diff options
Diffstat (limited to 'tools/perf')
189 files changed, 14425 insertions, 6437 deletions
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 9f2e44f2b17..eb30044a922 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -1,3 +1,5 @@ +include ../config/utilities.mak + OUTPUT := ./ ifeq ("$(origin O)", "command line") ifneq ($(O),) @@ -64,6 +66,7 @@ MAKEINFO=makeinfo INSTALL_INFO=install-info DOCBOOK2X_TEXI=docbook2x-texi DBLATEX=dblatex +XMLTO=xmlto ifndef PERL_PATH PERL_PATH = /usr/bin/perl endif @@ -71,6 +74,16 @@ endif -include ../config.mak.autogen -include ../config.mak +_tmp_tool_path := $(call get-executable,$(ASCIIDOC)) +ifeq ($(_tmp_tool_path),) + missing_tools = $(ASCIIDOC) +endif + +_tmp_tool_path := $(call get-executable,$(XMLTO)) +ifeq ($(_tmp_tool_path),) + missing_tools += $(XMLTO) +endif + # # For asciidoc ... # -7.1.2, no extra settings are needed. @@ -170,7 +183,12 @@ pdf: $(OUTPUT)user-manual.pdf install: install-man -install-man: man +check-man-tools: +ifdef missing_tools + $(error "You need to install $(missing_tools) for man pages") +endif + +do-install-man: man $(INSTALL) -d -m 755 $(DESTDIR)$(man1dir) # $(INSTALL) -d -m 755 $(DESTDIR)$(man5dir) # $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir) @@ -178,6 +196,15 @@ install-man: man # $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir) # $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir) +install-man: check-man-tools man + +try-install-man: +ifdef missing_tools + $(warning Please install $(missing_tools) to have the man pages installed) +else + $(MAKE) do-install-man +endif + install-info: info $(INSTALL) -d -m 755 $(DESTDIR)$(infodir) $(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir) @@ -195,10 +222,14 @@ install-pdf: pdf #install-html: html # '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir) +ifneq ($(MAKECMDGOALS),clean) +ifneq ($(MAKECMDGOALS),tags) $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE -include $(OUTPUT)PERF-VERSION-FILE +endif +endif # # Determine "include::" file references in asciidoc files. @@ -246,7 +277,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml $(QUIET_XMLTO)$(RM) $@ && \ - xmlto -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + $(XMLTO) -o $(OUTPUT) -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< $(OUTPUT)%.xml : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt new file mode 100644 index 00000000000..8484c3a04a6 --- /dev/null +++ b/tools/perf/Documentation/android.txt @@ -0,0 +1,78 @@ +How to compile perf for Android +========================================= + +I. Set the Android NDK environment +------------------------------------------------ + +(a). Use the Android NDK +------------------------------------------------ +1. You need to download and install the Android Native Development Kit (NDK). +Set the NDK variable to point to the path where you installed the NDK: + export NDK=/path/to/android-ndk + +2. Set cross-compiling environment variables for NDK toolchain and sysroot. +For arm: + export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi- + export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm +For x86: + export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android- + export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86 + +This method is not working for Android NDK versions up to Revision 8b. +perf uses some bionic enhancements that are not included in these NDK versions. +You can use method (b) described below instead. + +(b). Use the Android source tree +----------------------------------------------- +1. Download the master branch of the Android source tree. +Set the environment for the target you want using: + source build/envsetup.sh + lunch + +2. Build your own NDK sysroot to contain latest bionic changes and set the +NDK sysroot environment variable. + cd ${ANDROID_BUILD_TOP}/ndk +For arm: + ./build/tools/build-ndk-sysroot.sh --abi=arm + export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-arm +For x86: + ./build/tools/build-ndk-sysroot.sh --abi=x86 + export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-x86 + +3. Set the NDK toolchain environment variable. +For arm: + export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/arm-linux-androideabi- +For x86: + export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/i686-linux-android- + +II. Compile perf for Android +------------------------------------------------ +You need to run make with the NDK toolchain and sysroot defined above: +For arm: + make ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}" +For x86: + make ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}" + +III. Install perf +----------------------------------------------- +You need to connect to your Android device/emulator using adb. +Install perf using: + adb push perf /data/perf + +If you also want to use perf-archive you need busybox tools for Android. +For installing perf-archive, you first need to replace #!/bin/bash with #!/system/bin/sh: + sed 's/#!\/bin\/bash/#!\/system\/bin\/sh/g' perf-archive >> /tmp/perf-archive + chmod +x /tmp/perf-archive + adb push /tmp/perf-archive /data/perf-archive + +IV. Environment settings for running perf +------------------------------------------------ +Some perf features need environment variables to run properly. +You need to set these before running perf on the target: + adb shell + # PERF_PAGER=cat + +IV. Run perf +------------------------------------------------ +Run perf on your device/emulator to which you previously connected using adb: + # ./data/perf diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index c8ffd9fd5c6..5ad07ef417f 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -61,11 +61,13 @@ OPTIONS --stdio:: Use the stdio interface. ---tui:: Use the TUI interface Use of --tui requires a tty, if one is not +--tui:: Use the TUI interface. Use of --tui requires a tty, if one is not present, as when piping to other commands, the stdio interface is used. This interfaces starts by centering on the line with more samples, TAB/UNTAB cycles through the lines with more samples. +--gtk:: Use the GTK interface. + -C:: --cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can be provided as a comma-separated list with no space: 0,1. Ranges of @@ -88,6 +90,9 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--skip-missing:: + Skip symbols that cannot be annotated. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index c1057701a7d..e9a8349a717 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -24,6 +24,13 @@ OPTIONS -r:: --remove=:: Remove specified file from the cache. +-M:: +--missing=:: + List missing build ids in the cache for the specified file. +-u:: +--update:: + Update specified file of the cache. It can be used to update kallsyms + kernel dso to vmlinux in order to support annotation. -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index ab7f667de1b..5b3123d5721 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -22,10 +22,6 @@ specified perf.data files. OPTIONS ------- --M:: ---displacement:: - Show position displacement relative to baseline. - -D:: --dump-raw-trace:: Dump raw trace in ASCII. @@ -72,6 +68,66 @@ OPTIONS --symfs=<directory>:: Look for files with symbols relative to this directory. +-b:: +--baseline-only:: + Show only items with match in baseline. + +-c:: +--compute:: + Differential computation selection - delta,ratio,wdiff (default is delta). + If '+' is specified as a first character, the output is sorted based + on the computation results. + See COMPARISON METHODS section for more info. + +-p:: +--period:: + Show period values for both compared hist entries. + +-F:: +--formula:: + Show formula for given computation. + +COMPARISON METHODS +------------------ +delta +~~~~~ +If specified the 'Delta' column is displayed with value 'd' computed as: + + d = A->period_percent - B->period_percent + +with: + - A/B being matching hist entry from first/second file specified + (or perf.data/perf.data.old) respectively. + + - period_percent being the % of the hist entry period value within + single data file + +ratio +~~~~~ +If specified the 'Ratio' column is displayed with value 'r' computed as: + + r = A->period / B->period + +with: + - A/B being matching hist entry from first/second file specified + (or perf.data/perf.data.old) respectively. + + - period being the hist entry period value + +wdiff +~~~~~ +If specified the 'Weighted diff' column is displayed with value 'd' computed as: + + d = B->period * WEIGHT-A - A->period * WEIGHT-B + + - A/B being matching hist entry from first/second file specified + (or perf.data/perf.data.old) respectively. + + - period being the hist entry period value + + - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option + behind ':' separator like '-c wdiff:1,2'. + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt index 15217345c2f..1ceb3700ffb 100644 --- a/tools/perf/Documentation/perf-evlist.txt +++ b/tools/perf/Documentation/perf-evlist.txt @@ -28,6 +28,10 @@ OPTIONS --verbose=:: Show all fields. +-g:: +--group:: + Show event group information. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-list[1], diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt index 025630d43cd..a00a34276c5 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -29,6 +29,17 @@ OPTIONS -v:: --verbose:: Be more verbose. +-i:: +--input=:: + Input file name. (default: stdin) +-o:: +--output=:: + Output file name. (default: stdout) +-s:: +--sched-stat:: + Merge sched_stat and sched_switch for getting events where and how long + tasks slept. sched_switch contains a callchain where a task slept and + sched_stat contains a timeslice how long a task slept. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index b38a1f9ad46..938e8904f64 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -175,7 +175,7 @@ following filters are defined: + The option requires at least one branch type among any, any_call, any_ret, ind_call. -The privilege levels may be ommitted, in which case, the privilege levels of the associated +The privilege levels may be omitted, in which case, the privilege levels of the associated event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege levels are subject to permissions. When sampling on multiple events, branch stack sampling is enabled for all the sampling events. The sampled branch type is the same for all events. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index f4d91bebd59..02284a0067f 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -57,11 +57,44 @@ OPTIONS -s:: --sort=:: - Sort by key(s): pid, comm, dso, symbol, parent, srcline. + 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. + + Each key has following meaning: + + - comm: command (name) of the task which can be read via /proc/<pid>/comm + - pid: command and tid of the task + - dso: name of library or module executed at the time of sample + - symbol: name of function executed at the time of sample + - parent: name of function matched to the parent regex filter. Unmatched + entries are displayed as "[other]". + - cpu: cpu number the task ran at the time of sample + - srcline: filename and line number executed at the time of sample. The + DWARF debuggin info must be provided. + + By default, comm, dso and symbol keys are used. + (i.e. --sort comm,dso,symbol) + + If --branch-stack option is used, following sort keys are also + available: + dso_from, dso_to, symbol_from, symbol_to, mispredict. + + - dso_from: name of library or module branched from + - dso_to: name of library or module branched to + - symbol_from: name of function branched from + - symbol_to: name of function branched to + - mispredict: "N" for predicted branch, "Y" for mispredicted branch + + And default sort keys are changed to comm, dso_from, symbol_from, dso_to + and symbol_to, see '--branch-stack'. -p:: --parent=<regex>:: - regex filter to identify parent, see: '--sort parent' + A regex filter to identify parent. The parent is a caller of this + function and searched through the callchain, thus it requires callchain + information recorded. The pattern is in the exteneded regex format and + defaults to "\^sys_|^do_page_fault", see '--sort parent'. -x:: --exclude-other:: @@ -74,7 +107,6 @@ OPTIONS -t:: --field-separator=:: - Use a special separator character and don't pad with spaces, replacing all occurrences of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. @@ -171,6 +203,9 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--group:: + Show event group information together. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-annotate[1] diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index a4027f221a5..9f1f054b843 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -336,7 +336,6 @@ scripts listed by the 'perf script -l' command e.g.: ---- root@tropicana:~# perf script -l List of available trace scripts: - workqueue-stats workqueue stats (ins/exe/create/destroy) wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file rw-by-pid system-wide r/w activity @@ -402,7 +401,6 @@ should show a new entry for your script: ---- root@tropicana:~# perf script -l List of available trace scripts: - workqueue-stats workqueue stats (ins/exe/create/destroy) wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file rw-by-pid system-wide r/w activity diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 2fa173b5197..faf4f4feebc 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -108,7 +108,23 @@ with it. --append may be used here. Examples: 3>results perf stat --log-fd 3 -- $cmd 3>>results perf stat --log-fd 3 --append -- $cmd - +--pre:: +--post:: + Pre and post measurement hooks, e.g.: + +perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage + +-I msecs:: +--interval-print msecs:: + Print count deltas every N milliseconds (minimum: 100ms) + example: perf stat -I 1000 -e cycles -a sleep 5 + +--aggr-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 +socket number and the number of online processors on that socket. This is +useful to gauge the amount of aggregation. EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt index b24ac40fcd5..d1d3e5121f8 100644 --- a/tools/perf/Documentation/perf-test.txt +++ b/tools/perf/Documentation/perf-test.txt @@ -23,6 +23,10 @@ from 'perf test list'. OPTIONS ------- +-s:: +--skip:: + Tests to skip (comma separater numeric list). + -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 5b80d84d6b4..a414bc95fd5 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -60,7 +60,7 @@ Default is to monitor all CPUS. -i:: --inherit:: - Child tasks inherit counters, only makes sens with -p option. + Child tasks do not inherit counters. -k <path>:: --vmlinux=<path>:: diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 3a2ae37310a..68718ccdd17 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -48,6 +48,12 @@ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0- In per-thread mode with inheritance mode on (default), Events are captured only when the thread executes on the designated CPUs. Default is to monitor all CPUs. +--duration: + Show only events that had a duration greater than N.M ms. + +--sched: + Accrue thread runtime and provide a summary at the end of the session. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script[1] diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 80db3f4bcf7..39d41068484 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -11,11 +11,21 @@ lib/rbtree.c include/linux/swab.h arch/*/include/asm/unistd*.h arch/*/include/asm/perf_regs.h +arch/*/include/uapi/asm/unistd*.h +arch/*/include/uapi/asm/perf_regs.h arch/*/lib/memcpy*.S arch/*/lib/memset*.S include/linux/poison.h include/linux/magic.h include/linux/hw_breakpoint.h +include/linux/rbtree_augmented.h +include/uapi/linux/perf_event.h +include/uapi/linux/const.h +include/uapi/linux/swab.h +include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/svm.h arch/x86/include/asm/vmx.h arch/x86/include/asm/kvm_host.h +arch/x86/include/uapi/asm/svm.h +arch/x86/include/uapi/asm/vmx.h +arch/x86/include/uapi/asm/kvm.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 00deed4d615..a2108ca1cc1 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -47,10 +47,11 @@ include config/utilities.mak # backtrace post unwind. # # Define NO_BACKTRACE if you do not want stack backtrace debug feature +# +# Define NO_LIBNUMA if you do not want numa perf benchmark $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) --include $(OUTPUT)PERF-VERSION-FILE uname_M := $(shell uname -m 2>/dev/null || echo not) @@ -58,7 +59,7 @@ 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/sh[234].*/sh/ -e s/aarch64.*/arm64/ ) NO_PERF_REGS := 1 CC = $(CROSS_COMPILE)gcc @@ -148,30 +149,79 @@ RM = rm -f MKDIR = mkdir FIND = find INSTALL = install +FLEX = flex +BISON= bison # sparse is architecture-neutral, which means that we need to tell it # explicitly what architecture to check for. Fix this up for yours.. SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ +ifneq ($(MAKECMDGOALS),clean) +ifneq ($(MAKECMDGOALS),tags) -include config/feature-tests.mak -ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y) +ifeq ($(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,$(SOURCE_HELLO),-Werror -Wstack-protector),y) +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y) CFLAGS := $(CFLAGS) -Wstack-protector endif -ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wvolatile-register-var),y) +ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y) CFLAGS := $(CFLAGS) -Wvolatile-register-var endif ### --- END CONFIGURATION SECTION --- -BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +ifneq ($(objtree),) +#$(info Determined 'objtree' to be $(objtree)) +endif + +ifneq ($(OUTPUT),) +#$(info Determined 'OUTPUT' to be $(OUTPUT)) +endif + +BASIC_CFLAGS = \ + -Iutil/include \ + -Iarch/$(ARCH)/include \ + $(if $(objtree),-I$(objtree)/arch/$(ARCH)/include/generated/uapi) \ + -I$(srctree)/arch/$(ARCH)/include/uapi \ + -I$(srctree)/arch/$(ARCH)/include \ + $(if $(objtree),-I$(objtree)/include/generated/uapi) \ + -I$(srctree)/include/uapi \ + -I$(srctree)/include \ + -I$(OUTPUT)util \ + -Iutil \ + -I. \ + -I$(TRACE_EVENT_DIR) \ + -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE + BASIC_LDFLAGS = +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 + # Guard against environment variables BUILTIN_OBJS = LIB_H = @@ -195,11 +245,19 @@ endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a TE_LIB := -L$(TE_PATH) -ltraceevent +export LIBTRACEEVENT + +# python extension build directories +PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ +PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ +PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/ +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 -export LIBTRACEEVENT - $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ @@ -234,20 +292,17 @@ endif export PERL_PATH -FLEX = flex -BISON= bison - $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c: util/parse-events.y - $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c + $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_ $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c: util/pmu.y - $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c + $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_ $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c @@ -303,6 +358,7 @@ LIB_H += util/evlist.h LIB_H += util/exec_cmd.h LIB_H += util/types.h LIB_H += util/levenshtein.h +LIB_H += util/machine.h LIB_H += util/map.h LIB_H += util/parse-options.h LIB_H += util/parse-events.h @@ -319,6 +375,7 @@ LIB_H += util/svghelper.h LIB_H += util/tool.h LIB_H += util/run-command.h LIB_H += util/sigchain.h +LIB_H += util/dso.h LIB_H += util/symbol.h LIB_H += util/color.h LIB_H += util/values.h @@ -341,8 +398,11 @@ LIB_H += util/rblist.h LIB_H += util/intlist.h LIB_H += util/perf_regs.h LIB_H += util/unwind.h -LIB_H += ui/helpline.h LIB_H += util/vdso.h +LIB_H += ui/helpline.h +LIB_H += ui/progress.h +LIB_H += ui/util.h +LIB_H += ui/ui.h LIB_OBJS += $(OUTPUT)util/abspath.o LIB_OBJS += $(OUTPUT)util/alias.o @@ -362,7 +422,6 @@ LIB_OBJS += $(OUTPUT)util/help.o LIB_OBJS += $(OUTPUT)util/levenshtein.o LIB_OBJS += $(OUTPUT)util/parse-options.o LIB_OBJS += $(OUTPUT)util/parse-events.o -LIB_OBJS += $(OUTPUT)util/parse-events-test.o LIB_OBJS += $(OUTPUT)util/path.o LIB_OBJS += $(OUTPUT)util/rbtree.o LIB_OBJS += $(OUTPUT)util/bitmap.o @@ -377,15 +436,16 @@ LIB_OBJS += $(OUTPUT)util/top.o LIB_OBJS += $(OUTPUT)util/usage.o LIB_OBJS += $(OUTPUT)util/wrapper.o LIB_OBJS += $(OUTPUT)util/sigchain.o +LIB_OBJS += $(OUTPUT)util/dso.o LIB_OBJS += $(OUTPUT)util/symbol.o LIB_OBJS += $(OUTPUT)util/symbol-elf.o -LIB_OBJS += $(OUTPUT)util/dso-test-data.o LIB_OBJS += $(OUTPUT)util/color.o LIB_OBJS += $(OUTPUT)util/pager.o LIB_OBJS += $(OUTPUT)util/header.o LIB_OBJS += $(OUTPUT)util/callchain.o LIB_OBJS += $(OUTPUT)util/values.o LIB_OBJS += $(OUTPUT)util/debug.o +LIB_OBJS += $(OUTPUT)util/machine.o LIB_OBJS += $(OUTPUT)util/map.o LIB_OBJS += $(OUTPUT)util/pstack.o LIB_OBJS += $(OUTPUT)util/session.o @@ -413,10 +473,31 @@ LIB_OBJS += $(OUTPUT)util/intlist.o LIB_OBJS += $(OUTPUT)util/vdso.o LIB_OBJS += $(OUTPUT)util/stat.o +LIB_OBJS += $(OUTPUT)ui/setup.o LIB_OBJS += $(OUTPUT)ui/helpline.o +LIB_OBJS += $(OUTPUT)ui/progress.o +LIB_OBJS += $(OUTPUT)ui/util.o LIB_OBJS += $(OUTPUT)ui/hist.o LIB_OBJS += $(OUTPUT)ui/stdio/hist.o +LIB_OBJS += $(OUTPUT)arch/common.o + +LIB_OBJS += $(OUTPUT)tests/parse-events.o +LIB_OBJS += $(OUTPUT)tests/dso-data.o +LIB_OBJS += $(OUTPUT)tests/attr.o +LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o +LIB_OBJS += $(OUTPUT)tests/open-syscall.o +LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o +LIB_OBJS += $(OUTPUT)tests/open-syscall-tp-fields.o +LIB_OBJS += $(OUTPUT)tests/mmap-basic.o +LIB_OBJS += $(OUTPUT)tests/perf-record.o +LIB_OBJS += $(OUTPUT)tests/rdpmc.o +LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o +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 + BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o # Benchmark modules @@ -446,46 +527,65 @@ BUILTIN_OBJS += $(OUTPUT)builtin-probe.o BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o BUILTIN_OBJS += $(OUTPUT)builtin-lock.o BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o -BUILTIN_OBJS += $(OUTPUT)builtin-test.o BUILTIN_OBJS += $(OUTPUT)builtin-inject.o +BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT) # # Platform specific tweaks # +ifneq ($(MAKECMDGOALS),clean) +ifneq ($(MAKECMDGOALS),tags) # We choose to avoid "if .. else if .. else .. endif endif" # because maintaining the nesting to match is a pain. If # we had "elif" things would have been much nicer... --include config.mak.autogen --include config.mak - ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 NO_LIBUNWIND := 1 else FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y) +ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y) FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS) - ifneq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y) - msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); - else + ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),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 := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); endif else - FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS) - ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y) + # 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/ @@ -495,7 +595,7 @@ ifdef LIBUNWIND_DIR endif FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS) -ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND)),y) +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 @@ -524,7 +624,8 @@ LIB_OBJS += $(OUTPUT)util/symbol-minimal.o else # NO_LIBELF BASIC_CFLAGS += -DLIBELF_SUPPORT -ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON)),y) +FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) +ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) BASIC_CFLAGS += -DLIBELF_MMAP endif @@ -532,7 +633,8 @@ 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 + 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 @@ -550,7 +652,7 @@ endif ifndef NO_LIBAUDIT FLAGS_LIBAUDIT = $(ALL_CFLAGS) $(ALL_LDFLAGS) -laudit - ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT)),y) + ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y) msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev); else BASIC_CFLAGS += -DLIBAUDIT_SUPPORT @@ -561,53 +663,47 @@ endif ifndef NO_NEWT FLAGS_NEWT=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lnewt - ifneq ($(call try-cc,$(SOURCE_NEWT),$(FLAGS_NEWT)),y) + 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/setup.o 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/progress.o - LIB_OBJS += $(OUTPUT)ui/util.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 += $(OUTPUT)ui/tui/progress.o LIB_H += ui/browser.h LIB_H += ui/browsers/map.h LIB_H += ui/keysyms.h LIB_H += ui/libslang.h - LIB_H += ui/progress.h - LIB_H += ui/util.h - LIB_H += ui/ui.h endif endif ifndef NO_GTK2 FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) - ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y) + 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)),y) + 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 += $(OUTPUT)ui/gtk/helpline.o - # Make sure that it'd be included only once. - ifeq ($(findstring -DNEWT_SUPPORT,$(BASIC_CFLAGS)),) - LIB_OBJS += $(OUTPUT)ui/setup.o - LIB_OBJS += $(OUTPUT)ui/util.o - endif + LIB_OBJS += $(OUTPUT)ui/gtk/progress.o + LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o endif endif @@ -620,7 +716,7 @@ else PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) - ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED)),y) + ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y) BASIC_CFLAGS += -DNO_LIBPERL else ALL_LDFLAGS += $(PERL_EMBED_LDFLAGS) @@ -634,7 +730,7 @@ disable-python = $(eval $(disable-python_code)) define disable-python_code BASIC_CFLAGS += -DNO_LIBPYTHON $(if $(1),$(warning No $(1) was found)) - $(warning Python support won't be built) + $(warning Python support will not be built) endef override PYTHON := \ @@ -642,19 +738,10 @@ override PYTHON := \ ifndef PYTHON $(call disable-python,python interpreter) - python-clean := else PYTHON_WORD := $(call shell-wordify,$(PYTHON)) - # python extension build directories - PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ - PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ - PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/ - export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP - - python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so - ifdef NO_LIBPYTHON $(call disable-python) else @@ -674,11 +761,11 @@ else 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)),y) + 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)),y) + 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.) $(warning If you also have Python 2 installed, then) @@ -712,22 +799,22 @@ else BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE else FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd - has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD)) + 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)) + 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)) + 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)) + 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 @@ -749,21 +836,41 @@ ifeq ($(NO_PERF_REGS),0) endif ifndef NO_STRLCPY - ifeq ($(call try-cc,$(SOURCE_STRLCPY),),y) + ifeq ($(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,$(SOURCE_BACKTRACE),),y) + ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y) BASIC_CFLAGS += -DBACKTRACE_SUPPORT 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 +endif + ifdef 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)) @@ -805,7 +912,7 @@ strip: $(PROGRAMS) $(OUTPUT)perf $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \ + $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ $(ALL_CFLAGS) -c $(filter %.c,$^) -o $@ @@ -864,10 +971,20 @@ $(OUTPUT)%.s: %.S $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ - '-DBINDIR="$(bindir_relative_SQ)"' \ '-DPREFIX="$(prefix_SQ)"' \ $< +$(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \ + $< + +$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + -DPYTHONPATH='"$(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)"' $< @@ -883,6 +1000,9 @@ $(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_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 $< + $(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)"' $< @@ -954,20 +1074,15 @@ help: @echo 'Perf maintainer targets:' @echo ' clean - clean all binary objects and build output' -doc: - $(MAKE) -C Documentation all - -man: - $(MAKE) -C Documentation man -html: - $(MAKE) -C Documentation html +DOC_TARGETS := doc man html info pdf -info: - $(MAKE) -C Documentation info +INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man +INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html -pdf: - $(MAKE) -C Documentation pdf +# 'make doc' should call 'make -C Documentation all' +$(DOC_TARGETS): + $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) TAGS: $(RM) TAGS @@ -1018,7 +1133,7 @@ perfexec_instdir = $(prefix)/$(perfexecdir) endif perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) -install: all +install-bin: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' @@ -1034,33 +1149,19 @@ install: all $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d' $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests' + $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' + $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' + +install: install-bin try-install-man install-python_ext: $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' -install-doc: - $(MAKE) -C Documentation install - -install-man: - $(MAKE) -C Documentation install-man - -install-html: - $(MAKE) -C Documentation install-html - -install-info: - $(MAKE) -C Documentation install-info - -install-pdf: - $(MAKE) -C Documentation install-pdf - -quick-install-doc: - $(MAKE) -C Documentation quick-install - -quick-install-man: - $(MAKE) -C Documentation quick-install-man - -quick-install-html: - $(MAKE) -C Documentation quick-install-html +# 'make install-doc' should call 'make -C Documentation install' +$(INSTALL_DOC_TARGETS): + $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=) ### Cleaning rules @@ -1068,7 +1169,7 @@ clean: $(LIBTRACEEVENT)-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* - $(MAKE) -C Documentation/ clean + $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(RM) $(OUTPUT)util/*-bison* $(RM) $(OUTPUT)util/*-flex* diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c new file mode 100644 index 00000000000..aacef07ebf3 --- /dev/null +++ b/tools/perf/arch/common.c @@ -0,0 +1,212 @@ +#include <stdio.h> +#include <sys/utsname.h> +#include "common.h" +#include "../util/debug.h" + +const char *const arm_triplets[] = { + "arm-eabi-", + "arm-linux-androideabi-", + "arm-unknown-linux-", + "arm-unknown-linux-gnu-", + "arm-unknown-linux-gnueabi-", + NULL +}; + +const char *const powerpc_triplets[] = { + "powerpc-unknown-linux-gnu-", + "powerpc64-unknown-linux-gnu-", + NULL +}; + +const char *const s390_triplets[] = { + "s390-ibm-linux-", + NULL +}; + +const char *const sh_triplets[] = { + "sh-unknown-linux-gnu-", + "sh64-unknown-linux-gnu-", + NULL +}; + +const char *const sparc_triplets[] = { + "sparc-unknown-linux-gnu-", + "sparc64-unknown-linux-gnu-", + NULL +}; + +const char *const x86_triplets[] = { + "x86_64-pc-linux-gnu-", + "x86_64-unknown-linux-gnu-", + "i686-pc-linux-gnu-", + "i586-pc-linux-gnu-", + "i486-pc-linux-gnu-", + "i386-pc-linux-gnu-", + "i686-linux-android-", + "i686-android-linux-", + NULL +}; + +const char *const mips_triplets[] = { + "mips-unknown-linux-gnu-", + "mipsel-linux-android-", + NULL +}; + +static bool lookup_path(char *name) +{ + bool found = false; + char *path, *tmp; + char buf[PATH_MAX]; + char *env = getenv("PATH"); + + if (!env) + return false; + + env = strdup(env); + if (!env) + return false; + + path = strtok_r(env, ":", &tmp); + while (path) { + scnprintf(buf, sizeof(buf), "%s/%s", path, name); + if (access(buf, F_OK) == 0) { + found = true; + break; + } + path = strtok_r(NULL, ":", &tmp); + } + free(env); + return found; +} + +static int lookup_triplets(const char *const *triplets, const char *name) +{ + int i; + char buf[PATH_MAX]; + + for (i = 0; triplets[i] != NULL; i++) { + scnprintf(buf, sizeof(buf), "%s%s", triplets[i], name); + if (lookup_path(buf)) + return i; + } + return -1; +} + +/* + * Return architecture name in a normalized form. + * The conversion logic comes from the Makefile. + */ +static const char *normalize_arch(char *arch) +{ + if (!strcmp(arch, "x86_64")) + return "x86"; + if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6') + return "x86"; + if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5)) + return "sparc"; + if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110")) + return "arm"; + if (!strncmp(arch, "s390", 4)) + return "s390"; + if (!strncmp(arch, "parisc", 6)) + return "parisc"; + if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3)) + return "powerpc"; + if (!strncmp(arch, "mips", 4)) + return "mips"; + if (!strncmp(arch, "sh", 2) && isdigit(arch[2])) + return "sh"; + + return arch; +} + +static int perf_session_env__lookup_binutils_path(struct perf_session_env *env, + const char *name, + const char **path) +{ + int idx; + const char *arch, *cross_env; + struct utsname uts; + const char *const *path_list; + char *buf = NULL; + + arch = normalize_arch(env->arch); + + if (uname(&uts) < 0) + goto out; + + /* + * We don't need to try to find objdump path for native system. + * Just use default binutils path (e.g.: "objdump"). + */ + if (!strcmp(normalize_arch(uts.machine), arch)) + goto out; + + cross_env = getenv("CROSS_COMPILE"); + if (cross_env) { + if (asprintf(&buf, "%s%s", cross_env, name) < 0) + goto out_error; + if (buf[0] == '/') { + if (access(buf, F_OK) == 0) + goto out; + goto out_error; + } + if (lookup_path(buf)) + goto out; + free(buf); + buf = NULL; + } + + if (!strcmp(arch, "arm")) + path_list = arm_triplets; + else if (!strcmp(arch, "powerpc")) + path_list = powerpc_triplets; + else if (!strcmp(arch, "sh")) + path_list = sh_triplets; + else if (!strcmp(arch, "s390")) + path_list = s390_triplets; + else if (!strcmp(arch, "sparc")) + path_list = sparc_triplets; + else if (!strcmp(arch, "x86")) + path_list = x86_triplets; + else if (!strcmp(arch, "mips")) + path_list = mips_triplets; + else { + ui__error("binutils for %s not supported.\n", arch); + goto out_error; + } + + idx = lookup_triplets(path_list, name); + if (idx < 0) { + ui__error("Please install %s for %s.\n" + "You can add it to PATH, set CROSS_COMPILE or " + "override the default using --%s.\n", + name, arch, name); + goto out_error; + } + + if (asprintf(&buf, "%s%s", path_list[idx], name) < 0) + goto out_error; + +out: + *path = buf; + return 0; +out_error: + free(buf); + *path = NULL; + return -1; +} + +int perf_session_env__lookup_objdump(struct perf_session_env *env) +{ + /* + * For live mode, env->arch will be NULL and we can use + * the native objdump tool. + */ + if (env->arch == NULL) + return 0; + + return perf_session_env__lookup_binutils_path(env, "objdump", + &objdump_path); +} diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h new file mode 100644 index 00000000000..ede246eda9b --- /dev/null +++ b/tools/perf/arch/common.h @@ -0,0 +1,10 @@ +#ifndef ARCH_PERF_COMMON_H +#define ARCH_PERF_COMMON_H + +#include "../util/session.h" + +extern const char *objdump_path; + +int perf_session_env__lookup_objdump(struct perf_session_env *env); + +#endif /* ARCH_PERF_COMMON_H */ diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index 46fc9f15c6b..7fcdcdbee91 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -3,7 +3,7 @@ #include <stdlib.h> #include "../../util/types.h" -#include "../../../../../arch/x86/include/asm/perf_regs.h" +#include <asm/perf_regs.h> #ifndef ARCH_X86_64 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 8f89998eeaf..a5223e6a7b4 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -1,6 +1,7 @@ #ifndef BENCH_H #define BENCH_H +extern int bench_numa(int argc, const char **argv, const char *prefix); extern int bench_sched_messaging(int argc, const char **argv, const char *prefix); extern int bench_sched_pipe(int argc, const char **argv, const char *prefix); extern int bench_mem_memcpy(int argc, const char **argv, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c new file mode 100644 index 00000000000..30d1c3225b4 --- /dev/null +++ b/tools/perf/bench/numa.c @@ -0,0 +1,1731 @@ +/* + * numa.c + * + * numa: Simulate NUMA-sensitive workload and measure their NUMA performance + */ + +#include "../perf.h" +#include "../builtin.h" +#include "../util/util.h" +#include "../util/parse-options.h" + +#include "bench.h" + +#include <errno.h> +#include <sched.h> +#include <stdio.h> +#include <assert.h> +#include <malloc.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <pthread.h> +#include <sys/mman.h> +#include <sys/time.h> +#include <sys/wait.h> +#include <sys/prctl.h> +#include <sys/types.h> + +#include <numa.h> +#include <numaif.h> + +/* + * Regular printout to the terminal, supressed if -q is specified: + */ +#define tprintf(x...) do { if (g && g->p.show_details >= 0) printf(x); } while (0) + +/* + * Debug printf: + */ +#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0) + +struct thread_data { + int curr_cpu; + cpu_set_t bind_cpumask; + int bind_node; + u8 *process_data; + int process_nr; + int thread_nr; + int task_nr; + unsigned int loops_done; + u64 val; + u64 runtime_ns; + pthread_mutex_t *process_lock; +}; + +/* Parameters set by options: */ + +struct params { + /* Startup synchronization: */ + bool serialize_startup; + + /* Task hierarchy: */ + int nr_proc; + int nr_threads; + + /* Working set sizes: */ + const char *mb_global_str; + const char *mb_proc_str; + const char *mb_proc_locked_str; + const char *mb_thread_str; + + double mb_global; + double mb_proc; + double mb_proc_locked; + double mb_thread; + + /* Access patterns to the working set: */ + bool data_reads; + bool data_writes; + bool data_backwards; + bool data_zero_memset; + bool data_rand_walk; + u32 nr_loops; + u32 nr_secs; + u32 sleep_usecs; + + /* Working set initialization: */ + bool init_zero; + bool init_random; + bool init_cpu0; + + /* Misc options: */ + int show_details; + int run_all; + int thp; + + long bytes_global; + long bytes_process; + long bytes_process_locked; + long bytes_thread; + + int nr_tasks; + bool show_quiet; + + bool show_convergence; + bool measure_convergence; + + int perturb_secs; + int nr_cpus; + int nr_nodes; + + /* Affinity options -C and -N: */ + char *cpu_list_str; + char *node_list_str; +}; + + +/* Global, read-writable area, accessible to all processes and threads: */ + +struct global_info { + u8 *data; + + pthread_mutex_t startup_mutex; + int nr_tasks_started; + + pthread_mutex_t startup_done_mutex; + + pthread_mutex_t start_work_mutex; + int nr_tasks_working; + + pthread_mutex_t stop_work_mutex; + u64 bytes_done; + + struct thread_data *threads; + + /* Convergence latency measurement: */ + bool all_converged; + bool stop_work; + + int print_once; + + struct params p; +}; + +static struct global_info *g = NULL; + +static int parse_cpus_opt(const struct option *opt, const char *arg, int unset); +static int parse_nodes_opt(const struct option *opt, const char *arg, int unset); + +struct params p0; + +static const struct option options[] = { + OPT_INTEGER('p', "nr_proc" , &p0.nr_proc, "number of processes"), + OPT_INTEGER('t', "nr_threads" , &p0.nr_threads, "number of threads per process"), + + OPT_STRING('G', "mb_global" , &p0.mb_global_str, "MB", "global memory (MBs)"), + OPT_STRING('P', "mb_proc" , &p0.mb_proc_str, "MB", "process memory (MBs)"), + OPT_STRING('L', "mb_proc_locked", &p0.mb_proc_locked_str,"MB", "process serialized/locked memory access (MBs), <= process_memory"), + OPT_STRING('T', "mb_thread" , &p0.mb_thread_str, "MB", "thread memory (MBs)"), + + OPT_UINTEGER('l', "nr_loops" , &p0.nr_loops, "max number of loops to run"), + OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run"), + OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"), + + OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"), + OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"), + OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"), + OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"), + OPT_BOOLEAN('r', "data_rand_walk", &p0.data_rand_walk, "access the data with random (32bit LFSR) walk"), + + + OPT_BOOLEAN('z', "init_zero" , &p0.init_zero, "bzero the initial allocations"), + OPT_BOOLEAN('I', "init_random" , &p0.init_random, "randomize the contents of the initial allocations"), + OPT_BOOLEAN('0', "init_cpu0" , &p0.init_cpu0, "do the initial allocations on CPU#0"), + OPT_INTEGER('x', "perturb_secs", &p0.perturb_secs, "perturb thread 0/0 every X secs, to test convergence stability"), + + OPT_INCR ('d', "show_details" , &p0.show_details, "Show details"), + OPT_INCR ('a', "all" , &p0.run_all, "Run all tests in the suite"), + OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), + OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), + OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), + OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "bzero the initial allocations"), + OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), + + /* Special option string parsing callbacks: */ + OPT_CALLBACK('C', "cpus", NULL, "cpu[,cpu2,...cpuN]", + "bind the first N tasks to these specific cpus (the rest is unbound)", + parse_cpus_opt), + OPT_CALLBACK('M', "memnodes", NULL, "node[,node2,...nodeN]", + "bind the first N tasks to these specific memory nodes (the rest is unbound)", + parse_nodes_opt), + OPT_END() +}; + +static const char * const bench_numa_usage[] = { + "perf bench numa <options>", + NULL +}; + +static const char * const numa_usage[] = { + "perf bench numa mem [<options>]", + NULL +}; + +static cpu_set_t bind_to_cpu(int target_cpu) +{ + cpu_set_t orig_mask, mask; + int ret; + + ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); + BUG_ON(ret); + + CPU_ZERO(&mask); + + if (target_cpu == -1) { + int cpu; + + for (cpu = 0; cpu < g->p.nr_cpus; cpu++) + CPU_SET(cpu, &mask); + } else { + BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus); + CPU_SET(target_cpu, &mask); + } + + ret = sched_setaffinity(0, sizeof(mask), &mask); + BUG_ON(ret); + + return orig_mask; +} + +static cpu_set_t bind_to_node(int target_node) +{ + int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes; + cpu_set_t orig_mask, mask; + int cpu; + int ret; + + BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus); + BUG_ON(!cpus_per_node); + + ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); + BUG_ON(ret); + + CPU_ZERO(&mask); + + if (target_node == -1) { + for (cpu = 0; cpu < g->p.nr_cpus; cpu++) + CPU_SET(cpu, &mask); + } else { + int cpu_start = (target_node + 0) * cpus_per_node; + int cpu_stop = (target_node + 1) * cpus_per_node; + + BUG_ON(cpu_stop > g->p.nr_cpus); + + for (cpu = cpu_start; cpu < cpu_stop; cpu++) + CPU_SET(cpu, &mask); + } + + ret = sched_setaffinity(0, sizeof(mask), &mask); + BUG_ON(ret); + + return orig_mask; +} + +static void bind_to_cpumask(cpu_set_t mask) +{ + int ret; + + ret = sched_setaffinity(0, sizeof(mask), &mask); + BUG_ON(ret); +} + +static void mempol_restore(void) +{ + int ret; + + ret = set_mempolicy(MPOL_DEFAULT, NULL, g->p.nr_nodes-1); + + BUG_ON(ret); +} + +static void bind_to_memnode(int node) +{ + unsigned long nodemask; + int ret; + + if (node == -1) + return; + + BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)); + nodemask = 1L << node; + + ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8); + dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret); + + BUG_ON(ret); +} + +#define HPSIZE (2*1024*1024) + +#define set_taskname(fmt...) \ +do { \ + char name[20]; \ + \ + snprintf(name, 20, fmt); \ + prctl(PR_SET_NAME, name); \ +} while (0) + +static u8 *alloc_data(ssize_t bytes0, int map_flags, + int init_zero, int init_cpu0, int thp, int init_random) +{ + cpu_set_t orig_mask; + ssize_t bytes; + u8 *buf; + int ret; + + if (!bytes0) + return NULL; + + /* Allocate and initialize all memory on CPU#0: */ + if (init_cpu0) { + orig_mask = bind_to_node(0); + bind_to_memnode(0); + } + + bytes = bytes0 + HPSIZE; + + buf = (void *)mmap(0, bytes, PROT_READ|PROT_WRITE, MAP_ANON|map_flags, -1, 0); + BUG_ON(buf == (void *)-1); + + if (map_flags == MAP_PRIVATE) { + if (thp > 0) { + ret = madvise(buf, bytes, MADV_HUGEPAGE); + if (ret && !g->print_once) { + g->print_once = 1; + printf("WARNING: Could not enable THP - do: 'echo madvise > /sys/kernel/mm/transparent_hugepage/enabled'\n"); + } + } + if (thp < 0) { + ret = madvise(buf, bytes, MADV_NOHUGEPAGE); + if (ret && !g->print_once) { + g->print_once = 1; + printf("WARNING: Could not disable THP: run a CONFIG_TRANSPARENT_HUGEPAGE kernel?\n"); + } + } + } + + if (init_zero) { + bzero(buf, bytes); + } else { + /* Initialize random contents, different in each word: */ + if (init_random) { + u64 *wbuf = (void *)buf; + long off = rand(); + long i; + + for (i = 0; i < bytes/8; i++) + wbuf[i] = i + off; + } + } + + /* Align to 2MB boundary: */ + buf = (void *)(((unsigned long)buf + HPSIZE-1) & ~(HPSIZE-1)); + + /* Restore affinity: */ + if (init_cpu0) { + bind_to_cpumask(orig_mask); + mempol_restore(); + } + + return buf; +} + +static void free_data(void *data, ssize_t bytes) +{ + int ret; + + if (!data) + return; + + ret = munmap(data, bytes); + BUG_ON(ret); +} + +/* + * Create a shared memory buffer that can be shared between processes, zeroed: + */ +static void * zalloc_shared_data(ssize_t bytes) +{ + return alloc_data(bytes, MAP_SHARED, 1, g->p.init_cpu0, g->p.thp, g->p.init_random); +} + +/* + * Create a shared memory buffer that can be shared between processes: + */ +static void * setup_shared_data(ssize_t bytes) +{ + return alloc_data(bytes, MAP_SHARED, 0, g->p.init_cpu0, g->p.thp, g->p.init_random); +} + +/* + * Allocate process-local memory - this will either be shared between + * threads of this process, or only be accessed by this thread: + */ +static void * setup_private_data(ssize_t bytes) +{ + return alloc_data(bytes, MAP_PRIVATE, 0, g->p.init_cpu0, g->p.thp, g->p.init_random); +} + +/* + * Return a process-shared (global) mutex: + */ +static void init_global_mutex(pthread_mutex_t *mutex) +{ + pthread_mutexattr_t attr; + + pthread_mutexattr_init(&attr); + pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED); + pthread_mutex_init(mutex, &attr); +} + +static int parse_cpu_list(const char *arg) +{ + p0.cpu_list_str = strdup(arg); + + dprintf("got CPU list: {%s}\n", p0.cpu_list_str); + + return 0; +} + +static void parse_setup_cpu_list(void) +{ + struct thread_data *td; + char *str0, *str; + int t; + + if (!g->p.cpu_list_str) + return; + + dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); + + str0 = str = strdup(g->p.cpu_list_str); + t = 0; + + BUG_ON(!str); + + tprintf("# binding tasks to CPUs:\n"); + tprintf("# "); + + while (true) { + int bind_cpu, bind_cpu_0, bind_cpu_1; + char *tok, *tok_end, *tok_step, *tok_len, *tok_mul; + int bind_len; + int step; + int mul; + + tok = strsep(&str, ","); + if (!tok) + break; + + tok_end = strstr(tok, "-"); + + dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end); + if (!tok_end) { + /* Single CPU specified: */ + bind_cpu_0 = bind_cpu_1 = atol(tok); + } else { + /* CPU range specified (for example: "5-11"): */ + bind_cpu_0 = atol(tok); + bind_cpu_1 = atol(tok_end + 1); + } + + step = 1; + tok_step = strstr(tok, "#"); + if (tok_step) { + step = atol(tok_step + 1); + BUG_ON(step <= 0 || step >= g->p.nr_cpus); + } + + /* + * Mask length. + * Eg: "--cpus 8_4-16#4" means: '--cpus 8_4,12_4,16_4', + * where the _4 means the next 4 CPUs are allowed. + */ + bind_len = 1; + tok_len = strstr(tok, "_"); + if (tok_len) { + bind_len = atol(tok_len + 1); + BUG_ON(bind_len <= 0 || bind_len > g->p.nr_cpus); + } + + /* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */ + mul = 1; + tok_mul = strstr(tok, "x"); + if (tok_mul) { + mul = atol(tok_mul + 1); + BUG_ON(mul <= 0); + } + + dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul); + + BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus); + BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus); + BUG_ON(bind_cpu_0 > bind_cpu_1); + + for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { + int i; + + for (i = 0; i < mul; i++) { + int cpu; + + if (t >= g->p.nr_tasks) { + printf("\n# NOTE: ignoring bind CPUs starting at CPU#%d\n #", bind_cpu); + goto out; + } + td = g->threads + t; + + if (t) + tprintf(","); + if (bind_len > 1) { + tprintf("%2d/%d", bind_cpu, bind_len); + } else { + tprintf("%2d", bind_cpu); + } + + CPU_ZERO(&td->bind_cpumask); + for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) { + BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus); + CPU_SET(cpu, &td->bind_cpumask); + } + t++; + } + } + } +out: + + tprintf("\n"); + + if (t < g->p.nr_tasks) + printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t); + + free(str0); +} + +static int parse_cpus_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (!arg) + return -1; + + return parse_cpu_list(arg); +} + +static int parse_node_list(const char *arg) +{ + p0.node_list_str = strdup(arg); + + dprintf("got NODE list: {%s}\n", p0.node_list_str); + + return 0; +} + +static void parse_setup_node_list(void) +{ + struct thread_data *td; + char *str0, *str; + int t; + + if (!g->p.node_list_str) + return; + + dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); + + str0 = str = strdup(g->p.node_list_str); + t = 0; + + BUG_ON(!str); + + tprintf("# binding tasks to NODEs:\n"); + tprintf("# "); + + while (true) { + int bind_node, bind_node_0, bind_node_1; + char *tok, *tok_end, *tok_step, *tok_mul; + int step; + int mul; + + tok = strsep(&str, ","); + if (!tok) + break; + + tok_end = strstr(tok, "-"); + + dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end); + if (!tok_end) { + /* Single NODE specified: */ + bind_node_0 = bind_node_1 = atol(tok); + } else { + /* NODE range specified (for example: "5-11"): */ + bind_node_0 = atol(tok); + bind_node_1 = atol(tok_end + 1); + } + + step = 1; + tok_step = strstr(tok, "#"); + if (tok_step) { + step = atol(tok_step + 1); + BUG_ON(step <= 0 || step >= g->p.nr_nodes); + } + + /* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */ + mul = 1; + tok_mul = strstr(tok, "x"); + if (tok_mul) { + mul = atol(tok_mul + 1); + BUG_ON(mul <= 0); + } + + dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step); + + BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes); + BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes); + BUG_ON(bind_node_0 > bind_node_1); + + for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) { + int i; + + for (i = 0; i < mul; i++) { + if (t >= g->p.nr_tasks) { + printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node); + goto out; + } + td = g->threads + t; + + if (!t) + tprintf(" %2d", bind_node); + else + tprintf(",%2d", bind_node); + + td->bind_node = bind_node; + t++; + } + } + } +out: + + tprintf("\n"); + + if (t < g->p.nr_tasks) + printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t); + + free(str0); +} + +static int parse_nodes_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (!arg) + return -1; + + return parse_node_list(arg); + + return 0; +} + +#define BIT(x) (1ul << x) + +static inline uint32_t lfsr_32(uint32_t lfsr) +{ + const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31); + return (lfsr>>1) ^ ((0x0u - (lfsr & 0x1u)) & taps); +} + +/* + * Make sure there's real data dependency to RAM (when read + * accesses are enabled), so the compiler, the CPU and the + * kernel (KSM, zero page, etc.) cannot optimize away RAM + * accesses: + */ +static inline u64 access_data(u64 *data __attribute__((unused)), u64 val) +{ + if (g->p.data_reads) + val += *data; + if (g->p.data_writes) + *data = val + 1; + return val; +} + +/* + * The worker process does two types of work, a forwards going + * loop and a backwards going loop. + * + * We do this so that on multiprocessor systems we do not create + * a 'train' of processing, with highly synchronized processes, + * skewing the whole benchmark. + */ +static u64 do_work(u8 *__data, long bytes, int nr, int nr_max, int loop, u64 val) +{ + long words = bytes/sizeof(u64); + u64 *data = (void *)__data; + long chunk_0, chunk_1; + u64 *d0, *d, *d1; + long off; + long i; + + BUG_ON(!data && words); + BUG_ON(data && !words); + + if (!data) + return val; + + /* Very simple memset() work variant: */ + if (g->p.data_zero_memset && !g->p.data_rand_walk) { + bzero(data, bytes); + return val; + } + + /* Spread out by PID/TID nr and by loop nr: */ + chunk_0 = words/nr_max; + chunk_1 = words/g->p.nr_loops; + off = nr*chunk_0 + loop*chunk_1; + + while (off >= words) + off -= words; + + if (g->p.data_rand_walk) { + u32 lfsr = nr + loop + val; + int j; + + for (i = 0; i < words/1024; i++) { + long start, end; + + lfsr = lfsr_32(lfsr); + + start = lfsr % words; + end = min(start + 1024, words-1); + + if (g->p.data_zero_memset) { + bzero(data + start, (end-start) * sizeof(u64)); + } else { + for (j = start; j < end; j++) + val = access_data(data + j, val); + } + } + } else if (!g->p.data_backwards || (nr + loop) & 1) { + + d0 = data + off; + d = data + off + 1; + d1 = data + words; + + /* Process data forwards: */ + for (;;) { + if (unlikely(d >= d1)) + d = data; + if (unlikely(d == d0)) + break; + + val = access_data(d, val); + + d++; + } + } else { + /* Process data backwards: */ + + d0 = data + off; + d = data + off - 1; + d1 = data + words; + + /* Process data forwards: */ + for (;;) { + if (unlikely(d < data)) + d = data + words-1; + if (unlikely(d == d0)) + break; + + val = access_data(d, val); + + d--; + } + } + + return val; +} + +static void update_curr_cpu(int task_nr, unsigned long bytes_worked) +{ + unsigned int cpu; + + cpu = sched_getcpu(); + + g->threads[task_nr].curr_cpu = cpu; + prctl(0, bytes_worked); +} + +#define MAX_NR_NODES 64 + +/* + * Count the number of nodes a process's threads + * are spread out on. + * + * A count of 1 means that the process is compressed + * to a single node. A count of g->p.nr_nodes means it's + * spread out on the whole system. + */ +static int count_process_nodes(int process_nr) +{ + char node_present[MAX_NR_NODES] = { 0, }; + int nodes; + int n, t; + + for (t = 0; t < g->p.nr_threads; t++) { + struct thread_data *td; + int task_nr; + int node; + + task_nr = process_nr*g->p.nr_threads + t; + td = g->threads + task_nr; + + node = numa_node_of_cpu(td->curr_cpu); + node_present[node] = 1; + } + + nodes = 0; + + for (n = 0; n < MAX_NR_NODES; n++) + nodes += node_present[n]; + + return nodes; +} + +/* + * Count the number of distinct process-threads a node contains. + * + * A count of 1 means that the node contains only a single + * process. If all nodes on the system contain at most one + * process then we are well-converged. + */ +static int count_node_processes(int node) +{ + int processes = 0; + int t, p; + + for (p = 0; p < g->p.nr_proc; p++) { + for (t = 0; t < g->p.nr_threads; t++) { + struct thread_data *td; + int task_nr; + int n; + + task_nr = p*g->p.nr_threads + t; + td = g->threads + task_nr; + + n = numa_node_of_cpu(td->curr_cpu); + if (n == node) { + processes++; + break; + } + } + } + + return processes; +} + +static void calc_convergence_compression(int *strong) +{ + unsigned int nodes_min, nodes_max; + int p; + + nodes_min = -1; + nodes_max = 0; + + for (p = 0; p < g->p.nr_proc; p++) { + unsigned int nodes = count_process_nodes(p); + + nodes_min = min(nodes, nodes_min); + nodes_max = max(nodes, nodes_max); + } + + /* Strong convergence: all threads compress on a single node: */ + if (nodes_min == 1 && nodes_max == 1) { + *strong = 1; + } else { + *strong = 0; + tprintf(" {%d-%d}", nodes_min, nodes_max); + } +} + +static void calc_convergence(double runtime_ns_max, double *convergence) +{ + unsigned int loops_done_min, loops_done_max; + int process_groups; + int nodes[MAX_NR_NODES]; + int distance; + int nr_min; + int nr_max; + int strong; + int sum; + int nr; + int node; + int cpu; + int t; + + if (!g->p.show_convergence && !g->p.measure_convergence) + return; + + for (node = 0; node < g->p.nr_nodes; node++) + nodes[node] = 0; + + loops_done_min = -1; + loops_done_max = 0; + + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + unsigned int loops_done; + + cpu = td->curr_cpu; + + /* Not all threads have written it yet: */ + if (cpu < 0) + continue; + + node = numa_node_of_cpu(cpu); + + nodes[node]++; + + loops_done = td->loops_done; + loops_done_min = min(loops_done, loops_done_min); + loops_done_max = max(loops_done, loops_done_max); + } + + nr_max = 0; + nr_min = g->p.nr_tasks; + sum = 0; + + for (node = 0; node < g->p.nr_nodes; node++) { + nr = nodes[node]; + nr_min = min(nr, nr_min); + nr_max = max(nr, nr_max); + sum += nr; + } + BUG_ON(nr_min > nr_max); + + BUG_ON(sum > g->p.nr_tasks); + + if (0 && (sum < g->p.nr_tasks)) + return; + + /* + * Count the number of distinct process groups present + * on nodes - when we are converged this will decrease + * to g->p.nr_proc: + */ + process_groups = 0; + + for (node = 0; node < g->p.nr_nodes; node++) { + int processes = count_node_processes(node); + + nr = nodes[node]; + tprintf(" %2d/%-2d", nr, processes); + + process_groups += processes; + } + + distance = nr_max - nr_min; + + tprintf(" [%2d/%-2d]", distance, process_groups); + + tprintf(" l:%3d-%-3d (%3d)", + loops_done_min, loops_done_max, loops_done_max-loops_done_min); + + if (loops_done_min && loops_done_max) { + double skew = 1.0 - (double)loops_done_min/loops_done_max; + + tprintf(" [%4.1f%%]", skew * 100.0); + } + + calc_convergence_compression(&strong); + + if (strong && process_groups == g->p.nr_proc) { + if (!