diff options
Diffstat (limited to 'tools/perf')
106 files changed, 4252 insertions, 1959 deletions
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 5ad07ef417f0..e9cd39a92dc2 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -93,6 +93,9 @@ OPTIONS --skip-missing:: Skip symbols that cannot be annotated. +--group:: + Show event group information together + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt index fae174dc7d01..5032a142853e 100644 --- a/tools/perf/Documentation/perf-archive.txt +++ b/tools/perf/Documentation/perf-archive.txt @@ -13,7 +13,7 @@ SYNOPSIS DESCRIPTION ----------- This command runs runs perf-buildid-list --with-hits, and collects the files -with the buildids found so that analisys of perf.data contents can be possible +with the buildids found so that analysis of perf.data contents can be possible on another machine. diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt new file mode 100644 index 000000000000..888d51137fbe --- /dev/null +++ b/tools/perf/Documentation/perf-mem.txt @@ -0,0 +1,48 @@ +perf-mem(1) +=========== + +NAME +---- +perf-mem - Profile memory accesses + +SYNOPSIS +-------- +[verse] +'perf mem' [<options>] (record [<command>] | report) + +DESCRIPTION +----------- +"perf mem -t <TYPE> record" runs a command and gathers memory operation data +from it, into perf.data. Perf record options are accepted and are passed through. + +"perf mem -t <TYPE> report" displays the result. It invokes perf report with the +right set of options to display a memory access profile. + +OPTIONS +------- +<command>...:: + Any command you can specify in a shell. + +-t:: +--type=:: + Select the memory operation type: load or store (default: load) + +-D:: +--dump-raw-samples=:: + Dump the raw decoded samples on the screen in a format that is easy to parse with + one sample per line. + +-x:: +--field-separator:: + Specify the field separator used when dump raw samples (-D option). By default, + The separator is the space character. + +-C:: +--cpu-list:: + Restrict dump of raw samples to those provided via this option. Note that the same + option can be passed in record mode. It will be interpreted the same way as perf + record. + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 938e8904f64d..d4da111ef53d 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -182,6 +182,12 @@ is enabled for all the sampling events. The sampled branch type is the same for The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k Note that this feature may not be available on all processors. +-W:: +--weight:: +Enable weightened sampling. An additional weight is recorded per sample and can be +displayed with the weight and local_weight sort keys. This currently works for TSX +abort events and some memory events in precise mode on modern Intel CPUs. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 02284a0067f0..66dab7410c1d 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -59,7 +59,7 @@ OPTIONS --sort=:: Sort histogram entries by given key(s) - multiple keys can be specified in CSV format. Following sort keys are available: - pid, comm, dso, symbol, parent, cpu, srcline. + pid, comm, dso, symbol, parent, cpu, srcline, weight, local_weight. Each key has following meaning: @@ -206,6 +206,14 @@ OPTIONS --group:: Show event group information together. +--demangle:: + Demangle symbol names to human readable form. It's enabled by default, + disable with --no-demangle. + +--percent-limit:: + Do not show entries which have an overhead under that percent. + (Default: 0). + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-annotate[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index faf4f4feebcc..2fe87fb558f0 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -52,7 +52,7 @@ OPTIONS -r:: --repeat=<n>:: - repeat command and print average + stddev (max: 100) + repeat command and print average + stddev (max: 100). 0 means forever. -B:: --big-num:: @@ -119,13 +119,19 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m Print count deltas every N milliseconds (minimum: 100ms) example: perf stat -I 1000 -e cycles -a sleep 5 ---aggr-socket:: +--per-socket:: Aggregate counts per processor socket for system-wide mode measurements. This is a useful mode to detect imbalance between sockets. To enable this mode, -use --aggr-socket in addition to -a. (system-wide). The output includes the +use --per-socket in addition to -a. (system-wide). The output includes the socket number and the number of online processors on that socket. This is useful to gauge the amount of aggregation. +--per-core:: +Aggregate counts per physical processor for system-wide mode measurements. This +is a useful mode to detect imbalance between physical cores. To enable this mode, +use --per-core in addition to -a. (system-wide). The output includes the +core number and the number of online logical processors on that physical processor. + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index a414bc95fd52..7fdd1909e376 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -112,7 +112,7 @@ Default is to monitor all CPUS. -s:: --sort:: - Sort by key(s): pid, comm, dso, symbol, parent, srcline. + Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, local_weight. -n:: --show-nr-samples:: @@ -155,6 +155,10 @@ Default is to monitor all CPUS. Default: fractal,0.5,callee. +--percent-limit:: + Do not show entries which have an overhead under that percent. + (Default: 0). + INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 39d41068484f..025de796067c 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,6 +1,7 @@ tools/perf tools/scripts tools/lib/traceevent +tools/lib/lk include/linux/const.h include/linux/perf_event.h include/linux/rbtree.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index bb74c79cd16e..203cb0eecff2 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -35,7 +35,9 @@ include config/utilities.mak # # Define WERROR=0 to disable treating any warnings as errors. # -# Define NO_NEWT if you do not want TUI support. +# Define NO_NEWT if you do not want TUI support. (deprecated) +# +# Define NO_SLANG if you do not want TUI support. # # Define NO_GTK2 if you do not want GTK+ GUI support. # @@ -49,184 +51,63 @@ include config/utilities.mak # Define NO_BACKTRACE if you do not want stack backtrace debug feature # # Define NO_LIBNUMA if you do not want numa perf benchmark +# +# Define NO_LIBAUDIT if you do not want libaudit support +# +# Define NO_LIBBIONIC if you do not want bionic support -$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE - @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) - -uname_M := $(shell uname -m 2>/dev/null || echo not) - -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ - -e s/arm.*/arm/ -e s/sa110/arm/ \ - -e s/s390x/s390/ -e s/parisc64/parisc/ \ - -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ - -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ ) -NO_PERF_REGS := 1 - -CC = $(CROSS_COMPILE)gcc -AR = $(CROSS_COMPILE)ar - -# Additional ARCH settings for x86 -ifeq ($(ARCH),i386) - override ARCH := x86 - NO_PERF_REGS := 0 - LIBUNWIND_LIBS = -lunwind -lunwind-x86 -endif -ifeq ($(ARCH),x86_64) - override ARCH := x86 - IS_X86_64 := 0 - ifeq (, $(findstring m32,$(EXTRA_CFLAGS))) - IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1) - endif - ifeq (${IS_X86_64}, 1) - RAW_ARCH := x86_64 - ARCH_CFLAGS := -DARCH_X86_64 - ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S - endif - NO_PERF_REGS := 0 - LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 -endif - -# Treat warnings as errors unless directed not to -ifneq ($(WERROR),0) - CFLAGS_WERROR := -Werror +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) endif -ifeq ("$(origin DEBUG)", "command line") - PERF_DEBUG = $(DEBUG) -endif -ifndef PERF_DEBUG - CFLAGS_OPTIMIZE = -O6 +ifneq ($(objtree),) +#$(info Determined 'objtree' to be $(objtree)) endif -ifdef PARSER_DEBUG - PARSER_DEBUG_BISON := -t - PARSER_DEBUG_FLEX := -d - PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG +ifneq ($(OUTPUT),) +#$(info Determined 'OUTPUT' to be $(OUTPUT)) endif -CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS) -EXTLIBS = -lpthread -lrt -lelf -lm -ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE -ALL_LDFLAGS = $(LDFLAGS) -STRIP ?= strip - -# Among the variables below, these: -# perfexecdir -# template_dir -# mandir -# infodir -# htmldir -# ETC_PERFCONFIG (but not sysconfdir) -# can be specified as a relative path some/where/else; -# this is interpreted as relative to $(prefix) and "perf" at -# runtime figures out where they are based on the path to the executable. -# This can help installing the suite in a relocatable way. - -# Make the path relative to DESTDIR, not to prefix -ifndef DESTDIR -prefix = $(HOME) -endif -bindir_relative = bin -bindir = $(prefix)/$(bindir_relative) -mandir = share/man -infodir = share/info -perfexecdir = libexec/perf-core -sharedir = $(prefix)/share -template_dir = share/perf-core/templates -htmldir = share/doc/perf-doc -ifeq ($(prefix),/usr) -sysconfdir = /etc -ETC_PERFCONFIG = $(sysconfdir)/perfconfig -else -sysconfdir = $(prefix)/etc -ETC_PERFCONFIG = etc/perfconfig -endif -lib = lib +$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE + @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) -export prefix bindir sharedir sysconfdir +CC = $(CROSS_COMPILE)gcc +AR = $(CROSS_COMPILE)ar -RM = rm -f -MKDIR = mkdir -FIND = find +RM = rm -f +MKDIR = mkdir +FIND = find INSTALL = install -FLEX = flex -BISON= bison - -# sparse is architecture-neutral, which means that we need to tell it -# explicitly what architecture to check for. Fix this up for yours.. -SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ +FLEX = flex +BISON = bison +STRIP = strip -ifneq ($(MAKECMDGOALS),clean) -ifneq ($(MAKECMDGOALS),tags) --include config/feature-tests.mak +LK_DIR = $(srctree)/tools/lib/lk/ +TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ -ifeq ($(call get-executable,$(FLEX)),) - dummy := $(error Error: $(FLEX) is missing on this system, please install it) -endif - -ifeq ($(call get-executable,$(BISON)),) - dummy := $(error Error: $(BISON) is missing on this system, please install it) -endif - -ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y) - CFLAGS := $(CFLAGS) -fstack-protector-all -endif - -ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y) - CFLAGS := $(CFLAGS) -Wstack-protector -endif +# include config/Makefile by default and rule out +# non-config cases +config := 1 -ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y) - CFLAGS := $(CFLAGS) -Wvolatile-register-var -endif +NON_CONFIG_TARGETS := clean TAGS tags cscope help -ifndef PERF_DEBUG - ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y) - CFLAGS := $(CFLAGS) -D_FORTIFY_SOURCE=2 - endif +ifdef MAKECMDGOALS +ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) + config := 0 endif - -### --- END CONFIGURATION SECTION --- - -ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(shell pwd))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -#$(info Determined 'srctree' to be $(srctree)) endif -ifneq ($(objtree),) -#$(info Determined 'objtree' to be $(objtree)) +ifeq ($(config),1) +include config/Makefile endif -ifneq ($(OUTPUT),) -#$(info Determined 'OUTPUT' to be $(OUTPUT)) -endif +export prefix bindir sharedir sysconfdir -BASIC_CFLAGS = \ - -Iutil/include \ - -Iarch/$(ARCH)/include \ - $(if $(objtree),-I$(objtree)/arch/$(ARCH)/include/generated/uapi) \ - -I$(srctree)/arch/$(ARCH)/include/uapi \ - -I$(srctree)/arch/$(ARCH)/include \ - $(if $(objtree),-I$(objtree)/include/generated/uapi) \ - -I$(srctree)/include/uapi \ - -I$(srctree)/include \ - -I$(OUTPUT)util \ - -Iutil \ - -I. \ - -I$(TRACE_EVENT_DIR) \ - -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE - -BASIC_LDFLAGS = - -ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y) - BIONIC := 1 - EXTLIBS := $(filter-out -lrt,$(EXTLIBS)) - EXTLIBS := $(filter-out -lpthread,$(EXTLIBS)) - BASIC_CFLAGS += -I. -endif -endif # MAKECMDGOALS != tags -endif # MAKECMDGOALS != clean +# sparse is architecture-neutral, which means that we need to tell it +# explicitly what architecture to check for. Fix this up for yours.. +SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ # Guard against environment variables BUILTIN_OBJS = @@ -240,19 +121,25 @@ SCRIPT_SH += perf-archive.sh grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) -TRACE_EVENT_DIR = ../lib/traceevent/ +LK_PATH=$(LK_DIR) ifneq ($(OUTPUT),) - TE_PATH=$(OUTPUT) + TE_PATH=$(OUTPUT) +ifneq ($(subdir),) + LK_PATH=$(OUTPUT)$(LK_DIR) else - TE_PATH=$(TRACE_EVENT_DIR) + LK_PATH=$(OUTPUT) +endif +else + TE_PATH=$(TRACE_EVENT_DIR) endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a -TE_LIB := -L$(TE_PATH) -ltraceevent - export LIBTRACEEVENT +LIBLK = $(LK_PATH)liblk.a +export LIBLK + # python extension build directories PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ @@ -262,10 +149,10 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources) -PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py +PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK) $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) - $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \ + $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ mkdir -p $(OUTPUT)python && \ cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/ @@ -280,8 +167,6 @@ SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) # PROGRAMS += $(OUTPUT)perf -LANG_BINDINGS = - # what 'all' will build and 'install' will install, in perfexecdir ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) @@ -290,10 +175,10 @@ OTHER_PROGRAMS = $(OUTPUT)perf # Set paths to tools early so that they can be used for version tests. ifndef SHELL_PATH - SHELL_PATH = /bin/sh + SHELL_PATH = /bin/sh endif ifndef PERL_PATH - PERL_PATH = /usr/bin/perl + PERL_PATH = /usr/bin/perl endif export PERL_PATH @@ -355,7 +240,6 @@ LIB_H += util/cache.h LIB_H += util/callchain.h LIB_H += util/build-id.h LIB_H += util/debug.h -LIB_H += util/debugfs.h LIB_H += util/sysfs.h LIB_H += util/pmu.h LIB_H += util/event.h @@ -416,7 +300,6 @@ LIB_OBJS += $(OUTPUT)util/annotate.o LIB_OBJS += $(OUTPUT)util/build-id.o LIB_OBJS += $(OUTPUT)util/config.o LIB_OBJS += $(OUTPUT)util/ctype.o -LIB_OBJS += $(OUTPUT)util/debugfs.o LIB_OBJS += $(OUTPUT)util/sysfs.o LIB_OBJS += $(OUTPUT)util/pmu.o LIB_OBJS += $(OUTPUT)util/environment.o @@ -503,6 +386,10 @@ LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o LIB_OBJS += $(OUTPUT)tests/pmu.o LIB_OBJS += $(OUTPUT)tests/hists_link.o LIB_OBJS += $(OUTPUT)tests/python-use.o +LIB_OBJS += $(OUTPUT)tests/bp_signal.o +LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o +LIB_OBJS += $(OUTPUT)tests/task-exit.o +LIB_OBJS += $(OUTPUT)tests/sw-clock.o BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o @@ -535,82 +422,18 @@ BUILTIN_OBJS += $(OUTPUT)builtin-lock.o BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o BUILTIN_OBJS += $(OUTPUT)builtin-inject.o BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o +BUILTIN_OBJS += $(OUTPUT)builtin-mem.o -PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT) - -# -# Platform specific tweaks -# -ifneq ($(MAKECMDGOALS),clean) -ifneq ($(MAKECMDGOALS),tags) +PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT) # We choose to avoid "if .. else if .. else .. endif endif" # because maintaining the nesting to match is a pain. If # we had "elif" things would have been much nicer... -ifdef NO_LIBELF - NO_DWARF := 1 - NO_DEMANGLE := 1 - NO_LIBUNWIND := 1 -else -FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y) - FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS) - ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y) - LIBC_SUPPORT := 1 - endif - ifeq ($(BIONIC),1) - LIBC_SUPPORT := 1 - endif - ifeq ($(LIBC_SUPPORT),1) - msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev); - - NO_LIBELF := 1 - NO_DWARF := 1 - NO_DEMANGLE := 1 - else - msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); - endif -else - # for linking with debug library, run like: - # make DEBUG=1 LIBDW_DIR=/opt/libdw/ - ifdef LIBDW_DIR - LIBDW_CFLAGS := -I$(LIBDW_DIR)/include - LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib - endif - - FLAGS_DWARF=$(ALL_CFLAGS) $(LIBDW_CFLAGS) -ldw -lelf $(LIBDW_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) - ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y) - msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); - NO_DWARF := 1 - endif # Dwarf support -endif # SOURCE_LIBELF -endif # NO_LIBELF - -# There's only x86 (both 32 and 64) support for CFI unwind so far -ifneq ($(ARCH),x86) - NO_LIBUNWIND := 1 -endif - -ifndef NO_LIBUNWIND -# for linking with debug library, run like: -# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ -ifdef LIBUNWIND_DIR - LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include - LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib -endif - -FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS) -ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y) - msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99); - NO_LIBUNWIND := 1 -endif # Libunwind support -endif # NO_LIBUNWIND - -include arch/$(ARCH)/Makefile ifneq ($(OUTPUT),) - BASIC_CFLAGS += -I$(OUTPUT) + CFLAGS += -I$(OUTPUT) endif ifdef NO_LIBELF @@ -628,281 +451,74 @@ BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS)) LIB_OBJS += $(OUTPUT)util/symbol-minimal.o else # NO_LIBELF -BASIC_CFLAGS += -DLIBELF_SUPPORT - -FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) - BASIC_CFLAGS += -DLIBELF_MMAP -endif - 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); -else - BASIC_CFLAGS := -DDWARF_SUPPORT $(LIBDW_CFLAGS) $(BASIC_CFLAGS) - BASIC_LDFLAGS := $(LIBDW_LDFLAGS) $(BASIC_LDFLAGS) - EXTLIBS += -lelf -ldw - LIB_OBJS += $(OUTPUT)util/probe-finder.o - LIB_OBJS += $(OUTPUT)util/dwarf-aux.o -endif # PERF_HAVE_DWARF_REGS + LIB_OBJS += $(OUTPUT)util/probe-finder.o + LIB_OBJS += $(OUTPUT)util/dwarf-aux.o endif # NO_DWARF endif # NO_LIBELF 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 + LIB_OBJS += $(OUTPUT)util/unwind.o endif ifndef NO_LIBAUDIT - FLAGS_LIBAUDIT = $(ALL_CFLAGS) $(ALL_LDFLAGS) -laudit - ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y) - msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev); - else - BASIC_CFLAGS += -DLIBAUDIT_SUPPORT - BUILTIN_OBJS += $(OUTPUT)builtin-trace.o - EXTLIBS += -laudit - endif + BUILTIN_OBJS += $(OUTPUT)builtin-trace.o endif -ifndef NO_NEWT - FLAGS_NEWT=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lnewt - ifneq ($(call try-cc,$(SOURCE_NEWT),$(FLAGS_NEWT),libnewt),y) - msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev); - 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/browser.o - LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o - LIB_OBJS += $(OUTPUT)ui/browsers/hists.o - LIB_OBJS += $(OUTPUT)ui/browsers/map.o - LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o - LIB_OBJS += $(OUTPUT)ui/tui/setup.o - LIB_OBJS += $(OUTPUT)ui/tui/util.o - LIB_OBJS += $(OUTPUT)ui/tui/helpline.o - LIB_OBJS += $(OUTPUT)ui/tui/progress.o - LIB_H += ui/browser.h - LIB_H += ui/browsers/map.h - LIB_H += ui/keysyms.h - LIB_H += ui/libslang.h - endif +ifndef NO_SLANG + LIB_OBJS += $(OUTPUT)ui/browser.o + LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o + LIB_OBJS += $(OUTPUT)ui/browsers/hists.o + LIB_OBJS += $(OUTPUT)ui/browsers/map.o + LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o + LIB_OBJS += $(OUTPUT)ui/tui/setup.o + LIB_OBJS += $(OUTPUT)ui/tui/util.o + LIB_OBJS += $(OUTPUT)ui/tui/helpline.o + LIB_OBJS += $(OUTPUT)ui/tui/progress.o + LIB_H += ui/browser.h + LIB_H += ui/browsers/map.h + LIB_H += ui/keysyms.h + LIB_H += ui/libslang.h endif ifndef NO_GTK2 - FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) - ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y) - msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); - else - ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),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 - LIB_OBJS += $(OUTPUT)ui/gtk/hists.o - LIB_OBJS += $(OUTPUT)ui/gtk/setup.o - LIB_OBJS += $(OUTPUT)ui/gtk/util.o - LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o - LIB_OBJS += $(OUTPUT)ui/gtk/progress.o - LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o - endif -endif - -ifdef NO_LIBPERL - BASIC_CFLAGS += -DNO_LIBPERL -else - PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) - PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) - PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) - PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` - FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) - - ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y) - BASIC_CFLAGS += -DNO_LIBPERL - else - ALL_LDFLAGS += $(PERL_EMBED_LDFLAGS) - EXTLIBS += $(PERL_EMBED_LIBADD) - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o - LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o - endif + LIB_OBJS += $(OUTPUT)ui/gtk/browser.o + LIB_OBJS += $(OUTPUT)ui/gtk/hists.o + LIB_OBJS += $(OUTPUT)ui/gtk/setup.o + LIB_OBJS += $(OUTPUT)ui/gtk/util.o + LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o + LIB_OBJS += $(OUTPUT)ui/gtk/progress.o + LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o endif -disable-python = $(eval $(disable-python_code)) -define disable-python_code - BASIC_CFLAGS += -DNO_LIBPYTHON - $(if $(1),$(warning No $(1) was found)) - $(warning Python support will not be built) -endef - -override PYTHON := \ - $(call get-executable-or-default,PYTHON,python) - -ifndef PYTHON - $(call disable-python,python interpreter) -else - - PYTHON_WORD := $(call shell-wordify,$(PYTHON)) - - ifdef NO_LIBPYTHON - $(call disable-python) - else - - override PYTHON_CONFIG := \ - $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config) - - ifndef PYTHON_CONFIG - $(call disable-python,python-config tool) - else - - PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) - - PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) - PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) - PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) - PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) - - ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y) - $(call disable-python,Python.h (for Python 2.x)) - else - - ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y) - $(warning Python 3 is not yet supported; please set) - $(warning PYTHON and/or PYTHON_CONFIG appropriately.) - $(warning If you also have Python 2 installed, then) - $(warning try something like:) - $(warning $(and ,)) - $(warning $(and ,) make PYTHON=python2) - $(warning $(and ,)) - $(warning Otherwise, disable Python support entirely:) - $(warning $(and ,)) - $(warning $(and ,) make NO_LIBPYTHON=1) - $(warning $(and ,)) - $(error $(and ,)) - else - ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS) - EXTLIBS += $(PYTHON_EMBED_LIBADD) - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o - LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o - LANG_BINDINGS += $(OUTPUT)python/perf.so - endif - - endif - endif - endif +ifndef NO_LIBPERL + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o + LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o endif -ifdef NO_DEMANGLE - BASIC_CFLAGS += -DNO_DEMANGLE -else - ifdef HAVE_CPLUS_DEMANGLE - EXTLIBS += -liberty - BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE - else - FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd - has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd) - ifeq ($(has_bfd),y) - EXTLIBS += -lbfd - else - FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty - has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty) - ifeq ($(has_bfd_iberty),y) - EXTLIBS += -lbfd -liberty - else - FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz - has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz) - ifeq ($(has_bfd_iberty_z),y) - EXTLIBS += -lbfd -liberty -lz - else - FLAGS_CPLUS_DEMANGLE=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -liberty - has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle) - ifeq ($(has_cplus_demangle),y) - EXTLIBS += -liberty - BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE - else - msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling) - BASIC_CFLAGS += -DNO_DEMANGLE - endif - endif - endif - endif - endif +ifndef NO_LIBPYTHON + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o + LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o endif ifeq ($(NO_PERF_REGS),0) - ifeq ($(ARCH),x86) - LIB_H += arch/x86/include/perf_regs.h - endif - BASIC_CFLAGS += -DHAVE_PERF_REGS -endif - -ifndef NO_STRLCPY - ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y) - BASIC_CFLAGS += -DHAVE_STRLCPY - endif -endif - -ifndef NO_ON_EXIT - ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y) - BASIC_CFLAGS += -DHAVE_ON_EXIT - endif -endif - -ifndef NO_BACKTRACE - ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y) - BASIC_CFLAGS += -DBACKTRACE_SUPPORT - endif + ifeq ($(ARCH),x86) + LIB_H += arch/x86/include/perf_regs.h + endif endif ifndef NO_LIBNUMA - FLAGS_LIBNUMA = $(ALL_CFLAGS) $(ALL_LDFLAGS) -lnuma - ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y) - msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev); - else - BASIC_CFLAGS += -DLIBNUMA_SUPPORT - BUILTIN_OBJS += $(OUTPUT)bench/numa.o - EXTLIBS += -lnuma - endif + BUILTIN_OBJS += $(OUTPUT)bench/numa.o endif ifdef ASCIIDOC8 - export ASCIIDOC8 + export ASCIIDOC8 endif -endif # MAKECMDGOALS != tags -endif # MAKECMDGOALS != clean - -# Shell quote (do not use $(call) to accommodate ancient setups); - -ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) - -DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) -bindir_SQ = $(subst ','\'',$(bindir)) -bindir_relative_SQ = $(subst ','\'',$(bindir_relative)) -mandir_SQ = $(subst ','\'',$(mandir)) -infodir_SQ = $(subst ','\'',$(infodir)) -perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) -template_dir_SQ = $(subst ','\'',$(template_dir)) -htmldir_SQ = $(subst ','\'',$(htmldir)) -prefix_SQ = $(subst ','\'',$(prefix)) -sysconfdir_SQ = $(subst ','\'',$(sysconfdir)) - -SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) - LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group -ALL_CFLAGS += $(BASIC_CFLAGS) -ALL_CFLAGS += $(ARCH_CFLAGS) -ALL_LDFLAGS += $(BASIC_LDFLAGS) - export INSTALL SHELL_PATH - ### Build rules SHELL = $(SHELL_PATH) @@ -920,20 +536,20 @@ strip: $(PROGRAMS) $(OUTPUT)perf $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - $(ALL_CFLAGS) -c $(filter %.c,$^) -o $@ + $(CFLAGS) -c $(filter %.c,$^) -o $@ $(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS) - $(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \ + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \ $(BUILTIN_OBJS) $(LIBS) -o $@ $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ '-DPERF_MAN_PATH="$(mandir_SQ)"' \ '-DPERF_INFO_PATH="$(infodir_SQ)"' $< $(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ '-DPERF_MAN_PATH="$(mandir_SQ)"' \ '-DPERF_INFO_PATH="$(infodir_SQ)"' $< @@ -958,77 +574,77 @@ $(OUTPUT)perf.o perf.spec \ # over the general rule for .o $(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -w $< + $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $< $(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $< + $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $< $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< $(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $< + $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< $(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -S $(ALL_CFLAGS) $< + $(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $< $(OUTPUT)%.o: %.S - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< $(OUTPUT)%.s: %.S - $(QUIET_CC)$(CC) -o $@ -E $(ALL_CFLAGS) $< + $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ '-DPREFIX="$(prefix_SQ)"' \ $< $(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \ $< $(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ -DPYTHONPATH='"$(OUTPUT)python"' \ -DPYTHON='"$(PYTHON_WORD)"' \ $< $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< $(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< $(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< $(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< $(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $< $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< $(OUTPUT)perf-%: %.o $(PERFLIBS) - $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) + $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS) $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) @@ -1051,6 +667,18 @@ $(LIBTRACEEVENT): $(LIBTRACEEVENT)-clean: $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean +# if subdir is set, we've been called from above so target has been built +# already +$(LIBLK): +ifeq ($(subdir),) + $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a +endif + +$(LIBLK)-clean: +ifeq ($(subdir),) + $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean +endif + help: @echo 'Perf make targets:' @echo ' doc - make *all* documentation (see below)' @@ -1103,7 +731,7 @@ cscope: $(FIND) . -name '*.[hcS]' -print | xargs cscope -b ### Detect prefix changes -TRACK_CFLAGS = $(subst ','\'',$(ALL_CFLAGS)):\ +TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\ $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ) $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS @@ -1124,7 +752,7 @@ check: $(OUTPUT)common-cmds.h then \ for i in *.c */*.c; \ do \ - sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \ + sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \ done; \ else \ exit 1; \ @@ -1132,13 +760,6 @@ check: $(OUTPUT)common-cmds.h ### Installation rules -ifneq ($(filter /%,$(firstword $(perfexecdir))),) -perfexec_instdir = $(perfexecdir) -else -perfexec_instdir = $(prefix)/$(perfexecdir) -endif -perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) - install-bin: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)' @@ -1171,7 +792,7 @@ $(INSTALL_DOC_TARGETS): ### Cleaning rules -clean: $(LIBTRACEEVENT)-clean +clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(RM) $(ALL_PROGRAMS) perf $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* @@ -1181,6 +802,6 @@ clean: $(LIBTRACEEVENT)-clean $(RM) $(OUTPUT)util/*-flex* $(python-clean) -.PHONY: all install clean strip $(LIBTRACEEVENT) +.PHONY: all install clean strip $(LIBTRACEEVENT) $(LIBLK) .