before starting a run"), - OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, - "print large numbers with thousands\' separators", - stat__set_big_num), - OPT_STRING('C', "cpu", &target.cpu_list, "cpu", - "list of cpus to monitor in system-wide"), - OPT_BOOLEAN('A', "no-aggr", &no_aggr, - "disable CPU count aggregation"), - OPT_STRING('x', "field-separator", &csv_sep, "separator", - "print counts with custom separator"), - OPT_CALLBACK('G', "cgroup", &evsel_list, "name", - "monitor event in cgroup name only", - parse_cgroups), - OPT_STRING('o', "output", &output_name, "file", - "output file name"), - OPT_BOOLEAN(0, "append", &append_file, "append to the output file"), - OPT_INTEGER(0, "log-fd", &output_fd, - "log output to fd, instead of stderr"), - OPT_END() -}; - /* * Add default attributes, if there were no attributes specified or * if -d/--detailed, -d -d or -d -d -d is used: */ static int add_default_attributes(void) { + struct perf_event_attr default_attrs[] = { + + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS }, + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS }, + + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES }, + +}; + +/* + * Detailed stats (-d), covering the L1 and last level data caches: + */ + struct perf_event_attr detailed_attrs[] = { + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_LL << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_LL << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, +}; + +/* + * Very detailed stats (-d -d), covering the instruction cache and the TLB caches: + */ + struct perf_event_attr very_detailed_attrs[] = { + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1I << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1I << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_DTLB << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_DTLB << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_ITLB << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_ITLB << 0 | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, + +}; + +/* + * Very, very detailed stats (-d -d -d), adding prefetch events: + */ + struct perf_event_attr very_very_detailed_attrs[] = { + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D << 0 | + (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) }, + + { .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D << 0 | + (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, +}; + /* Set attrs if no event is selected and !null_run: */ if (null_run) return 0; @@ -1130,8 +1069,59 @@ static int add_default_attributes(void) int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) { + bool append_file = false, + sync_run = false; + int output_fd = 0; + const char *output_name = NULL; + const struct option options[] = { + OPT_CALLBACK('e', "event", &evsel_list, "event", + "event selector. use 'perf list' to list available events", + parse_events_option), + OPT_CALLBACK(0, "filter", &evsel_list, "filter", + "event filter", parse_filter), + OPT_BOOLEAN('i', "no-inherit", &no_inherit, + "child tasks do not inherit counters"), + OPT_STRING('p', "pid", &target.pid, "pid", + "stat events on existing process id"), + OPT_STRING('t', "tid", &target.tid, "tid", + "stat events on existing thread id"), + OPT_BOOLEAN('a', "all-cpus", &target.system_wide, + "system-wide collection from all CPUs"), + OPT_BOOLEAN('g', "group", &group, + "put the counters into a counter group"), + OPT_BOOLEAN('c', "scale", &scale, "scale/normalize counters"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_INTEGER('r', "repeat", &run_count, + "repeat command and print average + stddev (max: 100)"), + OPT_BOOLEAN('n', "null", &null_run, + "null run - dont start any counters"), + OPT_INCR('d', "detailed", &detailed_run, + "detailed run - start a lot of events"), + OPT_BOOLEAN('S', "sync", &sync_run, + "call sync() before starting a run"), + OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, + "print large numbers with thousands\' separators", + stat__set_big_num), + OPT_STRING('C', "cpu", &target.cpu_list, "cpu", + "list of cpus to monitor in system-wide"), + OPT_BOOLEAN('A', "no-aggr", &no_aggr, "disable CPU count aggregation"), + OPT_STRING('x', "field-separator", &csv_sep, "separator", + "print counts with custom separator"), + OPT_CALLBACK('G', "cgroup", &evsel_list, "name", + "monitor event in cgroup name only", parse_cgroups), + OPT_STRING('o', "output", &output_name, "file", "output file name"), + OPT_BOOLEAN(0, "append", &append_file, "append to the output file"), + OPT_INTEGER(0, "log-fd", &output_fd, + "log output to fd, instead of stderr"), + OPT_END() + }; + const char * const stat_usage[] = { + "perf stat [<options>] [<command>]", + NULL + }; struct perf_evsel *pos; - int status = -ENOMEM; + int status = -ENOMEM, run_idx; const char *mode; setlocale(LC_ALL, ""); diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 484f26cc0c00..e2d9872de3d7 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -35,7 +35,6 @@ static int test__vmlinux_matches_kallsyms(void) struct map *kallsyms_map, *vmlinux_map; struct machine kallsyms, vmlinux; enum map_type type = MAP__FUNCTION; - long page_size = sysconf(_SC_PAGE_SIZE); struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", }; /* @@ -1007,7 +1006,6 @@ static void segfault_handler(int sig __maybe_unused, static int __test__rdpmc(void) { - long page_size = sysconf(_SC_PAGE_SIZE); volatile int tmp = 0; u64 i, loops = 1000; int n; diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index b1a8a3b841cc..f251b613b2f3 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -38,9 +38,6 @@ #define PWR_EVENT_EXIT -1 -static const char *input_name; -static const char *output_name = "output.svg"; - static unsigned int numcpus; static u64 min_freq; /* Lowest CPU frequency seen */ static u64 max_freq; /* Highest CPU frequency seen */ @@ -968,16 +965,15 @@ static void write_svg_file(const char *filename) svg_close(); } -static struct perf_tool perf_timechart = { - .comm = process_comm_event, - .fork = process_fork_event, - .exit = process_exit_event, - .sample = process_sample_event, - .ordered_samples = true, -}; - -static int __cmd_timechart(void) +static int __cmd_timechart(const char *input_name, const char *output_name) { + struct perf_tool perf_timechart = { + .comm = process_comm_event, + .fork = process_fork_event, + .exit = process_exit_event, + .sample = process_sample_event, + .ordered_samples = true, + }; struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_timechart); int ret = -EINVAL; @@ -1005,40 +1001,25 @@ out_delete: return ret; } -static const char * const timechart_usage[] = { - "perf timechart [<options>] {record}", - NULL -}; - -#ifdef SUPPORT_OLD_POWER_EVENTS -static const char * const record_old_args[] = { - "record", - "-a", - "-R", - "-f", - "-c", "1", - "-e", "power:power_start", - "-e", "power:power_end", - "-e", "power:power_frequency", - "-e", "sched:sched_wakeup", - "-e", "sched:sched_switch", -}; -#endif - -static const char * const record_new_args[] = { - "record", - "-a", - "-R", - "-f", - "-c", "1", - "-e", "power:cpu_frequency", - "-e", "power:cpu_idle", - "-e", "sched:sched_wakeup", - "-e", "sched:sched_switch", -}; - static int __cmd_record(int argc, const char **argv) { +#ifdef SUPPORT_OLD_POWER_EVENTS + const char * const record_old_args[] = { + "record", "-a", "-R", "-f", "-c", "1", + "-e", "power:power_start", + "-e", "power:power_end", + "-e", "power:power_frequency", + "-e", "sched:sched_wakeup", + "-e", "sched:sched_switch", + }; +#endif + const char * const record_new_args[] = { + "record", "-a", "-R", "-f", "-c", "1", + "-e", "power:cpu_frequency", + "-e", "power:cpu_idle", + "-e", "sched:sched_wakeup", + "-e", "sched:sched_switch", + }; unsigned int rec_argc, i, j; const char **rec_argv; const char * const *record_args = record_new_args; @@ -1077,27 +1058,28 @@ parse_process(const struct option *opt __maybe_unused, const char *arg, return 0; } -static const struct option options[] = { - OPT_STRING('i', "input", &input_name, "file", - "input file name"), - OPT_STRING('o', "output", &output_name, "file", - "output file name"), - OPT_INTEGER('w', "width", &svg_page_width, - "page width"), - OPT_BOOLEAN('P', "power-only", &power_only, - "output power data only"), +int cmd_timechart(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + const char *input_name; + const char *output_name = "output.svg"; + const struct option options[] = { + OPT_STRING('i', "input", &input_name, "file", "input file name"), + OPT_STRING('o', "output", &output_name, "file", "output file name"), + OPT_INTEGER('w', "width", &svg_page_width, "page width"), + OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"), OPT_CALLBACK('p', "process", NULL, "process", "process selector. Pass a pid or process name.", parse_process), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), OPT_END() -}; - + }; + const char * const timechart_usage[] = { + "perf timechart [<options>] {record}", + NULL + }; -int cmd_timechart(int argc, const char **argv, - const char *prefix __maybe_unused) -{ argc = parse_options(argc, argv, options, timechart_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -1110,5 +1092,5 @@ int cmd_timechart(int argc, const char **argv, setup_pager(); - return __cmd_timechart(); + return __cmd_timechart(input_name, output_name); } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index e434a16bb5ac..fb9da71eba1f 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -26,6 +26,7 @@ #include "util/color.