*convergence) { + *convergence = runtime_ns_max; + tprintf(" (%6.1fs converged)\n", *convergence/1e9); + if (g->p.measure_convergence) { + g->all_converged = true; + g->stop_work = true; + } + } + } else { + if (*convergence) { + tprintf(" (%6.1fs de-converged)", runtime_ns_max/1e9); + *convergence = 0; + } + tprintf("\n"); + } +} + +static void show_summary(double runtime_ns_max, int l, double *convergence) +{ + tprintf("\r # %5.1f%% [%.1f mins]", + (double)(l+1)/g->p.nr_loops*100.0, runtime_ns_max/1e9 / 60.0); + + calc_convergence(runtime_ns_max, convergence); + + if (g->p.show_details >= 0) + fflush(stdout); +} + +static void *worker_thread(void *__tdata) +{ + struct thread_data *td = __tdata; + struct timeval start0, start, stop, diff; + int process_nr = td->process_nr; + int thread_nr = td->thread_nr; + unsigned long last_perturbance; + int task_nr = td->task_nr; + int details = g->p.show_details; + int first_task, last_task; + double convergence = 0; + u64 val = td->val; + double runtime_ns_max; + u8 *global_data; + u8 *process_data; + u8 *thread_data; + u64 bytes_done; + long work_done; + u32 l; + + bind_to_cpumask(td->bind_cpumask); + bind_to_memnode(td->bind_node); + + set_taskname("thread %d/%d", process_nr, thread_nr); + + global_data = g->data; + process_data = td->process_data; + thread_data = setup_private_data(g->p.bytes_thread); + + bytes_done = 0; + + last_task = 0; + if (process_nr == g->p.nr_proc-1 && thread_nr == g->p.nr_threads-1) + last_task = 1; + + first_task = 0; + if (process_nr == 0 && thread_nr == 0) + first_task = 1; + + if (details >= 2) { + printf("# thread %2d / %2d global mem: %p, process mem: %p, thread mem: %p\n", + process_nr, thread_nr, global_data, process_data, thread_data); + } + + if (g->p.serialize_startup) { + pthread_mutex_lock(&g->startup_mutex); + g->nr_tasks_started++; + pthread_mutex_unlock(&g->startup_mutex); + + /* Here we will wait for the main process to start us all at once: */ + pthread_mutex_lock(&g->start_work_mutex); + g->nr_tasks_working++; + + /* Last one wake the main process: */ + if (g->nr_tasks_working == g->p.nr_tasks) + pthread_mutex_unlock(&g->startup_done_mutex); + + pthread_mutex_unlock(&g->start_work_mutex); + } + + gettimeofday(&start0, NULL); + + start = stop = start0; + last_perturbance = start.tv_sec; + + for (l = 0; l < g->p.nr_loops; l++) { + start = stop; + + if (g->stop_work) + break; + + val += do_work(global_data, g->p.bytes_global, process_nr, g->p.nr_proc, l, val); + val += do_work(process_data, g->p.bytes_process, thread_nr, g->p.nr_threads, l, val); + val += do_work(thread_data, g->p.bytes_thread, 0, 1, l, val); + + if (g->p.sleep_usecs) { + pthread_mutex_lock(td->process_lock); + usleep(g->p.sleep_usecs); + pthread_mutex_unlock(td->process_lock); + } + /* + * Amount of work to be done under a process-global lock: + */ + if (g->p.bytes_process_locked) { + pthread_mutex_lock(td->process_lock); + val += do_work(process_data, g->p.bytes_process_locked, thread_nr, g->p.nr_threads, l, val); + pthread_mutex_unlock(td->process_lock); + } + + work_done = g->p.bytes_global + g->p.bytes_process + + g->p.bytes_process_locked + g->p.bytes_thread; + + update_curr_cpu(task_nr, work_done); + bytes_done += work_done; + + if (details < 0 && !g->p.perturb_secs && !g->p.measure_convergence && !g->p.nr_secs) + continue; + + td->loops_done = l; + + gettimeofday(&stop, NULL); + + /* Check whether our max runtime timed out: */ + if (g->p.nr_secs) { + timersub(&stop, &start0, &diff); + if (diff.tv_sec >= g->p.nr_secs) { + g->stop_work = true; + break; + } + } + + /* Update the summary at most once per second: */ + if (start.tv_sec == stop.tv_sec) + continue; + + /* + * Perturb the first task's equilibrium every g->p.perturb_secs seconds, + * by migrating to CPU#0: + */ + if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) { + cpu_set_t orig_mask; + int target_cpu; + int this_cpu; + + last_perturbance = stop.tv_sec; + + /* + * Depending on where we are running, move into + * the other half of the system, to create some + * real disturbance: + */ + this_cpu = g->threads[task_nr].curr_cpu; + if (this_cpu < g->p.nr_cpus/2) + target_cpu = g->p.nr_cpus-1; + else + target_cpu = 0; + + orig_mask = bind_to_cpu(target_cpu); + + /* Here we are running on the target CPU already */ + if (details >= 1) + printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu); + + bind_to_cpumask(orig_mask); + } + + if (details >= 3) { + timersub(&stop, &start, &diff); + runtime_ns_max = diff.tv_sec * 1000000000; + runtime_ns_max += diff.tv_usec * 1000; + + if (details >= 0) { + printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n", + process_nr, thread_nr, runtime_ns_max / bytes_done, val); + } + fflush(stdout); + } + if (!last_task) + continue; + + timersub(&stop, &start0, &diff); + runtime_ns_max = diff.tv_sec * 1000000000ULL; + runtime_ns_max += diff.tv_usec * 1000ULL; + + show_summary(runtime_ns_max, l, &convergence); + } + + gettimeofday(&stop, NULL); + timersub(&stop, &start0, &diff); + td->runtime_ns = diff.tv_sec * 1000000000ULL; + td->runtime_ns += diff.tv_usec * 1000ULL; + + free_data(thread_data, g->p.bytes_thread); + + pthread_mutex_lock(&g->stop_work_mutex); + g->bytes_done += bytes_done; + pthread_mutex_unlock(&g->stop_work_mutex); + + return NULL; +} + +/* + * A worker process starts a couple of threads: + */ +static void worker_process(int process_nr) +{ + pthread_mutex_t process_lock; + struct thread_data *td; + pthread_t *pthreads; + u8 *process_data; + int task_nr; + int ret; + int t; + + pthread_mutex_init(&process_lock, NULL); + set_taskname("process %d", process_nr); + + /* + * Pick up the memory policy and the CPU binding of our first thread, + * so that we initialize memory accordingly: + */ + task_nr = process_nr*g->p.nr_threads; + td = g->threads + task_nr; + + bind_to_memnode(td->bind_node); + bind_to_cpumask(td->bind_cpumask); + + pthreads = zalloc(g->p.nr_threads * sizeof(pthread_t)); + process_data = setup_private_data(g->p.bytes_process); + + if (g->p.show_details >= 3) { + printf(" # process %2d global mem: %p, process mem: %p\n", + process_nr, g->data, process_data); + } + + for (t = 0; t < g->p.nr_threads; t++) { + task_nr = process_nr*g->p.nr_threads + t; + td = g->threads + task_nr; + + td->process_data = process_data; + td->process_nr = process_nr; + td->thread_nr = t; + td->task_nr = task_nr; + td->val = rand(); + td->curr_cpu = -1; + td->process_lock = &process_lock; + + ret = pthread_create(pthreads + t, NULL, worker_thread, td); + BUG_ON(ret); + } + + for (t = 0; t < g->p.nr_threads; t++) { + ret = pthread_join(pthreads[t], NULL); + BUG_ON(ret); + } + + free_data(process_data, g->p.bytes_process); + free(pthreads); +} + +static void print_summary(void) +{ + if (g->p.show_details < 0) + return; + + printf("\n ###\n"); + printf(" # %d %s will execute (on %d nodes, %d CPUs):\n", + g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus); + printf(" # %5dx %5ldMB global shared mem operations\n", + g->p.nr_loops, g->p.bytes_global/1024/1024); + printf(" # %5dx %5ldMB process shared mem operations\n", + g->p.nr_loops, g->p.bytes_process/1024/1024); + printf(" # %5dx %5ldMB thread local mem operations\n", + g->p.nr_loops, g->p.bytes_thread/1024/1024); + + printf(" ###\n"); + + printf("\n ###\n"); fflush(stdout); +} + +static void init_thread_data(void) +{ + ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + int t; + + g->threads = zalloc_shared_data(size); + + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + int cpu; + + /* Allow all nodes by default: */ + td->bind_node = -1; + + /* Allow all CPUs by default: */ + CPU_ZERO(&td->bind_cpumask); + for (cpu = 0; cpu < g->p.nr_cpus; cpu++) + CPU_SET(cpu, &td->bind_cpumask); + } +} + +static void deinit_thread_data(void) +{ + ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + + free_data(g->threads, size); +} + +static int init(void) +{ + g = (void *)alloc_data(sizeof(*g), MAP_SHARED, 1, 0, 0 /* THP */, 0); + + /* Copy over options: */ + g->p = p0; + + g->p.nr_cpus = numa_num_configured_cpus(); + + g->p.nr_nodes = numa_max_node() + 1; + + /* char array in count_process_nodes(): */ + BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0); + + if (g->p.show_quiet && !g->p.show_details) + g->p.show_details = -1; + + /* Some memory should be specified: */ + if (!g->p.mb_global_str && !g->p.mb_proc_str && !g->p.mb_thread_str) + return -1; + + if (g->p.mb_global_str) { + g->p.mb_global = atof(g->p.mb_global_str); + BUG_ON(g->p.mb_global < 0); + } + + if (g->p.mb_proc_str) { + g->p.mb_proc = atof(g->p.mb_proc_str); + BUG_ON(g->p.mb_proc < 0); + } + + if (g->p.mb_proc_locked_str) { + g->p.mb_proc_locked = atof(g->p.mb_proc_locked_str); + BUG_ON(g->p.mb_proc_locked < 0); + BUG_ON(g->p.mb_proc_locked > g->p.mb_proc); + } + + if (g->p.mb_thread_str) { + g->p.mb_thread = atof(g->p.mb_thread_str); + BUG_ON(g->p.mb_thread < 0); + } + + BUG_ON(g->p.nr_threads <= 0); + BUG_ON(g->p.nr_proc <= 0); + + g->p.nr_tasks = g->p.nr_proc*g->p.nr_threads; + + g->p.bytes_global = g->p.mb_global *1024L*1024L; + g->p.bytes_process = g->p.mb_proc *1024L*1024L; + g->p.bytes_process_locked = g->p.mb_proc_locked *1024L*1024L; + g->p.bytes_thread = g->p.mb_thread *1024L*1024L; + + g->data = setup_shared_data(g->p.bytes_global); + + /* Startup serialization: */ + init_global_mutex(&g->start_work_mutex); + init_global_mutex(&g->startup_mutex); + init_global_mutex(&g->startup_done_mutex); + init_global_mutex(&g->stop_work_mutex); + + init_thread_data(); + + tprintf("#\n"); + parse_setup_cpu_list(); + parse_setup_node_list(); + tprintf("#\n"); + + print_summary(); + + return 0; +} + +static void deinit(void) +{ + free_data(g->data, g->p.bytes_global); + g->data = NULL; + + deinit_thread_data(); + + free_data(g, sizeof(*g)); + g = NULL; +} + +/* + * Print a short or long result, depending on the verbosity setting: + */ +static void print_res(const char *name, double val, + const char *txt_unit, const char *txt_short, const char *txt_long) +{ + if (!name) + name = "main,"; + + if (g->p.show_quiet) + printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short); + else + printf(" %14.3f %s\n", val, txt_long); +} + +static int __bench_numa(const char *name) +{ + struct timeval start, stop, diff; + u64 runtime_ns_min, runtime_ns_sum; + pid_t *pids, pid, wpid; + double delta_runtime; + double runtime_avg; + double runtime_sec_max; + double runtime_sec_min; + int wait_stat; + double bytes; + int i, t; + + if (init()) + return -1; + + pids = zalloc(g->p.nr_proc * sizeof(*pids)); + pid = -1; + + /* All threads try to acquire it, this way we can wait for them to start up: */ + pthread_mutex_lock(&g->start_work_mutex); + + if (g->p.serialize_startup) { + tprintf(" #\n"); + tprintf(" # Startup synchronization: ..."); fflush(stdout); + } + + gettimeofday(&start, NULL); + + for (i = 0; i < g->p.nr_proc; i++) { + pid = fork(); + dprintf(" # process %2d: PID %d\n", i, pid); + + BUG_ON(pid < 0); + if (!pid) { + /* Child process: */ + worker_process(i); + + exit(0); + } + pids[i] = pid; + + } + /* Wait for all the threads to start up: */ + while (g->nr_tasks_started != g->p.nr_tasks) + usleep(1000); + + BUG_ON(g->nr_tasks_started != g->p.nr_tasks); + + if (g->p.serialize_startup) { + double startup_sec; + + pthread_mutex_lock(&g->startup_done_mutex); + + /* This will start all threads: */ + pthread_mutex_unlock(&g->start_work_mutex); + + /* This mutex is locked - the last started thread will wake us: */ + pthread_mutex_lock(&g->startup_done_mutex); + + gettimeofday(&stop, NULL); + + timersub(&stop, &start, &diff); + + startup_sec = diff.tv_sec * 1000000000.0; + startup_sec += diff.tv_usec * 1000.0; + startup_sec /= 1e9; + + tprintf(" threads initialized in %.6f seconds.\n", startup_sec); + tprintf(" #\n"); + + start = stop; + pthread_mutex_unlock(&g->startup_done_mutex); + } else { + gettimeofday(&start, NULL); + } + + /* Parent process: */ + + + for (i = 0; i < g->p.nr_proc; i++) { + wpid = waitpid(pids[i], &wait_stat, 0); + BUG_ON(wpid < 0); + BUG_ON(!WIFEXITED(wait_stat)); + + } + + runtime_ns_sum = 0; + runtime_ns_min = -1LL; + + for (t = 0; t < g->p.nr_tasks; t++) { + u64 thread_runtime_ns = g->threads[t].runtime_ns; + + runtime_ns_sum += thread_runtime_ns; + runtime_ns_min = min(thread_runtime_ns, runtime_ns_min); + } + + gettimeofday(&stop, NULL); + timersub(&stop, &start, &diff); + + BUG_ON(bench_format != BENCH_FORMAT_DEFAULT); + + tprintf("\n ###\n"); + tprintf("\n"); + + runtime_sec_max = diff.tv_sec * 1000000000.0; + runtime_sec_max += diff.tv_usec * 1000.0; + runtime_sec_max /= 1e9; + + runtime_sec_min = runtime_ns_min/1e9; + + bytes = g->bytes_done; + runtime_avg = (double)runtime_ns_sum / g->p.nr_tasks / 1e9; + + if (g->p.measure_convergence) { + print_res(name, runtime_sec_max, + "secs,", "NUMA-convergence-latency", "secs latency to NUMA-converge"); + } + + print_res(name, runtime_sec_max, + "secs,", "runtime-max/thread", "secs slowest (max) thread-runtime"); + + print_res(name, runtime_sec_min, + "secs,", "runtime-min/thread", "secs fastest (min) thread-runtime"); + + print_res(name, runtime_avg, + "secs,", "runtime-avg/thread", "secs average thread-runtime"); + + delta_runtime = (runtime_sec_max - runtime_sec_min)/2.0; + print_res(name, delta_runtime / runtime_sec_max * 100.0, + "%,", "spread-runtime/thread", "% difference between max/avg runtime"); + + print_res(name, bytes / g->p.nr_tasks / 1e9, + "GB,", "data/thread", "GB data processed, per thread"); + + print_res(name, bytes / 1e9, + "GB,", "data-total", "GB data processed, total"); + + print_res(name, runtime_sec_max * 1e9 / (bytes / g->p.nr_tasks), + "nsecs,", "runtime/byte/thread","nsecs/byte/thread runtime"); + + print_res(name, bytes / g->p.nr_tasks / 1e9 / runtime_sec_max, + "GB/sec,", "thread-speed", "GB/sec/thread speed"); + + print_res(name, bytes / runtime_sec_max / 1e9, + "GB/sec,", "total-speed", "GB/sec total speed"); + + free(pids); + + deinit(); + + return 0; +} + +#define MAX_ARGS 50 + +static int command_size(const char **argv) +{ + int size = 0; + + while (*argv) { + size++; + argv++; + } + + BUG_ON(size >= MAX_ARGS); + + return size; +} + +static void init_params(struct params *p, const char *name, int argc, const char **argv) +{ + int i; + + printf("\n # Running %s \"perf bench numa", name); + + for (i = 0; i < argc; i++) + printf(" %s", argv[i]); + + printf("\"\n"); + + memset(p, 0, sizeof(*p)); + + /* Initialize nonzero defaults: */ + + p->serialize_startup = 1; + p->data_reads = true; + p->data_writes = true; + p->data_backwards = true; + p->data_rand_walk = true; + p->nr_loops = -1; + p->init_random = true; +} + +static int run_bench_numa(const char *name, const char **argv) +{ + int argc = command_size(argv); + + init_params(&p0, name, argc, argv); + argc = parse_options(argc, argv, options, bench_numa_usage, 0); + if (argc) + goto err; + + if (__bench_numa(name)) + goto err; + + return 0; + +err: + usage_with_options(numa_usage, options); + return -1; +} + +#define OPT_BW_RAM "-s", "20", "-zZq", "--thp", " 1", "--no-data_rand_walk" +#define OPT_BW_RAM_NOTHP OPT_BW_RAM, "--thp", "-1" + +#define OPT_CONV "-s", "100", "-zZ0qcm", "--thp", " 1" +#define OPT_CONV_NOTHP OPT_CONV, "--thp", "-1" + +#define OPT_BW "-s", "20", "-zZ0q", "--thp", " 1" +#define OPT_BW_NOTHP OPT_BW, "--thp", "-1" + +/* + * The built-in test-suite executed by "perf bench numa -a". + * + * (A minimum of 4 nodes and 16 GB of RAM is recommended.) + */ +static const char *tests[][MAX_ARGS] = { + /* Basic single-stream NUMA bandwidth measurements: */ + { "RAM-bw-local,", "mem", "-p", "1", "-t", "1", "-P", "1024", + "-C" , "0", "-M", "0", OPT_BW_RAM }, + { "RAM-bw-local-NOTHP,", + "mem", "-p", "1", "-t", "1", "-P", "1024", + "-C" , "0", "-M", "0", OPT_BW_RAM_NOTHP }, + { "RAM-bw-remote,", "mem", "-p", "1", "-t", "1", "-P", "1024", + "-C" , "0", "-M", "1", OPT_BW_RAM }, + + /* 2-stream NUMA bandwidth measurements: */ + { "RAM-bw-local-2x,", "mem", "-p", "2", "-t", "1", "-P", "1024", + "-C", "0,2", "-M", "0x2", OPT_BW_RAM }, + { "RAM-bw-remote-2x,", "mem", "-p", "2", "-t", "1", "-P", "1024", + "-C", "0,2", "-M", "1x2", OPT_BW_RAM }, + + /* Cross-stream NUMA bandwidth measurement: */ + { "RAM-bw-cross,", "mem", "-p", "2", "-t", "1", "-P", "1024", + "-C", "0,8", "-M", "1,0", OPT_BW_RAM }, + + /* Convergence latency measurements: */ + { " 1x3-convergence,", "mem", "-p", "1", "-t", "3", "-P", "512", OPT_CONV }, + { " 1x4-convergence,", "mem", "-p", "1", "-t", "4", "-P", "512", OPT_CONV }, + { " 1x6-convergence,", "mem", "-p", "1", "-t", "6", "-P", "1020", OPT_CONV }, + { " 2x3-convergence,", "mem", "-p", "3", "-t", "3", "-P", "1020", OPT_CONV }, + { " 3x3-convergence,", "mem", "-p", "3", "-t", "3", "-P", "1020", OPT_CONV }, + { " 4x4-convergence,", "mem", "-p", "4", "-t", "4", "-P", "512", OPT_CONV }, + { " 4x4-convergence-NOTHP,", + "mem", "-p", "4", "-t", "4", "-P", "512", OPT_CONV_NOTHP }, + { " 4x6-convergence,", "mem", "-p", "4", "-t", "6", "-P", "1020", OPT_CONV }, + { " 4x8-convergence,", "mem", "-p", "4", "-t", "8", "-P", "512", OPT_CONV }, + { " 8x4-convergence,", "mem", "-p", "8", "-t", "4", "-P", "512", OPT_CONV }, + { " 8x4-convergence-NOTHP,", + "mem", "-p", "8", "-t", "4", "-P", "512", OPT_CONV_NOTHP }, + { " 3x1-convergence,", "mem", "-p", "3", "-t", "1", "-P", "512", OPT_CONV }, + { " 4x1-convergence,", "mem", "-p", "4", "-t", "1", "-P", "512", OPT_CONV }, + { " 8x1-convergence,", "mem", "-p", "8", "-t", "1", "-P", "512", OPT_CONV }, + { "16x1-convergence,", "mem", "-p", "16", "-t", "1", "-P", "256", OPT_CONV }, + { "32x1-convergence,", "mem", "-p", "32", "-t", "1", "-P", "128", OPT_CONV }, + + /* Various NUMA process/thread layout bandwidth measurements: */ + { " 2x1-bw-process,", "mem", "-p", "2", "-t", "1", "-P", "1024", OPT_BW }, + { " 3x1-bw-process,", "mem", "-p", "3", "-t", "1", "-P", "1024", OPT_BW }, + { " 4x1-bw-process,", "mem", "-p", "4", "-t", "1", "-P", "1024", OPT_BW }, + { " 8x1-bw-process,", "mem", "-p", "8", "-t", "1", "-P", " 512", OPT_BW }, + { " 8x1-bw-process-NOTHP,", + "mem", "-p", "8", "-t", "1", "-P", " 512", OPT_BW_NOTHP }, + { "16x1-bw-process,", "mem", "-p", "16", "-t", "1", "-P", "256", OPT_BW }, + + { " 4x1-bw-thread,", "mem", "-p", "1", "-t", "4", "-T", "256", OPT_BW }, + { " 8x1-bw-thread,", "mem", "-p", "1", "-t", "8", "-T", "256", OPT_BW }, + { "16x1-bw-thread,", "mem", "-p", "1", "-t", "16", "-T", "128", OPT_BW }, + { "32x1-bw-thread,", "mem", "-p", "1", "-t", "32", "-T", "64", OPT_BW }, + + { " 2x3-bw-thread,", "mem", "-p", "2", "-t", "3", "-P", "512", OPT_BW }, + { " 4x4-bw-thread,", "mem", "-p", "4", "-t", "4", "-P", "512", OPT_BW }, + { " 4x6-bw-thread,", "mem", "-p", "4", "-t", "6", "-P", "512", OPT_BW }, + { " 4x8-bw-thread,", "mem", "-p", "4", "-t", "8", "-P", "512", OPT_BW }, + { " 4x8-bw-thread-NOTHP,", + "mem", "-p", "4", "-t", "8", "-P", "512", OPT_BW_NOTHP }, + { " 3x3-bw-thread,", "mem", "-p", "3", "-t", "3", "-P", "512", OPT_BW }, + { " 5x5-bw-thread,", "mem", "-p", "5", "-t", "5", "-P", "512", OPT_BW }, + + { "2x16-bw-thread,", "mem", "-p", "2", "-t", "16", "-P", "512", OPT_BW }, + { "1x32-bw-thread,", "mem", "-p", "1", "-t", "32", "-P", "2048", OPT_BW }, + + { "numa02-bw,", "mem", "-p", "1", "-t", "32", "-T", "32", OPT_BW }, + { "numa02-bw-NOTHP,", "mem", "-p", "1", "-t", "32", "-T", "32", OPT_BW_NOTHP }, + { "numa01-bw-thread,", "mem", "-p", "2", "-t", "16", "-T", "192", OPT_BW }, + { "numa01-bw-thread-NOTHP,", + "mem", "-p", "2", "-t", "16", "-T", "192", OPT_BW_NOTHP }, +}; + +static int bench_all(void) +{ + int nr = ARRAY_SIZE(tests); + int ret; + int i; + + ret = system("echo ' #'; echo ' # Running test on: '$(uname -a); echo ' #'"); + BUG_ON(ret < 0); + + for (i = 0; i < nr; i++) { + if (run_bench_numa(tests[i][0], tests[i] + 1)) + return -1; + } + + printf("\n"); + + return 0; +} + +int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused) +{ + init_params(&p0, "main,", argc, argv); + argc = parse_options(argc, argv, options, bench_numa_usage, 0); + if (argc) + goto err; + + if (p0.run_all) + return bench_all(); + + if (__bench_numa(NULL)) + goto err; + + return 0; + +err: + usage_with_options(numa_usage, options); + return -1; +} diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 9ea38540b87..2e6961ea318 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -28,15 +28,16 @@ #include "util/hist.h" #include "util/session.h" #include "util/tool.h" +#include "arch/common.h" #include <linux/bitmap.h> struct perf_annotate { struct perf_tool tool; - char const *input_name; - bool force, use_tui, use_stdio; + bool force, use_tui, use_stdio, use_gtk; bool full_paths; bool print_line; + bool skip_missing; const char *sym_hist_filter; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -138,9 +139,22 @@ find_next: continue; } - if (use_browser > 0) { - key = hist_entry__tui_annotate(he, evidx, NULL, NULL, 0); + if (use_browser == 2) { + int ret; + + ret = hist_entry__gtk_annotate(he, evidx, 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); switch (key) { + case -1: + if (!ann->skip_missing) + return; + /* fall through */ case K_RIGHT: next = rb_next(nd); break; @@ -174,7 +188,7 @@ static int __cmd_annotate(struct perf_annotate *ann) struct perf_evsel *pos; u64 total_nr_samples; - session = perf_session__new(ann->input_name, O_RDONLY, + session = perf_session__new(input_name, O_RDONLY, ann->force, false, &ann->tool); if (session == NULL) return -ENOMEM; @@ -186,6 +200,12 @@ static int __cmd_annotate(struct perf_annotate *ann) goto out_delete; } + if (!objdump_path) { + ret = perf_session_env__lookup_objdump(&session->header.env); + if (ret) + goto out_delete; + } + ret = perf_session__process_events(session, &ann->tool); if (ret) goto out_delete; @@ -218,6 +238,10 @@ static int __cmd_annotate(struct perf_annotate *ann) ui__error("The %s file has no samples!\n", session->filename); goto out_delete; } + + if (use_browser == 2) + perf_gtk__show_annotations(); + out_delete: /* * Speed up the exit process, for large files this can @@ -246,13 +270,14 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) .sample = process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .ordered_samples = true, .ordering_requires_timestamps = true, }, }; const struct option options[] = { - OPT_STRING('i', "input", &annotate.input_name, "file", + OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", "only consider symbols in these dsos"), @@ -263,6 +288,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"), OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"), OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, @@ -273,6 +299,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "print matching source lines (may be slow)"), OPT_BOOLEAN('P', "full-paths", &annotate.full_paths, "Don't shorten the displayed pathnames"), + OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing, + "Skip symbols that cannot be annotated"), OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), @@ -293,6 +321,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) use_browser = 0; else if (annotate.use_tui) use_browser = 1; + else if (annotate.use_gtk) + use_browser = 2; setup_browser(true); @@ -302,7 +332,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) if (symbol__init() < 0) return -1; - setup_sorting(annotate_usage, options); + if (setup_sorting() < 0) + usage_with_options(annotate_usage, options); if (argc) { /* diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index cae9a5fd2ec..77298bf892b 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -35,6 +35,18 @@ struct bench_suite { /* sentinel: easy for help */ #define suite_all { "all", "Test all benchmark suites", NULL } +#ifdef LIBNUMA_SUPPORT +static struct bench_suite numa_suites[] = { + { "mem", + "Benchmark for NUMA workloads", + bench_numa }, + suite_all, + { NULL, + NULL, + NULL } +}; +#endif + static struct bench_suite sched_suites[] = { { "messaging", "Benchmark for scheduler and IPC mechanisms", @@ -68,6 +80,11 @@ struct bench_subsys { }; static struct bench_subsys subsystems[] = { +#ifdef LIBNUMA_SUPPORT + { "numa", + "NUMA scheduling and MM behavior", + numa_suites }, +#endif { "sched", "scheduler and IPC mechanism", sched_suites }, @@ -159,6 +176,7 @@ static void all_suite(struct bench_subsys *subsys) /* FROM HERE */ printf("# Running %s/%s benchmark...\n", subsys->name, suites[i].name); + fflush(stdout); argv[1] = suites[i].name; suites[i].fn(1, argv, NULL); @@ -225,6 +243,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) printf("# Running %s/%s benchmark...\n", subsystems[i].name, subsystems[i].suites[j].name); + fflush(stdout); status = subsystems[i].suites[j].fn(argc - 1, argv + 1, prefix); goto end; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index d37e077f4b1..c96c8fa3824 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -13,6 +13,8 @@ #include "util/header.h" #include "util/parse-options.h" #include "util/strlist.h" +#include "util/build-id.h" +#include "util/session.h" #include "util/symbol.h" static int build_id_cache__add_file(const char *filename, const char *debugdir) @@ -57,19 +59,89 @@ static int build_id_cache__remove_file(const char *filename, return err; } +static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) +{ + char filename[PATH_MAX]; + u8 build_id[BUILD_ID_SIZE]; + + if (dso__build_id_filename(dso, filename, sizeof(filename)) && + filename__read_build_id(filename, build_id, + sizeof(build_id)) != sizeof(build_id)) { + if (errno == ENOENT) + return false; + + pr_warning("Problems with %s file, consider removing it from the cache\n", + filename); + } else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) { + pr_warning("Problems with %s file, consider removing it from the cache\n", + filename); + } + + return true; +} + +static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp) +{ + struct perf_session *session = perf_session__new(filename, O_RDONLY, + force, false, NULL); + if (session == NULL) + return -1; + + perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0); + perf_session__delete(session); + + return 0; +} + +static int build_id_cache__update_file(const char *filename, + const char *debugdir) +{ + u8 build_id[BUILD_ID_SIZE]; + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + int err; + + if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { + pr_debug("Couldn't read a build-id in %s\n", filename); + return -1; + } + + build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + err = build_id_cache__remove_s(sbuild_id, debugdir); + if (!err) { + err = build_id_cache__add_s(sbuild_id, debugdir, filename, + false, false); + } + if (verbose) + pr_info("Updating %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); + + return err; +} + int cmd_buildid_cache(int argc, const char **argv, const char *prefix __maybe_unused) { struct strlist *list; struct str_node *pos; + int ret = 0; + bool force = false; char debugdir[PATH_MAX]; char const *add_name_list_str = NULL, - *remove_name_list_str = NULL; + *remove_name_list_str = NULL, + *missing_filename = NULL, + *update_name_list_str = NULL; + const struct option buildid_cache_options[] = { OPT_STRING('a', "add", &add_name_list_str, "file list", "file(s) to add"), OPT_STRING('r', "remove", &remove_name_list_str, "file list", "file(s) to remove"), + OPT_STRING('M', "missing", &missing_filename, "file", + "to find missing build ids in the cache"), + OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), + OPT_STRING('u', "update", &update_name_list_str, "file list", + "file(s) to update"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_END() }; @@ -124,5 +196,26 @@ int cmd_buildid_cache(int argc, const char **argv, } } - return 0; + if (missing_filename) + ret = build_id_cache__fprintf_missing(missing_filename, force, stdout); + + if (update_name_list_str) { + list = strlist__new(true, update_name_list_str); + if (list) { + strlist__for_each(pos, list) + if (build_id_cache__update_file(pos->s, debugdir)) { + if (errno == ENOENT) { + pr_debug("%s wasn't in the cache\n", + pos->s); + continue; + } + pr_warning("Couldn't update %s: %s\n", + pos->s, strerror(errno)); + } + + strlist__delete(list); + } + } + + return ret; } diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index a0e94fffa03..e74366a1321 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -44,24 +44,26 @@ static int filename__fprintf_build_id(const char *name, FILE *fp) return fprintf(fp, "%s\n", sbuild_id); } -static int perf_session__list_build_ids(const char *input_name, - bool force, bool with_hits) +static bool dso__skip_buildid(struct dso *dso, int with_hits) +{ + return with_hits && !dso->hit; +} + +static int perf_session__list_build_ids(bool force, bool with_hits) { struct perf_session *session; symbol__elf_init(); - - session = perf_session__new(input_name, O_RDONLY, force, false, - &build_id__mark_dso_hit_ops); - if (session == NULL) - return -1; - /* * See if this is an ELF file first: */ - if (filename__fprintf_build_id(session->filename, stdout)) + if (filename__fprintf_build_id(input_name, stdout)) goto out; + session = perf_session__new(input_name, O_RDONLY, force, false, + &build_id__mark_dso_hit_ops); + if (session == NULL) + return -1; /* * in pipe-mode, the only way to get the buildids is to parse * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID @@ -69,9 +71,9 @@ static int perf_session__list_build_ids(const char *input_name, if (with_hits || session->fd_pipe) perf_session__process_events(session, &build_id__mark_dso_hit_ops); - perf_session__fprintf_dsos_buildid(session, stdout, with_hits); -out: + perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits); perf_session__delete(session); +out: return 0; } @@ -81,7 +83,6 @@ int cmd_buildid_list(int argc, const char **argv, bool show_kernel = false; bool with_hits = false; bool force = false; - const char *input_name = NULL; const struct option options[] = { OPT_BOOLEAN('H', "with-hits", &with_hits, "Show only DSOs with hits"), OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -101,5 +102,5 @@ int cmd_buildid_list(int argc, const char **argv, if (show_kernel) return sysfs__fprintf_build_id(stdout); - return perf_session__list_build_ids(input_name, force, with_hits); + return perf_session__list_build_ids(force, with_hits); } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index a0b531c14b9..d207a97a2db 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -23,7 +23,212 @@ static char const *input_old = "perf.data.old", *input_new = "perf.data"; static char diff__default_sort_order[] = "dso,symbol"; static bool force; -static bool show_displacement; +static bool show_period; +static bool show_formula; +static bool show_baseline_only; +static bool sort_compute; + +static s64 compute_wdiff_w1; +static s64 compute_wdiff_w2; + +enum { + COMPUTE_DELTA, + COMPUTE_RATIO, + COMPUTE_WEIGHTED_DIFF, + COMPUTE_MAX, +}; + +const char *compute_names[COMPUTE_MAX] = { + [COMPUTE_DELTA] = "delta", + [COMPUTE_RATIO] = "ratio", + [COMPUTE_WEIGHTED_DIFF] = "wdiff", +}; + +static int compute; + +static int setup_compute_opt_wdiff(char *opt) +{ + char *w1_str = opt; + char *w2_str; + + int ret = -EINVAL; + + if (!opt) + goto out; + + w2_str = strchr(opt, ','); + if (!w2_str) + goto out; + + *w2_str++ = 0x0; + if (!*w2_str) + goto out; + + compute_wdiff_w1 = strtol(w1_str, NULL, 10); + compute_wdiff_w2 = strtol(w2_str, NULL, 10); + + if (!compute_wdiff_w1 || !compute_wdiff_w2) + goto out; + + pr_debug("compute wdiff w1(%" PRId64 ") w2(%" PRId64 ")\n", + compute_wdiff_w1, compute_wdiff_w2); + + ret = 0; + + out: + if (ret) + pr_err("Failed: wrong weight data, use 'wdiff:w1,w2'\n"); + + return ret; +} + +static int setup_compute_opt(char *opt) +{ + if (compute == COMPUTE_WEIGHTED_DIFF) + return setup_compute_opt_wdiff(opt); + + if (opt) { + pr_err("Failed: extra option specified '%s'", opt); + return -EINVAL; + } + + return 0; +} + +static int setup_compute(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + int *cp = (int *) opt->value; + char *cstr = (char *) str; + char buf[50]; + unsigned i; + char *option; + + if (!str) { + *cp = COMPUTE_DELTA; + return 0; + } + + if (*str == '+') { + sort_compute = true; + cstr = (char *) ++str; + if (!*str) + return 0; + } + + option = strchr(str, ':'); + if (option) { + unsigned len = option++ - str; + + /* + * The str data are not writeable, so we need + * to use another buffer. + */ + + /* No option value is longer. */ + if (len >= sizeof(buf)) + return -EINVAL; + + strncpy(buf, str, len); + buf[len] = 0x0; + cstr = buf; + } + + for (i = 0; i < COMPUTE_MAX; i++) + if (!strcmp(cstr, compute_names[i])) { + *cp = i; + return setup_compute_opt(option); + } + + pr_err("Failed: '%s' is not computation method " + "(use 'delta','ratio' or 'wdiff')\n", str); + return -EINVAL; +} + +double perf_diff__period_percent(struct hist_entry *he, u64 period) +{ + u64 total = he->hists->stats.total_period; + return (period * 100.0) / total; +} + +double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair) +{ + double new_percent = perf_diff__period_percent(he, he->stat.period); + double old_percent = perf_diff__period_percent(pair, pair->stat.period); + + he->diff.period_ratio_delta = new_percent - old_percent; + he->diff.computed = true; + return he->diff.period_ratio_delta; +} + +double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair) +{ + double new_period = he->stat.period; + double old_period = pair->stat.period; + + he->diff.computed = true; + he->diff.period_ratio = new_period / old_period; + return he->diff.period_ratio; +} + +s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair) +{ + u64 new_period = he->stat.period; + u64 old_period = pair->stat.period; + + he->diff.computed = true; + he->diff.wdiff = new_period * compute_wdiff_w2 - + old_period * compute_wdiff_w1; + + return he->diff.wdiff; +} + +static int formula_delta(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) +{ + return scnprintf(buf, size, + "(%" PRIu64 " * 100 / %" PRIu64 ") - " + "(%" PRIu64 " * 100 / %" PRIu64 ")", + he->stat.period, he->hists->stats.total_period, + pair->stat.period, pair->hists->stats.total_period); +} + +static int formula_ratio(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) +{ + double new_period = he->stat.period; + double old_period = pair->stat.period; + + return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period); +} + +static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) +{ + u64 new_period = he->stat.period; + u64 old_period = pair->stat.period; + + return scnprintf(buf, size, + "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")", + new_period, compute_wdiff_w2, old_period, compute_wdiff_w1); +} + +int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) +{ + switch (compute) { + case COMPUTE_DELTA: + return formula_delta(he, pair, buf, size); + case COMPUTE_RATIO: + return formula_ratio(he, pair, buf, size); + case COMPUTE_WEIGHTED_DIFF: + return formula_wdiff(he, pair, buf, size); + default: + BUG_ON(1); + } + + return -1; +} static int hists__add_entry(struct hists *self, struct addr_location *al, u64 period) @@ -47,7 +252,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (al.filtered || al.sym == NULL) + if (al.filtered) return 0; if (hists__add_entry(&evsel->hists, &al, sample->period)) { @@ -63,115 +268,197 @@ static struct perf_tool tool = { .sample = diff__process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .lost = perf_event__process_lost, .ordered_samples = true, .ordering_requires_timestamps = true, }; -static void insert_hist_entry_by_name(struct rb_root *root, - struct hist_entry *he) +static struct perf_evsel *evsel_match(struct perf_evsel *evsel, + struct perf_evlist *evlist) { - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; + struct perf_evsel *e; - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); - if (hist_entry__cmp(he, iter) < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; + list_for_each_entry(e, &evlist->entries, node) + if (perf_evsel__match2(evsel, e)) + return e; + + return NULL; +} + +static void perf_evlist__collapse_resort(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + struct hists *hists = &evsel->hists; + + hists__collapse_resort(hists); } +} - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); +static void hists__baseline_only(struct hists *hists) +{ + 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_in); + + next = rb_next(&he->rb_node_in); + if (!hist_entry__next_pair(he)) { + rb_erase(&he->rb_node_in, root); + hist_entry__free(he); + } + } } -static void hists__name_resort(struct hists *self, bool sort) +static void hists__precompute(struct hists *hists) { - unsigned long position = 1; - struct rb_root tmp = RB_ROOT; - struct rb_node *next = rb_first(&self->entries); + struct rb_node *next = rb_first(&hists->entries); while (next != NULL) { - struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node); + struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + struct hist_entry *pair = hist_entry__next_pair(he); - next = rb_next(&n->rb_node); - n->position = position++; + next = rb_next(&he->rb_node); + if (!pair) + continue; - if (sort) { - rb_erase(&n->rb_node, &self->entries); - insert_hist_entry_by_name(&tmp, n); + switch (compute) { + case COMPUTE_DELTA: + perf_diff__compute_delta(he, pair); + break; + case COMPUTE_RATIO: + perf_diff__compute_ratio(he, pair); + break; + case COMPUTE_WEIGHTED_DIFF: + perf_diff__compute_wdiff(he, pair); + break; + default: + BUG_ON(1); } } +} - if (sort) - self->entries = tmp; +static int64_t cmp_doubles(double l, double r) +{ + if (l > r) + return -1; + else if (l < r) + return 1; + else + return 0; } -static struct hist_entry *hists__find_entry(struct hists *self, - struct hist_entry *he) +static int64_t +hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, + int c) { - struct rb_node *n = self->entries.rb_node; + switch (c) { + case COMPUTE_DELTA: + { + double l = left->diff.period_ratio_delta; + double r = right->diff.period_ratio_delta; - while (n) { - struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node); - int64_t cmp = hist_entry__cmp(he, iter); + return cmp_doubles(l, r); + } + case COMPUTE_RATIO: + { + double l = left->diff.period_ratio; + double r = right->diff.period_ratio; - if (cmp < 0) - n = n->rb_left; - else if (cmp > 0) - n = n->rb_right; - else - return iter; + return cmp_doubles(l, r); } + case COMPUTE_WEIGHTED_DIFF: + { + s64 l = left->diff.wdiff; + s64 r = right->diff.wdiff; - return NULL; + return r - l; + } + default: + BUG_ON(1); + } + + return 0; } -static void hists__match(struct hists *older, struct hists *newer) +static void insert_hist_entry_by_compute(struct rb_root *root, + struct hist_entry *he, + int c) { - struct rb_node *nd; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct hist_entry *iter; - for (nd = rb_first(&newer->entries); nd; nd = rb_next(nd)) { - struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node); - pos->pair = hists__find_entry(older, pos); + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct hist_entry, rb_node); + if (hist_entry__cmp_compute(he, iter, c) < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; } + + rb_link_node(&he->rb_node, parent, p); + rb_insert_color(&he->rb_node, root); } -static struct perf_evsel *evsel_match(struct perf_evsel *evsel, - struct perf_evlist *evlist) +static void hists__compute_resort(struct hists *hists) { - struct perf_evsel *e; + struct rb_root *root; + struct rb_node *next; - list_for_each_entry(e, &evlist->entries, node) - if (perf_evsel__match2(evsel, e)) - return e; + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; - return NULL; -} + hists->entries = RB_ROOT; + next = rb_first(root); -static void perf_evlist__resort_hists(struct perf_evlist *evlist, bool name) -{ - struct perf_evsel *evsel; + hists->nr_entries = 0; + hists->stats.total_period = 0; + hists__reset_col_len(hists); - list_for_each_entry(evsel, &evlist->entries, node) { - struct hists *hists = &evsel->hists; + while (next != NULL) { + struct hist_entry *he; - hists__output_resort(hists); + he = rb_entry(next, struct hist_entry, rb_node_in); + next = rb_next(&he->rb_node_in); - /* - * The hists__name_resort only sets possition - * if name is false. - */ - if (name || ((!name) && show_displacement)) - hists__name_resort(hists, name); + insert_hist_entry_by_compute(&hists->entries, he, compute); + hists__inc_nr_entries(hists, he); } } +static void hists__process(struct hists *old, struct hists *new) +{ + hists__match(new, old); + + if (show_baseline_only) + hists__baseline_only(new); + else + hists__link(new, old); + + if (sort_compute) { + hists__precompute(new); + hists__compute_resort(new); + } else { + hists__output_resort(new); + } + + hists__fprintf(new, true, 0, 0, stdout); +} + static int __cmd_diff(void) { int ret, i; @@ -198,8 +485,8 @@ static int __cmd_diff(void) evlist_old = older->evlist; evlist_new = newer->evlist; - perf_evlist__resort_hists(evlist_old, true); - perf_evlist__resort_hists(evlist_new, false); + perf_evlist__collapse_resort(evlist_old); + perf_evlist__collapse_resort(evlist_new); list_for_each_entry(evsel, &evlist_new->entries, node) { struct perf_evsel *evsel_old; @@ -213,8 +500,7 @@ static int __cmd_diff(void) first = false; - hists__match(&evsel_old->hists, &evsel->hists); - hists__fprintf(&evsel->hists, true, 0, 0, stdout); + hists__process(&evsel_old->hists, &evsel->hists); } out_delete: @@ -233,8 +519,16 @@ static const char * const diff_usage[] = { static const struct option options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('M', "displacement", &show_displacement, - "Show position displacement relative to baseline"), + OPT_BOOLEAN('b', "baseline-only", &show_baseline_only, + "Show only items with match in baseline"), + OPT_CALLBACK('c', "compute", &compute, + "delta,ratio,wdiff:w1,w2 (default delta)", + "Entries differential computation selection", + setup_compute), + OPT_BOOLEAN('p', "period", &show_period, + "Show period values."), + OPT_BOOLEAN('F', "formula", &show_formula, + "Show formula."), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), @@ -258,17 +552,33 @@ static const struct option options[] = { static void ui_init(void) { - perf_hpp__init(); - - /* No overhead column. */ - perf_hpp__column_enable(PERF_HPP__OVERHEAD, false); - - /* Display baseline/delta/displacement columns. */ - perf_hpp__column_enable(PERF_HPP__BASELINE, true); - perf_hpp__column_enable(PERF_HPP__DELTA, true); - - if (show_displacement) - perf_hpp__column_enable(PERF_HPP__DISPL, true); + /* + * Display baseline/delta/ratio + * formula/periods columns. + */ + perf_hpp__column_enable(PERF_HPP__BASELINE); + + switch (compute) { + case COMPUTE_DELTA: + perf_hpp__column_enable(PERF_HPP__DELTA); + break; + case COMPUTE_RATIO: + perf_hpp__column_enable(PERF_HPP__RATIO); + break; + case COMPUTE_WEIGHTED_DIFF: + perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF); + break; + default: + BUG_ON(1); + }; + + if (show_formula) + perf_hpp__column_enable(PERF_HPP__FORMULA); + + if (show_period) { + perf_hpp__column_enable(PERF_HPP__PERIOD); + perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE); + } } int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) @@ -295,7 +605,9 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) ui_init(); - setup_sorting(diff_usage, options); + if (setup_sorting() < 0) + usage_with_options(diff_usage, options); + setup_pager(); sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", NULL); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 997afb82691..05bd9dfe875 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -15,94 +15,17 @@ #include "util/parse-options.h" #include "util/session.h" -struct perf_attr_details { - bool freq; - bool verbose; -}; - -static int comma_printf(bool *first, const char *fmt, ...) -{ - va_list args; - int ret = 0; - - if (!*first) { - ret += printf(","); - } else { - ret += printf(":"); - *first = false; - } - - va_start(args, fmt); - ret += vprintf(fmt, args); - va_end(args); - return ret; -} - -static int __if_print(bool *first, const char *field, u64 value) -{ - if (value == 0) - return 0; - - return comma_printf(first, " %s: %" PRIu64, field, value); -} - -#define if_print(field) __if_print(&first, #field, pos->attr.field) - -static int __cmd_evlist(const char *input_name, struct perf_attr_details *details) +static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { struct perf_session *session; struct perf_evsel *pos; - session = perf_session__new(input_name, O_RDONLY, 0, false, NULL); + session = perf_session__new(file_name, O_RDONLY, 0, false, NULL); if (session == NULL) return -ENOMEM; - list_for_each_entry(pos, &session->evlist->entries, node) { - bool first = true; - - printf("%s", perf_evsel__name(pos)); - - if (details->verbose || details->freq) { - comma_printf(&first, " sample_freq=%" PRIu64, - (u64)pos->attr.sample_freq); - } - - if (details->verbose) { - if_print(type); - if_print(config); - if_print(config1); - if_print(config2); - if_print(size); - if_print(sample_type); - if_print(read_format); - if_print(disabled); - if_print(inherit); - if_print(pinned); - if_print(exclusive); - if_print(exclude_user); - if_print(exclude_kernel); - if_print(exclude_hv); - if_print(exclude_idle); - if_print(mmap); - if_print(comm); - if_print(freq); - if_print(inherit_stat); - if_print(enable_on_exec); - if_print(task); - if_print(watermark); - if_print(precise_ip); - if_print(mmap_data); - if_print(sample_id_all); - if_print(exclude_host); - if_print(exclude_guest); - if_print(__reserved_1); - if_print(wakeup_events); - if_print(bp_type); - if_print(branch_sample_type); - } - - putchar('\n'); - } + list_for_each_entry(pos, &session->evlist->entries, node) + perf_evsel__fprintf(pos, details, stdout); perf_session__delete(session); return 0; @@ -111,12 +34,13 @@ static int __cmd_evlist(const char *input_name, struct perf_attr_details *detail int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_attr_details details = { .verbose = false, }; - const char *input_name = NULL; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "Input file name"), OPT_BOOLEAN('F', "freq", &details.freq, "Show the sample frequency"), OPT_BOOLEAN('v', "verbose", &details.verbose, "Show all event attr details"), + OPT_BOOLEAN('g', "group", &details.event_group, + "Show event group information"), OPT_END() }; const char * const evlist_usage[] = { @@ -128,5 +52,10 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(evlist_usage, options); + if (details.event_group && (details.verbose || details.freq)) { + pr_err("--group option is not compatible with other options\n"); + usage_with_options(evlist_usage, options); + } + return __cmd_evlist(input_name, &details); } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 4688bea95c1..84ad6abe425 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -8,33 +8,53 @@ #include "builtin.h" #include "perf.h" +#include "util/color.h" +#include "util/evlist.h" +#include "util/evsel.h" #include "util/session.h" #include "util/tool.h" #include "util/debug.h" +#include "util/build-id.h" #include "util/parse-options.h" +#include <linux/list.h> + struct perf_inject { struct perf_tool tool; bool build_ids; + bool sched_stat; + const char *input_name; + int pipe_output, + output; + u64 bytes_written; + struct list_head samples; +}; + +struct event_entry { + struct list_head node; + u32 tid; + union perf_event event[0]; }; -static int perf_event__repipe_synth(struct perf_tool *tool __maybe_unused, +static int perf_event__repipe_synth(struct perf_tool *tool, union perf_event *event, struct machine *machine __maybe_unused) { + struct perf_inject *inject = container_of(tool, struct perf_inject, tool); uint32_t size; void *buf = event; size = event->header.size; while (size) { - int ret = write(STDOUT_FILENO, buf, size); + int ret = write(inject->output, buf, size); if (ret < 0) return -errno; size -= ret; buf += ret; + inject->bytes_written += ret; } return 0; @@ -80,12 +100,25 @@ static int perf_event__repipe(struct perf_tool *tool, return perf_event__repipe_synth(tool, event, machine); } +typedef int (*inject_handler)(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine); + static int perf_event__repipe_sample(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct machine *machine) + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) { + if (evsel->handler.func) { + inject_handler f = evsel->handler.func; + return f(tool, event, sample, evsel, machine); + } + + build_id__mark_dso_hit(tool, event, sample, evsel, machine); + return perf_event__repipe_synth(tool, event, machine); } @@ -102,14 +135,14 @@ static int perf_event__repipe_mmap(struct perf_tool *tool, return err; } -static int perf_event__repipe_task(struct perf_tool *tool, +static int perf_event__repipe_fork(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { int err; - err = perf_event__process_task(tool, event, sample, machine); + err = perf_event__process_fork(tool, event, sample, machine); perf_event__repipe(tool, event, sample, machine); return err; @@ -210,6 +243,80 @@ repipe: return 0; } +static int perf_inject__sched_process_exit(struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct perf_inject *inject = container_of(tool, struct perf_inject, tool); + struct event_entry *ent; + + list_for_each_entry(ent, &inject->samples, node) { + if (sample->tid == ent->tid) { + list_del_init(&ent->node); + free(ent); + break; + } + } + + return 0; +} + +static int perf_inject__sched_switch(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + struct perf_inject *inject = container_of(tool, struct perf_inject, tool); + struct event_entry *ent; + + perf_inject__sched_process_exit(tool, event, sample, evsel, machine); + + ent = malloc(event->header.size + sizeof(struct event_entry)); + if (ent == NULL) { + color_fprintf(stderr, PERF_COLOR_RED, + "Not enough memory to process sched switch event!"); + return -1; + } + + ent->tid = sample->tid; + memcpy(&ent->event, event, event->header.size); + list_add(&ent->node, &inject->samples); + return 0; +} + +static int perf_inject__sched_stat(struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + struct event_entry *ent; + union perf_event *event_sw; + struct perf_sample sample_sw; + struct perf_inject *inject = container_of(tool, struct perf_inject, tool); + u32 pid = perf_evsel__intval(evsel, sample, "pid"); + + list_for_each_entry(ent, &inject->samples, node) { + if (pid == ent->tid) + goto found; + } + + return 0; +found: + event_sw = &ent->event[0]; + perf_evsel__parse_sample(evsel, event_sw, &sample_sw); + + sample_sw.period = sample->period; + sample_sw.time = sample->time; + perf_event__synthesize_sample(event_sw, evsel->attr.sample_type, + &sample_sw, false); + build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine); + return perf_event__repipe(tool, event_sw, &sample_sw, machine); +} + extern volatile int session_done; static void sig_handler(int sig __maybe_unused) @@ -217,6 +324,21 @@ static void sig_handler(int sig __maybe_unused) session_done = 1; } +static int perf_evsel__check_stype(struct perf_evsel *evsel, + u64 sample_type, const char *sample_msg) +{ + struct perf_event_attr *attr = &evsel->attr; + const char *name = perf_evsel__name(evsel); + + if (!