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c index e8d5c551c69c..33ec5b339da8 100644 --- a/tools/perf/arch/arm/util/dwarf-regs.c +++ b/tools/perf/arch/arm/util/dwarf-regs.c @@ -8,10 +8,7 @@ * published by the Free Software Foundation. */ -#include <stdlib.h> -#ifndef __UCLIBC__ -#include <libio.h> -#endif +#include <stddef.h> #include <dwarf-regs.h> struct pt_regs_dwarfnum { diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c index 7cdd61d0e27c..733151cdf46e 100644 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -9,10 +9,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <stdlib.h> -#ifndef __UCLIBC__ -#include <libio.h> -#endif +#include <stddef.h> #include <dwarf-regs.h> diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c index e19653e025fa..0469df02ee62 100644 --- a/tools/perf/arch/s390/util/dwarf-regs.c +++ b/tools/perf/arch/s390/util/dwarf-regs.c @@ -6,7 +6,7 @@ * */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> #define NUM_GPRS 16 diff --git a/tools/perf/arch/sh/util/dwarf-regs.c b/tools/perf/arch/sh/util/dwarf-regs.c index a11edb007a6c..0d0897f57a10 100644 --- a/tools/perf/arch/sh/util/dwarf-regs.c +++ b/tools/perf/arch/sh/util/dwarf-regs.c @@ -19,7 +19,7 @@ * */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> /* diff --git a/tools/perf/arch/sparc/util/dwarf-regs.c b/tools/perf/arch/sparc/util/dwarf-regs.c index 0ab88483720c..92eda412fed3 100644 --- a/tools/perf/arch/sparc/util/dwarf-regs.c +++ b/tools/perf/arch/sparc/util/dwarf-regs.c @@ -9,7 +9,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> #define SPARC_MAX_REGS 96 diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c index a794d3081928..be22dd463232 100644 --- a/tools/perf/arch/x86/util/dwarf-regs.c +++ b/tools/perf/arch/x86/util/dwarf-regs.c @@ -20,7 +20,7 @@ * */ -#include <libio.h> +#include <stddef.h> #include <dwarf-regs.h> /* diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 2e6961ea3184..db491e9a812b 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -63,7 +63,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return 0; } - he = __hists__add_entry(&evsel->hists, al, NULL, 1); + he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1); if (he == NULL) return -ENOMEM; @@ -109,14 +109,16 @@ static int process_sample_event(struct perf_tool *tool, return 0; } -static int hist_entry__tty_annotate(struct hist_entry *he, int evidx, +static int hist_entry__tty_annotate(struct hist_entry *he, + struct perf_evsel *evsel, struct perf_annotate *ann) { - return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx, + return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel, ann->print_line, ann->full_paths, 0, 0); } -static void hists__find_annotations(struct hists *self, int evidx, +static void hists__find_annotations(struct hists *self, + struct perf_evsel *evsel, struct perf_annotate *ann) { struct rb_node *nd = rb_first(&self->entries), *next; @@ -142,14 +144,14 @@ find_next: if (use_browser == 2) { int ret; - ret = hist_entry__gtk_annotate(he, evidx, NULL); + ret = hist_entry__gtk_annotate(he, evsel, NULL); if (!ret || !ann->skip_missing) return; /* skip missing symbols */ nd = rb_next(nd); } else if (use_browser == 1) { - key = hist_entry__tui_annotate(he, evidx, NULL); + key = hist_entry__tui_annotate(he, evsel, NULL); switch (key) { case -1: if (!ann->skip_missing) @@ -168,7 +170,7 @@ find_next: if (next != NULL) nd = next; } else { - hist_entry__tty_annotate(he, evidx, ann); + hist_entry__tty_annotate(he, evsel, ann); nd = rb_next(nd); /* * Since we have a hist_entry per IP for the same @@ -230,7 +232,12 @@ static int __cmd_annotate(struct perf_annotate *ann) total_nr_samples += nr_samples; hists__collapse_resort(hists); hists__output_resort(hists); - hists__find_annotations(hists, pos->idx, ann); + + if (symbol_conf.event_group && + !perf_evsel__is_group_leader(pos)) + continue; + + hists__find_annotations(hists, pos, ann); } } @@ -312,6 +319,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_BOOLEAN(0, "group", &symbol_conf.event_group, + "Show event group information together"), OPT_END() }; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index d207a97a2db1..da8f8eb383a0 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -231,9 +231,10 @@ int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, } static int hists__add_entry(struct hists *self, - struct addr_location *al, u64 period) + struct addr_location *al, u64 period, + u64 weight) { - if (__hists__add_entry(self, al, NULL, period) != NULL) + if (__hists__add_entry(self, al, NULL, period, weight) != NULL) return 0; return -ENOMEM; } @@ -255,7 +256,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, if (al.filtered) return 0; - if (hists__add_entry(&evsel->hists, &al, sample->period)) { + if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight)) { pr_warning("problem incrementing symbol period, skipping event\n"); return -1; } @@ -322,13 +323,20 @@ static void hists__baseline_only(struct hists *hists) static void hists__precompute(struct hists *hists) { - struct rb_node *next = rb_first(&hists->entries); + struct rb_root *root; + struct rb_node *next; + + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + next = rb_first(root); while (next != NULL) { - struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in); struct hist_entry *pair = hist_entry__next_pair(he); - next = rb_next(&he->rb_node); + next = rb_next(&he->rb_node_in); if (!pair) continue; @@ -456,7 +464,7 @@ static void hists__process(struct hists *old, struct hists *new) hists__output_resort(new); } - hists__fprintf(new, true, 0, 0, stdout); + hists__fprintf(new, true, 0, 0, 0, stdout); } static int __cmd_diff(void) @@ -610,9 +618,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) setup_pager(); - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", NULL); - sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", NULL); - sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", NULL); + sort__setup_elide(NULL); return __cmd_diff(); } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 37a769d7f9fe..24b78aecc928 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -12,7 +12,7 @@ #include "util/parse-options.h" #include "util/trace-event.h" #include "util/debug.h" -#include "util/debugfs.h" +#include <lk/debugfs.h> #include "util/tool.h" #include "util/stat.h" @@ -328,6 +328,7 @@ static int kvm_events_hash_fn(u64 key) static bool kvm_event_expand(struct kvm_event *event, int vcpu_id) { int old_max_vcpu = event->max_vcpu; + void *prev; if (vcpu_id < event->max_vcpu) return true; @@ -335,9 +336,11 @@ static bool kvm_event_expand(struct kvm_event *event, int vcpu_id) while (event->max_vcpu <= vcpu_id) event->max_vcpu += DEFAULT_VCPU_NUM; + prev = event->vcpu; event->vcpu = realloc(event->vcpu, event->max_vcpu * sizeof(*event->vcpu)); if (!event->vcpu) { + free(prev); pr_err("Not enough memory\n"); return false; } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c new file mode 100644 index 000000000000..a8ff6d264e50 --- /dev/null +++ b/tools/perf/builtin-mem.c @@ -0,0 +1,242 @@ +#include "builtin.h" +#include "perf.h" + +#include "util/parse-options.h" +#include "util/trace-event.h" +#include "util/tool.h" +#include "util/session.h" + +#define MEM_OPERATION_LOAD "load" +#define MEM_OPERATION_STORE "store" + +static const char *mem_operation = MEM_OPERATION_LOAD; + +struct perf_mem { + struct perf_tool tool; + char const *input_name; + symbol_filter_t annotate_init; + bool hide_unresolved; + bool dump_raw; + const char *cpu_list; + DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); +}; + +static const char * const mem_usage[] = { + "perf mem [<options>] {record <command> |report}", + NULL +}; + +static int __cmd_record(int argc, const char **argv) +{ + int rec_argc, i = 0, j; + const char **rec_argv; + char event[64]; + int ret; + + rec_argc = argc + 4; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + if (!rec_argv) + return -1; + + rec_argv[i++] = strdup("record"); + if (!strcmp(mem_operation, MEM_OPERATION_LOAD)) + rec_argv[i++] = strdup("-W"); + rec_argv[i++] = strdup("-d"); + rec_argv[i++] = strdup("-e"); + + if (strcmp(mem_operation, MEM_OPERATION_LOAD)) + sprintf(event, "cpu/mem-stores/pp"); + else + sprintf(event, "cpu/mem-loads/pp"); + + rec_argv[i++] = strdup(event); + for (j = 1; j < argc; j++, i++) + rec_argv[i] = argv[j]; + + ret = cmd_record(i, rec_argv, NULL); + free(rec_argv); + return ret; +} + +static int +dump_raw_samples(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel __maybe_unused, + struct machine *machine) +{ + struct perf_mem *mem = container_of(tool, struct perf_mem, tool); + struct addr_location al; + const char *fmt; + + if (perf_event__preprocess_sample(event, machine, &al, sample, + mem->annotate_init) < 0) { + fprintf(stderr, "problem processing %d event, skipping it.\n", + event->header.type); + return -1; + } + + if (al.filtered || (mem->hide_unresolved && al.sym == NULL)) + return 0; + + if (al.map != NULL) + al.map->dso->hit = 1; + + if (symbol_conf.field_sep) { + fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64 + "%s0x%"PRIx64"%s%s:%s\n"; + } else { + fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64 + "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n"; + symbol_conf.field_sep = " "; + } + + printf(fmt, + sample->pid, + symbol_conf.field_sep, + sample->tid, + symbol_conf.field_sep, + event->ip.ip, + symbol_conf.field_sep, + sample->addr, + symbol_conf.field_sep, + sample->weight, + symbol_conf.field_sep, + sample->data_src, + symbol_conf.field_sep, + al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", + al.sym ? al.sym->name : "???"); + + return 0; +} + +static int process_sample_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + return dump_raw_samples(tool, event, sample, evsel, machine); +} + +static int report_raw_events(struct perf_mem *mem) +{ + int err = -EINVAL; + int ret; + struct perf_session *session = perf_session__new(input_name, O_RDONLY, + 0, false, &mem->tool); + + if (session == NULL) + return -ENOMEM; + + if (mem->cpu_list) { + ret = perf_session__cpu_bitmap(session, mem->cpu_list, + mem->cpu_bitmap); + if (ret) + goto out_delete; + } + + if (symbol__init() < 0) + return -1; + + printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); + + err = perf_session__process_events(session, &mem->tool); + if (err) + return err; + + return 0; + +out_delete: + perf_session__delete(session); + return err; +} + +static int report_events(int argc, const char **argv, struct perf_mem *mem) +{ + const char **rep_argv; + int ret, i = 0, j, rep_argc; + + if (mem->dump_raw) + return report_raw_events(mem); + + rep_argc = argc + 3; + rep_argv = calloc(rep_argc + 1, sizeof(char *)); + if (!rep_argv) + return -1; + + rep_argv[i++] = strdup("report"); + rep_argv[i++] = strdup("--mem-mode"); + rep_argv[i++] = strdup("-n"); /* display number of samples */ + + /* + * there is no weight (cost) associated with stores, so don't print + * the column + */ + if (strcmp(mem_operation, MEM_OPERATION_LOAD)) + rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked"); + + for (j = 1; j < argc; j++, i++) + rep_argv[i] = argv[j]; + + ret = cmd_report(i, rep_argv, NULL); + free(rep_argv); + return ret; +} + +int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) +{ + struct stat st; + struct perf_mem mem = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .lost = perf_event__process_lost, + .fork = perf_event__process_fork, + .build_id = perf_event__process_build_id, + .ordered_samples = true, + }, + .input_name = "perf.data", + }; + const struct option mem_options[] = { + OPT_STRING('t', "type", &mem_operation, + "type", "memory operations(load/store)"), + OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw, + "dump raw samples in ASCII"), + OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved, + "Only display entries resolved to a symbol"), + OPT_STRING('i', "input", &input_name, "file", + "input file name"), + OPT_STRING('C', "cpu", &mem.cpu_list, "cpu", + "list of cpus to profile"), + OPT_STRING('x', "field-separator", &symbol_conf.field_sep, + "separator", + "separator for columns, no spaces will be added" + " between columns '.' is reserved."), + OPT_END() + }; + + argc = parse_options(argc, argv, mem_options, mem_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation)) + usage_with_options(mem_usage, mem_options); + + if (!mem.input_name || !strlen(mem.input_name)) { + if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) + mem.input_name = "-"; + else + mem.input_name = "perf.data"; + } + + if (!strncmp(argv[0], "rec", 3)) + return __cmd_record(argc, argv); + else if (!strncmp(argv[0], "rep", 3)) + return report_events(argc, argv, &mem); + else + usage_with_options(mem_usage, mem_options); + + return 0; +} diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index de38a034b129..e8a66f9a6715 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -37,7 +37,7 @@ #include "util/strfilter.h" #include "util/symbol.h" #include "util/debug.h" -#include "util/debugfs.h" +#include <lk/debugfs.h> #include "util/parse-options.h" #include "util/probe-finder.h" #include "util/probe-event.h" diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f1a939ebc19c..fff985cf3852 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -5,8 +5,6 @@ * (or a CPU, or a PID) into the perf.data output file - for * later analysis via perf report. */ -#define _FILE_OFFSET_BITS 64 - #include "builtin.h" #include "perf.h" @@ -200,7 +198,6 @@ static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg) return; signal(signr, SIG_DFL); - kill(getpid(), signr); } static bool perf_evlist__equal(struct perf_evlist *evlist, @@ -406,6 +403,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); signal(SIGUSR1, sig_handler); + signal(SIGTERM, sig_handler); if (!output_name) { if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode)) @@ -474,7 +472,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) } if (forks) { - err = perf_evlist__prepare_workload(evsel_list, opts, argv); + err = perf_evlist__prepare_workload(evsel_list, &opts->target, + argv, opts->pipe_output, + true); if (err < 0) { pr_err("Couldn't run the workload!\n"); goto out_delete_session; @@ -953,6 +953,8 @@ const struct option record_options[] = { OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack, "branch filter mask", "branch stack filter modes", parse_branch_stack), + OPT_BOOLEAN('W', "weight", &record.opts.sample_weight, + "sample by weight (on special events only)"), OPT_END() }; @@ -964,7 +966,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) struct perf_record *rec = &record; char errbuf[BUFSIZ]; - evsel_list = perf_evlist__new(NULL, NULL); + evsel_list = perf_evlist__new(); if (evsel_list == NULL) return -ENOMEM; @@ -1026,7 +1028,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) ui__error("%s", errbuf); err = -saved_errno; - goto out_free_fd; + goto out_symbol_exit; } err = -ENOMEM; @@ -1057,6 +1059,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) } err = __cmd_record(&record, argc, argv); + + perf_evlist__munmap(evsel_list); + perf_evlist__close(evsel_list); out_free_fd: perf_evlist__delete_maps(evsel_list); out_symbol_exit: diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 96b5a7fee4bb..ca98d34cd58b 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -13,7 +13,6 @@ #include "util/annotate.h" #include "util/color.h" #include <linux/list.h> -#include "util/cache.h" #include <linux/rbtree.h> #include "util/symbol.h" #include "util/callchain.h" @@ -47,11 +46,13 @@ struct perf_report { bool show_full_info; bool show_threads; bool inverted_callchain; + bool mem_mode; struct perf_read_values show_threads_values; const char *pretty_printing_style; symbol_filter_t annotate_init; const char *cpu_list; const char *symbol_filter_str; + float min_percent; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; @@ -61,10 +62,108 @@ static int perf_report_config(const char *var, const char *value, void *cb) symbol_conf.event_group = perf_config_bool(var, value); return 0; } + if (!strcmp(var, "report.percent-limit")) { + struct perf_report *rep = cb; + rep->min_percent = strtof(value, NULL); + return 0; + } return perf_default_config(var, value, cb); } +static int perf_report__add_mem_hist_entry(struct perf_tool *tool, + struct addr_location *al, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine, + union perf_event *event) +{ + struct perf_report *rep = container_of(tool, struct perf_report, tool); + struct symbol *parent = NULL; + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + int err = 0; + struct hist_entry *he; + struct mem_info *mi, *mx; + uint64_t cost; + + if ((sort__has_parent || symbol_conf.use_callchain) && + sample->callchain) { + err = machine__resolve_callchain(machine, evsel, al->thread, + sample, &parent); + if (err) + return err; + } + + mi = machine__resolve_mem(machine, al->thread, sample, cpumode); + if (!mi) + return -ENOMEM; + + if (rep->hide_unresolved && !al->sym) + return 0; + + cost = sample->weight; + if (!cost) + cost = 1; + + /* + * must pass period=weight in order to get the correct + * sorting from hists__collapse_resort() which is solely + * based on periods. We want sorting be done on nr_events * weight + * and this is indirectly achieved by passing period=weight here + * and the he_stat__add_period() function. + */ + he = __hists__add_mem_entry(&evsel->hists, al, parent, mi, cost, cost); + if (!he) + return -ENOMEM; + + /* + * In the TUI browser, we are doing integrated annotation, + * so we don't allocate the extra space needed because the stdio + * code will not use it. + */ + if (sort__has_sym && he->ms.sym && use_browser > 0) { + struct annotation *notes = symbol__annotation(he->ms.sym); + + assert(evsel != NULL); + + if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0) + goto out; + + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (err) + goto out; + } + + if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) { + struct annotation *notes; + + mx = he->mem_info; + + notes = symbol__annotation(mx->daddr.sym); + if (notes->src == NULL && symbol__alloc_hist(mx->daddr.sym) < 0) + goto out; + + err = symbol__inc_addr_samples(mx->daddr.sym, + mx->daddr.map, + evsel->idx, + mx->daddr.al_addr); + if (err) + goto out; + } + + evsel->hists.stats.total_period += cost; + hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + err = 0; + + if (symbol_conf.use_callchain) { + err = callchain_append(he->callchain, + &callchain_cursor, + sample->period); + } +out: + return err; +} + static int perf_report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al, struct perf_sample *sample, @@ -94,15 +193,17 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, for (i = 0; i < sample->branch_stack->nr; i++) { if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym)) continue; + + err = -ENOMEM; + /* * The report shows the percentage of total branches captured * and not events sampled. Thus we use a pseudo period of 1. */ he = __hists__add_branch_entry(&evsel->hists, al, parent, - &bi[i], 1); + &bi[i], 1, 1); if (he) { struct annotation *notes; - err = -ENOMEM; bx = he->branch_info; if (bx->from.sym && use_browser == 1 && sort__has_sym) { notes = symbol__annotation(bx->from.sym); @@ -133,11 +234,12 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, } evsel->hists.stats.total_period += 1; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); - err = 0; } else - return -ENOMEM; + goto out; } + err = 0; out: + free(bi); return err; } @@ -157,7 +259,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, return err; } - he = __hists__add_entry(&evsel->hists, al, parent, sample->period); + he = __hists__add_entry(&evsel->hists, al, parent, sample->period, + sample->weight); if (he == NULL) return -ENOMEM; @@ -169,7 +272,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, return err; } /* - * Only in the newt browser we are doing integrated annotation, + * Only in the TUI browser we are doing integrated annotation, * so we don't allocated the extra space needed because the stdio * code will not use it. */ @@ -200,6 +303,7 @@ static int process_sample_event(struct perf_tool *tool, { struct perf_report *rep = container_of(tool, struct perf_report, tool); struct addr_location al; + int ret; if (perf_event__preprocess_sample(event, machine, &al, sample, rep->annotate_init) < 0) { @@ -214,22 +318,25 @@ static int process_sample_event(struct perf_tool *tool, if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) return 0; - if (sort__branch_mode == 1) { - if (perf_report__add_branch_hist_entry(tool, &al, sample, - evsel, machine)) { + if (sort__mode == SORT_MODE__BRANCH) { + ret = perf_report__add_branch_hist_entry(tool, &al, sample, + evsel, machine); + if (ret < 0) pr_debug("problem adding lbr entry, skipping event\n"); - return -1; - } + } else if (rep->mem_mode == 1) { + ret = perf_report__add_mem_hist_entry(tool, &al, sample, + evsel, machine, event); + if (ret < 0) + pr_debug("problem adding mem entry, skipping event\n"); } else { if (al.map != NULL) al.map->dso->hit = 1; - if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) { + ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine); + if (ret < 0) pr_debug("problem incrementing symbol period, skipping event\n"); - return -1; - } } - return 0; + return ret; } static int process_read_event(struct perf_tool *tool, @@ -284,7 +391,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep) } } - if (sort__branch_mode == 1) { + if (sort__mode == SORT_MODE__BRANCH) { if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_BRANCH_STACK)) { ui__error("Selected -b but no branch data. " @@ -303,7 +410,8 @@ static void sig_handler(int sig __maybe_unused) session_done = 1; } -static size_t hists__fprintf_nr_sample_events(struct hists *self, +static size_t hists__fprintf_nr_sample_events(struct perf_report *rep, + struct hists *self, const char *evname, FILE *fp) { size_t ret; @@ -314,7 +422,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, char buf[512]; size_t size = sizeof(buf); - if (symbol_conf.event_group && evsel->nr_members > 1) { + if (perf_evsel__is_group_event(evsel)) { struct perf_evsel *pos; perf_evsel__group_desc(evsel, buf, size); @@ -331,7 +439,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, if (evname != NULL) ret += fprintf(fp, " of event '%s'", evname); - ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); + if (rep->mem_mode) { + ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events); + ret += fprintf(fp, "\n# Sort order : %s", sort_order); + } else + ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); return ret + fprintf(fp, "\n#\n"); } @@ -349,8 +461,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, !perf_evsel__is_group_leader(pos)) continue; - hists__fprintf_nr_sample_events(hists, evname, stdout); - hists__fprintf(hists, true, 0, 0, stdout); + hists__fprintf_nr_sample_events(rep, hists, evname, stdout); + hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout); fprintf(stdout, "\n\n"); } @@ -469,8 +581,8 @@ static int __cmd_report(struct perf_report *rep) if (use_browser > 0) { if (use_browser == 1) { ret = perf_evlist__tui_browse_hists(session->evlist, - help, - NULL, + help, NULL, + rep->min_percent, &session->header.env); /* * Usually "ret" is the last pressed key, and we only @@ -481,7 +593,7 @@ static int __cmd_report(struct perf_report *rep) } else if (use_browser == 2) { perf_evlist__gtk_browse_hists(session->evlist, help, - NULL); + NULL, rep->min_percent); } } else perf_evlist__tty_browse_hists(session->evlist, rep, help); @@ -586,7 +698,19 @@ static int parse_branch_mode(const struct option *opt __maybe_unused, const char *str __maybe_unused, int unset) { - sort__branch_mode = !unset; + int *branch_mode = opt->value; + + *branch_mode = !unset; + return 0; +} + +static int +parse_percent_limit(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct perf_report *rep = opt->value; + + rep->min_percent = strtof(str, NULL); return 0; } @@ -595,6 +719,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) struct perf_session *session; struct stat st; bool has_br_stack = false; + int branch_mode = -1; int ret = -1; char callchain_default_opt[] = "fractal,0.5,callee"; const char * const report_usage[] = { @@ -645,7 +770,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Use the stdio interface"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline," - " dso_to, dso_from, symbol_to, symbol_from, mispredict"), + " dso_to, dso_from, symbol_to, symbol_from, mispredict," + " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, " + "snoop, locked"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", @@ -689,14 +816,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Show a column with the sum of periods"), OPT_BOOLEAN(0, "group", &symbol_conf.event_group, "Show event group information together"), - OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "", + OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "", "use branch records for histogram filling", parse_branch_mode), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, + "Disable symbol demangling"), + OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), + OPT_CALLBACK(0, "percent-limit", &report, "percent", + "Don't show entries under that percent", parse_percent_limit), OPT_END() }; - perf_config(perf_report_config, NULL); + perf_config(perf_report_config, &report); argc = parse_options(argc, argv, options, report_usage, 0); @@ -736,11 +868,11 @@ repeat: has_br_stack = perf_header__has_feat(&session->header, HEADER_BRANCH_STACK); - if (sort__branch_mode == -1 && has_br_stack) - sort__branch_mode = 1; + if (branch_mode == -1 && has_br_stack) + sort__mode = SORT_MODE__BRANCH; - /* sort__branch_mode could be 0 if --no-branch-stack */ - if (sort__branch_mode == 1) { + /* sort__mode could be NORMAL if --no-branch-stack */ + if (sort__mode == SORT_MODE__BRANCH) { /* * if no sort_order is provided, then specify * branch-mode specific order @@ -750,12 +882,26 @@ repeat: "dso_to,symbol_to"; } + if (report.mem_mode) { + if (sort__mode == SORT_MODE__BRANCH) { + fprintf(stderr, "branch and mem mode incompatible\n"); + goto error; + } + sort__mode = SORT_MODE__MEMORY; + + /* + * if no sort_order is provided, then specify + * branch-mode specific order + */ + if (sort_order == default_sort_order) + sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; + } if (setup_sorting() < 0) usage_with_options(report_usage, options); /* - * Only in the newt browser we are doing integrated annotation, + * Only in the TUI browser we are doing integrated annotation, * so don't allocate extra space that won't be used in the stdio * implementation. */ @@ -807,17 +953,7 @@ repeat: report.symbol_filter_str = argv[0]; } - sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout); - - if (sort__branch_mode == 1) { - sort_entry__setup_elide(&sort_dso_from, symbol_conf.dso_from_list, "dso_from", stdout); - sort_entry__setup_elide(&sort_dso_to, symbol_conf.dso_to_list, "dso_to", stdout); - sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout); - sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout); - } else { - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout); - sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout); - } + sort__setup_elide(stdout); ret = __cmd_report(&report); if (ret == K_SWITCH_INPUT_DATA) { diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 138229439a93..2da2a6ca22bf 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1671,7 +1671,6 @@ 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, - .exit = perf_event__process_exit, .fork = perf_event__process_fork, .ordered_samples = true, }, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 99848761f573..7e910bab1097 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -68,7 +68,7 @@ static void print_stat(int argc, const char **argv); static void print_counter_aggr(struct perf_evsel *counter, char *prefix); static void print_counter(struct perf_evsel *counter, char *prefix); -static void print_aggr_socket(char *prefix); +static void print_aggr(char *prefix); static struct perf_evlist *evsel_list; @@ -76,11 +76,17 @@ static struct perf_target target = { .uid = UINT_MAX, }; +enum aggr_mode { + AGGR_NONE, + AGGR_GLOBAL, + AGGR_SOCKET, + AGGR_CORE, +}; + static int run_count = 1; static bool no_inherit = false; static bool scale = true; -static bool no_aggr = false; -static bool aggr_socket = false; +static enum aggr_mode aggr_mode = AGGR_GLOBAL; static pid_t child_pid = -1; static bool null_run = false; static int detailed_run = 0; @@ -94,8 +100,10 @@ static const char *pre_cmd = NULL; static const char *post_cmd = NULL; static bool sync_run = false; static unsigned int interval = 0; +static bool forever = false; static struct timespec ref_time; -static struct cpu_map *sock_map; +static struct cpu_map *aggr_map; +static int (*aggr_get_id)(struct cpu_map *m, int cpu); static volatile int done = 0; @@ -125,6 +133,11 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) return perf_evsel__cpus(evsel)->nr; } +static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +{ + memset(evsel->priv, 0, sizeof(struct perf_stat)); +} + static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat)); @@ -160,6 +173,35 @@ static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) evsel->prev_raw_counts = NULL; } +static void perf_evlist__free_stats(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + perf_evsel__free_stat_priv(evsel); + perf_evsel__free_counts(evsel); + perf_evsel__free_prev_raw_counts(evsel); + } +} + +static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (perf_evsel__alloc_stat_priv(evsel) < 0 || + perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 || + (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0)) + goto out_free; + } + + return 0; + +out_free: + perf_evlist__free_stats(evlist); + return -1; +} + static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; static struct stats runtime_cycles_stats[MAX_NR_CPUS]; static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS]; @@ -173,6 +215,29 @@ static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS]; static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS]; static struct stats walltime_nsecs_stats; +static void perf_stat__reset_stats(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + perf_evsel__reset_stat_priv(evsel); + perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel)); + } + + memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats)); + memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats)); + memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats)); + memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats)); + memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats)); + memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats)); + memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats)); + memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats)); + memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats)); + memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats)); + memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats)); + memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); +} + static int create_perf_stat_counter(struct perf_evsel *evsel) { struct perf_event_attr *attr = &evsel->attr; @@ -249,7 +314,7 @@ static int read_counter_aggr(struct perf_evsel *counter) int i; if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter), - evsel_list->threads->nr, scale) < 0) + thread_map__nr(evsel_list->threads), scale) < 0) return -1; for (i = 0; i < 3; i++) @@ -297,56 +362,68 @@ static void print_interval(void) struct timespec ts, rs; char prefix[64]; - if (no_aggr) { + if (aggr_mode == AGGR_GLOBAL) { list_for_each_entry(counter, &evsel_list->entries, node) { ps = counter->priv; memset(ps->res_stats, 0, sizeof(ps->res_stats)); - read_counter(counter); + read_counter_aggr(counter); } - } else { + } else { list_for_each_entry(counter, &evsel_list->entries, node) { ps = counter->priv; memset(ps->res_stats, 0, sizeof(ps->res_stats)); - read_counter_aggr(counter); + read_counter(counter); } } + clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep); if (num_print_interval == 0 && !csv_output) { - if (aggr_socket) + switch (aggr_mode) { + case AGGR_SOCKET: fprintf(output, "# time socket cpus counts events\n"); - else if (no_aggr) + break; + case AGGR_CORE: + fprintf(output, "# time core cpus counts events\n"); + break; + case AGGR_NONE: fprintf(output, "# time CPU counts events\n"); - else + break; + case AGGR_GLOBAL: + default: fprintf(output, "# time counts events\n"); + } } if (++num_print_interval == 25) num_print_interval = 0; - if (aggr_socket) - print_aggr_socket(prefix); - else if (no_aggr) { + switch (aggr_mode) { + case AGGR_CORE: + case AGGR_SOCKET: + print_aggr(prefix); + break; + case AGGR_NONE: list_for_each_entry(counter, &evsel_list->entries, node) print_counter(counter, prefix); - } else { + break; + case AGGR_GLOBAL: + default: list_for_each_entry(counter, &evsel_list->entries, node) print_counter_aggr(counter, prefix); } } -static int __run_perf_stat(int argc __maybe_unused, const char **argv) +static int __run_perf_stat(int argc, const char **argv) { char msg[512]; unsigned long long t0, t1; struct perf_evsel *counter; struct timespec ts; int status = 0; - int child_ready_pipe[2], go_pipe[2]; const bool forks = (argc > 0); - char buf; if (interval) { ts.tv_sec = interval / 1000; @@ -356,61 +433,12 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv) ts.tv_nsec = 0; } - if (aggr_socket - && cpu_map__build_socket_map(evsel_list->cpus, &sock_map)) { - perror("cannot build socket map"); - return -1; - } - - if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) { - perror("failed to create pipes"); - return -1; - } - if (forks) { - if ((child_pid = fork()) < 0) - perror("failed to fork"); - - if (!child_pid) { - close(child_ready_pipe[0]); - close(go_pipe[1]); - fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); - - /* - * Do a dummy execvp to get the PLT entry resolved, - * so we avoid the resolver overhead on the real - * execvp call. - */ - execvp("", (char **)argv); - - /* - * Tell the parent we're ready to go - */ - close(child_ready_pipe[1]); - - /* - * Wait until the parent tells us to go. - */ - if (read(go_pipe[0], &buf, 1) == -1) - perror("unable to read pipe"); - - execvp(argv[0], (char **)argv); - - perror(argv[0]); - exit(-1); + if (perf_evlist__prepare_workload(evsel_list, &target, argv, + false, false) < 0) { + perror("failed to prepare workload"); + return -1; } - - if (perf_target__none(&target)) - evsel_list->threads->map[0] = child_pid; - - /* - * Wait for the child to be ready to exec. - */ - close(child_ready_pipe[1]); - close(go_pipe[0]); - if (read(child_ready_pipe[0], &buf, 1) == -1) - perror("unable to read pipe"); - close(child_ready_pipe[0]); } if (group) @@ -457,7 +485,8 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv) clock_gettime(CLOCK_MONOTONIC, &ref_time); if (forks) { - close(go_pipe[1]); + perf_evlist__start_workload(evsel_list); + if (interval) { while (!waitpid(child_pid, &status, WNOHANG)) { nanosleep(&ts, NULL); @@ -479,16 +508,16 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv) update_stats(&walltime_nsecs_stats, t1 - t0); - if (no_aggr) { + if (aggr_mode == AGGR_GLOBAL) { list_for_each_entry(counter, &evsel_list->entries, node) { - read_counter(counter); - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1); + read_counter_aggr(counter); + perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), + thread_map__nr(evsel_list->threads)); } } else { list_for_each_entry(counter, &evsel_list->entries, node) { - read_counter_aggr(counter); - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), - evsel_list->threads->nr); + read_counter(counter); + perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1); } } @@ -542,26 +571,47 @@ static void print_noise(struct perf_evsel *evsel, double avg) print_noise_pct(stddev_stats(&ps->res_stats[0]), avg); } -static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) +static void aggr_printout(struct perf_evsel *evsel, int id, int nr) { - double msecs = avg / 1e6; - char cpustr[16] = { '\0', }; - const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s"; - - if (aggr_socket) - sprintf(cpustr, "S%*d%s%*d%s", + switch (aggr_mode) { + case AGGR_CORE: + fprintf(output, "S%d-C%*d%s%*d%s", + cpu_map__id_to_socket(id), + csv_output ? 0 : -8, + cpu_map__id_to_cpu(id), + csv_sep, + csv_output ? 0 : 4, + nr, + csv_sep); + break; + case AGGR_SOCKET: + fprintf(output, "S%*d%s%*d%s", csv_output ? 0 : -5, - cpu, + id, csv_sep, csv_output ? 0 : 4, nr, csv_sep); - else if (no_aggr) - sprintf(cpustr, "CPU%*d%s", + break; + case AGGR_NONE: + fprintf(output, "CPU%*d%s", csv_output ? 