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/machine.h" #include "util/session.h" #include "util/symbol.h" #include "util/thread.h" @@ -316,7 +317,7 @@ static void perf_top__print_sym_table(struct perf_top *top) hists__output_recalc_col_len(&top->sym_evsel->hists, top->winsize.ws_row - 3); putchar('\n'); - hists__fprintf(&top->sym_evsel->hists, NULL, false, false, + hists__fprintf(&top->sym_evsel->hists, false, top->winsize.ws_row - 4 - printed, win_width, stdout); } @@ -871,7 +872,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) &sample, machine); } else if (event->header.type < PERF_RECORD_MAX) { hists__inc_nr_events(&evsel->hists, event->header.type); - perf_event__process(&top->tool, event, &sample, machine); + machine__process_event(machine, event); } else ++session->hists.stats.nr_unknown_events; } @@ -1159,11 +1160,6 @@ setup: return 0; } -static const char * const top_usage[] = { - "perf top [<options>]", - NULL -}; - int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_evsel *pos; @@ -1250,6 +1246,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_STRING('u', "uid", &top.target.uid_str, "user", "user to profile"), OPT_END() }; + const char * const top_usage[] = { + "perf top [<options>]", + NULL + }; top.evlist = perf_evlist__new(NULL, NULL); if (top.evlist == NULL) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 8f113dab8bf1..4e9320bf11e1 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -52,6 +52,13 @@ struct trace { struct perf_record_opts opts; }; +static bool done = false; + +static void sig_handler(int sig __maybe_unused) +{ + done = true; +} + static int trace__read_syscall_info(struct trace *trace, int id) { char tp_name[128]; @@ -114,33 +121,99 @@ static size_t syscall__fprintf_args(struct syscall *sc, unsigned long *args, FIL return printed; } -static int trace__run(struct trace *trace) +typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample); + +static struct syscall *trace__syscall_info(struct trace *trace, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + int id = perf_evsel__intval(evsel, sample, "id"); + + if (id < 0) { + printf("Invalid syscall %d id, skipping...\n", id); + return NULL; + } + + if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) && + trace__read_syscall_info(trace, id)) + goto out_cant_read; + + if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL)) + goto out_cant_read; + + return &trace->syscalls.table[id]; + +out_cant_read: + printf("Problems reading syscall %d information\n", id); + return NULL; +} + +static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample) +{ + void *args; + struct syscall *sc = trace__syscall_info(trace, evsel, sample); + + if (sc == NULL) + return -1; + + args = perf_evsel__rawptr(evsel, sample, "args"); + if (args == NULL) { + printf("Problems reading syscall arguments\n"); + return -1; + } + + printf("%s(", sc->name); + syscall__fprintf_args(sc, args, stdout); + + return 0; +} + +static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample) +{ + int ret; + struct syscall *sc = trace__syscall_info(trace, evsel, sample); + + if (sc == NULL) + return -1; + + ret = perf_evsel__intval(evsel, sample, "ret"); + + if (ret < 0 && sc->fmt && sc->fmt->errmsg) { + char bf[256]; + const char *emsg = strerror_r(-ret, bf, sizeof(bf)), + *e = audit_errno_to_name(-ret); + + printf(") = -1 %s %s", e, emsg); + } else if (ret == 0 && sc->fmt && sc->fmt->timeout) + printf(") = 0 Timeout"); + else + printf(") = %d", ret); + + putchar('\n'); + return 0; +} + +static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); - struct perf_evsel *evsel, *evsel_enter, *evsel_exit; + struct perf_evsel *evsel; int err = -1, i, nr_events = 0, before; + const bool forks = argc > 0; if (evlist == NULL) { printf("Not enough memory to run!\n"); goto out; } - evsel_enter = perf_evsel__newtp("raw_syscalls", "sys_enter", 0); - if (evsel_enter == NULL) { - printf("Couldn't read the raw_syscalls:sys_enter tracepoint information!\n"); + if (perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_enter", trace__sys_enter) || + perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit)) { + printf("Couldn't read the raw_syscalls tracepoints information!\n"); goto out_delete_evlist; } - perf_evlist__add(evlist, evsel_enter); - - evsel_exit = perf_evsel__newtp("raw_syscalls", "sys_exit", 1); - if (evsel_exit == NULL) { - printf("Couldn't read the raw_syscalls:sys_exit tracepoint information!\n"); - goto out_delete_evlist; - } - - perf_evlist__add(evlist, evsel_exit); - err = perf_evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { printf("Problems parsing the target to trace, check your options!\n"); @@ -149,6 +222,17 @@ static int trace__run(struct trace *trace) perf_evlist__config_attrs(evlist, &trace->opts); + signal(SIGCHLD, sig_handler); + signal(SIGINT, sig_handler); + + if (forks) { + err = perf_evlist__prepare_workload(evlist, &trace->opts, argv); + if (err < 0) { + printf("Couldn't run the workload!\n"); + goto out_delete_evlist; + } + } + err = perf_evlist__open(evlist); if (err < 0) { printf("Couldn't create the events: %s\n", strerror(errno)); @@ -162,6 +246,10 @@ static int trace__run(struct trace *trace) } perf_evlist__enable(evlist); + + if (forks) + perf_evlist__start_workload(evlist); + again: before = nr_events; @@ -170,9 +258,8 @@ again: while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { const u32 type = event->header.type; - struct syscall *sc; + tracepoint_handler handler; struct perf_sample sample; - int id; ++nr_events; @@ -200,50 +287,23 @@ again: continue; } - id = perf_evsel__intval(evsel, &sample, "id"); - if (id < 0) { - printf("Invalid syscall %d id, skipping...\n", id); - continue; - } - - if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) && - trace__read_syscall_info(trace, id)) - continue; - - if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL)) - continue; - - sc = &trace->syscalls.table[id]; - if (evlist->threads->map[0] == -1 || evlist->threads->nr > 1) printf("%d ", sample.tid); - if (evsel == evsel_enter) { - void *args = perf_evsel__rawptr(evsel, &sample, "args"); - - printf("%s(", sc->name); - syscall__fprintf_args(sc, args, stdout); - } else if (evsel == evsel_exit) { - int ret = perf_evsel__intval(evsel, &sample, "ret"); - - if (ret < 0 && sc->fmt && sc->fmt->errmsg) { - char bf[256]; - const char *emsg = strerror_r(-ret, bf, sizeof(bf)), - *e = audit_errno_to_name(-ret); - - printf(") = -1 %s %s", e, emsg); - } else if (ret == 0 && sc->fmt && sc->fmt->timeout) - printf(") = 0 Timeout"); - else - printf(") = %d", ret); - - putchar('\n'); - } + handler = evsel->handler.func; + handler(trace, evsel, &sample); } } - if (nr_events == before) + if (nr_events == before) { + if (done) + goto out_delete_evlist; + poll(evlist->pollfd, evlist->nr_fds, -1); + } + + if (done) + perf_evlist__disable(evlist); goto again; @@ -256,7 +316,8 @@ out: int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const trace_usage[] = { - "perf trace [<options>]", + "perf trace [<options>] [<command>]", + "perf trace [<options>] -- <command> [<options>]", NULL }; struct trace trace = { @@ -293,18 +354,26 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) OPT_END() }; int err; + char bf[BUFSIZ]; argc = parse_options(argc, argv, trace_options, trace_usage, 0); - if (argc) - usage_with_options(trace_usage, trace_options); + + err = perf_target__validate(&trace.opts.target); + if (err) { + perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf)); + printf("%s", bf); + return err; + } err = perf_target__parse_uid(&trace.opts.target); if (err) { - char bf[BUFSIZ]; perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf)); printf("%s", bf); return err; } - return trace__run(&trace); + if (!argc && perf_target__none(&trace.opts.target)) + trace.opts.target.system_wide = true; + + return trace__run(&trace, argc, argv); } diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index 4add41bb0c7e..3ef5ec9cdff8 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -43,6 +43,15 @@ int main(void) } endef +define SOURCE_BIONIC +#include <android/api-level.h> + +int main(void) +{ + return __ANDROID_API__; +} +endef + define SOURCE_ELF_MMAP #include <libelf.h> int main(void) @@ -203,4 +212,13 @@ int main(void) return audit_open(); } endef -endif
\ No newline at end of file +endif + +define SOURCE_ON_EXIT +#include <stdio.h> + +int main(void) +{ + return on_exit(NULL, NULL); +} +endef diff --git a/tools/perf/perf.c b/tools/perf/perf.c index fc2f770e3027..d480d8a412b8 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -48,14 +48,14 @@ static struct cmd_struct commands[] = { { "version", cmd_version, 0 }, { "script", cmd_script, 0 }, { "sched", cmd_sched, 0 }, -#ifndef NO_LIBELF_SUPPORT +#ifdef LIBELF_SUPPORT { "probe", cmd_probe, 0 }, #endif { "kmem", cmd_kmem, 0 }, { "lock", cmd_lock, 0 }, { "kvm", cmd_kvm, 0 }, { "test", cmd_test, 0 }, -#ifndef NO_LIBAUDIT_SUPPORT +#ifdef LIBAUDIT_SUPPORT { "trace", cmd_trace, 0 }, #endif { "inject", cmd_inject, 0 }, @@ -440,6 +440,8 @@ int main(int argc, const char **argv) { const char *cmd; + page_size = sysconf(_SC_PAGE_SIZE); + cmd = perf_extract_argv0_path(argv[0]); if (!cmd) cmd = "perf-help"; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index a21f40bebbac..0568536ecf67 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -569,7 +569,8 @@ static int hist_browser__show_callchain(struct hist_browser *browser, static int hist_browser__hpp_color_ ## _name(struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - double percent = 100.0 * he->_field / hpp->total_period; \ + struct hists *hists = he->hists; \ + double percent = 100.0 * he->stat._field / hists->stats.total_period; \ *(double *)hpp->ptr = percent; \ return scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); \ } @@ -584,7 +585,7 @@ HPP__COLOR_FN(overhead_guest_us, period_guest_us) void hist_browser__init_hpp(void) { - perf_hpp__init(false, false); + perf_hpp__init(); perf_hpp__format[PERF_HPP__OVERHEAD].color = hist_browser__hpp_color_overhead; @@ -624,7 +625,6 @@ static int hist_browser__show_entry(struct hist_browser *browser, struct perf_hpp hpp = { .buf = s, .size = sizeof(s), - .total_period = browser->hists->stats.total_period, }; ui_browser__gotorc(&browser->b, row, 0); @@ -982,7 +982,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, folded_sign = hist_entry__folded(he); hist_entry__sort_snprintf(he, s, sizeof(s), browser->hists); - percent = (he->period * 