(attr->sample_type & sample_type)) { + pr_err("Samples for %s event do not have %s attribute set.", + name, sample_msg); + return -EINVAL; + } + + return 0; +} + static int __cmd_inject(struct perf_inject *inject) { struct perf_session *session; @@ -224,19 +346,48 @@ static int __cmd_inject(struct perf_inject *inject) signal(SIGINT, sig_handler); - if (inject->build_ids) { - inject->tool.sample = perf_event__inject_buildid; + if (inject->build_ids || inject->sched_stat) { inject->tool.mmap = perf_event__repipe_mmap; - inject->tool.fork = perf_event__repipe_task; + inject->tool.fork = perf_event__repipe_fork; inject->tool.tracing_data = perf_event__repipe_tracing_data; } - session = perf_session__new("-", O_RDONLY, false, true, &inject->tool); + session = perf_session__new(inject->input_name, O_RDONLY, false, true, &inject->tool); if (session == NULL) return -ENOMEM; + if (inject->build_ids) { + inject->tool.sample = perf_event__inject_buildid; + } else if (inject->sched_stat) { + struct perf_evsel *evsel; + + inject->tool.ordered_samples = true; + + list_for_each_entry(evsel, &session->evlist->entries, node) { + const char *name = perf_evsel__name(evsel); + + if (!strcmp(name, "sched:sched_switch")) { + if (perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID")) + return -EINVAL; + + evsel->handler.func = perf_inject__sched_switch; + } else if (!strcmp(name, "sched:sched_process_exit")) + evsel->handler.func = perf_inject__sched_process_exit; + else if (!strncmp(name, "sched:sched_stat_", 17)) + evsel->handler.func = perf_inject__sched_stat; + } + } + + if (!inject->pipe_output) + lseek(inject->output, session->header.data_offset, SEEK_SET); + ret = perf_session__process_events(session, &inject->tool); + if (!inject->pipe_output) { + session->header.data_size = inject->bytes_written; + perf_session__write_header(session, session->evlist, inject->output, true); + } + perf_session__delete(session); return ret; @@ -260,10 +411,20 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .tracing_data = perf_event__repipe_tracing_data_synth, .build_id = perf_event__repipe_op2_synth, }, + .input_name = "-", + .samples = LIST_HEAD_INIT(inject.samples), }; + const char *output_name = "-"; const struct option options[] = { OPT_BOOLEAN('b', "build-ids", &inject.build_ids, "Inject build-ids into the output stream"), + OPT_STRING('i', "input", &inject.input_name, "file", + "input file name"), + OPT_STRING('o', "output", &output_name, "file", + "output file name"), + OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat, + "Merge sched-stat and sched-switch for getting events " + "where and how long tasks slept"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show build ids, etc)"), OPT_END() @@ -281,6 +442,18 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(inject_usage, options); + if (!strcmp(output_name, "-")) { + inject.pipe_output = 1; + inject.output = STDOUT_FILENO; + } else { + inject.output = open(output_name, O_CREAT | O_WRONLY | O_TRUNC, + S_IRUSR | S_IWUSR); + if (inject.output < 0) { + perror("failed to create output file"); + return -1; + } + } + if (symbol__init() < 0) return -1; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 14bf82f6365..46878daca5c 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -17,6 +17,7 @@ #include "util/debug.h" #include <linux/rbtree.h> +#include <linux/string.h> struct alloc_stat; typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *); @@ -340,7 +341,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session, int n_lines, int is_caller) { struct rb_node *next; - struct machine *machine; + struct machine *machine = &session->machines.host; printf("%.102s\n", graph_dotted_line); printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr"); @@ -349,11 +350,6 @@ static void __print_result(struct rb_root *root, struct perf_session *session, next = rb_first(root); - machine = perf_session__find_host_machine(session); - if (!machine) { - pr_err("__print_result: couldn't find kernel information\n"); - return; - } while (next && n_lines--) { struct alloc_stat *data = rb_entry(next, struct alloc_stat, node); @@ -477,7 +473,7 @@ static void sort_result(void) __sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort); } -static int __cmd_kmem(const char *input_name) +static int __cmd_kmem(void) { int err = -EINVAL; struct perf_session *session; @@ -614,8 +610,7 @@ static struct sort_dimension *avail_sorts[] = { &pingpong_sort_dimension, }; -#define NUM_AVAIL_SORTS \ - (int)(sizeof(avail_sorts) / sizeof(struct sort_dimension *)) +#define NUM_AVAIL_SORTS ((int)ARRAY_SIZE(avail_sorts)) static int sort_dimension__add(const char *tok, struct list_head *list) { @@ -624,12 +619,11 @@ static int sort_dimension__add(const char *tok, struct list_head *list) for (i = 0; i < NUM_AVAIL_SORTS; i++) { if (!strcmp(avail_sorts[i]->name, tok)) { - sort = malloc(sizeof(*sort)); + sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i])); if (!sort) { - pr_err("%s: malloc failed\n", __func__); + pr_err("%s: memdup failed\n", __func__); return -1; } - memcpy(sort, avail_sorts[i], sizeof(*sort)); list_add_tail(&sort->list, list); return 0; } @@ -743,7 +737,6 @@ static int __cmd_record(int argc, const char **argv) int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const default_sort_order = "frag,hit,bytes"; - const char *input_name = NULL; const struct option kmem_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_CALLBACK_NOOPT(0, "caller", NULL, NULL, @@ -779,7 +772,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (list_empty(&alloc_sort)) setup_sorting(&alloc_sort, default_sort_order); - return __cmd_kmem(input_name); + return __cmd_kmem(); } else usage_with_options(kmem_usage, kmem_options); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 260abc535b5..37a769d7f9f 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -22,9 +22,10 @@ #include <pthread.h> #include <math.h> -#include "../../arch/x86/include/asm/svm.h" -#include "../../arch/x86/include/asm/vmx.h" -#include "../../arch/x86/include/asm/kvm.h" +#if defined(__i386__) || defined(__x86_64__) +#include <asm/svm.h> +#include <asm/vmx.h> +#include <asm/kvm.h> struct event_key { #define INVALID_KEY (~0ULL) @@ -58,7 +59,7 @@ struct kvm_event_key { }; -struct perf_kvm; +struct perf_kvm_stat; struct kvm_events_ops { bool (*is_begin_event)(struct perf_evsel *evsel, @@ -66,7 +67,7 @@ struct kvm_events_ops { struct event_key *key); bool (*is_end_event)(struct perf_evsel *evsel, struct perf_sample *sample, struct event_key *key); - void (*decode_key)(struct perf_kvm *kvm, struct event_key *key, + void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, char decode[20]); const char *name; }; @@ -79,7 +80,7 @@ struct exit_reasons_table { #define EVENTS_BITS 12 #define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) -struct perf_kvm { +struct perf_kvm_stat { struct perf_tool tool; struct perf_session *session; @@ -146,7 +147,7 @@ static struct exit_reasons_table svm_exit_reasons[] = { SVM_EXIT_REASONS }; -static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code) +static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code) { int i = kvm->exit_reasons_size; struct exit_reasons_table *tbl = kvm->exit_reasons; @@ -162,7 +163,7 @@ static const char *get_exit_reason(struct perf_kvm *kvm, u64 exit_code) return "UNKNOWN"; } -static void exit_event_decode_key(struct perf_kvm *kvm, +static void exit_event_decode_key(struct perf_kvm_stat *kvm, struct event_key *key, char decode[20]) { @@ -228,7 +229,7 @@ static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, return false; } -static void mmio_event_decode_key(struct perf_kvm *kvm __maybe_unused, +static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char decode[20]) { @@ -271,7 +272,7 @@ static bool ioport_event_end(struct perf_evsel *evsel, return kvm_entry_event(evsel); } -static void ioport_event_decode_key(struct perf_kvm *kvm __maybe_unused, +static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char decode[20]) { @@ -286,7 +287,7 @@ static struct kvm_events_ops ioport_events = { .name = "IO Port Access" }; -static bool register_kvm_events_ops(struct perf_kvm *kvm) +static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) { bool ret = true; @@ -311,11 +312,11 @@ struct vcpu_event_record { }; -static void init_kvm_event_record(struct perf_kvm *kvm) +static void init_kvm_event_record(struct perf_kvm_stat *kvm) { - int i; + unsigned int i; - for (i = 0; i < (int)EVENTS_CACHE_SIZE; i++) + for (i = 0; i < EVENTS_CACHE_SIZE; i++) INIT_LIST_HEAD(&kvm->kvm_events_cache[i]); } @@ -360,7 +361,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key) return event; } -static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm, +static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, struct event_key *key) { struct kvm_event *event; @@ -369,9 +370,10 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm, BUG_ON(key->key == INVALID_KEY); head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)]; - list_for_each_entry(event, head, hash_entry) + list_for_each_entry(event, head, hash_entry) { if (event->key.key == key->key && event->key.info == key->info) return event; + } event = kvm_alloc_init_event(key); if (!event) @@ -381,7 +383,7 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm *kvm, return event; } -static bool handle_begin_event(struct perf_kvm *kvm, +static bool handle_begin_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, u64 timestamp) { @@ -416,7 +418,10 @@ static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event) static bool update_kvm_event(struct kvm_event *event, int vcpu_id, u64 time_diff) { - kvm_update_event_stats(&event->total, time_diff); + if (vcpu_id == -1) { + kvm_update_event_stats(&event->total, time_diff); + return true; + } if (!kvm_event_expand(event, vcpu_id)) return false; @@ -425,13 +430,19 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id, return true; } -static bool handle_end_event(struct perf_kvm *kvm, +static bool handle_end_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, u64 timestamp) { struct kvm_event *event; u64 time_begin, time_diff; + int vcpu; + + if (kvm->trace_vcpu == -1) + vcpu = -1; + else + vcpu = vcpu_record->vcpu_id; event = vcpu_record->last_event; time_begin = vcpu_record->start_time; @@ -461,7 +472,7 @@ static bool handle_end_event(struct perf_kvm *kvm, BUG_ON(timestamp < time_begin); time_diff = timestamp - time_begin; - return update_kvm_event(event, vcpu_record->vcpu_id, time_diff); + return update_kvm_event(event, vcpu, time_diff); } static @@ -486,7 +497,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread, return thread->priv; } -static bool handle_kvm_event(struct perf_kvm *kvm, +static bool handle_kvm_event(struct perf_kvm_stat *kvm, struct thread *thread, struct perf_evsel *evsel, struct perf_sample *sample) @@ -498,6 +509,11 @@ static bool handle_kvm_event(struct perf_kvm *kvm, if (!vcpu_record) return true; + /* only process events for vcpus user cares about */ + if ((kvm->trace_vcpu != -1) && + (kvm->trace_vcpu != vcpu_record->vcpu_id)) + return true; + if (kvm->events_ops->is_begin_event(evsel, sample, &key)) return handle_begin_event(kvm, vcpu_record, &key, sample->time); @@ -541,7 +557,7 @@ static struct kvm_event_key keys[] = { { NULL, NULL } }; -static bool select_key(struct perf_kvm *kvm) +static bool select_key(struct perf_kvm_stat *kvm) { int i; @@ -577,7 +593,8 @@ static void insert_to_result(struct rb_root *result, struct kvm_event *event, rb_insert_color(&event->rb, result); } -static void update_total_count(struct perf_kvm *kvm, struct kvm_event *event) +static void +update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event) { int vcpu = kvm->trace_vcpu; @@ -590,19 +607,21 @@ static bool event_is_valid(struct kvm_event *event, int vcpu) return !!get_event_count(event, vcpu); } -static void sort_result(struct perf_kvm *kvm) +static void sort_result(struct perf_kvm_stat *kvm) { unsigned int i; int vcpu = kvm->trace_vcpu; struct kvm_event *event; - for (i = 0; i < EVENTS_CACHE_SIZE; i++) - list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) + for (i = 0; i < EVENTS_CACHE_SIZE; i++) { + list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) { if (event_is_valid(event, vcpu)) { update_total_count(kvm, event); insert_to_result(&kvm->result, event, kvm->compare, vcpu); } + } + } } /* returns left most element of result, and erase it */ @@ -627,7 +646,7 @@ static void print_vcpu_info(int vcpu) pr_info("VCPU %d:\n\n", vcpu); } -static void print_result(struct perf_kvm *kvm) +static void print_result(struct perf_kvm_stat *kvm) { char decode[20]; struct kvm_event *event; @@ -659,8 +678,8 @@ static void print_result(struct perf_kvm *kvm) pr_info("\n"); } - pr_info("\nTotal Samples:%lld, Total events handled time:%.2fus.\n\n", - (unsigned long long)kvm->total_count, kvm->total_time / 1e3); + pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n", + kvm->total_count, kvm->total_time / 1e3); } static int process_sample_event(struct perf_tool *tool, @@ -670,7 +689,8 @@ static int process_sample_event(struct perf_tool *tool, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, sample->tid); - struct perf_kvm *kvm = container_of(tool, struct perf_kvm, tool); + struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, + tool); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", @@ -701,7 +721,7 @@ static int get_cpu_isa(struct perf_session *session) return isa; } -static int read_events(struct perf_kvm *kvm) +static int read_events(struct perf_kvm_stat *kvm) { int ret; @@ -750,7 +770,7 @@ static bool verify_vcpu(int vcpu) return true; } -static int kvm_events_report_vcpu(struct perf_kvm *kvm) +static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) { int ret = -EINVAL; int vcpu = kvm->trace_vcpu; @@ -798,7 +818,8 @@ static const char * const record_args[] = { _p; \ }) -static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv) +static int +kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) { unsigned int rec_argc, i, j; const char **rec_argv; @@ -821,7 +842,8 @@ static int kvm_events_record(struct perf_kvm *kvm, int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -static int kvm_events_report(struct perf_kvm *kvm, int argc, const char **argv) +static int +kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) { const struct option kvm_events_report_options[] = { OPT_STRING(0, "event", &kvm->report_event, "report event", @@ -864,24 +886,37 @@ static void print_kvm_stat_usage(void) printf("\nOtherwise, it is the alias of 'perf stat':\n"); } -static int kvm_cmd_stat(struct perf_kvm *kvm, int argc, const char **argv) +static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) { + struct perf_kvm_stat kvm = { + .file_name = file_name, + + .trace_vcpu = -1, + .report_event = "vmexit", + .sort_key = "sample", + + .exit_reasons = svm_exit_reasons, + .exit_reasons_size = ARRAY_SIZE(svm_exit_reasons), + .exit_reasons_isa = "SVM", + }; + if (argc == 1) { print_kvm_stat_usage(); goto perf_stat; } if (!strncmp(argv[1], "rec", 3)) - return kvm_events_record(kvm, argc - 1, argv + 1); + return kvm_events_record(&kvm, argc - 1, argv + 1); if (!strncmp(argv[1], "rep", 3)) - return kvm_events_report(kvm, argc - 1 , argv + 1); + return kvm_events_report(&kvm, argc - 1 , argv + 1); perf_stat: return cmd_stat(argc, argv, NULL); } +#endif -static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv) +static int __cmd_record(const char *file_name, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -890,7 +925,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv) rec_argv = calloc(rec_argc + 1, sizeof(char *)); rec_argv[i++] = strdup("record"); rec_argv[i++] = strdup("-o"); - rec_argv[i++] = strdup(kvm->file_name); + rec_argv[i++] = strdup(file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -899,7 +934,7 @@ static int __cmd_record(struct perf_kvm *kvm, int argc, const char **argv) return cmd_record(i, rec_argv, NULL); } -static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv) +static int __cmd_report(const char *file_name, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -908,7 +943,7 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv) rec_argv = calloc(rec_argc + 1, sizeof(char *)); rec_argv[i++] = strdup("report"); rec_argv[i++] = strdup("-i"); - rec_argv[i++] = strdup(kvm->file_name); + rec_argv[i++] = strdup(file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -917,7 +952,8 @@ static int __cmd_report(struct perf_kvm *kvm, int argc, const char **argv) return cmd_report(i, rec_argv, NULL); } -static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv) +static int +__cmd_buildid_list(const char *file_name, int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; @@ -926,7 +962,7 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv) rec_argv = calloc(rec_argc + 1, sizeof(char *)); rec_argv[i++] = strdup("buildid-list"); rec_argv[i++] = strdup("-i"); - rec_argv[i++] = strdup(kvm->file_name); + rec_argv[i++] = strdup(file_name); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -937,20 +973,11 @@ static int __cmd_buildid_list(struct perf_kvm *kvm, int argc, const char **argv) int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) { - struct perf_kvm kvm = { - .trace_vcpu = -1, - .report_event = "vmexit", - .sort_key = "sample", - - .exit_reasons = svm_exit_reasons, - .exit_reasons_size = ARRAY_SIZE(svm_exit_reasons), - .exit_reasons_isa = "SVM", - }; - + const char *file_name = NULL; const struct option kvm_options[] = { - OPT_STRING('i', "input", &kvm.file_name, "file", + OPT_STRING('i', "input", &file_name, "file", "Input file name"), - OPT_STRING('o', "output", &kvm.file_name, "file", + OPT_STRING('o', "output", &file_name, "file", "Output file name"), OPT_BOOLEAN(0, "guest", &perf_guest, "Collect guest os data"), @@ -985,32 +1012,34 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) if (!perf_host) perf_guest = 1; - if (!kvm.file_name) { + if (!file_name) { if (perf_host && !perf_guest) - kvm.file_name = strdup("perf.data.host"); + file_name = strdup("perf.data.host"); else if (!perf_host && perf_guest) - kvm.file_name = strdup("perf.data.guest"); + file_name = strdup("perf.data.guest"); else - kvm.file_name = strdup("perf.data.kvm"); + file_name = strdup("perf.data.kvm"); - if (!kvm.file_name) { + if (!file_name) { pr_err("Failed to allocate memory for filename\n"); return -ENOMEM; } } if (!strncmp(argv[0], "rec", 3)) - return __cmd_record(&kvm, argc, argv); + return __cmd_record(file_name, argc, argv); else if (!strncmp(argv[0], "rep", 3)) - return __cmd_report(&kvm, argc, argv); + return __cmd_report(file_name, argc, argv); else if (!strncmp(argv[0], "diff", 4)) return cmd_diff(argc, argv, NULL); else if (!strncmp(argv[0], "top", 3)) return cmd_top(argc, argv, NULL); else if (!strncmp(argv[0], "buildid-list", 12)) - return __cmd_buildid_list(&kvm, argc, argv); + return __cmd_buildid_list(file_name, argc, argv); +#if defined(__i386__) || defined(__x86_64__) else if (!strncmp(argv[0], "stat", 4)) - return kvm_cmd_stat(&kvm, argc, argv); + return kvm_cmd_stat(file_name, argc, argv); +#endif else usage_with_options(kvm_usage, kvm_options); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 6f5f328157a..42583006974 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -335,8 +335,6 @@ alloc_failed: return NULL; } -static const char *input_name; - struct trace_lock_handler { int (*acquire_event)(struct perf_evsel *evsel, struct perf_sample *sample); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e9231659754..774c90713a5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -31,6 +31,38 @@ #include <sched.h> #include <sys/mman.h> +#ifndef HAVE_ON_EXIT +#ifndef ATEXIT_MAX +#define ATEXIT_MAX 32 +#endif +static int __on_exit_count = 0; +typedef void (*on_exit_func_t) (int, void *); +static on_exit_func_t __on_exit_funcs[ATEXIT_MAX]; +static void *__on_exit_args[ATEXIT_MAX]; +static int __exitcode = 0; +static void __handle_on_exit_funcs(void); +static int on_exit(on_exit_func_t function, void *arg); +#define exit(x) (exit)(__exitcode = (x)) + +static int on_exit(on_exit_func_t function, void *arg) +{ + if (__on_exit_count == ATEXIT_MAX) + return -ENOMEM; + else if (__on_exit_count == 0) + atexit(__handle_on_exit_funcs); + __on_exit_funcs[__on_exit_count] = function; + __on_exit_args[__on_exit_count++] = arg; + return 0; +} + +static void __handle_on_exit_funcs(void) +{ + int i; + for (i = 0; i < __on_exit_count; i++) + __on_exit_funcs[i] (__exitcode, __on_exit_args[i]); +} +#endif + enum write_mode_t { WRITE_FORCE, WRITE_APPEND @@ -192,121 +224,28 @@ static bool perf_evlist__equal(struct perf_evlist *evlist, static int perf_record__open(struct perf_record *rec) { + char msg[512]; struct perf_evsel *pos; struct perf_evlist *evlist = rec->evlist; struct perf_session *session = rec->session; struct perf_record_opts *opts = &rec->opts; int rc = 0; - perf_evlist__config_attrs(evlist, opts); - - if (opts->group) - perf_evlist__set_leader(evlist); + perf_evlist__config(evlist, opts); list_for_each_entry(pos, &evlist->entries, node) { - struct perf_event_attr *attr = &pos->attr; - /* - * Check if parse_single_tracepoint_event has already asked for - * PERF_SAMPLE_TIME. - * - * XXX this is kludgy but short term fix for problems introduced by - * eac23d1c that broke 'perf script' by having different sample_types - * when using multiple tracepoint events when we use a perf binary - * that tries to use sample_id_all on an older kernel. - * - * We need to move counter creation to perf_session, support - * different sample_types, etc. - */ - bool time_needed = attr->sample_type & PERF_SAMPLE_TIME; - -fallback_missing_features: - if (opts->exclude_guest_missing) - attr->exclude_guest = attr->exclude_host = 0; -retry_sample_id: - attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1; try_again: if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) { - int err = errno; - - if (err == EPERM || err == EACCES) { - ui__error_paranoid(); - rc = -err; - goto out; - } else if (err == ENODEV && opts->target.cpu_list) { - pr_err("No such device - did you specify" - " an out-of-range profile CPU?\n"); - rc = -err; - goto out; - } else if (err == EINVAL) { - if (!opts->exclude_guest_missing && - (attr->exclude_guest || attr->exclude_host)) { - pr_debug("Old kernel, cannot exclude " - "guest or host samples.\n"); - opts->exclude_guest_missing = true; - goto fallback_missing_features; - } else if (!opts->sample_id_all_missing) { - /* - * Old kernel, no attr->sample_id_type_all field - */ - opts->sample_id_all_missing = true; - if (!opts->sample_time && !opts->raw_samples && !time_needed) - attr->sample_type &= ~PERF_SAMPLE_TIME; - - goto retry_sample_id; - } - } - - /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support. - * - * PPC returns ENXIO until 2.6.37 (behavior changed - * with commit b0a873e). - */ - if ((err == ENOENT || err == ENXIO) - && attr->type == PERF_TYPE_HARDWARE - && attr->config == PERF_COUNT_HW_CPU_CYCLES) { - + if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) { if (verbose) - ui__warning("The cycles event is not supported, " - "trying to fall back to cpu-clock-ticks\n"); - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - if (pos->name) { - free(pos->name); - pos->name = NULL; - } + ui__warning("%s\n", msg); goto try_again; } - if (err == ENOENT) { - ui__error("The %s event is not supported.\n", - perf_evsel__name(pos)); - rc = -err; - goto out; - } - - printf("\n"); - error("sys_perf_event_open() syscall returned with %d " - "(%s) for event %s. /bin/dmesg may provide " - "additional information.\n", - err, strerror(err), perf_evsel__name(pos)); - -#if defined(__i386__) || defined(__x86_64__) - if (attr->type == PERF_TYPE_HARDWARE && - err == EOPNOTSUPP) { - pr_err("No hardware sampling interrupt available." - " No APIC? If so then you can boot the kernel" - " with the \"lapic\" boot parameter to" - " force-enable it.\n"); - rc = -err; - goto out; - } -#endif - - pr_err("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - rc = -err; + rc = -errno; + perf_evsel__open_strerror(pos, &opts->target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); goto out; } } @@ -326,7 +265,8 @@ try_again: "or try again with a smaller value of -m/--mmap_pages.\n" "(current value: %d)\n", opts->mmap_pages); rc = -errno; - } else if (!is_power_of_2(opts->mmap_pages)) { + } else if (!is_power_of_2(opts->mmap_pages) && + (opts->mmap_pages != UINT_MAX)) { pr_err("--mmap_pages/-m value must be a power of two."); rc = -EINVAL; } else { @@ -388,10 +328,6 @@ static void perf_event__synthesize_guest_os(struct machine *machine, void *data) { int err; struct perf_tool *tool = data; - - if (machine__is_host(machine)) - return; - /* *As for guest kernel when processing subcommand record&report, *we arrange module mmap prior to guest kernel mmap and trigger @@ -460,6 +396,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) struct perf_evlist *evsel_list = rec->evlist; const char *output_name = rec->output_name; struct perf_session *session; + bool disabled = false; rec->progname = argv[0]; @@ -549,6 +486,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) goto out_delete_session; } + if (!evsel_list->nr_groups) + perf_header__clear_feat(&session->header, HEADER_GROUP_DESC); + /* * perf_session__delete(session) will be called at perf_record__exit() */ @@ -575,12 +515,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) rec->post_processing_offset = lseek(output, 0, SEEK_CUR); - machine = perf_session__find_host_machine(session); - if (!machine) { - pr_err("Couldn't find native kernel information.\n"); - err = -1; - goto out_delete_session; - } + machine = &session->machines.host; if (opts->pipe_output) { err = perf_event__synthesize_attrs(tool, session, @@ -633,9 +568,10 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" "Check /proc/modules permission or run as root.\n"); - if (perf_guest) - perf_session__process_machines(session, tool, - perf_event__synthesize_guest_os); + if (perf_guest) { + machines__process_guests(&session->machines, + perf_event__synthesize_guest_os, tool); + } if (!opts->target.system_wide) err = perf_event__synthesize_thread_map(tool, evsel_list->threads, @@ -659,7 +595,13 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) } } - perf_evlist__enable(evsel_list); + /* + * When perf is starting the traced process, all the events + * (apart from group members) have enable_on_exec=1 set, + * so don't spoil it by prematurely enabling them. + */ + if (!perf_target__none(&opts->target)) + perf_evlist__enable(evsel_list); /* * Let the child rip @@ -682,8 +624,15 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) waking++; } - if (done) + /* + * When perf is starting the traced process, at the end events + * die with the process and we wait for that. Thus no need to + * disable events in this case. + */ + if (done && !disabled && !perf_target__none(&opts->target)) { perf_evlist__disable(evsel_list); + disabled = true; + } } if (quiet || signr == SIGUSR1) @@ -819,11 +768,10 @@ static int get_stack_size(char *str, unsigned long *_size) } #endif /* LIBUNWIND_SUPPORT */ -static int -parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, - int unset) +int record_parse_callchain_opt(const struct option *opt, + const char *arg, int unset) { - struct perf_record *rec = (struct perf_record *)opt->value; + struct perf_record_opts *opts = opt->value; char *tok, *name, *saveptr = NULL; char *buf; int ret = -1; @@ -849,7 +797,7 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, /* Framepointer style */ if (!strncmp(name, "fp", sizeof("fp"))) { if (!strtok_r(NULL, ",", &saveptr)) { - rec->opts.call_graph = CALLCHAIN_FP; + opts->call_graph = CALLCHAIN_FP; ret = 0; } else pr_err("callchain: No more arguments " @@ -862,20 +810,20 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, const unsigned long default_stack_dump_size = 8192; ret = 0; - rec->opts.call_graph = CALLCHAIN_DWARF; - rec->opts.stack_dump_size = default_stack_dump_size; + opts->call_graph = CALLCHAIN_DWARF; + opts->stack_dump_size = default_stack_dump_size; tok = strtok_r(NULL, ",", &saveptr); if (tok) { unsigned long size = 0; ret = get_stack_size(tok, &size); - rec->opts.stack_dump_size = size; + opts->stack_dump_size = size; } if (!ret) pr_debug("callchain: stack dump size %d\n", - rec->opts.stack_dump_size); + opts->stack_dump_size); #endif /* LIBUNWIND_SUPPORT */ } else { pr_err("callchain: Unknown -g option " @@ -888,7 +836,7 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, free(buf); if (!ret) - pr_debug("callchain: type %d\n", rec->opts.call_graph); + pr_debug("callchain: type %d\n", opts->call_graph); return ret; } @@ -926,9 +874,9 @@ static struct perf_record record = { #define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " #ifdef LIBUNWIND_SUPPORT -static const char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; #else -static const char callchain_help[] = CALLCHAIN_HELP "[fp]"; +const char record_callchain_help[] = CALLCHAIN_HELP "[fp]"; #endif /* @@ -972,9 +920,9 @@ const struct option record_options[] = { "number of mmap data pages"), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]", - callchain_help, &parse_callchain_opt, - "fp"), + OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts, + "mode[,dump_size]", record_callchain_help, + &record_parse_callchain_opt, "fp"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"), diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index a61725d89d3..96b5a7fee4b 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -8,6 +8,7 @@ #include "builtin.h" #include "util/util.h" +#include "util/cache.h" #include "util/annotate.h" #include "util/color.h" @@ -33,13 +34,13 @@ #include "util/thread.h" #include "util/sort.h" #include "util/hist.h" +#include "arch/common.h" #include <linux/bitmap.h> struct perf_report { struct perf_tool tool; struct perf_session *session; - char const *input_name; bool force, use_tui, use_gtk, use_stdio; bool hide_unresolved; bool dont_use_callchains; @@ -54,6 +55,16 @@ struct perf_report { DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; +static int perf_report_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "report.group")) { + symbol_conf.event_group = perf_config_bool(var, value); + return 0; + } + + return perf_default_config(var, value, cb); +} + static int perf_report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al, struct perf_sample *sample, @@ -299,6 +310,21 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, char unit; unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE]; u64 nr_events = self->stats.total_period; + struct perf_evsel *evsel = hists_to_evsel(self); + char buf[512]; + size_t size = sizeof(buf); + + if (symbol_conf.event_group && evsel->nr_members > 1) { + struct perf_evsel *pos; + + perf_evsel__group_desc(evsel, buf, size); + evname = buf; + + for_each_group_member(pos, evsel) { + nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos->hists.stats.total_period; + } + } nr_samples = convert_unit(nr_samples, &unit); ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit); @@ -319,6 +345,10 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, struct hists *hists = &pos->hists; const char *evname = perf_evsel__name(pos); + if (symbol_conf.event_group && + !perf_evsel__is_group_leader(pos)) + continue; + hists__fprintf_nr_sample_events(hists, evname, stdout); hists__fprintf(hists, true, 0, 0, stdout); fprintf(stdout, "\n\n"); @@ -372,7 +402,7 @@ static int __cmd_report(struct perf_report *rep) if (ret) goto out_delete; - kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION]; + kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION]; kernel_kmap = map__kmap(kernel_map); if (kernel_map == NULL || (kernel_map->dso->hit && @@ -416,8 +446,16 @@ static int __cmd_report(struct perf_report *rep) hists->symbol_filter_str = rep->symbol_filter_str; hists__collapse_resort(hists); - hists__output_resort(hists); nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE]; + + /* Non-group events are considered as leader */ + if (symbol_conf.event_group && + !perf_evsel__is_group_leader(pos)) { + struct hists *leader_hists = &pos->leader->hists; + + hists__match(leader_hists, hists); + hists__link(leader_hists, hists); + } } if (nr_samples == 0) { @@ -425,13 +463,25 @@ static int __cmd_report(struct perf_report *rep) goto out_delete; } + list_for_each_entry(pos, &session->evlist->entries, node) + hists__output_resort(&pos->hists); + if (use_browser > 0) { if (use_browser == 1) { - perf_evlist__tui_browse_hists(session->evlist, help, - NULL, NULL, 0); + ret = perf_evlist__tui_browse_hists(session->evlist, + help, + NULL, + &session->header.env); + /* + * Usually "ret" is the last pressed key, and we only + * care if the key notifies us to switch data file. + */ + if (ret != K_SWITCH_INPUT_DATA) + ret = 0; + } else if (use_browser == 2) { perf_evlist__gtk_browse_hists(session->evlist, help, - NULL, NULL, 0); + NULL); } } else perf_evlist__tty_browse_hists(session->evlist, rep, help); @@ -556,8 +606,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .sample = process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .lost = perf_event__process_lost, .read = process_read_event, .attr = perf_event__process_attr, @@ -570,7 +620,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .pretty_printing_style = "normal", }; const struct option options[] = { - OPT_STRING('i', "input", &report.input_name, "file", + OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), @@ -594,8 +644,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "stdio", &report.use_stdio, "Use the stdio interface"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent, dso_to," - " dso_from, symbol_to, symbol_from, mispredict"), + "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline," + " dso_to, dso_from, symbol_to, symbol_from, mispredict"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", @@ -637,6 +687,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "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, "", "use branch records for histogram filling", parse_branch_mode), OPT_STRING(0, "objdump", &objdump_path, "path", @@ -644,6 +696,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_END() }; + perf_config(perf_report_config, NULL); + argc = parse_options(argc, argv, options, report_usage, 0); if (report.use_stdio) @@ -656,13 +710,23 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) if (report.inverted_callchain) callchain_param.order = ORDER_CALLER; - if (!report.input_name || !strlen(report.input_name)) { + if (!input_name || !strlen(input_name)) { if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) - report.input_name = "-"; + input_name = "-"; else - report.input_name = "perf.data"; + input_name = "perf.data"; + } + + if (strcmp(input_name, "-") != 0) + setup_browser(true); + else { + use_browser = 0; + perf_hpp__column_enable(PERF_HPP__OVERHEAD); + perf_hpp__init(); } - session = perf_session__new(report.input_name, O_RDONLY, + +repeat: + session = perf_session__new(input_name, O_RDONLY, report.force, false, &report.tool); if (session == NULL) return -ENOMEM; @@ -687,14 +751,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) } - if (strcmp(report.input_name, "-") != 0) - setup_browser(true); - else { - use_browser = 0; - perf_hpp__init(); - } - - setup_sorting(report_usage, options); + if (setup_sorting() < 0) + usage_with_options(report_usage, options); /* * Only in the newt browser we are doing integrated annotation, @@ -762,6 +820,12 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) } ret = __cmd_report(&report); + if (ret == K_SWITCH_INPUT_DATA) { + perf_session__delete(session); + goto repeat; + } else + ret = 0; + error: perf_session__delete(session); return ret; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 3488ead3b60..138229439a9 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -120,7 +120,6 @@ struct trace_sched_handler { struct perf_sched { struct perf_tool tool; - const char *input_name; const char *sort_order; unsigned long nr_tasks; struct task_desc *pid_to_task[MAX_PID]; @@ -1460,7 +1459,7 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy, }; struct perf_session *session; - session = perf_session__new(sched->input_name, O_RDONLY, 0, false, &sched->tool); + session = perf_session__new(input_name, O_RDONLY, 0, false, &sched->tool); if (session == NULL) { pr_debug("No Memory for session\n"); return -1; @@ -1476,9 +1475,9 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy, goto out_delete; } - sched->nr_events = session->hists.stats.nr_events[0]; - sched->nr_lost_events = session->hists.stats.total_lost; - sched->nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST]; + sched->nr_events = session->stats.nr_events[0]; + sched->nr_lost_events = session->stats.total_lost; + sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST]; } if (destroy) @@ -1672,7 +1671,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, .lost = perf_event__process_lost, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .ordered_samples = true, }, .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), @@ -1707,7 +1707,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) OPT_END() }; const struct option sched_options[] = { - OPT_STRING('i', "input", &sched.input_name, "file", + OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index fb9625083a2..92d4658f56f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -520,8 +520,8 @@ static struct perf_tool perf_script = { .sample = process_sample_event, .mmap = perf_event__process_mmap, .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, .attr = perf_event__process_attr, .event_type = perf_event__process_event_type, .tracing_data = perf_event__process_tracing_data, @@ -692,7 +692,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { char *tok; - int i, imax = sizeof(all_output_options) / sizeof(struct output_option); + int i, imax = ARRAY_SIZE(all_output_options); int j; int rc = 0; char *str = strdup(arg); @@ -909,18 +909,6 @@ static const char *ends_with(const char *str, const char *suffix) return NULL; } -static char *ltrim(char *str) -{ - int len = strlen(str); - - while (len && isspace(*str)) { - len--; - str++; - } - - return str; -} - static int read_script_info(struct script_desc *desc, const char *filename) { char line[BUFSIZ], *p; @@ -1030,6 +1018,68 @@ static int list_available_scripts(const struct option *opt __maybe_unused, } /* + * Some scripts specify the required events in their "xxx-record" file, + * this function will check if the events in perf.data match those + * mentioned in the "xxx-record". + * + * Fixme: All existing "xxx-record" are all in good formats "-e event ", + * which is covered well now. And new parsing code should be added to + * cover the future complexing formats like event groups etc. + */ +static int check_ev_match(char *dir_name, char *scriptname, + struct perf_session *session) +{ + char filename[MAXPATHLEN], evname[128]; + char line[BUFSIZ], *p; + struct perf_evsel *pos; + int match, len; + FILE *fp; + + sprintf(filename, "%s/bin/%s-record", dir_name, scriptname); + + fp = fopen(filename, "r"); + if (!fp) + return -1; + + while (fgets(line, sizeof(line), fp)) { + p = ltrim(line); + if (*p == '#') + continue; + + while (strlen(p)) { + p = strstr(p, "-e"); + if (!p) + break; + + p += 2; + p = ltrim(p); + len = strcspn(p, " \t"); + if (!len) + break; + + snprintf(evname, len + 1, "%s", p); + + match = 0; + list_for_each_entry(pos, + &session->evlist->entries, node) { + if (!strcmp(perf_evsel__name(pos), evname)) { + match = 1; + break; + } + } + + if (!match) { + fclose(fp); + return -1; + } + } + } + + fclose(fp); + return 0; +} + +/* * Return -1 if none is found, otherwise the actual scripts number. * * Currently the only user of this function is the script browser, which @@ -1039,17 +1089,23 @@ static int list_available_scripts(const struct option *opt __maybe_unused, int find_scripts(char **scripts_array, char **scripts_path_array) { struct dirent *script_next, *lang_next, script_dirent, lang_dirent; - char scripts_path[MAXPATHLEN]; + char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; - char lang_path[MAXPATHLEN]; + struct perf_session *session; char *temp; int i = 0; + session = perf_session__new(input_name, O_RDONLY, 0, false, NULL); + if (!session) + return -1; + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path()); scripts_dir = opendir(scripts_path); - if (!scripts_dir) + if (!scripts_dir) { + perf_session__delete(session); return -1; + } for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, @@ -1077,10 +1133,18 @@ int find_scripts(char **scripts_array, char **scripts_path_array) snprintf(scripts_array[i], (temp - script_dirent.d_name) + 1, "%s", script_dirent.d_name); + + if (check_ev_match(lang_path, + scripts_array[i], session)) + continue; + i++; } + closedir(lang_dir); } + closedir(scripts_dir); + perf_session__delete(session); return i; } @@ -1175,7 +1239,6 @@ static int have_cmd(int argc, const char **argv) int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) { bool show_full_info = false; - const char *input_name = NULL; char *rec_script_path = NULL; char *rep_script_path = NULL; struct perf_session *session; @@ -1412,7 +1475,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - perf_session__fprintf_info(session, stdout, show_full_info); + if (!script_name && !generate_script_lang) + perf_session__fprintf_info(session, stdout, show_full_info); if (!no_callchain) symbol_conf.use_callchain = true; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 93b9011fa3e..99848761f57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -57,6 +57,7 @@ #include "util/thread.h" #include "util/thread_map.h" +#include <stdlib.h> #include <sys/prctl.h> #include <locale.h> @@ -64,6 +65,11 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" +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 struct perf_evlist *evsel_list; static struct perf_target target = { @@ -74,6 +80,7 @@ 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 pid_t child_pid = -1; static bool null_run = false; static int detailed_run = 0; @@ -83,6 +90,12 @@ static const char *csv_sep = NULL; static bool csv_output = false; static bool group = false; static FILE *output = NULL; +static const char *pre_cmd = NULL; +static const char *post_cmd = NULL; +static bool sync_run = false; +static unsigned int interval = 0; +static struct timespec ref_time; +static struct cpu_map *sock_map; static volatile int done = 0; @@ -90,6 +103,28 @@ struct perf_stat { struct stats res_stats[3]; }; +static inline void diff_timespec(struct timespec *r, struct timespec *a, + struct timespec *b) +{ + r->tv_sec = a->tv_sec - b->tv_sec; + if (a->tv_nsec < b->tv_nsec) { + r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec; + r->tv_sec--; + } else { + r->tv_nsec = a->tv_nsec - b->tv_nsec ; + } +} + +static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +{ + return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus; +} + +static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) +{ + return perf_evsel__cpus(evsel)->nr; +} + static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat)); @@ -102,14 +137,27 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) evsel->priv = NULL; } -static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel) { - return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus; + void *addr; + size_t sz; + + sz = sizeof(*evsel->counts) + + (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values)); + + addr = zalloc(sz); + if (!addr) + return -ENOMEM; + + evsel->prev_raw_counts = addr; + + return 0; } -static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) +static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) { - return perf_evsel__cpus(evsel)->nr; + free(evsel->prev_raw_counts); + evsel->prev_raw_counts = NULL; } static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; @@ -125,12 +173,9 @@ 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 int create_perf_stat_counter(struct perf_evsel *evsel, - struct perf_evsel *first) +static int create_perf_stat_counter(struct perf_evsel *evsel) { struct perf_event_attr *attr = &evsel->attr; - bool exclude_guest_missing = false; - int ret; if (scale) attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | @@ -138,37 +183,16 @@ static int create_perf_stat_counter(struct perf_evsel *evsel, attr->inherit = !no_inherit; -retry: - if (exclude_guest_missing) - evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; - - if (perf_target__has_cpu(&target)) { - ret = perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); - if (ret) - goto check_ret; - return 0; - } + if (perf_target__has_cpu(&target)) + return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); - if (!perf_target__has_task(&target) && (!group || evsel == first)) { + if (!perf_target__has_task(&target) && + perf_evsel__is_group_leader(evsel)) { attr->disabled = 1; attr->enable_on_exec = 1; } - ret = perf_evsel__open_per_thread(evsel, evsel_list->threads); - if (!ret) - return 0; - /* fall through */ -check_ret: - if (ret && errno == EINVAL) { - if (!exclude_guest_missing && - (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { - pr_debug("Old kernel, cannot exclude " - "guest or host samples.\n"); - exclude_guest_missing = true; - goto retry; - } - } - return ret; + return perf_evsel__open_per_thread(evsel, evsel_list->threads); } /* @@ -265,15 +289,79 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static int run_perf_stat(int argc __maybe_unused, const char **argv) +static void print_interval(void) +{ + static int num_print_interval; + struct perf_evsel *counter; + struct perf_stat *ps; + struct timespec ts, rs; + char prefix[64]; + + if (no_aggr) { + list_for_each_entry(counter, &evsel_list->entries, node) { + ps = counter->priv; + memset(ps->res_stats, 0, sizeof(ps->res_stats)); + read_counter(counter); + } + } 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); + } + } + 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) + fprintf(output, "# time socket cpus counts events\n"); + else if (no_aggr) + fprintf(output, "# time CPU counts events\n"); + else + 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) { + list_for_each_entry(counter, &evsel_list->entries, node) + print_counter(counter, prefix); + } else { + 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) { + char msg[512]; unsigned long long t0, t1; - struct perf_evsel *counter, *first; + 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; + ts.tv_nsec = (interval % 1000) * 1000000; + } else { + ts.tv_sec = 1; + 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; @@ -328,10 +416,8 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv) if (group) perf_evlist__set_leader(evsel_list); - first = perf_evlist__first(evsel_list); - list_for_each_entry(counter, &evsel_list->entries, node) { - if (create_perf_stat_counter(counter, first) < 0) { + if (create_perf_stat_counter(counter) < 0) { /* * PPC returns ENXIO for HW counters until 2.6.37 * (behavior changed with commit b0a873e). @@ -346,20 +432,13 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv) continue; } - if (errno == EPERM || errno == EACCES) { - error("You may not have permission to collect %sstats.\n" - "\t Consider tweaking" - " /proc/sys/kernel/perf_event_paranoid or running as root.", - target.system_wide ? "system-wide " : ""); - } else { - error("open_counter returned with %d (%s). " - "/bin/dmesg may provide additional information.\n", - errno, strerror(errno)); - } + perf_evsel__open_strerror(counter, &target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); + if (child_pid != -1) kill(child_pid, SIGTERM); - pr_err("Not all events could be opened.\n"); return -1; } counter->supported = true; @@ -375,14 +454,25 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv) * Enable counters and exec the command: */ t0 = rdclock(); + clock_gettime(CLOCK_MONOTONIC, &ref_time); if (forks) { close(go_pipe[1]); + if (interval) { + while (!waitpid(child_pid, &status, WNOHANG)) { + nanosleep(&ts, NULL); + print_interval(); + } + } wait(&status); if (WIFSIGNALED(status)) psignal(WTERMSIG(status), argv[0]); } else { - while(!done) sleep(1); + while (!done) { + nanosleep(&ts, NULL); + if (interval) + print_interval(); + } } t1 = rdclock(); @@ -405,6 +495,32 @@ static int run_perf_stat(int argc __maybe_unused, const char **argv) return WEXITSTATUS(status); } +static int run_perf_stat(int argc __maybe_unused, const char **argv) +{ + int ret; + + if (pre_cmd) { + ret = system(pre_cmd); + if (ret) + return ret; + } + + if (sync_run) + sync(); + + ret = __run_perf_stat(argc, argv); + if (ret) + return ret; + + if (post_cmd) { + ret = system(post_cmd); + if (ret) + return ret; + } + + return ret; +} + static void print_noise_pct(double total, double avg) { double pct = rel_stddev_stats(total, avg); @@ -426,13 +542,21 @@ 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, struct perf_evsel *evsel, double avg) +static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) { double msecs = avg / 1e6; char cpustr[16] = { '\0', }; const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s"; - if (no_aggr) + 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); @@ -442,7 +566,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); - if (csv_output) + if (csv_output || interval) return; if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) @@ -631,7 +755,7 @@ static void print_ll_cache_misses(int cpu, fprintf(output, " of all LL-cache hits "); } -static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) +static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) { double total, ratio = 0.0; char cpustr[16] = { '\0', }; @@ -644,7 +768,15 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) else fmt = "%s%18.0f%s%-25s"; - if (no_aggr) + 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); @@ -656,12 +788,11 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); - if (csv_output) + if (csv_output || interval) return; if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { total = avg_stats(&runtime_cycles_stats[cpu]); - if (total) ratio = avg / total; @@ -751,16 +882,83 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) } } +static void print_aggr_socket(char *prefix) +{ + struct perf_evsel *counter; + u64 ena, run, val; + int cpu, s, s2, sock, nr; + + if (!sock_map) + return; + + for (s = 0; s < sock_map->nr; s++) { + sock = cpu_map__socket(sock_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) + continue; + val += counter->counts->cpu[cpu].val; + ena += counter->counts->cpu[cpu].ena; + run += counter->counts->cpu[cpu].run; + nr++; + } + if (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, + 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); + + fputc('\n', output); + continue; + } + + if (nsec_counter(counter)) + nsec_printout(sock, nr, counter, val); + else + abs_printout(sock, nr, counter, val); + + if (!csv_output) { + print_noise(counter, 1.0); + + if (run != ena) + fprintf(output, " (%.2f%%)", + 100.0 * run / ena); + } + fputc('\n', output); + } + } +} + /* * Print out the results of a single counter: * aggregated counts in system-wide mode */ -static void print_counter_aggr(struct perf_evsel *counter) +static void print_counter_aggr(struct perf_evsel *counter, char *prefix) { struct perf_stat *ps = counter->priv; double avg = avg_stats(&ps->res_stats[0]); int scaled = counter->counts->scaled; + if (prefix) + fprintf(output, "%s", prefix); + if (scaled == -1) { fprintf(output, "%*s%s%*s", csv_output ? 0 : 18, @@ -777,9 +975,9 @@ static void print_counter_aggr(struct perf_evsel *counter) } if (nsec_counter(counter)) - nsec_printout(-1, counter, avg); + nsec_printout(-1, 0, counter, avg); else - abs_printout(-1, counter, avg); + abs_printout(-1, 0, counter, avg); print_noise(counter, avg); @@ -803,7 +1001,7 @@ static void print_counter_aggr(struct perf_evsel *counter) * Print out the results of a single counter: * does not use aggregated count in system-wide */ -static void print_counter(struct perf_evsel *counter) +static void print_counter(struct perf_evsel *counter, char *prefix) { u64 ena, run, val; int cpu; @@ -812,6 +1010,10 @@ static void print_counter(struct perf_evsel *counter) val = counter->counts->cpu[cpu].val; ena = counter->counts->cpu[cpu].ena; run = counter->counts->cpu[cpu].run; + + if (prefix) + fprintf(output, "%s", prefix); + if (run == 0 || ena == 0) { fprintf(output, "CPU%*d%s%*s%s%*s", csv_output ? 