0 : -4, - perf_evsel__cpus(evsel)->map[cpu], csv_sep); + perf_evsel__cpus(evsel)->map[id], csv_sep); + break; + case AGGR_GLOBAL: + default: + break; + } +} + +static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) +{ + double msecs = avg / 1e6; + const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s"; + + aggr_printout(evsel, cpu, nr); - fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel)); + fprintf(output, fmt, msecs, csv_sep, perf_evsel__name(evsel)); if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); @@ -758,32 +808,21 @@ static void print_ll_cache_misses(int cpu, static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) { double total, ratio = 0.0; - char cpustr[16] = { '\0', }; const char *fmt; if (csv_output) - fmt = "%s%.0f%s%s"; + fmt = "%.0f%s%s"; else if (big_num) - fmt = "%s%'18.0f%s%-25s"; + fmt = "%'18.0f%s%-25s"; else - fmt = "%s%18.0f%s%-25s"; + fmt = "%18.0f%s%-25s"; - if (aggr_socket) - sprintf(cpustr, "S%*d%s%*d%s", - csv_output ? 0 : -5, - cpu, - csv_sep, - csv_output ? 0 : 4, - nr, - csv_sep); - else if (no_aggr) - sprintf(cpustr, "CPU%*d%s", - csv_output ? 0 : -4, - perf_evsel__cpus(evsel)->map[cpu], csv_sep); - else + aggr_printout(evsel, cpu, nr); + + if (aggr_mode == AGGR_GLOBAL) cpu = 0; - fprintf(output, fmt, cpustr, avg, csv_sep, perf_evsel__name(evsel)); + fprintf(output, fmt, avg, csv_sep, perf_evsel__name(evsel)); if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); @@ -882,23 +921,23 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) } } -static void print_aggr_socket(char *prefix) +static void print_aggr(char *prefix) { struct perf_evsel *counter; + int cpu, s, s2, id, nr; u64 ena, run, val; - int cpu, s, s2, sock, nr; - if (!sock_map) + if (!(aggr_map || aggr_get_id)) return; - for (s = 0; s < sock_map->nr; s++) { - sock = cpu_map__socket(sock_map, s); + for (s = 0; s < aggr_map->nr; s++) { + id = aggr_map->map[s]; list_for_each_entry(counter, &evsel_list->entries, node) { val = ena = run = 0; nr = 0; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - s2 = cpu_map__get_socket(evsel_list->cpus, cpu); - if (s2 != sock) + s2 = aggr_get_id(evsel_list->cpus, cpu); + if (s2 != id) continue; val += counter->counts->cpu[cpu].val; ena += counter->counts->cpu[cpu].ena; @@ -909,18 +948,15 @@ static void print_aggr_socket(char *prefix) fprintf(output, "%s", prefix); if (run == 0 || ena == 0) { - fprintf(output, "S%*d%s%*d%s%*s%s%*s", - csv_output ? 0 : -5, - s, - csv_sep, - csv_output ? 0 : 4, - nr, - csv_sep, + aggr_printout(counter, cpu, nr); + + fprintf(output, "%*s%s%*s", csv_output ? 0 : 18, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep, csv_output ? 0 : -24, perf_evsel__name(counter)); + if (counter->cgrp) fprintf(output, "%s%s", csv_sep, counter->cgrp->name); @@ -930,9 +966,9 @@ static void print_aggr_socket(char *prefix) } if (nsec_counter(counter)) - nsec_printout(sock, nr, counter, val); + nsec_printout(id, nr, counter, val); else - abs_printout(sock, nr, counter, val); + abs_printout(id, nr, counter, val); if (!csv_output) { print_noise(counter, 1.0); @@ -1073,14 +1109,21 @@ static void print_stat(int argc, const char **argv) fprintf(output, ":\n\n"); } - if (aggr_socket) - print_aggr_socket(NULL); - else if (no_aggr) { - list_for_each_entry(counter, &evsel_list->entries, node) - print_counter(counter, NULL); - } else { + switch (aggr_mode) { + case AGGR_CORE: + case AGGR_SOCKET: + print_aggr(NULL); + break; + case AGGR_GLOBAL: list_for_each_entry(counter, &evsel_list->entries, node) print_counter_aggr(counter, NULL); + break; + case AGGR_NONE: + list_for_each_entry(counter, &evsel_list->entries, node) + print_counter(counter, NULL); + break; + default: + break; } if (!csv_output) { @@ -1126,6 +1169,32 @@ static int stat__set_big_num(const struct option *opt __maybe_unused, return 0; } +static int perf_stat_init_aggr_mode(void) +{ + switch (aggr_mode) { + case AGGR_SOCKET: + if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) { + perror("cannot build socket map"); + return -1; + } + aggr_get_id = cpu_map__get_socket; + break; + case AGGR_CORE: + if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) { + perror("cannot build core map"); + return -1; + } + aggr_get_id = cpu_map__get_core; + break; + case AGGR_NONE: + case AGGR_GLOBAL: + default: + break; + } + return 0; +} + + /* * Add default attributes, if there were no attributes specified or * if -d/--detailed, -d -d or -d -d -d is used: @@ -1296,7 +1365,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) 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)"), + "repeat command and print average + stddev (max: 100, forever: 0)"), OPT_BOOLEAN('n', "null", &null_run, "null run - dont start any counters"), OPT_INCR('d', "detailed", &detailed_run, @@ -1308,7 +1377,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) 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_SET_UINT('A', "no-aggr", &aggr_mode, + "disable CPU count aggregation", AGGR_NONE), OPT_STRING('x', "field-separator", &csv_sep, "separator", "print counts with custom separator"), OPT_CALLBACK('G', "cgroup", &evsel_list, "name", @@ -1323,20 +1393,22 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) "command to run after to the measured command"), OPT_UINTEGER('I', "interval-print", &interval, "print counts at regular interval in ms (>= 100)"), - OPT_BOOLEAN(0, "aggr-socket", &aggr_socket, "aggregate counts per processor socket"), + OPT_SET_UINT(0, "per-socket", &aggr_mode, + "aggregate counts per processor socket", AGGR_SOCKET), + OPT_SET_UINT(0, "per-core", &aggr_mode, + "aggregate counts per physical processor core", AGGR_CORE), OPT_END() }; const char * const stat_usage[] = { "perf stat [<options>] [<command>]", NULL }; - struct perf_evsel *pos; int status = -ENOMEM, run_idx; const char *mode; setlocale(LC_ALL, ""); - evsel_list = perf_evlist__new(NULL, NULL); + evsel_list = perf_evlist__new(); if (evsel_list == NULL) return -ENOMEM; @@ -1399,23 +1471,21 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (!argc && !perf_target__has_task(&target)) usage_with_options(stat_usage, options); - if (run_count <= 0) + if (run_count < 0) { usage_with_options(stat_usage, options); + } else if (run_count == 0) { + forever = true; + run_count = 1; + } /* no_aggr, cgroup are for system-wide only */ - if ((no_aggr || nr_cgroups) && !perf_target__has_cpu(&target)) { + if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) + && !perf_target__has_cpu(&target)) { fprintf(stderr, "both cgroup and no-aggregation " "modes only available in system-wide mode\n"); usage_with_options(stat_usage, options); - } - - if (aggr_socket) { - if (!perf_target__has_cpu(&target)) { - fprintf(stderr, "--aggr-socket only available in system-wide mode (-a)\n"); - usage_with_options(stat_usage, options); - } - no_aggr = true; + return -1; } if (add_default_attributes()) @@ -1438,17 +1508,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - list_for_each_entry(pos, &evsel_list->entries, node) { - if (perf_evsel__alloc_stat_priv(pos) < 0 || - perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0) - goto out_free_fd; - } - if (interval) { - list_for_each_entry(pos, &evsel_list->entries, node) { - if (perf_evsel__alloc_prev_raw_counts(pos) < 0) - goto out_free_fd; - } - } + if (perf_evlist__alloc_stats(evsel_list, interval)) + goto out_free_maps; + + if (perf_stat_init_aggr_mode()) + goto out; /* * We dont want to block the signals - that would cause @@ -1457,28 +1521,30 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) * task, but being ignored by perf stat itself: */ atexit(sig_atexit); - signal(SIGINT, skip_signal); + if (!forever) + signal(SIGINT, skip_signal); signal(SIGCHLD, skip_signal); signal(SIGALRM, skip_signal); signal(SIGABRT, skip_signal); status = 0; - for (run_idx = 0; run_idx < run_count; run_idx++) { + for (run_idx = 0; forever || run_idx < run_count; run_idx++) { if (run_count != 1 && verbose) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); status = run_perf_stat(argc, argv); + if (forever && status != -1) { + print_stat(argc, argv); + perf_stat__reset_stats(evsel_list); + } } - if (status != -1 && !interval) + if (!forever && status != -1 && !interval) print_stat(argc, argv); -out_free_fd: - list_for_each_entry(pos, &evsel_list->entries, node) { - perf_evsel__free_stat_priv(pos); - perf_evsel__free_counts(pos); - perf_evsel__free_prev_raw_counts(pos); - } + + perf_evlist__free_stats(evsel_list); +out_free_maps: perf_evlist__delete_maps(evsel_list); out: perf_evlist__delete(evsel_list); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 72f6eb7b4173..f036af9b6f09 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -70,10 +70,11 @@ static volatile int done; +#define HEADER_LINE_NR 5 + static void perf_top__update_print_entries(struct perf_top *top) { - if (top->print_entries > 9) - top->print_entries -= 9; + top->print_entries = top->winsize.ws_row - HEADER_LINE_NR; } static void perf_top__sig_winch(int sig __maybe_unused, @@ -82,13 +83,6 @@ static void perf_top__sig_winch(int sig __maybe_unused, struct perf_top *top = arg; get_term_dimensions(&top->winsize); - if (!top->print_entries - || (top->print_entries+4) > top->winsize.ws_row) { - top->print_entries = top->winsize.ws_row; - } else { - top->print_entries += 4; - top->winsize.ws_row = top->print_entries; - } perf_top__update_print_entries(top); } @@ -231,7 +225,7 @@ static void perf_top__show_details(struct perf_top *top) printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name); printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter); - more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel->idx, + more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, 0, top->sym_pcnt_filter, top->print_entries, 4); if (top->zero) symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx); @@ -251,7 +245,11 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel, { struct hist_entry *he; - he = __hists__add_entry(&evsel->hists, al, NULL, sample->period); + pthread_mutex_lock(&evsel->hists.lock); + he = __hists__add_entry(&evsel->hists, al, NULL, sample->period, + sample->weight); + pthread_mutex_unlock(&evsel->hists.lock); + if (he == NULL) return NULL; @@ -289,16 +287,17 @@ static void perf_top__print_sym_table(struct perf_top *top) return; } - hists__collapse_resort_threaded(&top->sym_evsel->hists); - hists__output_resort_threaded(&top->sym_evsel->hists); - hists__decay_entries_threaded(&top->sym_evsel->hists, - top->hide_user_symbols, - top->hide_kernel_symbols); + hists__collapse_resort(&top->sym_evsel->hists); + hists__output_resort(&top->sym_evsel->hists); + hists__decay_entries(&top->sym_evsel->hists, + top->hide_user_symbols, + top->hide_kernel_symbols); hists__output_recalc_col_len(&top->sym_evsel->hists, - top->winsize.ws_row - 3); + top->print_entries - printed); putchar('\n'); hists__fprintf(&top->sym_evsel->hists, false, - top->winsize.ws_row - 4 - printed, win_width, stdout); + top->print_entries - printed, win_width, + top->min_percent, stdout); } static void prompt_integer(int *target, const char *msg) @@ -476,7 +475,6 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) perf_top__sig_winch(SIGWINCH, NULL, top); sigaction(SIGWINCH, &act, NULL); } else { - perf_top__sig_winch(SIGWINCH, NULL, top); signal(SIGWINCH, SIG_DFL); } break; @@ -555,11 +553,11 @@ static void perf_top__sort_new_samples(void *arg) if (t->evlist->selected != NULL) t->sym_evsel = t->evlist->selected; - hists__collapse_resort_threaded(&t->sym_evsel->hists); - hists__output_resort_threaded(&t->sym_evsel->hists); - hists__decay_entries_threaded(&t->sym_evsel->hists, - t->hide_user_symbols, - t->hide_kernel_symbols); + hists__collapse_resort(&t->sym_evsel->hists); + hists__output_resort(&t->sym_evsel->hists); + hists__decay_entries(&t->sym_evsel->hists, + t->hide_user_symbols, + t->hide_kernel_symbols); } static void *display_thread_tui(void *arg) @@ -583,7 +581,7 @@ static void *display_thread_tui(void *arg) list_for_each_entry(pos, &top->evlist->entries, node) pos->hists.uid_filter_str = top->record_opts.target.uid_str; - perf_evlist__tui_browse_hists(top->evlist, help, &hbt, + perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, &top->session->header.env); done = 1; @@ -793,7 +791,7 @@ static void perf_event__process_sample(struct perf_tool *tool, return; } - if (top->sort_has_symbols) + if (sort__has_sym) perf_top__record_precise_ip(top, he, evsel->idx, ip); } @@ -911,9 +909,9 @@ out_err: return -1; } -static int perf_top__setup_sample_type(struct perf_top *top) +static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused) { - if (!top->sort_has_symbols) { + if (!sort__has_sym) { if (symbol_conf.use_callchain) { ui__error("Selected -g but \"sym\" not present in --sort/-s."); return -EINVAL; @@ -1024,6 +1022,16 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) return record_parse_callchain_opt(opt, arg, unset); } +static int +parse_percent_limit(const struct option *opt, const char *arg, + int unset __maybe_unused) +{ + struct perf_top *top = opt->value; + + top->min_percent = strtof(arg, NULL); + return 0; +} + int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) { int status; @@ -1088,7 +1096,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent"), + "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, @@ -1109,6 +1117,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), + OPT_CALLBACK(0, "percent-limit", &top, "percent", + "Don't show entries under that percent", parse_percent_limit), OPT_END() }; const char * const top_usage[] = { @@ -1116,7 +1126,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; - top.evlist = perf_evlist__new(NULL, NULL); + top.evlist = perf_evlist__new(); if (top.evlist == NULL) return -ENOMEM; @@ -1132,6 +1142,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (setup_sorting() < 0) usage_with_options(top_usage, options); + /* display thread wants entries to be collapsed in a different tree */ + sort__need_collapse = 1; + if (top.use_stdio) use_browser = 0; else if (top.use_tui) @@ -1199,15 +1212,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (symbol__init() < 0) return -1; - sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout); - sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout); - sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout); - - /* - * Avoid annotation data structures overhead when symbols aren't on the - * sort list. - */ - top.sort_has_symbols = sort_sym.list.next != NULL; + sort__setup_elide(stdout); get_term_dimensions(&top.winsize); if (top.print_entries == 0) { diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index d222d7fc7e96..ab3ed4af1466 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -419,7 +419,7 @@ out_dump: static int trace__run(struct trace *trace, int argc, const char **argv) { - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evlist *evlist = perf_evlist__new(); struct perf_evsel *evsel; int err = -1, i; unsigned long before; @@ -452,7 +452,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) err = trace__symbols_init(trace, evlist); if (err < 0) { printf("Problems initializing symbol libraries!\n"); - goto out_delete_evlist; + goto out_delete_maps; } perf_evlist__config(evlist, &trace->opts); @@ -461,23 +461,24 @@ static int trace__run(struct trace *trace, int argc, const char **argv) signal(SIGINT, sig_handler); if (forks) { - err = perf_evlist__prepare_workload(evlist, &trace->opts, argv); + err = perf_evlist__prepare_workload(evlist, &trace->opts.target, + argv, false, false); if (err < 0) { printf("Couldn't run the workload!\n"); - goto out_delete_evlist; + goto out_delete_maps; } } err = perf_evlist__open(evlist); if (err < 0) { printf("Couldn't create the events: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_delete_maps; } err = perf_evlist__mmap(evlist, UINT_MAX, false); if (err < 0) { printf("Couldn't mmap the events: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_close_evlist; } perf_evlist__enable(evlist); @@ -526,13 +527,6 @@ again: continue; } - if (sample.raw_data == NULL) { - printf("%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", - perf_evsel__name(evsel), sample.tid, - sample.cpu, sample.raw_size); - continue; - } - handler = evsel->handler.func; handler(trace, evsel, &sample); } @@ -540,7 +534,7 @@ again: if (trace->nr_events == before) { if (done) - goto out_delete_evlist; + goto out_unmap_evlist; poll(evlist->pollfd, evlist->nr_fds, -1); } @@ -550,6 +544,12 @@ again: goto again; +out_unmap_evlist: + perf_evlist__munmap(evlist); +out_close_evlist: + perf_evlist__close(evlist); +out_delete_maps: + perf_evlist__delete_maps(evlist); out_delete_evlist: perf_evlist__delete(evlist); out: diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 08143bd854c7..b210d62907e4 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -36,6 +36,7 @@ extern int cmd_kvm(int argc, const char **argv, const char *prefix); extern int cmd_test(int argc, const char **argv, const char *prefix); extern int cmd_trace(int argc, const char **argv, const char *prefix); extern int cmd_inject(int argc, const char **argv, const char *prefix); +extern int cmd_mem(int argc, const char **argv, const char *prefix); extern int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 3e86bbd8c2d5..0906fc401c52 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -10,17 +10,18 @@ perf-buildid-list mainporcelain common perf-diff mainporcelain common perf-evlist mainporcelain common perf-inject mainporcelain common +perf-kmem mainporcelain common +perf-kvm mainporcelain common perf-list mainporcelain common -perf-sched mainporcelain common +perf-lock mainporcelain common +perf-mem mainporcelain common +perf-probe mainporcelain full perf-record mainporcelain common perf-report mainporcelain common +perf-sched mainporcelain common +perf-script mainporcelain common perf-stat mainporcelain common +perf-test mainporcelain common perf-timechart mainporcelain common perf-top mainporcelain common perf-trace mainporcelain common -perf-script mainporcelain common -perf-probe mainporcelain full -perf-kmem mainporcelain common -perf-lock mainporcelain common -perf-kvm mainporcelain common -perf-test mainporcelain common diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile new file mode 100644 index 000000000000..f139dcd2796e --- /dev/null +++ b/tools/perf/config/Makefile @@ -0,0 +1,477 @@ +uname_M := $(shell uname -m 2>/dev/null || echo not) + +ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ + -e s/arm.*/arm/ -e s/sa110/arm/ \ + -e s/s390x/s390/ -e s/parisc64/parisc/ \ + -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ + -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ ) +NO_PERF_REGS := 1 +CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) + +# Additional ARCH settings for x86 +ifeq ($(ARCH),i386) + override ARCH := x86 + NO_PERF_REGS := 0 + LIBUNWIND_LIBS = -lunwind -lunwind-x86 +endif + +ifeq ($(ARCH),x86_64) + override ARCH := x86 + IS_X86_64 := 0 + ifeq (, $(findstring m32,$(CFLAGS))) + IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1) + endif + ifeq (${IS_X86_64}, 1) + RAW_ARCH := x86_64 + CFLAGS += -DARCH_X86_64 + ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S + endif + NO_PERF_REGS := 0 + LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 +endif + +ifeq ($(NO_PERF_REGS),0) + CFLAGS += -DHAVE_PERF_REGS +endif + +ifeq ($(src-perf),) +src-perf := $(srctree)/tools/perf +endif + +ifeq ($(obj-perf),) +obj-perf := $(objtree) +endif + +ifneq ($(obj-perf),) +obj-perf := $(abspath $(obj-perf))/ +endif + +# include ARCH specific config +-include $(src-perf)/arch/$(ARCH)/Makefile + +include $(src-perf)/config/feature-tests.mak +include $(src-perf)/config/utilities.mak + +ifeq ($(call get-executable,$(FLEX)),) + dummy := $(error Error: $(FLEX) is missing on this system, please install it) +endif + +ifeq ($(call get-executable,$(BISON)),) + dummy := $(error Error: $(BISON) is missing on this system, please install it) +endif + +# Treat warnings as errors unless directed not to +ifneq ($(WERROR),0) + CFLAGS += -Werror +endif + +ifeq ("$(origin DEBUG)", "command line") + PERF_DEBUG = $(DEBUG) +endif +ifndef PERF_DEBUG + CFLAGS += -O6 +endif + +ifdef PARSER_DEBUG + PARSER_DEBUG_BISON := -t + PARSER_DEBUG_FLEX := -d + CFLAGS += -DPARSER_DEBUG +endif + +CFLAGS += -fno-omit-frame-pointer +CFLAGS += -ggdb3 +CFLAGS += -funwind-tables +CFLAGS += -Wall +CFLAGS += -Wextra +CFLAGS += -std=gnu99 + +EXTLIBS = -lpthread -lrt -lelf -lm + +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y) + CFLAGS += -fstack-protector-all +endif + +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y) + CFLAGS += -Wstack-protector +endif + +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y) + CFLAGS += -Wvolatile-register-var +endif + +ifndef PERF_DEBUG + ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y) + CFLAGS += -D_FORTIFY_SOURCE=2 + endif +endif + +CFLAGS += -I$(src-perf)/util/include +CFLAGS += -I$(src-perf)/arch/$(ARCH)/include +CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi +CFLAGS += -I$(srctree)/arch/$(ARCH)/include +CFLAGS += -I$(srctree)/include/uapi +CFLAGS += -I$(srctree)/include + +# $(obj-perf) for generated common-cmds.h +# $(obj-perf)/util for generated bison/flex headers +ifneq ($(OUTPUT),) +CFLAGS += -I$(obj-perf)/util +CFLAGS += -I$(obj-perf) +endif + +CFLAGS += -I$(src-perf)/util +CFLAGS += -I$(src-perf) +CFLAGS += -I$(TRACE_EVENT_DIR) +CFLAGS += -I$(srctree)/tools/lib/ + +CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE + +ifndef NO_BIONIC +ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y) + BIONIC := 1 + EXTLIBS := $(filter-out -lrt,$(EXTLIBS)) + EXTLIBS := $(filter-out -lpthread,$(EXTLIBS)) +endif +endif # NO_BIONIC + +ifdef NO_LIBELF + NO_DWARF := 1 + NO_DEMANGLE := 1 + NO_LIBUNWIND := 1 +else +FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) +ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y) + FLAGS_GLIBC=$(CFLAGS) $(LDFLAGS) + ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y) + LIBC_SUPPORT := 1 + endif + ifeq ($(BIONIC),1) + LIBC_SUPPORT := 1 + endif + ifeq ($(LIBC_SUPPORT),1) + msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev); + + NO_LIBELF := 1 + NO_DWARF := 1 + NO_DEMANGLE := 1 + else + msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); + endif +else + # for linking with debug library, run like: + # make DEBUG=1 LIBDW_DIR=/opt/libdw/ + ifdef LIBDW_DIR + LIBDW_CFLAGS := -I$(LIBDW_DIR)/include + LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib + endif + + FLAGS_DWARF=$(CFLAGS) $(LIBDW_CFLAGS) -ldw -lelf $(LIBDW_LDFLAGS) $(LDFLAGS) $(EXTLIBS) + ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y) + msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); + NO_DWARF := 1 + endif # Dwarf support +endif # SOURCE_LIBELF +endif # NO_LIBELF + +ifndef NO_LIBELF +CFLAGS += -DLIBELF_SUPPORT +FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) +ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) + CFLAGS += -DLIBELF_MMAP +endif + +# include ARCH specific config +-include $(src-perf)/arch/$(ARCH)/Makefile + +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); + NO_DWARF := 1 +else + CFLAGS += -DDWARF_SUPPORT $(LIBDW_CFLAGS) + LDFLAGS += $(LIBDW_LDFLAGS) + EXTLIBS += -lelf -ldw +endif # PERF_HAVE_DWARF_REGS +endif # NO_DWARF + +endif # NO_LIBELF + +ifndef NO_LIBELF +CFLAGS += -DLIBELF_SUPPORT +FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) +ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) + CFLAGS += -DLIBELF_MMAP +endif # try-cc +endif # NO_LIBELF + +# There's only x86 (both 32 and 64) support for CFI unwind so far +ifneq ($(ARCH),x86) + NO_LIBUNWIND := 1 +endif + +ifndef NO_LIBUNWIND +# for linking with debug library, run like: +# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ +ifdef LIBUNWIND_DIR + LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include + LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib +endif + +FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS) +ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y) + msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99); + NO_LIBUNWIND := 1 +endif # Libunwind support +endif # NO_LIBUNWIND + +ifndef NO_LIBUNWIND + CFLAGS += -DLIBUNWIND_SUPPORT + EXTLIBS += $(LIBUNWIND_LIBS) + CFLAGS += $(LIBUNWIND_CFLAGS) + LDFLAGS += $(LIBUNWIND_LDFLAGS) +endif # NO_LIBUNWIND + +ifndef NO_LIBAUDIT + FLAGS_LIBAUDIT = $(CFLAGS) $(LDFLAGS) -laudit + ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y) + msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev); + NO_LIBAUDIT := 1 + else + CFLAGS += -DLIBAUDIT_SUPPORT + EXTLIBS += -laudit + endif +endif + +ifdef NO_NEWT + NO_SLANG=1 +endif + +ifndef NO_SLANG + FLAGS_SLANG=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang + ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y) + msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev); + NO_SLANG := 1 + else + # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h + CFLAGS += -I/usr/include/slang + CFLAGS += -DSLANG_SUPPORT + EXTLIBS += -lslang + endif +endif + +ifndef NO_GTK2 + FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) + ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y) + msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); + NO_GTK2 := 1 + else + ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),y) + CFLAGS += -DHAVE_GTK_INFO_BAR + endif + CFLAGS += -DGTK2_SUPPORT + CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null) + EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null) + endif +endif + +grep-libs = $(filter -l%,$(1)) +strip-libs = $(filter-out -l%,$(1)) + +ifdef NO_LIBPERL + CFLAGS += -DNO_LIBPERL +else + PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) + PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) + PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) + PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` + FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) + + ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y) + CFLAGS += -DNO_LIBPERL + NO_LIBPERL := 1 + else + LDFLAGS += $(PERL_EMBED_LDFLAGS) + EXTLIBS += $(PERL_EMBED_LIBADD) + endif +endif + +disable-python = $(eval $(disable-python_code)) +define disable-python_code + CFLAGS += -DNO_LIBPYTHON + $(if $(1),$(warning No $(1) was found)) + $(warning Python support will not be built) + NO_LIBPYTHON := 1 +endef + +override PYTHON := \ + $(call get-executable-or-default,PYTHON,python) + +ifndef PYTHON + $(call disable-python,python interpreter) +else + + PYTHON_WORD := $(call shell-wordify,$(PYTHON)) + + ifdef NO_LIBPYTHON + $(call disable-python) + else + + override PYTHON_CONFIG := \ + $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config) + + ifndef PYTHON_CONFIG + $(call disable-python,python-config tool) + else + + PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) + + PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) + PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) + PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) + PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) + FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + + ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y) + $(call disable-python,Python.h (for Python 2.x)) + else + + ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y) + $(warning Python 3 is not yet supported; please set) + $(warning PYTHON and/or PYTHON_CONFIG appropriately.) + $(warning If you also have Python 2 installed, then) + $(warning try something like:) + $(warning $(and ,)) + $(warning $(and ,) make PYTHON=python2) + $(warning $(and ,)) + $(warning Otherwise, disable Python support entirely:) + $(warning $(and ,)) + $(warning $(and ,) make NO_LIBPYTHON=1) + $(warning $(and ,)) + $(error $(and ,)) + else + LDFLAGS += $(PYTHON_EMBED_LDFLAGS) + EXTLIBS += $(PYTHON_EMBED_LIBADD) + LANG_BINDINGS += $(obj-perf)python/perf.so + endif + endif + endif + endif +endif + +ifdef NO_DEMANGLE + CFLAGS += -DNO_DEMANGLE +else + ifdef HAVE_CPLUS_DEMANGLE + EXTLIBS += -liberty + CFLAGS += -DHAVE_CPLUS_DEMANGLE + else + FLAGS_BFD=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd + has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd) + ifeq ($(has_bfd),y) + EXTLIBS += -lbfd + else + FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty + has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty) + ifeq ($(has_bfd_iberty),y) + EXTLIBS += -lbfd -liberty + else + FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz + has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz) + ifeq ($(has_bfd_iberty_z),y) + EXTLIBS += -lbfd -liberty -lz + else + FLAGS_CPLUS_DEMANGLE=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -liberty + has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle) + ifeq ($(has_cplus_demangle),y) + EXTLIBS += -liberty + CFLAGS += -DHAVE_CPLUS_DEMANGLE + else + msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling) + CFLAGS += -DNO_DEMANGLE + endif + endif + endif + endif + endif +endif + +ifndef NO_STRLCPY + ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y) + CFLAGS += -DHAVE_STRLCPY + endif +endif + +ifndef NO_ON_EXIT + ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y) + CFLAGS += -DHAVE_ON_EXIT + endif +endif + +ifndef NO_BACKTRACE + ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y) + CFLAGS += -DBACKTRACE_SUPPORT + endif +endif + +ifndef NO_LIBNUMA + FLAGS_LIBNUMA = $(CFLAGS) $(LDFLAGS) -lnuma + ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y) + msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev); + NO_LIBNUMA := 1 + else + CFLAGS += -DLIBNUMA_SUPPORT + EXTLIBS += -lnuma + endif +endif + +# Among the variables below, these: +# perfexecdir +# template_dir +# mandir +# infodir +# htmldir +# ETC_PERFCONFIG (but not sysconfdir) +# can be specified as a relative path some/where/else; +# this is interpreted as relative to $(prefix) and "perf" at +# runtime figures out where they are based on the path to the executable. +# This can help installing the suite in a relocatable way. + +# Make the path relative to DESTDIR, not to prefix +ifndef DESTDIR +prefix = $(HOME) +endif +bindir_relative = bin +bindir = $(prefix)/$(bindir_relative) +mandir = share/man +infodir = share/info +perfexecdir = libexec/perf-core +sharedir = $(prefix)/share +template_dir = share/perf-core/templates +htmldir = share/doc/perf-doc +ifeq ($(prefix),/usr) +sysconfdir = /etc +ETC_PERFCONFIG = $(sysconfdir)/perfconfig +else +sysconfdir = $(prefix)/etc +ETC_PERFCONFIG = etc/perfconfig +endif +lib = lib + +# Shell quote (do not use $(call) to accommodate ancient setups); +ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) +DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) +bindir_SQ = $(subst ','\'',$(bindir)) +mandir_SQ = $(subst ','\'',$(mandir)) +infodir_SQ = $(subst ','\'',$(infodir)) +perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) +template_dir_SQ = $(subst ','\'',$(template_dir)) +htmldir_SQ = $(subst ','\'',$(htmldir)) +prefix_SQ = $(subst ','\'',$(prefix)) +sysconfdir_SQ = $(subst ','\'',$(sysconfdir)) + +ifneq ($(filter /%,$(firstword $(perfexecdir))),) +perfexec_instdir = $(perfexecdir) +else +perfexec_instdir = $(prefix)/$(perfexecdir) +endif +perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index b4eabb44e381..708fb8e9822a 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -61,15 +61,13 @@ int main(void) } endef -ifndef NO_NEWT -define SOURCE_NEWT -#include <newt.h> +ifndef NO_SLANG +define SOURCE_SLANG +#include <slang.h> int main(void) { - newtInit(); - newtCls(); - return newtFinished(); + return SLsmg_init_smg(); } endef endif @@ -235,4 +233,4 @@ int main(void) numa_available(); return 0; } -endef