100.0) / browser->hists->stats.total_period; + percent = (he->stat.period * 100.0) / browser->hists->stats.total_period; if (symbol_conf.use_callchain) printed += fprintf(fp, "%c ", folded_sign); @@ -990,10 +990,10 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, printed += fprintf(fp, " %5.2f%%", percent); if (symbol_conf.show_nr_samples) - printed += fprintf(fp, " %11u", he->nr_events); + printed += fprintf(fp, " %11u", he->stat.nr_events); if (symbol_conf.show_total_period) - printed += fprintf(fp, " %12" PRIu64, he->period); + printed += fprintf(fp, " %12" PRIu64, he->stat.period); printed += fprintf(fp, "%s\n", rtrim(s)); diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index 7ff99ec1d95e..4125c6284114 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -49,7 +49,8 @@ static const char *perf_gtk__get_percent_color(double percent) static int perf_gtk__hpp_color_ ## _name(struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - double percent = 100.0 * he->_field / hpp->total_period; \ + struct hists *hists = he->hists; \ + double percent = 100.0 * he->stat._field / hists->stats.total_period; \ const char *markup; \ int ret = 0; \ \ @@ -73,7 +74,7 @@ HPP__COLOR_FN(overhead_guest_us, period_guest_us) void perf_gtk__init_hpp(void) { - perf_hpp__init(false, false); + perf_hpp__init(); perf_hpp__format[PERF_HPP__OVERHEAD].color = perf_gtk__hpp_color_overhead; @@ -102,7 +103,6 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) struct perf_hpp hpp = { .buf = s, .size = sizeof(s), - .total_period = hists->stats.total_period, }; nr_cols = 0; diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c index 8aada5b3c04c..ccb046aac98b 100644 --- a/tools/perf/ui/gtk/util.c +++ b/tools/perf/ui/gtk/util.c @@ -116,7 +116,7 @@ struct perf_error_ops perf_gtk_eops = { * FIXME: Functions below should be implemented properly. * For now, just add stubs for NO_NEWT=1 build. */ -#ifdef NO_NEWT_SUPPORT +#ifndef NEWT_SUPPORT void ui_progress__update(u64 curr __maybe_unused, u64 total __maybe_unused, const char *title __maybe_unused) { diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h index 2b667ee454c3..baa28a4d16b9 100644 --- a/tools/perf/ui/helpline.h +++ b/tools/perf/ui/helpline.h @@ -23,25 +23,25 @@ void ui_helpline__puts(const char *msg); extern char ui_helpline__current[512]; -#ifdef NO_NEWT_SUPPORT +#ifdef NEWT_SUPPORT +extern char ui_helpline__last_msg[]; +int ui_helpline__show_help(const char *format, va_list ap); +#else static inline int ui_helpline__show_help(const char *format __maybe_unused, va_list ap __maybe_unused) { return 0; } -#else -extern char ui_helpline__last_msg[]; -int ui_helpline__show_help(const char *format, va_list ap); -#endif /* NO_NEWT_SUPPORT */ +#endif /* NEWT_SUPPORT */ -#ifdef NO_GTK2_SUPPORT +#ifdef GTK2_SUPPORT +int perf_gtk__show_helpline(const char *format, va_list ap); +#else static inline int perf_gtk__show_helpline(const char *format __maybe_unused, va_list ap __maybe_unused) { return 0; } -#else -int perf_gtk__show_helpline(const char *format, va_list ap); -#endif /* NO_GTK2_SUPPORT */ +#endif /* GTK2_SUPPORT */ #endif /* _PERF_UI_HELPLINE_H_ */ diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index e3f8cd46e7d7..4f5f4756faac 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -8,9 +8,7 @@ /* hist period print (hpp) functions */ static int hpp__header_overhead(struct perf_hpp *hpp) { - const char *fmt = hpp->ptr ? "Baseline" : "Overhead"; - - return scnprintf(hpp->buf, hpp->size, fmt); + return scnprintf(hpp->buf, hpp->size, "Overhead"); } static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused) @@ -20,38 +18,18 @@ static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused) static int hpp__color_overhead(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period / hpp->total_period; - - if (hpp->ptr) { - struct hists *old_hists = hpp->ptr; - u64 total_period = old_hists->stats.total_period; - u64 base_period = he->pair ? he->pair->period : 0; - - if (total_period) - percent = 100.0 * base_period / total_period; - else - percent = 0.0; - } + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period / hists->stats.total_period; return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); } static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period / hists->stats.total_period; const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%"; - if (hpp->ptr) { - struct hists *old_hists = hpp->ptr; - u64 total_period = old_hists->stats.total_period; - u64 base_period = he->pair ? he->pair->period : 0; - - if (total_period) - percent = 100.0 * base_period / total_period; - else - percent = 0.0; - } - return scnprintf(hpp->buf, hpp->size, fmt, percent); } @@ -69,13 +47,16 @@ static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused) static int hpp__color_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_sys / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_sys / hists->stats.total_period; + return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); } static int hpp__entry_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_sys / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_sys / hists->stats.total_period; const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; return scnprintf(hpp->buf, hpp->size, fmt, percent); @@ -95,13 +76,16 @@ static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused) static int hpp__color_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_us / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_us / hists->stats.total_period; + return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); } static int hpp__entry_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_us / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_us / hists->stats.total_period; const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; return scnprintf(hpp->buf, hpp->size, fmt, percent); @@ -120,14 +104,17 @@ static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __maybe_unused) static int hpp__color_overhead_guest_sys(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_guest_sys / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period; + return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); } static int hpp__entry_overhead_guest_sys(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_guest_sys / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period; const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; return scnprintf(hpp->buf, hpp->size, fmt, percent); @@ -146,19 +133,69 @@ static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __maybe_unused) static int hpp__color_overhead_guest_us(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_guest_us / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period; + return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); } static int hpp__entry_overhead_guest_us(struct perf_hpp *hpp, struct hist_entry *he) { - double percent = 100.0 * he->period_guest_us / hpp->total_period; + struct hists *hists = he->hists; + double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period; const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; return scnprintf(hpp->buf, hpp->size, fmt, percent); } +static int hpp__header_baseline(struct perf_hpp *hpp) +{ + return scnprintf(hpp->buf, hpp->size, "Baseline"); +} + +static int hpp__width_baseline(struct perf_hpp *hpp __maybe_unused) +{ + return 8; +} + +static double baseline_percent(struct hist_entry *he) +{ + struct hist_entry *pair = he->pair; + struct hists *pair_hists = pair ? pair->hists : NULL; + double percent = 0.0; + + if (pair) { + u64 total_period = pair_hists->stats.total_period; + u64 base_period = pair->stat.period; + + percent = 100.0 * base_period / total_period; + } + + return percent; +} + +static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = baseline_percent(he); + + if (he->pair) + return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); + else + return scnprintf(hpp->buf, hpp->size, " "); +} + +static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he) +{ + double percent = baseline_percent(he); + const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%"; + + if (he->pair || symbol_conf.field_sep) + return scnprintf(hpp->buf, hpp->size, fmt, percent); + else + return scnprintf(hpp->buf, hpp->size, " "); +} + static int hpp__header_samples(struct perf_hpp *hpp) { const char *fmt = symbol_conf.field_sep ? "%s" : "%11s"; @@ -175,7 +212,7 @@ static int hpp__entry_samples(struct perf_hpp *hpp, struct hist_entry *he) { const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%11" PRIu64; - return scnprintf(hpp->buf, hpp->size, fmt, he->nr_events); + return scnprintf(hpp->buf, hpp->size, fmt, he->stat.nr_events); } static int hpp__header_period(struct perf_hpp *hpp) @@ -194,9 +231,29 @@ static int hpp__entry_period(struct perf_hpp *hpp, struct hist_entry *he) { const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64; - return scnprintf(hpp->buf, hpp->size, fmt, he->period); + return scnprintf(hpp->buf, hpp->size, fmt, he->stat.period); +} + +static int hpp__header_period_baseline(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%12s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Period Base"); +} + +static int hpp__width_period_baseline(struct perf_hpp *hpp __maybe_unused) +{ + return 12; } +static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *he) +{ + struct hist_entry *pair = he->pair; + u64 period = pair ? pair->stat.period : 0; + const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64; + + return scnprintf(hpp->buf, hpp->size, fmt, period); +} static int hpp__header_delta(struct perf_hpp *hpp) { const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; @@ -211,28 +268,79 @@ static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused) static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he) { - struct hists *pair_hists = hpp->ptr; - u64 old_total, new_total; - double old_percent = 0, new_percent = 0; - double diff; const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s"; char