0 : -4, @@ -831,9 +1033,9 @@ static void print_counter(struct perf_evsel *counter) } if (nsec_counter(counter)) - nsec_printout(cpu, counter, val); + nsec_printout(cpu, 0, counter, val); else - abs_printout(cpu, counter, val); + abs_printout(cpu, 0, counter, val); if (!csv_output) { print_noise(counter, 1.0); @@ -871,12 +1073,14 @@ static void print_stat(int argc, const char **argv) fprintf(output, ":\n\n"); } - if (no_aggr) { + if (aggr_socket) + print_aggr_socket(NULL); + else if (no_aggr) { list_for_each_entry(counter, &evsel_list->entries, node) - print_counter(counter); + print_counter(counter, NULL); } else { list_for_each_entry(counter, &evsel_list->entries, node) - print_counter_aggr(counter); + print_counter_aggr(counter, NULL); } if (!csv_output) { @@ -897,7 +1101,7 @@ static volatile int signr = -1; static void skip_signal(int signo) { - if(child_pid == -1) + if ((child_pid == -1) || interval) done = 1; signr = signo; @@ -1069,8 +1273,7 @@ static int add_default_attributes(void) int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) { - bool append_file = false, - sync_run = false; + bool append_file = false; int output_fd = 0; const char *output_name = NULL; const struct option options[] = { @@ -1114,6 +1317,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "append", &append_file, "append to the output file"), OPT_INTEGER(0, "log-fd", &output_fd, "log output to fd, instead of stderr"), + OPT_STRING(0, "pre", &pre_cmd, "command", + "command to run prior to the measured command"), + OPT_STRING(0, "post", &post_cmd, "command", + "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_END() }; const char * const stat_usage[] = { @@ -1200,6 +1410,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) 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; + } + if (add_default_attributes()) goto out; @@ -1214,12 +1432,23 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) usage_with_options(stat_usage, options); return -1; } + if (interval && interval < 100) { + pr_err("print interval must be >= 100ms\n"); + usage_with_options(stat_usage, options); + 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; + } + } /* * We dont want to block the signals - that would cause @@ -1229,6 +1458,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) */ atexit(sig_atexit); signal(SIGINT, skip_signal); + signal(SIGCHLD, skip_signal); signal(SIGALRM, skip_signal); signal(SIGABRT, skip_signal); @@ -1238,17 +1468,17 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); - if (sync_run) - sync(); - status = run_perf_stat(argc, argv); } - if (status != -1) + if (status != -1 && !interval) print_stat(argc, argv); out_free_fd: - list_for_each_entry(pos, &evsel_list->entries, node) + 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__delete_maps(evsel_list); out: perf_evlist__delete(evsel_list); diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c deleted file mode 100644 index 484f26cc0c0..00000000000 --- a/tools/perf/builtin-test.c +++ /dev/null @@ -1,1547 +0,0 @@ -/* - * builtin-test.c - * - * Builtin regression testing command: ever growing number of sanity tests - */ -#include "builtin.h" - -#include "util/cache.h" -#include "util/debug.h" -#include "util/debugfs.h" -#include "util/evlist.h" -#include "util/parse-options.h" -#include "util/parse-events.h" -#include "util/symbol.h" -#include "util/thread_map.h" -#include "util/pmu.h" -#include "event-parse.h" -#include "../../include/linux/hw_breakpoint.h" - -#include <sys/mman.h> - -static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused, - struct symbol *sym) -{ - bool *visited = symbol__priv(sym); - *visited = true; - return 0; -} - -static int test__vmlinux_matches_kallsyms(void) -{ - int err = -1; - struct rb_node *nd; - struct symbol *sym; - struct map *kallsyms_map, *vmlinux_map; - struct machine kallsyms, vmlinux; - enum map_type type = MAP__FUNCTION; - long page_size = sysconf(_SC_PAGE_SIZE); - struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", }; - - /* - * Step 1: - * - * Init the machines that will hold kernel, modules obtained from - * both vmlinux + .ko files and from /proc/kallsyms split by modules. - */ - machine__init(&kallsyms, "", HOST_KERNEL_ID); - machine__init(&vmlinux, "", HOST_KERNEL_ID); - - /* - * Step 2: - * - * Create the kernel maps for kallsyms and the DSO where we will then - * load /proc/kallsyms. Also create the modules maps from /proc/modules - * and find the .ko files that match them in /lib/modules/`uname -r`/. - */ - if (machine__create_kernel_maps(&kallsyms) < 0) { - pr_debug("machine__create_kernel_maps "); - return -1; - } - - /* - * Step 3: - * - * Load and split /proc/kallsyms into multiple maps, one per module. - */ - if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, NULL) <= 0) { - pr_debug("dso__load_kallsyms "); - goto out; - } - - /* - * Step 4: - * - * kallsyms will be internally on demand sorted by name so that we can - * find the reference relocation * symbol, i.e. the symbol we will use - * to see if the running kernel was relocated by checking if it has the - * same value in the vmlinux file we load. - */ - kallsyms_map = machine__kernel_map(&kallsyms, type); - - sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL); - if (sym == NULL) { - pr_debug("dso__find_symbol_by_name "); - goto out; - } - - ref_reloc_sym.addr = sym->start; - - /* - * Step 5: - * - * Now repeat step 2, this time for the vmlinux file we'll auto-locate. - */ - if (machine__create_kernel_maps(&vmlinux) < 0) { - pr_debug("machine__create_kernel_maps "); - goto out; - } - - vmlinux_map = machine__kernel_map(&vmlinux, type); - map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym; - - /* - * Step 6: - * - * Locate a vmlinux file in the vmlinux path that has a buildid that - * matches the one of the running kernel. - * - * While doing that look if we find the ref reloc symbol, if we find it - * we'll have its ref_reloc_symbol.unrelocated_addr and then - * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines - * to fixup the symbols. - */ - if (machine__load_vmlinux_path(&vmlinux, type, - vmlinux_matches_kallsyms_filter) <= 0) { - pr_debug("machine__load_vmlinux_path "); - goto out; - } - - err = 0; - /* - * Step 7: - * - * Now look at the symbols in the vmlinux DSO and check if we find all of them - * in the kallsyms dso. For the ones that are in both, check its names and - * end addresses too. - */ - for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) { - struct symbol *pair, *first_pair; - bool backwards = true; - - sym = rb_entry(nd, struct symbol, rb_node); - - if (sym->start == sym->end) - continue; - - first_pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL); - pair = first_pair; - - if (pair && pair->start == sym->start) { -next_pair: - if (strcmp(sym->name, pair->name) == 0) { - /* - * kallsyms don't have the symbol end, so we - * set that by using the next symbol start - 1, - * in some cases we get this up to a page - * wrong, trace_kmalloc when I was developing - * this code was one such example, 2106 bytes - * off the real size. More than that and we - * _really_ have a problem. - */ - s64 skew = sym->end - pair->end; - if (llabs(skew) < page_size) - continue; - - pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n", - sym->start, sym->name, sym->end, pair->end); - } else { - struct rb_node *nnd; -detour: - nnd = backwards ? rb_prev(&pair->rb_node) : - rb_next(&pair->rb_node); - if (nnd) { - struct symbol *next = rb_entry(nnd, struct symbol, rb_node); - - if (next->start == sym->start) { - pair = next; - goto next_pair; - } - } - - if (backwards) { - backwards = false; - pair = first_pair; - goto detour; - } - - pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", - sym->start, sym->name, pair->name); - } - } else - pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->start, sym->name); - - err = -1; - } - - if (!verbose) - goto out; - - pr_info("Maps only in vmlinux:\n"); - - for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node), *pair; - /* - * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while - * the kernel will have the path for the vmlinux file being used, - * so use the short name, less descriptive but the same ("[kernel]" in - * both cases. - */ - pair = map_groups__find_by_name(&kallsyms.kmaps, type, - (pos->dso->kernel ? - pos->dso->short_name : - pos->dso->name)); - if (pair) - pair->priv = 1; - else - map__fprintf(pos, stderr); - } - - pr_info("Maps in vmlinux with a different name in kallsyms:\n"); - - for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node), *pair; - - pair = map_groups__find(&kallsyms.kmaps, type, pos->start); - if (pair == NULL || pair->priv) - continue; - - if (pair->start == pos->start) { - pair->priv = 1; - pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", - pos->start, pos->end, pos->pgoff, pos->dso->name); - if (pos->pgoff != pair->pgoff || pos->end != pair->end) - pr_info(": \n*%" PRIx64 "-%" PRIx64 " %" PRIx64 "", - pair->start, pair->end, pair->pgoff); - pr_info(" %s\n", pair->dso->name); - pair->priv = 1; - } - } - - pr_info("Maps only in kallsyms:\n"); - - for (nd = rb_first(&kallsyms.kmaps.maps[type]); - nd; nd = rb_next(nd)) { - struct map *pos = rb_entry(nd, struct map, rb_node); - - if (!pos->priv) - map__fprintf(pos, stderr); - } -out: - return err; -} - -#include "util/cpumap.h" -#include "util/evsel.h" -#include <sys/types.h> - -static int trace_event__id(const char *evname) -{ - char *filename; - int err = -1, fd; - - if (asprintf(&filename, - "%s/syscalls/%s/id", - tracing_events_path, evname) < 0) - return -1; - - fd = open(filename, O_RDONLY); - if (fd >= 0) { - char id[16]; - if (read(fd, id, sizeof(id)) > 0) - err = atoi(id); - close(fd); - } - - free(filename); - return err; -} - -static int test__open_syscall_event(void) -{ - int err = -1, fd; - struct thread_map *threads; - struct perf_evsel *evsel; - struct perf_event_attr attr; - unsigned int nr_open_calls = 111, i; - int id = trace_event__id("sys_enter_open"); - - if (id < 0) { - pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); - return -1; - } - - threads = thread_map__new(-1, getpid(), UINT_MAX); - if (threads == NULL) { - pr_debug("thread_map__new\n"); - return -1; - } - - memset(&attr, 0, sizeof(attr)); - attr.type = PERF_TYPE_TRACEPOINT; - attr.config = id; - evsel = perf_evsel__new(&attr, 0); - if (evsel == NULL) { - pr_debug("perf_evsel__new\n"); - goto out_thread_map_delete; - } - - if (perf_evsel__open_per_thread(evsel, threads) < 0) { - pr_debug("failed to open counter: %s, " - "tweak /proc/sys/kernel/perf_event_paranoid?\n", - strerror(errno)); - goto out_evsel_delete; - } - - for (i = 0; i < nr_open_calls; ++i) { - fd = open("/etc/passwd", O_RDONLY); - close(fd); - } - - if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) { - pr_debug("perf_evsel__read_on_cpu\n"); - goto out_close_fd; - } - - if (evsel->counts->cpu[0].val != nr_open_calls) { - pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n", - nr_open_calls, evsel->counts->cpu[0].val); - goto out_close_fd; - } - - err = 0; -out_close_fd: - perf_evsel__close_fd(evsel, 1, threads->nr); -out_evsel_delete: - perf_evsel__delete(evsel); -out_thread_map_delete: - thread_map__delete(threads); - return err; -} - -#include <sched.h> - -static int test__open_syscall_event_on_all_cpus(void) -{ - int err = -1, fd, cpu; - struct thread_map *threads; - struct cpu_map *cpus; - struct perf_evsel *evsel; - struct perf_event_attr attr; - unsigned int nr_open_calls = 111, i; - cpu_set_t cpu_set; - int id = trace_event__id("sys_enter_open"); - - if (id < 0) { - pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); - return -1; - } - - threads = thread_map__new(-1, getpid(), UINT_MAX); - if (threads == NULL) { - pr_debug("thread_map__new\n"); - return -1; - } - - cpus = cpu_map__new(NULL); - if (cpus == NULL) { - pr_debug("cpu_map__new\n"); - goto out_thread_map_delete; - } - - - CPU_ZERO(&cpu_set); - - memset(&attr, 0, sizeof(attr)); - attr.type = PERF_TYPE_TRACEPOINT; - attr.config = id; - evsel = perf_evsel__new(&attr, 0); - if (evsel == NULL) { - pr_debug("perf_evsel__new\n"); - goto out_thread_map_delete; - } - - if (perf_evsel__open(evsel, cpus, threads) < 0) { - pr_debug("failed to open counter: %s, " - "tweak /proc/sys/kernel/perf_event_paranoid?\n", - strerror(errno)); - goto out_evsel_delete; - } - - for (cpu = 0; cpu < cpus->nr; ++cpu) { - unsigned int ncalls = nr_open_calls + cpu; - /* - * XXX eventually lift this restriction in a way that - * keeps perf building on older glibc installations - * without CPU_ALLOC. 1024 cpus in 2010 still seems - * a reasonable upper limit tho :-) - */ - if (cpus->map[cpu] >= CPU_SETSIZE) { - pr_debug("Ignoring CPU %d\n", cpus->map[cpu]); - continue; - } - - CPU_SET(cpus->map[cpu], &cpu_set); - if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { - pr_debug("sched_setaffinity() failed on CPU %d: %s ", - cpus->map[cpu], - strerror(errno)); - goto out_close_fd; - } - for (i = 0; i < ncalls; ++i) { - fd = open("/etc/passwd", O_RDONLY); - close(fd); - } - CPU_CLR(cpus->map[cpu], &cpu_set); - } - - /* - * Here we need to explicitely preallocate the counts, as if - * we use the auto allocation it will allocate just for 1 cpu, - * as we start by cpu 0. - */ - if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) { - pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr); - goto out_close_fd; - } - - err = 0; - - for (cpu = 0; cpu < cpus->nr; ++cpu) { - unsigned int expected; - - if (cpus->map[cpu] >= CPU_SETSIZE) - continue; - - if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) { - pr_debug("perf_evsel__read_on_cpu\n"); - err = -1; - break; - } - - expected = nr_open_calls + cpu; - if (evsel->counts->cpu[cpu].val != expected) { - pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", - expected, cpus->map[cpu], evsel->counts->cpu[cpu].val); - err = -1; - } - } - -out_close_fd: - perf_evsel__close_fd(evsel, 1, threads->nr); -out_evsel_delete: - perf_evsel__delete(evsel); -out_thread_map_delete: - thread_map__delete(threads); - return err; -} - -/* - * This test will generate random numbers of calls to some getpid syscalls, - * then establish an mmap for a group of events that are created to monitor - * the syscalls. - * - * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated - * sample.id field to map back to its respective perf_evsel instance. - * - * Then it checks if the number of syscalls reported as perf events by - * the kernel corresponds to the number of syscalls made. - */ -static int test__basic_mmap(void) -{ - int err = -1; - union perf_event *event; - struct thread_map *threads; - struct cpu_map *cpus; - struct perf_evlist *evlist; - struct perf_event_attr attr = { - .type = PERF_TYPE_TRACEPOINT, - .read_format = PERF_FORMAT_ID, - .sample_type = PERF_SAMPLE_ID, - .watermark = 0, - }; - cpu_set_t cpu_set; - const char *syscall_names[] = { "getsid", "getppid", "getpgrp", - "getpgid", }; - pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp, - (void*)getpgid }; -#define nsyscalls ARRAY_SIZE(syscall_names) - int ids[nsyscalls]; - unsigned int nr_events[nsyscalls], - expected_nr_events[nsyscalls], i, j; - struct perf_evsel *evsels[nsyscalls], *evsel; - - for (i = 0; i < nsyscalls; ++i) { - char name[64]; - - snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]); - ids[i] = trace_event__id(name); - if (ids[i] < 0) { - pr_debug("Is debugfs mounted on /sys/kernel/debug?\n"); - return -1; - } - nr_events[i] = 0; - expected_nr_events[i] = random() % 257; - } - - threads = thread_map__new(-1, getpid(), UINT_MAX); - if (threads == NULL) { - pr_debug("thread_map__new\n"); - return -1; - } - - cpus = cpu_map__new(NULL); - if (cpus == NULL) { - pr_debug("cpu_map__new\n"); - goto out_free_threads; - } - - CPU_ZERO(&cpu_set); - CPU_SET(cpus->map[0], &cpu_set); - sched_setaffinity(0, sizeof(cpu_set), &cpu_set); - if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { - pr_debug("sched_setaffinity() failed on CPU %d: %s ", - cpus->map[0], strerror(errno)); - goto out_free_cpus; - } - - evlist = perf_evlist__new(cpus, threads); - if (evlist == NULL) { - pr_debug("perf_evlist__new\n"); - goto out_free_cpus; - } - - /* anonymous union fields, can't be initialized above */ - attr.wakeup_events = 1; - attr.sample_period = 1; - - for (i = 0; i < nsyscalls; ++i) { - attr.config = ids[i]; - evsels[i] = perf_evsel__new(&attr, i); - if (evsels[i] == NULL) { - pr_debug("perf_evsel__new\n"); - goto out_free_evlist; - } - - perf_evlist__add(evlist, evsels[i]); - - if (perf_evsel__open(evsels[i], cpus, threads) < 0) { - pr_debug("failed to open counter: %s, " - "tweak /proc/sys/kernel/perf_event_paranoid?\n", - strerror(errno)); - goto out_close_fd; - } - } - - if (perf_evlist__mmap(evlist, 128, true) < 0) { - pr_debug("failed to mmap events: %d (%s)\n", errno, - strerror(errno)); - goto out_close_fd; - } - - for (i = 0; i < nsyscalls; ++i) - for (j = 0; j < expected_nr_events[i]; ++j) { - int foo = syscalls[i](); - ++foo; - } - - while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { - struct perf_sample sample; - - if (event->header.type != PERF_RECORD_SAMPLE) { - pr_debug("unexpected %s event\n", - perf_event__name(event->header.type)); - goto out_munmap; - } - - err = perf_evlist__parse_sample(evlist, event, &sample); - if (err) { - pr_err("Can't parse sample, err = %d\n", err); - goto out_munmap; - } - - evsel = perf_evlist__id2evsel(evlist, sample.id); - if (evsel == NULL) { - pr_debug("event with id %" PRIu64 - " doesn't map to an evsel\n", sample.id); - goto out_munmap; - } - nr_events[evsel->idx]++; - } - - list_for_each_entry(evsel, &evlist->entries, node) { - if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) { - pr_debug("expected %d %s events, got %d\n", - expected_nr_events[evsel->idx], - perf_evsel__name(evsel), nr_events[evsel->idx]); - goto out_munmap; - } - } - - err = 0; -out_munmap: - perf_evlist__munmap(evlist); -out_close_fd: - for (i = 0; i < nsyscalls; ++i) - perf_evsel__close_fd(evsels[i], 1, threads->nr); -out_free_evlist: - perf_evlist__delete(evlist); -out_free_cpus: - cpu_map__delete(cpus); -out_free_threads: - thread_map__delete(threads); - return err; -#undef nsyscalls -} - -static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t **maskp, - size_t *sizep) -{ - cpu_set_t *mask; - size_t size; - int i, cpu = -1, nrcpus = 1024; -realloc: - mask = CPU_ALLOC(nrcpus); - size = CPU_ALLOC_SIZE(nrcpus); - CPU_ZERO_S(size, mask); - - if (sched_getaffinity(pid, size, mask) == -1) { - CPU_FREE(mask); - if (errno == EINVAL && nrcpus < (1024 << 8)) { - nrcpus = nrcpus << 2; - goto realloc; - } - perror("sched_getaffinity"); - return -1; - } - - for (i = 0; i < nrcpus; i++) { - if (CPU_ISSET_S(i, size, mask)) { - if (cpu == -1) { - cpu = i; - *maskp = mask; - *sizep = size; - } else - CPU_CLR_S(i, size, mask); - } - } - - if (cpu == -1) - CPU_FREE(mask); - - return cpu; -} - -static int test__PERF_RECORD(void) -{ - struct perf_record_opts opts = { - .target = { - .uid = UINT_MAX, - .uses_mmap = true, - }, - .no_delay = true, - .freq = 10, - .mmap_pages = 256, - }; - cpu_set_t *cpu_mask = NULL; - size_t cpu_mask_size = 0; - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); - struct perf_evsel *evsel; - struct perf_sample sample; - const char *cmd = "sleep"; - const char *argv[] = { cmd, "1", NULL, }; - char *bname; - u64 prev_time = 0; - bool found_cmd_mmap = false, - found_libc_mmap = false, - found_vdso_mmap = false, - found_ld_mmap = false; - int err = -1, errs = 0, i, wakeups = 0; - u32 cpu; - int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, }; - - if (evlist == NULL || argv == NULL) { - pr_debug("Not enough memory to create evlist\n"); - goto out; - } - - /* - * 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_delete_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. - */ - err = perf_evlist__create_maps(evlist, &opts.target); - if (err < 0) { - pr_debug("Not enough memory to create thread/cpu maps\n"); - goto out_delete_evlist; - } - - /* - * Prepare the workload in argv[] to run, it'll fork it, and then wait - * for perf_evlist__start_workload() to exec it. This is done this way - * 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); - if (err < 0) { - pr_debug("Couldn't run the workload!\n"); - goto out_delete_evlist; - } - - /* - * Config the evsels, setting attr->comm on the first one, etc. - */ - evsel = perf_evlist__first(evlist); - evsel->attr.sample_type |= PERF_SAMPLE_CPU; - evsel->attr.sample_type |= PERF_SAMPLE_TID; - evsel->attr.sample_type |= PERF_SAMPLE_TIME; - perf_evlist__config_attrs(evlist, &opts); - - err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask, - &cpu_mask_size); - if (err < 0) { - pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno)); - goto out_delete_evlist; - } - - cpu = err; - - /* - * So that we can check perf_sample.cpu on all the samples. - */ - if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, cpu_mask) < 0) { - pr_debug("sched_setaffinity: %s\n", strerror(errno)); - goto out_free_cpu_mask; - } - - /* - * Call sys_perf_event_open on all the fds on all the evsels, - * grouping them if asked to. - */ - err = perf_evlist__open(evlist); - if (err < 0) { - pr_debug("perf_evlist__open: %s\n", strerror(errno)); - goto out_delete_evlist; - } - - /* - * mmap the first fd on a given CPU and ask for events for the other - * fds in the same CPU to be injected in the same mmap ring buffer - * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)). - */ - err = perf_evlist__mmap(evlist, opts.mmap_pages, false); - if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); - goto out_delete_evlist; - } - - /* - * Now that all is properly set up, enable the events, they will - * count just on workload.pid, which will start... - */ - perf_evlist__enable(evlist); - - /* - * Now! - */ - perf_evlist__start_workload(evlist); - - while (1) { - int before = total_events; - - for (i = 0; i < evlist->nr_mmaps; i++) { - union perf_event *event; - - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { - const u32 type = event->header.type; - const char *name = perf_event__name(type); - - ++total_events; - if (type < PERF_RECORD_MAX) - nr_events[type]++; - - err = perf_evlist__parse_sample(evlist, event, &sample); - if (err < 0) { - if (verbose) - perf_event__fprintf(event, stderr); - pr_debug("Couldn't parse sample\n"); - goto out_err; - } - - if (verbose) { - pr_info("%" PRIu64" %d ", sample.time, sample.cpu); - perf_event__fprintf(event, stderr); - } - - if (prev_time > sample.time) { - pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n", - name, prev_time, sample.time); - ++errs; - } - - prev_time = sample.time; - - if (sample.cpu != cpu) { - pr_debug("%s with unexpected cpu, expected %d, got %d\n", - name, cpu, sample.cpu); - ++errs; - } - - if ((pid_t)sample.pid != evlist->workload.pid) { - pr_debug("%s with unexpected pid, expected %d, got %d\n", - name, evlist->workload.pid, sample.pid); - ++errs; - } - - if ((pid_t)sample.tid != evlist->workload.pid) { - pr_debug("%s with unexpected tid, expected %d, got %d\n", - name, evlist->workload.pid, sample.tid); - ++errs; - } - - if ((type == PERF_RECORD_COMM || - type == PERF_RECORD_MMAP || - type == PERF_RECORD_FORK || - type == PERF_RECORD_EXIT) && - (pid_t)event->comm.pid != evlist->workload.pid) { - pr_debug("%s with unexpected pid/tid\n", name); - ++errs; - } - - if ((type == PERF_RECORD_COMM || - type == PERF_RECORD_MMAP) && - event->comm.pid != event->comm.tid) { - pr_debug("%s with different pid/tid!\n", name); - ++errs; - } - - switch (type) { - case PERF_RECORD_COMM: - if (strcmp(event->comm.comm, cmd)) { - pr_debug("%s with unexpected comm!\n", name); - ++errs; - } - break; - case PERF_RECORD_EXIT: - goto found_exit; - case PERF_RECORD_MMAP: - bname = strrchr(event->mmap.filename, '/'); - if (bname != NULL) { - if (!found_cmd_mmap) - found_cmd_mmap = !strcmp(bname + 1, cmd); - if (!found_libc_mmap) - found_libc_mmap = !strncmp(bname + 1, "libc", 4); - if (!found_ld_mmap) - found_ld_mmap = !strncmp(bname + 1, "ld", 2); - } else if (!found_vdso_mmap) - found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]"); - break; - - case PERF_RECORD_SAMPLE: - /* Just ignore samples for now */ - break; - default: - pr_debug("Unexpected perf_event->header.type %d!\n", - type); - ++errs; - } - } - } - - /* - * We don't use poll here because at least at 3.1 times the - * PERF_RECORD_{!SAMPLE} events don't honour - * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does. - */ - if (total_events == before && false) - poll(evlist->pollfd, evlist->nr_fds, -1); - - sleep(1); - if (++wakeups > 5) { - pr_debug("No PERF_RECORD_EXIT event!\n"); - break; - } - } - -found_exit: - if (nr_events[PERF_RECORD_COMM] > 1) { - pr_debug("Excessive number of PERF_RECORD_COMM events!\n"); - ++errs; - } - - if (nr_events[PERF_RECORD_COMM] == 0) { - pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd); - ++errs; - } - - if (!found_cmd_mmap) { - pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd); - ++errs; - } - - if (!found_libc_mmap) { - pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc"); - ++errs; - } - - if (!found_ld_mmap) { - pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld"); - ++errs; - } - - if (!found_vdso_mmap) { - pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]"); - ++errs; - } -out_err: - perf_evlist__munmap(evlist); -out_free_cpu_mask: - CPU_FREE(cpu_mask); -out_delete_evlist: - perf_evlist__delete(evlist); -out: - return (err < 0 || errs > 0) ? -1 : 0; -} - - -#if defined(__x86_64__) || defined(__i386__) - -#define barrier() asm volatile("" ::: "memory") - -static u64 rdpmc(unsigned int counter) -{ - unsigned int low, high; - - asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter)); - - return low | ((u64)high) << 32; -} - -static u64 rdtsc(void) -{ - unsigned int low, high; - - asm volatile("rdtsc" : "=a" (low), "=d" (high)); - - return low | ((u64)high) << 32; -} - -static u64 mmap_read_self(void *addr) -{ - struct perf_event_mmap_page *pc = addr; - u32 seq, idx, time_mult = 0, time_shift = 0; - u64 count, cyc = 0, time_offset = 0, enabled, running, delta; - - do { - seq = pc->lock; - barrier(); - - enabled = pc->time_enabled; - running = pc->time_running; - - if (enabled != running) { - cyc = rdtsc(); - time_mult = pc->time_mult; - time_shift = pc->time_shift; - time_offset = pc->time_offset; - } - - idx = pc->index; - count = pc->offset; - if (idx) - count += rdpmc(idx - 1); - - barrier(); - } while (pc->lock != seq); - - if (enabled != running) { - u64 quot, rem; - - quot = (cyc >> time_shift); - rem = cyc & ((1 << time_shift) - 1); - delta = time_offset + quot * time_mult + - ((rem * time_mult) >> time_shift); - - enabled += delta; - if (idx) - running += delta; - - quot = count / running; - rem = count % running; - count = quot * enabled + (rem * enabled) / running; - } - - return count; -} - -/* - * If the RDPMC instruction faults then signal this back to the test parent task: - */ -static void segfault_handler(int sig __maybe_unused, - siginfo_t *info __maybe_unused, - void *uc __maybe_unused) -{ - exit(-1); -} - -static int __test__rdpmc(void) -{ - long page_size = sysconf(_SC_PAGE_SIZE); - volatile int tmp = 0; - u64 i, loops = 1000; - int n; - int fd; - void *addr; - struct perf_event_attr attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_INSTRUCTIONS, - .exclude_kernel = 1, - }; - u64 delta_sum = 0; - struct sigaction sa; - - sigfillset(&sa.sa_mask); - sa.sa_sigaction = segfault_handler; - sigaction(SIGSEGV, &sa, NULL); - - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - if (fd < 0) { - pr_err("Error: sys_perf_event_open() syscall returned " - "with %d (%s)\n", fd, strerror(errno)); - return -1; - } - - addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0); - if (addr == (void *)(-1)) { - pr_err("Error: mmap() syscall returned with (%s)\n", - strerror(errno)); - goto out_close; - } - - for (n = 0; n < 6; n++) { - u64 stamp, now, delta; - - stamp = mmap_read_self(addr); - - for (i = 0; i < loops; i++) - tmp++; - - now = mmap_read_self(addr); - loops *= 10; - - delta = now - stamp; - pr_debug("%14d: %14Lu\n", n, (long long)delta); - - delta_sum += delta; - } - - munmap(addr, page_size); - pr_debug(" "); -out_close: - close(fd); - - if (!delta_sum) - return -1; - - return 0; -} - -static int test__rdpmc(void) -{ - int status = 0; - int wret = 0; - int ret; - int pid; - - pid = fork(); - if (pid < 0) - return -1; - - if (!pid) { - ret = __test__rdpmc(); - - exit(ret); - } - - wret = waitpid(pid, &status, 0); - if (wret < 0 || status) - return -1; - - return 0; -} - -#endif - -static int test__perf_pmu(void) -{ - return perf_pmu__test(); -} - -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); - - if (evlist == NULL) - return -ENOMEM; - - for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { - for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { - /* skip invalid cache type */ - if (!perf_evsel__is_cache_op_valid(type, op)) - continue; - - for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - __perf_evsel__hw_cache_type_op_res_name(type, op, i, - name, sizeof(name)); - err = parse_events(evlist, name, 0); - if (err) - ret = err; - } - } - } - - idx = 0; - evsel = perf_evlist__first(evlist); - - for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { - for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { - /* skip invalid cache type */ - if (!perf_evsel__is_cache_op_valid(type, op)) - continue; - - for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - __perf_evsel__hw_cache_type_op_res_name(type, op, i, - name, sizeof(name)); - if (evsel->idx != idx) - continue; - - ++idx; - - if (strcmp(perf_evsel__name(evsel), name)) { - pr_debug("%s != %s\n", perf_evsel__name(evsel), name); - ret = -1; - } - - evsel = perf_evsel__next(evsel); - } - } - } - - perf_evlist__delete(evlist); - return ret; -} - -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); - - if (evlist == NULL) - return -ENOMEM; - - for (i = 0; i < nr_names; ++i) { - err = parse_events(evlist, names[i], 0); - if (err) { - pr_debug("failed to parse event '%s', err %d\n", - names[i], err); - goto out_delete_evlist; - } - } - - err = 0; - list_for_each_entry(evsel, &evlist->entries, node) { - if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) { - --err; - pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]); - } - } - -out_delete_evlist: - perf_evlist__delete(evlist); - return err; -} - -#define perf_evsel__name_array_test(names) \ - __perf_evsel__name_array_test(names, ARRAY_SIZE(names)) - -static int perf_evsel__roundtrip_name_test(void) -{ - int err = 0, ret = 0; - - err = perf_evsel__name_array_test(perf_evsel__hw_names); - if (err) - ret = err; - - err = perf_evsel__name_array_test(perf_evsel__sw_names); - if (err) - ret = err; - - err = perf_evsel__roundtrip_cache_name_test(); - if (err) - ret = err; - - return ret; -} - -static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, - int size, bool should_be_signed) -{ - struct format_field *field = perf_evsel__field(evsel, name); - int is_signed; - int ret = 0; - - if (field == NULL) { - pr_debug("%s: \"%s\" field not found!\n", evsel->name, name); - return -1; - } - - is_signed = !!(field->flags | FIELD_IS_SIGNED); - if (should_be_signed && !is_signed) { - pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", - evsel->name, name, is_signed, should_be_signed); - ret = -1; - } - - if (field->size != size) { - pr_debug("%s: \"%s\" size (%d) should be %d!\n", - evsel->name, name, field->size, size); - ret = -1; - } - - return ret; -} - -static int perf_evsel__tp_sched_test(void) -{ - struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch", 0); - int ret = 0; - - if (evsel == NULL) { - pr_debug("perf_evsel__new\n"); - return -1; - } - - if (perf_evsel__test_field(evsel, "prev_comm", 16, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "prev_pid", 4, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "prev_prio", 4, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "prev_state", 8, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "next_comm", 16, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "next_pid", 4, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "next_prio", 4, true)) - ret = -1; - - perf_evsel__delete(evsel); - - evsel = perf_evsel__newtp("sched", "sched_wakeup", 0); - - if (perf_evsel__test_field(evsel, "comm", 16, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "pid", 4, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "prio", 4, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "success", 4, true)) - ret = -1; - - if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) - ret = -1; - - return ret; -} - -static int test__syscall_open_tp_fields(void) -{ - struct perf_record_opts opts = { - .target = { - .uid = UINT_MAX, - .uses_mmap = true, - }, - .no_delay = true, - .freq = 1, - .mmap_pages = 256, - .raw_samples = true, - }; - const char *filename = "/etc/passwd"; - int flags = O_RDONLY | O_DIRECTORY; - struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); - struct perf_evsel *evsel; - int err = -1, i, nr_events = 0, nr_polls = 0; - - if (evlist == NULL) { - pr_debug("%s: perf_evlist__new\n", __func__); - goto out; - } - - evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0); - if (evsel == NULL) { - pr_debug("%s: perf_evsel__newtp\n", __func__); - goto out_delete_evlist; - } - - perf_evlist__add(evlist, evsel); - - err = perf_evlist__create_maps(evlist, &opts.target); - if (err < 0) { - pr_debug("%s: perf_evlist__create_maps\n", __func__); - goto out_delete_evlist; - } - - perf_evsel__config(evsel, &opts, evsel); - - evlist->threads->map[0] = getpid(); - - err = perf_evlist__open(evlist); - if (err < 0) { - pr_debug("perf_evlist__open: %s\n", strerror(errno)); - goto out_delete_evlist; - } - - err = perf_evlist__mmap(evlist, UINT_MAX, false); - if (err < 0) { - pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); - goto out_delete_evlist; - } - - perf_evlist__enable(evlist); - - /* - * Generate the event: - */ - open(filename, flags); - - while (1) { - int before = nr_events; - - for (i = 0; i < evlist->nr_mmaps; i++) { - union perf_event *event; - - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { - const u32 type = event->header.type; - int tp_flags; - struct perf_sample sample; - - ++nr_events; - - if (type != PERF_RECORD_SAMPLE) - continue; - - err = perf_evsel__parse_sample(evsel, event, &sample); - if (err) { - pr_err("Can't parse sample, err = %d\n", err); - goto out_munmap; - } - - tp_flags = perf_evsel__intval(evsel, &sample, "flags"); - - if (flags != tp_flags) { - pr_debug("%s: Expected flags=%#x, got %#x\n", - __func__, flags, tp_flags); - goto out_munmap; - } - - goto out_ok; - } - } - - if (nr_events == before) - poll(evlist->pollfd, evlist->nr_fds, 10); - - if (++nr_polls > 5) { - pr_debug("%s: no events!\n", __func__); - goto out_munmap; - } - } -out_ok: - err = 0; -out_munmap: - perf_evlist__munmap(evlist); -out_delete_evlist: - perf_evlist__delete(evlist); -out: - return err; -} - -static struct test { - const char *desc; - int (*func)(void); -} tests[] = { - { - .desc = "vmlinux symtab matches kallsyms", - .func = test__vmlinux_matches_kallsyms, - }, - { - .desc = "detect open syscall event", - .func = test__open_syscall_event, - }, - { - .desc = "detect open syscall event on all cpus", - .func = test__open_syscall_event_on_all_cpus, - }, - { - .desc = "read samples using the mmap interface", - .func = test__basic_mmap, - }, - { - .desc = "parse events tests", - .func = parse_events__test, - }, -#if defined(__x86_64__) || defined(__i386__) - { - .desc = "x86 rdpmc test", - .func = test__rdpmc, - }, -#endif - { - .desc = "Validate PERF_RECORD_* events & perf_sample fields", - .func = test__PERF_RECORD, - }, - { - .desc = "Test perf pmu format parsing", - .func = test__perf_pmu, - }, - { - .desc = "Test dso data interface", - .func = dso__test_data, - }, - { - .desc = "roundtrip evsel->name check", - .func = perf_evsel__roundtrip_name_test, - }, - { - .desc = "Check parsing of sched tracepoints fields", - .func = perf_evsel__tp_sched_test, - }, - { - .desc = "Generate and check syscalls:sys_enter_open event fields", - .func = test__syscall_open_tp_fields, - }, - { - .func = NULL, - }, -}; - -static bool perf_test__matches(int curr, int argc, const char *argv[]) -{ - int i; - - if (argc == 0) - return true; - - for (i = 0; i < argc; ++i) { - char *end; - long nr = strtoul(argv[i], &end, 10); - - if (*end == '\0') { - if (nr == curr + 1) - return true; - continue; - } - - if (strstr(tests[curr].desc, argv[i])) - return true; - } - - return false; -} - -static int __cmd_test(int argc, const char *argv[]) -{ - int i = 0; - - while (tests[i].func) { - int curr = i++, err; - - if (!perf_test__matches(curr, argc, argv)) - continue; - - pr_info("%2d: %s:", i, tests[curr].desc); - pr_debug("\n--- start ---\n"); - err = tests[curr].func(); - pr_debug("---- end ----\n%s:", tests[curr].desc); - pr_info(" %s\n", err ? "FAILED!\n" : "Ok"); - } - - return 0; -} - -static int perf_test__list(int argc, const char **argv) -{ - int i = 0; - - while (tests[i].func) { - int curr = i++; - - if (argc > 1 && !strstr(tests[curr].desc, argv[1])) - continue; - - pr_info("%2d: %s\n", i, tests[curr].desc); - } - - return 0; -} - -int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) -{ - const char * const test_usage[] = { - "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", - NULL, - }; - const struct option test_options[] = { - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show symbol address, etc)"), - OPT_END() - }; - - argc = parse_options(argc, argv, test_options, test_usage, 0); - if (argc >= 1 && !strcmp(argv[0], "list")) - return perf_test__list(argc, argv); - - symbol_conf.priv_size = sizeof(int); - symbol_conf.sort_by_name = true; - symbol_conf.try_vmlinux_path = true; - - if (symbol__init() < 0) - return -1; - - return __cmd_test(argc, argv); -} diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index f251b613b2f..ab4cf232b85 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -965,7 +965,7 @@ static void write_svg_file(const char *filename) svg_close(); } -static int __cmd_timechart(const char *input_name, const char *output_name) +static int __cmd_timechart(const char *output_name) { struct perf_tool perf_timechart = { .comm = process_comm_event, @@ -1061,7 +1061,6 @@ parse_process(const struct option *opt __maybe_unused, const char *arg, int cmd_timechart(int argc, const char **argv, const char *prefix __maybe_unused) { - const char *input_name; const char *output_name = "output.svg"; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -1092,5 +1091,5 @@ int cmd_timechart(int argc, const char **argv, setup_pager(); - return __cmd_timechart(input_name, output_name); + return __cmd_timechart(output_name); } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ff6db808680..72f6eb7b417 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -26,6 +26,7 @@ #include "util/color.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/machine.h" #include "util/session.h" #include "util/symbol.h" #include "util/thread.h" @@ -67,27 +68,7 @@ #include <linux/unistd.h> #include <linux/types.h> -void get_term_dimensions(struct winsize *ws) -{ - char *s = getenv("LINES"); - - if (s != NULL) { - ws->ws_row = atoi(s); - s = getenv("COLUMNS"); - if (s != NULL) { - ws->ws_col = atoi(s); - if (ws->ws_row && ws->ws_col) - return; - } - } -#ifdef TIOCGWINSZ - if (ioctl(1, TIOCGWINSZ, ws) == 0 && - ws->ws_row && ws->ws_col) - return; -#endif - ws->ws_row = 25; - ws->ws_col = 80; -} +static volatile int done; static void perf_top__update_print_entries(struct perf_top *top) { @@ -452,8 +433,10 @@ static int perf_top__key_mapped(struct perf_top *top, int c) return 0; } -static void perf_top__handle_keypress(struct perf_top *top, int c) +static bool perf_top__handle_keypress(struct perf_top *top, int c) { + bool ret = true; + if (!perf_top__key_mapped(top, c)) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; struct termios tc, save; @@ -474,7 +457,7 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) tcsetattr(0, TCSAFLUSH, &save); if (!perf_top__key_mapped(top, c)) - return; + return ret; } switch (c) { @@ -536,7 +519,8 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) printf("exiting.\n"); if (top->dump_symtab) perf_session__fprintf_dsos(top->session, stderr); - exit(0); + ret = false; + break; case 's': perf_top__prompt_symbol(top, "Enter details symbol"); break; @@ -559,6 +543,8 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) default: break; } + + return ret; } static void perf_top__sort_new_samples(void *arg) @@ -581,6 +567,11 @@ static void *display_thread_tui(void *arg) struct perf_evsel *pos; struct perf_top *top = arg; const char *help = "For a higher level overview, try: perf top --sort comm,dso"; + struct hist_browser_timer hbt = { + .timer = perf_top__sort_new_samples, + .arg = top, + .refresh = top->delay_secs, + }; perf_top__sort_new_samples(top); @@ -590,14 +581,12 @@ static void *display_thread_tui(void *arg) * via --uid. */ list_for_each_entry(pos, &top->evlist->entries, node) - pos->hists.uid_filter_str = top->target.uid_str; + pos->hists.uid_filter_str = top->record_opts.target.uid_str; - perf_evlist__tui_browse_hists(top->evlist, help, - perf_top__sort_new_samples, - top, top->delay_secs); + perf_evlist__tui_browse_hists(top->evlist, help, &hbt, + &top->session->header.env); - exit_browser(0); - exit(0); + done = 1; return NULL; } @@ -621,7 +610,7 @@ repeat: /* trash return*/ getc(stdin); - while (1) { + while (!done) { perf_top__print_sym_table(top); /* * Either timeout expired or we got an EINTR due to SIGWINCH, @@ -635,15 +624,14 @@ repeat: continue; /* Fall trhu */ default: - goto process_hotkey; + c = getc(stdin); + tcsetattr(0, TCSAFLUSH, &save); + + if (perf_top__handle_keypress(top, c)) + goto repeat; + done = 1; } } -process_hotkey: - c = getc(stdin); - tcsetattr(0, TCSAFLUSH, &save); - - perf_top__handle_keypress(top, c); - goto repeat; return NULL; } @@ -711,7 +699,7 @@ static void perf_event__process_sample(struct perf_tool *tool, static struct intlist *seen; if (!seen) - seen = intlist__new(); + seen = intlist__new(NULL); if (!intlist__has_entry(seen, event->ip.pid)) { pr_err("Can't find guest [%d]'s kernel information\n", @@ -722,8 +710,8 @@ static void perf_event__process_sample(struct perf_tool *tool, } if (!machine) { - pr_err("%u unprocessable samples recorded.", - top->session->hists.stats.nr_unprocessable_samples++); + pr_err("%u unprocessable samples recorded.\r", + top->session->stats.nr_unprocessable_samples++); return; } @@ -842,13 +830,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) ++top->us_samples; if (top->hide_user_symbols) continue; - machine = perf_session__find_host_machine(session); + machine = &session->machines.host; break; case PERF_RECORD_MISC_KERNEL: ++top->kernel_samples; if (top->hide_kernel_symbols) continue; - machine = perf_session__find_host_machine(session); + machine = &session->machines.host; break; case PERF_RECORD_MISC_GUEST_KERNEL: ++top->guest_kernel_samples; @@ -871,9 +859,9 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) &sample, machine); } else if (event->header.type < PERF_RECORD_MAX) { hists__inc_nr_events(&evsel->hists, event->header.type); - perf_event__process(&top->tool, event, &sample, machine); + machine__process_event(machine, event); } else - ++session->hists.stats.nr_unknown_events; + ++session->stats.nr_unknown_events; } } @@ -885,119 +873,42 @@ static void perf_top__mmap_read(struct perf_top *top) perf_top__mmap_read_idx(top, i); } -static void perf_top__start_counters(struct perf_top *top) +static int perf_top__start_counters(struct perf_top *top) { + char msg[512]; struct perf_evsel *counter; struct perf_evlist *evlist = top->evlist; + struct perf_record_opts *opts = &top->record_opts; - if (top->group) - perf_evlist__set_leader(evlist); + perf_evlist__config(evlist, opts); list_for_each_entry(counter, &evlist->entries, node) { - struct perf_event_attr *attr = &counter->attr; - - attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; - - if (top->freq) { - attr->sample_type |= PERF_SAMPLE_PERIOD; - attr->freq = 1; - attr->sample_freq = top->freq; - } - - if (evlist->nr_entries > 1) { - attr->sample_type |= PERF_SAMPLE_ID; - attr->read_format |= PERF_FORMAT_ID; - } - - if (perf_target__has_cpu(&top->target)) - attr->sample_type |= PERF_SAMPLE_CPU; - - if (symbol_conf.use_callchain) - attr->sample_type |= PERF_SAMPLE_CALLCHAIN; - - attr->mmap = 1; - attr->comm = 1; - attr->inherit = top->inherit; -fallback_missing_features: - if (top->exclude_guest_missing) - attr->exclude_guest = attr->exclude_host = 0; -retry_sample_id: - attr->sample_id_all = top->sample_id_all_missing ? 0 : 1; try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads) < 0) { - int err = errno; - - if (err == EPERM || err == EACCES) { - ui__error_paranoid(); - goto out_err; - } else if (err == EINVAL) { - if (!top->exclude_guest_missing && - (attr->exclude_guest || attr->exclude_host)) { - pr_debug("Old kernel, cannot exclude " - "guest or host samples.\n"); - top->exclude_guest_missing = true; - goto fallback_missing_features; - } else if (!top->sample_id_all_missing) { - /* - * Old kernel, no attr->sample_id_type_all field - */ - top->sample_id_all_missing = true; - goto retry_sample_id; - } - } - /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support: - */ - if ((err == ENOENT || err == ENXIO) && - (attr->type == PERF_TYPE_HARDWARE) && - (attr->config == PERF_COUNT_HW_CPU_CYCLES)) { - + if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { if (verbose) - ui__warning("Cycles event not supported,\n" - "trying to fall back to cpu-clock-ticks\n"); - - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - if (counter->name) { - free(counter->name); - counter->name = NULL; - } + ui__warning("%s\n", msg); goto try_again; } - if (err == ENOENT) { - ui__error("The %s event is not supported.\n", - perf_evsel__name(counter)); - goto out_err; - } else if (err == EMFILE) { - ui__error("Too many events are opened.\n" - "Try again after reducing the number of events\n"); - goto out_err; - } - - ui__error("The sys_perf_event_open() syscall " - "returned with %d (%s). /bin/dmesg " - "may provide additional information.\n" - "No CONFIG_PERF_EVENTS=y kernel support " - "configured?\n", err, strerror(err)); + perf_evsel__open_strerror(counter, &opts->target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); goto out_err; } } - if (perf_evlist__mmap(evlist, top->mmap_pages, false) < 0) { + if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) { ui__error("Failed to mmap with %d (%s)\n", errno, strerror(errno)); goto out_err; } - return; + return 0; out_err: - exit_browser(0); - exit(0); + return -1; } static int perf_top__setup_sample_type(struct perf_top *top) @@ -1007,7 +918,7 @@ static int perf_top__setup_sample_type(struct perf_top *top) ui__error("Selected -g but \"sym\" not present in --sort/-s."); return -EINVAL; } - } else if (!top->dont_use_callchains && callchain_param.mode != CHAIN_NONE) { + } else if (callchain_param.mode != CHAIN_NONE) { if (callchain_register_param(&callchain_param) < 0) { ui__error("Can't register callchain params.\n"); return -EINVAL; @@ -1019,6 +930,7 @@ static int perf_top__setup_sample_type(struct perf_top *top) static int __cmd_top(struct perf_top *top) { + struct perf_record_opts *opts = &top->record_opts; pthread_t thread; int ret; /* @@ -1033,26 +945,42 @@ static int __cmd_top(struct perf_top *top) if (ret) goto out_delete; - if (perf_target__has_task(&top->target)) + if (perf_target__has_task(&opts->target)) perf_event__synthesize_thread_map(&top->tool, top->evlist->threads, perf_event__process, - &top->session->host_machine); + &top->session->machines.host); else perf_event__synthesize_threads(&top->tool, perf_event__process, - &top->session->host_machine); - perf_top__start_counters(top); + &top->session->machines.host); + + ret = perf_top__start_counters(top); + if (ret) + goto out_delete; + top->session->evlist = top->evlist; perf_session__set_id_hdr_size(top->session); + /* + * When perf is starting the traced process, all the events (apart from + * group members) have enable_on_exec=1 set, so don't spoil it by + * prematurely enabling them. + * + * XXX 'top' still doesn't start workloads like record, trace, but should, + * so leave the check here. + */ + if (!perf_target__none(&opts->target)) + perf_evlist__enable(top->evlist); + /* Wait for a minimal set of events before starting the snapshot */ poll(top->evlist->pollfd, top->evlist->nr_fds, 100); perf_top__mmap_read(top); + ret = -1; if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui : display_thread), top)) { ui__error("Could not create display thread.\n"); - exit(-1); + goto out_delete; } if (top->realtime_prio) { @@ -1061,11 +989,11 @@ static int __cmd_top(struct perf_top *top) param.sched_priority = top->realtime_prio; if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { ui__error("Could not set realtime priority.\n"); - exit(-1); + goto out_delete; } } - while (1) { + while (!done) { u64 hits = top->samples; perf_top__mmap_read(top); @@ -1074,126 +1002,67 @@ static int __cmd_top(struct perf_top *top) ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100); } + ret = 0; out_delete: perf_session__delete(top->session); top->session = NULL; - return 0; + return ret; } static int parse_callchain_opt(const struct option *opt, const char *arg, int unset) { - struct perf_top *top = (struct perf_top *)opt->value; - char *tok, *tok2; - char *endptr; - /* * --no-call-graph */ - if (unset) { - top->dont_use_callchains = true; + if (unset) return 0; - } symbol_conf.use_callchain = true; - if (!arg) - return 0; - - tok = strtok((char *)arg, ","); - if (!tok) - return -1; - - /* get the output mode */ - if (!strncmp(tok, "graph", strlen(arg))) - callchain_param.mode = CHAIN_GRAPH_ABS; - - else if (!strncmp(tok, "flat", strlen(arg))) - callchain_param.mode = CHAIN_FLAT; - - else if (!strncmp(tok, "fractal", strlen(arg))) - callchain_param.mode = CHAIN_GRAPH_REL; - - else if (!strncmp(tok, "none", strlen(arg))) { - callchain_param.mode = CHAIN_NONE; - symbol_conf.use_callchain = false; - - return 0; - } else - return -1; - - /* get the min percentage */ - tok = strtok(NULL, ","); - if (!tok) - goto setup; - - callchain_param.min_percent = strtod(tok, &endptr); - if (tok == endptr) - return -1; - - /* get the print limit */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - - if (tok2[0] != 'c') { - callchain_param.print_limit = strtod(tok2, &endptr); - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - } - - /* get the call chain order */ - if (!strcmp(tok2, "caller")) - callchain_param.order = ORDER_CALLER; - else if (!strcmp(tok2, "callee")) - callchain_param.order = ORDER_CALLEE; - else - return -1; -setup: - if (callchain_register_param(&callchain_param) < 0) { - fprintf(stderr, "Can't register callchain params\n"); - return -1; - } - return 0; + return record_parse_callchain_opt(opt, arg, unset); } int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) { - struct perf_evsel *pos; int status; char errbuf[BUFSIZ]; struct perf_top top = { .count_filter = 5, .delay_secs = 2, - .freq = 4000, /* 4 KHz */ - .mmap_pages = 128, - .sym_pcnt_filter = 5, - .target = { - .uses_mmap = true, + .record_opts = { + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, /* 4 KHz */ + .target = { + .uses_mmap = true, + }, }, + .sym_pcnt_filter = 5, }; - char callchain_default_opt[] = "fractal,0.5,callee"; + struct perf_record_opts *opts = &top.record_opts; + struct perf_target *target = &opts->target; const struct option options[] = { OPT_CALLBACK('e', "event", &top.evlist, "event", "event selector. use 'perf list' to list available events", parse_events_option), - OPT_INTEGER('c', "count", &top.default_interval, - "event period to sample"), - OPT_STRING('p', "pid", &top.target.pid, "pid", + OPT_U64('c', "count", &opts->user_interval, "event period to sample"), + OPT_STRING('p', "pid", &target->pid, "pid", "profile events on existing process id"), - OPT_STRING('t', "tid", &top.target.tid, "tid", + OPT_STRING('t', "tid", &target->tid, "tid", "profile events on existing thread id"), - OPT_BOOLEAN('a', "all-cpus", &top.target.system_wide, + OPT_BOOLEAN('a', "all-cpus", &target->system_wide, "system-wide collection from all CPUs"), - OPT_STRING('C', "cpu", &top.target.cpu_list, "cpu", + OPT_STRING('C', "cpu", &target->cpu_list, "cpu", "list of cpus to monitor"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols, "hide kernel symbols"), - OPT_UINTEGER('m', "mmap-pages", &top.mmap_pages, "number of mmap data pages"), + OPT_UINTEGER('m', "mmap-pages", &opts->mmap_pages, + "number of mmap data pages"), OPT_INTEGER('r', "realtime", &top.realtime_prio, "collect data with this RT SCHED_FIFO priority"), OPT_INTEGER('d', "delay", &top.delay_secs, @@ -1202,16 +1071,14 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "dump the symbol table used for profiling"), OPT_INTEGER('f', "count-filter", &top.count_filter, "only display functions with more events than this"), - OPT_BOOLEAN('g', "group", &top.group, + OPT_BOOLEAN('g', "group", &opts->group, "put the counters into a counter group"), - OPT_BOOLEAN('i', "inherit", &top.inherit, - "child tasks inherit counters"), + OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit, + "child tasks do not inherit counters"), OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name", "symbol to annotate"), - OPT_BOOLEAN('z', "zero", &top.zero, - "zero history across updates"), - OPT_INTEGER('F', "freq", &top.freq, - "profile at this frequency"), + OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"), + OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"), OPT_INTEGER('E', "entries", &top.print_entries, "display this many functions"), OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols, @@ -1224,10 +1091,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "sort by key(s): pid, comm, dso, symbol, parent"), 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, "output_type,min_percent, call_order", - "Display callchains using output_type (graph, flat, fractal, or none), min percent threshold and callchain order. " - "Default: fractal,0.5,callee", &parse_callchain_opt, - callchain_default_opt), + OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, + "mode[,dump_size]", record_callchain_help, + &parse_callchain_opt, "fp"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", @@ -1242,7 +1108,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING('u', "uid", &top.target.uid_str, "user", "user to profile"), + OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_END() }; const char * const top_usage[] = { @@ -1263,7 +1129,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (sort_order == default_sort_order) sort_order = "dso,symbol"; - setup_sorting(top_usage, options); + if (setup_sorting() < 0) + usage_with_options(top_usage, options); if (top.use_stdio) use_browser = 0; @@ -1272,33 +1139,33 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) setup_browser(false); - status = perf_target__validate(&top.target); + status = perf_target__validate(target); if (status) { - perf_target__strerror(&top.target, status, errbuf, BUFSIZ); + perf_target__strerror(target, status, errbuf, BUFSIZ); ui__warning("%s", errbuf); } - status = perf_target__parse_uid(&top.target); + status = perf_target__parse_uid(target); if (status) { int saved_errno = errno; - perf_target__strerror(&top.target, status, errbuf, BUFSIZ); + perf_target__strerror(target, status, errbuf, BUFSIZ); ui__error("%s", errbuf); status = -saved_errno; goto out_delete_evlist; } - if (perf_target__none(&top.target)) - top.target.system_wide = true; + if (perf_target__none(target)) + target->system_wide = true; - if (perf_evlist__create_maps(top.evlist, &top.target) < 0) + if (perf_evlist__create_maps(top.evlist, target) < 0) usage_with_options(top_usage, options); if (!top.evlist->nr_entries && perf_evlist__add_default(top.evlist) < 0) { ui__error("Not enough memory for event selector list\n"); - return -ENOMEM; + goto out_delete_maps; } symbol_conf.nr_events = top.evlist->nr_entries; @@ -1306,24 +1173,22 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.delay_secs < 1) top.delay_secs = 1; + if (opts->user_interval != ULLONG_MAX) + opts->default_interval = opts->user_interval; + if (opts->user_freq != UINT_MAX) + opts->freq = opts->user_freq; + /* * User specified count overrides default frequency. */ - if (top.default_interval) - top.freq = 0; - else if (top.freq) { - top.default_interval = top.freq; + if (opts->default_interval) + opts->freq = 0; + else if (opts->freq) { + opts->default_interval = opts->freq; } else { ui__error("frequency and count are zero, aborting\n"); - exit(EXIT_FAILURE); - } - - list_for_each_entry(pos, &top.evlist->entries, node) { - /* - * Fill in the ones not specifically initialized via -c: - */ - if (!pos->attr.sample_period) - pos->attr.sample_period = top.default_interval; + status = -EINVAL; + goto out_delete_maps; } top.sym_evsel = perf_evlist__first(top.evlist); @@ -1356,6 +1221,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) status = __cmd_top(&top); +out_delete_maps: + perf_evlist__delete_maps(top.evlist); out_delete_evlist: perf_evlist__delete(top.evlist); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 7aaee39f677..d222d7fc7e9 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1,5 +1,8 @@ #include "builtin.h" +#include "util/color.h" #include "util/evlist.h" +#include "util/machine.h" +#include "util/thread.h" #include "util/parse-options.h" #include "util/thread_map.h" #include "event-parse.h" @@ -13,15 +16,18 @@ static struct syscall_fmt { bool errmsg; bool timeout; } syscall_fmts[] = { + { .name = "access", .errmsg = true, }, { .name = "arch_prctl", .errmsg = true, .alias = "prctl", }, { .name = "fstat", .errmsg = true, .alias = "newfstat", }, { .name = "fstatat", .errmsg = true, .alias = "newfstatat", }, { .name = "futex", .errmsg = true, }, + { .name = "open", .errmsg = true, }, { .name = "poll", .errmsg = true, .timeout = true, }, { .name = "ppoll", .errmsg = true, .timeout = true, }, { .name = "read", .errmsg = true, }, { .name = "recvfrom", .errmsg = true, }, { .name = "select", .errmsg = true, .timeout = true, }, + { .name = "socket", .errmsg = true, }, { .name = "stat", .errmsg = true, .alias = "newstat", }, }; @@ -43,6 +49,57 @@ struct syscall { struct syscall_fmt *fmt; }; +static size_t fprintf_duration(unsigned long t, FILE *fp) +{ + double duration = (double)t / NSEC_PER_MSEC; + size_t printed = fprintf(fp, "("); + + if (duration >= 1.0) + printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration); + else if (duration >= 0.01) + printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration); + else + printed += color_fprintf(fp, PERF_COLOR_NORMAL, "%6.3f ms", duration); + return printed + fprintf(stdout, "): "); +} + +struct thread_trace { + u64 entry_time; + u64 exit_time; + bool entry_pending; + unsigned long nr_events; + char *entry_str; + double runtime_ms; +}; + +static struct thread_trace *thread_trace__new(void) +{ + return zalloc(sizeof(struct thread_trace)); +} + +static struct thread_trace *thread__trace(struct thread *thread) +{ + struct thread_trace *ttrace; + + if (thread == NULL) + goto fail; + + if (thread->priv == NULL) + thread->priv = thread_trace__new(); + + if (thread->priv == NULL) + goto fail; + + ttrace = thread->priv; + ++ttrace->nr_events; + + return ttrace; +fail: + color_fprintf(stdout, PERF_COLOR_RED, + "WARNING: not enough memory, dropping samples!