\ No newline at end of file +endef diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 095b88207cd3..85e1aed95204 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -13,7 +13,7 @@ #include "util/quote.h" #include "util/run-command.h" #include "util/parse-events.h" -#include "util/debugfs.h" +#include <lk/debugfs.h> #include <pthread.h> const char perf_usage_string[] = @@ -60,6 +60,7 @@ static struct cmd_struct commands[] = { { "trace", cmd_trace, 0 }, #endif { "inject", cmd_inject, 0 }, + { "mem", cmd_mem, 0 }, }; struct pager_config { @@ -193,13 +194,13 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) fprintf(stderr, "No directory given for --debugfs-dir.\n"); usage(perf_usage_string); } - debugfs_set_path((*argv)[1]); + perf_debugfs_set_path((*argv)[1]); if (envchanged) *envchanged = 1; (*argv)++; (*argc)--; } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) { - debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR)); + perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR)); fprintf(stderr, "dir: %s\n", debugfs_mountpoint); if (envchanged) *envchanged = 1; @@ -461,7 +462,7 @@ int main(int argc, const char **argv) if (!cmd) cmd = "perf-help"; /* get debugfs mount point from /proc/mounts */ - debugfs_mount(NULL); + perf_debugfs_mount(NULL); /* * "perf-xxxx" is the same as "perf xxxx", but we obviously: * @@ -517,9 +518,8 @@ int main(int argc, const char **argv) while (1) { static int done_help; - static int was_alias; + int was_alias = run_argv(&argc, &argv); - was_alias = run_argv(&argc, &argv); if (errno != ENOENT) break; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 74659ecf93e0..32bd102c32b6 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -218,6 +218,7 @@ struct perf_record_opts { bool pipe_output; bool raw_samples; bool sample_address; + bool sample_weight; bool sample_time; bool period; unsigned int freq; diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index a4ffc9500023..b5740599aabd 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -15,35 +15,38 @@ kallsyms = [] def get_kallsyms_table(): global kallsyms + try: f = open("/proc/kallsyms", "r") - linecount = 0 - for line in f: - linecount = linecount+1 - f.seek(0) except: return - - j = 0 for line in f: loc = int(line.split()[0], 16) name = line.split()[2] - j = j +1 - if ((j % 100) == 0): - print "\r" + str(j) + "/" + str(linecount), - kallsyms.append({ 'loc': loc, 'name' : name}) - - print "\r" + str(j) + "/" + str(linecount) + kallsyms.append((loc, name)) kallsyms.sort() - return def get_sym(sloc): loc = int(sloc) - for i in kallsyms: - if (i['loc'] >= loc): - return (i['name'], i['loc']-loc) - return (None, 0) + + # Invariant: kallsyms[i][0] <= loc for all 0 <= i <= start + # kallsyms[i][0] > loc for all end <= i < len(kallsyms) + start, end = -1, len(kallsyms) + while end != start + 1: + pivot = (start + end) // 2 + if loc < kallsyms[pivot][0]: + end = pivot + else: + start = pivot + + # Now (start == -1 or kallsyms[start][0] <= loc) + # and (start == len(kallsyms) - 1 or loc < kallsyms[start + 1][0]) + if start >= 0: + symloc, name = kallsyms[start] + return (name, loc - symloc) + else: + return (None, 0) def print_drop_table(): print "%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT") @@ -64,7 +67,7 @@ def trace_end(): # called from perf, when it finds a correspoinding event def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, - skbaddr, protocol, location): + skbaddr, location, protocol): slocation = str(location) try: drop_log[slocation] = drop_log[slocation] + 1 diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index bdcceb886f77..00218f503b2e 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -147,10 +147,15 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, static int run_dir(const char *d, const char *perf) { + char v[] = "-vvvvv"; + int vcnt = min(verbose, (int) sizeof(v) - 1); char cmd[3*PATH_MAX]; - snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %s", - d, d, perf, verbose ? "-v" : ""); + if (verbose) + vcnt++; + + snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s", + d, d, perf, vcnt, v); return system(cmd); } @@ -173,6 +178,6 @@ int test__attr(void) !lstat(path_perf, &st)) return run_dir(path_dir, path_perf); - fprintf(stderr, " (ommitted)"); + fprintf(stderr, " (omitted)"); return 0; } diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 2f629ca485bc..c9b4b6269b51 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -24,6 +24,7 @@ class Unsup(Exception): class Event(dict): terms = [ + 'cpu', 'flags', 'type', 'size', @@ -121,7 +122,7 @@ class Test(object): parser = ConfigParser.SafeConfigParser() parser.read(path) - log.debug("running '%s'" % path) + log.warning("running '%s'" % path) self.path = path self.test_dir = options.test_dir @@ -172,7 +173,7 @@ class Test(object): self.perf, self.command, tempdir, self.args) ret = os.WEXITSTATUS(os.system(cmd)) - log.warning(" running '%s' ret %d " % (cmd, ret)) + log.info(" '%s' ret %d " % (cmd, ret)) if ret != int(self.ret): raise Unsup(self) diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 5bc3880f7be5..e9bd6391f2ae 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -2,6 +2,7 @@ fd=1 group_fd=-1 flags=0 +cpu=* type=0|1 size=96 config=0 @@ -26,8 +27,8 @@ watermark=0 precise_ip=0 mmap_data=0 sample_id_all=1 -exclude_host=0 -exclude_guest=1 +exclude_host=0|1 +exclude_guest=0|1 exclude_callchain_kernel=0 exclude_callchain_user=0 wakeup_events=0 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index 4bd79a82784f..91cd48b399f3 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -2,6 +2,7 @@ fd=1 group_fd=-1 flags=0 +cpu=* type=0 size=96 config=0 @@ -26,8 +27,8 @@ watermark=0 precise_ip=0 mmap_data=0 sample_id_all=0 -exclude_host=0 -exclude_guest=1 +exclude_host=0|1 +exclude_guest=0|1 exclude_callchain_kernel=0 exclude_callchain_user=0 wakeup_events=0 diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0 new file mode 100644 index 000000000000..d6a7e43f61b3 --- /dev/null +++ b/tools/perf/tests/attr/test-record-C0 @@ -0,0 +1,13 @@ +[config] +command = record +args = -C 0 kill >/dev/null 2>&1 + +[event:base-record] +cpu=0 + +# no enable on exec for CPU attached +enable_on_exec=0 + +# PERF_SAMPLE_IP | PERF_SAMPLE_TID PERF_SAMPLE_TIME | # PERF_SAMPLE_PERIOD +# + PERF_SAMPLE_CPU added by -C 0 +sample_type=391 diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data index 6627c3e7534a..716e143b5291 100644 --- a/tools/perf/tests/attr/test-record-data +++ b/tools/perf/tests/attr/test-record-data @@ -4,5 +4,8 @@ args = -d kill >/dev/null 2>&1 [event:base-record] sample_period=4000 -sample_type=271 + +# sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME | +# PERF_SAMPLE_ADDR | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC +sample_type=33039 mmap_data=1 diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0 new file mode 100644 index 000000000000..aa835950751f --- /dev/null +++ b/tools/perf/tests/attr/test-stat-C0 @@ -0,0 +1,9 @@ +[config] +command = stat +args = -e cycles -C 0 kill >/dev/null 2>&1 +ret = 1 + +[event:base-stat] +# events are enabled by default when attached to cpu +disabled=0 +enable_on_exec=0 diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c new file mode 100644 index 000000000000..aba095489193 --- /dev/null +++ b/tools/perf/tests/bp_signal.c @@ -0,0 +1,192 @@ +/* + * Inspired by breakpoint overflow test done by + * Vince Weaver <vincent.weaver@maine.edu> for perf_event_tests + * (git://github.com/deater/perf_event_tests) + */ + +/* + * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select + * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu. + */ +#define __SANE_USERSPACE_TYPES__ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include <sys/ioctl.h> +#include <time.h> +#include <fcntl.h> +#include <signal.h> +#include <sys/mman.h> +#include <linux/compiler.h> +#include <linux/hw_breakpoint.h> + +#include "tests.h" +#include "debug.h" +#include "perf.h" + +static int fd1; +static int fd2; +static int overflows; + +__attribute__ ((noinline)) +static int test_function(void) +{ + return time(NULL); +} + +static void sig_handler(int signum __maybe_unused, + siginfo_t *oh __maybe_unused, + void *uc __maybe_unused) +{ + overflows++; + + if (overflows > 10) { + /* + * This should be executed only once during + * this test, if we are here for the 10th + * time, consider this the recursive issue. + * + * We can get out of here by disable events, + * so no new SIGIO is delivered. + */ + ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + } +} + +static int bp_event(void *fn, int setup_signal) +{ + struct perf_event_attr pe; + int fd; + + memset(&pe, 0, sizeof(struct perf_event_attr)); + pe.type = PERF_TYPE_BREAKPOINT; + pe.size = sizeof(struct perf_event_attr); + + pe.config = 0; + pe.bp_type = HW_BREAKPOINT_X; + pe.bp_addr = (unsigned long) fn; + pe.bp_len = sizeof(long); + + pe.sample_period = 1; + pe.sample_type = PERF_SAMPLE_IP; + pe.wakeup_events = 1; + + pe.disabled = 1; + pe.exclude_kernel = 1; + pe.exclude_hv = 1; + + fd = sys_perf_event_open(&pe, 0, -1, -1, 0); + if (fd < 0) { + pr_debug("failed opening event %llx\n", pe.config); + return TEST_FAIL; + } + + if (setup_signal) { + fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC); + fcntl(fd, F_SETSIG, SIGIO); + fcntl(fd, F_SETOWN, getpid()); + } + + ioctl(fd, PERF_EVENT_IOC_RESET, 0); + + return fd; +} + +static long long bp_count(int fd) +{ + long long count; + int ret; + + ret = read(fd, &count, sizeof(long long)); + if (ret != sizeof(long long)) { + pr_debug("failed to read: %d\n", ret); + return TEST_FAIL; + } + + return count; +} + +int test__bp_signal(void) +{ + struct sigaction sa; + long long count1, count2; + + /* setup SIGIO signal handler */ + memset(&sa, 0, sizeof(struct sigaction)); + sa.sa_sigaction = (void *) sig_handler; + sa.sa_flags = SA_SIGINFO; + + if (sigaction(SIGIO, &sa, NULL) < 0) { + pr_debug("failed setting up signal handler\n"); + return TEST_FAIL; + } + + /* + * We create following events: + * + * fd1 - breakpoint event on test_function with SIGIO + * signal configured. We should get signal + * notification each time the breakpoint is hit + * + * fd2 - breakpoint event on sig_handler without SIGIO + * configured. + * + * Following processing should happen: + * - execute test_function + * - fd1 event breakpoint hit -> count1 == 1 + * - SIGIO is delivered -> overflows == 1 + * - fd2 event breakpoint hit -> count2 == 1 + * + * The test case check following error conditions: + * - we get stuck in signal handler because of debug + * exception being triggered receursively due to + * the wrong RF EFLAG management + * + * - we never trigger the sig_handler breakpoint due + * to the rong RF EFLAG management + * + */ + + fd1 = bp_event(test_function, 1); + fd2 = bp_event(sig_handler, 0); + + ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0); + ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0); + + /* + * Kick off the test by trigering 'fd1' + * breakpoint. + */ + test_function(); + + ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0); + ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0); + + count1 = bp_count(fd1); + count2 = bp_count(fd2); + + close(fd1); + close(fd2); + + pr_debug("count1 %lld, count2 %lld, overflow %d\n", + count1, count2, overflows); + + if (count1 != 1) { + if (count1 == 11) + pr_debug("failed: RF EFLAG recursion issue detected\n"); + else + pr_debug("failed: wrong count for bp1%lld\n", count1); + } + + if (overflows != 1) + pr_debug("failed: wrong overflow hit\n"); + + if (count2 != 1) + pr_debug("failed: wrong count for bp2\n"); + + return count1 == 1 && overflows == 1 && count2 == 1 ? + TEST_OK : TEST_FAIL; +} diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c new file mode 100644 index 000000000000..44ac82179708 --- /dev/null +++ b/tools/perf/tests/bp_signal_overflow.c @@ -0,0 +1,132 @@ +/* + * Originally done by Vince Weaver <vincent.weaver@maine.edu> for + * perf_event_tests (git://github.com/deater/perf_event_tests) + */ + +/* + * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select + * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu. + */ +#define __SANE_USERSPACE_TYPES__ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include <sys/ioctl.h> +#include <time.h> +#include <fcntl.h> +#include <signal.h> +#include <sys/mman.h> +#include <linux/compiler.h> +#include <linux/hw_breakpoint.h> + +#include "tests.h" +#include "debug.h" +#include "perf.h" + +static int overflows; + +__attribute__ ((noinline)) +static int test_function(void) +{ + return time(NULL); +} + +static void sig_handler(int signum __maybe_unused, + siginfo_t *oh __maybe_unused, + void *uc __maybe_unused) +{ + overflows++; +} + +static long long bp_count(int fd) +{ + long long count; + int ret; + + ret = read(fd, &count, sizeof(long long)); + if (ret != sizeof(long long)) { + pr_debug("failed to read: %d\n", ret); + return TEST_FAIL; + } + + return count; +} + +#define EXECUTIONS 10000 +#define THRESHOLD 100 + +int test__bp_signal_overflow(void) +{ + struct perf_event_attr pe; + struct sigaction sa; + long long count; + int fd, i, fails = 0; + + /* setup SIGIO signal handler */ + memset(&sa, 0, sizeof(struct sigaction)); + sa.sa_sigaction = (void *) sig_handler; + sa.sa_flags = SA_SIGINFO; + + if (sigaction(SIGIO, &sa, NULL) < 0) { + pr_debug("failed setting up signal handler\n"); + return TEST_FAIL; + } + + memset(&pe, 0, sizeof(struct perf_event_attr)); + pe.type = PERF_TYPE_BREAKPOINT; + pe.size = sizeof(struct perf_event_attr); + + pe.config = 0; + pe.bp_type = HW_BREAKPOINT_X; + pe.bp_addr = (unsigned long) test_function; + pe.bp_len = sizeof(long); + + pe.sample_period = THRESHOLD; + pe.sample_type = PERF_SAMPLE_IP; + pe.wakeup_events = 1; + + pe.disabled = 1; + pe.exclude_kernel = 1; + pe.exclude_hv = 1; + + fd = sys_perf_event_open(&pe, 0, -1, -1, 0); + if (fd < 0) { + pr_debug("failed opening event %llx\n", pe.config); + return TEST_FAIL; + } + + fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC); + fcntl(fd, F_SETSIG, SIGIO); + fcntl(fd, F_SETOWN, getpid()); + + ioctl(fd, PERF_EVENT_IOC_RESET, 0); + ioctl(fd, PERF_EVENT_IOC_ENABLE, 0); + + for (i = 0; i < EXECUTIONS; i++) + test_function(); + + ioctl(fd, PERF_EVENT_IOC_DISABLE, 0); + + count = bp_count(fd); + + close(fd); + + pr_debug("count %lld, overflow %d\n", + count, overflows); + + if (count != EXECUTIONS) { + pr_debug("\tWrong number of executions %lld != %d\n", + count, EXECUTIONS); + fails++; + } + + if (overflows != EXECUTIONS / THRESHOLD) { + pr_debug("\tWrong number of overflows %d != %d\n", + overflows, EXECUTIONS / THRESHOLD); + fails++; + } + + return fails ? TEST_FAIL : TEST_OK; +} diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index acb98e0e39f2..35b45f1466b5 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -70,7 +70,7 @@ static struct test { .func = test__attr, }, { - .desc = "Test matching and linking mutliple hists", + .desc = "Test matching and linking multiple hists", .func = test__hists_link, }, { @@ -78,6 +78,22 @@ static struct test { .func = test__python_use, }, { + .desc = "Test breakpoint overflow signal handler", + .func = test__bp_signal, + }, + { + .desc = "Test breakpoint overflow sampling", + .func = test__bp_signal_overflow, + }, + { + .desc = "Test number of exit event of a simple workload", + .func = test__task_exit, + }, + { + .desc = "Test software clock events have valid period values", + .func = test__sw_clock_freq, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 0fd99a9adb91..0197bda9c461 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -8,7 +8,7 @@ static int perf_evsel__roundtrip_cache_name_test(void) char name[128]; int type, op, err = 0, ret = 0, i, idx; struct perf_evsel *evsel; - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evlist *evlist = perf_evlist__new(); if (evlist == NULL) return -ENOMEM; @@ -64,7 +64,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names) { int i, err; struct perf_evsel *evsel; - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evlist *evlist = perf_evlist__new(); if (evlist == NULL) return -ENOMEM; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 1be64a6c5daf..89085a9615e2 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -223,7 +223,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) &sample, 0) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); if (he == NULL) goto out; @@ -247,7 +247,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) &sample, 0) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); if (he == NULL) goto out; @@ -436,7 +436,7 @@ int test__hists_link(void) struct machines machines; struct machine *machine = NULL; struct perf_evsel *evsel, *first; - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evlist *evlist = perf_evlist__new(); if (evlist == NULL) return -ENOMEM; diff --git a/tools/perf/tests/make b/tools/perf/tests/make new file mode 100644 index 000000000000..c441a2875128 --- /dev/null +++ b/tools/perf/tests/make @@ -0,0 +1,138 @@ +PERF := . +MK := Makefile + +# standard single make variable specified +make_clean_all := clean all +make_python_perf_so := python/perf.so +make_debug := DEBUG=1 +make_no_libperl := NO_LIBPERL=1 +make_no_libpython := NO_LIBPYTHON=1 +make_no_scripts := NO_LIBPYTHON=1 NO_LIBPERL=1 +make_no_newt := NO_NEWT=1 +make_no_slang := NO_SLANG=1 +make_no_gtk2 := NO_GTK2=1 +make_no_ui := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 +make_no_demangle := NO_DEMANGLE=1 +make_no_libelf := NO_LIBELF=1 +make_no_libunwind := NO_LIBUNWIND=1 +make_no_backtrace := NO_BACKTRACE=1 +make_no_libnuma := NO_LIBNUMA=1 +make_no_libaudit := NO_LIBAUDIT=1 +make_no_libbionic := NO_LIBBIONIC=1 +make_tags := tags +make_cscope := cscope +make_help := help +make_doc := doc +make_perf_o := perf.o +make_util_map_o := util/map.o + +# all the NO_* variable combined +make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 +make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 +make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 + +# $(run) contains all available tests +run := make_pure +run += make_clean_all +run += make_python_perf_so +run += make_debug +run += make_no_libperl +run += make_no_libpython +run += make_no_scripts +run += make_no_newt +run += make_no_slang +run += make_no_gtk2 +run += make_no_ui +run += make_no_demangle +run += make_no_libelf +run += make_no_libunwind +run += make_no_backtrace +run += make_no_libnuma +run += make_no_libaudit +run += make_no_libbionic +run += make_tags +run += make_cscope +run += make_help +run += make_doc +run += make_perf_o +run += make_util_map_o +run += make_minimal + +# $(run_O) contains same portion of $(run) tests with '_O' attached +# to distinguish O=... tests +run_O := $(addsuffix _O,$(run)) + +# disable some tests for O=... +run_O := $(filter-out make_python_perf_so_O,$(run_O)) + +# define test for each compile as 'test_NAME' variable +# with the test itself as a value +test_make_tags = test -f tags +test_make_cscope = test -f cscope.out + +test_make_tags_O := $(test_make_tags) +test_make_cscope_O := $(test_make_cscope) + +test_ok := true +test_make_help := $(test_ok) +test_make_doc := $(test_ok) +test_make_help_O := $(test_ok) +test_make_doc_O := $(test_ok) + +test_make_python_perf_so := test -f $(PERF)/python/perf.so + +test_make_perf_o := test -f $(PERF)/perf.o +test_make_util_map_o := test -f $(PERF)/util/map.o + +# Kbuild tests only +#test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so +#test_make_perf_o_O := test -f $$TMP/tools/perf/perf.o +#test_make_util_map_o_O := test -f $$TMP/tools/perf/util/map.o + +test_make_perf_o_O := true +test_make_util_map_o_O := true + +test_default = test -x $(PERF)/perf +test = $(if $(test_$1),$(test_$1),$(test_default)) + +test_default_O = test -x $$TMP/perf +test_O = $(if $(test_$1),$(test_$1),$(test_default_O)) + +all: + +ifdef DEBUG +d := $(info run $(run)) +d := $(info run_O $(run_O)) +endif + +MAKEFLAGS := --no-print-directory + +clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null) + +$(run): + $(call clean) + @cmd="cd $(PERF) && make -f $(MK) $($@)"; \ + echo "- $@: $$cmd" && echo $$cmd > $@ && \ + ( eval $$cmd ) >> $@ 2>&1; \ + echo " test: $(call test,$@)"; \ + $(call test,$@) && \ + rm -f $@ + +$(run_O): + $(call clean) + @TMP=$$(mktemp -d); \ + cmd="cd $(PERF) && make -f $(MK) $($(patsubst %_O,%,$@)) O=$$TMP"; \ + echo "- $@: $$cmd" && echo $$cmd > $@ && \ + ( eval $$cmd ) >> $@ 2>&1 && \ + echo " test: $(call test_O,$@)"; \ + $(call test_O,$@) && \ + rm -f $@ && \ + rm -rf $$TMP + +all: $(run) $(run_O) + @echo OK + +out: $(run_O) + @echo OK + +.PHONY: all $(run) $(run_O) clean diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index cdd50755af51..5b1b5aba722b 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -53,12 +53,14 @@ int test__basic_mmap(void) goto out_free_cpus; } - evlist = perf_evlist__new(cpus, threads); + evlist = perf_evlist__new(); if (evlist == NULL) { pr_debug("perf_evlist__new\n"); goto out_free_cpus; } + perf_evlist__set_maps(evlist, cpus, threads); + for (i = 0; i < nsyscalls; ++i) { char name[64]; diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c index 1c52fdc1164e..fc5b9fca8b47 100644 --- a/tools/perf/tests/open-syscall-tp-fields.c +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -18,7 +18,7 @@ int test__syscall_open_tp_fields(void) }; const char *filename = "/etc/passwd"; int flags = O_RDONLY | O_DIRECTORY; - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evlist *evlist = perf_evlist__new(); struct perf_evsel *evsel; int err = -1, i, nr_events = 0, nr_polls = 0; @@ -48,13 +48,13 @@ int test__syscall_open_tp_fields(void) err = perf_evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_delete_maps; } err = perf_evlist__mmap(evlist, UINT_MAX, false); if (err < 0) { pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_close_evlist; } perf_evlist__enable(evlist); @@ -110,6 +110,10 @@ out_ok: err = 0; out_munmap: perf_evlist__munmap(evlist); +out_close_evlist: + perf_evlist__close(evlist); +out_delete_maps: + perf_evlist__delete_maps(evlist); out_delete_evlist: perf_evlist__delete(evlist); out: diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index c5636f36fe31..0275bab4ea9e 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -3,7 +3,7 @@ #include "evsel.h" #include "evlist.h" #include "sysfs.h" -#include "debugfs.h" +#include <lk/debugfs.h> #include "tests.h" #include <linux/hw_breakpoint.h> @@ -1218,7 +1218,7 @@ static int test_event(struct evlist_test *e) struct perf_evlist *evlist; int ret; - evlist = perf_evlist__new(NULL, NULL); + evlist = perf_evlist__new(); if (evlist == NULL) return -ENOMEM; @@ -1321,7 +1321,7 @@ static int test_pmu_events(void) ret = stat(path, &st); if (ret) { - pr_debug("ommiting PMU cpu events tests\n"); + pr_debug("omitting PMU cpu events tests\n"); return 0; } diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 1e8e5128d0da..72d8881873b0 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -45,7 +45,7 @@ int test__PERF_RECORD(void) }; cpu_set_t cpu_mask; size_t cpu_mask_size = sizeof(cpu_mask); - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evlist *evlist = perf_evlist__new(); struct perf_evsel *evsel; struct perf_sample sample; const char *cmd = "sleep"; @@ -93,7 +93,8 @@ int test__PERF_RECORD(void) * so that we have time to open the evlist (calling sys_perf_event_open * on all the fds) and then mmap them. */ - err = perf_evlist__prepare_workload(evlist, &opts, argv); + err = perf_evlist__prepare_workload(evlist, &opts.target, argv, + false, false); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_maps; @@ -142,7 +143,7 @@ int test__PERF_RECORD(void) err = perf_evlist__mmap(evlist, opts.mmap_pages, false); if (err < 0) { pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); - goto out_delete_maps; + goto out_close_evlist; } /* @@ -305,6 +306,8 @@ found_exit: } out_err: perf_evlist__munmap(evlist); +out_close_evlist: + perf_evlist__close(evlist); out_delete_maps: perf_evlist__delete_maps(evlist); out_delete_evlist: diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c new file mode 100644 index 000000000000..2e41e2d32ccc --- /dev/null +++ b/tools/perf/tests/sw-clock.c @@ -0,0 +1,119 @@ +#include <unistd.h> +#include <stdlib.h> +#include <signal.h> +#include <sys/mman.h> + +#include "tests.h" +#include "util/evsel.h" +#include "util/evlist.h" +#include "util/cpumap.h" +#include "util/thread_map.h" + +#define NR_LOOPS 1000000 + +/* + * This test will open software clock events (cpu-clock, task-clock) + * then check their frequency -> period conversion has no artifact of + * setting period to 1 forcefully. + */ +static int __test__sw_clock_freq(enum perf_sw_ids clock_id) +{ + int i, err = -1; + volatile int tmp = 0; + u64 total_periods = 0; + int nr_samples = 0; + union perf_event *event; + struct perf_evsel *evsel; + struct perf_evlist *evlist; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = clock_id, + .sample_type = PERF_SAMPLE_PERIOD, + .exclude_kernel = 1, + .disabled = 1, + .freq = 1, + }; + + attr.sample_freq = 10000; + + evlist = perf_evlist__new(); + if (evlist == NULL) { + pr_debug("perf_evlist__new\n"); + return -1; + } + + evsel = perf_evsel__new(&attr, 0); + if (evsel == NULL) { + pr_debug("perf_evsel__new\n"); + goto out_free_evlist; + } + perf_evlist__add(evlist, evsel); + + evlist->cpus = cpu_map__dummy_new(); + evlist->threads = thread_map__new_by_tid(getpid()); + if (!evlist->cpus || !evlist->threads) { + err = -ENOMEM; + pr_debug("Not enough memory to create thread/cpu maps\n"); + goto out_delete_maps; + } + + perf_evlist__open(evlist); + + err = perf_evlist__mmap(evlist, 128, true); + if (err < 0) { + pr_debug("failed to mmap event: %d (%s)\n", errno, + strerror(errno)); + goto out_close_evlist; + } + + perf_evlist__enable(evlist); + + /* collect samples */ + for (i = 0; i < NR_LOOPS; i++) + tmp++; + + perf_evlist__disable(evlist); + + while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { + struct perf_sample sample; + + if (event->header.type != PERF_RECORD_SAMPLE) + continue; + + err = perf_evlist__parse_sample(evlist, event, &sample); + if (err < 0) { + pr_debug("Error during parse sample\n"); + goto out_unmap_evlist; + } + + total_periods += sample.period; + nr_samples++; + } + + if ((u64) nr_samples == total_periods) { + pr_debug("All (%d) samples have period value of 1!\n", + nr_samples); + err = -1; + } + +out_unmap_evlist: + perf_evlist__munmap(evlist); +out_close_evlist: + perf_evlist__close(evlist); +out_delete_maps: + perf_evlist__delete_maps(evlist); +out_free_evlist: + perf_evlist__delete(evlist); + return err; +} + +int test__sw_clock_freq(void) +{ + int ret; + + ret = __test__sw_clock_freq(PERF_COUNT_SW_CPU_CLOCK); + if (!ret) + ret = __test__sw_clock_freq(PERF_COUNT_SW_TASK_CLOCK); + + return ret; +} diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c new file mode 100644 index 000000000000..28fe5894b061 --- /dev/null +++ b/tools/perf/tests/task-exit.c @@ -0,0 +1,123 @@ +#include "evlist.h" +#include "evsel.h" +#include "thread_map.h" +#include "cpumap.h" +#include "tests.h" + +#include <signal.h> + +static int exited; +static int nr_exit; + +static void sig_handler(int sig) +{ + exited = 1; + + if (sig == SIGUSR1) + nr_exit = -1; +} + +/* + * This test will start a workload that does nothing then it checks + * if the number of exit event reported by the kernel is 1 or not + * in order to check the kernel returns correct number of event. + */ +int test__task_exit(void) +{ + int err = -1; + union perf_event *event; + struct perf_evsel *evsel; + struct perf_evlist *evlist; + struct perf_target target = { + .uid = UINT_MAX, + .uses_mmap = true, + }; + const char *argv[] = { "true", NULL }; + + signal(SIGCHLD, sig_handler); + signal(SIGUSR1, sig_handler); + + evlist = perf_evlist__new(); + if (evlist == NULL) { + pr_debug("perf_evlist__new\n"); + return -1; + } + /* + * We need at least one evsel in the evlist, use the default + * one: "cycles". + */ + err = perf_evlist__add_default(evlist); + if (err < 0) { + pr_debug("Not enough memory to create evsel\n"); + goto out_free_evlist; + } + + /* + * Create maps of threads and cpus to monitor. In this case + * we start with all threads and cpus (-1, -1) but then in + * perf_evlist__prepare_workload we'll fill in the only thread + * we're monitoring, the one forked there. + */ + evlist->cpus = cpu_map__dummy_new(); + evlist->threads = thread_map__new_by_tid(-1); + if (!evlist->cpus || !evlist->threads) { + err = -ENOMEM; + pr_debug("Not enough memory to create thread/cpu maps\n"); + goto out_delete_maps; + } + + err = perf_evlist__prepare_workload(evlist, &target, argv, false, true); + if (err < 0) { + pr_debug("Couldn't run the workload!\n"); + goto out_delete_maps; + } + + evsel = perf_evlist__first(evlist); + evsel->attr.task = 1; + evsel->attr.sample_freq = 0; + evsel->attr.inherit = 0; + evsel->attr.watermark = 0; + evsel->attr.wakeup_events = 1; + evsel->attr.exclude_kernel = 1; + + err = perf_evlist__open(evlist); + if (err < 0) { + pr_debug("Couldn't open the evlist: %s\n", strerror(-err)); + goto out_delete_maps; + } + + if (perf_evlist__mmap(evlist, 128, true) < 0) { + pr_debug("failed to mmap events: %d (%s)\n", errno, + strerror(errno)); + goto out_close_evlist; + } + + perf_evlist__start_workload(evlist); + +retry: + while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { + if (event->header.type != PERF_RECORD_EXIT) + continue; + + nr_exit++; + } + + if (!exited || !nr_exit) { + poll(evlist->pollfd, evlist->nr_fds, -1); + goto retry; + } + + if (nr_exit != 1) { + pr_debug("received %d EXIT records\n", nr_exit); + err = -1; + } + + perf_evlist__munmap(evlist); +out_close_evlist: + perf_evlist__close(evlist); +out_delete_maps: + perf_evlist__delete_maps(evlist); +out_free_evlist: + perf_evlist__delete(evlist); + return err; +} diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 5de0be1ff4b6..dd7feae2d37b 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -23,5 +23,9 @@ int test__dso_data(void); int test__parse_events(void); int test__hists_link(void); int test__python_use(void); +int test__bp_signal(void); +int test__bp_signal_overflow(void); +int test__task_exit(void); +int test__sw_clock_freq(void); #endif /* TESTS_H */ diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 809ea4632a34..bbc782e364b0 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -2,7 +2,6 @@ #include "../cache.h" #include "../../perf.h" #include "libslang.h" -#include <newt.h> #include "ui.h" #include "util.h" #include <linux/compiler.h> @@ -234,7 +233,7 @@ void ui_browser__reset_index(struct ui_browser *browser) void __ui_browser__show_title(struct ui_browser *browser, const char *title) { SLsmg_gotorc(0, 0); - ui_browser__set_color(browser, NEWT_COLORSET_ROOT); + ui_browser__set_color(browser, HE_COLORSET_ROOT); slsmg_write_nstring(title, browser->width + 1); } @@ -514,6 +513,12 @@ static struct ui_browser_colorset { .bg = "default", }, { + .colorset = HE_COLORSET_ROOT, + .name = "root", + .fg = "white", + .bg = "blue", + }, + { .name = NULL, } }; diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index af70314605e5..404ff66a3e36 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -11,6 +11,7 @@ #define HE_COLORSET_SELECTED 53 #define HE_COLORSET_CODE 54 #define HE_COLORSET_ADDR 55 +#define HE_COLORSET_ROOT 56 struct ui_browser { u64 index, top_idx; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 7dca1555c610..cc64d3f7fc36 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -8,15 +8,19 @@ #include "../../util/hist.h" #include "../../util/sort.h" #include "../../util/symbol.h" +#include "../../util/evsel.h" #include <pthread.h> -#include <newt.h> struct browser_disasm_line { struct rb_node rb_node; - double percent; u32 idx; int idx_asm; int jump_sources; + /* + * actual length of this array is saved on the nr_events field + * of the struct annotate_browser + */ + double percent[1]; }; static struct annotate_browser_opt { @@ -33,8 +37,9 @@ struct annotate_browser { struct ui_browser b; struct rb_root entries; struct rb_node *curr_hot; - struct disasm_line *selection; + struct disasm_line *selection; struct disasm_line **offsets; + int nr_events; u64 start; int nr_asm_entries; int nr_entries; @@ -94,14 +99,24 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int (!current_entry || (browser->use_navkeypressed && !browser->navkeypressed))); int width = browser->width, printed; + int i, pcnt_width = 7 * ab->nr_events; + double percent_max = 0.0; char bf[256]; - if (dl->offset != -1 && bdl->percent != 0.0) { - ui_browser__set_percent_color(browser, bdl->percent, current_entry); - slsmg_printf("%6.2f ", bdl->percent); + for (i = 0; i < ab->nr_events; i++) { + if (bdl->percent[i] > percent_max) + percent_max = bdl->percent[i]; + } + + if (dl->offset != -1 && percent_max != 0.0) { + for (i = 0; i < ab->nr_events; i++) { + ui_browser__set_percent_color(browser, bdl->percent[i], + current_entry); + slsmg_printf("%6.2f ", bdl->percent[i]); + } } else { ui_browser__set_percent_color(browser, 0, current_entry); - slsmg_write_nstring(" ", 7); + slsmg_write_nstring(" ", pcnt_width); } SLsmg_write_char(' '); @@ -111,12 +126,12 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int width += 1; if (!