buf[32] = " "; + double diff; - old_total = pair_hists->stats.total_period; - if (old_total > 0 && he->pair) - old_percent = 100.0 * he->pair->period / old_total; - - new_total = hpp->total_period; - if (new_total > 0) - new_percent = 100.0 * he->period / new_total; + if (he->diff.computed) + diff = he->diff.period_ratio_delta; + else + diff = perf_diff__compute_delta(he); - diff = new_percent - old_percent; if (fabs(diff) >= 0.01) scnprintf(buf, sizeof(buf), "%+4.2F%%", diff); return scnprintf(hpp->buf, hpp->size, fmt, buf); } +static int hpp__header_ratio(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Ratio"); +} + +static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused) +{ + return 14; +} + +static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; + char buf[32] = " "; + double ratio; + + if (he->diff.computed) + ratio = he->diff.period_ratio; + else + ratio = perf_diff__compute_ratio(he); + + if (ratio > 0.0) + scnprintf(buf, sizeof(buf), "%+14.6F", ratio); + + return scnprintf(hpp->buf, hpp->size, fmt, buf); +} + +static int hpp__header_wdiff(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Weighted diff"); +} + +static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused) +{ + return 14; +} + +static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; + char buf[32] = " "; + s64 wdiff; + + if (he->diff.computed) + wdiff = he->diff.wdiff; + else + wdiff = perf_diff__compute_wdiff(he); + + if (wdiff != 0) + scnprintf(buf, sizeof(buf), "%14ld", wdiff); + + return scnprintf(hpp->buf, hpp->size, fmt, buf); +} + static int hpp__header_displ(struct perf_hpp *hpp) { return scnprintf(hpp->buf, hpp->size, "Displ."); @@ -244,14 +352,37 @@ static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused) } static int hpp__entry_displ(struct perf_hpp *hpp, - struct hist_entry *he __maybe_unused) + struct hist_entry *he) { + struct hist_entry *pair = he->pair; + long displacement = pair ? pair->position - he->position : 0; const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s"; char buf[32] = " "; - if (hpp->displacement) - scnprintf(buf, sizeof(buf), "%+4ld", hpp->displacement); + if (displacement) + scnprintf(buf, sizeof(buf), "%+4ld", displacement); + + return scnprintf(hpp->buf, hpp->size, fmt, buf); +} + +static int hpp__header_formula(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%70s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Formula"); +} + +static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused) +{ + return 70; +} +static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s"; + char buf[96] = " "; + + perf_diff__formula(buf, sizeof(buf), he); return scnprintf(hpp->buf, hpp->size, fmt, buf); } @@ -267,6 +398,7 @@ static int hpp__entry_displ(struct perf_hpp *hpp, .entry = hpp__entry_ ## _name struct perf_hpp_fmt perf_hpp__format[] = { + { .cond = false, HPP__COLOR_PRINT_FNS(baseline) }, { .cond = true, HPP__COLOR_PRINT_FNS(overhead) }, { .cond = false, HPP__COLOR_PRINT_FNS(overhead_sys) }, { .cond = false, HPP__COLOR_PRINT_FNS(overhead_us) }, @@ -274,14 +406,18 @@ struct perf_hpp_fmt perf_hpp__format[] = { { .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_us) }, { .cond = false, HPP__PRINT_FNS(samples) }, { .cond = false, HPP__PRINT_FNS(period) }, + { .cond = false, HPP__PRINT_FNS(period_baseline) }, { .cond = false, HPP__PRINT_FNS(delta) }, - { .cond = false, HPP__PRINT_FNS(displ) } + { .cond = false, HPP__PRINT_FNS(ratio) }, + { .cond = false, HPP__PRINT_FNS(wdiff) }, + { .cond = false, HPP__PRINT_FNS(displ) }, + { .cond = false, HPP__PRINT_FNS(formula) } }; #undef HPP__COLOR_PRINT_FNS #undef HPP__PRINT_FNS -void perf_hpp__init(bool need_pair, bool show_displacement) +void perf_hpp__init(void) { if (symbol_conf.show_cpu_utilization) { perf_hpp__format[PERF_HPP__OVERHEAD_SYS].cond = true; @@ -298,13 +434,12 @@ void perf_hpp__init(bool need_pair, bool show_displacement) if (symbol_conf.show_total_period) perf_hpp__format[PERF_HPP__PERIOD].cond = true; +} - if (need_pair) { - perf_hpp__format[PERF_HPP__DELTA].cond = true; - - if (show_displacement) - perf_hpp__format[PERF_HPP__DISPL].cond = true; - } +void perf_hpp__column_enable(unsigned col, bool enable) +{ + BUG_ON(col >= PERF_HPP__MAX_INDEX); + perf_hpp__format[col].cond = enable; } static inline void advance_hpp(struct perf_hpp *hpp, int inc) @@ -319,6 +454,7 @@ int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, const char *sep = symbol_conf.field_sep; char *start = hpp->buf; int i, ret; + bool first = true; if (symbol_conf.exclude_other && !he->parent) return 0; @@ -327,9 +463,10 @@ int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, if (!perf_hpp__format[i].cond) continue; - if (!sep || i > 0) { + if (!sep || !first) { ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " "); advance_hpp(hpp, ret); + first = false; } if (color && perf_hpp__format[i].color) diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index bd7d460f844c..ebb4cc107876 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -30,7 +30,7 @@ void setup_browser(bool fallback_to_pager) if (fallback_to_pager) setup_pager(); - perf_hpp__init(false, false); + perf_hpp__init(); break; } } diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 882461a42830..f0ee204f99bb 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -271,7 +271,7 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, { switch (callchain_param.mode) { case CHAIN_GRAPH_REL: - return callchain__fprintf_graph(fp, &he->sorted_chain, he->period, + return callchain__fprintf_graph(fp, &he->sorted_chain, he->stat.period, left_margin); break; case CHAIN_GRAPH_ABS: @@ -292,9 +292,10 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, static size_t hist_entry__callchain_fprintf(struct hist_entry *he, struct hists *hists, - u64 total_period, FILE *fp) + FILE *fp) { int left_margin = 0; + u64 total_period = hists->stats.total_period; if (sort__first_dimension == SORT_COMM) { struct sort_entry *se = list_first_entry(&hist_entry__sort_list, @@ -307,17 +308,13 @@ static size_t hist_entry__callchain_fprintf(struct hist_entry *he, } static int hist_entry__fprintf(struct hist_entry *he, size_t size, - struct hists *hists, struct hists *pair_hists, - long displacement, u64 total_period, FILE *fp) + struct hists *hists, FILE *fp) { char bf[512]; int ret; struct perf_hpp hpp = { .buf = bf, .size = size, - .total_period = total_period, - .displacement = displacement, - .ptr = pair_hists, }; bool color = !symbol_conf.field_sep; @@ -330,32 +327,27 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); if (symbol_conf.use_callchain) - ret += hist_entry__callchain_fprintf(he, hists, - total_period, fp); + ret += hist_entry__callchain_fprintf(he, hists, fp); return ret; } -size_t hists__fprintf(struct hists *hists, struct hists *pair, - bool show_displacement, bool show_header, int max_rows, +size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, FILE *fp) { struct sort_entry *se; struct rb_node *nd; size_t ret = 0; - u64 total_period; - unsigned long position = 1; - long displacement = 0; unsigned int width; const char *sep = symbol_conf.field_sep; const char *col_width = symbol_conf.col_width_list_str; int idx, nr_rows = 0; - char bf[64]; + char bf[96]; struct perf_hpp dummy_hpp = { .buf = bf, .size = sizeof(bf), - .ptr = pair, }; + bool first = true; init_rem_hits(); @@ -367,8 +359,10 @@ size_t hists__fprintf(struct hists *hists, struct hists *pair, if (!perf_hpp__format[idx].cond) continue; - if (idx) + if (!first) fprintf(fp, "%s", sep ?: " "); + else + first = false; perf_hpp__format[idx].header(&dummy_hpp); fprintf(fp, "%s", bf); @@ -403,6 +397,8 @@ size_t hists__fprintf(struct hists *hists, struct hists *pair, if (sep) goto print_entries; + first = true; + fprintf(fp, "# "); for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { unsigned int i; @@ -410,8 +406,10 @@ size_t hists__fprintf(struct hists *hists, struct hists *pair, if (!perf_hpp__format[idx].cond) continue; - if (idx) + if (!first) fprintf(fp, "%s", sep ?: " "); + else + first = false; width = perf_hpp__format[idx].width(&dummy_hpp); for (i = 0; i < width; i++) @@ -441,24 +439,13 @@ size_t hists__fprintf(struct hists *hists, struct hists *pair, goto out; print_entries: - total_period = hists->stats.total_period; - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); if (h->filtered) continue; - if (show_displacement) { - if (h->pair != NULL) - displacement = ((long)h->pair->position - - (long)position); - else - displacement = 0; - ++position; - } - ret += hist_entry__fprintf(h, max_cols, hists, pair, displacement, - total_period, fp); + ret += hist_entry__fprintf(h, max_cols, hists, fp); if (max_rows && ++nr_rows >= max_rows) goto out; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 9b5b21e7b032..39242dcee8f2 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -138,7 +138,10 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, bool print_lines, bool full_paths, int min_pcnt, int max_lines); -#ifdef NO_NEWT_SUPPORT +#ifdef NEWT_SUPPORT +int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, + void(*timer)(void *arg), void *arg, int delay_secs); +#else static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, struct map *map __maybe_unused, int evidx __maybe_unused, @@ -148,9 +151,6 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, { return 0; } -#else -int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, - void(*timer)(void *arg), void *arg, int delay_secs); #endif extern const char *disassembler_style; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 8e3a740ddbd4..6a6399955ef2 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -64,7 +64,7 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, struct perf_tool build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, .mmap = perf_event__process_mmap, - .fork = perf_event__process_task, + .fork = perf_event__process_fork, .exit = perf_event__exit_del_thread, .