\n"); + return NULL; +} + struct trace { int audit_machine; struct { @@ -50,8 +107,96 @@ struct trace { struct syscall *table; } syscalls; struct perf_record_opts opts; + struct machine host; + u64 base_time; + unsigned long nr_events; + bool sched; + bool multiple_threads; + double duration_filter; + double runtime_ms; }; +static bool trace__filter_duration(struct trace *trace, double t) +{ + return t < (trace->duration_filter * NSEC_PER_MSEC); +} + +static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) +{ + double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC; + + return fprintf(fp, "%10.3f ", ts); +} + +static bool done = false; + +static void sig_handler(int sig __maybe_unused) +{ + done = true; +} + +static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread, + u64 duration, u64 tstamp, FILE *fp) +{ + size_t printed = trace__fprintf_tstamp(trace, tstamp, fp); + printed += fprintf_duration(duration, fp); + + if (trace->multiple_threads) + printed += fprintf(fp, "%d ", thread->pid); + + return printed; +} + +static int trace__process_event(struct machine *machine, union perf_event *event) +{ + int ret = 0; + + switch (event->header.type) { + case PERF_RECORD_LOST: + color_fprintf(stdout, PERF_COLOR_RED, + "LOST %" PRIu64 " events!\n", event->lost.lost); + ret = machine__process_lost_event(machine, event); + default: + ret = machine__process_event(machine, event); + break; + } + + return ret; +} + +static int trace__tool_process(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return trace__process_event(machine, event); +} + +static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) +{ + int err = symbol__init(); + + if (err) + return err; + + machine__init(&trace->host, "", HOST_KERNEL_ID); + machine__create_kernel_maps(&trace->host); + + if (perf_target__has_task(&trace->opts.target)) { + err = perf_event__synthesize_thread_map(NULL, evlist->threads, + trace__tool_process, + &trace->host); + } else { + err = perf_event__synthesize_threads(NULL, trace__tool_process, + &trace->host); + } + + if (err) + symbol__exit(); + + return err; +} + static int trace__read_syscall_info(struct trace *trace, int id) { char tp_name[128]; @@ -93,7 +238,8 @@ static int trace__read_syscall_info(struct trace *trace, int id) return sc->tp_format != NULL ? 0 : -1; } -static size_t syscall__fprintf_args(struct syscall *sc, unsigned long *args, FILE *fp) +static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, + unsigned long *args) { int i = 0; size_t printed = 0; @@ -102,12 +248,15 @@ static size_t syscall__fprintf_args(struct syscall *sc, unsigned long *args, FIL struct format_field *field; for (field = sc->tp_format->format.fields->next; field; field = field->next) { - printed += fprintf(fp, "%s%s: %ld", printed ? ", " : "", - field->name, args[i++]); + printed += scnprintf(bf + printed, size - printed, + "%s%s: %ld", printed ? ", " : "", + field->name, args[i++]); } } else { while (i < 6) { - printed += fprintf(fp, "%sarg%d: %ld", printed ? ", " : "", i, args[i]); + printed += scnprintf(bf + printed, size - printed, + "%sarg%d: %ld", + printed ? ", " : "", i, args[i]); ++i; } } @@ -139,17 +288,24 @@ static struct syscall *trace__syscall_info(struct trace *trace, return &trace->syscalls.table[id]; out_cant_read: - printf("Problems reading syscall %d information\n", id); + printf("Problems reading syscall %d", id); + if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL) + printf("(%s)", trace->syscalls.table[id].name); + puts(" information"); return NULL; } static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, struct perf_sample *sample) { + char *msg; void *args; + size_t printed = 0; + struct thread *thread = machine__findnew_thread(&trace->host, sample->tid); struct syscall *sc = trace__syscall_info(trace, evsel, sample); + struct thread_trace *ttrace = thread__trace(thread); - if (sc == NULL) + if (ttrace == NULL || sc == NULL) return -1; args = perf_evsel__rawptr(evsel, sample, "args"); @@ -158,8 +314,27 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, return -1; } - printf("%s(", sc->name); - syscall__fprintf_args(sc, args, stdout); + ttrace = thread->priv; + + if (ttrace->entry_str == NULL) { + ttrace->entry_str = malloc(1024); + if (!ttrace->entry_str) + return -1; + } + + ttrace->entry_time = sample->time; + msg = ttrace->entry_str; + printed += scnprintf(msg + printed, 1024 - printed, "%s(", sc->name); + + printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed, args); + + if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) { + if (!trace->duration_filter) { + trace__fprintf_entry_head(trace, thread, 1, sample->time, stdout); + printf("%-70s\n", ttrace->entry_str); + } + } else + ttrace->entry_pending = true; return 0; } @@ -168,13 +343,37 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, struct perf_sample *sample) { int ret; + u64 duration = 0; + struct thread *thread = machine__findnew_thread(&trace->host, sample->tid); + struct thread_trace *ttrace = thread__trace(thread); struct syscall *sc = trace__syscall_info(trace, evsel, sample); - if (sc == NULL) + if (ttrace == NULL || sc == NULL) return -1; ret = perf_evsel__intval(evsel, sample, "ret"); + ttrace = thread->priv; + + ttrace->exit_time = sample->time; + + if (ttrace->entry_time) { + duration = sample->time - ttrace->entry_time; + if (trace__filter_duration(trace, duration)) + goto out; + } else if (trace->duration_filter) + goto out; + + trace__fprintf_entry_head(trace, thread, duration, sample->time, stdout); + + if (ttrace->entry_pending) { + printf("%-70s", ttrace->entry_str); + } else { + printf(" ... ["); + color_fprintf(stdout, PERF_COLOR_YELLOW, "continued"); + printf("]: %s()", sc->name); + } + if (ret < 0 && sc->fmt && sc->fmt->errmsg) { char bf[256]; const char *emsg = strerror_r(-ret, bf, sizeof(bf)), @@ -187,14 +386,44 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, printf(") = %d", ret); putchar('\n'); +out: + ttrace->entry_pending = false; + + return 0; +} + +static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample) +{ + u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); + double runtime_ms = (double)runtime / NSEC_PER_MSEC; + struct thread *thread = machine__findnew_thread(&trace->host, sample->tid); + struct thread_trace *ttrace = thread__trace(thread); + + if (ttrace == NULL) + goto out_dump; + + ttrace->runtime_ms += runtime_ms; + trace->runtime_ms += runtime_ms; + return 0; + +out_dump: + printf("%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n", + evsel->name, + perf_evsel__strval(evsel, sample, "comm"), + (pid_t)perf_evsel__intval(evsel, sample, "pid"), + runtime, + perf_evsel__intval(evsel, sample, "vruntime")); return 0; } -static int trace__run(struct trace *trace) +static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); struct perf_evsel *evsel; - int err = -1, i, nr_events = 0, before; + int err = -1, i; + unsigned long before; + const bool forks = argc > 0; if (evlist == NULL) { printf("Not enough memory to run!\n"); @@ -207,13 +436,37 @@ static int trace__run(struct trace *trace) goto out_delete_evlist; } + if (trace->sched && + perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", + trace__sched_stat_runtime)) { + printf("Couldn't read the sched_stat_runtime tracepoint information!\n"); + goto out_delete_evlist; + } + err = perf_evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { printf("Problems parsing the target to trace, check your options!\n"); goto out_delete_evlist; } - perf_evlist__config_attrs(evlist, &trace->opts); + err = trace__symbols_init(trace, evlist); + if (err < 0) { + printf("Problems initializing symbol libraries!\n"); + goto out_delete_evlist; + } + + perf_evlist__config(evlist, &trace->opts); + + signal(SIGCHLD, sig_handler); + signal(SIGINT, sig_handler); + + if (forks) { + err = perf_evlist__prepare_workload(evlist, &trace->opts, argv); + if (err < 0) { + printf("Couldn't run the workload!\n"); + goto out_delete_evlist; + } + } err = perf_evlist__open(evlist); if (err < 0) { @@ -228,8 +481,13 @@ static int trace__run(struct trace *trace) } perf_evlist__enable(evlist); + + if (forks) + perf_evlist__start_workload(evlist); + + trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1; again: - before = nr_events; + before = trace->nr_events; for (i = 0; i < evlist->nr_mmaps; i++) { union perf_event *event; @@ -239,19 +497,7 @@ again: tracepoint_handler handler; struct perf_sample sample; - ++nr_events; - - switch (type) { - case PERF_RECORD_SAMPLE: - break; - case PERF_RECORD_LOST: - printf("LOST %" PRIu64 " events!\n", event->lost.lost); - continue; - default: - printf("Unexpected %s event, skipping...\n", - perf_event__name(type)); - continue; - } + ++trace->nr_events; err = perf_evlist__parse_sample(evlist, event, &sample); if (err) { @@ -259,14 +505,26 @@ again: continue; } + if (trace->base_time == 0) + trace->base_time = sample.time; + + if (type != PERF_RECORD_SAMPLE) { + trace__process_event(&trace->host, event); + continue; + } + evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { printf("Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); continue; } - if (evlist->threads->map[0] == -1 || evlist->threads->nr > 1) - printf("%d ", sample.tid); + 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; + } if (sample.raw_data == NULL) { printf("%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", @@ -280,8 +538,15 @@ again: } } - if (nr_events == before) + if (trace->nr_events == before) { + if (done) + goto out_delete_evlist; + poll(evlist->pollfd, evlist->nr_fds, -1); + } + + if (done) + perf_evlist__disable(evlist); goto again; @@ -291,10 +556,65 @@ out: return err; } +static size_t trace__fprintf_threads_header(FILE *fp) +{ + size_t printed; + + printed = fprintf(fp, "\n _____________________________________________________________________\n"); + printed += fprintf(fp," __) Summary of events (__\n\n"); + printed += fprintf(fp," [ task - pid ] [ events ] [ ratio ] [ runtime ]\n"); + printed += fprintf(fp," _____________________________________________________________________\n\n"); + + return printed; +} + +static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) +{ + size_t printed = trace__fprintf_threads_header(fp); + struct rb_node *nd; + + for (nd = rb_first(&trace->host.threads); nd; nd = rb_next(nd)) { + struct thread *thread = rb_entry(nd, struct thread, rb_node); + struct thread_trace *ttrace = thread->priv; + const char *color; + double ratio; + + if (ttrace == NULL) + continue; + + ratio = (double)ttrace->nr_events / trace->nr_events * 100.0; + + color = PERF_COLOR_NORMAL; + if (ratio > 50.0) + color = PERF_COLOR_RED; + else if (ratio > 25.0) + color = PERF_COLOR_GREEN; + else if (ratio > 5.0) + color = PERF_COLOR_YELLOW; + + printed += color_fprintf(fp, color, "%20s", thread->comm); + printed += fprintf(fp, " - %-5d :%11lu [", thread->pid, ttrace->nr_events); + printed += color_fprintf(fp, color, "%5.1f%%", ratio); + printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms); + } + + return printed; +} + +static int trace__set_duration(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct trace *trace = opt->value; + + trace->duration_filter = atof(str); + return 0; +} + int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const trace_usage[] = { - "perf trace [<options>]", + "perf trace [<options>] [<command>]", + "perf trace [<options>] -- <command> [<options>]", NULL }; struct trace trace = { @@ -328,21 +648,38 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) "number of mmap data pages"), OPT_STRING(0, "uid", &trace.opts.target.uid_str, "user", "user to profile"), + OPT_CALLBACK(0, "duration", &trace, "float", + "show only events with duration > N.M ms", + trace__set_duration), + OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"), OPT_END() }; int err; + char bf[BUFSIZ]; argc = parse_options(argc, argv, trace_options, trace_usage, 0); - if (argc) - usage_with_options(trace_usage, trace_options); + + err = perf_target__validate(&trace.opts.target); + if (err) { + perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf)); + printf("%s", bf); + return err; + } err = perf_target__parse_uid(&trace.opts.target); if (err) { - char bf[BUFSIZ]; perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf)); printf("%s", bf); return err; } - return trace__run(&trace); + if (!argc && perf_target__none(&trace.opts.target)) + trace.opts.target.system_wide = true; + + err = trace__run(&trace, argc, argv); + + if (trace.sched && !err) + trace__fprintf_thread_summary(&trace, stdout); + + return err; } diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index 4add41bb0c7..b4eabb44e38 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -43,6 +43,15 @@ int main(void) } endef +define SOURCE_BIONIC +#include <android/api-level.h> + +int main(void) +{ + return __ANDROID_API__; +} +endef + define SOURCE_ELF_MMAP #include <libelf.h> int main(void) @@ -112,7 +121,10 @@ define SOURCE_PYTHON_VERSION #if PY_VERSION_HEX >= 0x03000000 #error #endif -int main(void){} +int main(void) +{ + return 0; +} endef define SOURCE_PYTHON_EMBED #include <Python.h> @@ -203,4 +215,24 @@ int main(void) return audit_open(); } endef -endif
\ No newline at end of file +endif + +define SOURCE_ON_EXIT +#include <stdio.h> + +int main(void) +{ + return on_exit(NULL, NULL); +} +endef + +define SOURCE_LIBNUMA +#include <numa.h> +#include <numaif.h> + +int main(void) +{ + numa_available(); + return 0; +} +endef
\ No newline at end of file diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak index 8046182a19e..8ef3bd30a54 100644 --- a/tools/perf/config/utilities.mak +++ b/tools/perf/config/utilities.mak @@ -13,7 +13,7 @@ newline := $(newline) # what should replace a newline when escaping # newlines; the default is a bizarre string. # -nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n) +nl-escape = $(if $(1),$(1),m822df3020w6a44id34bt574ctac44eb9f4n) # escape-nl # @@ -173,16 +173,22 @@ _ge-abspath = $(if $(is-executable),$(1)) # Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default) # define get-executable-or-default -$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2))) +$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2),$(1))) endef -_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2))) +_ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2))) _gea_warn = $(warning The path '$(1)' is not executable.) _gea_err = $(if $(1),$(error Please set '$(1)' appropriately)) # try-cc -# Usage: option = $(call try-cc, source-to-build, cc-options) +# Usage: option = $(call try-cc, source-to-build, cc-options, msg) +ifndef V +TRY_CC_OUTPUT= > /dev/null 2>&1 +endif +TRY_CC_MSG=echo " CHK $(3)" 1>&2; + try-cc = $(shell sh -c \ 'TMP="$(OUTPUT)$(TMPOUT).$$$$"; \ + $(TRY_CC_MSG) \ echo "$(1)" | \ - $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \ + $(CC) -x c - $(2) -o "$$TMP" $(TRY_CC_OUTPUT) && echo y; \ rm -f "$$TMP"') diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 6d50eb0b425..095b88207cd 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -24,6 +24,7 @@ const char perf_more_info_string[] = int use_browser = -1; static int use_pager = -1; +const char *input_name; struct cmd_struct { const char *cmd; @@ -84,21 +85,26 @@ int check_pager_config(const char *cmd) return c.val; } -static int tui_command_config(const char *var, const char *value, void *data) +static int browser_command_config(const char *var, const char *value, void *data) { struct pager_config *c = data; if (!prefixcmp(var, "tui.") && !strcmp(var + 4, c->cmd)) c->val = perf_config_bool(var, value); + if (!prefixcmp(var, "gtk.") && !strcmp(var + 4, c->cmd)) + c->val = perf_config_bool(var, value) ? 2 : 0; return 0; } -/* returns 0 for "no tui", 1 for "use tui", and -1 for "not specified" */ -static int check_tui_config(const char *cmd) +/* + * returns 0 for "no tui", 1 for "use tui", 2 for "use gtk", + * and -1 for "not specified" + */ +static int check_browser_config(const char *cmd) { struct pager_config c; c.cmd = cmd; c.val = -1; - perf_config(tui_command_config, &c); + perf_config(browser_command_config, &c); return c.val; } @@ -301,7 +307,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) prefix = NULL; /* setup_perf_directory(); */ if (use_browser == -1) - use_browser = check_tui_config(p->cmd); + use_browser = check_browser_config(p->cmd); if (use_pager == -1 && p->option & RUN_SETUP) use_pager = check_pager_config(p->cmd); @@ -322,14 +328,23 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode)) return 0; + status = 1; /* Check for ENOSPC and EIO errors.. */ - if (fflush(stdout)) - die("write failure on standard output: %s", strerror(errno)); - if (ferror(stdout)) - die("unknown write failure on standard output"); - if (fclose(stdout)) - die("close failed on standard output: %s", strerror(errno)); - return 0; + if (fflush(stdout)) { + fprintf(stderr, "write failure on standard output: %s", strerror(errno)); + goto out; + } + if (ferror(stdout)) { + fprintf(stderr, "unknown write failure on standard output"); + goto out; + } + if (fclose(stdout)) { + fprintf(stderr, "close failed on standard output: %s", strerror(errno)); + goto out; + } + status = 0; +out: + return status; } static void handle_internal_command(int argc, const char **argv) @@ -440,6 +455,8 @@ int main(int argc, const char **argv) { const char *cmd; + page_size = sysconf(_SC_PAGE_SIZE); + cmd = perf_extract_argv0_path(argv[0]); if (!cmd) cmd = "perf-help"; @@ -459,7 +476,8 @@ int main(int argc, const char **argv) cmd += 5; argv[0] = cmd; handle_internal_command(argc, argv); - die("cannot handle %s internally", cmd); + fprintf(stderr, "cannot handle %s internally", cmd); + goto out; } /* Look for flags.. */ @@ -477,10 +495,12 @@ int main(int argc, const char **argv) printf("\n usage: %s\n\n", perf_usage_string); list_common_cmds_help(); printf("\n %s\n\n", perf_more_info_string); - exit(1); + goto out; } cmd = argv[0]; + test_attr__init(); + /* * We use PATH to find perf commands, but we prepend some higher * precedence paths: the "--exec-path" option, the PERF_EXEC_PATH @@ -507,7 +527,7 @@ int main(int argc, const char **argv) fprintf(stderr, "Expansion of alias '%s' failed; " "'%s' is not a perf-command\n", cmd, argv[0]); - exit(1); + goto out; } if (!done_help) { cmd = argv[0] = help_unknown_cmd(cmd); @@ -518,6 +538,6 @@ int main(int argc, const char **argv) fprintf(stderr, "Failed to run command '%s': %s\n", cmd, strerror(errno)); - +out: return 1; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index c50985eaec4..74659ecf93e 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -1,12 +1,9 @@ #ifndef _PERF_PERF_H #define _PERF_PERF_H -struct winsize; - -void get_term_dimensions(struct winsize *ws); +#include <asm/unistd.h> #if defined(__i386__) -#include "../../arch/x86/include/asm/unistd.h" #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); #define CPUINFO_PROC "model name" @@ -16,7 +13,6 @@ void get_term_dimensions(struct winsize *ws); #endif #if defined(__x86_64__) -#include "../../arch/x86/include/asm/unistd.h" #define rmb() asm volatile("lfence" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); #define CPUINFO_PROC "model name" @@ -26,20 +22,18 @@ void get_term_dimensions(struct winsize *ws); #endif #ifdef __powerpc__ -#include "../../arch/powerpc/include/asm/unistd.h" +#include "../../arch/powerpc/include/uapi/asm/unistd.h" #define rmb() asm volatile ("sync" ::: "memory") #define cpu_relax() asm volatile ("" ::: "memory"); #define CPUINFO_PROC "cpu" #endif #ifdef __s390__ -#include "../../arch/s390/include/asm/unistd.h" #define rmb() asm volatile("bcr 15,0" ::: "memory") #define cpu_relax() asm volatile("" ::: "memory"); #endif #ifdef __sh__ -#include "../../arch/sh/include/asm/unistd.h" #if defined(__SH4A__) || defined(__SH5__) # define rmb() asm volatile("synco" ::: "memory") #else @@ -50,35 +44,30 @@ void get_term_dimensions(struct winsize *ws); #endif #ifdef __hppa__ -#include "../../arch/parisc/include/asm/unistd.h" #define rmb() asm volatile("" ::: "memory") #define cpu_relax() asm volatile("" ::: "memory"); #define CPUINFO_PROC "cpu" #endif #ifdef __sparc__ -#include "../../arch/sparc/include/uapi/asm/unistd.h" #define rmb() asm volatile("":::"memory") #define cpu_relax() asm volatile("":::"memory") #define CPUINFO_PROC "cpu" #endif #ifdef __alpha__ -#include "../../arch/alpha/include/asm/unistd.h" #define rmb() asm volatile("mb" ::: "memory") #define cpu_relax() asm volatile("" ::: "memory") #define CPUINFO_PROC "cpu model" #endif #ifdef __ia64__ -#include "../../arch/ia64/include/asm/unistd.h" #define rmb() asm volatile ("mf" ::: "memory") #define cpu_relax() asm volatile ("hint @pause" ::: "memory") #define CPUINFO_PROC "model name" #endif #ifdef __arm__ -#include "../../arch/arm/include/asm/unistd.h" /* * Use the __kuser_memory_barrier helper in the CPU helper page. See * arch/arm/kernel/entry-armv.S in the kernel source for details. @@ -89,13 +78,11 @@ void get_term_dimensions(struct winsize *ws); #endif #ifdef __aarch64__ -#include "../../arch/arm64/include/asm/unistd.h" #define rmb() asm volatile("dmb ld" ::: "memory") #define cpu_relax() asm volatile("yield" ::: "memory") #endif #ifdef __mips__ -#include "../../arch/mips/include/asm/unistd.h" #define rmb() asm volatile( \ ".set mips2\n\t" \ "sync\n\t" \ @@ -107,41 +94,27 @@ void get_term_dimensions(struct winsize *ws); #define CPUINFO_PROC "cpu model" #endif +#ifdef __arc__ +#define rmb() asm volatile("" ::: "memory") +#define cpu_relax() rmb() +#define CPUINFO_PROC "Processor" +#endif + +#ifdef __metag__ +#define rmb() asm volatile("" ::: "memory") +#define cpu_relax() asm volatile("" ::: "memory") +#define CPUINFO_PROC "CPU" +#endif + #include <time.h> #include <unistd.h> #include <sys/types.h> #include <sys/syscall.h> -#include "../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> #include "util/types.h" #include <stdbool.h> -struct perf_mmap { - void *base; - int mask; - unsigned int prev; -}; - -static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) -{ - struct perf_event_mmap_page *pc = mm->base; - int head = pc->data_head; - rmb(); - return head; -} - -static inline void perf_mmap__write_tail(struct perf_mmap *md, - unsigned long tail) -{ - struct perf_event_mmap_page *pc = md->base; - - /* - * ensure all reads are done before we write the tail out. - */ - /* mb(); */ - pc->data_tail = tail; -} - /* * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all * counters in the current task. @@ -174,13 +147,25 @@ static inline unsigned long long rdclock(void) (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) +extern bool test_attr__enabled; +void test_attr__init(void); +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags); + static inline int sys_perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu, int group_fd, unsigned long flags) { - return syscall(__NR_perf_event_open, attr, pid, cpu, - group_fd, flags); + int fd; + + fd = syscall(__NR_perf_event_open, attr, pid, cpu, + group_fd, flags); + + if (unlikely(test_attr__enabled)) + test_attr__open(attr, pid, cpu, fd, group_fd, flags); + + return fd; } #define MAX_COUNTERS 256 @@ -208,6 +193,7 @@ struct branch_stack { struct branch_entry entries[0]; }; +extern const char *input_name; extern bool perf_host, perf_guest; extern const char perf_version_string[]; @@ -233,8 +219,6 @@ struct perf_record_opts { bool raw_samples; bool sample_address; bool sample_time; - bool sample_id_all_missing; - bool exclude_guest_missing; bool period; unsigned int freq; unsigned int mmap_pages; diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record deleted file mode 100644 index 8edda9078d5..00000000000 --- a/tools/perf/scripts/perl/bin/workqueue-stats-record +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -perf record -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@ diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report deleted file mode 100644 index 6d91411d248..00000000000 --- a/tools/perf/scripts/perl/bin/workqueue-stats-report +++ /dev/null @@ -1,3 +0,0 @@ -#!/bin/bash -# description: workqueue stats (ins/exe/create/destroy) -perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/workqueue-stats.pl diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl index 4bb3ecd3347..8b20787021c 100644 --- a/tools/perf/scripts/perl/rwtop.pl +++ b/tools/perf/scripts/perl/rwtop.pl @@ -17,6 +17,7 @@ use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; use lib "./Perf-Trace-Util/lib"; use Perf::Trace::Core; use Perf::Trace::Util; +use POSIX qw/SIGALRM SA_RESTART/; my $default_interval = 3; my $nlines = 20; @@ -90,7 +91,10 @@ sub syscalls::sys_enter_write sub trace_begin { - $SIG{ALRM} = \&set_print_pending; + my $sa = POSIX::SigAction->new(\&set_print_pending); + $sa->flags(SA_RESTART); + $sa->safe(1); + POSIX::sigaction(SIGALRM, $sa) or die "Can't set SIGALRM handler: $!\n"; alarm 1; } diff --git a/tools/perf/scripts/perl/workqueue-stats.pl b/tools/perf/scripts/perl/workqueue-stats.pl deleted file mode 100644 index a8eaff5119e..00000000000 --- a/tools/perf/scripts/perl/workqueue-stats.pl +++ /dev/null @@ -1,129 +0,0 @@ -#!/usr/bin/perl -w -# (c) 2009, Tom Zanussi <tzanussi@gmail.com> -# Licensed under the terms of the GNU GPL License version 2 - -# Displays workqueue stats -# -# Usage: -# -# perf record -c 1 -f -a -R -e workqueue:workqueue_creation -e -# workqueue:workqueue_destruction -e workqueue:workqueue_execution -# -e workqueue:workqueue_insertion -# -# perf script -p -s tools/perf/scripts/perl/workqueue-stats.pl - -use 5.010000; -use strict; -use warnings; - -use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; -use lib "./Perf-Trace-Util/lib"; -use Perf::Trace::Core; -use Perf::Trace::Util; - -my @cpus; - -sub workqueue::workqueue_destruction -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid) = @_; - - $cpus[$common_cpu]{$thread_pid}{destroyed}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub workqueue::workqueue_creation -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid, $cpu) = @_; - - $cpus[$common_cpu]{$thread_pid}{created}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub workqueue::workqueue_execution -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid, $func) = @_; - - $cpus[$common_cpu]{$thread_pid}{executed}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub workqueue::workqueue_insertion -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid, $func) = @_; - - $cpus[$common_cpu]{$thread_pid}{inserted}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub trace_end -{ - print "workqueue work stats:\n\n"; - my $cpu = 0; - printf("%3s %6s %6s\t%-20s\n", "cpu", "ins", "exec", "name"); - printf("%3s %6s %6s\t%-20s\n", "---", "---", "----", "----"); - foreach my $pidhash (@cpus) { - while ((my $pid, my $wqhash) = each %$pidhash) { - my $ins = $$wqhash{'inserted'} || 0; - my $exe = $$wqhash{'executed'} || 0; - my $comm = $$wqhash{'comm'} || ""; - if ($ins || $exe) { - printf("%3u %6u %6u\t%-20s\n", $cpu, $ins, $exe, $comm); - } - } - $cpu++; - } - - $cpu = 0; - print "\nworkqueue lifecycle stats:\n\n"; - printf("%3s %6s %6s\t%-20s\n", "cpu", "created", "destroyed", "name"); - printf("%3s %6s %6s\t%-20s\n", "---", "-------", "---------", "----"); - foreach my $pidhash (@cpus) { - while ((my $pid, my $wqhash) = each %$pidhash) { - my $created = $$wqhash{'created'} || 0; - my $destroyed = $$wqhash{'destroyed'} || 0; - my $comm = $$wqhash{'comm'} || ""; - if ($created || $destroyed) { - printf("%3u %6u %6u\t%-20s\n", $cpu, $created, $destroyed, - $comm); - } - } - $cpu++; - } - - print_unhandled(); -} - -my %unhandled; - -sub print_unhandled -{ - if ((scalar keys %unhandled) == 0) { - return; - } - - print "\nunhandled events:\n\n"; - - printf("%-40s %10s\n", "event", "count"); - printf("%-40s %10s\n", "----------------------------------------", - "-----------"); - - foreach my $event_name (keys %unhandled) { - printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); - } -} - -sub trace_unhandled -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm) = @_; - - $unhandled{$event_name}++; -} diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c new file mode 100644 index 00000000000..bdcceb886f7 --- /dev/null +++ b/tools/perf/tests/attr.c @@ -0,0 +1,178 @@ + +/* + * The struct perf_event_attr test support. + * + * This test is embedded inside into perf directly and is governed + * by the PERF_TEST_ATTR environment variable and hook inside + * sys_perf_event_open function. + * + * The general idea is to store 'struct perf_event_attr' details for + * each event created within single perf command. Each event details + * are stored into separate text file. Once perf command is finished + * these files can be checked for values we expect for command. + * + * Besides 'struct perf_event_attr' values we also store 'fd' and + * 'group_fd' values to allow checking for groups created. + * + * This all is triggered by setting PERF_TEST_ATTR environment variable. + * It must contain name of existing directory with access and write + * permissions. All the event text files are stored there. + */ + +/* + * 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 <inttypes.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include "../perf.h" +#include "util.h" +#include "exec_cmd.h" +#include "tests.h" + +#define ENV "PERF_TEST_ATTR" + +extern int verbose; + +static char *dir; + +void test_attr__init(void) +{ + dir = getenv(ENV); + test_attr__enabled = (dir != NULL); +} + +#define BUFSIZE 1024 + +#define __WRITE_ASS(str, fmt, data) \ +do { \ + char buf[BUFSIZE]; \ + size_t size; \ + \ + size = snprintf(buf, BUFSIZE, #str "=%"fmt "\n", data); \ + if (1 != fwrite(buf, size, 1, file)) { \ + perror("test attr - failed to write event file"); \ + fclose(file); \ + return -1; \ + } \ + \ +} while (0) + +#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field) + +static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags) +{ + FILE *file; + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir, + attr->type, attr->config, fd); + + file = fopen(path, "w+"); + if (!file) { + perror("test attr - failed to open event file"); + return -1; + } + + if (fprintf(file, "[event-%d-%llu-%d]\n", + attr->type, attr->config, fd) < 0) { + perror("test attr - failed to write event file"); + fclose(file); + return -1; + } + + /* syscall arguments */ + __WRITE_ASS(fd, "d", fd); + __WRITE_ASS(group_fd, "d", group_fd); + __WRITE_ASS(cpu, "d", cpu); + __WRITE_ASS(pid, "d", pid); + __WRITE_ASS(flags, "lu", flags); + + /* struct perf_event_attr */ + WRITE_ASS(type, PRIu32); + WRITE_ASS(size, PRIu32); + WRITE_ASS(config, "llu"); + WRITE_ASS(sample_period, "llu"); + WRITE_ASS(sample_type, "llu"); + WRITE_ASS(read_format, "llu"); + WRITE_ASS(disabled, "d"); + WRITE_ASS(inherit, "d"); + WRITE_ASS(pinned, "d"); + WRITE_ASS(exclusive, "d"); + WRITE_ASS(exclude_user, "d"); + WRITE_ASS(exclude_kernel, "d"); + WRITE_ASS(exclude_hv, "d"); + WRITE_ASS(exclude_idle, "d"); + WRITE_ASS(mmap, "d"); + WRITE_ASS(comm, "d"); + WRITE_ASS(freq, "d"); + WRITE_ASS(inherit_stat, "d"); + WRITE_ASS(enable_on_exec, "d"); + WRITE_ASS(task, "d"); + WRITE_ASS(watermark, "d"); + WRITE_ASS(precise_ip, "d"); + WRITE_ASS(mmap_data, "d"); + WRITE_ASS(sample_id_all, "d"); + WRITE_ASS(exclude_host, "d"); + WRITE_ASS(exclude_guest, "d"); + WRITE_ASS(exclude_callchain_kernel, "d"); + WRITE_ASS(exclude_callchain_user, "d"); + WRITE_ASS(wakeup_events, PRIu32); + WRITE_ASS(bp_type, PRIu32); + WRITE_ASS(config1, "llu"); + WRITE_ASS(config2, "llu"); + WRITE_ASS(branch_sample_type, "llu"); + WRITE_ASS(sample_regs_user, "llu"); + WRITE_ASS(sample_stack_user, PRIu32); + + fclose(file); + return 0; +} + +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags) +{ + int errno_saved = errno; + + if (store_event(attr, pid, cpu, fd, group_fd, flags)) + die("test attr FAILED"); + + errno = errno_saved; +} + +static int run_dir(const char *d, const char *perf) +{ + 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" : ""); + + return system(cmd); +} + +int test__attr(void) +{ + struct stat st; + char path_perf[PATH_MAX]; + char path_dir[PATH_MAX]; + + /* First try developement tree tests. */ + if (!lstat("./tests", &st)) + return run_dir("./tests", "./perf"); + + /* Then installed path. */ + snprintf(path_dir, PATH_MAX, "%s/tests", perf_exec_path()); + snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR); + + if (!lstat(path_dir, &st) && + !lstat(path_perf, &st)) + return run_dir(path_dir, path_perf); + + fprintf(stderr, " (ommitted)"); + return 0; +} diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py new file mode 100644 index 00000000000..2f629ca485b --- /dev/null +++ b/tools/perf/tests/attr.py @@ -0,0 +1,331 @@ +#! /usr/bin/python + +import os +import sys +import glob +import optparse +import tempfile +import logging +import shutil +import ConfigParser + +class Fail(Exception): + def __init__(self, test, msg): + self.msg = msg + self.test = test + def getMsg(self): + return '\'%s\' - %s' % (self.test.path, self.msg) + +class Unsup(Exception): + def __init__(self, test): + self.test = test + def getMsg(self): + return '\'%s\'' % self.test.path + +class Event(dict): + terms = [ + 'flags', + 'type', + 'size', + 'config', + 'sample_period', + 'sample_type', + 'read_format', + 'disabled', + 'inherit', + 'pinned', + 'exclusive', + 'exclude_user', + 'exclude_kernel', + 'exclude_hv', + 'exclude_idle', + 'mmap', + 'comm', + 'freq', + 'inherit_stat', + 'enable_on_exec', + 'task', + 'watermark', + 'precise_ip', + 'mmap_data', + 'sample_id_all', + 'exclude_host', + 'exclude_guest', + 'exclude_callchain_kernel', + 'exclude_callchain_user', + 'wakeup_events', + 'bp_type', + 'config1', + 'config2', + 'branch_sample_type', + 'sample_regs_user', + 'sample_stack_user', + ] + + def add(self, data): + for key, val in data: + log.debug(" %s = %s" % (key, val)) + self[key] = val + + def __init__(self, name, data, base): + log.debug(" Event %s" % name); + self.name = name; + self.group = '' + self.add(base) + self.add(data) + + def compare_data(self, a, b): + # Allow multiple values in assignment separated by '|' + a_list = a.split('|') + b_list = b.split('|') + + for a_item in a_list: + for b_item in b_list: + if (a_item == b_item): + return True + elif (a_item == '*') or (b_item == '*'): + return True + + return False + + def equal(self, other): + for t in Event.terms: + log.debug(" [%s] %s %s" % (t, self[t], other[t])); + if not self.has_key(t) or not other.has_key(t): + return False + if not self.compare_data(self[t], other[t]): + return False + return True + + def diff(self, other): + for t in Event.terms: + if not self.has_key(t) or not other.has_key(t): + continue + if not self.compare_data(self[t], other[t]): + log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) + + +# Test file description needs to have following sections: +# [config] +# - just single instance in file +# - needs to specify: +# 'command' - perf command name +# 'args' - special command arguments +# 'ret' - expected command return value (0 by default) +# +# [eventX:base] +# - one or multiple instances in file +# - expected values assignments +class Test(object): + def __init__(self, path, options): + parser = ConfigParser.SafeConfigParser() + parser.read(path) + + log.debug("running '%s'" % path) + + self.path = path + self.test_dir = options.test_dir + self.perf = options.perf + self.command = parser.get('config', 'command') + self.args = parser.get('config', 'args') + + try: + self.ret = parser.get('config', 'ret') + except: + self.ret = 0 + + self.expect = {} + self.result = {} + log.debug(" loading expected events"); + self.load_events(path, self.expect) + + def is_event(self, name): + if name.find("event") == -1: + return False + else: + return True + + def load_events(self, path, events): + parser_event = ConfigParser.SafeConfigParser() + parser_event.read(path) + + # The event record section header contains 'event' word, + # optionaly followed by ':' allowing to load 'parent + # event' first as a base + for section in filter(self.is_event, parser_event.sections()): + + parser_items = parser_event.items(section); + base_items = {} + + # Read parent event if there's any + if (':' in section): + base = section[section.index(':') + 1:] + parser_base = ConfigParser.SafeConfigParser() + parser_base.read(self.test_dir + '/' + base) + base_items = parser_base.items('event') + + e = Event(section, parser_items, base_items) + events[section] = e + + def run_cmd(self, tempdir): + cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir, + self.perf, self.command, tempdir, self.args) + ret = os.WEXITSTATUS(os.system(cmd)) + + log.warning(" running '%s' ret %d " % (cmd, ret)) + + if ret != int(self.ret): + raise Unsup(self) + + def compare(self, expect, result): + match = {} + + log.debug(" compare"); + + # For each expected event find all matching + # events in result. Fail if there's not any. + for exp_name, exp_event in expect.items(): + exp_list = [] + log.debug(" matching [%s]" % exp_name) + for res_name, res_event in result.items(): + log.debug(" to [%s]" % res_name) + if (exp_event.equal(res_event)): + exp_list.append(res_name) + log.debug(" ->OK") + else: + log.debug(" ->FAIL"); + + log.debug(" match: [%s] matches %s" % (exp_name, str(exp_list))) + + # we did not any matching event - fail + if (not exp_list): + exp_event.diff(res_event) + raise Fail(self, 'match failure'); + + match[exp_name] = exp_list + + # For each defined group in the expected events + # check we match the same group in the result. + for exp_name, exp_event in expect.items(): + group = exp_event.group + + if (group == ''): + continue + + for res_name in match[exp_name]: + res_group = result[res_name].group + if res_group not in match[group]: + raise Fail(self, 'group failure') + + log.debug(" group: [%s] matches group leader %s" % + (exp_name, str(match[group]))) + + log.debug(" matched") + + def resolve_groups(self, events): + for name, event in events.items(): + group_fd = event['group_fd']; + if group_fd == '-1': + continue; + + for iname, ievent in events.items(): + if (ievent['fd'] == group_fd): + event.group = iname + log.debug('[%s] has group leader [%s]' % (name, iname)) + break; + + def run(self): + tempdir = tempfile.mkdtemp(); + + try: + # run the test script + self.run_cmd(tempdir); + + # load events expectation for the test + log.debug(" loading result events"); + for f in glob.glob(tempdir + '/event*'): + self.load_events(f, self.result); + + # resolve group_fd to event names + self.resolve_groups(self.expect); + self.resolve_groups(self.result); + + # do the expectation - results matching - both ways + self.compare(self.expect, self.result) + self.compare(self.result, self.expect) + + finally: + # cleanup + shutil.rmtree(tempdir) + + +def run_tests(options): + for f in glob.glob(options.test_dir + '/' + options.test): + try: + Test(f, options).run() + except Unsup, obj: + log.warning("unsupp %s" % obj.getMsg()) + +def setup_log(verbose): + global log + level = logging.CRITICAL + + if verbose == 1: + level = logging.WARNING + if verbose == 2: + level = logging.INFO + if verbose >= 3: + level = logging.DEBUG + + log = logging.getLogger('test') + log.setLevel(level) + ch = logging.StreamHandler() + ch.setLevel(level) + formatter = logging.Formatter('%(message)s') + ch.setFormatter(formatter) + log.addHandler(ch) + +USAGE = '''%s [OPTIONS] + -d dir # tests dir + -p path # perf binary + -t test # single test + -v # verbose level +''' % sys.argv[0] + +def main(): + parser = optparse.OptionParser(usage=USAGE) + + parser.add_option("-t", "--test", + action="store", type="string", dest="test") + parser.add_option("-d", "--test-dir", + action="store", type="string", dest="test_dir") + parser.add_option("-p", "--perf", + action="store", type="string", dest="perf") + parser.add_option("-v", "--verbose", + action="count", dest="verbose") + + options, args = parser.parse_args() + if args: + parser.error('FAILED wrong arguments %s' % ' '.join(args)) + return -1 + + setup_log(options.verbose) + + if not options.test_dir: + print 'FAILED no -d option specified' + sys.exit(-1) + + if not options.test: + options.test = 'test*' + + try: + run_tests(options) + + except Fail, obj: + print "FAILED %s" % obj.getMsg(); + sys.exit(-1) + + sys.exit(0) + +if __name__ == '__main__': + main() diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README new file mode 100644 index 00000000000..d102957cd59 --- /dev/null +++ b/tools/perf/tests/attr/README @@ -0,0 +1,64 @@ +The struct perf_event_attr test (attr tests) support +==================================================== +This testing support is embedded into perf directly and is governed +by the PERF_TEST_ATTR environment variable and hook inside the +sys_perf_event_open function. + +The general idea is to store 'struct perf_event_attr' details for +each event created within single perf command. Each event details +are stored into separate text file. Once perf command is finished +these files are checked for values we expect for command. + +The attr tests consist of following parts: + +tests/attr.c +------------ +This is the sys_perf_event_open hook implementation. The hook +is triggered when the PERF_TEST_ATTR environment variable is +defined. It must contain name of existing directory with access +and write permissions. + +For each sys_perf_event_open call event details are stored in +separate file. Besides 'struct perf_event_attr' values we also +store 'fd' and 'group_fd' values to allow checking for groups. + +tests/attr.py +------------- +This is the python script that does all the hard work. It reads +the test definition, executes it and checks results. + +tests/attr/ +----------- +Directory containing all attr test definitions. +Following tests are defined (with perf commands): + + perf record kill (test-record-basic) + perf record -b kill (test-record-branch-any) + perf record -j any kill (test-record-branch-filter-any) + perf record -j any_call kill (test-record-branch-filter-any_call) + perf record -j any_ret kill (test-record-branch-filter-any_ret) + perf record -j hv kill (test-record-branch-filter-hv) + perf record -j ind_call kill (test-record-branch-filter-ind_call) + perf record -j k kill (test-record-branch-filter-k) + perf record -j u kill (test-record-branch-filter-u) + perf record -c 123 kill (test-record-count) + perf record -d kill (test-record-data) + perf record -F 100 kill (test-record-freq) + perf record -g -- kill (test-record-graph-default) + perf record -g dwarf -- kill (test-record-graph-dwarf) + perf record -g fp kill (test-record-graph-fp) + perf record --group -e cycles,instructions kill (test-record-group) + perf record -e '{cycles,instructions}' kill (test-record-group1) + perf record -D kill (test-record-no-delay) + perf record -i kill (test-record-no-inherit) + perf record -n kill (test-record-no-samples) + perf record -c 100 -P kill (test-record-period) + perf record -R kill (test-record-raw) + perf stat -e cycles kill (test-stat-basic) + perf stat kill (test-stat-default) + perf stat -d kill (test-stat-detailed-1) + perf stat -dd kill (test-stat-detailed-2) + perf stat -ddd kill (test-stat-detailed-3) + perf stat --group -e cycles,instructions kill (test-stat-group) + perf stat -e '{cycles,instructions}' kill (test-stat-group1) + perf stat -i -e cycles kill (test-stat-no-inherit) diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record new file mode 100644 index 00000000000..5bc3880f7be --- /dev/null +++ b/tools/perf/tests/attr/base-record @@ -0,0 +1,39 @@ +[event] +fd=1 +group_fd=-1 +flags=0 +type=0|1 +size=96 +config=0 +sample_period=4000 +sample_type=263 +read_format=0 +disabled=1 +inherit=1 +pinned=0 +exclusive=0 +exclude_user=0 +exclude_kernel=0 +exclude_hv=0 +exclude_idle=0 +mmap=1 +comm=1 +freq=1 +inherit_stat=0 +enable_on_exec=1 +task=0 +watermark=0 +precise_ip=0 +mmap_data=0 +sample_id_all=1 +exclude_host=0 +exclude_guest=1 +exclude_callchain_kernel=0 +exclude_callchain_user=0 +wakeup_events=0 +bp_type=0 +config1=0 +config2=0 +branch_sample_type=0 +sample_regs_user=0 +sample_stack_user=0 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat new file mode 100644 index 00000000000..4bd79a82784 --- /dev/null +++ b/tools/perf/tests/attr/base-stat @@ -0,0 +1,39 @@ +[event] +fd=1 +group_fd=-1 +flags=0 +type=0 +size=96 +config=0 +sample_period=0 +sample_type=0 +read_format=3 +disabled=1 +inherit=1 +pinned=0 +exclusive=0 +exclude_user=0 +exclude_kernel=0 +exclude_hv=0 +exclude_idle=0 +mmap=0 +comm=0 +freq=0 +inherit_stat=0 +enable_on_exec=1 +task=0 +watermark=0 +precise_ip=0 +mmap_data=0 +sample_id_all=0 +exclude_host=0 +exclude_guest=1 +exclude_callchain_kernel=0 +exclude_callchain_user=0 +wakeup_events=0 +bp_type=0 +config1=0 +config2=0 +branch_sample_type=0 +sample_regs_user=0 +sample_stack_user=0 diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic new file mode 100644 index 00000000000..55c0428370c --- /dev/null +++ b/tools/perf/tests/attr/test-record-basic @@ -0,0 +1,5 @@ +[config] +command = record +args = kill >/dev/null 2>&1 + +[event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any new file mode 100644 index 00000000000..1421960ed4e --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-any @@ -0,0 +1,8 @@ +[config] +command = record +args = -b kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any new file mode 100644 index 00000000000..915c4df0e0c --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-filter-any @@ -0,0 +1,8 @@ +[config] +command = record +args = -j any kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call new file mode 100644 index 00000000000..8708dbd4f37 --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-filter-any_call @@ -0,0 +1,8 @@ +[config] +command = record +args = -j any_call kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=16 diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret new file mode 100644 index 00000000000..0d3607a6dcb --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret @@ -0,0 +1,8 @@ +[config] +command = record +args = -j any_ret kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=32 diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv new file mode 100644 index 00000000000..f25526740ce --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-filter-hv @@ -0,0 +1,8 @@ +[config] +command = record +args = -j hv kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call new file mode 100644 index 00000000000..e862dd17912 --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call @@ -0,0 +1,8 @@ +[config] +command = record +args = -j ind_call kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=64 diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k new file mode 100644 index 00000000000..182971e898f --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-filter-k @@ -0,0 +1,8 @@ +[config] +command = record +args = -j k kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u new file mode 100644 index 00000000000..83449ef9e68 --- /dev/null +++ b/tools/perf/tests/attr/test-record-branch-filter-u @@ -0,0 +1,8 @@ +[config] +command = record +args = -j u kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=2311 +branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count new file mode 100644 index 00000000000..2f841de56f6 --- /dev/null +++ b/tools/perf/tests/attr/test-record-count @@ -0,0 +1,8 @@ +[config] +command = record +args = -c 123 kill >/dev/null 2>&1 + +[event:base-record] +sample_period=123 +sample_type=7 +freq=0 diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data new file mode 100644 index 00000000000..6627c3e7534 --- /dev/null +++ b/tools/perf/tests/attr/test-record-data @@ -0,0 +1,8 @@ +[config] +command = record +args = -d kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=271 +mmap_data=1 diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq new file mode 100644 index 00000000000..600d0f8f258 --- /dev/null +++ b/tools/perf/tests/attr/test-record-freq @@ -0,0 +1,6 @@ +[config] +command = record +args = -F 100 kill >/dev/null 2>&1 + +[event:base-record] +sample_period=100 diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default new file mode 100644 index 00000000000..833d1849d76 --- /dev/null +++ b/tools/perf/tests/attr/test-record-graph-default @@ -0,0 +1,6 @@ +[config] +command = record +args = -g -- kill >/dev/null 2>&1 + +[event:base-record] +sample_type=295 diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf new file mode 100644 index 00000000000..e93e082f520 --- /dev/null +++ b/tools/perf/tests/attr/test-record-graph-dwarf @@ -0,0 +1,10 @@ +[config] +command = record +args = -g dwarf -- kill >/dev/null 2>&1 + +[event:base-record] +sample_type=12583 +exclude_callchain_user=1 +sample_stack_user=8192 +# TODO different for each arch, no support for that now +sample_regs_user=* diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp new file mode 100644 index 00000000000..7cef3743f03 --- /dev/null +++ b/tools/perf/tests/attr/test-record-graph-fp @@ -0,0 +1,6 @@ +[config] +command = record +args = -g fp kill >/dev/null 2>&1 + +[event:base-record] +sample_type=295 diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group new file mode 100644 index 00000000000..57739cacdb2 --- /dev/null +++ b/tools/perf/tests/attr/test-record-group @@ -0,0 +1,20 @@ +[config] +command = record +args = --group -e cycles,instructions kill >/dev/null 2>&1 + +[event-1:base-record] +fd=1 +group_fd=-1 +sample_type=327 +read_format=4 + +[event-2:base-record] +fd=2 +group_fd=1 +config=1 +sample_type=327 +read_format=4 +mmap=0 +comm=0 +enable_on_exec=0 +disabled=0 diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1 new file mode 100644 index 00000000000..c5548d054af --- /dev/null +++ b/tools/perf/tests/attr/test-record-group1 @@ -0,0 +1,21 @@ +[config] +command = record +args = -e '{cycles,instructions}' kill >/dev/null 2>&1 + +[event-1:base-record] +fd=1 +group_fd=-1 +sample_type=327 +read_format=4 + +[event-2:base-record] +fd=2 +group_fd=1 +type=0 +config=1 +sample_type=327 +read_format=4 +mmap=0 +comm=0 +enable_on_exec=0 +disabled=0 diff --git a/tools/perf/tests/attr/test-record-no-delay b/tools/perf/tests/attr/test-record-no-delay new file mode 100644 index 00000000000..f253b78cdbf --- /dev/null +++ b/tools/perf/tests/attr/test-record-no-delay @@ -0,0 +1,9 @@ +[config] +command = record +args = -D kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=263 +watermark=0 +wakeup_events=1 diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit new file mode 100644 index 00000000000..9079a25cd64 --- /dev/null +++ b/tools/perf/tests/attr/test-record-no-inherit @@ -0,0 +1,7 @@ +[config] +command = record +args = -i kill >/dev/null 2>&1 + +[event:base-record] +sample_type=259 +inherit=0 diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples new file mode 100644 index 00000000000..d0141b2418b --- /dev/null +++ b/tools/perf/tests/attr/test-record-no-samples @@ -0,0 +1,6 @@ +[config] +command = record +args = -n kill >/dev/null 2>&1 + +[event:base-record] +sample_period=0 diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period new file mode 100644 index 00000000000..8abc5314fc5 --- /dev/null +++ b/tools/perf/tests/attr/test-record-period @@ -0,0 +1,7 @@ +[config] +command = record +args = -c 100 -P kill >/dev/null 2>&1 + +[event:base-record] +sample_period=100 +freq=0 diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw new file mode 100644 index 00000000000..4a8ef25b5f4 --- /dev/null +++ b/tools/perf/tests/attr/test-record-raw @@ -0,0 +1,7 @@ +[config] +command = record +args = -R kill >/dev/null 2>&1 + +[event:base-record] +sample_period=4000 +sample_type=1415 diff --git a/tools/perf/tests/attr/test-stat-basic b/tools/perf/tests/attr/test-stat-basic new file mode 100644 index 00000000000..74e17881f2b --- /dev/null +++ b/tools/perf/tests/attr/test-stat-basic @@ -0,0 +1,6 @@ +[config] +command = stat +args = -e cycles kill >/dev/null 2>&1 +ret = 1 + +[event:base-stat] diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default new file mode 100644 index 00000000000..19270f54c96 --- /dev/null +++ b/tools/perf/tests/attr/test-stat-default @@ -0,0 +1,64 @@ +[config] +command = stat +args = kill >/dev/null 2>&1 +ret = 1 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK +[event1:base-stat] +fd=1 +type=1 +config=1 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES +[event2:base-stat] +fd=2 +type=1 +config=3 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS +[event3:base-stat] +fd=3 +type=1 +config=4 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS +[event4:base-stat] +fd=4 +type=1 +config=2 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES +[event5:base-stat] +fd=5 +type=0 +config=0 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND +[event6:base-stat] +fd=6 +type=0 +config=7 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND +[event7:base-stat] +fd=7 +type=0 +config=8 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS +[event8:base-stat] +fd=8 +type=0 +config=1 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS +[event9:base-stat] +fd=9 +type=0 +config=4 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES +[event10:base-stat] +fd=10 +type=0 +config=5 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 new file mode 100644 index 00000000000..51426b87153 --- /dev/null +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -0,0 +1,101 @@ +[config] +command = stat +args = -d kill >/dev/null 2>&1 +ret = 1 + + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK +[event1:base-stat] +fd=1 +type=1 +config=1 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES +[event2:base-stat] +fd=2 +type=1 +config=3 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS +[event3:base-stat] +fd=3 +type=1 +config=4 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS +[event4:base-stat] +fd=4 +type=1 +config=2 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES +[event5:base-stat] +fd=5 +type=0 +config=0 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND +[event6:base-stat] +fd=6 +type=0 +config=7 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND +[event7:base-stat] +fd=7 +type=0 +config=8 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS +[event8:base-stat] +fd=8 +type=0 +config=1 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS +[event9:base-stat] +fd=9 +type=0 +config=4 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES +[event10:base-stat] +fd=10 +type=0 +config=5 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event11:base-stat] +fd=11 +type=3 +config=0 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event12:base-stat] +fd=12 +type=3 +config=65536 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_LL << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event13:base-stat] +fd=13 +type=3 +config=2 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_LL << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event14:base-stat] +fd=14 +type=3 +config=65538 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 new file mode 100644 index 00000000000..8de5acc31c2 --- /dev/null +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -0,0 +1,155 @@ +[config] +command = stat +args = -dd kill >/dev/null 2>&1 +ret = 1 + + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK +[event1:base-stat] +fd=1 +type=1 +config=1 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES +[event2:base-stat] +fd=2 +type=1 +config=3 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS +[event3:base-stat] +fd=3 +type=1 +config=4 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS +[event4:base-stat] +fd=4 +type=1 +config=2 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES +[event5:base-stat] +fd=5 +type=0 +config=0 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND +[event6:base-stat] +fd=6 +type=0 +config=7 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND +[event7:base-stat] +fd=7 +type=0 +config=8 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS +[event8:base-stat] +fd=8 +type=0 +config=1 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS +[event9:base-stat] +fd=9 +type=0 +config=4 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES +[event10:base-stat] +fd=10 +type=0 +config=5 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event11:base-stat] +fd=11 +type=3 +config=0 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event12:base-stat] +fd=12 +type=3 +config=65536 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_LL << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event13:base-stat] +fd=13 +type=3 +config=2 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_LL << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event14:base-stat] +fd=14 +type=3 +config=65538 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_L1I << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event15:base-stat] +fd=15 +type=3 +config=1 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_L1I << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event16:base-stat] +fd=16 +type=3 +config=65537 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_DTLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event17:base-stat] +fd=17 +type=3 +config=3 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_DTLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event18:base-stat] +fd=18 +type=3 +config=65539 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_ITLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event19:base-stat] +fd=19 +type=3 +config=4 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_ITLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event20:base-stat] +fd=20 +type=3 +config=65540 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 new file mode 100644 index 00000000000..0a1f45bf7d7 --- /dev/null +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -0,0 +1,173 @@ +[config] +command = stat +args = -ddd kill >/dev/null 2>&1 +ret = 1 + + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK +[event1:base-stat] +fd=1 +type=1 +config=1 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES +[event2:base-stat] +fd=2 +type=1 +config=3 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS +[event3:base-stat] +fd=3 +type=1 +config=4 + +# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS +[event4:base-stat] +fd=4 +type=1 +config=2 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES +[event5:base-stat] +fd=5 +type=0 +config=0 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND +[event6:base-stat] +fd=6 +type=0 +config=7 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND +[event7:base-stat] +fd=7 +type=0 +config=8 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS +[event8:base-stat] +fd=8 +type=0 +config=1 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS +[event9:base-stat] +fd=9 +type=0 +config=4 + +# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES +[event10:base-stat] +fd=10 +type=0 +config=5 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event11:base-stat] +fd=11 +type=3 +config=0 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event12:base-stat] +fd=12 +type=3 +config=65536 + +# PERF_TYPE_HW_CACHE / +# PERF_COUNT_HW_CACHE_LL << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event13:base-stat] +fd=13 +type=3 +config=2 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_LL << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event14:base-stat] +fd=14 +type=3 +config=65538 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_L1I << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event15:base-stat] +fd=15 +type=3 +config=1 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_L1I << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event16:base-stat] +fd=16 +type=3 +config=65537 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_DTLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event17:base-stat] +fd=17 +type=3 +config=3 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_DTLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event18:base-stat] +fd=18 +type=3 +config=65539 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_ITLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event19:base-stat] +fd=19 +type=3 +config=4 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_ITLB << 0 | +# (PERF_COUNT_HW_CACHE_OP_READ << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event20:base-stat] +fd=20 +type=3 +config=65540 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) +[event21:base-stat] +fd=21 +type=3 +config=512 + +# PERF_TYPE_HW_CACHE, +# PERF_COUNT_HW_CACHE_L1D << 0 | +# (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | +# (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) +[event22:base-stat] +fd=22 +type=3 +config=66048 diff --git a/tools/perf/tests/attr/test-stat-group b/tools/perf/tests/attr/test-stat-group new file mode 100644 index 00000000000..fdc1596a886 --- /dev/null +++ b/tools/perf/tests/attr/test-stat-group @@ -0,0 +1,15 @@ +[config] +command = stat +args = --group -e cycles,instructions kill >/dev/null 2>&1 +ret = 1 + +[event-1:base-stat] +fd=1 +group_fd=-1 + +[event-2:base-stat] +fd=2 +group_fd=1 +config=1 +disabled=0 +enable_on_exec=0 diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1 new file mode 100644 index 00000000000..2a1f86e4a90 --- /dev/null +++ b/tools/perf/tests/attr/test-stat-group1 @@ -0,0 +1,15 @@ +[config] +command = stat +args = -e '{cycles,instructions}' kill >/dev/null 2>&1 +ret = 1 + +[event-1:base-stat] +fd=1 +group_fd=-1 + +[event-2:base-stat] +fd=2 +group_fd=1 +config=1 +disabled=0 +enable_on_exec=0 diff --git a/tools/perf/tests/attr/test-stat-no-inherit b/tools/perf/tests/attr/test-stat-no-inherit new file mode 100644 index 00000000000..d54b2a1e3e2 --- /dev/null +++ b/tools/perf/tests/attr/test-stat-no-inherit @@ -0,0 +1,7 @@ +[config] +command = stat +args = -i -e cycles kill >/dev/null 2>&1 +ret = 1 + +[event:base-stat] +inherit=0 diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c new file mode 100644 index 00000000000..acb98e0e39f --- /dev/null +++ b/tools/perf/tests/builtin-test.c @@ -0,0 +1,203 @@ +/* + * builtin-test.c + * + * Builtin regression testing command: ever growing number of sanity tests + */ +#include "builtin.h" +#include "intlist.h" +#include "tests.h" +#include "debug.h" +#include "color.h" +#include "parse-options.h" +#include "symbol.h" + +static struct test { + const char *desc; + int (*func)(void); +} tests[] = { + { + .desc = "vmlinux symtab matches kallsyms", + .func = test__vmlinux_matches_kallsyms, + }, + { + .desc = "detect open syscall event", + .func = test__open_syscall_event, + }, + { + .desc = "detect open syscall event on all cpus", + .func = test__open_syscall_event_on_all_cpus, + }, + { + .desc = "read samples using the mmap interface", + .func = test__basic_mmap, + }, + { + .desc = "parse events tests", + .func = test__parse_events, + }, +#if defined(__x86_64__) || defined(__i386__) + { + .desc = "x86 rdpmc test", + .func = test__rdpmc, + }, +#endif + { + .desc = "Validate PERF_RECORD_* events & perf_sample fields", + .func = test__PERF_RECORD, + }, + { + .desc = "Test perf pmu format parsing", + .func = test__pmu, + }, + { + .desc = "Test dso data interface", + .func = test__dso_data, + }, + { + .desc = "roundtrip evsel->name check", + .func = test__perf_evsel__roundtrip_name_test, + }, + { + .desc = "Check parsing of sched tracepoints fields", + .func = test__perf_evsel__tp_sched_test, + }, + { + .desc = "Generate and check syscalls:sys_enter_open event fields", + .func = test__syscall_open_tp_fields, + }, + { + .desc = "struct perf_event_attr setup", + .func = test__attr, + }, + { + .desc = "Test matching and linking mutliple hists", + .func = test__hists_link, + }, + { + .desc = "Try 'use perf' in python, checking link problems", + .func = test__python_use, + }, + { + .func = NULL, + }, +}; + +static bool perf_test__matches(int curr, int argc, const char *argv[]) +{ + int i; + + if (argc == 0) + return true; + + for (i = 0; i < argc; ++i) { + char *end; + long nr = strtoul(argv[i], &end, 10); + + if (*end == '\0') { + if (nr == curr + 1) + return true; + continue; + } + + if (strstr(tests[curr].desc, argv[i])) + return true; + } + + return false; +} + +static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) +{ + int i = 0; + int width = 0; + + while (tests[i].func) { + int len = strlen(tests[i].desc); + + if (width < len) + width = len; + ++i; + } + + i = 0; + while (tests[i].func) { + int curr = i++, err; + + if (!perf_test__matches(curr, argc, argv)) + continue; + + pr_info("%2d: %-*s:", i, width, tests[curr].desc); + + if (intlist__find(skiplist, i)) { + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); + continue; + } + + pr_debug("\n--- start ---\n"); + err = tests[curr].func(); + pr_debug("---- end ----\n%s:", tests[curr].desc); + + switch (err) { + case TEST_OK: + pr_info(" Ok\n"); + break; + case TEST_SKIP: + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n"); + break; + case TEST_FAIL: + default: + color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n"); + break; + } + } + + return 0; +} + +static int perf_test__list(int argc, const char **argv) +{ + int i = 0; + + while (tests[i].func) { + int curr = i++; + + if (argc > 1 && !strstr(tests[curr].desc, argv[1])) + continue; + + pr_info("%2d: %s\n", i, tests[curr].desc); + } + + return 0; +} + +int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) +{ + const char * const test_usage[] = { + "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", + NULL, + }; + const char *skip = NULL; + const struct option test_options[] = { + OPT_STRING('s', "skip", &skip, "tests", "tests to skip"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show symbol address, etc)"), + OPT_END() + }; + struct intlist *skiplist = NULL; + + argc = parse_options(argc, argv, test_options, test_usage, 0); + if (argc >= 1 && !strcmp(argv[0], "list")) + return perf_test__list(argc, argv); + + symbol_conf.priv_size = sizeof(int); + symbol_conf.sort_by_name = true; + symbol_conf.try_vmlinux_path = true; + + if (symbol__init() < 0) + return -1; + + if (skip != NULL) + skiplist = intlist__new(skip); + + return __cmd_test(argc, argv, skiplist); +} diff --git a/tools/perf/util/dso-test-data.c b/tools/perf/tests/dso-data.c index c6caedeb1d6..5eaffa2de9c 100644 --- a/tools/perf/util/dso-test-data.c +++ b/tools/perf/tests/dso-data.c @@ -6,7 +6,9 @@ #include <fcntl.h> #include <string.h> +#include "machine.h" #include "symbol.h" +#include "tests.h" #define TEST_ASSERT_VAL(text, cond) \ do { \ @@ -24,6 +26,10 @@ static char *test_file(int size) unsigned char *buf; fd = mkstemp(templ); + if (fd < 0) { + perror("mkstemp failed"); + return NULL; + } buf = malloc(size); if (!buf) { @@ -94,7 +100,7 @@ struct test_data_offset offsets[] = { }, }; -int dso__test_data(void) +int test__dso_data(void) { struct machine machine; struct dso *dso; diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c new file mode 100644 index 00000000000..0fd99a9adb9 --- /dev/null +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -0,0 +1,114 @@ +#include "evlist.h" +#include "evsel.h" +#include "parse-events.h" +#include "tests.h" + +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); + + if (evlist == NULL) + return -ENOMEM; + + for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + /* skip invalid cache type */ + if (!perf_evsel__is_cache_op_valid(type, op)) + continue; + + for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + __perf_evsel__hw_cache_type_op_res_name(type, op, i, + name, sizeof(name)); + err = parse_events(evlist, name); + if (err) + ret = err; + } + } + } + + idx = 0; + evsel = perf_evlist__first(evlist); + + for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + /* skip invalid cache type */ + if (!perf_evsel__is_cache_op_valid(type, op)) + continue; + + for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + __perf_evsel__hw_cache_type_op_res_name(type, op, i, + name, sizeof(name)); + if (evsel->idx != idx) + continue; + + ++idx; + + if (strcmp(perf_evsel__name(evsel), name)) { + pr_debug("%s != %s\n", perf_evsel__name(evsel), name); + ret = -1; + } + + evsel = perf_evsel__next(evsel); + } + } + } + + perf_evlist__delete(evlist); + return ret; +} + +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); + + if (evlist == NULL) + return -ENOMEM; + + for (i = 0; i < nr_names; ++i) { + err = parse_events(evlist, names[i]); + if (err) { + pr_debug("failed to parse event '%s', err %d\n", + names[i], err); + goto out_delete_evlist; + } + } + + err = 0; + list_for_each_entry(evsel, &evlist->entries, node) { + if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) { + --err; + pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]); + } + } + +out_delete_evlist: + perf_evlist__delete(evlist); + return err; +} + +#define perf_evsel__name_array_test(names) \ + __perf_evsel__name_array_test(names, ARRAY_SIZE(names)) + +int test__perf_evsel__roundtrip_name_test(void) +{ + int err = 0, ret = 0; + + err = perf_evsel__name_array_test(perf_evsel__hw_names); + if (err) + ret = err; + + err = perf_evsel__name_array_test(perf_evsel__sw_names); + if (err) + ret = err; + + err = perf_evsel__roundtrip_cache_name_test(); + if (err) + ret = err; + + return ret; +} diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c new file mode 100644 index 00000000000..a5d2fcc5ae3 --- /dev/null +++ b/tools/perf/tests/evsel-tp-sched.c @@ -0,0 +1,84 @@ +#include "evsel.h" +#include "tests.h" +#include "event-parse.h" + +static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, + int size, bool should_be_signed) +{ + struct format_field *field = perf_evsel__field(evsel, name); + int is_signed; + int ret = 0; + + if (field == NULL) { + pr_debug("%s: \"%s\" field not found!\n", evsel->name, name); + return -1; + } + + is_signed = !!(field->flags | FIELD_IS_SIGNED); + if (should_be_signed && !is_signed) { + pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", + evsel->name, name, is_signed, should_be_signed); + ret = -1; + } + + if (field->size != size) { + pr_debug("%s: \"%s\" size (%d) should be %d!\n", + evsel->name, name, field->size, size); + ret = -1; + } + + return ret; +} + +int test__perf_evsel__tp_sched_test(void) +{ + struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch", 0); + int ret = 0; + + if (evsel == NULL) { + pr_debug("perf_evsel__new\n"); + return -1; + } + + if (perf_evsel__test_field(evsel, "prev_comm", 16, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prev_pid", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prev_prio", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prev_state", 8, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "next_comm", 16, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "next_pid", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "next_prio", 4, true)) + ret = -1; + + perf_evsel__delete(evsel); + + evsel = perf_evsel__newtp("sched", "sched_wakeup", 0); + + if (perf_evsel__test_field(evsel, "comm", 16, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "pid", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "prio", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "success", 4, true)) + ret = -1; + + if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) + ret = -1; + + return ret; +} diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c new file mode 100644 index 00000000000..1be64a6c5da --- /dev/null +++ b/tools/perf/tests/hists_link.c @@ -0,0 +1,500 @@ +#include "perf.h" +#include "tests.h" +#include "debug.h" +#include "symbol.h" +#include "sort.h" +#include "evsel.h" +#include "evlist.h" +#include "machine.h" +#include "thread.h" +#include "parse-events.h" + +static struct { + u32 pid; + const char *comm; +} fake_threads[] = { + { 100, "perf" }, + { 200, "perf" }, + { 300, "bash" }, +}; + +static struct { + u32 pid; + u64 start; + const char *filename; +} fake_mmap_info[] = { + { 100, 0x40000, "perf" }, + { 100, 0x50000, "libc" }, + { 100, 0xf0000, "[kernel]" }, + { 200, 0x40000, "perf" }, + { 200, 0x50000, "libc" }, + { 200, 0xf0000, "[kernel]" }, + { 300, 0x40000, "bash" }, + { 300, 0x50000, "libc" }, + { 300, 0xf0000, "[kernel]" }, +}; + +struct fake_sym { + u64 start; + u64 length; + const char *name; +}; + +static struct fake_sym perf_syms[] = { + { 700, 100, "main" }, + { 800, 100, "run_command" }, + { 900, 100, "cmd_record" }, +}; + +static struct fake_sym bash_syms[] = { + { 700, 100, "main" }, + { 800, 100, "xmalloc" }, + { 900, 100, "xfree" }, +}; + +static struct fake_sym libc_syms[] = { + { 700, 100, "malloc" }, + { 800, 100, "free" }, + { 900, 100, "realloc" }, +}; + +static struct fake_sym kernel_syms[] = { + { 700, 100, "schedule" }, + { 800, 100, "page_fault" }, + { 900, 100, "sys_perf_event_open" }, +}; + +static struct { + const char *dso_name; + struct fake_sym *syms; + size_t nr_syms; +} fake_symbols[] = { + { "perf", perf_syms, ARRAY_SIZE(perf_syms) }, + { "bash", bash_syms, ARRAY_SIZE(bash_syms) }, + { "libc", libc_syms, ARRAY_SIZE(libc_syms) }, + { "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) }, +}; + +static struct machine *setup_fake_machine(struct machines *machines) +{ + struct machine *machine = machines__find(machines, HOST_KERNEL_ID); + size_t i; + + if (machine == NULL) { + pr_debug("Not enough memory for machine setup\n"); + return NULL; + } + + for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { + struct thread *thread; + + thread = machine__findnew_thread(machine, fake_threads[i].pid); + if (thread == NULL) + goto out; + + thread__set_comm(thread, fake_threads[i].comm); + } + + for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) { + union perf_event fake_mmap_event = { + .mmap = { + .header = { .misc = PERF_RECORD_MISC_USER, }, + .pid = fake_mmap_info[i].pid, + .start = fake_mmap_info[i].start, + .len = 0x1000ULL, + .pgoff = 0ULL, + }, + }; + + strcpy(fake_mmap_event.mmap.filename, + fake_mmap_info[i].filename); + + machine__process_mmap_event(machine, &fake_mmap_event); + } + + for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) { + size_t k; + struct dso *dso; + + dso = __dsos__findnew(&machine->user_dsos, + fake_symbols[i].dso_name); + if (dso == NULL) + goto out; + + /* emulate dso__load() */ + dso__set_loaded(dso, MAP__FUNCTION); + + for (k = 0; k < fake_symbols[i].nr_syms; k++) { + struct symbol *sym; + struct fake_sym *fsym = &fake_symbols[i].syms[k]; + + sym = symbol__new(fsym->start, fsym->length, + STB_GLOBAL, fsym->name); + if (sym == NULL) + goto out; + + symbols__insert(&dso->symbols[MAP__FUNCTION], sym); + } + } + + return machine; + +out: + pr_debug("Not enough memory for machine setup\n"); + machine__delete_threads(machine); + machine__delete(machine); + return NULL; +} + +struct sample { + u32 pid; + u64 ip; + struct thread *thread; + struct map *map; + struct symbol *sym; +}; + +static struct sample fake_common_samples[] = { + /* perf [kernel] schedule() */ + { .pid = 100, .ip = 0xf0000 + 700, }, + /* perf [perf] main() */ + { .pid = 200, .ip = 0x40000 + 700, }, + /* perf [perf] cmd_record() */ + { .pid = 200, .ip = 0x40000 + 900, }, + /* bash [bash] xmalloc() */ + { .pid = 300, .ip = 0x40000 + 800, }, + /* bash [libc] malloc() */ + { .pid = 300, .ip = 0x50000 + 700, }, +}; + +static struct sample fake_samples[][5] = { + { + /* perf [perf] run_command() */ + { .pid = 100, .ip = 0x40000 + 800, }, + /* perf [libc] malloc() */ + { .pid = 100, .ip = 0x50000 + 700, }, + /* perf [kernel] page_fault() */ + { .pid = 100, .ip = 0xf0000 + 800, }, + /* perf [kernel] sys_perf_event_open() */ + { .pid = 200, .ip = 0xf0000 + 900, }, + /* bash [libc] free() */ + { .pid = 300, .ip = 0x50000 + 800, }, + }, + { + /* perf [libc] free() */ + { .pid = 200, .ip = 0x50000 + 800, }, + /* bash [libc] malloc() */ + { .pid = 300, .ip = 0x50000 + 700, }, /* will be merged */ + /* bash [bash] xfee() */ + { .pid = 300, .ip = 0x40000 + 900, }, + /* bash [libc] realloc() */ + { .pid = 300, .ip = 0x50000 + 900, }, + /* bash [kernel] page_fault() */ + { .pid = 300, .ip = 0xf0000 + 800, }, + }, +}; + +static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) +{ + struct perf_evsel *evsel; + struct addr_location al; + struct hist_entry *he; + struct perf_sample sample = { .cpu = 0, }; + size_t i = 0, k; + + /* + * each evsel will have 10 samples - 5 common and 5 distinct. + * However the second evsel also has a collapsed entry for + * "bash [libc] malloc" so total 9 entries will be in the tree. + */ + list_for_each_entry(evsel, &evlist->entries, node) { + for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) { + const union perf_event event = { + .ip = { + .header = { + .misc = PERF_RECORD_MISC_USER, + }, + .pid = fake_common_samples[k].pid, + .ip = fake_common_samples[k].ip, + }, + }; + + if (perf_event__preprocess_sample(&event, machine, &al, + &sample, 0) < 0) + goto out; + + he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + if (he == NULL) + goto out; + + fake_common_samples[k].thread = al.thread; + fake_common_samples[k].map = al.map; + fake_common_samples[k].sym = al.sym; + } + + for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) { + const union perf_event event = { + .ip = { + .header = { + .misc = PERF_RECORD_MISC_USER, + }, + .pid = fake_samples[i][k].pid, + .ip = fake_samples[i][k].ip, + }, + }; + + if (perf_event__preprocess_sample(&event, machine, &al, + &sample, 0) < 0) + goto out; + + he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + if (he == NULL) + goto out; + + fake_samples[i][k].thread = al.thread; + fake_samples[i][k].map = al.map; + fake_samples[i][k].sym = al.sym; + } + i++; + } + + return 0; + +out: + pr_debug("Not enough memory for adding a hist entry\n"); + return -1; +} + +static int find_sample(struct sample *samples, size_t nr_samples, + struct thread *t, struct map *m, struct symbol *s) +{ + while (nr_samples--) { + if (samples->thread == t && samples->map == m && + samples->sym == s) + return 1; + samples++; + } + return 0; +} + +static int __validate_match(struct hists *hists) +{ + size_t count = 0; + struct rb_root *root; + struct rb_node *node; + + /* + * Only entries from fake_common_samples should have a pair. + */ + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node_in); + + if (hist_entry__has_pairs(he)) { + if (find_sample(fake_common_samples, + ARRAY_SIZE(fake_common_samples), + he->thread, he->ms.map, he->ms.sym)) { + count++; + } else { + pr_debug("Can't find the matched entry\n"); + return -1; + } + } + + node = rb_next(node); + } + + if (count != ARRAY_SIZE(fake_common_samples)) { + pr_debug("Invalid count for matched entries: %zd of %zd\n", + count, ARRAY_SIZE(fake_common_samples)); + return -1; + } + + return 0; +} + +static int validate_match(struct hists *leader, struct hists *other) +{ + return __validate_match(leader) || __validate_match(other); +} + +static int __validate_link(struct hists *hists, int idx) +{ + size_t count = 0; + size_t count_pair = 0; + size_t count_dummy = 0; + struct rb_root *root; + struct rb_node *node; + + /* + * Leader hists (idx = 0) will have dummy entries from other, + * and some entries will have no pair. However every entry + * in other hists should have (dummy) pair. + */ + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node_in); + + if (hist_entry__has_pairs(he)) { + if (!find_sample(fake_common_samples, + ARRAY_SIZE(fake_common_samples), + he->thread, he->ms.map, he->ms.sym) && + !find_sample(fake_samples[idx], + ARRAY_SIZE(fake_samples[idx]), + he->thread, he->ms.map, he->ms.sym)) { + count_dummy++; + } + count_pair++; + } else if (idx) { + pr_debug("A entry from the other hists should have pair\n"); + return -1; + } + + count++; + node = rb_next(node); + } + + /* + * Note that we have a entry collapsed in the other (idx = 1) hists. + */ + if (idx == 0) { + if (count_dummy != ARRAY_SIZE(fake_samples[1]) - 1) { + pr_debug("Invalid count of dummy entries: %zd of %zd\n", + count_dummy, ARRAY_SIZE(fake_samples[1]) - 1); + return -1; + } + if (count != count_pair + ARRAY_SIZE(fake_samples[0])) { + pr_debug("Invalid count of total leader entries: %zd of %zd\n", + count, count_pair + ARRAY_SIZE(fake_samples[0])); + return -1; + } + } else { + if (count != count_pair) { + pr_debug("Invalid count of total other entries: %zd of %zd\n", + count, count_pair); + return -1; + } + if (count_dummy > 0) { + pr_debug("Other hists should not have dummy entries: %zd\n", + count_dummy); + return -1; + } + } + + return 0; +} + +static int validate_link(struct hists *leader, struct hists *other) +{ + return __validate_link(leader, 0) || __validate_link(other, 1); +} + +static void print_hists(struct hists *hists) +{ + int i = 0; + struct rb_root *root; + struct rb_node *node; + + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + pr_info("----- %s --------\n", __func__); + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node_in); + + pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n", + i, he->thread->comm, he->ms.map->dso->short_name, + he->ms.sym->name, he->stat.period); + + i++; + node = rb_next(node); + } +} + +int test__hists_link(void) +{ + int err = -1; + struct machines machines; + struct machine *machine = NULL; + struct perf_evsel *evsel, *first; + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + + if (evlist == NULL) + return -ENOMEM; + + err = parse_events(evlist, "cpu-clock"); + if (err) + goto out; + err = parse_events(evlist, "task-clock"); + if (err) + goto out; + + /* default sort order (comm,dso,sym) will be used */ + if (setup_sorting() < 0) + goto out; + + machines__init(&machines); + + /* setup threads/dso/map/symbols also */ + machine = setup_fake_machine(&machines); + if (!machine) + goto out; + + if (verbose > 1) + machine__fprintf(machine, stderr); + + /* process sample events */ + err = add_hist_entries(evlist, machine); + if (err < 0) + goto out; + + list_for_each_entry(evsel, &evlist->entries, node) { + hists__collapse_resort(&evsel->hists); + + if (verbose > 2) + print_hists(&evsel->hists); + } + + first = perf_evlist__first(evlist); + evsel = perf_evlist__last(evlist); + + /* match common entries */ + hists__match(&first->hists, &evsel->hists); + err = validate_match(&first->hists, &evsel->hists); + if (err) + goto out; + + /* link common and/or dummy entries */ + hists__link(&first->hists, &evsel->hists); + err = validate_link(&first->hists, &evsel->hists); + if (err) + goto out; + + err = 0; + +out: + /* tear down everything */ + perf_evlist__delete(evlist); + machines__exit(&machines); + + return err; +} diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c new file mode 100644 index 00000000000..cdd50755af5 --- /dev/null +++ b/tools/perf/tests/mmap-basic.c @@ -0,0 +1,148 @@ +#include "evlist.h" +#include "evsel.h" +#include "thread_map.h" +#include "cpumap.h" +#include "tests.h" + +/* + * This test will generate random numbers of calls to some getpid syscalls, + * then establish an mmap for a group of events that are created to monitor + * the syscalls. + * + * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated + * sample.id field to map back to its respective perf_evsel instance. + * + * Then it checks if the number of syscalls reported as perf events by + * the kernel corresponds to the number of syscalls made. + */ +int test__basic_mmap(void) +{ + int err = -1; + union perf_event *event; + struct thread_map *threads; + struct cpu_map *cpus; + struct perf_evlist *evlist; + cpu_set_t cpu_set; + const char *syscall_names[] = { "getsid", "getppid", "getpgrp", + "getpgid", }; + pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp, + (void*)getpgid }; +#define nsyscalls ARRAY_SIZE(syscall_names) + unsigned int nr_events[nsyscalls], + expected_nr_events[nsyscalls], i, j; + struct perf_evsel *evsels[nsyscalls], *evsel; + + threads = thread_map__new(-1, getpid(), UINT_MAX); + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + cpus = cpu_map__new(NULL); + if (cpus == NULL) { + pr_debug("cpu_map__new\n"); + goto out_free_threads; + } + + CPU_ZERO(&cpu_set); + CPU_SET(cpus->map[0], &cpu_set); + sched_setaffinity(0, sizeof(cpu_set), &cpu_set); + if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { + pr_debug("sched_setaffinity() failed on CPU %d: %s ", + cpus->map[0], strerror(errno)); + goto out_free_cpus; + } + + evlist = perf_evlist__new(cpus, threads); + if (evlist == NULL) { + pr_debug("perf_evlist__new\n"); + goto out_free_cpus; + } + + for (i = 0; i < nsyscalls; ++i) { + char name[64]; + + snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]); + evsels[i] = perf_evsel__newtp("syscalls", name, i); + if (evsels[i] == NULL) { + pr_debug("perf_evsel__new\n"); + goto out_free_evlist; + } + + evsels[i]->attr.wakeup_events = 1; + perf_evsel__set_sample_id(evsels[i]); + + perf_evlist__add(evlist, evsels[i]); + + if (perf_evsel__open(evsels[i], cpus, threads) < 0) { + pr_debug("failed to open counter: %s, " + "tweak /proc/sys/kernel/perf_event_paranoid?\n", + strerror(errno)); + goto out_close_fd; + } + + nr_events[i] = 0; + expected_nr_events[i] = 1 + rand() % 127; + } + + if (perf_evlist__mmap(evlist, 128, true) < 0) { + pr_debug("failed to mmap events: %d (%s)\n", errno, + strerror(errno)); + goto out_close_fd; + } + + for (i = 0; i < nsyscalls; ++i) + for (j = 0; j < expected_nr_events[i]; ++j) { + int foo = syscalls[i](); + ++foo; + } + + while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { + struct perf_sample sample; + + if (event->header.type != PERF_RECORD_SAMPLE) { + pr_debug("unexpected %s event\n", + perf_event__name(event->header.type)); + goto out_munmap; + } + + err = perf_evlist__parse_sample(evlist, event, &sample); + if (err) { + pr_err("Can't parse sample, err = %d\n", err); + goto out_munmap; + } + + err = -1; + evsel = perf_evlist__id2evsel(evlist, sample.id); + if (evsel == NULL) { + pr_debug("event with id %" PRIu64 + " doesn't map to an evsel\n", sample.id); + goto out_munmap; + } + nr_events[evsel->idx]++; + } + + err = 0; + list_for_each_entry(evsel, &evlist->entries, node) { + if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) { + pr_debug("expected %d %s events, got %d\n", + expected_nr_events[evsel->idx], + perf_evsel__name(evsel), nr_events[evsel->idx]); + err = -1; + goto out_munmap; + } + } + +out_munmap: + perf_evlist__munmap(evlist); +out_close_fd: + for (i = 0; i < nsyscalls; ++i) + perf_evsel__close_fd(evsels[i], 1, threads->nr); +out_free_evlist: + perf_evlist__delete(evlist); +out_free_cpus: + cpu_map__delete(cpus); +out_free_threads: + thread_map__delete(threads); + return err; +} diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c new file mode 100644 index 00000000000..b0657a9ccda --- /dev/null +++ b/tools/perf/tests/open-syscall-all-cpus.c @@ -0,0 +1,109 @@ +#include "evsel.h" +#include "tests.h" +#include "thread_map.h" +#include "cpumap.h" +#include "debug.h" + +int test__open_syscall_event_on_all_cpus(void) +{ + int err = -1, fd, cpu; + struct cpu_map *cpus; + struct perf_evsel *evsel; + unsigned int nr_open_calls = 111, i; + cpu_set_t cpu_set; + struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); + + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + cpus = cpu_map__new(NULL); + if (cpus == NULL) { + pr_debug("cpu_map__new\n"); + goto out_thread_map_delete; + } + + CPU_ZERO(&cpu_set); + + evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0); + if (evsel == NULL) { + pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); + goto out_thread_map_delete; + } + + if (perf_evsel__open(evsel, cpus, threads) < 0) { + pr_debug("failed to open counter: %s, " + "tweak /proc/sys/kernel/perf_event_paranoid?\n", + strerror(errno)); + goto out_evsel_delete; + } + + for (cpu = 0; cpu < cpus->nr; ++cpu) { + unsigned int ncalls = nr_open_calls + cpu; + /* + * XXX eventually lift this restriction in a way that + * keeps perf building on older glibc installations + * without CPU_ALLOC. 1024 cpus in 2010 still seems + * a reasonable upper limit tho :-) + */ + if (cpus->map[cpu] >= CPU_SETSIZE) { + pr_debug("Ignoring CPU %d\n", cpus->map[cpu]); + continue; + } + + CPU_SET(cpus->map[cpu], &cpu_set); + if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { + pr_debug("sched_setaffinity() failed on CPU %d: %s ", + cpus->map[cpu], + strerror(errno)); + goto out_close_fd; + } + for (i = 0; i < ncalls; ++i) { + fd = open("/etc/passwd", O_RDONLY); + close(fd); + } + CPU_CLR(cpus->map[cpu], &cpu_set); + } + + /* + * Here we need to explicitely preallocate the counts, as if + * we use the auto allocation it will allocate just for 1 cpu, + * as we start by cpu 0. + */ + if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) { + pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr); + goto out_close_fd; + } + + err = 0; + + for (cpu = 0; cpu < cpus->nr; ++cpu) { + unsigned int expected; + + if (cpus->map[cpu] >= CPU_SETSIZE) + continue; + + if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) { + pr_debug("perf_evsel__read_on_cpu\n"); + err = -1; + break; + } + + expected = nr_open_calls + cpu; + if (evsel->counts->cpu[cpu].val != expected) { + pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", + expected, cpus->map[cpu], evsel->counts->cpu[cpu].val); + err = -1; + } + } + + perf_evsel__free_counts(evsel); +out_close_fd: + perf_evsel__close_fd(evsel, 1, threads->nr); +out_evsel_delete: + perf_evsel__delete(evsel); +out_thread_map_delete: + thread_map__delete(threads); + return err; +} diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c new file mode 100644 index 00000000000..1c52fdc1164 --- /dev/null +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -0,0 +1,117 @@ +#include "perf.h" +#include "evlist.h" +#include "evsel.h" +#include "thread_map.h" +#include "tests.h" + +int test__syscall_open_tp_fields(void) +{ + struct perf_record_opts opts = { + .target = { + .uid = UINT_MAX, + .uses_mmap = true, + }, + .no_delay = true, + .freq = 1, + .mmap_pages = 256, + .raw_samples = true, + }; + const char *filename = "/etc/passwd"; + int flags = O_RDONLY | O_DIRECTORY; + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evsel *evsel; + int err = -1, i, nr_events = 0, nr_polls = 0; + + if (evlist == NULL) { + pr_debug("%s: perf_evlist__new\n", __func__); + goto out; + } + + evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0); + if (evsel == NULL) { + pr_debug("%s: perf_evsel__newtp\n", __func__); + goto out_delete_evlist; + } + + perf_evlist__add(evlist, evsel); + + err = perf_evlist__create_maps(evlist, &opts.target); + if (err < 0) { + pr_debug("%s: perf_evlist__create_maps\n", __func__); + goto out_delete_evlist; + } + + perf_evsel__config(evsel, &opts); + + evlist->threads->map[0] = getpid(); + + err = perf_evlist__open(evlist); + if (err < 0) { + pr_debug("perf_evlist__open: %s\n", strerror(errno)); + goto out_delete_evlist; + } + + err = perf_evlist__mmap(evlist, UINT_MAX, false); + if (err < 0) { + pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); + goto out_delete_evlist; + } + + perf_evlist__enable(evlist); + + /* + * Generate the event: + */ + open(filename, flags); + + while (1) { + int before = nr_events; + + for (i = 0; i < evlist->nr_mmaps; i++) { + union perf_event *event; + + while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + const u32 type = event->header.type; + int tp_flags; + struct perf_sample sample; + + ++nr_events; + + if (type != PERF_RECORD_SAMPLE) + continue; + + err = perf_evsel__parse_sample(evsel, event, &sample); + if (err) { + pr_err("Can't parse sample, err = %d\n", err); + goto out_munmap; + } + + tp_flags = perf_evsel__intval(evsel, &sample, "flags"); + + if (flags != tp_flags) { + pr_debug("%s: Expected flags=%#x, got %#x\n", + __func__, flags, tp_flags); + goto out_munmap; + } + + goto out_ok; + } + } + + if (nr_events == before) + poll(evlist->pollfd, evlist->nr_fds, 10); + + if (++nr_polls > 5) { + pr_debug("%s: no events!\n", __func__); + goto out_munmap; + } + } +out_ok: + err = 0; +out_munmap: + perf_evlist__munmap(evlist); +out_delete_evlist: + perf_evlist__delete(evlist); +out: + return err; +} diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c new file mode 100644 index 00000000000..befc0671f95 --- /dev/null +++ b/tools/perf/tests/open-syscall.c @@ -0,0 +1,55 @@ +#include "thread_map.h" +#include "evsel.h" +#include "debug.h" +#include "tests.h" + +int test__open_syscall_event(void) +{ + int err = -1, fd; + struct perf_evsel *evsel; + unsigned int nr_open_calls = 111, i; + struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); + + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0); + if (evsel == NULL) { + pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); + goto out_thread_map_delete; + } + + if (perf_evsel__open_per_thread(evsel, threads) < 0) { + pr_debug("failed to open counter: %s, " + "tweak /proc/sys/kernel/perf_event_paranoid?\n", + strerror(errno)); + goto out_evsel_delete; + } + + for (i = 0; i < nr_open_calls; ++i) { + fd = open("/etc/passwd", O_RDONLY); + close(fd); + } + + if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) { + pr_debug("perf_evsel__read_on_cpu\n"); + goto out_close_fd; + } + + if (evsel->counts->cpu[0].val != nr_open_calls) { + pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n", + nr_open_calls, evsel->counts->cpu[0].val); + goto out_close_fd; + } + + err = 0; +out_close_fd: + perf_evsel__close_fd(evsel, 1, threads->nr); +out_evsel_delete: + perf_evsel__delete(evsel); +out_thread_map_delete: + thread_map__delete(threads); + return err; +} diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/tests/parse-events.c index 516ecd9ddd6..c5636f36fe3 100644 --- a/tools/perf/util/parse-events-test.c +++ b/tools/perf/tests/parse-events.c @@ -3,7 +3,9 @@ #include "evsel.h" #include "evlist.h" #include "sysfs.h" -#include "../../../include/linux/hw_breakpoint.h" +#include "debugfs.h" +#include "tests.h" +#include <linux/hw_breakpoint.h> #define TEST_ASSERT_VAL(text, cond) \ do { \ @@ -21,6 +23,7 @@ static int test__checkevent_tracepoint(struct perf_evlist *evlist) struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups); TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); TEST_ASSERT_VAL("wrong sample_type", PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); @@ -33,6 +36,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist) struct perf_evsel *evsel; TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1); + TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups); list_for_each_entry(evsel, &evlist->entries, node) { TEST_ASSERT_VAL("wrong type", @@ -443,12 +447,29 @@ static int test__checkevent_pmu_name(struct perf_evlist *evlist) return 0; } +static int test__checkevent_pmu_events(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evsel = list_entry(evlist->entries.next, struct perf_evsel, node); + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); + TEST_ASSERT_VAL("wrong exclude_user", + !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", + evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + + return 0; +} + static int test__checkterms_simple(struct list_head *terms) { - struct parse_events__term *term; + struct parse_events_term *term; /* config=10 */ - term = list_entry(terms->next, struct parse_events__term, list); + term = list_entry(terms->next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG); TEST_ASSERT_VAL("wrong type val", @@ -457,7 +478,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong config", !term->config); /* config1 */ - term = list_entry(term->list.next, struct parse_events__term, list); + term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1); TEST_ASSERT_VAL("wrong type val", @@ -466,7 +487,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong config", !term->config); /* config2=3 */ - term = list_entry(term->list.next, struct parse_events__term, list); + term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2); TEST_ASSERT_VAL("wrong type val", @@ -475,7 +496,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong config", !term->config); /* umask=1*/ - term = list_entry(term->list.next, struct parse_events__term, list); + term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_USER); TEST_ASSERT_VAL("wrong type val", @@ -491,6 +512,7 @@ static int test__group1(struct perf_evlist *evlist) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* instructions:k */ evsel = leader = perf_evlist__first(evlist); @@ -503,7 +525,9 @@ static int test__group1(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cycles:upp */ evsel = perf_evsel__next(evsel); @@ -518,6 +542,7 @@ static int test__group1(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } @@ -527,6 +552,7 @@ static int test__group2(struct perf_evlist *evlist) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* faults + :ku modifier */ evsel = leader = perf_evlist__first(evlist); @@ -539,7 +565,9 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cache-references + :u modifier */ evsel = perf_evsel__next(evsel); @@ -549,10 +577,11 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* cycles:k */ evsel = perf_evsel__next(evsel); @@ -565,7 +594,7 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); return 0; } @@ -575,6 +604,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* group1 syscalls:sys_enter_open:H */ evsel = leader = perf_evlist__first(evlist); @@ -588,9 +618,11 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong group name", !strcmp(leader->group_name, "group1")); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* group1 cycles:kppp */ evsel = perf_evsel__next(evsel); @@ -606,6 +638,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* group2 cycles + G modifier */ evsel = leader = perf_evsel__next(evsel); @@ -618,9 +651,11 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong group name", !strcmp(leader->group_name, "group2")); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* group2 1:3 + G modifier */ evsel = perf_evsel__next(evsel); @@ -633,6 +668,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* instructions:u */ evsel = perf_evsel__next(evsel); @@ -645,7 +681,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); return 0; } @@ -655,6 +691,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:u + p */ evsel = leader = perf_evlist__first(evlist); @@ -669,7 +706,9 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* instructions:kp + p */ evsel = perf_evsel__next(evsel); @@ -684,6 +723,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } @@ -693,6 +733,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* cycles + G */ evsel = leader = perf_evlist__first(evlist); @@ -706,7 +747,9 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* instructions + G */ evsel = perf_evsel__next(evsel); @@ -720,6 +763,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* cycles:G */ evsel = leader = perf_evsel__next(evsel); @@ -733,7 +777,9 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* instructions:G */ evsel = perf_evsel__next(evsel); @@ -747,6 +793,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* cycles */ evsel = perf_evsel__next(evsel); @@ -759,18 +806,235 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + + return 0; +} + +static int test__group_gh1(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles + :H group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:G + :H group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + + return 0; +} + +static int test__group_gh2(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles + :G group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:H + :G group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } -struct test__event_st { +static int test__group_gh3(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles:G + :u group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:H + :u group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + + return 0; +} + +static int test__group_gh4(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles:G + :uG group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:H + :uG group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + + return 0; +} + +static int count_tracepoints(void) +{ + char events_path[PATH_MAX]; + struct dirent *events_ent; + DIR *events_dir; + int cnt = 0; + + scnprintf(events_path, PATH_MAX, "%s/tracing/events", + debugfs_find_mountpoint()); + + events_dir = opendir(events_path); + + TEST_ASSERT_VAL("Can't open events dir", events_dir); + + while ((events_ent = readdir(events_dir))) { + char sys_path[PATH_MAX]; + struct dirent *sys_ent; + DIR *sys_dir; + + if (!strcmp(events_ent->d_name, ".") + || !strcmp(events_ent->d_name, "..") + || !strcmp(events_ent->d_name, "enable") + || !strcmp(events_ent->d_name, "header_event") + || !strcmp(events_ent->d_name, "header_page")) + continue; + + scnprintf(sys_path, PATH_MAX, "%s/%s", + events_path, events_ent->d_name); + + sys_dir = opendir(sys_path); + TEST_ASSERT_VAL("Can't open sys dir", sys_dir); + + while ((sys_ent = readdir(sys_dir))) { + if (!strcmp(sys_ent->d_name, ".") + || !strcmp(sys_ent->d_name, "..") + || !strcmp(sys_ent->d_name, "enable") + || !strcmp(sys_ent->d_name, "filter")) + continue; + + cnt++; + } + + closedir(sys_dir); + } + + closedir(events_dir); + return cnt; +} + +static int test__all_tracepoints(struct perf_evlist *evlist) +{ + TEST_ASSERT_VAL("wrong events count", + count_tracepoints() == evlist->nr_entries); + + return test__checkevent_tracepoint_multi(evlist); +} + +struct evlist_test { const char *name; __u32 type; int (*check)(struct perf_evlist *evlist); }; -static struct test__event_st test__events[] = { +static struct evlist_test test__events[] = { [0] = { .name = "syscalls:sys_enter_open", .check = test__checkevent_tracepoint, @@ -903,9 +1167,29 @@ static struct test__event_st test__events[] = { .name = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles", .check = test__group5, }, + [33] = { + .name = "*:*", + .check = test__all_tracepoints, + }, + [34] = { + .name = "{cycles,cache-misses:G}:H", + .check = test__group_gh1, + }, + [35] = { + .name = "{cycles,cache-misses:H}:G", + .check = test__group_gh2, + }, + [36] = { + .name = "{cycles:G,cache-misses:H}:u", + .check = test__group_gh3, + }, + [37] = { + .name = "{cycles:G,cache-misses:H}:uG", + .check = test__group_gh4, + }, }; -static struct test__event_st test__events_pmu[] = { +static struct evlist_test test__events_pmu[] = { [0] = { .name = "cpu/config=10,config1,config2=3,period=1000/u", .check = test__checkevent_pmu, @@ -916,20 +1200,20 @@ static struct test__event_st test__events_pmu[] = { }, }; -struct test__term { +struct terms_test { const char *str; __u32 type; int (*check)(struct list_head *terms); }; -static struct test__term test__terms[] = { +static struct terms_test test__terms[] = { [0] = { .str = "config=10,config1,config2=3,umask=1", .check = test__checkterms_simple, }, }; -static int test_event(struct test__event_st *e) +static int test_event(struct evlist_test *e) { struct perf_evlist *evlist; int ret; @@ -938,7 +1222,7 @@ static int test_event(struct test__event_st *e) if (evlist == NULL) return -ENOMEM; - ret = parse_events(evlist, e->name, 0); + ret = parse_events(evlist, e->name); if (ret) { pr_debug("failed to parse event '%s', err %d\n", e->name, ret); @@ -951,13 +1235,13 @@ static int test_event(struct test__event_st *e) return ret; } -static int test_events(struct test__event_st *events, unsigned cnt) +static int test_events(struct evlist_test *events, unsigned cnt) { int ret1, ret2 = 0; unsigned i; for (i = 0; i < cnt; i++) { - struct test__event_st *e = &events[i]; + struct evlist_test *e = &events[i]; pr_debug("running test %d '%s'\n", i, e->name); ret1 = test_event(e); @@ -968,7 +1252,7 @@ static int test_events(struct test__event_st *events, unsigned cnt) return ret2; } -static int test_term(struct test__term *t) +static int test_term(struct terms_test *t) { struct list_head *terms; int ret; @@ -992,13 +1276,13 @@ static int test_term(struct test__term *t) return ret; } -static int test_terms(struct test__term *terms, unsigned cnt) +static int test_terms(struct terms_test *terms, unsigned cnt) { int ret = 0; unsigned i; for (i = 0; i < cnt; i++) { - struct test__term *t = &terms[i]; + struct terms_test *t = &terms[i]; pr_debug("running test %d '%s'\n", i, t->str); ret = test_term(t); @@ -1024,7 +1308,52 @@ static int test_pmu(void) return !ret; } -int parse_events__test(void) +static int test_pmu_events(void) +{ + struct stat st; + char path[PATH_MAX]; + struct dirent *ent; + DIR *dir; + int ret; + + snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/events/", + sysfs_find_mountpoint()); + + ret = stat(path, &st); + if (ret) { + pr_debug("ommiting PMU cpu events tests\n"); + return 0; + } + + dir = opendir(path); + if (!dir) { + pr_debug("can't open pmu event dir"); + return -1; + } + + while (!ret && (ent = readdir(dir))) { +#define MAX_NAME 100 + struct evlist_test e; + char name[MAX_NAME]; + + if (!strcmp(ent->d_name, ".") || + !strcmp(ent->d_name, "..")) + continue; + + snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name); + + e.name = name; + e.check = test__checkevent_pmu_events; + + ret = test_event(&e); +#undef MAX_NAME + } + + closedir(dir); + return ret; +} + +int test__parse_events(void) { int ret1, ret2 = 0; @@ -1040,6 +1369,12 @@ do { \ if (test_pmu()) TEST_EVENTS(test__events_pmu); + if (test_pmu()) { + int ret = test_pmu_events(); + if (ret) + return ret; + } + ret1 = test_terms(test__terms, ARRAY_SIZE(test__terms)); if (!ret2) ret2 = ret1; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c new file mode 100644 index 00000000000..1e8e5128d0d --- /dev/null +++ b/tools/perf/tests/perf-record.c @@ -0,0 +1,314 @@ +#include <sched.h> +#include "evlist.h" +#include "evsel.h" +#include "perf.h" +#include "debug.h" +#include "tests.h" + +static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp) +{ + int i, cpu = -1, nrcpus = 1024; +realloc: + CPU_ZERO(maskp); + + if (sched_getaffinity(pid, sizeof(*maskp), maskp) == -1) { + if (errno == EINVAL && nrcpus < (1024 << 8)) { + nrcpus = nrcpus << 2; + goto realloc; + } + perror("sched_getaffinity"); + return -1; + } + + for (i = 0; i < nrcpus; i++) { + if (CPU_ISSET(i, maskp)) { + if (cpu == -1) + cpu = i; + else + CPU_CLR(i, maskp); + } + } + + return cpu; +} + +int test__PERF_RECORD(void) +{ + struct perf_record_opts opts = { + .target = { + .uid = UINT_MAX, + .uses_mmap = true, + }, + .no_delay = true, + .freq = 10, + .mmap_pages = 256, + }; + cpu_set_t cpu_mask; + size_t cpu_mask_size = sizeof(cpu_mask); + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + struct perf_evsel *evsel; + struct perf_sample sample; + const char *cmd = "sleep"; + const char *argv[] = { cmd, "1", NULL, }; + char *bname; + u64 prev_time = 0; + bool found_cmd_mmap = false, + found_libc_mmap = false, + found_vdso_mmap = false, + found_ld_mmap = false; + int err = -1, errs = 0, i, wakeups = 0; + u32 cpu; + int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, }; + + if (evlist == NULL || argv == NULL) { + pr_debug("Not enough memory to create evlist\n"); + goto out; + } + + /* + * 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_delete_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. + */ + err = perf_evlist__create_maps(evlist, &opts.target); + if (err < 0) { + pr_debug("Not enough memory to create thread/cpu maps\n"); + goto out_delete_evlist; + } + + /* + * Prepare the workload in argv[] to run, it'll fork it, and then wait + * for perf_evlist__start_workload() to exec it. This is done this way + * 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); + if (err < 0) { + pr_debug("Couldn't run the workload!\n"); + goto out_delete_maps; + } + + /* + * Config the evsels, setting attr->comm on the first one, etc. + */ + evsel = perf_evlist__first(evlist); + perf_evsel__set_sample_bit(evsel, CPU); + perf_evsel__set_sample_bit(evsel, TID); + perf_evsel__set_sample_bit(evsel, TIME); + perf_evlist__config(evlist, &opts); + + err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask); + if (err < 0) { + pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno)); + goto out_delete_maps; + } + + cpu = err; + + /* + * So that we can check perf_sample.cpu on all the samples. + */ + if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) { + pr_debug("sched_setaffinity: %s\n", strerror(errno)); + goto out_delete_maps; + } + + /* + * Call sys_perf_event_open on all the fds on all the evsels, + * grouping them if asked to. + */ + err = perf_evlist__open(evlist); + if (err < 0) { + pr_debug("perf_evlist__open: %s\n", strerror(errno)); + goto out_delete_maps; + } + + /* + * mmap the first fd on a given CPU and ask for events for the other + * fds in the same CPU to be injected in the same mmap ring buffer + * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)). + */ + 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; + } + + /* + * Now that all is properly set up, enable the events, they will + * count just on workload.pid, which will start... + */ + perf_evlist__enable(evlist); + + /* + * Now! + */ + perf_evlist__start_workload(evlist); + + while (1) { + int before = total_events; + + for (i = 0; i < evlist->nr_mmaps; i++) { + union perf_event *event; + + while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + const u32 type = event->header.type; + const char *name = perf_event__name(type); + + ++total_events; + if (type < PERF_RECORD_MAX) + nr_events[type]++; + + err = perf_evlist__parse_sample(evlist, event, &sample); + if (err < 0) { + if (verbose) + perf_event__fprintf(event, stderr); + pr_debug("Couldn't parse sample\n"); + goto out_err; + } + + if (verbose) { + pr_info("%" PRIu64" %d ", sample.time, sample.cpu); + perf_event__fprintf(event, stderr); + } + + if (prev_time > sample.time) { + pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n", + name, prev_time, sample.time); + ++errs; + } + + prev_time = sample.time; + + if (sample.cpu != cpu) { + pr_debug("%s with unexpected cpu, expected %d, got %d\n", + name, cpu, sample.cpu); + ++errs; + } + + if ((pid_t)sample.pid != evlist->workload.pid) { + pr_debug("%s with unexpected pid, expected %d, got %d\n", + name, evlist->workload.pid, sample.pid); + ++errs; + } + + if ((pid_t)sample.tid != evlist->workload.pid) { + pr_debug("%s with unexpected tid, expected %d, got %d\n", + name, evlist->workload.pid, sample.tid); + ++errs; + } + + if ((type == PERF_RECORD_COMM || + type == PERF_RECORD_MMAP || + type == PERF_RECORD_FORK || + type == PERF_RECORD_EXIT) && + (pid_t)event->comm.pid != evlist->workload.pid) { + pr_debug("%s with unexpected pid/tid\n", name); + ++errs; + } + + if ((type == PERF_RECORD_COMM || + type == PERF_RECORD_MMAP) && + event->comm.pid != event->comm.tid) { + pr_debug("%s with different pid/tid!\n", name); + ++errs; + } + + switch (type) { + case PERF_RECORD_COMM: + if (strcmp(event->comm.comm, cmd)) { + pr_debug("%s with unexpected comm!