*dl->line) - slsmg_write_nstring(" ", width - 7); + slsmg_write_nstring(" ", width - pcnt_width); else if (dl->offset == -1) { printed = scnprintf(bf, sizeof(bf), "%*s ", ab->addr_width, " "); slsmg_write_nstring(bf, printed); - slsmg_write_nstring(dl->line, width - printed - 6); + slsmg_write_nstring(dl->line, width - printed - pcnt_width + 1); } else { u64 addr = dl->offset; int color = -1; @@ -175,7 +190,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int } disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset); - slsmg_write_nstring(bf, width - 10 - printed); + slsmg_write_nstring(bf, width - pcnt_width - 3 - printed); } if (current_entry) @@ -200,6 +215,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) unsigned int from, to; struct map_symbol *ms = ab->b.priv; struct symbol *sym = ms->sym; + u8 pcnt_width = 7; /* PLT symbols contain external offsets */ if (strstr(sym->name, "@plt")) @@ -223,57 +239,44 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) to = (u64)btarget->idx; } + pcnt_width *= ab->nr_events; + ui_browser__set_color(browser, HE_COLORSET_CODE); - __ui_browser__line_arrow(browser, 9 + ab->addr_width, from, to); + __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width, + from, to); } static unsigned int annotate_browser__refresh(struct ui_browser *browser) { + struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); int ret = ui_browser__list_head_refresh(browser); + int pcnt_width; + + pcnt_width = 7 * ab->nr_events; if (annotate_browser__opts.jump_arrows) annotate_browser__draw_current_jump(browser); ui_browser__set_color(browser, HE_COLORSET_NORMAL); - __ui_browser__vline(browser, 7, 0, browser->height - 1); + __ui_browser__vline(browser, pcnt_width, 0, browser->height - 1); return ret; } -static double disasm_line__calc_percent(struct disasm_line *dl, struct symbol *sym, int evidx) +static int disasm__cmp(struct browser_disasm_line *a, + struct browser_disasm_line *b, int nr_pcnt) { - double percent = 0.0; - - if (dl->offset != -1) { - int len = sym->end - sym->start; - unsigned int hits = 0; - struct annotation *notes = symbol__annotation(sym); - struct source_line *src_line = notes->src->lines; - struct sym_hist *h = annotation__histogram(notes, evidx); - s64 offset = dl->offset; - struct disasm_line *next; + int i; - next = disasm__get_next_ip_line(¬es->src->source, dl); - while (offset < (s64)len && - (next == NULL || offset < next->offset)) { - if (src_line) { - percent += src_line[offset].percent; - } else - hits += h->addr[offset]; - - ++offset; - } - /* - * If the percentage wasn't already calculated in - * symbol__get_source_line, do it now: - */ - if (src_line == NULL && h->sum) - percent = 100.0 * hits / h->sum; + for (i = 0; i < nr_pcnt; i++) { + if (a->percent[i] == b->percent[i]) + continue; + return a->percent[i] < b->percent[i]; } - - return percent; + return 0; } -static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl) +static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl, + int nr_events) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -282,7 +285,8 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_l while (*p != NULL) { parent = *p; l = rb_entry(parent, struct browser_disasm_line, rb_node); - if (bdl->percent < l->percent) + + if (disasm__cmp(bdl, l, nr_events)) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -331,12 +335,13 @@ static void annotate_browser__set_rb_top(struct annotate_browser *browser, } static void annotate_browser__calc_percent(struct annotate_browser *browser, - int evidx) + struct perf_evsel *evsel) { struct map_symbol *ms = browser->b.priv; struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); - struct disasm_line *pos; + struct disasm_line *pos, *next; + s64 len = symbol__size(sym); browser->entries = RB_ROOT; @@ -344,12 +349,34 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, list_for_each_entry(pos, ¬es->src->source, node) { struct browser_disasm_line *bpos = disasm_line__browser(pos); - bpos->percent = disasm_line__calc_percent(pos, sym, evidx); - if (bpos->percent < 0.01) { + const char *path = NULL; + double max_percent = 0.0; + int i; + + if (pos->offset == -1) { + RB_CLEAR_NODE(&bpos->rb_node); + continue; + } + + next = disasm__get_next_ip_line(¬es->src->source, pos); + + for (i = 0; i < browser->nr_events; i++) { + bpos->percent[i] = disasm__calc_percent(notes, + evsel->idx + i, + pos->offset, + next ? next->offset : len, + &path); + + if (max_percent < bpos->percent[i]) + max_percent = bpos->percent[i]; + } + + if (max_percent < 0.01) { RB_CLEAR_NODE(&bpos->rb_node); continue; } - disasm_rb_tree__insert(&browser->entries, bpos); + disasm_rb_tree__insert(&browser->entries, bpos, + browser->nr_events); } pthread_mutex_unlock(¬es->lock); @@ -401,7 +428,8 @@ static void annotate_browser__init_asm_mode(struct annotate_browser *browser) browser->b.nr_entries = browser->nr_asm_entries; } -static bool annotate_browser__callq(struct annotate_browser *browser, int evidx, +static bool annotate_browser__callq(struct annotate_browser *browser, + struct perf_evsel *evsel, struct hist_browser_timer *hbt) { struct map_symbol *ms = browser->b.priv; @@ -432,7 +460,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, int evidx, } pthread_mutex_unlock(¬es->lock); - symbol__tui_annotate(target, ms->map, evidx, hbt); + symbol__tui_annotate(target, ms->map, evsel, hbt); ui_browser__show_title(&browser->b, sym->name); return true; } @@ -615,7 +643,8 @@ static void annotate_browser__update_addr_width(struct annotate_browser *browser browser->addr_width += browser->jumps_width + 1; } -static int annotate_browser__run(struct annotate_browser *browser, int evidx, +static int annotate_browser__run(struct annotate_browser *browser, + struct perf_evsel *evsel, struct hist_browser_timer *hbt) { struct rb_node *nd = NULL; @@ -628,7 +657,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx, if (ui_browser__show(&browser->b, sym->name, help) < 0) return -1; - annotate_browser__calc_percent(browser, evidx); + annotate_browser__calc_percent(browser, evsel); if (browser->curr_hot) { annotate_browser__set_rb_top(browser, browser->curr_hot); @@ -641,7 +670,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx, key = ui_browser__run(&browser->b, delay_secs); if (delay_secs != 0) { - annotate_browser__calc_percent(browser, evidx); + annotate_browser__calc_percent(browser, evsel); /* * Current line focus got out of the list of most active * lines, NULL it so that if TAB|UNTAB is pressed, we @@ -657,7 +686,7 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx, hbt->timer(hbt->arg); if (delay_secs != 0) - symbol__annotate_decay_histogram(sym, evidx); + symbol__annotate_decay_histogram(sym, evsel->idx); continue; case K_TAB: if (nd != NULL) { @@ -754,7 +783,7 @@ show_help: goto show_sup_ins; goto out; } else if (!(annotate_browser__jump(browser) || - annotate_browser__callq(browser, evidx, hbt))) { + annotate_browser__callq(browser, evsel, hbt))) { show_sup_ins: ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions."); } @@ -776,10 +805,10 @@ out: return key; } -int hist_entry__tui_annotate(struct hist_entry *he, int evidx, +int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct hist_browser_timer *hbt) { - return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, hbt); + return symbol__tui_annotate(he->ms.sym, he->ms.map, evsel, hbt); } static void annotate_browser__mark_jump_targets(struct annotate_browser *browser, @@ -826,7 +855,8 @@ static inline int width_jumps(int n) return 1; } -int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, +int symbol__tui_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, struct hist_browser_timer *hbt) { struct disasm_line *pos, *n; @@ -847,6 +877,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, }, }; int ret = -1; + int nr_pcnt = 1; + size_t sizeof_bdl = sizeof(struct browser_disasm_line); if (sym == NULL) return -1; @@ -862,7 +894,12 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, return -1; } - if (symbol__annotate(sym, map, sizeof(struct browser_disasm_line)) < 0) { + if (perf_evsel__is_group_event(evsel)) { + nr_pcnt = evsel->nr_members; + sizeof_bdl += sizeof(double) * (nr_pcnt - 1); + } + + if (symbol__annotate(sym, map, sizeof_bdl) < 0) { ui__error("%s", ui_helpline__last_msg); goto out_free_offsets; } @@ -900,6 +937,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, browser.addr_width = browser.target_width = browser.min_addr_width = hex_width(size); browser.max_addr_width = hex_width(sym->end); browser.jumps_width = width_jumps(browser.max_jump_sources); + browser.nr_events = nr_pcnt; browser.b.nr_entries = browser.nr_entries; browser.b.entries = ¬es->src->source, browser.b.width += 18; /* Percentage */ @@ -909,7 +947,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, annotate_browser__update_addr_width(&browser); - ret = annotate_browser__run(&browser, evidx, hbt); + ret = annotate_browser__run(&browser, evsel, hbt); list_for_each_entry_safe(pos, n, ¬es->src->source, node) { list_del(&pos->node); disasm_line__free(pos); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index aa22704047d6..fc0bd3843d34 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2,7 +2,6 @@ #include "../libslang.h" #include <stdlib.h> #include <string.h> -#include <newt.h> #include <linux/rbtree.h> #include "../../util/evsel.h" @@ -26,7 +25,8 @@ struct hist_browser { struct map_symbol *selection; int print_seq; bool show_dso; - bool has_symbols; + float min_pcnt; + u64 nr_pcnt_entries; }; extern void hist_browser__init_hpp(void); @@ -310,6 +310,8 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser) "Or reduce the sampling frequency."); } +static void hist_browser__update_pcnt_entries(struct hist_browser *hb); + static int hist_browser__run(struct hist_browser *browser, const char *ev_name, struct hist_browser_timer *hbt) { @@ -319,6 +321,8 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, browser->b.entries = &browser->hists->entries; browser->b.nr_entries = browser->hists->nr_entries; + if (browser->min_pcnt) + browser->b.nr_entries = browser->nr_pcnt_entries; hist_browser__refresh_dimensions(browser); hists__browser_title(browser->hists, title, sizeof(title), ev_name); @@ -331,9 +335,18 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, key = ui_browser__run(&browser->b, delay_secs); switch (key) { - case K_TIMER: + case K_TIMER: { + u64 nr_entries; hbt->timer(hbt->arg); - ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries); + + if (browser->min_pcnt) { + hist_browser__update_pcnt_entries(browser); + nr_entries = browser->nr_pcnt_entries; + } else { + nr_entries = browser->hists->nr_entries; + } + + ui_browser__update_nr_entries(&browser->b, nr_entries); if (browser->hists->stats.nr_lost_warned != browser->hists->stats.nr_events[PERF_RECORD_LOST]) { @@ -345,6 +358,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, hists__browser_title(browser->hists, title, sizeof(title), ev_name); ui_browser__show_title(&browser->b, title); continue; + } case 'D': { /* Debug */ static int seq; struct hist_entry *h = rb_entry(browser->b.top, @@ -797,10 +811,15 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) for (nd = browser->top; nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + float percent = h->stat.period * 100.0 / + hb->hists->stats.total_period; if (h->filtered) continue; + if (percent < hb->min_pcnt) + continue; + row += hist_browser__show_entry(hb, h, row); if (row == browser->height) break; @@ -809,10 +828,18 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) return row; } -static struct rb_node *hists__filter_entries(struct rb_node *nd) +static struct rb_node *hists__filter_entries(struct rb_node *nd, + struct hists *hists, + float min_pcnt) { while (nd != NULL) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + float percent = h->stat.period * 100.0 / + hists->stats.total_period; + + if (percent < min_pcnt) + return NULL; + if (!h->filtered) return nd; @@ -822,11 +849,16 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd) return NULL; } -static struct rb_node *hists__filter_prev_entries(struct rb_node *nd) +static struct rb_node *hists__filter_prev_entries(struct rb_node *nd, + struct hists *hists, + float min_pcnt) { while (nd != NULL) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - if (!h->filtered) + float percent = h->stat.period * 100.0 / + hists->stats.total_period; + + if (!h->filtered && percent >= min_pcnt) return nd; nd = rb_prev(nd); @@ -841,6 +873,9 @@ static void ui_browser__hists_seek(struct ui_browser *browser, struct hist_entry *h; struct rb_node *nd; bool first = true; + struct hist_browser *hb; + + hb = container_of(browser, struct hist_browser, b); if (browser->nr_entries == 0) return; @@ -849,13 +884,15 @@ static void ui_browser__hists_seek(struct ui_browser *browser, switch (whence) { case SEEK_SET: - nd = hists__filter_entries(rb_first(browser->entries)); + nd = hists__filter_entries(rb_first(browser->entries), + hb->hists, hb->min_pcnt); break; case SEEK_CUR: nd = browser->top; goto do_offset; case SEEK_END: - nd = hists__filter_prev_entries(rb_last(browser->entries)); + nd = hists__filter_prev_entries(rb_last(browser->entries), + hb->hists, hb->min_pcnt); first = false; break; default: @@ -898,7 +935,8 @@ do_offset: break; } } - nd = hists__filter_entries(rb_next(nd)); + nd = hists__filter_entries(rb_next(nd), hb->hists, + hb->min_pcnt); if (nd == NULL) break; --offset; @@ -931,7 +969,8 @@ do_offset: } } - nd = hists__filter_prev_entries(rb_prev(nd)); + nd = hists__filter_prev_entries(rb_prev(nd), hb->hists, + hb->min_pcnt); if (nd == NULL) break; ++offset; @@ -1100,14 +1139,17 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp) { - struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries)); + struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries), + browser->hists, + browser->min_pcnt); int printed = 0; while (nd) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); printed += hist_browser__fprintf_entry(browser, h, fp); - nd = hists__filter_entries(rb_next(nd)); + nd = hists__filter_entries(rb_next(nd), browser->hists, + browser->min_pcnt); } return printed; @@ -1156,10 +1198,6 @@ static struct hist_browser *hist_browser__new(struct hists *hists) browser->b.refresh = hist_browser__refresh; browser->b.seek = ui_browser__hists_seek; browser->b.use_navkeypressed = true; - if (sort__branch_mode == 1) - browser->has_symbols = sort_sym_from.list.next != NULL; - else - browser->has_symbols = sort_sym.list.next != NULL; } return browser; @@ -1193,7 +1231,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, char buf[512]; size_t buflen = sizeof(buf); - if (symbol_conf.event_group && evsel->nr_members > 1) { + if (perf_evsel__is_group_event(evsel)) { struct perf_evsel *pos; perf_evsel__group_desc(evsel, buf, buflen); @@ -1330,11 +1368,25 @@ close_file_and_continue: return ret; } +static void hist_browser__update_pcnt_entries(struct hist_browser *hb) +{ + u64 nr_entries = 0; + struct rb_node *nd = rb_first(&hb->hists->entries); + + while (nd) { + nr_entries++; + nd = hists__filter_entries(rb_next(nd), hb->hists, + hb->min_pcnt); + } + + hb->nr_pcnt_entries = nr_entries; +} static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, const char *helpline, const char *ev_name, bool left_exits, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_session_env *env) { struct hists *hists = &evsel->hists; @@ -1351,6 +1403,11 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (browser == NULL) return -1; + if (min_pcnt) { + browser->min_pcnt = min_pcnt; + hist_browser__update_pcnt_entries(browser); + } + fstack = pstack__new(2); if (fstack == NULL) goto out; @@ -1387,7 +1444,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, */ goto out_free_stack; case 'a': - if (!browser->has_symbols) { + if (!sort__has_sym) { ui_browser__warning(&browser->b, delay_secs * 2, "Annotation is only available for symbolic views, " "include \"sym*\" in --sort to use it."); @@ -1486,10 +1543,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, continue; } - if (!browser->has_symbols) + if (!sort__has_sym) goto add_exit_option; - if (sort__branch_mode == 1) { + if (sort__mode == SORT_MODE__BRANCH) { bi = browser->he_selection->branch_info; if (browser->selection != NULL && bi && @@ -1599,7 +1656,7 @@ do_annotate: * Don't let this be freed, say, by hists__decay_entry. */ he->used = true; - err = hist_entry__tui_annotate(he, evsel->idx, hbt); + err = hist_entry__tui_annotate(he, evsel, hbt); he->used = false; /* * offer option to annotate the other branch source or target @@ -1690,6 +1747,7 @@ struct perf_evsel_menu { struct ui_browser b; struct perf_evsel *selection; bool lost_events, lost_events_warned; + float min_pcnt; struct perf_session_env *env; }; @@ -1709,7 +1767,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser, ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : HE_COLORSET_NORMAL); - if (symbol_conf.event_group && evsel->nr_members > 1) { + if (perf_evsel__is_group_event(evsel)) { struct perf_evsel *pos; ev_name = perf_evsel__group_name(evsel); @@ -1783,6 +1841,7 @@ browse_hists: ev_name = perf_evsel__name(pos); key = perf_evsel__hists_browse(pos, nr_events, help, ev_name, true, hbt, + menu->min_pcnt, menu->env); ui_browser__show_title(&menu->b, title); switch (key) { @@ -1844,6 +1903,7 @@ static bool filter_group_entries(struct ui_browser *self __maybe_unused, static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, int nr_entries, const char *help, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_session_env *env) { struct perf_evsel *pos; @@ -1857,6 +1917,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, .nr_entries = nr_entries, .priv = evlist, }, + .min_pcnt = min_pcnt, .env = env, }; @@ -1875,6 +1936,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_session_env *env) { int nr_entries = evlist->nr_entries; @@ -1886,7 +1948,8 @@ single_entry: const char *ev_name = perf_evsel__name(first); return perf_evsel__hists_browse(first, nr_entries, help, - ev_name, false, hbt, env); + ev_name, false, hbt, min_pcnt, + env); } if (symbol_conf.event_group) { @@ -1902,5 +1965,5 @@ single_entry: } return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, - hbt, env); + hbt, min_pcnt, env); } diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index 98851d55a53e..95c7cfb8f2c6 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -1,6 +1,5 @@ #include "../libslang.h" #include <elf.h> -#include <newt.h> #include <inttypes.h> #include <sys/ttydefaults.h> #include <string.h> @@ -10,41 +9,9 @@ #include "../../util/symbol.h" #include "../browser.h" #include "../helpline.h" +#include "../keysyms.h" #include "map.h" -static int ui_entry__read(const char *title, char *bf, size_t size, int width) -{ - struct newtExitStruct es; - newtComponent form, entry; - const char *result; - int err = -1; - - newtCenteredWindow(width, 1, title); - form = newtForm(NULL, NULL, 0); - if (form == NULL) - return -1; - - entry = newtEntry(0, 0, "0x", width, &result, NEWT_FLAG_SCROLL); - if (entry == NULL) - goto out_free_form; - - newtFormAddComponent(form, entry); - newtFormAddHotKey(form, NEWT_KEY_ENTER); - newtFormAddHotKey(form, NEWT_KEY_ESCAPE); - newtFormAddHotKey(form, NEWT_KEY_LEFT); - newtFormAddHotKey(form, CTRL('c')); - newtFormRun(form, &es); - - if (result != NULL) { - strncpy(bf, result, size); - err = 0; - } -out_free_form: - newtPopWindow(); - newtFormDestroy(form); - return err; -} - struct map_browser { struct ui_browser b; struct map *map; @@ -78,10 +45,11 @@ static int map_browser__search(struct map_browser *self) { char target[512]; struct symbol *sym; - int err = ui_entry__read("Search by name/addr", target, sizeof(target), 40); - - if (err) - return err; + int err = ui_browser__input_window("Search by name/addr", + "Prefix with 0x to search by address", + target, "ENTER: OK, ESC: Cancel", 0); + if (err != K_ENTER) + return -1; if (target[0] == '0' && tolower(target[1]) == 'x') { u64 addr = strtoull(target, NULL, 16); @@ -112,12 +80,20 @@ static int map_browser__run(struct map_browser *self) while (1) { key = ui_browser__run(&self->b, 0); - if (verbose && key == '/') - map_browser__search(self); - else + switch (key) { + case '/': + if (verbose) + map_browser__search(self); + default: break; + case K_LEFT: + case K_ESC: + case 'q': + case CTRL('c'): + goto out; + } } - +out: ui_browser__hide(&self->b); return key; } diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index cbbd44b0d93e..12f009e61e94 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -1,5 +1,4 @@ #include <elf.h> -#include <newt.h> #include <inttypes.h> #include <sys/ttydefaults.h> #include <string.h> diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 7d8dc581a545..f538794615db 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -1,6 +1,7 @@ #include "gtk.h" #include "util/debug.h" #include "util/annotate.h" +#include "util/evsel.h" #include "ui/helpline.h" @@ -32,7 +33,7 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, return 0; symhist = annotation__histogram(symbol__annotation(sym), evidx); - if (!symhist->addr[dl->offset]) + if (!symbol_conf.event_group && !symhist->addr[dl->offset]) return 0; percent = 100.0 * symhist->addr[dl->offset] / symhist->sum; @@ -85,7 +86,7 @@ static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl) } static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, - struct map *map, int evidx, + struct map *map, struct perf_evsel *evsel, struct hist_browser_timer *hbt __maybe_unused) { struct disasm_line *pos, *n; @@ -118,10 +119,24 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, list_for_each_entry(pos, ¬es->src->source, node) { GtkTreeIter iter; + int ret = 0; gtk_list_store_append(store, &iter); - if (perf_gtk__get_percent(s, sizeof(s), sym, pos, evidx)) + if (perf_evsel__is_group_event(evsel)) { + for (i = 0; i < evsel->nr_members; i++) { + ret += perf_gtk__get_percent(s + ret, + sizeof(s) - ret, + sym, pos, + evsel->idx + i); + ret += scnprintf(s + ret, sizeof(s) - ret, " "); + } + } else { + ret = perf_gtk__get_percent(s, sizeof(s), sym, pos, + evsel->idx); + } + + if (ret) gtk_list_store_set(store, &iter, ANN_COL__PERCENT, s, -1); if (perf_gtk__get_offset(s, sizeof(s), sym, map, pos)) gtk_list_store_set(store, &iter, ANN_COL__OFFSET, s, -1); @@ -139,7 +154,8 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, return 0; } -int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx, +int symbol__gtk_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, struct hist_browser_timer *hbt) { GtkWidget *window; @@ -206,7 +222,7 @@ int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx, gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label); - perf_gtk__annotate_symbol(scrolled_window, sym, map, evidx, hbt); + perf_gtk__annotate_symbol(scrolled_window, sym, map, evsel, hbt); return 0; } diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 1e764a8ad259..9708dd5fb8f3 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -32,21 +32,18 @@ static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, int ret; double percent = 0.0; struct hists *hists = he->hists; + struct perf_evsel *evsel = hists_to_evsel(hists); if (hists->stats.total_period) percent = 100.0 * get_field(he) / hists->stats.total_period; ret = __percent_color_snprintf(hpp->buf, hpp->size, percent); - if (symbol_conf.event_group) { + if (perf_evsel__is_group_event(evsel)) { int prev_idx, idx_delta; - struct perf_evsel *evsel = hists_to_evsel(hists); struct hist_entry *pair; int nr_members = evsel->nr_members; - if (nr_members <= 1) - return ret; - prev_idx = perf_evsel__group_idx(evsel); list_for_each_entry(pair, &he->pairs.head, pairs.node) { @@ -127,7 +124,8 @@ void perf_gtk__init_hpp(void) perf_gtk__hpp_color_overhead_guest_us; } -static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) +static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, + float min_pcnt) { struct perf_hpp_fmt *fmt; GType col_types[MAX_COLUMNS]; @@ -192,10 +190,15 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); GtkTreeIter iter; + float percent = h->stat.period * 100.0 / + hists->stats.total_period; if (h->filtered) continue; + if (percent < min_pcnt) + continue; + gtk_list_store_append(store, &iter); col_idx = 0; @@ -225,7 +228,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, - struct hist_browser_timer *hbt __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + float min_pcnt) { struct perf_evsel *pos; GtkWidget *vbox; @@ -289,7 +293,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, GTK_POLICY_AUTOMATIC, GTK_POLICY_AUTOMATIC); - perf_gtk__show_hists(scrolled_window, hists); + perf_gtk__show_hists(scrolled_window, hists, min_pcnt); tab_label = gtk_label_new(evname); diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index d671e63aa351..4bf91b09d62d 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -16,6 +16,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, { int ret; struct hists *hists = he->hists; + struct perf_evsel *evsel = hists_to_evsel(hists); if (fmt_percent) { double percent = 0.0; @@ -28,15 +29,11 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, } else ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he)); - if (symbol_conf.event_group) { + if (perf_evsel__is_group_event(evsel)) { int prev_idx, idx_delta; - struct perf_evsel *evsel = hists_to_evsel(hists); struct hist_entry *pair; int nr_members = evsel->nr_members; - if (nr_members <= 1) - return ret; - prev_idx = perf_evsel__group_idx(evsel); list_for_each_entry(pair, &he->pairs.head, pairs.node) { diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index ff1f60cf442e..ae7a75432249 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -334,7 +334,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, } size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, - int max_cols, FILE *fp) + int max_cols, float min_pcnt, FILE *fp) { struct perf_hpp_fmt *fmt; struct sort_entry *se; @@ -440,10 +440,15 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, print_entries: for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + float percent = h->stat.period * 100.0 / + hists->stats.total_period; if (h->filtered) continue; + if (percent < min_pcnt) + continue; + ret += hist_entry__fprintf(h, max_cols, hists, fp); if (max_rows && ++nr_rows >= max_rows) diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 81efa192e86c..b9401482d110 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -1,4 +1,3 @@ -#include <newt.h> #include <signal.h> #include <stdbool.h> @@ -88,13 +87,6 @@ int ui__getch(int delay_secs) return SLkp_getkey(); } -static void newt_suspend(void *d __maybe_unused) -{ - newtSuspend(); - raise(SIGTSTP); - newtResume(); -} - static void ui__signal(int sig) { ui__exit(false); @@ -106,7 +98,17 @@ int ui__init(void) { int err; - newtInit(); + SLutf8_enable(-1); + SLtt_get_terminfo(); + SLtt_get_screen_size(); + + err = SLsmg_init_smg(); + if (err < 0) + goto out; + err = SLang_init_tty(0, 0, 0); + if (err < 0) + goto out; + err = SLkp_init(); if (err < 0) { pr_err("TUI initialization failed.\n"); @@ -115,7 +117,6 @@ int ui__init(void) SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB); - newtSetSuspendCallback(newt_suspend, NULL); ui_helpline__init(); ui_browser__init(); ui_progress__init(); diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h index d86359c99907..70cb0d4eb8aa 100644 --- a/tools/perf/ui/ui.h +++ b/tools/perf/ui/ui.h @@ -12,7 +12,7 @@ extern int use_browser; void setup_browser(bool fallback_to_pager); void exit_browser(bool wait_for_ok); -#ifdef NEWT_SUPPORT +#ifdef SLANG_SUPPORT int ui__init(void); void ui__exit(bool wait_for_ok); #else diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index d33fe937e6f1..d102716c43a1 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -14,6 +14,7 @@ #include "symbol.h" #include "debug.h" #include "annotate.h" +#include "evsel.h" #include <pthread.h> #include <linux/bitops.h> @@ -602,8 +603,42 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa return NULL; } +double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, + s64 end, const char **path) +{ + struct source_line *src_line = notes->src->lines; + double percent = 0.0; + + if (src_line) { + size_t sizeof_src_line = sizeof(*src_line) + + sizeof(src_line->p) * (src_line->nr_pcnt - 1); + + while (offset < end) { + src_line = (void *)notes->src->lines + + (sizeof_src_line * offset); + + if (*path == NULL) + *path = src_line->path; + + percent += src_line->p[evidx].percent; + offset++; + } + } else { + struct sym_hist *h = annotation__histogram(notes, evidx); + unsigned int hits = 0; + + while (offset < end) + hits += h->addr[offset++]; + + if (h->sum) + percent = 100.0 * hits / h->sum; + } + + return percent; +} + static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start, - int evidx, u64 len, int min_pcnt, int printed, + struct perf_evsel *evsel, u64 len, int min_pcnt, int printed, int max_lines, struct disasm_line *queue) { static const char *prev_line; @@ -611,34 +646,37 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st if (dl->offset != -1) { const char *path = NULL; - unsigned int hits = 0; - double percent = 0.0; + double percent, max_percent = 0.0; + double *ppercents = &percent; + int i, nr_percent = 1; const char *color; struct annotation *notes = symbol__annotation(sym); - struct source_line *src_line = notes->src->lines; - struct sym_hist *h = annotation__histogram(notes, evidx); s64 offset = dl->offset; const u64 addr = start + offset; struct disasm_line *next; next = disasm__get_next_ip_line(¬es->src->source, dl); - while (offset < (s64)len && - (next == NULL || offset < next->offset)) { - if (src_line) { - if (path == NULL) - path = src_line[offset].path; - percent += src_line[offset].percent; - } else - hits += h->addr[offset]; - - ++offset; + if (perf_evsel__is_group_event(evsel)) { + nr_percent = evsel->nr_members; + ppercents = calloc(nr_percent, sizeof(double)); + if (ppercents == NULL) + return -1; } - if (src_line == NULL && h->sum) - percent = 100.0 * hits / h->sum; + for (i = 0; i < nr_percent; i++) { + percent = disasm__calc_percent(notes, + notes->src->lines ? i : evsel->idx + i, + offset, + next ? next->offset : (s64) len, + &path); + + ppercents[i] = percent; + if (percent > max_percent) + max_percent = percent; + } - if (percent < min_pcnt) + if (max_percent < min_pcnt) return -1; if (max_lines && printed >= max_lines) @@ -648,12 +686,12 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st list_for_each_entry_from(queue, ¬es->src->source, node) { if (queue == dl) break; - disasm_line__print(queue, sym, start, evidx, len, + disasm_line__print(queue, sym, start, evsel, len, 0, 0, 1, NULL); } } - color = get_percent_color(percent); + color = get_percent_color(max_percent); /* * Also color the filename and line if needed, with @@ -669,25 +707,59 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st } } - color_fprintf(stdout, color, " %7.2f", percent); + for (i = 0; i < nr_percent; i++) { + percent = ppercents[i]; + color = get_percent_color(percent); + color_fprintf(stdout, color, " %7.2f", percent); + } + printf(" : "); color_fprintf(stdout, PERF_COLOR_MAGENTA, " %" PRIx64 ":", addr); color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line); + + if (ppercents != &percent) + free(ppercents); + } else if (max_lines && printed >= max_lines) return 1; else { + int width = 8; + if (queue) return -1; + if (perf_evsel__is_group_event(evsel)) + width *= evsel->nr_members; + if (!*dl->line) - printf(" :\n"); + printf(" %*s:\n", width, " "); else - printf(" : %s\n", dl->line); + printf(" %*s: %s\n", width, " ", dl->line); } return 0; } +/* + * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw) + * which looks like following + * + * 0000000000415500 <_init>: + * 415500: sub $0x8,%rsp + * 415504: mov 0x2f5ad5(%rip),%rax # 70afe0 <_DYNAMIC+0x2f8> + * 41550b: test %rax,%rax + * 41550e: je 415515 <_init+0x15> + * 415510: callq 416e70 <__gmon_start__@plt> + * 415515: add $0x8,%rsp + * 415519: retq + * + * it will be parsed and saved into struct disasm_line as + * <offset> <name> <ops.raw> + * + * The offset will be a relative offset from the start of the symbol and -1 + * means that it's not a disassembly line so should be treated differently. + * The ops.raw part will be parsed further according to type of the instruction. + */ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, FILE *file, size_t privsize) { @@ -858,7 +930,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin struct source_line *iter; struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; - int ret; + int i, ret; while (*p != NULL) { parent = *p; @@ -866,7 +938,8 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin ret = strcmp(iter->path, src_line->path); if (ret == 0) { - iter->percent_sum += src_line->percent; + for (i = 0; i < src_line->nr_pcnt; i++) + iter->p[i].percent_sum += src_line->p[i].percent; return; } @@ -876,12 +949,26 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin p = &(*p)->rb_right; } - src_line->percent_sum = src_line->percent; + for (i = 0; i < src_line->nr_pcnt; i++) + src_line->p[i].percent_sum = src_line->p[i].percent; rb_link_node(&src_line->node, parent, p); rb_insert_color(&src_line->node, root); } +static int cmp_source_line(struct source_line *a, struct source_line *b) +{ + int i; + + for (i = 0; i < a->nr_pcnt; i++) { + if (a->p[i].percent_sum == b->p[i].percent_sum) + continue; + return a->p[i].percent_sum > b->p[i].percent_sum; + } + + return 0; +} + static void __resort_source_line(struct rb_root *root, struct source_line *src_line) { struct source_line *iter; @@ -892,7 +979,7 @@ static void __resort_source_line(struct rb_root *root, struct source_line *src_l parent = *p; iter = rb_entry(parent, struct source_line, node); - if (src_line->percent_sum > iter->percent_sum) + if (cmp_source_line(src_line, iter)) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -924,32 +1011,52 @@ static void symbol__free_source_line(struct symbol *sym, int len) { struct annotation *notes = symbol__annotation(sym); struct source_line *src_line = notes->src->lines; + size_t sizeof_src_line; int i; - for (i = 0; i < len; i++) - free(src_line[i].path); + sizeof_src_line = sizeof(*src_line) + + (sizeof(src_line->p) * (src_line->nr_pcnt - 1)); + + for (i = 0; i < len; i++) { + free(src_line->path); + src_line = (void *)src_line + sizeof_src_line; + } - free(src_line); + free(notes->src->lines); notes->src->lines = NULL; } /* Get the filename:line for the colored entries */ static int symbol__get_source_line(struct symbol *sym, struct map *map, - int evidx, struct rb_root *root, int len, + struct perf_evsel *evsel, + struct rb_root *root, int len, const char *filename) { u64 start; - int i; + int i, k; + int evidx = evsel->idx; char cmd[PATH_MAX * 2]; struct source_line *src_line; struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evidx); struct rb_root tmp_root = RB_ROOT; + int nr_pcnt = 1; + u64 h_sum = h->sum; + size_t sizeof_src_line = sizeof(struct source_line); + + if (perf_evsel__is_group_event(evsel)) { + for (i = 1; i < evsel->nr_members; i++) { + h = annotation__histogram(notes, evidx + i); + h_sum += h->sum; + } + nr_pcnt = evsel->nr_members; + sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p); + } - if (!h->sum) + if (!h_sum) return 0; - src_line = notes->src->lines = calloc(len, sizeof(struct source_line)); + src_line = notes->src->lines = calloc(len, sizeof_src_line); if (!notes->src->lines) return -1; @@ -960,29 +1067,41 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, size_t line_len; u64 offset; FILE *fp; + double percent_max = 0.0; - src_line[i].percent = 100.0 * h->addr[i] / h->sum; - if (src_line[i].percent <= 0.5) - continue; + src_line->nr_pcnt = nr_pcnt; + + for (k = 0; k < nr_pcnt; k++) { + h = annotation__histogram(notes, evidx + k); + src_line->p[k].percent = 100.0 * h->addr[i] / h->sum; + + if (src_line->p[k].percent > percent_max) + percent_max = src_line->p[k].percent; + } + + if (percent_max <= 0.5) + goto next; offset = start + i; sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset); fp = popen(cmd, "r"); if (!fp) - continue; + goto next; if (getline(&path, &line_len, fp) < 0 || !line_len) - goto next; + goto next_close; - src_line[i].path = malloc(sizeof(char) * line_len + 1); - if (!src_line[i].path) - goto next; + src_line->path = malloc(sizeof(char) * line_len + 1); + if (!src_line->path) + goto next_close; - strcpy(src_line[i].path, path); - insert_source_line(&tmp_root, &src_line[i]); + strcpy(src_line->path, path); + insert_source_line(&tmp_root, src_line); - next: + next_close: pclose(fp); + next: + src_line = (void *)src_line + sizeof_src_line; } resort_source_line(root, &tmp_root); @@ -1004,24 +1123,33 @@ static void print_summary(struct rb_root *root, const char *filename) node = rb_first(root); while (node) { - double percent; + double percent, percent_max = 0.0; const char *color; char *path; + int i; src_line = rb_entry(node, struct source_line, node); - percent = src_line->percent_sum; - color = get_percent_color(percent); + for (i = 0; i < src_line->nr_pcnt; i++) { + percent = src_line->p[i].percent_sum; + color = get_percent_color(percent); + color_fprintf(stdout, color, " %7.2f", percent); + + if (percent > percent_max) + percent_max = percent; + } + path = src_line->path; + color = get_percent_color(percent_max); + color_fprintf(stdout, color, " %s", path); - color_fprintf(stdout, color, " %7.2f %s", percent, path); node = rb_next(node); } } -static void symbol__annotate_hits(struct symbol *sym, int evidx) +static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel) { struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evidx); + struct sym_hist *h = annotation__histogram(notes, evsel->idx); u64 len = symbol__size(sym), offset; for (offset = 0; offset < len; ++offset) @@ -1031,9 +1159,9 @@ static void symbol__annotate_hits(struct symbol *sym, int evidx) printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum); } -int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, - bool full_paths, int min_pcnt, int max_lines, - int context) +int symbol__annotate_printf(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, bool full_paths, + int min_pcnt, int max_lines, int context) { struct dso *dso = map->dso; char *filename; @@ -1044,6 +1172,8 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, int printed = 2, queue_len = 0; int more = 0; u64 len; + int width = 8; + int namelen; filename = strdup(dso->long_name); if (!filename) @@ -1055,12 +1185,18 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, d_filename = basename(filename); len = symbol__size(sym); + namelen = strlen(d_filename); + + if (perf_evsel__is_group_event(evsel)) + width *= evsel->nr_members; - printf(" Percent | Source code & Disassembly of %s\n", d_filename); - printf("------------------------------------------------\n"); + printf(" %-*.