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index ab1769426541..2bd51370ad28 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -33,39 +33,41 @@ extern int pager_use_color; extern int use_browser; -#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) -static inline void setup_browser(bool fallback_to_pager) -{ - if (fallback_to_pager) - setup_pager(); -} -static inline void exit_browser(bool wait_for_ok __maybe_unused) {} -#else +#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT) void setup_browser(bool fallback_to_pager); void exit_browser(bool wait_for_ok); -#ifdef NO_NEWT_SUPPORT +#ifdef NEWT_SUPPORT +int ui__init(void); +void ui__exit(bool wait_for_ok); +#else static inline int ui__init(void) { return -1; } static inline void ui__exit(bool wait_for_ok __maybe_unused) {} -#else -int ui__init(void); -void ui__exit(bool wait_for_ok); #endif -#ifdef NO_GTK2_SUPPORT +#ifdef GTK2_SUPPORT +int perf_gtk__init(void); +void perf_gtk__exit(bool wait_for_ok); +#else static inline int perf_gtk__init(void) { return -1; } static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {} -#else -int perf_gtk__init(void); -void perf_gtk__exit(bool wait_for_ok); #endif -#endif /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ + +#else /* NEWT_SUPPORT || GTK2_SUPPORT */ + +static inline void setup_browser(bool fallback_to_pager) +{ + if (fallback_to_pager) + setup_pager(); +} +static inline void exit_browser(bool wait_for_ok __maybe_unused) {} +#endif /* NEWT_SUPPORT || GTK2_SUPPORT */ char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); @@ -105,7 +107,7 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2 extern char *perf_pathdup(const char *fmt, ...) __attribute__((format (printf, 1, 2))); -#ifdef NO_STRLCPY +#ifndef HAVE_STRLCPY extern size_t strlcpy(char *dest, const char *src, size_t size); #endif diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 66eb3828ceb5..03f830b48148 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -49,7 +49,7 @@ int dump_printf(const char *fmt, ...) return ret; } -#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) +#if !defined(NEWT_SUPPORT) && !defined(GTK2_SUPPORT) int ui__warning(const char *format, ...) { va_list args; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index bb2e7d1007ab..dec98750b484 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -15,7 +15,14 @@ void trace_event(union perf_event *event); struct ui_progress; struct perf_error_ops; -#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) +#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT) + +#include "../ui/progress.h" +int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); +#include "../ui/util.h" + +#else + static inline void ui_progress__update(u64 curr __maybe_unused, u64 total __maybe_unused, const char *title __maybe_unused) {} @@ -34,13 +41,7 @@ perf_error__unregister(struct perf_error_ops *eops __maybe_unused) return 0; } -#else /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ - -#include "../ui/progress.h" -int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -#include "../ui/util.h" - -#endif /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ +#endif /* NEWT_SUPPORT || GTK2_SUPPORT */ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); int ui__error_paranoid(void); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 6715b1938725..0ae444ef1429 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include "event.h" #include "debug.h" +#include "machine.h" #include "sort.h" #include "string.h" #include "strlist.h" @@ -519,134 +520,15 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused, struct perf_sample *sample __maybe_unused, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->comm.tid); - - if (dump_trace) - perf_event__fprintf_comm(event, stdout); - - if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { - dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); - return -1; - } - - return 0; + return machine__process_comm_event(machine, event); } int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, - struct machine *machine __maybe_unused) -{ - dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", - event->lost.id, event->lost.lost); - return 0; -} - -static void perf_event__set_kernel_mmap_len(union perf_event *event, - struct map **maps) + struct machine *machine) { - maps[MAP__FUNCTION]->start = event->mmap.start; - maps[MAP__FUNCTION]->end = event->mmap.start + event->mmap.len; - /* - * Be a bit paranoid here, some perf.data file came with - * a zero sized synthesized MMAP event for the kernel. - */ - if (maps[MAP__FUNCTION]->end == 0) - maps[MAP__FUNCTION]->end = ~0ULL; -} - -static int perf_event__process_kernel_mmap(struct perf_tool *tool - __maybe_unused, - union perf_event *event, - struct machine *machine) -{ - struct map *map; - char kmmap_prefix[PATH_MAX]; - enum dso_kernel_type kernel_type; - bool is_kernel_mmap; - - machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); - if (machine__is_host(machine)) - kernel_type = DSO_TYPE_KERNEL; - else - kernel_type = DSO_TYPE_GUEST_KERNEL; - - is_kernel_mmap = memcmp(event->mmap.filename, - kmmap_prefix, - strlen(kmmap_prefix) - 1) == 0; - if (event->mmap.filename[0] == '/' || - (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - - char short_module_name[1024]; - char *name, *dot; - - if (event->mmap.filename[0] == '/') { - name = strrchr(event->mmap.filename, '/'); - if (name == NULL) - goto out_problem; - - ++name; /* skip / */ - dot = strrchr(name, '.'); - if (dot == NULL) - goto out_problem; - snprintf(short_module_name, sizeof(short_module_name), - "[%.*s]", (int)(dot - name), name); - strxfrchar(short_module_name, '-', '_'); - } else - strcpy(short_module_name, event->mmap.filename); - - map = machine__new_module(machine, event->mmap.start, - event->mmap.filename); - if (map == NULL) - goto out_problem; - - name = strdup(short_module_name); - if (name == NULL) - goto out_problem; - - map->dso->short_name = name; - map->dso->sname_alloc = 1; - map->end = map->start + event->mmap.len; - } else if (is_kernel_mmap) { - const char *symbol_name = (event->mmap.filename + - strlen(kmmap_prefix)); - /* - * Should be there already, from the build-id table in - * the header. - */ - struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, - kmmap_prefix); - if (kernel == NULL) - goto out_problem; - - kernel->kernel = kernel_type; - if (__machine__create_kernel_maps(machine, kernel) < 0) - goto out_problem; - - perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps); - - /* - * Avoid using a zero address (kptr_restrict) for the ref reloc - * symbol. Effectively having zero here means that at record - * time /proc/sys/kernel/kptr_restrict was non zero. - */ - if (event->mmap.pgoff != 0) { - maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, - symbol_name, - event->mmap.pgoff); - } - - if (machine__is_default_guest(machine)) { - /* - * preload dso of guest kernel and modules - */ - dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION], - NULL); - } - } - return 0; -out_problem: - return -1; + return machine__process_lost_event(machine, event); } size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) @@ -656,43 +538,12 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) event->mmap.len, event->mmap.pgoff, event->mmap.filename); } -int perf_event__process_mmap(struct perf_tool *tool, +int perf_event__process_mmap(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, struct machine *machine) { - struct thread *thread; - struct map *map; - u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - int ret = 0; - - if (dump_trace) - perf_event__fprintf_mmap(event, stdout); - - if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || - cpumode == PERF_RECORD_MISC_KERNEL) { - ret = perf_event__process_kernel_mmap(tool, event, machine); - if (ret < 0) - goto out_problem; - return 0; - } - - thread = machine__findnew_thread(machine, event->mmap.pid); - if (thread == NULL) - goto out_problem; - map = map__new(&machine->user_dsos, event->mmap.start, - event->mmap.len, event->mmap.pgoff, - event->mmap.pid, event->mmap.filename, - MAP__FUNCTION); - if (map == NULL) - goto out_problem; - - thread__insert_map(thread, map); - return 0; - -out_problem: - dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); - return 0; + return machine__process_mmap_event(machine, event); } size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) @@ -702,29 +553,20 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) event->fork.ppid, event->fork.ptid); } -int perf_event__process_task(struct perf_tool *tool __maybe_unused, +int perf_event__process_fork(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, - struct machine *machine) + struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->fork.tid); - struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); - - if (dump_trace) - perf_event__fprintf_task(event, stdout); - - if (event->header.type == PERF_RECORD_EXIT) { - machine__remove_thread(machine, thread); - return 0; - } - - if (thread == NULL || parent == NULL || - thread__fork(thread, parent) < 0) { - dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); - return -1; - } + return machine__process_fork_event(machine, event); +} - return 0; +int perf_event__process_exit(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_exit_event(machine, event); } size_t perf_event__fprintf(union perf_event *event, FILE *fp) @@ -750,27 +592,12 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) return ret; } -int perf_event__process(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample, struct machine *machine) +int perf_event__process(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) { - switch (event->header.type) { - case PERF_RECORD_COMM: - perf_event__process_comm(tool, event, sample, machine); - break; - case PERF_RECORD_MMAP: - perf_event__process_mmap(tool, event, sample, machine); - break; - case PERF_RECORD_FORK: - case PERF_RECORD_EXIT: - perf_event__process_task(tool, event, sample, machine); - break; - case PERF_RECORD_LOST: - perf_event__process_lost(tool, event, sample, machine); - default: - break; - } - - return 0; + return machine__process_event(machine, event); } void thread__find_addr_map(struct thread *self, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 21b99e741a87..da97aff5bd75 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -191,7 +191,11 @@ int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); -int perf_event__process_task(struct perf_tool *tool, +int perf_event__process_fork(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ae89686102f4..a41dc4a5c2de 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -154,8 +154,8 @@ error: return -ENOMEM; } -int perf_evlist__add_attrs(struct perf_evlist *evlist, - struct perf_event_attr *attrs, size_t nr_attrs) +static int perf_evlist__add_attrs(struct perf_evlist *evlist, + struct perf_event_attr *attrs, size_t nr_attrs) { struct perf_evsel *evsel, *n; LIST_HEAD(head); @@ -189,60 +189,6 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, return perf_evlist__add_attrs(evlist, attrs, nr_attrs); } -static int trace_event__id(const char *evname) -{ - char *filename, *colon; - int err = -1, fd; - - if (asprintf(&filename, "%s/%s/id", tracing_events_path, evname) < 0) - return -1; - - colon = strrchr(filename, ':'); - if (colon != NULL) - *colon = '/'; - - fd = open(filename, O_RDONLY); - if (fd >= 0) { - char id[16]; - if (read(fd, id, sizeof(id)) > 0) - err = atoi(id); - close(fd); - } - - free(filename); - return err; -} - -int perf_evlist__add_tracepoints(struct perf_evlist *evlist, - const char *tracepoints[], - size_t nr_tracepoints) -{ - int err; - size_t i; - struct perf_event_attr *attrs = zalloc(nr_tracepoints * sizeof(*attrs)); - - if (attrs == NULL) - return -1; - - for (i = 0; i < nr_tracepoints; i++) { - err = trace_event__id(tracepoints[i]); - - if (err < 0) - goto out_free_attrs; - - attrs[i].type = PERF_TYPE_TRACEPOINT; - attrs[i].config = err; - attrs[i].sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | - PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD); - attrs[i].sample_period = 1; - } - - err = perf_evlist__add_attrs(evlist, attrs, nr_tracepoints); -out_free_attrs: - free(attrs); - return err; -} - struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) { @@ -257,32 +203,18 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) return NULL; } -int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, - const struct perf_evsel_str_handler *assocs, - size_t nr_assocs) +int perf_evlist__add_newtp(struct perf_evlist *evlist, + const char *sys, const char *name, void *handler) { struct perf_evsel *evsel; - int err; - size_t i; - - for (i = 0; i < nr_assocs; i++) { - err = trace_event__id(assocs[i].name); - if (err < 0) - goto out; - - evsel = perf_evlist__find_tracepoint_by_id(evlist, err); - if (evsel == NULL) - continue; - err = -EEXIST; - if (evsel->handler.func != NULL) - goto out; - evsel->handler.func = assocs[i].handler; - } + evsel = perf_evsel__newtp(sys, name, evlist->nr_entries); + if (evsel == NULL) + return -1; - err = 0; -out: - return err; + evsel->handler.func = handler; + perf_evlist__add(evlist, evsel); + return 0; } void perf_evlist__disable(struct perf_evlist *evlist) @@ -393,8 +325,6 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { - /* XXX Move this to perf.c, making it generally available */ - unsigned int page_size = sysconf(_SC_PAGE_SIZE); struct perf_mmap *md = &evlist->mmap[idx]; unsigned int head = perf_mmap__read_head(md); unsigned int old = md->prev; @@ -596,7 +526,6 @@ out_unmap: int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite) { - unsigned int page_size = sysconf(_SC_PAGE_SIZE); struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; const struct thread_map *threads = evlist->threads; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 3f1fb66be022..56003f779e60 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -51,26 +51,14 @@ void perf_evlist__delete(struct perf_evlist *evlist); void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry); int perf_evlist__add_default(struct perf_evlist *evlist); -int perf_evlist__add_attrs(struct perf_evlist *evlist, - struct perf_event_attr *attrs, size_t nr_attrs); int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); -int perf_evlist__add_tracepoints(struct perf_evlist *evlist, - const char *tracepoints[], size_t nr_tracepoints); -int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, - const struct perf_evsel_str_handler *assocs, - size_t nr_assocs); - -#define perf_evlist__add_attrs_array(evlist, array) \ - perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array)) + #define perf_evlist__add_default_attrs(evlist, array) \ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) -#define perf_evlist__add_tracepoints_array(evlist, array) \ - perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array)) - -#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \ - perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) +int perf_evlist__add_newtp(struct perf_evlist *evlist, + const char *sys, const char *name, void *handler); int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 389590c1ad21..3ac38031d534 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -22,7 +22,7 @@ do }' "Documentation/perf-$cmd.txt" done -echo "#ifndef NO_LIBELF_SUPPORT" +echo "#ifdef LIBELF_SUPPORT" sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt | sort | while read cmd @@ -35,5 +35,5 @@ do p }' "Documentation/perf-$cmd.txt" done -echo "#endif /* NO_LIBELF_SUPPORT */" +echo "#endif /* LIBELF_SUPPORT */" echo "};" diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 236bc9d98ff2..277947a669b2 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -135,31 +135,47 @@ static void hist_entry__add_cpumode_period(struct hist_entry *he, { switch (cpumode) { case PERF_RECORD_MISC_KERNEL: - he->period_sys += period; + he->stat.period_sys += period; break; case PERF_RECORD_MISC_USER: - he->period_us += period; + he->stat.period_us += period; break; case PERF_RECORD_MISC_GUEST_KERNEL: - he->period_guest_sys += period; + he->stat.period_guest_sys += period; break; case PERF_RECORD_MISC_GUEST_USER: - he->period_guest_us += period; + he->stat.period_guest_us += period; break; default: break; } } +static void he_stat__add_period(struct he_stat *he_stat, u64 period) +{ + he_stat->period += period; + he_stat->nr_events += 1; +} + +static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) +{ + dest->period += src->period; + dest->period_sys += src->period_sys; + dest->period_us += src->period_us; + dest->period_guest_sys += src->period_guest_sys; + dest->period_guest_us += src->period_guest_us; + dest->nr_events += src->nr_events; +} + static void hist_entry__decay(struct hist_entry *he) { - he->period = (he->period * 7) / 8; - he->nr_events = (he->nr_events * 7) / 8; + he->stat.period = (he->stat.period * 7) / 8; + he->stat.nr_events = (he->stat.nr_events * 7) / 8; } static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) { - u64 prev_period = he->period; + u64 prev_period = he->stat.period; if (prev_period == 0) return true; @@ -167,9 +183,9 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) hist_entry__decay(he); if (!he->filtered) - hists->stats.total_period -= prev_period - he->period; + hists->stats.total_period -= prev_period - he->stat.period; - return he->period == 0; + return he->stat.period == 0; } static void __hists__decay_entries(struct hists *hists, bool zap_user, @@ -223,7 +239,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) if (he != NULL) { *he = *template; - he->nr_events = 1; + if (he->ms.map) he->ms.map->referenced = true; if (symbol_conf.use_callchain) @@ -238,7 +254,7 @@ static void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) if (!h->filtered) { hists__calc_col_len(hists, h); ++hists->nr_entries; - hists->stats.total_period += h->period; + hists->stats.total_period += h->stat.period; } } @@ -270,8 +286,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, cmp = hist_entry__cmp(entry, he); if (!cmp) { - he->period += period; - ++he->nr_events; + he_stat__add_period(&he->stat, period); /* If the map of an existing hist_entry has * become out-of-date due to an exec() or @@ -321,10 +336,14 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, .cpu = al->cpu, .ip = bi->to.addr, .level = al->level, - .period = period, + .stat = { + .period = period, + .nr_events = 1, + }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), .branch_info = bi, + .hists = self, }; return add_hist_entry(self, &entry, al, period); @@ -343,9 +362,13 @@ struct hist_entry *__hists__add_entry(struct hists *self, .cpu = al->cpu, .ip = al->addr, .level = al->level, - .period = period, + .stat = { + .period = period, + .nr_events = 1, + }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), + .hists = self, }; return add_hist_entry(self, &entry, al, period); @@ -410,12 +433,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, cmp = hist_entry__collapse(iter, he); if (!cmp) { - iter->period += he->period; - iter->period_sys += he->period_sys; - iter->period_us += he->period_us; - iter->period_guest_sys += he->period_guest_sys; - iter->period_guest_us += he->period_guest_us; - iter->nr_events += he->nr_events; + he_stat__add_stat(&iter->stat, &he->stat); if (symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); @@ -518,7 +536,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node); - if (he->period > iter->period) + if (he->stat.period > iter->stat.period) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -579,8 +597,8 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h if (h->ms.unfolded) hists->nr_entries += h->nr_rows; h->row_offset = 0; - hists->stats.total_period += h->period; - hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; + hists->stats.total_period += h->stat.period; + hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events; hists__calc_col_len(hists, h); } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index