*s| Source code & Disassembly of %s\n", + width, width, "Percent", d_filename); + printf("-%-*.*s-------------------------------------\n", + width+namelen, width+namelen, graph_dotted_line); if (verbose) - symbol__annotate_hits(sym, evidx); + symbol__annotate_hits(sym, evsel); list_for_each_entry(pos, ¬es->src->source, node) { if (context && queue == NULL) { @@ -1068,7 +1204,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, queue_len = 0; } - switch (disasm_line__print(pos, sym, start, evidx, len, + switch (disasm_line__print(pos, sym, start, evsel, len, min_pcnt, printed, max_lines, queue)) { case 0: @@ -1163,9 +1299,9 @@ size_t disasm__fprintf(struct list_head *head, FILE *fp) return printed; } -int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, - bool print_lines, bool full_paths, int min_pcnt, - int max_lines) +int symbol__tty_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, bool print_lines, + bool full_paths, int min_pcnt, int max_lines) { struct dso *dso = map->dso; const char *filename = dso->long_name; @@ -1178,12 +1314,12 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, len = symbol__size(sym); if (print_lines) { - symbol__get_source_line(sym, map, evidx, &source_line, + symbol__get_source_line(sym, map, evsel, &source_line, len, filename); print_summary(&source_line, filename); } - symbol__annotate_printf(sym, map, evidx, full_paths, + symbol__annotate_printf(sym, map, evsel, full_paths, min_pcnt, max_lines, 0); if (print_lines) symbol__free_source_line(sym, len); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index c422440fe611..af755156d278 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -50,6 +50,8 @@ bool ins__is_jump(const struct ins *ins); bool ins__is_call(const struct ins *ins); int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); +struct annotation; + struct disasm_line { struct list_head node; s64 offset; @@ -68,17 +70,24 @@ void disasm_line__free(struct disasm_line *dl); struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos); int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); size_t disasm__fprintf(struct list_head *head, FILE *fp); +double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, + s64 end, const char **path); struct sym_hist { u64 sum; u64 addr[0]; }; -struct source_line { - struct rb_node node; +struct source_line_percent { double percent; double percent_sum; +}; + +struct source_line { + struct rb_node node; char *path; + int nr_pcnt; + struct source_line_percent p[1]; }; /** struct annotated_source - symbols with hits have this attached as in sannotation @@ -130,47 +139,49 @@ void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize); int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym); -int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, - bool full_paths, int min_pcnt, int max_lines, - int context); +int symbol__annotate_printf(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, bool full_paths, + int min_pcnt, int max_lines, int context); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void disasm__purge(struct list_head *head); -int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, - bool print_lines, bool full_paths, int min_pcnt, - int max_lines); +int symbol__tty_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, bool print_lines, + bool full_paths, int min_pcnt, int max_lines); -#ifdef NEWT_SUPPORT -int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, +#ifdef SLANG_SUPPORT +int symbol__tui_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, struct hist_browser_timer *hbt); #else static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, - struct map *map __maybe_unused, - int evidx __maybe_unused, - struct hist_browser_timer *hbt - __maybe_unused) + struct map *map __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct hist_browser_timer *hbt + __maybe_unused) { return 0; } #endif #ifdef GTK2_SUPPORT -int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx, +int symbol__gtk_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, struct hist_browser_timer *hbt); -static inline int hist_entry__gtk_annotate(struct hist_entry *he, int evidx, +static inline int hist_entry__gtk_annotate(struct hist_entry *he, + struct perf_evsel *evsel, struct hist_browser_timer *hbt) { - return symbol__gtk_annotate(he->ms.sym, he->ms.map, evidx, hbt); + return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt); } void perf_gtk__show_annotations(void); #else static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused, - int evidx __maybe_unused, - struct hist_browser_timer *hbt - __maybe_unused) + struct perf_evsel *evsel __maybe_unused, + struct hist_browser_timer *hbt __maybe_unused) { return 0; } diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index f817046e22b1..beb8cf9f9976 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -4,6 +4,7 @@ #include "cpumap.h" #include <assert.h> #include <stdio.h> +#include <stdlib.h> static struct cpu_map *cpu_map__default_new(void) { @@ -219,7 +220,7 @@ int cpu_map__get_socket(struct cpu_map *map, int idx) if (!mnt) return -1; - sprintf(path, + snprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d/topology/physical_package_id", mnt, cpu); @@ -231,27 +232,88 @@ int cpu_map__get_socket(struct cpu_map *map, int idx) return ret == 1 ? cpu : -1; } -int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp) +static int cmp_ids(const void *a, const void *b) { - struct cpu_map *sock; + return *(int *)a - *(int *)b; +} + +static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, + int (*f)(struct cpu_map *map, int cpu)) +{ + struct cpu_map *c; int nr = cpus->nr; int cpu, s1, s2; - sock = calloc(1, sizeof(*sock) + nr * sizeof(int)); - if (!sock) + /* allocate as much as possible */ + c = calloc(1, sizeof(*c) + nr * sizeof(int)); + if (!c) return -1; for (cpu = 0; cpu < nr; cpu++) { - s1 = cpu_map__get_socket(cpus, cpu); - for (s2 = 0; s2 < sock->nr; s2++) { - if (s1 == sock->map[s2]) + s1 = f(cpus, cpu); + for (s2 = 0; s2 < c->nr; s2++) { + if (s1 == c->map[s2]) break; } - if (s2 == sock->nr) { - sock->map[sock->nr] = s1; - sock->nr++; + if (s2 == c->nr) { + c->map[c->nr] = s1; + c->nr++; } } - *sockp = sock; + /* ensure we process id in increasing order */ + qsort(c->map, c->nr, sizeof(int), cmp_ids); + + *res = c; return 0; } + +int cpu_map__get_core(struct cpu_map *map, int idx) +{ + FILE *fp; + const char *mnt; + char path[PATH_MAX]; + int cpu, ret, s; + + if (idx > map->nr) + return -1; + + cpu = map->map[idx]; + + mnt = sysfs_find_mountpoint(); + if (!mnt) + return -1; + + snprintf(path, PATH_MAX, + "%s/devices/system/cpu/cpu%d/topology/core_id", + mnt, cpu); + + fp = fopen(path, "r"); + if (!fp) + return -1; + ret = fscanf(fp, "%d", &cpu); + fclose(fp); + if (ret != 1) + return -1; + + s = cpu_map__get_socket(map, idx); + if (s == -1) + return -1; + + /* + * encode socket in upper 16 bits + * core_id is relative to socket, and + * we need a global id. So we combine + * socket+ core id + */ + return (s << 16) | (cpu & 0xffff); +} + +int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp) +{ + return cpu_map__build_map(cpus, sockp, cpu_map__get_socket); +} + +int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) +{ + return cpu_map__build_map(cpus, corep, cpu_map__get_core); +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 161b00756a12..9bed02e5fb3d 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -15,7 +15,9 @@ void cpu_map__delete(struct cpu_map *map); struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); int cpu_map__get_socket(struct cpu_map *map, int idx); +int cpu_map__get_core(struct cpu_map *map, int idx); int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); +int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep); static inline int cpu_map__socket(struct cpu_map *sock, int s) { @@ -24,6 +26,16 @@ static inline int cpu_map__socket(struct cpu_map *sock, int s) return sock->map[s]; } +static inline int cpu_map__id_to_socket(int id) +{ + return id >> 16; +} + +static inline int cpu_map__id_to_cpu(int id) +{ + return id & 0xffff; +} + static inline int cpu_map__nr(const struct cpu_map *map) { return map ? map->nr : 1; diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c deleted file mode 100644 index dd8b19319c03..000000000000 --- a/tools/perf/util/debugfs.c +++ /dev/null @@ -1,114 +0,0 @@ -#include "util.h" -#include "debugfs.h" -#include "cache.h" - -#include <linux/kernel.h> -#include <sys/mount.h> - -static int debugfs_premounted; -char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug"; -char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events"; - -static const char *debugfs_known_mountpoints[] = { - "/sys/kernel/debug/", - "/debug/", - 0, -}; - -static int debugfs_found; - -/* find the path to the mounted debugfs */ -const char *debugfs_find_mountpoint(void) -{ - const char **ptr; - char type[100]; - FILE *fp; - - if (debugfs_found) - return (const char *) debugfs_mountpoint; - - ptr = debugfs_known_mountpoints; - while (*ptr) { - if (debugfs_valid_mountpoint(*ptr) == 0) { - debugfs_found = 1; - strcpy(debugfs_mountpoint, *ptr); - return debugfs_mountpoint; - } - ptr++; - } - - /* give up and parse /proc/mounts */ - fp = fopen("/proc/mounts", "r"); - if (fp == NULL) - return NULL; - - while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", - debugfs_mountpoint, type) == 2) { - if (strcmp(type, "debugfs") == 0) - break; - } - fclose(fp); - - if (strcmp(type, "debugfs") != 0) - return NULL; - - debugfs_found = 1; - - return debugfs_mountpoint; -} - -/* verify that a mountpoint is actually a debugfs instance */ - -int debugfs_valid_mountpoint(const char *debugfs) -{ - struct statfs st_fs; - - if (statfs(debugfs, &st_fs) < 0) - return -ENOENT; - else if (st_fs.f_type != (long) DEBUGFS_MAGIC) - return -ENOENT; - - return 0; -} - -static void debugfs_set_tracing_events_path(const char *mountpoint) -{ - snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", - mountpoint, "tracing/events"); -} - -/* mount the debugfs somewhere if it's not mounted */ - -char *debugfs_mount(const char *mountpoint) -{ - /* see if it's already mounted */ - if (debugfs_find_mountpoint()) { - debugfs_premounted = 1; - goto out; - } - - /* if not mounted and no argument */ - if (mountpoint == NULL) { - /* see if environment variable set */ - mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT); - /* if no environment variable, use default */ - if (mountpoint == NULL) - mountpoint = "/sys/kernel/debug"; - } - - if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0) - return NULL; - - /* save the mountpoint */ - debugfs_found = 1; - strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint)); -out: - debugfs_set_tracing_events_path(debugfs_mountpoint); - return debugfs_mountpoint; -} - -void debugfs_set_path(const char *mountpoint) -{ - snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint); - debugfs_set_tracing_events_path(mountpoint); -} diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h deleted file mode 100644 index 68f3e87ec57f..000000000000 --- a/tools/perf/util/debugfs.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef __DEBUGFS_H__ -#define __DEBUGFS_H__ - -const char *debugfs_find_mountpoint(void); -int debugfs_valid_mountpoint(const char *debugfs); -char *debugfs_mount(const char *mountpoint); -void debugfs_set_path(const char *mountpoint); - -extern char debugfs_mountpoint[]; -extern char tracing_events_path[]; - -#endif /* __DEBUGFS_H__ */ diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 0d573ff4771a..181389535c0c 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -88,8 +88,10 @@ struct perf_sample { u64 id; u64 stream_id; u64 period; + u64 weight; u32 cpu; u32 raw_size; + u64 data_src; void *raw_data; struct ip_callchain *callchain; struct branch_stack *branch_stack; @@ -97,6 +99,13 @@ struct perf_sample { struct stack_dump user_stack; }; +#define PERF_MEM_DATA_SRC_NONE \ + (PERF_MEM_S(OP, NA) |\ + PERF_MEM_S(LVL, NA) |\ + PERF_MEM_S(SNOOP, NA) |\ + PERF_MEM_S(LOCK, NA) |\ + PERF_MEM_S(TLB, NA)) + struct build_id_event { struct perf_event_header header; pid_t pid; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c8be0fbc5145..99b43dd18c57 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -7,7 +7,7 @@ * Released under the GPL v2. (and only v2, not any later version) */ #include "util.h" -#include "debugfs.h" +#include <lk/debugfs.h> #include <poll.h> #include "cpumap.h" #include "thread_map.h" @@ -38,13 +38,12 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, evlist->workload.pid = -1; } -struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, - struct thread_map *threads) +struct perf_evlist *perf_evlist__new(void) { struct perf_evlist *evlist = zalloc(sizeof(*evlist)); if (evlist != NULL) - perf_evlist__init(evlist, cpus, threads); + perf_evlist__init(evlist, NULL, NULL); return evlist; } @@ -228,12 +227,14 @@ void perf_evlist__disable(struct perf_evlist *evlist) { int cpu, thread; struct perf_evsel *pos; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = thread_map__nr(evlist->threads); - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { list_for_each_entry(pos, &evlist->entries, node) { if (!perf_evsel__is_group_leader(pos)) continue; - for (thread = 0; thread < evlist->threads->nr; thread++) + for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE, 0); } @@ -244,12 +245,14 @@ void perf_evlist__enable(struct perf_evlist *evlist) { int cpu, thread; struct perf_evsel *pos; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = thread_map__nr(evlist->threads); - for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { list_for_each_entry(pos, &evlist->entries, node) { if (!perf_evsel__is_group_leader(pos)) continue; - for (thread = 0; thread < evlist->threads->nr; thread++) + for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); } @@ -258,7 +261,9 @@ void perf_evlist__enable(struct perf_evlist *evlist) static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { - int nfds = cpu_map__nr(evlist->cpus) * evlist->threads->nr * evlist->nr_entries; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = thread_map__nr(evlist->threads); + int nfds = nr_cpus * nr_threads * evlist->nr_entries; evlist->pollfd = malloc(sizeof(struct pollfd) * nfds); return evlist->pollfd != NULL ? 0 : -ENOMEM; } @@ -417,7 +422,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { evlist->nr_mmaps = cpu_map__nr(evlist->cpus); if (cpu_map__all(evlist->cpus)) - evlist->nr_mmaps = evlist->threads->nr; + evlist->nr_mmaps = thread_map__nr(evlist->threads); evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); return evlist->mmap != NULL ? 0 : -ENOMEM; } @@ -442,11 +447,13 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m { struct perf_evsel *evsel; int cpu, thread; + int nr_cpus = cpu_map__nr(evlist->cpus); + int nr_threads = thread_map__nr(evlist->threads); - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { int output = -1; - for (thread = 0; thread < evlist->threads->nr; thread++) { + for (thread = 0; thread < nr_threads; thread++) { list_for_each_entry(evsel, &evlist->entries, node) { int fd = FD(evsel, cpu, thread); @@ -470,7 +477,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m return 0; out_unmap: - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (cpu = 0; cpu < nr_cpus; cpu++) { if (evlist->mmap[cpu].base != NULL) { munmap(evlist->mmap[cpu].base, evlist->mmap_len); evlist->mmap[cpu].base = NULL; @@ -483,8 +490,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in { struct perf_evsel *evsel; int thread; + int nr_threads = thread_map__nr(evlist->threads); - for (thread = 0; thread < evlist->threads->nr; thread++) { + for (thread = 0; thread < nr_threads; thread++) { int output = -1; list_for_each_entry(evsel, &evlist->entries, node) { @@ -509,7 +517,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in return 0; out_unmap: - for (thread = 0; thread < evlist->threads->nr; thread++) { + for (thread = 0; thread < nr_threads; thread++) { if (evlist->mmap[thread].base != NULL) { munmap(evlist->mmap[thread].base, evlist->mmap_len); evlist->mmap[thread].base = NULL; @@ -610,7 +618,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist) struct perf_evsel *evsel; int err = 0; const int ncpus = cpu_map__nr(evlist->cpus), - nthreads = evlist->threads->nr; + nthreads = thread_map__nr(evlist->threads); list_for_each_entry(evsel, &evlist->entries, node) { if (evsel->filter == NULL) @@ -629,7 +637,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) struct perf_evsel *evsel; int err = 0; const int ncpus = cpu_map__nr(evlist->cpus), - nthreads = evlist->threads->nr; + nthreads = thread_map__nr(evlist->threads); list_for_each_entry(evsel, &evlist->entries, node) { err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter); @@ -712,10 +720,20 @@ void perf_evlist__set_selected(struct perf_evlist *evlist, evlist->selected = evsel; } +void perf_evlist__close(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int ncpus = cpu_map__nr(evlist->cpus); + int nthreads = thread_map__nr(evlist->threads); + + list_for_each_entry_reverse(evsel, &evlist->entries, node) + perf_evsel__close(evsel, ncpus, nthreads); +} + int perf_evlist__open(struct perf_evlist *evlist) { struct perf_evsel *evsel; - int err, ncpus, nthreads; + int err; list_for_each_entry(evsel, &evlist->entries, node) { err = perf_evsel__open(evsel, evlist->cpus, evlist->threads); @@ -725,19 +743,15 @@ int perf_evlist__open(struct perf_evlist *evlist) return 0; out_err: - ncpus = evlist->cpus ? evlist->cpus->nr : 1; - nthreads = evlist->threads ? evlist->threads->nr : 1; - - list_for_each_entry_reverse(evsel, &evlist->entries, node) - perf_evsel__close(evsel, ncpus, nthreads); - + perf_evlist__close(evlist); errno = -err; return err; } int perf_evlist__prepare_workload(struct perf_evlist *evlist, - struct perf_record_opts *opts, - const char *argv[]) + struct perf_target *target, + const char *argv[], bool pipe_output, + bool want_signal) { int child_ready_pipe[2], go_pipe[2]; char bf; @@ -759,9 +773,11 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, } if (!evlist->workload.pid) { - if (opts->pipe_output) + if (pipe_output) dup2(2, 1); + signal(SIGTERM, SIG_DFL); + close(child_ready_pipe[0]); close(go_pipe[1]); fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); @@ -787,11 +803,12 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, execvp(argv[0], (char **)argv); perror(argv[0]); - kill(getppid(), SIGUSR1); + if (want_signal) + kill(getppid(), SIGUSR1); exit(-1); } - if (perf_target__none(&opts->target)) + if (perf_target__none(target)) evlist->threads->map[0] = evlist->workload.pid; close(child_ready_pipe[1]); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 2dd07bd60b4f..0583d36252be 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -49,8 +49,7 @@ struct perf_evsel_str_handler { void *handler; }; -struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, - struct thread_map *threads); +struct perf_evlist *perf_evlist__new(void); void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads); void perf_evlist__exit(struct perf_evlist *evlist); @@ -82,13 +81,15 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); int perf_evlist__open(struct perf_evlist *evlist); +void perf_evlist__close(struct perf_evlist *evlist); void perf_evlist__config(struct perf_evlist *evlist, struct perf_record_opts *opts); int perf_evlist__prepare_workload(struct perf_evlist *evlist, - struct perf_record_opts *opts, - const char *argv[]); + struct perf_target *target, + const char *argv[], bool pipe_output, + bool want_signal); int perf_evlist__start_workload(struct perf_evlist *evlist); int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 9c82f98f26de..63b6f8c8edf2 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -10,7 +10,7 @@ #include <byteswap.h> #include <linux/bitops.h> #include "asm/bug.h" -#include "debugfs.h" +#include <lk/debugfs.h> #include "event-parse.h" #include "evsel.h" #include "evlist.h" @@ -554,6 +554,9 @@ void perf_evsel__config(struct perf_evsel *evsel, perf_evsel__set_sample_bit(evsel, CPU); } + if (opts->sample_address) + attr->sample_type |= PERF_SAMPLE_DATA_SRC; + if (opts->no_delay) { attr->watermark = 0; attr->wakeup_events = 1; @@ -563,6 +566,9 @@ void perf_evsel__config(struct perf_evsel *evsel, attr->branch_sample_type = opts->branch_stack; } + if (opts->sample_weight) + attr->sample_type |= PERF_SAMPLE_WEIGHT; + attr->mmap = track; attr->comm = track; @@ -633,6 +639,12 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) return 0; } +void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus) +{ + memset(evsel->counts, 0, (sizeof(*evsel->counts) + + (ncpus * sizeof(struct perf_counts_values)))); +} + int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) { evsel->counts = zalloc((sizeof(*evsel->counts) + @@ -673,9 +685,8 @@ void perf_evsel__free_counts(struct perf_evsel *evsel) void perf_evsel__exit(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); - xyarray__delete(evsel->fd); - xyarray__delete(evsel->sample_id); - free(evsel->id); + perf_evsel__free_fd(evsel); + perf_evsel__free_id(evsel); } void perf_evsel__delete(struct perf_evsel *evsel) @@ -1012,6 +1023,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; data->period = 1; + data->weight = 0; if (event->header.type != PERF_RECORD_SAMPLE) { if (!evsel->attr.sample_id_all) @@ -1162,6 +1174,18 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } + data->weight = 0; + if (type & PERF_SAMPLE_WEIGHT) { + data->weight = *array; + array++; + } + + data->data_src = PERF_MEM_DATA_SRC_NONE; + if (type & PERF_SAMPLE_DATA_SRC) { + data->data_src = *array; + array++; + } + return 0; } @@ -1490,7 +1514,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, switch (err) { case EPERM: case EACCES: - return scnprintf(msg, size, "%s", + return scnprintf(msg, size, "You may not have permission to collect %sstats.\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" " -1 - Not paranoid at all\n" diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 52021c3087df..3f156ccc1acb 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -9,6 +9,7 @@ #include "xyarray.h" #include "cgroup.h" #include "hist.h" +#include "symbol.h" struct perf_counts_values { union { @@ -120,6 +121,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); +void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus); void perf_evsel__free_fd(struct perf_evsel *evsel); void perf_evsel__free_id(struct perf_evsel *evsel); void perf_evsel__free_counts(struct perf_evsel *evsel); @@ -246,11 +248,34 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel) return list_entry(evsel->node.next, struct perf_evsel, node); } +/** + * perf_evsel__is_group_leader - Return whether given evsel is a leader event + * + * @evsel - evsel selector to be tested + * + * Return %true if @evsel is a group leader or a stand-alone event + */ static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) { return evsel->leader == evsel; } +/** + * perf_evsel__is_group_event - Return whether given evsel is a group event + * + * @evsel - evsel selector to be tested + * + * Return %true iff event group view is enabled and @evsel is a actual group + * leader which has other members in the group + */ +static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel) +{ + if (!symbol_conf.event_group) + return false; + + return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1; +} + struct perf_attr_details { bool freq; bool verbose; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index f4bfd79ef6a7..738d3b8d9745 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,5 +1,3 @@ -#define _FILE_OFFSET_BITS 64 - #include "util.h" #include <sys/types.h> #include <byteswap.h> @@ -1672,8 +1670,8 @@ static int process_tracing_data(struct perf_file_section *section __maybe_unused struct perf_header *ph __maybe_unused, int fd, void *data) { - trace_report(fd, data, false); - return 0; + ssize_t ret = trace_report(fd, data, false); + return ret < 0 ? -1 : 0; } static int process_build_id(struct perf_file_section *section, @@ -2393,7 +2391,6 @@ out_err_write: } lseek(fd, header->data_offset + header->data_size, SEEK_SET); - header->frozen = 1; return 0; } @@ -2752,6 +2749,11 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, if (evsel->tp_format) return 0; + if (pevent == NULL) { + pr_debug("broken or missing trace data\n"); + return -1; + } + event = pevent_find_event(pevent, evsel->attr.config); if (event == NULL) return -1; @@ -2789,7 +2791,7 @@ int perf_session__read_header(struct perf_session *session, int fd) u64 f_id; int nr_attrs, nr_ids, i, j; - session->evlist = perf_evlist__new(NULL, NULL); + session->evlist = perf_evlist__new(); if (session->evlist == NULL) return -ENOMEM; @@ -2868,7 +2870,6 @@ int perf_session__read_header(struct perf_session *session, int fd) session->pevent)) goto out_delete_evlist; - header->frozen = 1; return 0; out_errno: return -errno; @@ -2940,7 +2941,7 @@ int perf_event__process_attr(union perf_event *event, struct perf_evlist *evlist = *pevlist; if (evlist == NULL) { - *pevlist = evlist = perf_evlist__new(NULL, NULL); + *pevlist = evlist = perf_evlist__new(); if (evlist == NULL) return -ENOMEM; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index c9fc55cada6d..16a3e83c584e 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -84,7 +84,6 @@ struct perf_session_env { }; struct perf_header { - int frozen; bool needs_swap; s64 attr_offset; u64 data_offset; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f855941bebea..b11a6cfdb414 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -67,12 +67,24 @@ static void hists__set_unres_dso_col_len(struct hists *hists, int dso) void hists__calc_col_len(struct hists *hists, struct hist_entry *h) { const unsigned int unresolved_col_width = BITS_PER_LONG / 4; + int symlen; u16 len; - if (h->ms.sym) - hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4); - else + /* + * +4 accounts for '[x] ' priv level info + * +2 accounts for 0x prefix on raw addresses + * +3 accounts for ' y ' symtab origin info + */ + if (h->ms.sym) { + symlen = h->ms.sym->namelen + 4; + if (verbose) + symlen += BITS_PER_LONG / 4 + 2 + 3; + hists__new_col_len(hists, HISTC_SYMBOL, symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_SYMBOL, symlen); hists__set_unres_dso_col_len(hists, HISTC_DSO); + } len = thread__comm_len(h->thread); if (hists__new_col_len(hists, HISTC_COMM, len)) @@ -87,13 +99,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen); if (h->branch_info) { - int symlen; - /* - * +4 accounts for '[x] ' priv level info - * +2 account of 0x prefix on raw addresses - */ if (h->branch_info->from.sym) { symlen = (int)h->branch_info->from.sym->namelen + 4; + if (verbose) + symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); symlen = dso__name_len(h->branch_info->from.map->dso); @@ -106,6 +115,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->branch_info->to.sym) { symlen = (int)h->branch_info->to.sym->namelen + 4; + if (verbose) + symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); symlen = dso__name_len(h->branch_info->to.map->dso); @@ -116,6 +127,38 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_unres_dso_col_len(hists, HISTC_DSO_TO); } } + + if (h->mem_info) { + if (h->mem_info->daddr.sym) { + symlen = (int)h->mem_info->daddr.sym->namelen + 4 + + unresolved_col_width + 2; + hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, + symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, + symlen); + } + if (h->mem_info->daddr.map) { + symlen = dso__name_len(h->mem_info->daddr.map->dso); + hists__new_col_len(hists, HISTC_MEM_DADDR_DSO, + symlen); + } else { + symlen = unresolved_col_width + 4 + 2; + hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); + } + } else { + symlen = unresolved_col_width + 4 + 2; + hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); + hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); + } + + hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); + hists__new_col_len(hists, HISTC_MEM_TLB, 22); + hists__new_col_len(hists, HISTC_MEM_SNOOP, 12); + hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3); + hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); + hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); } void hists__output_recalc_col_len(struct hists *hists, int max_rows) @@ -155,9 +198,12 @@ static void hist_entry__add_cpumode_period(struct hist_entry *he, } } -static void he_stat__add_period(struct he_stat *he_stat, u64 period) +static void he_stat__add_period(struct he_stat *he_stat, u64 period, + u64 weight) { + he_stat->period += period; + he_stat->weight += weight; he_stat->nr_events += 1; } @@ -169,12 +215,14 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->period_guest_sys += src->period_guest_sys; dest->period_guest_us += src->period_guest_us; dest->nr_events += src->nr_events; + dest->weight += src->weight; } static void hist_entry__decay(struct hist_entry *he) { he->stat.period = (he->stat.period * 7) / 8; he->stat.nr_events = (he->stat.nr_events * 7) / 8; + /* XXX need decay for weight too? */ } static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) @@ -192,8 +240,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) return he->stat.period == 0; } -static void __hists__decay_entries(struct hists *hists, bool zap_user, - bool zap_kernel, bool threaded) +void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) { struct rb_node *next = rb_first(&hists->entries); struct hist_entry *n; @@ -212,7 +259,7 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user, !n->used) { rb_erase(&n->rb_node, &hists->entries); - if (sort__need_collapse || threaded) + if (sort__need_collapse) rb_erase(&n->rb_node_in, &hists->entries_collapsed); hist_entry__free(n); @@ -221,17 +268,6 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user, } } -void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) -{ - return __hists__decay_entries(hists, zap_user, zap_kernel, false); -} - -void hists__decay_entries_threaded(struct hists *hists, - bool zap_user, bool zap_kernel) -{ - return __hists__decay_entries(hists, zap_user, zap_kernel, true); -} - /* * histogram, sorted on item, collects periods */ @@ -239,7 +275,7 @@ void hists__decay_entries_threaded(struct hists *hists, static struct hist_entry *hist_entry__new(struct hist_entry *template) { size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0; - struct hist_entry *he = malloc(sizeof(*he) + callchain_size); + struct hist_entry *he = zalloc(sizeof(*he) + callchain_size); if (he != NULL) { *he = *template; @@ -248,12 +284,33 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) he->ms.map->referenced = true; if (he->branch_info) { + /* + * This branch info is (a part of) allocated from + * machine__resolve_bstack() and will be freed after + * adding new entries. So we need to save a copy. + */ + he->branch_info = malloc(sizeof(*he->branch_info)); + if (he->branch_info == NULL) { + free(he); + return NULL; + } + + memcpy(he->branch_info, template->branch_info, + sizeof(*he->branch_info)); + if (he->branch_info->from.map) he->branch_info->from.map->referenced = true; if (he->branch_info->to.map) he->branch_info->to.map->referenced = true; } + if (he->mem_info) { + if (he->mem_info->iaddr.map) + he->mem_info->iaddr.map->referenced = true; + if (he->mem_info->daddr.map) + he->mem_info->daddr.map->referenced = true; + } + if (symbol_conf.use_callchain) callchain_init(he->callchain); @@ -282,15 +339,14 @@ static u8 symbol__parent_filter(const struct symbol *parent) static struct hist_entry *add_hist_entry(struct hists *hists, struct hist_entry *entry, struct addr_location *al, - u64 period) + u64 period, + u64 weight) { struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; int cmp; - pthread_mutex_lock(&hists->lock); - p = &hists->entries_in->rb_node; while (*p != NULL) { @@ -306,7 +362,13 @@ static struct hist_entry *add_hist_entry(struct hists *hists, cmp = hist_entry__cmp(he, entry); if (!cmp) { - he_stat__add_period(&he->stat, period); + he_stat__add_period(&he->stat, period, weight); + + /* + * This mem info was allocated from machine__resolve_mem + * and will not be used anymore. + */ + free(entry->mem_info); /* If the map of an existing hist_entry has * become out-of-date due to an exec() or @@ -330,22 +392,51 @@ static struct hist_entry *add_hist_entry(struct hists *hists, he = hist_entry__new(entry); if (!he) - goto out_unlock; + return NULL; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: hist_entry__add_cpumode_period(he, al->cpumode, period); -out_unlock: - pthread_mutex_unlock(&hists->lock); return he; } +struct hist_entry *__hists__add_mem_entry(struct hists *self, + struct addr_location *al, + struct symbol *sym_parent, + struct mem_info *mi, + u64 period, + u64 weight) +{ + struct hist_entry entry = { + .thread = al->thread, + .ms = { + .map = al->map, + .sym = al->sym, + }, + .stat = { + .period = period, + .weight = weight, + .nr_events = 1, + }, + .cpu = al->cpu, + .ip = al->addr, + .level = al->level, + .parent = sym_parent, + .filtered = symbol__parent_filter(sym_parent), + .hists = self, + .mem_info = mi, + .branch_info = NULL, + }; + return add_hist_entry(self, &entry, al, period, weight); +} + struct hist_entry *__hists__add_branch_entry(struct hists *self, struct addr_location *al, struct symbol *sym_parent, struct branch_info *bi, - u64 period) + u64 period, + u64 weight) { struct hist_entry entry = { .thread = al->thread, @@ -359,19 +450,22 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, .stat = { .period = period, .nr_events = 1, + .weight = weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), .branch_info = bi, .hists = self, + .mem_info = NULL, }; - return add_hist_entry(self, &entry, al, period); + return add_hist_entry(self, &entry, al, period, weight); } struct hist_entry *__hists__add_entry(struct hists *self, struct addr_location *al, - struct symbol *sym_parent, u64 period) + struct symbol *sym_parent, u64 period, + u64 weight) { struct hist_entry entry = { .thread = al->thread, @@ -385,13 +479,16 @@ struct hist_entry *__hists__add_entry(struct hists *self, .stat = { .period = period, .nr_events = 1, + .weight = weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), .hists = self, + .branch_info = NULL, + .mem_info = NULL, }; - return add_hist_entry(self, &entry, al, period); + return add_hist_entry(self, &entry, al, period, weight); } int64_t @@ -431,6 +528,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) void hist_entry__free(struct hist_entry *he) { free(he->branch_info); + free(he->mem_info); free(he); } @@ -499,13 +597,13 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he) hists__filter_entry_by_symbol(hists, he); } -static void __hists__collapse_resort(struct hists *hists, bool threaded) +void hists__collapse_resort(struct hists *hists) { struct rb_root *root; struct rb_node *next; struct hist_entry *n; - if (!sort__need_collapse && !threaded) + if (!sort__need_collapse) return; root = hists__get_rotate_entries_in(hists); @@ -527,16 +625,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded) } } -void hists__collapse_resort(struct hists *hists) -{ - return __hists__collapse_resort(hists, false); -} - -void hists__collapse_resort_threaded(struct hists *hists) -{ - return __hists__collapse_resort(hists, true); -} - /* * reverse the map, sort on period. */ @@ -623,7 +711,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, rb_insert_color(&he->rb_node, entries); } -static void __hists__output_resort(struct hists *hists, bool threaded) +void hists__output_resort(struct hists *hists) { struct rb_root *root; struct rb_node *next; @@ -632,7 +720,7 @@ static void __hists__output_resort(struct hists *hists, bool threaded) min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100); - if (sort__need_collapse || threaded) + if (sort__need_collapse) root = &hists->entries_collapsed; else root = hists->entries_in; @@ -653,16 +741,6 @@ static void __hists__output_resort(struct hists *hists, bool threaded) } } -void hists__output_resort(struct hists *hists) -{ - return __hists__output_resort(hists, false); -} - -void hists__output_resort_threaded(struct hists *hists) -{ - return __hists__output_resort(hists, true); -} - static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h, enum hist_filter filter) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 226a4ae2f936..2d3790fd99bb 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -43,12 +43,20 @@ enum hist_column { HISTC_COMM, HISTC_PARENT, HISTC_CPU, + HISTC_SRCLINE, HISTC_MISPREDICT, HISTC_SYMBOL_FROM, HISTC_SYMBOL_TO, HISTC_DSO_FROM, HISTC_DSO_TO, - HISTC_SRCLINE, + HISTC_LOCAL_WEIGHT, + HISTC_GLOBAL_WEIGHT, + HISTC_MEM_DADDR_SYMBOL, + HISTC_MEM_DADDR_DSO, + HISTC_MEM_LOCKED, + HISTC_MEM_TLB, + HISTC_MEM_LVL, + HISTC_MEM_SNOOP, HISTC_NR_COLS, /* Last entry */ }; @@ -73,7 +81,8 @@ struct hists { struct hist_entry *__hists__add_entry(struct hists *self, struct addr_location *al, - struct symbol *parent, u64 period); + struct symbol *parent, u64 period, + u64 weight); int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size, @@ -84,16 +93,20 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, struct addr_location *al, struct symbol *sym_parent, struct branch_info *bi, - u64 period); + u64 period, + u64 weight); + +struct hist_entry *__hists__add_mem_entry(struct hists *self, + struct addr_location *al, + struct symbol *sym_parent, + struct mem_info *mi, + u64 period, + u64 weight); void hists__output_resort(struct hists *self); -void hists__output_resort_threaded(struct hists *hists); void hists__collapse_resort(struct hists *self); -void hists__collapse_resort_threaded(struct hists *hists); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); -void hists__decay_entries_threaded(struct hists *hists, bool zap_user, - bool zap_kernel); void hists__output_recalc_col_len(struct hists *hists, int max_rows); void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h); @@ -102,7 +115,7 @@ void events_stats__inc(struct events_stats *stats, u32 type); size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *self, bool show_header, int max_rows, - int max_cols, FILE *fp); + int max_cols, float min_pcnt, 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); @@ -175,13 +188,14 @@ struct hist_browser_timer { int refresh; }; -#ifdef NEWT_SUPPORT +#ifdef SLANG_SUPPORT #include "../ui/keysyms.h" -int hist_entry__tui_annotate(struct hist_entry *he, int evidx, +int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct hist_browser_timer *hbt); int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_session_env *env); int script_browse(const char *script_opt); #else @@ -189,6 +203,7 @@ static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, + float min_pcnt __maybe_unused, struct perf_session_env *env __maybe_unused) { return 0; @@ -196,7 +211,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, static inline int hist_entry__tui_annotate(struct hist_entry *self __maybe_unused, - int evidx __maybe_unused, + struct perf_evsel *evsel + __maybe_unused, struct hist_browser_timer *hbt __maybe_unused) { @@ -215,12 +231,14 @@ static inline int script_browse(const char *script_opt __maybe_unused) #ifdef GTK2_SUPPORT int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, - struct hist_browser_timer *hbt __maybe_unused); + struct hist_browser_timer *hbt __maybe_unused, + float min_pcnt); #else static inline int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + float min_pcnt __maybe_unused) { return 0; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index efdb38e65a92..b2ecad6ec46b 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -955,6 +955,7 @@ 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; + enum map_type type; int ret = 0; if (dump_trace) @@ -971,10 +972,17 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event thread = machine__findnew_thread(machine, event->mmap.pid); if (thread == NULL) goto out_problem; + + if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) + type = MAP__VARIABLE; + else + type = MAP__FUNCTION; + map = map__new(&machine->user_dsos, event->mmap.start, event->mmap.len, event->mmap.pgoff, event->mmap.pid, event->mmap.filename, - MAP__FUNCTION); + type); + if (map == NULL) goto out_problem; @@ -1003,6 +1011,17 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event return 0; } +static void machine__remove_thread(struct machine *machine, struct thread *th) +{ + machine->last_match = NULL; + rb_erase(&th->rb_node, &machine->threads); + /* + * We may have references to this thread, for instance in some hist_entry + * instances, so just move them to a separate list. + */ + list_add_tail(&th->node, &machine->dead_threads); +} + int machine__process_exit_event(struct machine *machine, union perf_event *event) { struct thread *thread = machine__find_thread(machine, event->fork.tid); @@ -1039,17 +1058,6 @@ int machine__process_event(struct machine *machine, union perf_event *event) return ret; } -void machine__remove_thread(struct machine *machine, struct thread *th) -{ - machine->last_match = NULL; - rb_erase(&th->rb_node, &machine->threads); - /* - * We may have references to this thread, for instance in some hist_entry - * instances, so just move them to a separate list. - */ - list_add_tail(&th->node, &machine->dead_threads); -} - static bool symbol__match_parent_regex(struct symbol *sym) { if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) @@ -1097,6 +1105,38 @@ found: ams->map = al.map; } +static void ip__resolve_data(struct machine *machine, struct thread *thread, + u8 m, struct addr_map_symbol *ams, u64 addr) +{ + struct addr_location al; + + memset(&al, 0, sizeof(al)); + + thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, &al, + NULL); + ams->addr = addr; + ams->al_addr = al.addr; + ams->sym = al.sym; + ams->map = al.map; +} + +struct mem_info *machine__resolve_mem(struct machine *machine, + struct thread *thr, + struct perf_sample *sample, + u8 cpumode) +{ + struct mem_info *mi = zalloc(sizeof(*mi)); + + if (!mi) + return NULL; + + ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip); + ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr); + mi->data_src.val = sample->data_src; + + return mi; +} + struct branch_info *machine__resolve_bstack(struct machine *machine, struct thread *thr, struct branch_stack *bs) diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 5ac5892f2326..77940680f1fc 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -76,6 +76,9 @@ void machine__delete(struct machine *machine); struct branch_info *machine__resolve_bstack(struct machine *machine, struct thread *thread, struct branch_stack *bs); +struct mem_info *machine__resolve_mem(struct machine *machine, + struct thread *thread, + struct perf_sample *sample, u8 cpumode); int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, @@ -97,7 +100,6 @@ static inline bool machine__is_host(struct machine *machine) } struct thread *machine__findnew_thread(struct machine *machine, pid_t pid); -void machine__remove_thread(struct machine *machine, struct thread *th); size_t machine__fprintf(struct machine *machine, FILE *fp); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 6fcb9de62340..8bcdf9e54089 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -21,6 +21,7 @@ const char *map_type__name[MAP__NR_TYPES] = { static inline int is_anon_memory(const char *filename) { return !strcmp(filename, "//anon") || + !strcmp(filename, "/dev/zero (deleted)") || !strcmp(filename, "/anon_hugepage (deleted)"); } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c84f48cf9678..6c8bb0fb189b 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -10,7 +10,7 @@ #include "symbol.h" #include "cache.h" #include "header.h" -#include "debugfs.h" +#include <lk/debugfs.h> #include "parse-events-bison.h" #define YY_EXTRA_TYPE int #include "parse-events-flex.h" diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 49a256e6e0a2..aa04bf9c9ad7 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -40,7 +40,7 @@ #include "color.h" #include "symbol.h" #include "thread.h" -#include "debugfs.h" +#include <lk/debugfs.h> #include "trace-event.h" /* For __maybe_unused */ #include "probe-event.h" #include "probe-finder.h" diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 64536a993f4a..f75ae1b9900c 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -15,7 +15,6 @@ util/thread_map.c util/util.c util/xyarray.c util/cgroup.c -util/debugfs.c util/rblist.c util/strlist.c util/sysfs.c diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index bd85280bb6e8..cf1fe01b7e89 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,5 +1,3 @@ -#define _FILE_OFFSET_BITS 64 - #include <linux/kernel.h> #include <byteswap.h> @@ -800,6 +798,12 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); + + if (sample_type & PERF_SAMPLE_WEIGHT) + printf("... weight: %" PRIu64 "\n", sample->weight); + + if (sample_type & PERF_SAMPLE_DATA_SRC) + printf(" . data_src: 0x%"PRIx64"\n", sample->data_src); } static struct machine * @@ -1365,18 +1369,6 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp) return machine__fprintf(&session->machines.host, fp); } -void perf_session__remove_thread(struct perf_session *session, - struct thread *th) -{ - /* - * FIXME: This one makes no sense, we need to remove the thread from - * the machine it belongs to, perf_session can have many machines, so - * doing it always on ->machines.host is wrong. Fix when auditing all - * the 'perf kvm' code. - */ - machine__remove_thread(&session->machines.host, th); -} - struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type) { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index b5c0847edfa9..f3b235ec7bf4 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -37,7 +37,6 @@ struct perf_session { int fd; bool fd_pipe; bool repipe; - int cwdlen; char *cwd; struct ordered_samples ordered_samples; char filename[1]; @@ -72,7 +71,6 @@ void perf_event__attr_swap(struct perf_event_attr *attr); int perf_session__create_kernel_maps(struct perf_session *self); void perf_session__set_id_hdr_size(struct perf_session *session); -void perf_session__remove_thread(struct perf_session *self, struct thread *th); static inline struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid) diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 73d510269784..58ea5ca6c255 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -18,12 +18,14 @@ class install_lib(_install_lib): self.build_dir = build_lib -cflags = ['-fno-strict-aliasing', '-Wno-write-strings'] -cflags += getenv('CFLAGS', '').split() +cflags = getenv('CFLAGS', '').split() +# switch off several checks (need to be at the end of cflags list) +cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ] build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') +liblk = getenv('LIBLK') ext_sources = [f.strip() for f in file('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] @@ -32,7 +34,7 @@ perf = Extension('perf', sources = ext_sources, include_dirs = ['util/include'], extra_compile_args = cflags, - extra_objects = [libtraceevent], + extra_objects = [libtraceevent, liblk], ) setup(name='perf', diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d41926cb9e3f..313a5a730112 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,5 +1,6 @@ #include "sort.h" #include "hist.h" +#include "symbol.h" regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -9,7 +10,7 @@ const char *sort_order = default_sort_order; int sort__need_collapse = 0; int sort__has_parent = 0; int sort__has_sym = 0; -int sort__branch_mode = -1; /* -1 = means not set */ +enum sort_mode sort__mode = SORT_MODE__NORMAL; enum sort_type sort__first_dimension; @@ -194,15 +195,23 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, if (verbose) { char o = map ? dso__symtab_origin(map->dso) : '!'; ret += repsep_snprintf(bf, size, "%-#*llx %c ", - BITS_PER_LONG / 4, ip, o); + BITS_PER_LONG / 4 + 2, ip, o); } ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level); - if (sym) - ret += repsep_snprintf(bf + ret, size - ret, "%-*s", - width - ret, - sym->name); - else { + if (sym && map) { + if (map->type == MAP__VARIABLE) { + ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name); + ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", + ip - map->unmap_ip(map, sym->start)); + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + width - ret, ""); + } else { + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", + width - ret, + sym->name); + } + } else { size_t len = BITS_PER_LONG / 4; ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, ip); @@ -457,6 +466,304 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf, return repsep_snprintf(bf, size, "%-*s", width, out); } +/* --sort daddr_sym */ +static int64_t +sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = 0, r = 0; + + if (left->mem_info) + l = left->mem_info->daddr.addr; + if (right->mem_info) + r = right->mem_info->daddr.addr; + + return (int64_t)(r - l); +} + +static int hist_entry__daddr_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + uint64_t addr = 0; + struct map *map = NULL; + struct symbol *sym = NULL; + + if (self->mem_info) { + addr = self->mem_info->daddr.addr; + map = self->mem_info->daddr.map; + sym = self->mem_info->daddr.sym; + } + return _hist_entry__sym_snprintf(map, sym, addr, self->level, bf, size, + width); +} + +static int64_t +sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct map *map_l = NULL; + struct map *map_r = NULL; + + if (left->mem_info) + map_l = left->mem_info->daddr.map; + if (right->mem_info) + map_r = right->mem_info->daddr.map; + + return _sort__dso_cmp(map_l, map_r); +} + +static int hist_entry__dso_daddr_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + struct map *map = NULL; + + if (self->mem_info) + map = self->mem_info->daddr.map; + + return _hist_entry__dso_snprintf(map, bf, size, width); +} + +static int64_t +sort__locked_cmp(struct hist_entry *left, struct hist_entry *right) +{ + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; + + if (left->mem_info) + data_src_l = left->mem_info->data_src; + else + data_src_l.mem_lock = PERF_MEM_LOCK_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_lock = PERF_MEM_LOCK_NA; + + return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock); +} + +static int hist_entry__locked_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + const char *out; + u64 mask = PERF_MEM_LOCK_NA; + + if (self->mem_info) + mask = self->mem_info->data_src.mem_lock; + + if (mask & PERF_MEM_LOCK_NA) + out = "N/A"; + else if (mask & PERF_MEM_LOCK_LOCKED) + out = "Yes"; + else + out = "No"; + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +static int64_t +sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right) +{ + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; + + if (left->mem_info) + data_src_l = left->mem_info->data_src; + else + data_src_l.mem_dtlb = PERF_MEM_TLB_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_dtlb = PERF_MEM_TLB_NA; + + return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb); +} + +static const char * const tlb_access[] = { + "N/A", + "HIT", + "MISS", + "L1", + "L2", + "Walker", + "Fault", +}; +#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *)) + +static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + char out[64]; + size_t sz = sizeof(out) - 1; /* -1 for null termination */ + size_t l = 0, i; + u64 m = PERF_MEM_TLB_NA; + u64 hit, miss; + + out[0] = '\0'; + + if (self->mem_info) + m = self->mem_info->data_src.mem_dtlb; + + hit = m & PERF_MEM_TLB_HIT; + miss = m & PERF_MEM_TLB_MISS; + + /* already taken care of */ + m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS); + + for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + strncat(out, tlb_access[i], sz - l); + l += strlen(tlb_access[i]); + } + if (*out == '\0') + strcpy(out, "N/A"); + if (hit) + strncat(out, " hit", sz - l); + if (miss) + strncat(out, " miss", sz - l); + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +static int64_t +sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right) +{ + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; + + if (left->mem_info) + data_src_l = left->mem_info->data_src; + else + data_src_l.mem_lvl = PERF_MEM_LVL_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_lvl = PERF_MEM_LVL_NA; + + return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl); +} + +static const char * const mem_lvl[] = { + "N/A", + "HIT", + "MISS", + "L1", + "LFB", + "L2", + "L3", + "Local RAM", + "Remote RAM (1 hop)", + "Remote RAM (2 hops)", + "Remote Cache (1 hop)", + "Remote Cache (2 hops)", + "I/O", + "Uncached", +}; +#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *)) + +static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + char out[64]; + size_t sz = sizeof(out) - 1; /* -1 for null termination */ + size_t i, l = 0; + u64 m = PERF_MEM_LVL_NA; + u64 hit, miss; + + if (self->mem_info) + m = self->mem_info->data_src.mem_lvl; + + out[0] = '\0'; + + hit = m & PERF_MEM_LVL_HIT; + miss = m & PERF_MEM_LVL_MISS; + + /* already taken care of */ + m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); + + for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + strncat(out, mem_lvl[i], sz - l); + l += strlen(mem_lvl[i]); + } + if (*out == '\0') + strcpy(out, "N/A"); + if (hit) + strncat(out, " hit", sz - l); + if (miss) + strncat(out, " miss", sz - l); + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +static int64_t +sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right) +{ + union perf_mem_data_src data_src_l; + union perf_mem_data_src data_src_r; + + if (left->mem_info) + data_src_l = left->mem_info->data_src; + else + data_src_l.mem_snoop = PERF_MEM_SNOOP_NA; + + if (right->mem_info) + data_src_r = right->mem_info->data_src; + else + data_src_r.mem_snoop = PERF_MEM_SNOOP_NA; + + return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop); +} + +static const char * const snoop_access[] = { + "N/A", + "None", + "Miss", + "Hit", + "HitM", +}; +#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *)) + +static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + char out[64]; + size_t sz = sizeof(out) - 1; /* -1 for null termination */ + size_t i, l = 0; + u64 m = PERF_MEM_SNOOP_NA; + + out[0] = '\0'; + + if (self->mem_info) + m = self->mem_info->data_src.mem_snoop; + + for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (l) { + strcat(out, " or "); + l += 4; + } + strncat(out, snoop_access[i], sz - l); + l += strlen(snoop_access[i]); + } + + if (*out == '\0') + strcpy(out, "N/A"); + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + struct sort_entry sort_mispredict = { .se_header = "Branch Mispredicted", .se_cmp = sort__mispredict_cmp, @@ -464,6 +771,91 @@ struct sort_entry sort_mispredict = { .se_width_idx = HISTC_MISPREDICT, }; +static u64 he_weight(struct hist_entry *he) +{ + return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0; +} + +static int64_t +sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return he_weight(left) - he_weight(right); +} + +static int hist_entry__local_weight_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*llu", width, he_weight(self)); +} + +struct sort_entry sort_local_weight = { + .se_header = "Local Weight", + .se_cmp = sort__local_weight_cmp, + .se_snprintf = hist_entry__local_weight_snprintf, + .se_width_idx = HISTC_LOCAL_WEIGHT, +}; + +static int64_t +sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->stat.weight - right->stat.weight; +} + +static int hist_entry__global_weight_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*llu", width, self->stat.weight); +} + +struct sort_entry sort_global_weight = { + .se_header = "Weight", + .se_cmp = sort__global_weight_cmp, + .se_snprintf = hist_entry__global_weight_snprintf, + .se_width_idx = HISTC_GLOBAL_WEIGHT, +}; + +struct sort_entry sort_mem_daddr_sym = { + .se_header = "Data Symbol", + .se_cmp = sort__daddr_cmp, + .se_snprintf = hist_entry__daddr_snprintf, + .se_width_idx = HISTC_MEM_DADDR_SYMBOL, +}; + +struct sort_entry sort_mem_daddr_dso = { + .se_header = "Data Object", + .se_cmp = sort__dso_daddr_cmp, + .se_snprintf = hist_entry__dso_daddr_snprintf, + .se_width_idx = HISTC_MEM_DADDR_SYMBOL, +}; + +struct sort_entry sort_mem_locked = { + .se_header = "Locked", + .se_cmp = sort__locked_cmp, + .se_snprintf = hist_entry__locked_snprintf, + .se_width_idx = HISTC_MEM_LOCKED, +}; + +struct sort_entry sort_mem_tlb = { + .se_header = "TLB access", + .se_cmp = sort__tlb_cmp, + .se_snprintf = hist_entry__tlb_snprintf, + .se_width_idx = HISTC_MEM_TLB, +}; + +struct sort_entry sort_mem_lvl = { + .se_header = "Memory access", + .se_cmp = sort__lvl_cmp, + .se_snprintf = hist_entry__lvl_snprintf, + .se_width_idx = HISTC_MEM_LVL, +}; + +struct sort_entry sort_mem_snoop = { + .se_header = "Snoop", + .se_cmp = sort__snoop_cmp, + .se_snprintf = hist_entry__snoop_snprintf, + .se_width_idx = HISTC_MEM_SNOOP, +}; + struct sort_dimension { const char *name; struct sort_entry *entry; @@ -496,6 +888,36 @@ static struct sort_dimension bstack_sort_dimensions[] = { #undef DIM +#define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) } + +static struct sort_dimension memory_sort_dimensions[] = { + DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), + DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), + DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym), + DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso), + DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked), + DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb), + DIM(SORT_MEM_LVL, "mem", sort_mem_lvl), + DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), +}; + +#undef DIM + +static void __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx) +{ + if (sd->taken) + return; + + if (sd->entry->se_collapse) + sort__need_collapse = 1; + + if (list_empty(&hist_entry__sort_list)) + sort__first_dimension = idx; + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; +} + int sort_dimension__add(const char *tok) { unsigned int i; @@ -520,18 +942,7 @@ int sort_dimension__add(const char *tok) sort__has_sym = 1; } - if (sd->taken) - return 0; - - if (sd->entry->se_collapse) - sort__need_collapse = 1; - - if (list_empty(&hist_entry__sort_list)) - sort__first_dimension = i; - - list_add_tail(&sd->entry->list, &hist_entry__sort_list); - sd->taken = 1; - + __sort_dimension__add(sd, i); return 0; } @@ -541,24 +952,29 @@ int sort_dimension__add(const char *tok) if (strncasecmp(tok, sd->name, strlen(tok))) continue; - if (sort__branch_mode != 1) + if (sort__mode != SORT_MODE__BRANCH) return -EINVAL; if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) sort__has_sym = 1; - if (sd->taken) - return 0; + __sort_dimension__add(sd, i + __SORT_BRANCH_STACK); + return 0; + } + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { + struct sort_dimension *sd = &memory_sort_dimensions[i]; - if (sd->entry->se_collapse) - sort__need_collapse = 1; + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; - if (list_empty(&hist_entry__sort_list)) - sort__first_dimension = i + __SORT_BRANCH_STACK; + if (sort__mode != SORT_MODE__MEMORY) + return -EINVAL; - list_add_tail(&sd->entry->list, &hist_entry__sort_list); - sd->taken = 1; + if (sd->entry == &sort_mem_daddr_sym) + sort__has_sym = 1; + __sort_dimension__add(sd, i + __SORT_MEMORY_MODE); return 0; } @@ -591,8 +1007,9 @@ int setup_sorting(void) return ret; } -void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, - const char *list_name, FILE *fp) +static void sort_entry__setup_elide(struct sort_entry *self, + struct strlist *list, + const char *list_name, FILE *fp) { if (list && strlist__nr_entries(list) == 1) { if (fp != NULL) @@ -601,3 +1018,42 @@ void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, self->elide = true; } } + +void sort__setup_elide(FILE *output) +{ + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, + "dso", output); + sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, + "comm", output); + sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, + "symbol", output); + + if (sort__mode == SORT_MODE__BRANCH) { + sort_entry__setup_elide(&sort_dso_from, + symbol_conf.dso_from_list, + "dso_from", output); + sort_entry__setup_elide(&sort_dso_to, + symbol_conf.dso_to_list, + "dso_to", output); + sort_entry__setup_elide(&sort_sym_from, + symbol_conf.sym_from_list, + "sym_from", output); + sort_entry__setup_elide(&sort_sym_to, + symbol_conf.sym_to_list, + "sym_to", output); + } else if (sort__mode == SORT_MODE__MEMORY) { + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, + "symbol_daddr", output); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, + "dso_daddr", output); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, + "mem", output); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, + "local_weight", output); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, + "tlb", output); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, + "snoop", output); + } + +} diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index b13e56f6ccbe..45ac84c1e037 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -32,7 +32,7 @@ extern const char default_sort_order[]; extern int sort__need_collapse; extern int sort__has_parent; extern int sort__has_sym; -extern int sort__branch_mode; +extern enum sort_mode sort__mode; extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; extern struct sort_entry sort_sym; @@ -49,6 +49,7 @@ struct he_stat { u64 period_us; u64 period_guest_sys; u64 period_guest_us; + u64 weight; u32 nr_events; }; @@ -100,7 +101,8 @@ struct hist_entry { struct rb_root sorted_chain; struct branch_info *branch_info; struct hists *hists; - struct callchain_root callchain[0]; + struct mem_info *mem_info; + struct callchain_root callchain[0]; /* must be last member */ }; static inline bool hist_entry__has_pairs(struct hist_entry *he) @@ -115,12 +117,18 @@ static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he) return NULL; } -static inline void hist_entry__add_pair(struct hist_entry *he, - struct hist_entry *pair) +static inline void hist_entry__add_pair(struct hist_entry *pair, + struct hist_entry *he) { - list_add_tail(&he->pairs.head, &pair->pairs.node); + list_add_tail(&pair->pairs.node, &he->pairs.head); } +enum sort_mode { + SORT_MODE__NORMAL, + SORT_MODE__BRANCH, + SORT_MODE__MEMORY, +}; + enum sort_type { /* common sort keys */ SORT_PID, @@ -138,6 +146,17 @@ enum sort_type { SORT_SYM_FROM, SORT_SYM_TO, SORT_MISPREDICT, + + /* memory mode specific sort keys */ + __SORT_MEMORY_MODE, + SORT_LOCAL_WEIGHT = __SORT_MEMORY_MODE, + SORT_GLOBAL_WEIGHT, + SORT_MEM_DADDR_SYMBOL, + SORT_MEM_DADDR_DSO, + SORT_MEM_LOCKED, + SORT_MEM_TLB, + SORT_MEM_LVL, + SORT_MEM_SNOOP, }; /* @@ -162,7 +181,6 @@ extern struct list_head hist_entry__sort_list; int setup_sorting(void); extern int sort_dimension__add(const char *); -void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, - const char *list_name, FILE *fp); +void sort__setup_elide(FILE *fp); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 23742126f47c..7c59c28afcc5 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -37,7 +37,7 @@ double stddev_stats(struct stats *stats) { double variance, variance_mean; - if (!stats->n) + if (stats->n < 2) return 0.0; variance = stats->M2 / (stats->n - 1); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 54efcb5659ac..4b12bf850325 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -806,9 +806,12 @@ int dso__load_sym(struct dso *dso, struct map *map, * DWARF DW_compile_unit has this, but we don't always have access * to it... */ - demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI); - if (demangled != NULL) - elf_name = demangled; + if (symbol_conf.demangle) { + demangled = bfd_demangle(NULL, elf_name, + DMGL_PARAMS | DMGL_ANSI); + if (demangled != NULL) + elf_name = demangled; + } new_symbol: f = symbol__new(sym.st_value, sym.st_size, GELF_ST_BIND(sym.st_info), elf_name); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e6432d85b43d..8cf3b5426a9a 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -36,6 +36,7 @@ struct symbol_conf symbol_conf = { .use_modules = true, .try_vmlinux_path = true, .annotate_src = true, + .demangle = true, .symfs = "", }; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index b62ca37c4b77..5f720dc076da 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -97,7 +97,8 @@ struct symbol_conf { kptr_restrict, annotate_asm_raw, annotate_src, - event_group; + event_group, + demangle; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -155,6 +156,12 @@ struct branch_info { struct branch_flags flags; }; +struct mem_info { + struct addr_map_symbol iaddr; + struct addr_map_symbol daddr; + union perf_mem_data_src data_src; +}; + struct addr_location { struct thread *thread; struct map *map; diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 632e40e5ceca..40399cbcca77 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -14,6 +14,7 @@ struct thread *thread__new(pid_t pid) if (self != NULL) { map_groups__init(&self->mg); self->pid = pid; + self->ppid = -1; self->comm = malloc(32); if (self->comm) snprintf(self->comm, 32, ":%d", self->pid); @@ -82,5 +83,8 @@ int thread__fork(struct thread *self, struct thread *parent) for (i = 0; i < MAP__NR_TYPES; ++i) if (map_groups__clone(&self->mg, &parent->mg, i) < 0) return -ENOMEM; + + self->ppid = parent->pid; + return 0; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 5ad266403098..eeb7ac62b9e3 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -13,6 +13,7 @@ struct thread { }; struct map_groups mg; pid_t pid; + pid_t ppid; char shortname[3]; bool comm_set; char *comm; diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index f718df8a3c59..0cd8b3108084 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -21,4 +21,9 @@ void thread_map__delete(struct thread_map *threads); size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); +static inline int thread_map__nr(struct