f011ad4756e8..c751624d4153 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -98,9 +98,8 @@ void hists__output_recalc_col_len(struct hists *hists, int max_rows); void hists__inc_nr_events(struct hists *self, u32 type); size_t hists__fprintf_nr_events(struct hists *self, FILE *fp); -size_t hists__fprintf(struct hists *self, struct hists *pair, - bool show_displacement, bool show_header, - int max_rows, int max_cols, FILE *fp); +size_t hists__fprintf(struct hists *self, bool show_header, int max_rows, + int max_cols, FILE *fp); int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr); int hist_entry__annotate(struct hist_entry *self, size_t privsize); @@ -118,9 +117,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *he); struct perf_hpp { char *buf; size_t size; - u64 total_period; const char *sep; - long displacement; void *ptr; }; @@ -135,6 +132,7 @@ struct perf_hpp_fmt { extern struct perf_hpp_fmt perf_hpp__format[]; enum { + PERF_HPP__BASELINE, PERF_HPP__OVERHEAD, PERF_HPP__OVERHEAD_SYS, PERF_HPP__OVERHEAD_US, @@ -142,19 +140,32 @@ enum { PERF_HPP__OVERHEAD_GUEST_US, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, + PERF_HPP__PERIOD_BASELINE, PERF_HPP__DELTA, + PERF_HPP__RATIO, + PERF_HPP__WEIGHTED_DIFF, PERF_HPP__DISPL, + PERF_HPP__FORMULA, PERF_HPP__MAX_INDEX }; -void perf_hpp__init(bool need_pair, bool show_displacement); +void perf_hpp__init(void); +void perf_hpp__column_enable(unsigned col, bool enable); int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, bool color); struct perf_evlist; -#ifdef NO_NEWT_SUPPORT +#ifdef NEWT_SUPPORT +#include "../ui/keysyms.h" +int hist_entry__tui_annotate(struct hist_entry *he, int evidx, + void(*timer)(void *arg), void *arg, int delay_secs); + +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, + void(*timer)(void *arg), void *arg, + int refresh); +#else static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, @@ -177,17 +188,13 @@ static inline int hist_entry__tui_annotate(struct hist_entry *self } #define K_LEFT -1 #define K_RIGHT -2 -#else -#include "../ui/keysyms.h" -int hist_entry__tui_annotate(struct hist_entry *he, int evidx, - void(*timer)(void *arg), void *arg, int delay_secs); +#endif -int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, +#ifdef GTK2_SUPPORT +int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, void(*timer)(void *arg), void *arg, int refresh); -#endif - -#ifdef NO_GTK2_SUPPORT +#else static inline int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, @@ -197,13 +204,12 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, { return 0; } - -#else -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, - void(*timer)(void *arg), void *arg, - int refresh); #endif unsigned int hists__sort_list_width(struct hists *self); +double perf_diff__compute_delta(struct hist_entry *he); +double perf_diff__compute_ratio(struct hist_entry *he); +s64 perf_diff__compute_wdiff(struct hist_entry *he); +int perf_diff__formula(char *buf, size_t size, struct hist_entry *he); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c new file mode 100644 index 000000000000..502eec0d4773 --- /dev/null +++ b/tools/perf/util/machine.c @@ -0,0 +1,277 @@ +#include "debug.h" +#include "event.h" +#include "machine.h" +#include "map.h" +#include "thread.h" +#include <stdbool.h> + +static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, + bool create) +{ + struct rb_node **p = &machine->threads.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + /* + * Font-end cache - PID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: + */ + if (machine->last_match && machine->last_match->pid == pid) + return machine->last_match; + + while (*p != NULL) { + parent = *p; + th = rb_entry(parent, struct thread, rb_node); + + if (th->pid == pid) { + machine->last_match = th; + return th; + } + + if (pid < th->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + if (!create) + return NULL; + + th = thread__new(pid); + if (th != NULL) { + rb_link_node(&th->rb_node, parent, p); + rb_insert_color(&th->rb_node, &machine->threads); + machine->last_match = th; + } + + return th; +} + +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid) +{ + return __machine__findnew_thread(machine, pid, true); +} + +struct thread *machine__find_thread(struct machine *machine, pid_t pid) +{ + return __machine__findnew_thread(machine, pid, false); +} + +int machine__process_comm_event(struct machine *machine, union perf_event *event) +{ + struct thread *thread = machine__findnew_thread(machine, event->comm.tid); + + if (dump_trace) + perf_event__fprintf_comm(event, stdout); + + if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { + dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); + return -1; + } + + return 0; +} + +int machine__process_lost_event(struct machine *machine __maybe_unused, + union perf_event *event) +{ + dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", + event->lost.id, event->lost.lost); + return 0; +} + +static void machine__set_kernel_mmap_len(struct machine *machine, + union perf_event *event) +{ + machine->vmlinux_maps[MAP__FUNCTION]->start = event->mmap.start; + machine->vmlinux_maps[MAP__FUNCTION]->end = (event->mmap.start + + event->mmap.len); + /* + * Be a bit paranoid here, some perf.data file came with + * a zero sized synthesized MMAP event for the kernel. + */ + if (machine->vmlinux_maps[MAP__FUNCTION]->end == 0) + machine->vmlinux_maps[MAP__FUNCTION]->end = ~0ULL; +} + +static int machine__process_kernel_mmap_event(struct machine *machine, + union perf_event *event) +{ + struct map *map; + char kmmap_prefix[PATH_MAX]; + enum dso_kernel_type kernel_type; + bool is_kernel_mmap; + + machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); + if (machine__is_host(machine)) + kernel_type = DSO_TYPE_KERNEL; + else + kernel_type = DSO_TYPE_GUEST_KERNEL; + + is_kernel_mmap = memcmp(event->mmap.filename, + kmmap_prefix, + strlen(kmmap_prefix) - 1) == 0; + if (event->mmap.filename[0] == '/' || + (!is_kernel_mmap && event->mmap.filename[0] == '[')) { + + char short_module_name[1024]; + char *name, *dot; + + if (event->mmap.filename[0] == '/') { + name = strrchr(event->mmap.filename, '/'); + if (name == NULL) + goto out_problem; + + ++name; /* skip / */ + dot = strrchr(name, '.'); + if (dot == NULL) + goto out_problem; + snprintf(short_module_name, sizeof(short_module_name), + "[%.*s]", (int)(dot - name), name); + strxfrchar(short_module_name, '-', '_'); + } else + strcpy(short_module_name, event->mmap.filename); + + map = machine__new_module(machine, event->mmap.start, + event->mmap.filename); + if (map == NULL) + goto out_problem; + + name = strdup(short_module_name); + if (name == NULL) + goto out_problem; + + map->dso->short_name = name; + map->dso->sname_alloc = 1; + map->end = map->start + event->mmap.len; + } else if (is_kernel_mmap) { + const char *symbol_name = (event->mmap.filename + + strlen(kmmap_prefix)); + /* + * Should be there already, from the build-id table in + * the header. + */ + struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, + kmmap_prefix); + if (kernel == NULL) + goto out_problem; + + kernel->kernel = kernel_type; + if (__machine__create_kernel_maps(machine, kernel) < 0) + goto out_problem; + + machine__set_kernel_mmap_len(machine, event); + + /* + * Avoid using a zero address (kptr_restrict) for the ref reloc + * symbol. Effectively having zero here means that at record + * time /proc/sys/kernel/kptr_restrict was non zero. + */ + if (event->mmap.pgoff != 0) { + maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, + symbol_name, + event->mmap.pgoff); + } + + if (machine__is_default_guest(machine)) { + /* + * preload dso of guest kernel and modules + */ + dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION], + NULL); + } + } + return 0; +out_problem: + return -1; +} + +int machine__process_mmap_event(struct machine *machine, union perf_event *event) +{ + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct thread *thread; + struct map *map; + int ret = 0; + + if (dump_trace) + perf_event__fprintf_mmap(event, stdout); + + if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || + cpumode == PERF_RECORD_MISC_KERNEL) { + ret = machine__process_kernel_mmap_event(machine, event); + if (ret < 0) + goto out_problem; + return 0; + } + + thread = machine__findnew_thread(machine, event->mmap.pid); + if (thread == NULL) + goto out_problem; + map = map__new(&machine->user_dsos, event->mmap.start, + event->mmap.len, event->mmap.pgoff, + event->mmap.pid, event->mmap.filename, + MAP__FUNCTION); + if (map == NULL) + goto out_problem; + + thread__insert_map(thread, map); + return 0; + +out_problem: + dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); + return 0; +} + +int machine__process_fork_event(struct machine *machine, union perf_event *event) +{ + struct thread *thread = machine__findnew_thread(machine, event->fork.tid); + struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); + + if (dump_trace) + perf_event__fprintf_task(event, stdout); + + if (thread == NULL || parent == NULL || + thread__fork(thread, parent) < 0) { + dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); + return -1; + } + + return 0; +} + +int machine__process_exit_event(struct machine *machine, union perf_event *event) +{ + struct thread *thread = machine__find_thread(machine, event->fork.tid); + + if (dump_trace) + perf_event__fprintf_task(event, stdout); + + if (thread != NULL) + machine__remove_thread(machine, thread); + + return 0; +} + +int machine__process_event(struct machine *machine, union perf_event *event) +{ + int ret; + + switch (event->header.type) { + case PERF_RECORD_COMM: + ret = machine__process_comm_event(machine, event); break; + case PERF_RECORD_MMAP: + ret = machine__process_mmap_event(machine, event); break; + case PERF_RECORD_FORK: + ret = machine__process_fork_event(machine, event); break; + case PERF_RECORD_EXIT: + ret = machine__process_exit_event(machine, event); break; + case PERF_RECORD_LOST: + ret = machine__process_lost_event(machine, event); break; + default: + ret = -1; + break; + } + + return ret; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h new file mode 100644 index 000000000000..df152f1768be --- /dev/null +++ b/tools/perf/util/machine.h @@ -0,0 +1,19 @@ +#ifndef __PERF_MACHINE_H +#define __PERF_MACHINE_H + +#include <sys/types.h> + +struct thread; +struct machine; +union perf_event; + +struct thread *machine__find_thread(struct machine *machine, pid_t pid); + +int machine__process_comm_event(struct machine *machine, union perf_event *event); +int machine__process_exit_event(struct machine *machine, union perf_event *event); +int machine__process_fork_event(struct machine *machine, union perf_event *event); +int machine__process_lost_event(struct machine *machine, union perf_event *event); +int machine__process_mmap_event(struct machine *machine, union perf_event *event); +int machine__process_event(struct machine *machine, union perf_event *event); + +#endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index ead5316b3f89..6109fa4d14cd 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -162,7 +162,7 @@ int map__load(struct map *self, symbol_filter_t filter) pr_warning(", continuing without symbols\n"); return -1; } else if (nr == 0) { -#ifndef NO_LIBELF_SUPPORT +#ifdef LIBELF_SUPPORT const size_t len = strlen(name); const size_t real_len = len - sizeof(DSO__DELETED); diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 443fc116512b..2bc9e70df7e2 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -384,6 +384,8 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, return usage_with_options_internal(usagestr, options, 1); if (internal_help && !strcmp(arg + 2, "help")) return parse_options_usage(usagestr, options); + if (!strcmp(arg + 2, "list-opts")) + return PARSE_OPT_LIST; switch (parse_long_opt(ctx, arg + 2, options)) { case -1: return parse_options_usage(usagestr, options); @@ -422,6 +424,12 @@ int parse_options(int argc, const char **argv, const struct option *options, exit(129); case PARSE_OPT_DONE: break; + case PARSE_OPT_LIST: + while (options->type != OPTION_END) { + printf("--%s ", options->long_name); + options++; + } + exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { error("unknown option `%s'", ctx.argv[0] + 2); diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index abc31a1dac1a..7bb5999940ca 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -140,6 +140,7 @@ extern NORETURN void usage_with_options(const char * const *usagestr, enum { PARSE_OPT_HELP = -1, PARSE_OPT_DONE, + PARSE_OPT_LIST, PARSE_OPT_UNKNOWN, }; diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index bd7497711424..a8c49548ca48 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -22,7 +22,7 @@ static const char *get_perf_dir(void) return "."; } -#ifdef NO_STRLCPY +#ifndef HAVE_STRLCPY size_t strlcpy(char *dest, const char *src, size_t size) { size_t ret = strlen(src); diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 316dbe7f86ed..5a4f2b6f3738 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -1,7 +1,7 @@ #ifndef __PERF_REGS_H #define __PERF_REGS_H -#ifndef NO_PERF_REGS +#ifdef HAVE_PERF_REGS #include <perf_regs.h> #else #define PERF_REGS_MASK 0 @@ -10,5 +10,5 @@ static inline const char *perf_reg_name(int id __maybe_unused) { return NULL; } -#endif /* NO_PERF_REGS */ +#endif /* HAVE_PERF_REGS */ #endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 730c6630cba5..14683dfca2ee 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -32,7 +32,6 @@ #include "../event.h" #include "../thread.h" #include "../trace-event.h" -#include "../evsel.h" PyMODINIT_FUNC initperf_trace_context(void); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8cdd23239c90..15abe40dc702 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1375,15 +1375,13 @@ int __perf_session__process_events(struct perf_session *session, { u64 head, page_offset, file_offset, file_pos, progress_next; int err, mmap_prot, mmap_flags, map_idx = 0; - size_t page_size, mmap_size; + size_t mmap_size; char *buf, *mmaps[8]; union perf_event *event; uint32_t size; perf_tool__fill_defaults(tool); - page_size = sysconf(_SC_PAGESIZE); - page_offset = page_size * (data_offset / page_size); file_offset = page_offset; head = data_offset - page_offset; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 12d634792de5..13761d83a5a0 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -43,6 +43,31 @@ extern struct sort_entry sort_sym_from; extern struct sort_entry sort_sym_to; extern enum sort_type sort__first_dimension; +struct he_stat { + u64 period; + u64 period_sys; + u64 period_us; + u64 period_guest_sys; + u64 period_guest_us; + u32 nr_events; +}; + +struct hist_entry_diff { + bool computed; + + /* PERF_HPP__DISPL */ + int displacement; + + /* PERF_HPP__DELTA */ + double period_ratio_delta; + + /* PERF_HPP__RATIO */ + double period_ratio; + + /* HISTC_WEIGHTED_DIFF */ + s64 wdiff; +}; + /** * struct hist_entry - histogram entry * @@ -52,16 +77,13 @@ extern enum sort_type sort__first_dimension; struct hist_entry { struct rb_node rb_node_in; struct rb_node rb_node; - u64 period; - u64 period_sys; - u64 period_us; - u64 period_guest_sys; - u64 period_guest_us; + struct he_stat stat; struct map_symbol ms; struct thread *thread; u64 ip; s32 cpu; - u32 nr_events; + + struct hist_entry_diff diff; /* XXX These two should move to some tree widget lib */ u16 row_offset; @@ -73,12 +95,13 @@ struct hist_entry { u8 filtered; char *srcline; struct symbol *parent; + unsigned long position; union { - unsigned long position; struct hist_entry *pair; struct rb_root sorted_chain; }; struct branch_info *branch_info; + struct hists *hists; struct callchain_root callchain[0]; }; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index b441b07172b7..8b6ef7fac745 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -12,7 +12,7 @@ #include <byteswap.h> #include <libgen.h> -#ifndef NO_LIBELF_SUPPORT +#ifdef LIBELF_SUPPORT #include <libelf.h> #include <gelf.h> #include <elf.h> @@ -46,10 +46,10 @@ char *strxfrchar(char *s, char from, char to); * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: */ -#ifdef LIBELF_NO_MMAP -# define PERF_ELF_C_READ_MMAP ELF_C_READ -#else +#ifdef LIBELF_MMAP # define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP +#else +# define PERF_ELF_C_READ_MMAP ELF_C_READ #endif #ifndef DMGL_PARAMS @@ -233,7 +233,7 @@ struct symsrc { int fd; enum dso_binary_type type; -#ifndef NO_LIBELF_SUPPORT +#ifdef LIBELF_SUPPORT Elf *elf; GElf_Ehdr ehdr; diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index fb4b7ea6752f..fe3bb1ec1887 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -7,7 +7,7 @@ #include "util.h" #include "debug.h" -static struct thread *thread__new(pid_t pid) +struct thread *thread__new(pid_t pid) { struct thread *self = zalloc(sizeof(*self)); @@ -61,45 +61,6 @@ static size_t thread__fprintf(struct thread *self, FILE *fp) map_groups__fprintf(&self->mg, verbose, fp); } -struct thread *machine__findnew_thread(struct machine *self, pid_t pid) -{ - struct rb_node **p = &self->threads.rb_node; - struct rb_node *parent = NULL; - struct thread *th; - - /* - * Font-end cache - PID lookups come in blocks, - * so most of the time we dont have to look up - * the full rbtree: - */ - if (self->last_match && self->last_match->pid == pid) - return self->last_match; - - while (*p != NULL) { - parent = *p; - th = rb_entry(parent, struct thread, rb_node); - - if (th->pid == pid) { - self->last_match = th; - return th; - } - - if (pid < th->pid) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - th = thread__new(pid); - if (th != NULL) { - rb_link_node(&th->rb_node, parent, p); - rb_insert_color(&th->rb_node, &self->threads); - self->last_match = th; - } - - return th; -} - void thread__insert_map(struct thread *self, struct map *map) { map_groups__fixup_overlappings(&self->mg, map, verbose, stderr); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index f66610b7bacf..f2fa17caa7d5 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -3,6 +3,7 @@ #include <linux/rbtree.h> #include <unistd.h> +#include <sys/types.h> #include "symbol.h" struct thread { @@ -22,6 +23,7 @@ struct thread { struct machine; +struct thread *thread__new(pid_t pid); void thread__delete(struct thread *self); int thread__set_comm(struct thread *self, const char *comm); diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 719ed74a8565..3741572696af 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -47,8 +47,6 @@ int file_bigendian; int host_bigendian; static int long_size; -static unsigned long page_size; - static ssize_t calc_data_size; static bool repipe; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index a78c8b303bb5..cb6bc503a792 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -13,7 +13,7 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); -#ifndef NO_LIBUNWIND_SUPPORT +#ifdef LIBUNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct machine *machine, struct thread *thread, @@ -31,5 +31,5 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, { return 0; } -#endif /* NO_LIBUNWIND_SUPPORT */ +#endif /* LIBUNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 2055cf38041c..637b5cc54362 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,7 +1,7 @@ #include "../perf.h" #include "util.h" #include <sys/mman.h> -#ifndef NO_BACKTRACE +#ifdef BACKTRACE_SUPPORT #include <execinfo.h> #endif #include <stdio.h> @@ -10,6 +10,8 @@ /* * XXX We need to find a better place for these things... */ +unsigned int page_size; + bool perf_host = true; bool perf_guest = false; @@ -165,7 +167,7 @@ size_t hex_width(u64 v) } /* Obtain a backtrace and print it to stdout. */ -#ifndef NO_BACKTRACE +#ifdef BACKTRACE_SUPPORT void dump_stack(void) { void *array[16]; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 70fa70b535b2..a6b83f8ebef8 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -263,4 +263,6 @@ char *rtrim(char *s); void dump_stack(void); +extern unsigned int page_size; + #endif |