thread_map *threads) +{ + return threads ? threads->nr : 1; +} + #endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 54d37a4753c5..f857b51b6bde 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -23,20 +23,31 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) { - float samples_per_sec = top->samples / top->delay_secs; - float ksamples_per_sec = top->kernel_samples / top->delay_secs; - float esamples_percent = (100.0 * top->exact_samples) / top->samples; + float samples_per_sec; + float ksamples_per_sec; + float esamples_percent; struct perf_record_opts *opts = &top->record_opts; struct perf_target *target = &opts->target; size_t ret = 0; + if (top->samples) { + samples_per_sec = top->samples / top->delay_secs; + ksamples_per_sec = top->kernel_samples / top->delay_secs; + esamples_percent = (100.0 * top->exact_samples) / top->samples; + } else { + samples_per_sec = ksamples_per_sec = esamples_percent = 0.0; + } + if (!perf_guest) { + float ksamples_percent = 0.0; + + if (samples_per_sec) + ksamples_percent = (100.0 * ksamples_per_sec) / + samples_per_sec; ret = SNPRINTF(bf, size, " PerfTop:%8.0f irqs/sec kernel:%4.1f%%" " exact: %4.1f%% [", samples_per_sec, - 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) / - samples_per_sec)), - esamples_percent); + ksamples_percent, esamples_percent); } else { float us_samples_per_sec = top->us_samples / top->delay_secs; float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs; diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 7ebf357dc9e1..df46be93d902 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -26,7 +26,6 @@ struct perf_top { int print_entries, count_filter, delay_secs; bool hide_kernel_symbols, hide_user_symbols, zero; bool use_tui, use_stdio; - bool sort_has_symbols; bool kptr_restrict_warned; bool vmlinux_warned; bool dump_symtab; @@ -37,6 +36,7 @@ struct perf_top { int realtime_prio; int sym_pcnt_filter; const char *sym_filter; + float min_percent; }; size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size); diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index a8d81c35ef66..3917eb9a8479 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -38,52 +38,20 @@ #include "../perf.h" #include "trace-event.h" -#include "debugfs.h" +#include <lk/debugfs.h> #include "evsel.h" #define VERSION "0.5" -#define TRACE_CTRL "tracing_on" -#define TRACE "trace" -#define AVAILABLE "available_tracers" -#define CURRENT "current_tracer" -#define ITER_CTRL "trace_options" -#define MAX_LATENCY "tracing_max_latency" - -unsigned int page_size; - -static const char *output_file = "trace.info"; static int output_fd; -struct event_list { - struct event_list *next; - const char *event; -}; - -struct events { - struct events *sibling; - struct events *children; - struct events *next; - char *name; -}; - - -static void *malloc_or_die(unsigned int size) -{ - void *data; - - data = malloc(size); - if (!data) - die("malloc"); - return data; -} static const char *find_debugfs(void) { - const char *path = debugfs_mount(NULL); + const char *path = perf_debugfs_mount(NULL); if (!path) - die("Your kernel not support debugfs filesystem"); + pr_debug("Your kernel does not support the debugfs filesystem"); return path; } @@ -102,8 +70,12 @@ static const char *find_tracing_dir(void) return tracing; debugfs = find_debugfs(); + if (!debugfs) + return NULL; - tracing = malloc_or_die(strlen(debugfs) + 9); + tracing = malloc(strlen(debugfs) + 9); + if (!tracing) + return NULL; sprintf(tracing, "%s/tracing", debugfs); @@ -120,7 +92,9 @@ static char *get_tracing_file(const char *name) if (!tracing) return NULL; - file = malloc_or_die(strlen(tracing) + strlen(name) + 2); + file = malloc(strlen(tracing) + strlen(name) + 2); + if (!file) + return NULL; sprintf(file, "%s/%s", tracing, name); return file; @@ -131,24 +105,6 @@ static void put_tracing_file(char *file) free(file); } -static ssize_t calc_data_size; - -static ssize_t write_or_die(const void *buf, size_t len) -{ - int ret; - - if (calc_data_size) { - calc_data_size += len; - return len; - } - - ret = write(output_fd, buf, len); - if (ret < 0) - die("writing to '%s'", output_file); - - return ret; -} - int bigendian(void) { unsigned char str[] = { 0x1, 0x2, 0x3, 0x4, 0x0, 0x0, 0x0, 0x0}; @@ -159,59 +115,106 @@ int bigendian(void) } /* unfortunately, you can not stat debugfs or proc files for size */ -static void record_file(const char *file, size_t hdr_sz) +static int record_file(const char *file, ssize_t hdr_sz) { unsigned long long size = 0; char buf[BUFSIZ], *sizep; off_t hdr_pos = lseek(output_fd, 0, SEEK_CUR); int r, fd; + int err = -EIO; fd = open(file, O_RDONLY); - if (fd < 0) - die("Can't read '%s'", file); + if (fd < 0) { + pr_debug("Can't read '%s'", file); + return -errno; + } /* put in zeros for file size, then fill true size later */ - if (hdr_sz) - write_or_die(&size, hdr_sz); + if (hdr_sz) { + if (write(output_fd, &size, hdr_sz) != hdr_sz) + goto out; + } do { r = read(fd, buf, BUFSIZ); if (r > 0) { size += r; - write_or_die(buf, r); + if (write(output_fd, buf, r) != r) + goto out; } } while (r > 0); - close(fd); /* ugh, handle big-endian hdr_size == 4 */ sizep = (char*)&size; if (bigendian()) sizep += sizeof(u64) - hdr_sz; - if (hdr_sz && pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0) - die("writing to %s", output_file); + if (hdr_sz && pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0) { + pr_debug("writing file size failed\n"); + goto out; + } + + err = 0; +out: + close(fd); + return err; } -static void read_header_files(void) +static int read_header_files(void) { char *path; struct stat st; + int err = -EIO; path = get_tracing_file("events/header_page"); - if (stat(path, &st) < 0) - die("can't read '%s'", path); + if (!path) { + pr_debug("can't get tracing/events/header_page"); + return -ENOMEM; + } + + if (stat(path, &st) < 0) { + pr_debug("can't read '%s'", path); + goto out; + } + + if (write(output_fd, "header_page", 12) != 12) { + pr_debug("can't write header_page\n"); + goto out; + } + + if (record_file(path, 8) < 0) { + pr_debug("can't record header_page file\n"); + goto out; + } - write_or_die("header_page", 12); - record_file(path, 8); put_tracing_file(path); path = get_tracing_file("events/header_event"); - if (stat(path, &st) < 0) - die("can't read '%s'", path); + if (!path) { + pr_debug("can't get tracing/events/header_event"); + err = -ENOMEM; + goto out; + } + + if (stat(path, &st) < 0) { + pr_debug("can't read '%s'", path); + goto out; + } - write_or_die("header_event", 13); - record_file(path, 8); + if (write(output_fd, "header_event", 13) != 13) { + pr_debug("can't write header_event\n"); + goto out; + } + + if (record_file(path, 8) < 0) { + pr_debug("can't record header_event file\n"); + goto out; + } + + err = 0; +out: put_tracing_file(path); + return err; } static bool name_in_tp_list(char *sys, struct tracepoint_path *tps) @@ -225,7 +228,7 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } -static void copy_event_system(const char *sys, struct tracepoint_path *tps) +static int copy_event_system(const char *sys, struct tracepoint_path *tps) { struct dirent *dent; struct stat st; @@ -233,10 +236,13 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps) DIR *dir; int count = 0; int ret; + int err; dir = opendir(sys); - if (!dir) - die("can't read directory '%s'", sys); + if (!dir) { + pr_debug("can't read directory '%s'", sys); + return -errno; + } while ((dent = readdir(dir))) { if (dent->d_type != DT_DIR || @@ -244,7 +250,11 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10); + format = malloc(strlen(sys) + strlen(dent->d_name) + 10); + if (!format) { + err = -ENOMEM; + goto out; + } sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); free(format); @@ -253,7 +263,11 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps) count++; } - write_or_die(&count, 4); + if (write(output_fd, &count, 4) != 4) { + err = -EIO; + pr_debug("can't write count\n"); + goto out; + } rewinddir(dir); while ((dent = readdir(dir))) { @@ -262,27 +276,45 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps) strcmp(dent->d_name, "..") == 0 || !name_in_tp_list(dent->d_name, tps)) continue; - format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10); + format = malloc(strlen(sys) + strlen(dent->d_name) + 10); + if (!format) { + err = -ENOMEM; + goto out; + } sprintf(format, "%s/%s/format", sys, dent->d_name); ret = stat(format, &st); - if (ret >= 0) - record_file(format, 8); - + if (ret >= 0) { + err = record_file(format, 8); + if (err) { + free(format); + goto out; + } + } free(format); } + err = 0; +out: closedir(dir); + return err; } -static void read_ftrace_files(struct tracepoint_path *tps) +static int read_ftrace_files(struct tracepoint_path *tps) { char *path; + int ret; path = get_tracing_file("events/ftrace"); + if (!path) { + pr_debug("can't get tracing/events/ftrace"); + return -ENOMEM; + } - copy_event_system(path, tps); + ret = copy_event_system(path, tps); put_tracing_file(path); + + return ret; } static bool system_in_tp_list(char *sys, struct tracepoint_path *tps) @@ -296,7 +328,7 @@ static bool system_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } -static void read_event_files(struct tracepoint_path *tps) +static int read_event_files(struct tracepoint_path *tps) { struct dirent *dent; struct stat st; @@ -305,12 +337,20 @@ static void read_event_files(struct tracepoint_path *tps) DIR *dir; int count = 0; int ret; + int err; path = get_tracing_file("events"); + if (!path) { + pr_debug("can't get tracing/events"); + return -ENOMEM; + } dir = opendir(path); - if (!dir) - die("can't read directory '%s'", path); + if (!dir) { + err = -errno; + pr_debug("can't read directory '%s'", path); + goto out; + } while ((dent = readdir(dir))) { if (dent->d_type != DT_DIR || @@ -322,7 +362,11 @@ static void read_event_files(struct tracepoint_path *tps) count++; } - write_or_die(&count, 4); + if (write(output_fd, &count, 4) != 4) { + err = -EIO; + pr_debug("can't write count\n"); + goto out; + } rewinddir(dir); while ((dent = readdir(dir))) { @@ -332,56 +376,90 @@ static void read_event_files(struct tracepoint_path *tps) strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; - sys = malloc_or_die(strlen(path) + strlen(dent->d_name) + 2); + sys = malloc(strlen(path) + strlen(dent->d_name) + 2); + if (!sys) { + err = -ENOMEM; + goto out; + } sprintf(sys, "%s/%s", path, dent->d_name); ret = stat(sys, &st); if (ret >= 0) { - write_or_die(dent->d_name, strlen(dent->d_name) + 1); - copy_event_system(sys, tps); + ssize_t size = strlen(dent->d_name) + 1; + + if (write(output_fd, dent->d_name, size) != size || + copy_event_system(sys, tps) < 0) { + err = -EIO; + free(sys); + goto out; + } } free(sys); } - + err = 0; +out: closedir(dir); put_tracing_file(path); + + return err; } -static void read_proc_kallsyms(void) +static int read_proc_kallsyms(void) { unsigned int size; const char *path = "/proc/kallsyms"; struct stat st; - int ret; + int ret, err = 0; ret = stat(path, &st); if (ret < 0) { /* not found */ size = 0; - write_or_die(&size, 4); - return; + if (write(output_fd, &size, 4) != 4) + err = -EIO; + return err; } - record_file(path, 4); + return record_file(path, 4); } -static void read_ftrace_printk(void) +static int read_ftrace_printk(void) { unsigned int size; char *path; struct stat st; - int ret; + int ret, err = 0; path = get_tracing_file("printk_formats"); + if (!path) { + pr_debug("can't get tracing/printk_formats"); + return -ENOMEM; + } + ret = stat(path, &st); if (ret < 0) { /* not found */ size = 0; - write_or_die(&size, 4); + if (write(output_fd, &size, 4) != 4) + err = -EIO; goto out; } - record_file(path, 4); + err = record_file(path, 4); out: put_tracing_file(path); + return err; +} + +static void +put_tracepoints_path(struct tracepoint_path *tps) +{ + while (tps) { + struct tracepoint_path *t = tps; + + tps = tps->next; + free(t->name); + free(t->system); + free(t); + } } static struct tracepoint_path * @@ -396,27 +474,17 @@ get_tracepoints_path(struct list_head *pattrs) continue; ++nr_tracepoints; ppath->next = tracepoint_id_to_path(pos->attr.config); - if (!ppath->next) - die("%s\n", "No memory to alloc tracepoints list"); + if (!ppath->next) { + pr_debug("No memory to alloc tracepoints list\n"); + put_tracepoints_path(&path); + return NULL; + } ppath = ppath->next; } return nr_tracepoints > 0 ? path.next : NULL; } -static void -put_tracepoints_path(struct tracepoint_path *tps) -{ - while (tps) { - struct tracepoint_path *t = tps; - - tps = tps->next; - free(t->name); - free(t->system); - free(t); - } -} - bool have_tracepoints(struct list_head *pattrs) { struct perf_evsel *pos; @@ -428,9 +496,10 @@ bool have_tracepoints(struct list_head *pattrs) return false; } -static void tracing_data_header(void) +static int tracing_data_header(void) { char buf[20]; + ssize_t size; /* just guessing this is someone's birthday.. ;) */ buf[0] = 23; @@ -438,9 +507,12 @@ static void tracing_data_header(void) buf[2] = 68; memcpy(buf + 3, "tracing", 7); - write_or_die(buf, 10); + if (write(output_fd, buf, 10) != 10) + return -1; - write_or_die(VERSION, strlen(VERSION) + 1); + size = strlen(VERSION) + 1; + if (write(output_fd, VERSION, size) != size) + return -1; /* save endian */ if (bigendian()) @@ -450,15 +522,19 @@ static void tracing_data_header(void) read_trace_init(buf[0], buf[0]); - write_or_die(buf, 1); + if (write(output_fd, buf, 1) != 1) + return -1; /* save size of long */ buf[0] = sizeof(long); - write_or_die(buf, 1); + if (write(output_fd, buf, 1) != 1) + return -1; /* save page_size */ - page_size = sysconf(_SC_PAGESIZE); - write_or_die(&page_size, 4); + if (write(output_fd, &page_size, 4) != 4) + return -1; + + return 0; } struct tracing_data *tracing_data_get(struct list_head *pattrs, @@ -466,6 +542,7 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, { struct tracepoint_path *tps; struct tracing_data *tdata; + int err; output_fd = fd; @@ -473,7 +550,10 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, if (!tps) return NULL; - tdata = malloc_or_die(sizeof(*tdata)); + tdata = malloc(sizeof(*tdata)); + if (!tdata) + return NULL; + tdata->temp = temp; tdata->size = 0; @@ -482,12 +562,16 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, snprintf(tdata->temp_file, sizeof(tdata->temp_file), "/tmp/perf-XXXXXX"); - if (!mkstemp(tdata->temp_file)) - die("Can't make temp file"); + if (!mkstemp(tdata->temp_file)) { + pr_debug("Can't make temp file"); + return NULL; + } temp_fd = open(tdata->temp_file, O_RDWR); - if (temp_fd < 0) - die("Can't read '%s'", tdata->temp_file); + if (temp_fd < 0) { + pr_debug("Can't read '%s'", tdata->temp_file); + return NULL; + } /* * Set the temp file the default output, so all the @@ -496,13 +580,24 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, output_fd = temp_fd; } - tracing_data_header(); - read_header_files(); - read_ftrace_files(tps); - read_event_files(tps); - read_proc_kallsyms(); - read_ftrace_printk(); + err = tracing_data_header(); + if (err) + goto out; + err = read_header_files(); + if (err) + goto out; + err = read_ftrace_files(tps); + if (err) + goto out; + err = read_event_files(tps); + if (err) + goto out; + err = read_proc_kallsyms(); + if (err) + goto out; + err = read_ftrace_printk(); +out: /* * All tracing data are stored by now, we can restore * the default output file in case we used temp file. @@ -513,22 +608,31 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, output_fd = fd; } + if (err) { + free(tdata); + tdata = NULL; + } + put_tracepoints_path(tps); return tdata; } -void tracing_data_put(struct tracing_data *tdata) +int tracing_data_put(struct tracing_data *tdata) { + int err = 0; + if (tdata->temp) { - record_file(tdata->temp_file, 0); + err = record_file(tdata->temp_file, 0); unlink(tdata->temp_file); } free(tdata); + return err; } int read_tracing_data(int fd, struct list_head *pattrs) { + int err; struct tracing_data *tdata; /* @@ -539,6 +643,6 @@ int read_tracing_data(int fd, struct list_head *pattrs) if (!tdata) return -ENOMEM; - tracing_data_put(tdata); - return 0; + err = tracing_data_put(tdata); + return err; } diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 3aabcd687cd5..4454835a9ebc 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -183,43 +183,6 @@ void event_format__print(struct event_format *event, trace_seq_do_printf(&s); } -void print_trace_event(struct pevent *pevent, int cpu, void *data, int size) -{ - int type = trace_parse_common_type(pevent, data); - struct event_format *event = pevent_find_event(pevent, type); - - if (!event) { - warning("ug! no event found for type %d", type); - return; - } - - event_format__print(event, cpu, data, size); -} - -void print_event(struct pevent *pevent, int cpu, void *data, int size, - unsigned long long nsecs, char *comm) -{ - struct pevent_record record; - struct trace_seq s; - int pid; - - pevent->latency_format = latency_format; - - record.ts = nsecs; - record.cpu = cpu; - record.size = size; - record.data = data; - pid = pevent_data_pid(pevent, &record); - - if (!pevent_pid_is_registered(pevent, pid)) - pevent_register_comm(pevent, comm, pid); - - trace_seq_init(&s); - pevent_print_event(pevent, &s, &record); - trace_seq_do_printf(&s); - printf("\n"); -} - void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size __maybe_unused) { diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 3741572696af..af215c0d2379 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -18,8 +18,6 @@ * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -#define _FILE_OFFSET_BITS 64 - #include <dirent.h> #include <stdio.h> #include <stdlib.h> @@ -41,26 +39,14 @@ static int input_fd; -static int read_page; - int file_bigendian; int host_bigendian; static int long_size; -static ssize_t calc_data_size; +static ssize_t trace_data_size; static bool repipe; -static void *malloc_or_die(int size) -{ - void *ret; - - ret = malloc(size); - if (!ret) - die("malloc"); - return ret; -} - -static int do_read(int fd, void *buf, int size) +static int __do_read(int fd, void *buf, int size) { int rsize = size; @@ -73,8 +59,10 @@ static int do_read(int fd, void *buf, int size) if (repipe) { int retw = write(STDOUT_FILENO, buf, ret); - if (retw <= 0 || retw != ret) - die("repiping input file"); + if (retw <= 0 || retw != ret) { + pr_debug("repiping input file"); + return -1; + } } size -= ret; @@ -84,17 +72,18 @@ static int do_read(int fd, void *buf, int size) return rsize; } -static int read_or_die(void *data, int size) +static int do_read(void *data, int size) { int r; - r = do_read(input_fd, data, size); - if (r <= 0) - die("reading input file (size expected=%d received=%d)", - size, r); + r = __do_read(input_fd, data, size); + if (r <= 0) { + pr_debug("reading input file (size expected=%d received=%d)", + size, r); + return -1; + } - if (calc_data_size) - calc_data_size += r; + trace_data_size += r; return r; } @@ -107,7 +96,7 @@ static void skip(int size) while (size) { r = size > BUFSIZ ? BUFSIZ : size; - read_or_die(buf, r); + do_read(buf, r); size -= r; }; } @@ -116,7 +105,8 @@ static unsigned int read4(struct pevent *pevent) { unsigned int data; - read_or_die(&data, 4); + if (do_read(&data, 4) < 0) + return 0; return __data2host4(pevent, data); } @@ -124,7 +114,8 @@ static unsigned long long read8(struct pevent *pevent) { unsigned long long data; - read_or_die(&data, 8); + if (do_read(&data, 8) < 0) + return 0; return __data2host8(pevent, data); } @@ -138,17 +129,23 @@ static char *read_string(void) for (;;) { r = read(input_fd, &c, 1); - if (r < 0) - die("reading input file"); + if (r < 0) { + pr_debug("reading input file"); + goto out; + } - if (!r) - die("no data"); + if (!r) { + pr_debug("no data"); + goto out; + } if (repipe) { int retw = write(STDOUT_FILENO, &c, 1); - if (retw <= 0 || retw != r) - die("repiping input file string"); + if (retw <= 0 || retw != r) { + pr_debug("repiping input file string"); + goto out; + } } buf[size++] = c; @@ -157,60 +154,79 @@ static char *read_string(void) break; } - if (calc_data_size) - calc_data_size += size; - - str = malloc_or_die(size); - memcpy(str, buf, size); + trace_data_size += size; + str = malloc(size); + if (str) + memcpy(str, buf, size); +out: return str; } -static void read_proc_kallsyms(struct pevent *pevent) +static int read_proc_kallsyms(struct pevent *pevent) { unsigned int size; char *buf; size = read4(pevent); if (!size) - return; + return 0; + + buf = malloc(size + 1); + if (buf == NULL) + return -1; - buf = malloc_or_die(size + 1); - read_or_die(buf, size); + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } buf[size] = '\0'; parse_proc_kallsyms(pevent, buf, size); free(buf); + return 0; } -static void read_ftrace_printk(struct pevent *pevent) +static int read_ftrace_printk(struct pevent *pevent) { unsigned int size; char *buf; + /* it can have 0 size */ size = read4(pevent); if (!size) - return; + return 0; + + buf = malloc(size); + if (buf == NULL) + return -1; - buf = malloc_or_die(size); - read_or_die(buf, size); + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } parse_ftrace_printk(pevent, buf, size); free(buf); + return 0; } -static void read_header_files(struct pevent *pevent) +static int read_header_files(struct pevent *pevent) { unsigned long long size; char *header_event; char buf[BUFSIZ]; + int ret = 0; - read_or_die(buf, 12); + if (do_read(buf, 12) < 0) + return -1; - if (memcmp(buf, "header_page", 12) != 0) - die("did not read header page"); + if (memcmp(buf, "header_page", 12) != 0) { + pr_debug("did not read header page"); + return -1; + } size = read8(pevent); skip(size); @@ -221,269 +237,107 @@ static void read_header_files(struct pevent *pevent) */ long_size = header_page_size_size; - read_or_die(buf, 13); - if (memcmp(buf, "header_event", 13) != 0) - die("did not read header event"); + if (do_read(buf, 13) < 0) + return -1; + + if (memcmp(buf, "header_event", 13) != 0) { + pr_debug("did not read header event"); + return -1; + } size = read8(pevent); - header_event = malloc_or_die(size); - read_or_die(header_event, size); + header_event = malloc(size); + if (header_event == NULL) + return -1; + + if (do_read(header_event, size) < 0) + ret = -1; + free(header_event); + return ret; } -static void read_ftrace_file(struct pevent *pevent, unsigned long long size) +static int read_ftrace_file(struct pevent *pevent, unsigned long long size) { char *buf; - buf = malloc_or_die(size); - read_or_die(buf, size); + buf = malloc(size); + if (buf == NULL) + return -1; + + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } + parse_ftrace_file(pevent, buf, size); free(buf); + return 0; } -static void read_event_file(struct pevent *pevent, char *sys, +static int read_event_file(struct pevent *pevent, char *sys, unsigned long long size) { char *buf; - buf = malloc_or_die(size); - read_or_die(buf, size); + buf = malloc(size); + if (buf == NULL) + return -1; + + if (do_read(buf, size) < 0) { + free(buf); + return -1; + } + parse_event_file(pevent, buf, size, sys); free(buf); + return 0; } -static void read_ftrace_files(struct pevent *pevent) +static int read_ftrace_files(struct pevent *pevent) { unsigned long long size; int count; int i; + int ret; count = read4(pevent); for (i = 0; i < count; i++) { size = read8(pevent); - read_ftrace_file(pevent, size); + ret = read_ftrace_file(pevent, size); + if (ret) + return ret; } + return 0; } -static void read_event_files(struct pevent *pevent) +static int read_event_files(struct pevent *pevent) { unsigned long long size; char *sys; int systems; int count; int i,x; + int ret; systems = read4(pevent); for (i = 0; i < systems; i++) { sys = read_string(); + if (sys == NULL) + return -1; count = read4(pevent); + for (x=0; x < count; x++) { size = read8(pevent); - read_event_file(pevent, sys, size); + ret = read_event_file(pevent, sys, size); + if (ret) + return ret; } } -} - -struct cpu_data { - unsigned long long offset; - unsigned long long size; - unsigned long long timestamp; - struct pevent_record *next; - char *page; - int cpu; - int index; - int page_size; -}; - -static struct cpu_data *cpu_data; - -static void update_cpu_data_index(int cpu) -{ - cpu_data[cpu].offset += page_size; - cpu_data[cpu].size -= page_size; - cpu_data[cpu].index = 0; -} - -static void get_next_page(int cpu) -{ - off_t save_seek; - off_t ret; - - if (!cpu_data[cpu].page) - return; - - if (read_page) { - if (cpu_data[cpu].size <= page_size) { - free(cpu_data[cpu].page); - cpu_data[cpu].page = NULL; - return; - } - - update_cpu_data_index(cpu); - - /* other parts of the code may expect the pointer to not move */ - save_seek = lseek(input_fd, 0, SEEK_CUR); - - ret = lseek(input_fd, cpu_data[cpu].offset, SEEK_SET); - if (ret == (off_t)-1) - die("failed to lseek"); - ret = read(input_fd, cpu_data[cpu].page, page_size); - if (ret < 0) - die("failed to read page"); - - /* reset the file pointer back */ - lseek(input_fd, save_seek, SEEK_SET); - - return; - } - - munmap(cpu_data[cpu].page, page_size); - cpu_data[cpu].page = NULL; - - if (cpu_data[cpu].size <= page_size) - return; - - update_cpu_data_index(cpu); - - cpu_data[cpu].page = mmap(NULL, page_size, PROT_READ, MAP_PRIVATE, - input_fd, cpu_data[cpu].offset); - if (cpu_data[cpu].page == MAP_FAILED) - die("failed to mmap cpu %d at offset 0x%llx", - cpu, cpu_data[cpu].offset); -} - -static unsigned int type_len4host(unsigned int type_len_ts) -{ - if (file_bigendian) - return (type_len_ts >> 27) & ((1 << 5) - 1); - else - return type_len_ts & ((1 << 5) - 1); -} - -static unsigned int ts4host(unsigned int type_len_ts) -{ - if (file_bigendian) - return type_len_ts & ((1 << 27) - 1); - else - return type_len_ts >> 5; -} - -static int calc_index(void *ptr, int cpu) -{ - return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page; -} - -struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu) -{ - struct pevent_record *data; - void *page = cpu_data[cpu].page; - int idx = cpu_data[cpu].index; - void *ptr = page + idx; - unsigned long long extend; - unsigned int type_len_ts; - unsigned int type_len; - unsigned int delta; - unsigned int length = 0; - - if (cpu_data[cpu].next) - return cpu_data[cpu].next; - - if (!page) - return NULL; - - if (!idx) { - /* FIXME: handle header page */ - if (header_page_ts_size != 8) - die("expected a long long type for timestamp"); - cpu_data[cpu].timestamp = data2host8(pevent, ptr); - ptr += 8; - switch (header_page_size_size) { - case 4: - cpu_data[cpu].page_size = data2host4(pevent, ptr); - ptr += 4; - break; - case 8: - cpu_data[cpu].page_size = data2host8(pevent, ptr); - ptr += 8; - break; - default: - die("bad long size"); - } - ptr = cpu_data[cpu].page + header_page_data_offset; - } - -read_again: - idx = calc_index(ptr, cpu); - - if (idx >= cpu_data[cpu].page_size) { - get_next_page(cpu); - return trace_peek_data(pevent, cpu); - } - - type_len_ts = data2host4(pevent, ptr); - ptr += 4; - - type_len = type_len4host(type_len_ts); - delta = ts4host(type_len_ts); - - switch (type_len) { - case RINGBUF_TYPE_PADDING: - if (!delta) - die("error, hit unexpected end of page"); - length = data2host4(pevent, ptr); - ptr += 4; - length *= 4; - ptr += length; - goto read_again; - - case RINGBUF_TYPE_TIME_EXTEND: - extend = data2host4(pevent, ptr); - ptr += 4; - extend <<= TS_SHIFT; - extend += delta; - cpu_data[cpu].timestamp += extend; - goto read_again; - - case RINGBUF_TYPE_TIME_STAMP: - ptr += 12; - break; - case 0: - length = data2host4(pevent, ptr); - ptr += 4; - die("here! length=%d", length); - break; - default: - length = type_len * 4; - break; - } - - cpu_data[cpu].timestamp += delta; - - data = malloc_or_die(sizeof(*data)); - memset(data, 0, sizeof(*data)); - - data->ts = cpu_data[cpu].timestamp; - data->size = length; - data->data = ptr; - ptr += length; - - cpu_data[cpu].index = calc_index(ptr, cpu); - cpu_data[cpu].next = data; - - return data; -} - -struct pevent_record *trace_read_data(struct pevent *pevent, int cpu) -{ - struct pevent_record *data; - - data = trace_peek_data(pevent, cpu); - cpu_data[cpu].next = NULL; - - return data; + return 0; } ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) @@ -494,58 +348,85 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) int show_version = 0; int show_funcs = 0; int show_printk = 0; - ssize_t size; + ssize_t size = -1; + struct pevent *pevent; + int err; - calc_data_size = 1; - repipe = __repipe; + *ppevent = NULL; + repipe = __repipe; input_fd = fd; - read_or_die(buf, 3); - if (memcmp(buf, test, 3) != 0) - die("no trace data in the file"); + if (do_read(buf, 3) < 0) + return -1; + if (memcmp(buf, test, 3) != 0) { + pr_debug("no trace data in the file"); + return -1; + } - read_or_die(buf, 7); - if (memcmp(buf, "tracing", 7) != 0) - die("not a trace file (missing 'tracing' tag)"); + if (do_read(buf, 7) < 0) + return -1; + if (memcmp(buf, "tracing", 7) != 0) { + pr_debug("not a trace file (missing 'tracing' tag)"); + return -1; + } version = read_string(); + if (version == NULL) + return -1; if (show_version) printf("version = %s\n", version); free(version); - read_or_die(buf, 1); + if (do_read(buf, 1) < 0) + return -1; file_bigendian = buf[0]; host_bigendian = bigendian(); - *ppevent = read_trace_init(file_bigendian, host_bigendian); - if (*ppevent == NULL) - die("read_trace_init failed"); + pevent = read_trace_init(file_bigendian, host_bigendian); + if (pevent == NULL) { + pr_debug("read_trace_init failed"); + goto out; + } - read_or_die(buf, 1); + if (do_read(buf, 1) < 0) + goto out; long_size = buf[0]; - page_size = read4(*ppevent); - - read_header_files(*ppevent); - - read_ftrace_files(*ppevent); - read_event_files(*ppevent); - read_proc_kallsyms(*ppevent); - read_ftrace_printk(*ppevent); - - size = calc_data_size - 1; - calc_data_size = 0; + page_size = read4(pevent); + if (!page_size) + goto out; + + err = read_header_files(pevent); + if (err) + goto out; + err = read_ftrace_files(pevent); + if (err) + goto out; + err = read_event_files(pevent); + if (err) + goto out; + err = read_proc_kallsyms(pevent); + if (err) + goto out; + err = read_ftrace_printk(pevent); + if (err) + goto out; + + size = trace_data_size; repipe = false; if (show_funcs) { - pevent_print_funcs(*ppevent); - return size; - } - if (show_printk) { - pevent_print_printk(*ppevent); - return size; + pevent_print_funcs(pevent); + } else if (show_printk) { + pevent_print_printk(pevent); } + *ppevent = pevent; + pevent = NULL; + +out: + if (pevent) + pevent_free(pevent); return size; } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index a55fd37ffea1..1978c398ad87 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -30,13 +30,9 @@ enum { int bigendian(void); struct pevent *read_trace_init(int file_bigendian, int host_bigendian); -void print_trace_event(struct pevent *pevent, int cpu, void *data, int size); void event_format__print(struct event_format *event, int cpu, void *data, int size); -void print_event(struct pevent *pevent, int cpu, void *data, int size, - unsigned long long nsecs, char *comm); - int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size); int parse_event_file(struct pevent *pevent, char *buf, unsigned long size, char *sys); @@ -72,7 +68,7 @@ struct tracing_data { struct tracing_data *tracing_data_get(struct list_head *pattrs, int fd, bool temp); -void tracing_data_put(struct tracing_data *tdata); +int tracing_data_put(struct tracing_data *tdata); struct addr_location; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 805d1f52c5b4..59d868add275 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -17,6 +17,8 @@ bool test_attr__enabled; bool perf_host = true; bool perf_guest = false; +char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events"; + void event_attr_init(struct perf_event_attr *attr) { if (!perf_host) @@ -242,3 +244,28 @@ void get_term_dimensions(struct winsize *ws) ws->ws_row = 25; ws->ws_col = 80; } + +static void set_tracing_events_path(const char *mountpoint) +{ + snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", + mountpoint, "tracing/events"); +} + +const char *perf_debugfs_mount(const char *mountpoint) +{ + const char *mnt; + + mnt = debugfs_mount(mountpoint); + if (!mnt) + return NULL; + + set_tracing_events_path(mnt); + + return mnt; +} + +void perf_debugfs_set_path(const char *mntpt) +{ + snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt); + set_tracing_events_path(mntpt); +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 09b4c26b71aa..7a484c97e500 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,8 +1,6 @@ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H -#define _FILE_OFFSET_BITS 64 - #ifndef FLEX_ARRAY /* * See if our compiler is known to support flexible array members. @@ -73,10 +71,14 @@ #include <linux/magic.h> #include "types.h" #include <sys/ttydefaults.h> +#include <lk/debugfs.h> extern const char *graph_line; extern const char *graph_dotted_line; extern char buildid_dir[]; +extern char tracing_events_path[]; +extern void perf_debugfs_set_path(const char *mountpoint); +const char *perf_debugfs_mount(const char *mountpoint); /* On most systems <limits.h> would have given us this, but * not on some systems (e.g. GNU/Hurd). @@ -219,8 +221,8 @@ extern unsigned char sane_ctype[256]; #define isalpha(x) sane_istest(x,GIT_ALPHA) #define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) #define isprint(x) sane_istest(x,GIT_PRINT) -#define islower(x) (sane_istest(x,GIT_ALPHA) && sane_istest(x,0x20)) -#define isupper(x) (sane_istest(x,GIT_ALPHA) && !sane_istest(x,0x20)) +#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20)) +#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20)) #define tolower(x) sane_case((unsigned char)(x), 0x20) #define toupper(x) sane_case((unsigned char)(x), 0) @@ -274,5 +276,4 @@ extern unsigned int page_size; struct winsize; void get_term_dimensions(struct winsize *ws); - -#endif +#endif /* GIT_COMPAT_UTIL_H */ |