\n", name); + ++errs; + } + break; + case PERF_RECORD_EXIT: + goto found_exit; + case PERF_RECORD_MMAP: + bname = strrchr(event->mmap.filename, '/'); + if (bname != NULL) { + if (!found_cmd_mmap) + found_cmd_mmap = !strcmp(bname + 1, cmd); + if (!found_libc_mmap) + found_libc_mmap = !strncmp(bname + 1, "libc", 4); + if (!found_ld_mmap) + found_ld_mmap = !strncmp(bname + 1, "ld", 2); + } else if (!found_vdso_mmap) + found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]"); + break; + + case PERF_RECORD_SAMPLE: + /* Just ignore samples for now */ + break; + default: + pr_debug("Unexpected perf_event->header.type %d!\n", + type); + ++errs; + } + } + } + + /* + * We don't use poll here because at least at 3.1 times the + * PERF_RECORD_{!SAMPLE} events don't honour + * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does. + */ + if (total_events == before && false) + poll(evlist->pollfd, evlist->nr_fds, -1); + + sleep(1); + if (++wakeups > 5) { + pr_debug("No PERF_RECORD_EXIT event!\n"); + break; + } + } + +found_exit: + if (nr_events[PERF_RECORD_COMM] > 1) { + pr_debug("Excessive number of PERF_RECORD_COMM events!\n"); + ++errs; + } + + if (nr_events[PERF_RECORD_COMM] == 0) { + pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd); + ++errs; + } + + if (!found_cmd_mmap) { + pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd); + ++errs; + } + + if (!found_libc_mmap) { + pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc"); + ++errs; + } + + if (!found_ld_mmap) { + pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld"); + ++errs; + } + + if (!found_vdso_mmap) { + pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]"); + ++errs; + } +out_err: + perf_evlist__munmap(evlist); +out_delete_maps: + perf_evlist__delete_maps(evlist); +out_delete_evlist: + perf_evlist__delete(evlist); +out: + return (err < 0 || errs > 0) ? -1 : 0; +} diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c new file mode 100644 index 00000000000..12b322fa347 --- /dev/null +++ b/tools/perf/tests/pmu.c @@ -0,0 +1,173 @@ +#include "parse-events.h" +#include "pmu.h" +#include "util.h" +#include "tests.h" + +/* Simulated format definitions. */ +static struct test_format { + const char *name; + const char *value; +} test_formats[] = { + { "krava01", "config:0-1,62-63\n", }, + { "krava02", "config:10-17\n", }, + { "krava03", "config:5\n", }, + { "krava11", "config1:0,2,4,6,8,20-28\n", }, + { "krava12", "config1:63\n", }, + { "krava13", "config1:45-47\n", }, + { "krava21", "config2:0-3,10-13,20-23,30-33,40-43,50-53,60-63\n", }, + { "krava22", "config2:8,18,48,58\n", }, + { "krava23", "config2:28-29,38\n", }, +}; + +/* Simulated users input. */ +static struct parse_events_term test_terms[] = { + { + .config = (char *) "krava01", + .val.num = 15, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava02", + .val.num = 170, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava03", + .val.num = 1, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava11", + .val.num = 27, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava12", + .val.num = 1, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava13", + .val.num = 2, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava21", + .val.num = 119, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava22", + .val.num = 11, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, + { + .config = (char *) "krava23", + .val.num = 2, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + }, +}; + +/* + * Prepare format directory data, exported by kernel + * at /sys/bus/event_source/devices/<dev>/format. + */ +static char *test_format_dir_get(void) +{ + static char dir[PATH_MAX]; + unsigned int i; + + snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX"); + if (!mkdtemp(dir)) + return NULL; + + for (i = 0; i < ARRAY_SIZE(test_formats); i++) { + static char name[PATH_MAX]; + struct test_format *format = &test_formats[i]; + FILE *file; + + snprintf(name, PATH_MAX, "%s/%s", dir, format->name); + + file = fopen(name, "w"); + if (!file) + return NULL; + + if (1 != fwrite(format->value, strlen(format->value), 1, file)) + break; + + fclose(file); + } + + return dir; +} + +/* Cleanup format directory. */ +static int test_format_dir_put(char *dir) +{ + char buf[PATH_MAX]; + snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir); + if (system(buf)) + return -1; + + snprintf(buf, PATH_MAX, "rmdir %s\n", dir); + return system(buf); +} + +static struct list_head *test_terms_list(void) +{ + static LIST_HEAD(terms); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(test_terms); i++) + list_add_tail(&test_terms[i].list, &terms); + + return &terms; +} + +int test__pmu(void) +{ + char *format = test_format_dir_get(); + LIST_HEAD(formats); + struct list_head *terms = test_terms_list(); + int ret; + + if (!format) + return -EINVAL; + + do { + struct perf_event_attr attr; + + memset(&attr, 0, sizeof(attr)); + + ret = perf_pmu__format_parse(format, &formats); + if (ret) + break; + + ret = perf_pmu__config_terms(&formats, &attr, terms); + if (ret) + break; + + ret = -EINVAL; + + if (attr.config != 0xc00000000002a823) + break; + if (attr.config1 != 0x8000400000000145) + break; + if (attr.config2 != 0x0400000020041d07) + break; + + ret = 0; + } while (0); + + test_format_dir_put(format); + return ret; +} diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c new file mode 100644 index 00000000000..7760277c6de --- /dev/null +++ b/tools/perf/tests/python-use.c @@ -0,0 +1,23 @@ +/* + * Just test if we can load the python binding. + */ + +#include <stdio.h> +#include <stdlib.h> +#include "tests.h" + +extern int verbose; + +int test__python_use(void) +{ + char *cmd; + int ret; + + if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s", + PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0) + return -1; + + ret = system(cmd) ? -1 : 0; + free(cmd); + return ret; +} diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c new file mode 100644 index 00000000000..ff94886aad9 --- /dev/null +++ b/tools/perf/tests/rdpmc.c @@ -0,0 +1,175 @@ +#include <unistd.h> +#include <stdlib.h> +#include <signal.h> +#include <sys/mman.h> +#include "types.h" +#include "perf.h" +#include "debug.h" +#include "tests.h" + +#if defined(__x86_64__) || defined(__i386__) + +#define barrier() asm volatile("" ::: "memory") + +static u64 rdpmc(unsigned int counter) +{ + unsigned int low, high; + + asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter)); + + return low | ((u64)high) << 32; +} + +static u64 rdtsc(void) +{ + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((u64)high) << 32; +} + +static u64 mmap_read_self(void *addr) +{ + struct perf_event_mmap_page *pc = addr; + u32 seq, idx, time_mult = 0, time_shift = 0; + u64 count, cyc = 0, time_offset = 0, enabled, running, delta; + + do { + seq = pc->lock; + barrier(); + + enabled = pc->time_enabled; + running = pc->time_running; + + if (enabled != running) { + cyc = rdtsc(); + time_mult = pc->time_mult; + time_shift = pc->time_shift; + time_offset = pc->time_offset; + } + + idx = pc->index; + count = pc->offset; + if (idx) + count += rdpmc(idx - 1); + + barrier(); + } while (pc->lock != seq); + + if (enabled != running) { + u64 quot, rem; + + quot = (cyc >> time_shift); + rem = cyc & ((1 << time_shift) - 1); + delta = time_offset + quot * time_mult + + ((rem * time_mult) >> time_shift); + + enabled += delta; + if (idx) + running += delta; + + quot = count / running; + rem = count % running; + count = quot * enabled + (rem * enabled) / running; + } + + return count; +} + +/* + * If the RDPMC instruction faults then signal this back to the test parent task: + */ +static void segfault_handler(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + exit(-1); +} + +static int __test__rdpmc(void) +{ + volatile int tmp = 0; + u64 i, loops = 1000; + int n; + int fd; + void *addr; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .exclude_kernel = 1, + }; + u64 delta_sum = 0; + struct sigaction sa; + + sigfillset(&sa.sa_mask); + sa.sa_sigaction = segfault_handler; + sigaction(SIGSEGV, &sa, NULL); + + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (fd < 0) { + pr_err("Error: sys_perf_event_open() syscall returned " + "with %d (%s)\n", fd, strerror(errno)); + return -1; + } + + addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0); + if (addr == (void *)(-1)) { + pr_err("Error: mmap() syscall returned with (%s)\n", + strerror(errno)); + goto out_close; + } + + for (n = 0; n < 6; n++) { + u64 stamp, now, delta; + + stamp = mmap_read_self(addr); + + for (i = 0; i < loops; i++) + tmp++; + + now = mmap_read_self(addr); + loops *= 10; + + delta = now - stamp; + pr_debug("%14d: %14Lu\n", n, (long long)delta); + + delta_sum += delta; + } + + munmap(addr, page_size); + pr_debug(" "); +out_close: + close(fd); + + if (!delta_sum) + return -1; + + return 0; +} + +int test__rdpmc(void) +{ + int status = 0; + int wret = 0; + int ret; + int pid; + + pid = fork(); + if (pid < 0) + return -1; + + if (!pid) { + ret = __test__rdpmc(); + + exit(ret); + } + + wret = waitpid(pid, &status, 0); + if (wret < 0 || status) + return -1; + + return 0; +} + +#endif diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h new file mode 100644 index 00000000000..5de0be1ff4b --- /dev/null +++ b/tools/perf/tests/tests.h @@ -0,0 +1,27 @@ +#ifndef TESTS_H +#define TESTS_H + +enum { + TEST_OK = 0, + TEST_FAIL = -1, + TEST_SKIP = -2, +}; + +/* Tests */ +int test__vmlinux_matches_kallsyms(void); +int test__open_syscall_event(void); +int test__open_syscall_event_on_all_cpus(void); +int test__basic_mmap(void); +int test__PERF_RECORD(void); +int test__rdpmc(void); +int test__perf_evsel__roundtrip_name_test(void); +int test__perf_evsel__tp_sched_test(void); +int test__syscall_open_tp_fields(void); +int test__pmu(void); +int test__attr(void); +int test__dso_data(void); +int test__parse_events(void); +int test__hists_link(void); +int test__python_use(void); + +#endif /* TESTS_H */ diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c new file mode 100644 index 00000000000..7b4c4d26d1b --- /dev/null +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -0,0 +1,233 @@ +#include <linux/compiler.h> +#include <linux/rbtree.h> +#include <string.h> +#include "map.h" +#include "symbol.h" +#include "util.h" +#include "tests.h" +#include "debug.h" +#include "machine.h" + +static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused, + struct symbol *sym) +{ + bool *visited = symbol__priv(sym); + *visited = true; + return 0; +} + +int test__vmlinux_matches_kallsyms(void) +{ + int err = -1; + struct rb_node *nd; + struct symbol *sym; + struct map *kallsyms_map, *vmlinux_map; + struct machine kallsyms, vmlinux; + enum map_type type = MAP__FUNCTION; + struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", }; + + /* + * Step 1: + * + * Init the machines that will hold kernel, modules obtained from + * both vmlinux + .ko files and from /proc/kallsyms split by modules. + */ + machine__init(&kallsyms, "", HOST_KERNEL_ID); + machine__init(&vmlinux, "", HOST_KERNEL_ID); + + /* + * Step 2: + * + * Create the kernel maps for kallsyms and the DSO where we will then + * load /proc/kallsyms. Also create the modules maps from /proc/modules + * and find the .ko files that match them in /lib/modules/`uname -r`/. + */ + if (machine__create_kernel_maps(&kallsyms) < 0) { + pr_debug("machine__create_kernel_maps "); + goto out; + } + + /* + * Step 3: + * + * Load and split /proc/kallsyms into multiple maps, one per module. + */ + if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, NULL) <= 0) { + pr_debug("dso__load_kallsyms "); + goto out; + } + + /* + * Step 4: + * + * kallsyms will be internally on demand sorted by name so that we can + * find the reference relocation * symbol, i.e. the symbol we will use + * to see if the running kernel was relocated by checking if it has the + * same value in the vmlinux file we load. + */ + kallsyms_map = machine__kernel_map(&kallsyms, type); + + sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL); + if (sym == NULL) { + pr_debug("dso__find_symbol_by_name "); + goto out; + } + + ref_reloc_sym.addr = sym->start; + + /* + * Step 5: + * + * Now repeat step 2, this time for the vmlinux file we'll auto-locate. + */ + if (machine__create_kernel_maps(&vmlinux) < 0) { + pr_debug("machine__create_kernel_maps "); + goto out; + } + + vmlinux_map = machine__kernel_map(&vmlinux, type); + map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym; + + /* + * Step 6: + * + * Locate a vmlinux file in the vmlinux path that has a buildid that + * matches the one of the running kernel. + * + * While doing that look if we find the ref reloc symbol, if we find it + * we'll have its ref_reloc_symbol.unrelocated_addr and then + * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines + * to fixup the symbols. + */ + if (machine__load_vmlinux_path(&vmlinux, type, + vmlinux_matches_kallsyms_filter) <= 0) { + pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n"); + err = TEST_SKIP; + goto out; + } + + err = 0; + /* + * Step 7: + * + * Now look at the symbols in the vmlinux DSO and check if we find all of them + * in the kallsyms dso. For the ones that are in both, check its names and + * end addresses too. + */ + for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) { + struct symbol *pair, *first_pair; + bool backwards = true; + + sym = rb_entry(nd, struct symbol, rb_node); + + if (sym->start == sym->end) + continue; + + first_pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL); + pair = first_pair; + + if (pair && pair->start == sym->start) { +next_pair: + if (strcmp(sym->name, pair->name) == 0) { + /* + * kallsyms don't have the symbol end, so we + * set that by using the next symbol start - 1, + * in some cases we get this up to a page + * wrong, trace_kmalloc when I was developing + * this code was one such example, 2106 bytes + * off the real size. More than that and we + * _really_ have a problem. + */ + s64 skew = sym->end - pair->end; + if (llabs(skew) < page_size) + continue; + + pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n", + sym->start, sym->name, sym->end, pair->end); + } else { + struct rb_node *nnd; +detour: + nnd = backwards ? rb_prev(&pair->rb_node) : + rb_next(&pair->rb_node); + if (nnd) { + struct symbol *next = rb_entry(nnd, struct symbol, rb_node); + + if (next->start == sym->start) { + pair = next; + goto next_pair; + } + } + + if (backwards) { + backwards = false; + pair = first_pair; + goto detour; + } + + pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", + sym->start, sym->name, pair->name); + } + } else + pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->start, sym->name); + + err = -1; + } + + if (!verbose) + goto out; + + pr_info("Maps only in vmlinux:\n"); + + for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node), *pair; + /* + * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while + * the kernel will have the path for the vmlinux file being used, + * so use the short name, less descriptive but the same ("[kernel]" in + * both cases. + */ + pair = map_groups__find_by_name(&kallsyms.kmaps, type, + (pos->dso->kernel ? + pos->dso->short_name : + pos->dso->name)); + if (pair) + pair->priv = 1; + else + map__fprintf(pos, stderr); + } + + pr_info("Maps in vmlinux with a different name in kallsyms:\n"); + + for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node), *pair; + + pair = map_groups__find(&kallsyms.kmaps, type, pos->start); + if (pair == NULL || pair->priv) + continue; + + if (pair->start == pos->start) { + pair->priv = 1; + pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", + pos->start, pos->end, pos->pgoff, pos->dso->name); + if (pos->pgoff != pair->pgoff || pos->end != pair->end) + pr_info(": \n*%" PRIx64 "-%" PRIx64 " %" PRIx64 "", + pair->start, pair->end, pair->pgoff); + pr_info(" %s\n", pair->dso->name); + pair->priv = 1; + } + } + + pr_info("Maps only in kallsyms:\n"); + + for (nd = rb_first(&kallsyms.kmaps.maps[type]); + nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node); + + if (!pos->priv) + map__fprintf(pos, stderr); + } +out: + machine__exit(&kallsyms); + machine__exit(&vmlinux); + return err; +} diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 4aeb7d5df93..809ea4632a3 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -273,6 +273,8 @@ void ui_browser__hide(struct ui_browser *browser __maybe_unused) { pthread_mutex_lock(&ui__lock); ui_helpline__pop(); + free(browser->helpline); + browser->helpline = NULL; pthread_mutex_unlock(&ui__lock); } @@ -471,7 +473,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser) return row; } -static struct ui_browser__colorset { +static struct ui_browser_colorset { const char *name, *fg, *bg; int colorset; } ui_browser__colorsets[] = { @@ -706,7 +708,7 @@ void ui_browser__init(void) perf_config(ui_browser__color_config, NULL); while (ui_browser__colorsets[i].name) { - struct ui_browser__colorset *c = &ui_browser__colorsets[i++]; + struct ui_browser_colorset *c = &ui_browser__colorsets[i++]; sltt_set_color(c->colorset, c->name, c->fg, c->bg); } diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 8f8cd2d73b3..7dca1555c61 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -182,15 +182,30 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int ab->selection = dl; } +static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym) +{ + if (!dl || !dl->ins || !ins__is_jump(dl->ins) + || !disasm_line__has_offset(dl) + || dl->ops.target.offset >= symbol__size(sym)) + return false; + + return true; +} + static void annotate_browser__draw_current_jump(struct ui_browser *browser) { struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); struct disasm_line *cursor = ab->selection, *target; struct browser_disasm_line *btarget, *bcursor; unsigned int from, to; + struct map_symbol *ms = ab->b.priv; + struct symbol *sym = ms->sym; - if (!cursor || !cursor->ins || !ins__is_jump(cursor->ins) || - !disasm_line__has_offset(cursor)) + /* PLT symbols contain external offsets */ + if (strstr(sym->name, "@plt")) + return; + + if (!disasm_line__is_valid_jump(cursor, sym)) return; target = ab->offsets[cursor->ops.target.offset]; @@ -386,9 +401,8 @@ 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, void (*timer)(void *arg), - void *arg, int delay_secs) +static bool annotate_browser__callq(struct annotate_browser *browser, int evidx, + struct hist_browser_timer *hbt) { struct map_symbol *ms = browser->b.priv; struct disasm_line *dl = browser->selection; @@ -418,7 +432,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser, } pthread_mutex_unlock(¬es->lock); - symbol__tui_annotate(target, ms->map, evidx, timer, arg, delay_secs); + symbol__tui_annotate(target, ms->map, evidx, hbt); ui_browser__show_title(&browser->b, sym->name); return true; } @@ -602,13 +616,13 @@ static void annotate_browser__update_addr_width(struct annotate_browser *browser } static int annotate_browser__run(struct annotate_browser *browser, int evidx, - void(*timer)(void *arg), - void *arg, int delay_secs) + struct hist_browser_timer *hbt) { struct rb_node *nd = NULL; struct map_symbol *ms = browser->b.priv; struct symbol *sym = ms->sym; const char *help = "Press 'h' for help on key bindings"; + int delay_secs = hbt ? hbt->refresh : 0; int key; if (ui_browser__show(&browser->b, sym->name, help) < 0) @@ -639,8 +653,8 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx, switch (key) { case K_TIMER: - if (timer != NULL) - timer(arg); + if (hbt) + hbt->timer(hbt->arg); if (delay_secs != 0) symbol__annotate_decay_histogram(sym, evidx); @@ -676,8 +690,14 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx, "o Toggle disassembler output/simplified view\n" "s Toggle source code view\n" "/ Search string\n" + "r Run available scripts\n" "? Search previous string\n"); continue; + case 'r': + { + script_browse(NULL); + continue; + } case 'H': nd = browser->curr_hot; break; @@ -734,7 +754,7 @@ show_help: goto show_sup_ins; goto out; } else if (!(annotate_browser__jump(browser) || - annotate_browser__callq(browser, evidx, timer, arg, delay_secs))) { + annotate_browser__callq(browser, evidx, hbt))) { show_sup_ins: ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions."); } @@ -757,32 +777,29 @@ out: } int hist_entry__tui_annotate(struct hist_entry *he, int evidx, - void(*timer)(void *arg), void *arg, int delay_secs) + struct hist_browser_timer *hbt) { - return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, - timer, arg, delay_secs); + return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, hbt); } static void annotate_browser__mark_jump_targets(struct annotate_browser *browser, size_t size) { u64 offset; + struct map_symbol *ms = browser->b.priv; + struct symbol *sym = ms->sym; + + /* PLT symbols contain external offsets */ + if (strstr(sym->name, "@plt")) + return; for (offset = 0; offset < size; ++offset) { struct disasm_line *dl = browser->offsets[offset], *dlt; struct browser_disasm_line *bdlt; - if (!dl || !dl->ins || !ins__is_jump(dl->ins) || - !disasm_line__has_offset(dl)) + if (!disasm_line__is_valid_jump(dl, sym)) continue; - if (dl->ops.target.offset >= size) { - ui__error("jump to after symbol!\n" - "size: %zx, jump target: %" PRIx64, - size, dl->ops.target.offset); - continue; - } - dlt = browser->offsets[dl->ops.target.offset]; /* * FIXME: Oops, no jump target? Buggy disassembler? Or do we @@ -810,8 +827,7 @@ static inline int width_jumps(int n) } int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, - void(*timer)(void *arg), void *arg, - int delay_secs) + struct hist_browser_timer *hbt) { struct disasm_line *pos, *n; struct annotation *notes; @@ -893,7 +909,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, annotate_browser__update_addr_width(&browser); - ret = annotate_browser__run(&browser, evidx, timer, arg, delay_secs); + ret = annotate_browser__run(&browser, evidx, hbt); list_for_each_entry_safe(pos, n, ¬es->src->source, node) { list_del(&pos->node); disasm_line__free(pos); @@ -906,11 +922,11 @@ out_free_offsets: #define ANNOTATE_CFG(n) \ { .name = #n, .value = &annotate_browser__opts.n, } - + /* * Keep the entries sorted, they are bsearch'ed */ -static struct annotate__config { +static struct annotate_config { const char *name; bool *value; } annotate__configs[] = { @@ -924,7 +940,7 @@ static struct annotate__config { static int annotate_config__cmp(const void *name, const void *cfgp) { - const struct annotate__config *cfg = cfgp; + const struct annotate_config *cfg = cfgp; return strcmp(name, cfg->name); } @@ -932,7 +948,7 @@ static int annotate_config__cmp(const void *name, const void *cfgp) static int annotate__config(const char *var, const char *value, void *data __maybe_unused) { - struct annotate__config *cfg; + struct annotate_config *cfg; const char *name; if (prefixcmp(var, "annotate.") != 0) @@ -940,7 +956,7 @@ static int annotate__config(const char *var, const char *value, name = var + 9; cfg = bsearch(name, annotate__configs, ARRAY_SIZE(annotate__configs), - sizeof(struct annotate__config), annotate_config__cmp); + sizeof(struct annotate_config), annotate_config__cmp); if (cfg == NULL) return -1; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index ef2f93ca749..aa22704047d 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -11,6 +11,7 @@ #include "../../util/pstack.h" #include "../../util/sort.h" #include "../../util/util.h" +#include "../../arch/common.h" #include "../browser.h" #include "../helpline.h" @@ -310,10 +311,11 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser) } static int hist_browser__run(struct hist_browser *browser, const char *ev_name, - void(*timer)(void *arg), void *arg, int delay_secs) + struct hist_browser_timer *hbt) { int key; char title[160]; + int delay_secs = hbt ? hbt->refresh : 0; browser->b.entries = &browser->hists->entries; browser->b.nr_entries = browser->hists->nr_entries; @@ -330,7 +332,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, switch (key) { case K_TIMER: - timer(arg); + hbt->timer(hbt->arg); ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries); if (browser->hists->stats.nr_lost_warned != @@ -565,26 +567,128 @@ static int hist_browser__show_callchain(struct hist_browser *browser, return row - first_row; } -#define HPP__COLOR_FN(_name, _field) \ -static int hist_browser__hpp_color_ ## _name(struct perf_hpp *hpp, \ - struct hist_entry *he) \ +struct hpp_arg { + struct ui_browser *b; + char folded_sign; + bool current_entry; +}; + +static int __hpp__color_callchain(struct hpp_arg *arg) +{ + if (!symbol_conf.use_callchain) + return 0; + + slsmg_printf("%c ", arg->folded_sign); + return 2; +} + +static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, + u64 (*get_field)(struct hist_entry *), + int (*callchain_cb)(struct hpp_arg *)) +{ + int ret = 0; + double percent = 0.0; + struct hists *hists = he->hists; + struct hpp_arg *arg = hpp->ptr; + + if (hists->stats.total_period) + percent = 100.0 * get_field(he) / hists->stats.total_period; + + ui_browser__set_percent_color(arg->b, percent, arg->current_entry); + + if (callchain_cb) + ret += callchain_cb(arg); + + ret += scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); + slsmg_printf("%s", hpp->buf); + + if (symbol_conf.event_group) { + 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) + goto out; + + prev_idx = perf_evsel__group_idx(evsel); + + list_for_each_entry(pair, &he->pairs.head, pairs.node) { + u64 period = get_field(pair); + u64 total = pair->hists->stats.total_period; + + if (!total) + continue; + + evsel = hists_to_evsel(pair->hists); + idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members in the middle which + * have no sample + */ + ui_browser__set_percent_color(arg->b, 0.0, + arg->current_entry); + ret += scnprintf(hpp->buf, hpp->size, + " %6.2f%%", 0.0); + slsmg_printf("%s", hpp->buf); + } + + percent = 100.0 * period / total; + ui_browser__set_percent_color(arg->b, percent, + arg->current_entry); + ret += scnprintf(hpp->buf, hpp->size, + " %6.2f%%", percent); + slsmg_printf("%s", hpp->buf); + + prev_idx = perf_evsel__group_idx(evsel); + } + + idx_delta = nr_members - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members at last which have no sample + */ + ui_browser__set_percent_color(arg->b, 0.0, + arg->current_entry); + ret += scnprintf(hpp->buf, hpp->size, + " %6.2f%%", 0.0); + slsmg_printf("%s", hpp->buf); + } + } +out: + if (!arg->current_entry || !arg->b->navkeypressed) + ui_browser__set_color(arg->b, HE_COLORSET_NORMAL); + + return ret; +} + +#define __HPP_COLOR_PERCENT_FN(_type, _field, _cb) \ +static u64 __hpp_get_##_field(struct hist_entry *he) \ { \ - struct hists *hists = he->hists; \ - double percent = 100.0 * he->stat._field / hists->stats.total_period; \ - *(double *)hpp->ptr = percent; \ - return scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); \ + return he->stat._field; \ +} \ + \ +static int hist_browser__hpp_color_##_type(struct perf_hpp *hpp, \ + struct hist_entry *he) \ +{ \ + return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb); \ } -HPP__COLOR_FN(overhead, period) -HPP__COLOR_FN(overhead_sys, period_sys) -HPP__COLOR_FN(overhead_us, period_us) -HPP__COLOR_FN(overhead_guest_sys, period_guest_sys) -HPP__COLOR_FN(overhead_guest_us, period_guest_us) +__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__color_callchain) +__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, NULL) +__HPP_COLOR_PERCENT_FN(overhead_us, period_us, NULL) +__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, NULL) +__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL) -#undef HPP__COLOR_FN +#undef __HPP_COLOR_PERCENT_FN void hist_browser__init_hpp(void) { + perf_hpp__column_enable(PERF_HPP__OVERHEAD); + perf_hpp__init(); perf_hpp__format[PERF_HPP__OVERHEAD].color = @@ -604,13 +708,13 @@ static int hist_browser__show_entry(struct hist_browser *browser, unsigned short row) { char s[256]; - double percent; - int i, printed = 0; + int printed = 0; int width = browser->b.width; char folded_sign = ' '; bool current_entry = ui_browser__is_current_entry(&browser->b, row); off_t row_offset = entry->row_offset; bool first = true; + struct perf_hpp_fmt *fmt; if (current_entry) { browser->he_selection = entry; @@ -623,41 +727,30 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (row_offset == 0) { + struct hpp_arg arg = { + .b = &browser->b, + .folded_sign = folded_sign, + .current_entry = current_entry, + }; struct perf_hpp hpp = { .buf = s, .size = sizeof(s), + .ptr = &arg, }; ui_browser__gotorc(&browser->b, row, 0); - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - + perf_hpp__for_each_format(fmt) { if (!first) { slsmg_printf(" "); width -= 2; } first = false; - if (perf_hpp__format[i].color) { - hpp.ptr = &percent; - /* It will set percent for us. See HPP__COLOR_FN above. */ - width -= perf_hpp__format[i].color(&hpp, entry); - - ui_browser__set_percent_color(&browser->b, percent, current_entry); - - if (i == PERF_HPP__OVERHEAD && symbol_conf.use_callchain) { - slsmg_printf("%c ", folded_sign); - width -= 2; - } - - slsmg_printf("%s", s); - - if (!current_entry || !browser->b.navkeypressed) - ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL); + if (fmt->color) { + width -= fmt->color(&hpp, entry); } else { - width -= perf_hpp__format[i].entry(&hpp, entry); + width -= fmt->entry(&hpp, entry); slsmg_printf("%s", s); } } @@ -1096,6 +1189,21 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, const struct thread *thread = hists->thread_filter; unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; u64 nr_events = hists->stats.total_period; + struct perf_evsel *evsel = hists_to_evsel(hists); + char buf[512]; + size_t buflen = sizeof(buf); + + if (symbol_conf.event_group && evsel->nr_members > 1) { + struct perf_evsel *pos; + + perf_evsel__group_desc(evsel, buf, buflen); + ev_name = buf; + + for_each_group_member(pos, evsel) { + nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos->hists.stats.total_period; + } + } nr_samples = convert_unit(nr_samples, &unit); printed = scnprintf(bf, size, @@ -1127,11 +1235,107 @@ static inline void free_popup_options(char **options, int n) } } +/* Check whether the browser is for 'top' or 'report' */ +static inline bool is_report_browser(void *timer) +{ + return timer == NULL; +} + +/* + * Only runtime switching of perf data file will make "input_name" point + * to a malloced buffer. So add "is_input_name_malloced" flag to decide + * whether we need to call free() for current "input_name" during the switch. + */ +static bool is_input_name_malloced = false; + +static int switch_data_file(void) +{ + char *pwd, *options[32], *abs_path[32], *tmp; + DIR *pwd_dir; + int nr_options = 0, choice = -1, ret = -1; + struct dirent *dent; + + pwd = getenv("PWD"); + if (!pwd) + return ret; + + pwd_dir = opendir(pwd); + if (!pwd_dir) + return ret; + + memset(options, 0, sizeof(options)); + memset(options, 0, sizeof(abs_path)); + + while ((dent = readdir(pwd_dir))) { + char path[PATH_MAX]; + u64 magic; + char *name = dent->d_name; + FILE *file; + + if (!(dent->d_type == DT_REG)) + continue; + + snprintf(path, sizeof(path), "%s/%s", pwd, name); + + file = fopen(path, "r"); + if (!file) + continue; + + if (fread(&magic, 1, 8, file) < 8) + goto close_file_and_continue; + + if (is_perf_magic(magic)) { + options[nr_options] = strdup(name); + if (!options[nr_options]) + goto close_file_and_continue; + + abs_path[nr_options] = strdup(path); + if (!abs_path[nr_options]) { + free(options[nr_options]); + ui__warning("Can't search all data files due to memory shortage.\n"); + fclose(file); + break; + } + + nr_options++; + } + +close_file_and_continue: + fclose(file); + if (nr_options >= 32) { + ui__warning("Too many perf data files in PWD!\n" + "Only the first 32 files will be listed.\n"); + break; + } + } + closedir(pwd_dir); + + if (nr_options) { + choice = ui__popup_menu(nr_options, options); + if (choice < nr_options && choice >= 0) { + tmp = strdup(abs_path[choice]); + if (tmp) { + if (is_input_name_malloced) + free((void *)input_name); + input_name = tmp; + is_input_name_malloced = true; + ret = 0; + } else + ui__warning("Data switch failed due to memory shortage!\n"); + } + } + + free_popup_options(options, nr_options); + free_popup_options(abs_path, nr_options); + return ret; +} + + static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, const char *helpline, const char *ev_name, bool left_exits, - void(*timer)(void *arg), void *arg, - int delay_secs) + struct hist_browser_timer *hbt, + struct perf_session_env *env) { struct hists *hists = &evsel->hists; struct hist_browser *browser = hist_browser__new(hists); @@ -1141,6 +1345,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, int nr_options = 0; int key = -1; char buf[64]; + char script_opt[64]; + int delay_secs = hbt ? hbt->refresh : 0; if (browser == NULL) return -1; @@ -1159,10 +1365,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, int choice = 0, annotate = -2, zoom_dso = -2, zoom_thread = -2, annotate_f = -2, annotate_t = -2, browse_map = -2; + int scripts_comm = -2, scripts_symbol = -2, + scripts_all = -2, switch_data = -2; nr_options = 0; - key = hist_browser__run(browser, ev_name, timer, arg, delay_secs); + key = hist_browser__run(browser, ev_name, hbt); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -1211,6 +1419,14 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, hist_browser__reset(browser); } continue; + case 'r': + if (is_report_browser(hbt)) + goto do_scripts; + continue; + case 's': + if (is_report_browser(hbt)) + goto do_data_switch; + continue; case K_F1: case 'h': case '?': @@ -1229,6 +1445,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "E Expand all callchains\n" "d Zoom into current DSO\n" "t Zoom into current Thread\n" + "r Run available scripts('perf report' only)\n" + "s Switch to another data file in PWD ('perf report' only)\n" "P Print histograms to perf.hist.N\n" "V Verbose (DSO names in callchains, etc)\n" "/ Filter symbol by name"); @@ -1317,6 +1535,28 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, browser->selection->map != NULL && asprintf(&options[nr_options], "Browse map details") > 0) browse_map = nr_options++; + + /* perf script support */ + if (browser->he_selection) { + struct symbol *sym; + + if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]", + browser->he_selection->thread->comm) > 0) + scripts_comm = nr_options++; + + sym = browser->he_selection->ms.sym; + if (sym && sym->namelen && + asprintf(&options[nr_options], "Run scripts for samples of symbol [%s]", + sym->name) > 0) + scripts_symbol = nr_options++; + } + + if (asprintf(&options[nr_options], "Run scripts for all samples") > 0) + scripts_all = nr_options++; + + if (is_report_browser(hbt) && asprintf(&options[nr_options], + "Switch to another data file in PWD") > 0) + switch_data = nr_options++; add_exit_option: options[nr_options++] = (char *)"Exit"; retry_popup_menu: @@ -1334,6 +1574,9 @@ retry_popup_menu: struct hist_entry *he; int err; do_annotate: + if (!objdump_path && perf_session_env__lookup_objdump(env)) + continue; + he = hist_browser__selected_entry(browser); if (he == NULL) continue; @@ -1356,8 +1599,7 @@ do_annotate: * Don't let this be freed, say, by hists__decay_entry. */ he->used = true; - err = hist_entry__tui_annotate(he, evsel->idx, - timer, arg, delay_secs); + err = hist_entry__tui_annotate(he, evsel->idx, hbt); he->used = false; /* * offer option to annotate the other branch source or target @@ -1411,6 +1653,30 @@ zoom_out_thread: hists__filter_by_thread(hists); hist_browser__reset(browser); } + /* perf scripts support */ + else if (choice == scripts_all || choice == scripts_comm || + choice == scripts_symbol) { +do_scripts: + memset(script_opt, 0, 64); + + if (choice == scripts_comm) + sprintf(script_opt, " -c %s ", browser->he_selection->thread->comm); + + if (choice == scripts_symbol) + sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name); + + script_browse(script_opt); + } + /* Switch to another data file */ + else if (choice == switch_data) { +do_data_switch: + if (!switch_data_file()) { + key = K_SWITCH_INPUT_DATA; + break; + } else + ui__warning("Won't switch the data files due to\n" + "no valid data file get selected!\n"); + } } out_free_stack: pstack__delete(fstack); @@ -1424,6 +1690,7 @@ struct perf_evsel_menu { struct ui_browser b; struct perf_evsel *selection; bool lost_events, lost_events_warned; + struct perf_session_env *env; }; static void perf_evsel_menu__write(struct ui_browser *browser, @@ -1442,6 +1709,16 @@ 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) { + struct perf_evsel *pos; + + ev_name = perf_evsel__group_name(evsel); + + for_each_group_member(pos, evsel) { + nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + } + } + nr_events = convert_unit(nr_events, &unit); printed = scnprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events, unit, unit == ' ' ? "" : " ", ev_name); @@ -1466,11 +1743,12 @@ static void perf_evsel_menu__write(struct ui_browser *browser, static int perf_evsel_menu__run(struct perf_evsel_menu *menu, int nr_events, const char *help, - void(*timer)(void *arg), void *arg, int delay_secs) + struct hist_browser_timer *hbt) { struct perf_evlist *evlist = menu->b.priv; struct perf_evsel *pos; const char *ev_name, *title = "Available samples"; + int delay_secs = hbt ? hbt->refresh : 0; int key; if (ui_browser__show(&menu->b, title, @@ -1482,7 +1760,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu, switch (key) { case K_TIMER: - timer(arg); + hbt->timer(hbt->arg); if (!menu->lost_events_warned && menu->lost_events) { ui_browser__warn_lost_events(&menu->b); @@ -1500,12 +1778,12 @@ browse_hists: * Give the calling tool a chance to populate the non * default evsel resorted hists tree. */ - if (timer) - timer(arg); + if (hbt) + hbt->timer(hbt->arg); ev_name = perf_evsel__name(pos); key = perf_evsel__hists_browse(pos, nr_events, help, - ev_name, true, timer, - arg, delay_secs); + ev_name, true, hbt, + menu->env); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -1525,6 +1803,7 @@ browse_hists: "Do you really want to exit?")) continue; /* Fall thru */ + case K_SWITCH_INPUT_DATA: case 'q': case CTRL('c'): goto out; @@ -1551,10 +1830,21 @@ out: return key; } +static bool filter_group_entries(struct ui_browser *self __maybe_unused, + void *entry) +{ + struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); + + if (symbol_conf.event_group && !perf_evsel__is_group_leader(evsel)) + return true; + + return false; +} + static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, - const char *help, - void(*timer)(void *arg), void *arg, - int delay_secs) + int nr_entries, const char *help, + struct hist_browser_timer *hbt, + struct perf_session_env *env) { struct perf_evsel *pos; struct perf_evsel_menu menu = { @@ -1563,9 +1853,11 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, .refresh = ui_browser__list_head_refresh, .seek = ui_browser__list_head_seek, .write = perf_evsel_menu__write, - .nr_entries = evlist->nr_entries, + .filter = filter_group_entries, + .nr_entries = nr_entries, .priv = evlist, }, + .env = env, }; ui_helpline__push("Press ESC to exit"); @@ -1578,23 +1870,37 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, menu.b.width = line_len; } - return perf_evsel_menu__run(&menu, evlist->nr_entries, help, timer, - arg, delay_secs); + return perf_evsel_menu__run(&menu, nr_entries, help, hbt); } int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, - void(*timer)(void *arg), void *arg, - int delay_secs) + struct hist_browser_timer *hbt, + struct perf_session_env *env) { - if (evlist->nr_entries == 1) { + int nr_entries = evlist->nr_entries; + +single_entry: + if (nr_entries == 1) { struct perf_evsel *first = list_entry(evlist->entries.next, struct perf_evsel, node); const char *ev_name = perf_evsel__name(first); - return perf_evsel__hists_browse(first, evlist->nr_entries, help, - ev_name, false, timer, arg, - delay_secs); + + return perf_evsel__hists_browse(first, nr_entries, help, + ev_name, false, hbt, env); + } + + if (symbol_conf.event_group) { + struct perf_evsel *pos; + + nr_entries = 0; + list_for_each_entry(pos, &evlist->entries, node) + if (perf_evsel__is_group_leader(pos)) + nr_entries++; + + if (nr_entries == 1) + goto single_entry; } - return __perf_evlist__tui_browse_hists(evlist, help, - timer, arg, delay_secs); + return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, + hbt, env); } diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c new file mode 100644 index 00000000000..cbbd44b0d93 --- /dev/null +++ b/tools/perf/ui/browsers/scripts.c @@ -0,0 +1,189 @@ +#include <elf.h> +#include <newt.h> +#include <inttypes.h> +#include <sys/ttydefaults.h> +#include <string.h> +#include "../../util/sort.h" +#include "../../util/util.h" +#include "../../util/hist.h" +#include "../../util/debug.h" +#include "../../util/symbol.h" +#include "../browser.h" +#include "../helpline.h" +#include "../libslang.h" + +/* 2048 lines should be enough for a script output */ +#define MAX_LINES 2048 + +/* 160 bytes for one output line */ +#define AVERAGE_LINE_LEN 160 + +struct script_line { + struct list_head node; + char line[AVERAGE_LINE_LEN]; +}; + +struct perf_script_browser { + struct ui_browser b; + struct list_head entries; + const char *script_name; + int nr_lines; +}; + +#define SCRIPT_NAMELEN 128 +#define SCRIPT_MAX_NO 64 +/* + * Usually the full path for a script is: + * /home/username/libexec/perf-core/scripts/python/xxx.py + * /home/username/libexec/perf-core/scripts/perl/xxx.pl + * So 256 should be long enough to contain the full path. + */ +#define SCRIPT_FULLPATH_LEN 256 + +/* + * When success, will copy the full path of the selected script + * into the buffer pointed by script_name, and return 0. + * Return -1 on failure. + */ +static int list_scripts(char *script_name) +{ + char *buf, *names[SCRIPT_MAX_NO], *paths[SCRIPT_MAX_NO]; + int i, num, choice, ret = -1; + + /* Preset the script name to SCRIPT_NAMELEN */ + buf = malloc(SCRIPT_MAX_NO * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN)); + if (!buf) + return ret; + + for (i = 0; i < SCRIPT_MAX_NO; i++) { + names[i] = buf + i * (SCRIPT_NAMELEN + SCRIPT_FULLPATH_LEN); + paths[i] = names[i] + SCRIPT_NAMELEN; + } + + num = find_scripts(names, paths); + if (num > 0) { + choice = ui__popup_menu(num, names); + if (choice < num && choice >= 0) { + strcpy(script_name, paths[choice]); + ret = 0; + } + } + + free(buf); + return ret; +} + +static void script_browser__write(struct ui_browser *browser, + void *entry, int row) +{ + struct script_line *sline = list_entry(entry, struct script_line, node); + bool current_entry = ui_browser__is_current_entry(browser, row); + + ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : + HE_COLORSET_NORMAL); + + slsmg_write_nstring(sline->line, browser->width); +} + +static int script_browser__run(struct perf_script_browser *self) +{ + int key; + + if (ui_browser__show(&self->b, self->script_name, + "Press <- or ESC to exit") < 0) + return -1; + + while (1) { + key = ui_browser__run(&self->b, 0); + + /* We can add some special key handling here if needed */ + break; + } + + ui_browser__hide(&self->b); + return key; +} + + +int script_browse(const char *script_opt) +{ + char cmd[SCRIPT_FULLPATH_LEN*2], script_name[SCRIPT_FULLPATH_LEN]; + char *line = NULL; + size_t len = 0; + ssize_t retlen; + int ret = -1, nr_entries = 0; + FILE *fp; + void *buf; + struct script_line *sline; + + struct perf_script_browser script = { + .b = { + .refresh = ui_browser__list_head_refresh, + .seek = ui_browser__list_head_seek, + .write = script_browser__write, + }, + .script_name = script_name, + }; + + INIT_LIST_HEAD(&script.entries); + + /* Save each line of the output in one struct script_line object. */ + buf = zalloc((sizeof(*sline)) * MAX_LINES); + if (!buf) + return -1; + sline = buf; + + memset(script_name, 0, SCRIPT_FULLPATH_LEN); + if (list_scripts(script_name)) + goto exit; + + sprintf(cmd, "perf script -s %s ", script_name); + + if (script_opt) + strcat(cmd, script_opt); + + if (input_name) { + strcat(cmd, " -i "); + strcat(cmd, input_name); + } + + strcat(cmd, " 2>&1"); + + fp = popen(cmd, "r"); + if (!fp) + goto exit; + + while ((retlen = getline(&line, &len, fp)) != -1) { + strncpy(sline->line, line, AVERAGE_LINE_LEN); + + /* If one output line is very large, just cut it short */ + if (retlen >= AVERAGE_LINE_LEN) { + sline->line[AVERAGE_LINE_LEN - 1] = '\0'; + sline->line[AVERAGE_LINE_LEN - 2] = '\n'; + } + list_add_tail(&sline->node, &script.entries); + + if (script.b.width < retlen) + script.b.width = retlen; + + if (nr_entries++ >= MAX_LINES - 1) + break; + sline++; + } + + if (script.b.width > AVERAGE_LINE_LEN) + script.b.width = AVERAGE_LINE_LEN; + + if (line) + free(line); + pclose(fp); + + script.nr_lines = nr_entries; + script.b.nr_entries = nr_entries; + script.b.entries = &script.entries; + + ret = script_browser__run(&script); +exit: + free(buf); + return ret; +} diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c new file mode 100644 index 00000000000..7d8dc581a54 --- /dev/null +++ b/tools/perf/ui/gtk/annotate.c @@ -0,0 +1,229 @@ +#include "gtk.h" +#include "util/debug.h" +#include "util/annotate.h" +#include "ui/helpline.h" + + +enum { + ANN_COL__PERCENT, + ANN_COL__OFFSET, + ANN_COL__LINE, + + MAX_ANN_COLS +}; + +static const char *const col_names[] = { + "Overhead", + "Offset", + "Line" +}; + +static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, + struct disasm_line *dl, int evidx) +{ + struct sym_hist *symhist; + double percent = 0.0; + const char *markup; + int ret = 0; + + strcpy(buf, ""); + + if (dl->offset == (s64) -1) + return 0; + + symhist = annotation__histogram(symbol__annotation(sym), evidx); + if (!symhist->addr[dl->offset]) + return 0; + + percent = 100.0 * symhist->addr[dl->offset] / symhist->sum; + + markup = perf_gtk__get_percent_color(percent); + if (markup) + ret += scnprintf(buf, size, "%s", markup); + ret += scnprintf(buf + ret, size - ret, "%6.2f%%", percent); + if (markup) + ret += scnprintf(buf + ret, size - ret, "</span>"); + + return ret; +} + +static int perf_gtk__get_offset(char *buf, size_t size, struct symbol *sym, + struct map *map, struct disasm_line *dl) +{ + u64 start = map__rip_2objdump(map, sym->start); + + strcpy(buf, ""); + + if (dl->offset == (s64) -1) + return 0; + + return scnprintf(buf, size, "%"PRIx64, start + dl->offset); +} + +static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl) +{ + int ret = 0; + char *line = g_markup_escape_text(dl->line, -1); + const char *markup = "<span fgcolor='gray'>"; + + strcpy(buf, ""); + + if (!line) + return 0; + + if (dl->offset != (s64) -1) + markup = NULL; + + if (markup) + ret += scnprintf(buf, size, "%s", markup); + ret += scnprintf(buf + ret, size - ret, "%s", line); + if (markup) + ret += scnprintf(buf + ret, size - ret, "</span>"); + + g_free(line); + return ret; +} + +static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, + struct map *map, int evidx, + struct hist_browser_timer *hbt __maybe_unused) +{ + struct disasm_line *pos, *n; + struct annotation *notes; + GType col_types[MAX_ANN_COLS]; + GtkCellRenderer *renderer; + GtkListStore *store; + GtkWidget *view; + int i; + char s[512]; + + notes = symbol__annotation(sym); + + for (i = 0; i < MAX_ANN_COLS; i++) { + col_types[i] = G_TYPE_STRING; + } + store = gtk_list_store_newv(MAX_ANN_COLS, col_types); + + view = gtk_tree_view_new(); + renderer = gtk_cell_renderer_text_new(); + + for (i = 0; i < MAX_ANN_COLS; i++) { + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, col_names[i], renderer, "markup", + i, NULL); + } + + gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); + g_object_unref(GTK_TREE_MODEL(store)); + + list_for_each_entry(pos, ¬es->src->source, node) { + GtkTreeIter iter; + + gtk_list_store_append(store, &iter); + + if (perf_gtk__get_percent(s, sizeof(s), sym, pos, evidx)) + 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); + if (perf_gtk__get_line(s, sizeof(s), pos)) + gtk_list_store_set(store, &iter, ANN_COL__LINE, s, -1); + } + + gtk_container_add(GTK_CONTAINER(window), view); + + list_for_each_entry_safe(pos, n, ¬es->src->source, node) { + list_del(&pos->node); + disasm_line__free(pos); + } + + return 0; +} + +int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx, + struct hist_browser_timer *hbt) +{ + GtkWidget *window; + GtkWidget *notebook; + GtkWidget *scrolled_window; + GtkWidget *tab_label; + + if (map->dso->annotate_warned) + return -1; + + if (symbol__annotate(sym, map, 0) < 0) { + ui__error("%s", ui_helpline__current); + return -1; + } + + if (perf_gtk__is_active_context(pgctx)) { + window = pgctx->main_window; + notebook = pgctx->notebook; + } else { + GtkWidget *vbox; + GtkWidget *infobar; + GtkWidget *statbar; + + signal(SIGSEGV, perf_gtk__signal); + signal(SIGFPE, perf_gtk__signal); + signal(SIGINT, perf_gtk__signal); + signal(SIGQUIT, perf_gtk__signal); + signal(SIGTERM, perf_gtk__signal); + + window = gtk_window_new(GTK_WINDOW_TOPLEVEL); + gtk_window_set_title(GTK_WINDOW(window), "perf annotate"); + + g_signal_connect(window, "delete_event", gtk_main_quit, NULL); + + pgctx = perf_gtk__activate_context(window); + if (!pgctx) + return -1; + + vbox = gtk_vbox_new(FALSE, 0); + notebook = gtk_notebook_new(); + pgctx->notebook = notebook; + + gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); + + infobar = perf_gtk__setup_info_bar(); + if (infobar) { + gtk_box_pack_start(GTK_BOX(vbox), infobar, + FALSE, FALSE, 0); + } + + statbar = perf_gtk__setup_statusbar(); + gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); + + gtk_container_add(GTK_CONTAINER(window), vbox); + } + + scrolled_window = gtk_scrolled_window_new(NULL, NULL); + tab_label = gtk_label_new(sym->name); + + gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window), + GTK_POLICY_AUTOMATIC, + GTK_POLICY_AUTOMATIC); + + gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, + tab_label); + + perf_gtk__annotate_symbol(scrolled_window, sym, map, evidx, hbt); + return 0; +} + +void perf_gtk__show_annotations(void) +{ + GtkWidget *window; + + if (!perf_gtk__is_active_context(pgctx)) + return; + + window = pgctx->main_window; + gtk_widget_show_all(window); + + perf_gtk__resize_window(window); + gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); + + gtk_main(); + + perf_gtk__deactivate_context(&pgctx); +} diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index 4125c628411..c95012cdb43 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -8,15 +8,13 @@ #include <signal.h> -#define MAX_COLUMNS 32 - -static void perf_gtk__signal(int sig) +void perf_gtk__signal(int sig) { perf_gtk__exit(false); psignal(sig, "perf"); } -static void perf_gtk__resize_window(GtkWidget *window) +void perf_gtk__resize_window(GtkWidget *window) { GdkRectangle rect; GdkScreen *screen; @@ -36,7 +34,7 @@ static void perf_gtk__resize_window(GtkWidget *window) gtk_window_resize(GTK_WINDOW(window), width, height); } -static const char *perf_gtk__get_percent_color(double percent) +const char *perf_gtk__get_percent_color(double percent) { if (percent >= MIN_RED) return "<span fgcolor='red'>"; @@ -45,155 +43,8 @@ static const char *perf_gtk__get_percent_color(double percent) return NULL; } -#define HPP__COLOR_FN(_name, _field) \ -static int perf_gtk__hpp_color_ ## _name(struct perf_hpp *hpp, \ - struct hist_entry *he) \ -{ \ - struct hists *hists = he->hists; \ - double percent = 100.0 * he->stat._field / hists->stats.total_period; \ - const char *markup; \ - int ret = 0; \ - \ - markup = perf_gtk__get_percent_color(percent); \ - if (markup) \ - ret += scnprintf(hpp->buf, hpp->size, "%s", markup); \ - ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%6.2f%%", percent); \ - if (markup) \ - ret += scnprintf(hpp->buf + ret, hpp->size - ret, "</span>"); \ - \ - return ret; \ -} - -HPP__COLOR_FN(overhead, period) -HPP__COLOR_FN(overhead_sys, period_sys) -HPP__COLOR_FN(overhead_us, period_us) -HPP__COLOR_FN(overhead_guest_sys, period_guest_sys) -HPP__COLOR_FN(overhead_guest_us, period_guest_us) - -#undef HPP__COLOR_FN - -void perf_gtk__init_hpp(void) -{ - perf_hpp__init(); - - perf_hpp__format[PERF_HPP__OVERHEAD].color = - perf_gtk__hpp_color_overhead; - perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = - perf_gtk__hpp_color_overhead_sys; - perf_hpp__format[PERF_HPP__OVERHEAD_US].color = - perf_gtk__hpp_color_overhead_us; - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color = - perf_gtk__hpp_color_overhead_guest_sys; - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color = - perf_gtk__hpp_color_overhead_guest_us; -} - -static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) -{ - GType col_types[MAX_COLUMNS]; - GtkCellRenderer *renderer; - struct sort_entry *se; - GtkListStore *store; - struct rb_node *nd; - GtkWidget *view; - int i, col_idx; - int nr_cols; - char s[512]; - - struct perf_hpp hpp = { - .buf = s, - .size = sizeof(s), - }; - - nr_cols = 0; - - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - - col_types[nr_cols++] = G_TYPE_STRING; - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - col_types[nr_cols++] = G_TYPE_STRING; - } - - store = gtk_list_store_newv(nr_cols, col_types); - - view = gtk_tree_view_new(); - - renderer = gtk_cell_renderer_text_new(); - - col_idx = 0; - - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - - perf_hpp__format[i].header(&hpp); - - gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), - -1, s, - renderer, "markup", - col_idx++, NULL); - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), - -1, se->se_header, - renderer, "text", - col_idx++, NULL); - } - - gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); - - g_object_unref(GTK_TREE_MODEL(store)); - - 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; - - if (h->filtered) - continue; - - gtk_list_store_append(store, &iter); - - col_idx = 0; - - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - - if (perf_hpp__format[i].color) - perf_hpp__format[i].color(&hpp, h); - else - perf_hpp__format[i].entry(&hpp, h); - - gtk_list_store_set(store, &iter, col_idx++, s, -1); - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - se->se_snprintf(h, s, ARRAY_SIZE(s), - hists__col_len(hists, se->se_width_idx)); - - gtk_list_store_set(store, &iter, col_idx++, s, -1); - } - } - - gtk_container_add(GTK_CONTAINER(window), view); -} - #ifdef HAVE_GTK_INFO_BAR -static GtkWidget *perf_gtk__setup_info_bar(void) +GtkWidget *perf_gtk__setup_info_bar(void) { GtkWidget *info_bar; GtkWidget *label; @@ -220,7 +71,7 @@ static GtkWidget *perf_gtk__setup_info_bar(void) } #endif -static GtkWidget *perf_gtk__setup_statusbar(void) +GtkWidget *perf_gtk__setup_statusbar(void) { GtkWidget *stbar; unsigned ctxid; @@ -234,81 +85,3 @@ static GtkWidget *perf_gtk__setup_statusbar(void) return stbar; } - -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, - const char *help, - void (*timer) (void *arg)__maybe_unused, - void *arg __maybe_unused, - int delay_secs __maybe_unused) -{ - struct perf_evsel *pos; - GtkWidget *vbox; - GtkWidget *notebook; - GtkWidget *info_bar; - GtkWidget *statbar; - GtkWidget *window; - - signal(SIGSEGV, perf_gtk__signal); - signal(SIGFPE, perf_gtk__signal); - signal(SIGINT, perf_gtk__signal); - signal(SIGQUIT, perf_gtk__signal); - signal(SIGTERM, perf_gtk__signal); - - window = gtk_window_new(GTK_WINDOW_TOPLEVEL); - - gtk_window_set_title(GTK_WINDOW(window), "perf report"); - - g_signal_connect(window, "delete_event", gtk_main_quit, NULL); - - pgctx = perf_gtk__activate_context(window); - if (!pgctx) - return -1; - - vbox = gtk_vbox_new(FALSE, 0); - - notebook = gtk_notebook_new(); - - list_for_each_entry(pos, &evlist->entries, node) { - struct hists *hists = &pos->hists; - const char *evname = perf_evsel__name(pos); - GtkWidget *scrolled_window; - GtkWidget *tab_label; - - scrolled_window = gtk_scrolled_window_new(NULL, NULL); - - gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window), - GTK_POLICY_AUTOMATIC, - GTK_POLICY_AUTOMATIC); - - perf_gtk__show_hists(scrolled_window, hists); - - tab_label = gtk_label_new(evname); - - gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label); - } - - gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); - - info_bar = perf_gtk__setup_info_bar(); - if (info_bar) - gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0); - - statbar = perf_gtk__setup_statusbar(); - gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); - - gtk_container_add(GTK_CONTAINER(window), vbox); - - gtk_widget_show_all(window); - - perf_gtk__resize_window(window); - - gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); - - ui_helpline__push(help); - - gtk_main(); - - perf_gtk__deactivate_context(&pgctx); - - return 0; -} diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 687af0bba18..3d96785ef15 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -10,6 +10,7 @@ struct perf_gtk_context { GtkWidget *main_window; + GtkWidget *notebook; #ifdef HAVE_GTK_INFO_BAR GtkWidget *info_bar; @@ -30,9 +31,17 @@ struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window); int perf_gtk__deactivate_context(struct perf_gtk_context **ctx); void perf_gtk__init_helpline(void); +void perf_gtk__init_progress(void); void perf_gtk__init_hpp(void); -#ifndef HAVE_GTK_INFO_BAR +void perf_gtk__signal(int sig); +void perf_gtk__resize_window(GtkWidget *window); +const char *perf_gtk__get_percent_color(double percent); +GtkWidget *perf_gtk__setup_statusbar(void); + +#ifdef HAVE_GTK_INFO_BAR +GtkWidget *perf_gtk__setup_info_bar(void); +#else static inline GtkWidget *perf_gtk__setup_info_bar(void) { return NULL; diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c index 5db4432ff12..3388cbd1218 100644 --- a/tools/perf/ui/gtk/helpline.c +++ b/tools/perf/ui/gtk/helpline.c @@ -24,17 +24,7 @@ static void gtk_helpline_push(const char *msg) pgctx->statbar_ctx_id, msg); } -static struct ui_helpline gtk_helpline_fns = { - .pop = gtk_helpline_pop, - .push = gtk_helpline_push, -}; - -void perf_gtk__init_helpline(void) -{ - helpline_fns = >k_helpline_fns; -} - -int perf_gtk__show_helpline(const char *fmt, va_list ap) +static int gtk_helpline_show(const char *fmt, va_list ap) { int ret; char *ptr; @@ -54,3 +44,14 @@ int perf_gtk__show_helpline(const char *fmt, va_list ap) return ret; } + +static struct ui_helpline gtk_helpline_fns = { + .pop = gtk_helpline_pop, + .push = gtk_helpline_push, + .show = gtk_helpline_show, +}; + +void perf_gtk__init_helpline(void) +{ + helpline_fns = >k_helpline_fns; +} diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c new file mode 100644 index 00000000000..1e764a8ad25 --- /dev/null +++ b/tools/perf/ui/gtk/hists.c @@ -0,0 +1,312 @@ +#include "../evlist.h" +#include "../cache.h" +#include "../evsel.h" +#include "../sort.h" +#include "../hist.h" +#include "../helpline.h" +#include "gtk.h" + +#define MAX_COLUMNS 32 + +static int __percent_color_snprintf(char *buf, size_t size, double percent) +{ + int ret = 0; + const char *markup; + + markup = perf_gtk__get_percent_color(percent); + if (markup) + ret += scnprintf(buf, size, markup); + + ret += scnprintf(buf + ret, size - ret, " %6.2f%%", percent); + + if (markup) + ret += scnprintf(buf + ret, size - ret, "</span>"); + + return ret; +} + + +static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, + u64 (*get_field)(struct hist_entry *)) +{ + int ret; + double percent = 0.0; + struct hists *hists = he->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) { + 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) { + u64 period = get_field(pair); + u64 total = pair->hists->stats.total_period; + + evsel = hists_to_evsel(pair->hists); + idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members in the middle which + * have no sample + */ + ret += __percent_color_snprintf(hpp->buf + ret, + hpp->size - ret, + 0.0); + } + + percent = 100.0 * period / total; + ret += __percent_color_snprintf(hpp->buf + ret, + hpp->size - ret, + percent); + + prev_idx = perf_evsel__group_idx(evsel); + } + + idx_delta = nr_members - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members at last which have no sample + */ + ret += __percent_color_snprintf(hpp->buf + ret, + hpp->size - ret, + 0.0); + } + } + return ret; +} + +#define __HPP_COLOR_PERCENT_FN(_type, _field) \ +static u64 he_get_##_field(struct hist_entry *he) \ +{ \ + return he->stat._field; \ +} \ + \ +static int perf_gtk__hpp_color_##_type(struct perf_hpp *hpp, \ + struct hist_entry *he) \ +{ \ + return __hpp__color_fmt(hpp, he, he_get_##_field); \ +} + +__HPP_COLOR_PERCENT_FN(overhead, period) +__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys) +__HPP_COLOR_PERCENT_FN(overhead_us, period_us) +__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys) +__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us) + +#undef __HPP_COLOR_PERCENT_FN + + +void perf_gtk__init_hpp(void) +{ + perf_hpp__column_enable(PERF_HPP__OVERHEAD); + + perf_hpp__init(); + + perf_hpp__format[PERF_HPP__OVERHEAD].color = + perf_gtk__hpp_color_overhead; + perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = + perf_gtk__hpp_color_overhead_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_US].color = + perf_gtk__hpp_color_overhead_us; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color = + perf_gtk__hpp_color_overhead_guest_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color = + perf_gtk__hpp_color_overhead_guest_us; +} + +static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) +{ + struct perf_hpp_fmt *fmt; + GType col_types[MAX_COLUMNS]; + GtkCellRenderer *renderer; + struct sort_entry *se; + GtkListStore *store; + struct rb_node *nd; + GtkWidget *view; + int col_idx; + int nr_cols; + char s[512]; + + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + .ptr = hists_to_evsel(hists), + }; + + nr_cols = 0; + + perf_hpp__for_each_format(fmt) + col_types[nr_cols++] = G_TYPE_STRING; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + + col_types[nr_cols++] = G_TYPE_STRING; + } + + store = gtk_list_store_newv(nr_cols, col_types); + + view = gtk_tree_view_new(); + + renderer = gtk_cell_renderer_text_new(); + + col_idx = 0; + + perf_hpp__for_each_format(fmt) { + fmt->header(&hpp); + + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, ltrim(s), + renderer, "markup", + col_idx++, NULL); + } + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, se->se_header, + renderer, "text", + col_idx++, NULL); + } + + gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); + + g_object_unref(GTK_TREE_MODEL(store)); + + 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; + + if (h->filtered) + continue; + + gtk_list_store_append(store, &iter); + + col_idx = 0; + + perf_hpp__for_each_format(fmt) { + if (fmt->color) + fmt->color(&hpp, h); + else + fmt->entry(&hpp, h); + + gtk_list_store_set(store, &iter, col_idx++, s, -1); + } + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + + se->se_snprintf(h, s, ARRAY_SIZE(s), + hists__col_len(hists, se->se_width_idx)); + + gtk_list_store_set(store, &iter, col_idx++, s, -1); + } + } + + gtk_container_add(GTK_CONTAINER(window), view); +} + +int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, + const char *help, + struct hist_browser_timer *hbt __maybe_unused) +{ + struct perf_evsel *pos; + GtkWidget *vbox; + GtkWidget *notebook; + GtkWidget *info_bar; + GtkWidget *statbar; + GtkWidget *window; + + signal(SIGSEGV, perf_gtk__signal); + signal(SIGFPE, perf_gtk__signal); + signal(SIGINT, perf_gtk__signal); + signal(SIGQUIT, perf_gtk__signal); + signal(SIGTERM, perf_gtk__signal); + + window = gtk_window_new(GTK_WINDOW_TOPLEVEL); + + gtk_window_set_title(GTK_WINDOW(window), "perf report"); + + g_signal_connect(window, "delete_event", gtk_main_quit, NULL); + + pgctx = perf_gtk__activate_context(window); + if (!pgctx) + return -1; + + vbox = gtk_vbox_new(FALSE, 0); + + notebook = gtk_notebook_new(); + + gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); + + info_bar = perf_gtk__setup_info_bar(); + if (info_bar) + gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0); + + statbar = perf_gtk__setup_statusbar(); + gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); + + gtk_container_add(GTK_CONTAINER(window), vbox); + + list_for_each_entry(pos, &evlist->entries, node) { + struct hists *hists = &pos->hists; + const char *evname = perf_evsel__name(pos); + GtkWidget *scrolled_window; + GtkWidget *tab_label; + char buf[512]; + size_t size = sizeof(buf); + + if (symbol_conf.event_group) { + if (!perf_evsel__is_group_leader(pos)) + continue; + + if (pos->nr_members > 1) { + perf_evsel__group_desc(pos, buf, size); + evname = buf; + } + } + + scrolled_window = gtk_scrolled_window_new(NULL, NULL); + + gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window), + GTK_POLICY_AUTOMATIC, + GTK_POLICY_AUTOMATIC); + + perf_gtk__show_hists(scrolled_window, hists); + + tab_label = gtk_label_new(evname); + + gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label); + } + + gtk_widget_show_all(window); + + perf_gtk__resize_window(window); + + gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); + + ui_helpline__push(help); + + gtk_main(); + + perf_gtk__deactivate_context(&pgctx); + + return 0; +} diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c new file mode 100644 index 00000000000..482bcf3df9b --- /dev/null +++ b/tools/perf/ui/gtk/progress.c @@ -0,0 +1,59 @@ +#include <inttypes.h> + +#include "gtk.h" +#include "../progress.h" +#include "util.h" + +static GtkWidget *dialog; +static GtkWidget *progress; + +static void gtk_progress_update(u64 curr, u64 total, const char *title) +{ + double fraction = total ? 1.0 * curr / total : 0.0; + char buf[1024]; + + if (dialog == NULL) { + GtkWidget *vbox = gtk_vbox_new(TRUE, 5); + GtkWidget *label = gtk_label_new(title); + + dialog = gtk_window_new(GTK_WINDOW_TOPLEVEL); + progress = gtk_progress_bar_new(); + + gtk_box_pack_start(GTK_BOX(vbox), label, TRUE, FALSE, 3); + gtk_box_pack_start(GTK_BOX(vbox), progress, TRUE, TRUE, 3); + + gtk_container_add(GTK_CONTAINER(dialog), vbox); + + gtk_window_set_title(GTK_WINDOW(dialog), "perf"); + gtk_window_resize(GTK_WINDOW(dialog), 300, 80); + gtk_window_set_position(GTK_WINDOW(dialog), GTK_WIN_POS_CENTER); + + gtk_widget_show_all(dialog); + } + + gtk_progress_bar_set_fraction(GTK_PROGRESS_BAR(progress), fraction); + snprintf(buf, sizeof(buf), "%"PRIu64" / %"PRIu64, curr, total); + gtk_progress_bar_set_text(GTK_PROGRESS_BAR(progress), buf); + + /* we didn't call gtk_main yet, so do it manually */ + while (gtk_events_pending()) + gtk_main_iteration(); +} + +static void gtk_progress_finish(void) +{ + /* this will also destroy all of its children */ + gtk_widget_destroy(dialog); + + dialog = NULL; +} + +static struct ui_progress gtk_progress_fns = { + .update = gtk_progress_update, + .finish = gtk_progress_finish, +}; + +void perf_gtk__init_progress(void) +{ + progress_fns = >k_progress_fns; +} diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c index 3c4c6ef7828..6c2dd2e423f 100644 --- a/tools/perf/ui/gtk/setup.c +++ b/tools/perf/ui/gtk/setup.c @@ -8,7 +8,9 @@ int perf_gtk__init(void) { perf_error__register(&perf_gtk_eops); perf_gtk__init_helpline(); + perf_gtk__init_progress(); perf_gtk__init_hpp(); + return gtk_init_check(NULL, NULL) ? 0 : -1; } diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c index ccb046aac98..c06942a41c7 100644 --- a/tools/perf/ui/gtk/util.c +++ b/tools/perf/ui/gtk/util.c @@ -111,14 +111,3 @@ struct perf_error_ops perf_gtk_eops = { .warning = perf_gtk__warning_statusbar, #endif }; - -/* - * FIXME: Functions below should be implemented properly. - * For now, just add stubs for NO_NEWT=1 build. - */ -#ifndef NEWT_SUPPORT -void ui_progress__update(u64 curr __maybe_unused, u64 total __maybe_unused, - const char *title __maybe_unused) -{ -} -#endif diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c index a49bcf3c190..700fb3cfa1c 100644 --- a/tools/perf/ui/helpline.c +++ b/tools/perf/ui/helpline.c @@ -16,9 +16,16 @@ static void nop_helpline__push(const char *msg __maybe_unused) { } +static int nop_helpline__show(const char *fmt __maybe_unused, + va_list ap __maybe_unused) +{ + return 0; +} + static struct ui_helpline default_helpline_fns = { .pop = nop_helpline__pop, .push = nop_helpline__push, + .show = nop_helpline__show, }; struct ui_helpline *helpline_fns = &default_helpline_fns; @@ -59,3 +66,8 @@ void ui_helpline__puts(const char *msg) ui_helpline__pop(); ui_helpline__push(msg); } + +int ui_helpline__vshow(const char *fmt, va_list ap) +{ + return helpline_fns->show(fmt, ap); +} diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h index baa28a4d16b..46181f4fc07 100644 --- a/tools/perf/ui/helpline.h +++ b/tools/perf/ui/helpline.h @@ -9,6 +9,7 @@ struct ui_helpline { void (*pop)(void); void (*push)(const char *msg); + int (*show)(const char *fmt, va_list ap); }; extern struct ui_helpline *helpline_fns; @@ -20,28 +21,9 @@ void ui_helpline__push(const char *msg); void ui_helpline__vpush(const char *fmt, va_list ap); void ui_helpline__fpush(const char *fmt, ...); void ui_helpline__puts(const char *msg); +int ui_helpline__vshow(const char *fmt, va_list ap); extern char ui_helpline__current[512]; - -#ifdef NEWT_SUPPORT extern char ui_helpline__last_msg[]; -int ui_helpline__show_help(const char *format, va_list ap); -#else -static inline int ui_helpline__show_help(const char *format __maybe_unused, - va_list ap __maybe_unused) -{ - return 0; -} -#endif /* NEWT_SUPPORT */ - -#ifdef GTK2_SUPPORT -int perf_gtk__show_helpline(const char *format, va_list ap); -#else -static inline int perf_gtk__show_helpline(const char *format __maybe_unused, - va_list ap __maybe_unused) -{ - return 0; -} -#endif /* GTK2_SUPPORT */ #endif /* _PERF_UI_HELPLINE_H_ */ diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index f5a1e4f6526..d671e63aa35 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -3,151 +3,163 @@ #include "../util/hist.h" #include "../util/util.h" #include "../util/sort.h" - +#include "../util/evsel.h" /* hist period print (hpp) functions */ -static int hpp__header_overhead(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "Overhead"); -} -static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused) -{ - return 8; -} +typedef int (*hpp_snprint_fn)(char *buf, size_t size, const char *fmt, ...); -static int hpp__color_overhead(struct perf_hpp *hpp, struct hist_entry *he) +static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + u64 (*get_field)(struct hist_entry *), + const char *fmt, hpp_snprint_fn print_fn, + bool fmt_percent) { + int ret; struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period / hists->stats.total_period; - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); -} + if (fmt_percent) { + double percent = 0.0; -static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%"; + if (hists->stats.total_period) + percent = 100.0 * get_field(he) / + hists->stats.total_period; - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} + ret = print_fn(hpp->buf, hpp->size, fmt, percent); + } else + ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he)); -static int hpp__header_overhead_sys(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; + if (symbol_conf.event_group) { + int prev_idx, idx_delta; + struct perf_evsel *evsel = hists_to_evsel(hists); + struct hist_entry *pair; + int nr_members = evsel->nr_members; - return scnprintf(hpp->buf, hpp->size, fmt, "sys"); -} + if (nr_members <= 1) + return ret; -static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused) -{ - return 7; -} + prev_idx = perf_evsel__group_idx(evsel); -static int hpp__color_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_sys / hists->stats.total_period; + list_for_each_entry(pair, &he->pairs.head, pairs.node) { + u64 period = get_field(pair); + u64 total = pair->hists->stats.total_period; - return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); -} + if (!total) + continue; -static int hpp__entry_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_sys / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; + evsel = hists_to_evsel(pair->hists); + idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} + while (idx_delta--) { + /* + * zero-fill group members in the middle which + * have no sample + */ + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, 0); + } -static int hpp__header_overhead_us(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "user"); -} + if (fmt_percent) + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, 100.0 * period / total); + else + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, period); -static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused) -{ - return 7; -} - -static int hpp__color_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_us / hists->stats.total_period; - - return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); -} - -static int hpp__entry_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_us / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; - - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} - -static int hpp__header_overhead_guest_sys(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "guest sys"); -} - -static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __maybe_unused) -{ - return 9; -} - -static int hpp__color_overhead_guest_sys(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period; - - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); -} - -static int hpp__entry_overhead_guest_sys(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; + prev_idx = perf_evsel__group_idx(evsel); + } - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} + idx_delta = nr_members - prev_idx - 1; -static int hpp__header_overhead_guest_us(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "guest usr"); -} - -static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __maybe_unused) -{ - return 9; + while (idx_delta--) { + /* + * zero-fill group members at last which have no sample + */ + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, 0); + } + } + return ret; } -static int hpp__color_overhead_guest_us(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period; - - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); -} +#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ +static int hpp__header_##_type(struct perf_hpp *hpp) \ +{ \ + int len = _min_width; \ + \ + if (symbol_conf.event_group) { \ + struct perf_evsel *evsel = hpp->ptr; \ + \ + len = max(len, evsel->nr_members * _unit_width); \ + } \ + return scnprintf(hpp->buf, hpp->size, "%*s", len, _str); \ +} + +#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +static int hpp__width_##_type(struct perf_hpp *hpp __maybe_unused) \ +{ \ + int len = _min_width; \ + \ + if (symbol_conf.event_group) { \ + struct perf_evsel *evsel = hpp->ptr; \ + \ + len = max(len, evsel->nr_members * _unit_width); \ + } \ + return len; \ +} + +#define __HPP_COLOR_PERCENT_FN(_type, _field) \ +static u64 he_get_##_field(struct hist_entry *he) \ +{ \ + return he->stat._field; \ +} \ + \ +static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ + (hpp_snprint_fn)percent_color_snprintf, true); \ +} + +#define __HPP_ENTRY_PERCENT_FN(_type, _field) \ +static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ + return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ + scnprintf, true); \ +} + +#define __HPP_ENTRY_RAW_FN(_type, _field) \ +static u64 he_get_raw_##_field(struct hist_entry *he) \ +{ \ + return he->stat._field; \ +} \ + \ +static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64; \ + return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \ +} + +#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width) \ +__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ +__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +__HPP_COLOR_PERCENT_FN(_type, _field) \ +__HPP_ENTRY_PERCENT_FN(_type, _field) + +#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width) \ +__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ +__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +__HPP_ENTRY_RAW_FN(_type, _field) + + +HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8) +HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8) +HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8) +HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8) +HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8) + +HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12) +HPP_RAW_FNS(period, "Period", period, 12, 12) -static int hpp__entry_overhead_guest_us(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; - - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} static int hpp__header_baseline(struct perf_hpp *hpp) { @@ -161,7 +173,7 @@ static int hpp__width_baseline(struct perf_hpp *hpp __maybe_unused) static double baseline_percent(struct hist_entry *he) { - struct hist_entry *pair = he->pair; + struct hist_entry *pair = hist_entry__next_pair(he); struct hists *pair_hists = pair ? pair->hists : NULL; double percent = 0.0; @@ -179,7 +191,10 @@ static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he) { double percent = baseline_percent(he); - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); + if (hist_entry__has_pairs(he) || symbol_conf.field_sep) + return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); + else + return scnprintf(hpp->buf, hpp->size, " "); } static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he) @@ -187,45 +202,31 @@ static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he) double percent = baseline_percent(he); const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%"; - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} - -static int hpp__header_samples(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%11s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Samples"); -} - -static int hpp__width_samples(struct perf_hpp *hpp __maybe_unused) -{ - return 11; + if (hist_entry__has_pairs(he) || symbol_conf.field_sep) + return scnprintf(hpp->buf, hpp->size, fmt, percent); + else + return scnprintf(hpp->buf, hpp->size, " "); } -static int hpp__entry_samples(struct perf_hpp *hpp, struct hist_entry *he) -{ - const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%11" PRIu64; - - return scnprintf(hpp->buf, hpp->size, fmt, he->stat.nr_events); -} - -static int hpp__header_period(struct perf_hpp *hpp) +static int hpp__header_period_baseline(struct perf_hpp *hpp) { const char *fmt = symbol_conf.field_sep ? "%s" : "%12s"; - return scnprintf(hpp->buf, hpp->size, fmt, "Period"); + return scnprintf(hpp->buf, hpp->size, fmt, "Period Base"); } -static int hpp__width_period(struct perf_hpp *hpp __maybe_unused) +static int hpp__width_period_baseline(struct perf_hpp *hpp __maybe_unused) { return 12; } -static int hpp__entry_period(struct perf_hpp *hpp, struct hist_entry *he) +static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *he) { + struct hist_entry *pair = hist_entry__next_pair(he); + u64 period = pair ? pair->stat.period : 0; const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64; - return scnprintf(hpp->buf, hpp->size, fmt, he->stat.period); + return scnprintf(hpp->buf, hpp->size, fmt, period); } static int hpp__header_delta(struct perf_hpp *hpp) @@ -242,104 +243,188 @@ static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused) static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he) { - struct hist_entry *pair = he->pair; - struct hists *pair_hists = pair ? pair->hists : NULL; - struct hists *hists = he->hists; - u64 old_total, new_total; - double old_percent = 0, new_percent = 0; - double diff; + struct hist_entry *pair = hist_entry__next_pair(he); const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s"; char buf[32] = " "; + double diff = 0.0; - old_total = pair_hists ? pair_hists->stats.total_period : 0; - if (old_total > 0 && pair) - old_percent = 100.0 * pair->stat.period / old_total; - - new_total = hists->stats.total_period; - if (new_total > 0) - new_percent = 100.0 * he->stat.period / new_total; + if (pair) { + if (he->diff.computed) + diff = he->diff.period_ratio_delta; + else + diff = perf_diff__compute_delta(he, pair); + } else + diff = perf_diff__period_percent(he, he->stat.period); - diff = new_percent - old_percent; if (fabs(diff) >= 0.01) scnprintf(buf, sizeof(buf), "%+4.2F%%", diff); return scnprintf(hpp->buf, hpp->size, fmt, buf); } -static int hpp__header_displ(struct perf_hpp *hpp) +static int hpp__header_ratio(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Ratio"); +} + +static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused) +{ + return 14; +} + +static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he) +{ + struct hist_entry *pair = hist_entry__next_pair(he); + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; + char buf[32] = " "; + double ratio = 0.0; + + if (pair) { + if (he->diff.computed) + ratio = he->diff.period_ratio; + else + ratio = perf_diff__compute_ratio(he, pair); + } + + if (ratio > 0.0) + scnprintf(buf, sizeof(buf), "%+14.6F", ratio); + + return scnprintf(hpp->buf, hpp->size, fmt, buf); +} + +static int hpp__header_wdiff(struct perf_hpp *hpp) { - return scnprintf(hpp->buf, hpp->size, "Displ."); + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Weighted diff"); } -static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused) +static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused) { - return 6; + return 14; } -static int hpp__entry_displ(struct perf_hpp *hpp, - struct hist_entry *he) +static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he) { - struct hist_entry *pair = he->pair; - long displacement = pair ? pair->position - he->position : 0; - const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s"; + struct hist_entry *pair = hist_entry__next_pair(he); + const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; char buf[32] = " "; + s64 wdiff = 0; + + if (pair) { + if (he->diff.computed) + wdiff = he->diff.wdiff; + else + wdiff = perf_diff__compute_wdiff(he, pair); + } + + if (wdiff != 0) + scnprintf(buf, sizeof(buf), "%14ld", wdiff); + + return scnprintf(hpp->buf, hpp->size, fmt, buf); +} + +static int hpp__header_formula(struct perf_hpp *hpp) +{ + const char *fmt = symbol_conf.field_sep ? "%s" : "%70s"; + + return scnprintf(hpp->buf, hpp->size, fmt, "Formula"); +} + +static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused) +{ + return 70; +} + +static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he) +{ + struct hist_entry *pair = hist_entry__next_pair(he); + const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s"; + char buf[96] = " "; - if (displacement) - scnprintf(buf, sizeof(buf), "%+4ld", displacement); + if (pair) + perf_diff__formula(he, pair, buf, sizeof(buf)); return scnprintf(hpp->buf, hpp->size, fmt, buf); } -#define HPP__COLOR_PRINT_FNS(_name) \ - .header = hpp__header_ ## _name, \ - .width = hpp__width_ ## _name, \ - .color = hpp__color_ ## _name, \ - .entry = hpp__entry_ ## _name +#define HPP__COLOR_PRINT_FNS(_name) \ + { \ + .header = hpp__header_ ## _name, \ + .width = hpp__width_ ## _name, \ + .color = hpp__color_ ## _name, \ + .entry = hpp__entry_ ## _name \ + } -#define HPP__PRINT_FNS(_name) \ - .header = hpp__header_ ## _name, \ - .width = hpp__width_ ## _name, \ - .entry = hpp__entry_ ## _name +#define HPP__PRINT_FNS(_name) \ + { \ + .header = hpp__header_ ## _name, \ + .width = hpp__width_ ## _name, \ + .entry = hpp__entry_ ## _name \ + } struct perf_hpp_fmt perf_hpp__format[] = { - { .cond = false, HPP__COLOR_PRINT_FNS(baseline) }, - { .cond = true, HPP__COLOR_PRINT_FNS(overhead) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_sys) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_us) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_sys) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_us) }, - { .cond = false, HPP__PRINT_FNS(samples) }, - { .cond = false, HPP__PRINT_FNS(period) }, - { .cond = false, HPP__PRINT_FNS(delta) }, - { .cond = false, HPP__PRINT_FNS(displ) } + HPP__COLOR_PRINT_FNS(baseline), + HPP__COLOR_PRINT_FNS(overhead), + HPP__COLOR_PRINT_FNS(overhead_sys), + HPP__COLOR_PRINT_FNS(overhead_us), + HPP__COLOR_PRINT_FNS(overhead_guest_sys), + HPP__COLOR_PRINT_FNS(overhead_guest_us), + HPP__PRINT_FNS(samples), + HPP__PRINT_FNS(period), + HPP__PRINT_FNS(period_baseline), + HPP__PRINT_FNS(delta), + HPP__PRINT_FNS(ratio), + HPP__PRINT_FNS(wdiff), + HPP__PRINT_FNS(formula) }; +LIST_HEAD(perf_hpp__list); + + #undef HPP__COLOR_PRINT_FNS #undef HPP__PRINT_FNS +#undef HPP_PERCENT_FNS +#undef HPP_RAW_FNS + +#undef __HPP_HEADER_FN +#undef __HPP_WIDTH_FN +#undef __HPP_COLOR_PERCENT_FN +#undef __HPP_ENTRY_PERCENT_FN +#undef __HPP_ENTRY_RAW_FN + + void perf_hpp__init(void) { if (symbol_conf.show_cpu_utilization) { - perf_hpp__format[PERF_HPP__OVERHEAD_SYS].cond = true; - perf_hpp__format[PERF_HPP__OVERHEAD_US].cond = true; + perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS); + perf_hpp__column_enable(PERF_HPP__OVERHEAD_US); if (perf_guest) { - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].cond = true; - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].cond = true; + perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_SYS); + perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_US); } } if (symbol_conf.show_nr_samples) - perf_hpp__format[PERF_HPP__SAMPLES].cond = true; + perf_hpp__column_enable(PERF_HPP__SAMPLES); if (symbol_conf.show_total_period) - perf_hpp__format[PERF_HPP__PERIOD].cond = true; + perf_hpp__column_enable(PERF_HPP__PERIOD); +} + +void perf_hpp__column_register(struct perf_hpp_fmt *format) +{ + list_add_tail(&format->list, &perf_hpp__list); } -void perf_hpp__column_enable(unsigned col, bool enable) +void perf_hpp__column_enable(unsigned col) { BUG_ON(col >= PERF_HPP__MAX_INDEX); - perf_hpp__format[col].cond = enable; + perf_hpp__column_register(&perf_hpp__format[col]); } static inline void advance_hpp(struct perf_hpp *hpp, int inc) @@ -352,27 +437,29 @@ int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, bool color) { const char *sep = symbol_conf.field_sep; + struct perf_hpp_fmt *fmt; char *start = hpp->buf; - int i, ret; + int ret; bool first = true; if (symbol_conf.exclude_other && !he->parent) return 0; - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - + perf_hpp__for_each_format(fmt) { + /* + * If there's no field_sep, we still need + * to display initial ' '. + */ if (!sep || !first) { ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " "); advance_hpp(hpp, ret); + } else first = false; - } - if (color && perf_hpp__format[i].color) - ret = perf_hpp__format[i].color(hpp, he); + if (color && fmt->color) + ret = fmt->color(hpp, he); else - ret = perf_hpp__format[i].entry(hpp, he); + ret = fmt->entry(hpp, he); advance_hpp(hpp, ret); } @@ -404,16 +491,18 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size, */ unsigned int hists__sort_list_width(struct hists *hists) { + struct perf_hpp_fmt *fmt; struct sort_entry *se; - int i, ret = 0; + int i = 0, ret = 0; + struct perf_hpp dummy_hpp = { + .ptr = hists_to_evsel(hists), + }; - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; + perf_hpp__for_each_format(fmt) { if (i) ret += 2; - ret += perf_hpp__format[i].width(NULL); + ret += fmt->width(&dummy_hpp); } list_for_each_entry(se, &hist_entry__sort_list, list) diff --git a/tools/perf/ui/keysyms.h b/tools/perf/ui/keysyms.h index 809eca5707f..65092d576b4 100644 --- a/tools/perf/ui/keysyms.h +++ b/tools/perf/ui/keysyms.h @@ -23,5 +23,6 @@ #define K_TIMER -1 #define K_ERROR -2 #define K_RESIZE -3 +#define K_SWITCH_INPUT_DATA -4 #endif /* _PERF_KEYSYMS_H_ */ diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c index 13aa64e50e1..3ec695607a4 100644 --- a/tools/perf/ui/progress.c +++ b/tools/perf/ui/progress.c @@ -1,32 +1,26 @@ #include "../cache.h" #include "progress.h" -#include "libslang.h" -#include "ui.h" -#include "browser.h" -void ui_progress__update(u64 curr, u64 total, const char *title) +static void nop_progress_update(u64 curr __maybe_unused, + u64 total __maybe_unused, + const char *title __maybe_unused) { - int bar, y; - /* - * FIXME: We should have a per UI backend way of showing progress, - * stdio will just show a percentage as NN%, etc. - */ - if (use_browser <= 0) - return; +} - if (total == 0) - return; +static struct ui_progress default_progress_fns = +{ + .update = nop_progress_update, +}; - ui__refresh_dimensions(true); - pthread_mutex_lock(&ui__lock); - y = SLtt_Screen_Rows / 2 - 2; - SLsmg_set_color(0); - SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols); - SLsmg_gotorc(y++, 1); - SLsmg_write_string((char *)title); - SLsmg_set_color(HE_COLORSET_SELECTED); - bar = ((SLtt_Screen_Cols - 2) * curr) / total; - SLsmg_fill_region(y, 1, 1, bar, ' '); - SLsmg_refresh(); - pthread_mutex_unlock(&ui__lock); +struct ui_progress *progress_fns = &default_progress_fns; + +void ui_progress__update(u64 curr, u64 total, const char *title) +{ + return progress_fns->update(curr, total, title); +} + +void ui_progress__finish(void) +{ + if (progress_fns->finish) + progress_fns->finish(); } diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h index d9c205b59aa..257cc224f9c 100644 --- a/tools/perf/ui/progress.h +++ b/tools/perf/ui/progress.h @@ -3,6 +3,16 @@ #include <../types.h> +struct ui_progress { + void (*update)(u64, u64, const char *); + void (*finish)(void); +}; + +extern struct ui_progress *progress_fns; + +void ui_progress__init(void); + void ui_progress__update(u64 curr, u64 total, const char *title); +void ui_progress__finish(void); #endif diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index ebb4cc10787..ae6a789cb0f 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -8,7 +8,7 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; void setup_browser(bool fallback_to_pager) { - if (!isatty(1) || dump_trace) + if (use_browser < 2 && (!isatty(1) || dump_trace)) use_browser = 0; /* default to TUI */ @@ -30,6 +30,7 @@ void setup_browser(bool fallback_to_pager) if (fallback_to_pager) setup_pager(); + perf_hpp__column_enable(PERF_HPP__OVERHEAD); perf_hpp__init(); break; } diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index fbd4e32d074..ff1f60cf442 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -3,6 +3,7 @@ #include "../../util/util.h" #include "../../util/hist.h" #include "../../util/sort.h" +#include "../../util/evsel.h" static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) @@ -335,17 +336,19 @@ 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) { + struct perf_hpp_fmt *fmt; struct sort_entry *se; struct rb_node *nd; size_t ret = 0; unsigned int width; const char *sep = symbol_conf.field_sep; const char *col_width = symbol_conf.col_width_list_str; - int idx, nr_rows = 0; - char bf[64]; + int nr_rows = 0; + char bf[96]; struct perf_hpp dummy_hpp = { .buf = bf, .size = sizeof(bf), + .ptr = hists_to_evsel(hists), }; bool first = true; @@ -355,16 +358,14 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, goto print_entries; fprintf(fp, "# "); - for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { - if (!perf_hpp__format[idx].cond) - continue; + perf_hpp__for_each_format(fmt) { if (!first) fprintf(fp, "%s", sep ?: " "); else first = false; - perf_hpp__format[idx].header(&dummy_hpp); + fmt->header(&dummy_hpp); fprintf(fp, "%s", bf); } @@ -400,18 +401,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, first = true; fprintf(fp, "# "); - for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { - unsigned int i; - if (!perf_hpp__format[idx].cond) - continue; + perf_hpp__for_each_format(fmt) { + unsigned int i; if (!first) fprintf(fp, "%s", sep ?: " "); else first = false; - width = perf_hpp__format[idx].width(&dummy_hpp); + width = fmt->width(&dummy_hpp); for (i = 0; i < width; i++) fprintf(fp, "."); } @@ -462,7 +461,7 @@ out: return ret; } -size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) +size_t events_stats__fprintf(struct events_stats *stats, FILE *fp) { int i; size_t ret = 0; @@ -470,7 +469,7 @@ size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { const char *name; - if (hists->stats.nr_events[i] == 0) + if (stats->nr_events[i] == 0) continue; name = perf_event__name(i); @@ -478,7 +477,7 @@ size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) continue; ret += fprintf(fp, "%16s events: %10d\n", name, - hists->stats.nr_events[i]); + stats->nr_events[i]); } return ret; diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c index 2884d2f41e3..1c8b9afd5d6 100644 --- a/tools/perf/ui/tui/helpline.c +++ b/tools/perf/ui/tui/helpline.c @@ -8,6 +8,8 @@ #include "../ui.h" #include "../libslang.h" +char ui_helpline__last_msg[1024]; + static void tui_helpline__pop(void) { } @@ -23,20 +25,7 @@ static void tui_helpline__push(const char *msg) strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0'; } -struct ui_helpline tui_helpline_fns = { - .pop = tui_helpline__pop, - .push = tui_helpline__push, -}; - -void ui_helpline__init(void) -{ - helpline_fns = &tui_helpline_fns; - ui_helpline__puts(" "); -} - -char ui_helpline__last_msg[1024]; - -int ui_helpline__show_help(const char *format, va_list ap) +static int tui_helpline__show(const char *format, va_list ap) { int ret; static int backlog; @@ -55,3 +44,15 @@ int ui_helpline__show_help(const char *format, va_list ap) return ret; } + +struct ui_helpline tui_helpline_fns = { + .pop = tui_helpline__pop, + .push = tui_helpline__push, + .show = tui_helpline__show, +}; + +void ui_helpline__init(void) +{ + helpline_fns = &tui_helpline_fns; + ui_helpline__puts(" "); +} diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c new file mode 100644 index 00000000000..6c2184d53cb --- /dev/null +++ b/tools/perf/ui/tui/progress.c @@ -0,0 +1,42 @@ +#include "../cache.h" +#include "../progress.h" +#include "../libslang.h" +#include "../ui.h" +#include "../browser.h" + +static void tui_progress__update(u64 curr, u64 total, const char *title) +{ + int bar, y; + /* + * FIXME: We should have a per UI backend way of showing progress, + * stdio will just show a percentage as NN%, etc. + */ + if (use_browser <= 0) + return; + + if (total == 0) + return; + + ui__refresh_dimensions(true); + pthread_mutex_lock(&ui__lock); + y = SLtt_Screen_Rows / 2 - 2; + SLsmg_set_color(0); + SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols); + SLsmg_gotorc(y++, 1); + SLsmg_write_string((char *)title); + SLsmg_set_color(HE_COLORSET_SELECTED); + bar = ((SLtt_Screen_Cols - 2) * curr) / total; + SLsmg_fill_region(y, 1, 1, bar, ' '); + SLsmg_refresh(); + pthread_mutex_unlock(&ui__lock); +} + +static struct ui_progress tui_progress_fns = +{ + .update = tui_progress__update, +}; + +void ui_progress__init(void) +{ + progress_fns = &tui_progress_fns; +} diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 60debb81537..81efa192e86 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -118,6 +118,7 @@ int ui__init(void) newtSetSuspendCallback(newt_suspend, NULL); ui_helpline__init(); ui_browser__init(); + ui_progress__init(); signal(SIGSEGV, ui__signal); signal(SIGFPE, ui__signal); diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h index 7b67045479f..d86359c9990 100644 --- a/tools/perf/ui/ui.h +++ b/tools/perf/ui/ui.h @@ -3,9 +3,37 @@ #include <pthread.h> #include <stdbool.h> +#include <linux/compiler.h> extern pthread_mutex_t ui__lock; +extern int use_browser; + +void setup_browser(bool fallback_to_pager); +void exit_browser(bool wait_for_ok); + +#ifdef NEWT_SUPPORT +int ui__init(void); +void ui__exit(bool wait_for_ok); +#else +static inline int ui__init(void) +{ + return -1; +} +static inline void ui__exit(bool wait_for_ok __maybe_unused) {} +#endif + +#ifdef GTK2_SUPPORT +int perf_gtk__init(void); +void perf_gtk__exit(bool wait_for_ok); +#else +static inline int perf_gtk__init(void) +{ + return -1; +} +static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {} +#endif + void ui__refresh_dimensions(bool force); #endif /* _PERF_UI_H_ */ diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c index 4f989774c8c..e3e0a963d03 100644 --- a/tools/perf/ui/util.c +++ b/tools/perf/ui/util.c @@ -52,7 +52,6 @@ int ui__warning(const char *format, ...) return ret; } - /** * perf_error__register - Register error logging functions * @eops: The pointer to error logging function struct diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 95264f30417..055fef34b6f 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -9,18 +9,14 @@ GVF=${OUTPUT}PERF-VERSION-FILE LF=' ' +# # First check if there is a .git to get the version from git describe -# otherwise try to get the version from the kernel makefile +# otherwise try to get the version from the kernel Makefile +# if test -d ../../.git -o -f ../../.git && - VN=$(git describe --match 'v[0-9].[0-9]*' --abbrev=4 HEAD 2>/dev/null) && - case "$VN" in - *$LF*) (exit 1) ;; - v[0-9]*) - git update-index -q --refresh - test -z "$(git diff-index --name-only HEAD --)" || - VN="$VN-dirty" ;; - esac + VN=$(git tag 2>/dev/null | tail -1 | grep -E "v[0-9].[0-9]*") then + VN=$(echo $VN"-g"$(git log -1 --abbrev=4 --pretty=format:"%h" HEAD)) VN=$(echo "$VN" | sed -e 's/-/./g'); else VN=$(MAKEFLAGS= make -sC ../.. kernelversion) @@ -30,13 +26,13 @@ VN=$(expr "$VN" : v*'\(.*\)') if test -r $GVF then - VC=$(sed -e 's/^PERF_VERSION = //' <$GVF) + VC=$(sed -e 's/^#define PERF_VERSION "\(.*\)"/\1/' <$GVF) else VC=unset fi test "$VN" = "$VC" || { echo >&2 "PERF_VERSION = $VN" - echo "PERF_VERSION = $VN" >$GVF + echo "#define PERF_VERSION \"$VN\"" >$GVF } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index f0a91037137..d33fe937e6f 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -15,6 +15,7 @@ #include "debug.h" #include "annotate.h" #include <pthread.h> +#include <linux/bitops.h> const char *disassembler_style; const char *objdump_path; @@ -170,15 +171,15 @@ static int lock__parse(struct ins_operands *ops) if (disasm_line__parse(ops->raw, &name, &ops->locked.ops->raw) < 0) goto out_free_ops; - ops->locked.ins = ins__find(name); - if (ops->locked.ins == NULL) - goto out_free_ops; + ops->locked.ins = ins__find(name); + if (ops->locked.ins == NULL) + goto out_free_ops; - if (!ops->locked.ins->ops) - return 0; + if (!ops->locked.ins->ops) + return 0; - if (ops->locked.ins->ops->parse) - ops->locked.ins->ops->parse(ops->locked.ops); + if (ops->locked.ins->ops->parse) + ops->locked.ins->ops->parse(ops->locked.ops); return 0; @@ -400,6 +401,8 @@ static struct ins instructions[] = { { .name = "testb", .ops = &mov_ops, }, { .name = "testl", .ops = &mov_ops, }, { .name = "xadd", .ops = &mov_ops, }, + { .name = "xbeginl", .ops = &jump_ops, }, + { .name = "xbeginq", .ops = &jump_ops, }, }; static int ins__cmp(const void *name, const void *insp) @@ -806,7 +809,7 @@ fallback: pr_err("Can't annotate %s:\n\n" "No vmlinux file%s\nwas found in the path.\n\n" "Please use:\n\n" - " perf buildid-cache -av vmlinux\n\n" + " perf buildid-cache -vu vmlinux\n\n" "or:\n\n" " --vmlinux vmlinux\n", sym->name, build_id_msg ?: ""); @@ -855,21 +858,68 @@ 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; while (*p != NULL) { parent = *p; iter = rb_entry(parent, struct source_line, node); - if (src_line->percent > iter->percent) + ret = strcmp(iter->path, src_line->path); + if (ret == 0) { + iter->percent_sum += src_line->percent; + return; + } + + if (ret < 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; } + src_line->percent_sum = src_line->percent; + rb_link_node(&src_line->node, parent, p); rb_insert_color(&src_line->node, root); } +static void __resort_source_line(struct rb_root *root, struct source_line *src_line) +{ + struct source_line *iter; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct source_line, node); + + if (src_line->percent_sum > iter->percent_sum) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&src_line->node, parent, p); + rb_insert_color(&src_line->node, root); +} + +static void resort_source_line(struct rb_root *dest_root, struct rb_root *src_root) +{ + struct source_line *src_line; + struct rb_node *node; + + node = rb_first(src_root); + while (node) { + struct rb_node *next; + + src_line = rb_entry(node, struct source_line, node); + next = rb_next(node); + rb_erase(node, src_root); + + __resort_source_line(dest_root, src_line); + node = next; + } +} + static void symbol__free_source_line(struct symbol *sym, int len) { struct annotation *notes = symbol__annotation(sym); @@ -894,6 +944,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, 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; if (!h->sum) return 0; @@ -928,12 +979,13 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, goto next; strcpy(src_line[i].path, path); - insert_source_line(root, &src_line[i]); + insert_source_line(&tmp_root, &src_line[i]); next: pclose(fp); } + resort_source_line(root, &tmp_root); return 0; } @@ -957,7 +1009,7 @@ static void print_summary(struct rb_root *root, const char *filename) char *path; src_line = rb_entry(node, struct source_line, node); - percent = src_line->percent; + percent = src_line->percent_sum; color = get_percent_color(percent); path = src_line->path; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 39242dcee8f..c422440fe61 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -5,6 +5,8 @@ #include <stdint.h> #include "types.h" #include "symbol.h" +#include "hist.h" +#include "sort.h" #include <linux/list.h> #include <linux/rbtree.h> #include <pthread.h> @@ -75,6 +77,7 @@ struct sym_hist { struct source_line { struct rb_node node; double percent; + double percent_sum; char *path; }; @@ -140,20 +143,41 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, #ifdef NEWT_SUPPORT int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, - void(*timer)(void *arg), void *arg, int delay_secs); + 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, - void(*timer)(void *arg) __maybe_unused, - void *arg __maybe_unused, - int delay_secs __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, + struct hist_browser_timer *hbt); + +static inline int hist_entry__gtk_annotate(struct hist_entry *he, int evidx, + struct hist_browser_timer *hbt) +{ + return symbol__gtk_annotate(he->ms.sym, he->ms.map, evidx, 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) +{ + return 0; +} + +static inline void perf_gtk__show_annotations(void) {} +#endif + extern const char *disassembler_style; -extern const char *objdump_path; #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 8e3a740ddbd..5295625c0c0 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -16,11 +16,11 @@ #include "session.h" #include "tool.h" -static int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_sample *sample __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct machine *machine) +int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct perf_evsel *evsel __maybe_unused, + struct machine *machine) { struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; @@ -64,12 +64,27 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, struct perf_tool build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, .mmap = perf_event__process_mmap, - .fork = perf_event__process_task, + .fork = perf_event__process_fork, .exit = perf_event__exit_del_thread, .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, }; +int build_id__sprintf(const u8 *build_id, int len, char *bf) +{ + char *bid = bf; + const u8 *raw = build_id; + int i; + + for (i = 0; i < len; ++i) { + sprintf(bid, "%02x", *raw); + ++raw; + bid += 2; + } + + return raw - build_id; +} + char *dso__build_id_filename(struct dso *self, char *bf, size_t size) { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index a993ba87d99..a811f5c62e1 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -1,10 +1,19 @@ #ifndef PERF_BUILD_ID_H_ #define PERF_BUILD_ID_H_ 1 -#include "session.h" +#define BUILD_ID_SIZE 20 + +#include "tool.h" +#include "types.h" extern struct perf_tool build_id__mark_dso_hit_ops; +struct dso; +int build_id__sprintf(const u8 *build_id, int len, char *bf); char *dso__build_id_filename(struct dso *self, char *bf, size_t size); +int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct perf_evsel *evsel, + struct machine *machine); + #endif diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 2bd51370ad2..26e36723987 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -5,6 +5,7 @@ #include "util.h" #include "strbuf.h" #include "../perf.h" +#include "../ui/ui.h" #define CMD_EXEC_PATH "--exec-path" #define CMD_PERF_DIR "--perf-dir=" @@ -31,44 +32,6 @@ extern const char *pager_program; extern int pager_in_use(void); extern int pager_use_color; -extern int use_browser; - -#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT) -void setup_browser(bool fallback_to_pager); -void exit_browser(bool wait_for_ok); - -#ifdef NEWT_SUPPORT -int ui__init(void); -void ui__exit(bool wait_for_ok); -#else -static inline int ui__init(void) -{ - return -1; -} -static inline void ui__exit(bool wait_for_ok __maybe_unused) {} -#endif - -#ifdef GTK2_SUPPORT -int perf_gtk__init(void); -void perf_gtk__exit(bool wait_for_ok); -#else -static inline int perf_gtk__init(void) -{ - return -1; -} -static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {} -#endif - -#else /* NEWT_SUPPORT || GTK2_SUPPORT */ - -static inline void setup_browser(bool fallback_to_pager) -{ - if (fallback_to_pager) - setup_pager(); -} -static inline void exit_browser(bool wait_for_ok __maybe_unused) {} -#endif /* NEWT_SUPPORT || GTK2_SUPPORT */ - char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index d3b3f5d8213..42b6a632fe7 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -444,7 +444,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, struct callchain_cursor_node *node = *cursor->last; if (!node) { - node = calloc(sizeof(*node), 1); + node = calloc(1, sizeof(*node)); if (!node) return -ENOMEM; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index eb340571e7d..3ee9f67d5af 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -143,4 +143,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) cursor->curr = cursor->curr->next; cursor->pos++; } + +struct option; + +int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +extern const char record_callchain_help[]; #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 2b32ffa9ebd..f817046e22b 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,4 +1,5 @@ #include "util.h" +#include "sysfs.h" #include "../perf.h" #include "cpumap.h" #include <assert.h> @@ -201,3 +202,56 @@ void cpu_map__delete(struct cpu_map *map) { free(map); } + +int cpu_map__get_socket(struct cpu_map *map, int idx) +{ + FILE *fp; + const char *mnt; + char path[PATH_MAX]; + int cpu, ret; + + if (idx > map->nr) + return -1; + + cpu = map->map[idx]; + + mnt = sysfs_find_mountpoint(); + if (!mnt) + return -1; + + sprintf(path, + "%s/devices/system/cpu/cpu%d/topology/physical_package_id", + mnt, cpu); + + fp = fopen(path, "r"); + if (!fp) + return -1; + ret = fscanf(fp, "%d", &cpu); + fclose(fp); + return ret == 1 ? cpu : -1; +} + +int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp) +{ + struct cpu_map *sock; + int nr = cpus->nr; + int cpu, s1, s2; + + sock = calloc(1, sizeof(*sock) + nr * sizeof(int)); + if (!sock) + 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]) + break; + } + if (s2 == sock->nr) { + sock->map[sock->nr] = s1; + sock->nr++; + } + } + *sockp = sock; + return 0; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 2f68a3b8c28..161b00756a1 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -14,6 +14,15 @@ struct cpu_map *cpu_map__dummy_new(void); 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__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); + +static inline int cpu_map__socket(struct cpu_map *sock, int s) +{ + if (!sock || s > sock->nr || s < 0) + return 0; + return sock->map[s]; +} static inline int cpu_map__nr(const struct cpu_map *map) { diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 03f830b4814..399e74c34c1 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -23,10 +23,8 @@ int eprintf(int level, const char *fmt, ...) if (verbose >= level) { va_start(args, fmt); - if (use_browser == 1) - ret = ui_helpline__show_help(fmt, args); - else if (use_browser == 2) - ret = perf_gtk__show_helpline(fmt, args); + if (use_browser >= 1) + ui_helpline__vshow(fmt, args); else ret = vfprintf(stderr, fmt, args); va_end(args); @@ -49,28 +47,6 @@ int dump_printf(const char *fmt, ...) return ret; } -#if !defined(NEWT_SUPPORT) && !defined(GTK2_SUPPORT) -int ui__warning(const char *format, ...) -{ - va_list args; - - va_start(args, format); - vfprintf(stderr, format, args); - va_end(args); - return 0; -} -#endif - -int ui__error_paranoid(void) -{ - return ui__error("Permission error - are you root?\n" - "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" - " -1 - Not paranoid at all\n" - " 0 - Disallow raw tracepoint access for unpriv\n" - " 1 - Disallow cpu events for unpriv\n" - " 2 - Disallow kernel profiling for unpriv\n"); -} - void trace_event(union perf_event *event) { unsigned char *raw_event = (void *)event; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index dec98750b48..efbd98805ad 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -5,6 +5,8 @@ #include <stdbool.h> #include "event.h" #include "../ui/helpline.h" +#include "../ui/progress.h" +#include "../ui/util.h" extern int verbose; extern bool quiet, dump_trace; @@ -12,38 +14,7 @@ extern bool quiet, dump_trace; int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); -struct ui_progress; -struct perf_error_ops; - -#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT) - -#include "../ui/progress.h" int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -#include "../ui/util.h" - -#else - -static inline void ui_progress__update(u64 curr __maybe_unused, - u64 total __maybe_unused, - const char *title __maybe_unused) {} - -#define ui__error(format, arg...) ui__warning(format, ##arg) - -static inline int -perf_error__register(struct perf_error_ops *eops __maybe_unused) -{ - return 0; -} - -static inline int -perf_error__unregister(struct perf_error_ops *eops __maybe_unused) -{ - return 0; -} - -#endif /* NEWT_SUPPORT || GTK2_SUPPORT */ - int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); -int ui__error_paranoid(void); #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c new file mode 100644 index 00000000000..6f7d5a9d6b0 --- /dev/null +++ b/tools/perf/util/dso.c @@ -0,0 +1,595 @@ +#include "symbol.h" +#include "dso.h" +#include "machine.h" +#include "util.h" +#include "debug.h" + +char dso__symtab_origin(const struct dso *dso) +{ + static const char origin[] = { + [DSO_BINARY_TYPE__KALLSYMS] = 'k', + [DSO_BINARY_TYPE__VMLINUX] = 'v', + [DSO_BINARY_TYPE__JAVA_JIT] = 'j', + [DSO_BINARY_TYPE__DEBUGLINK] = 'l', + [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', + [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', + [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', + [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', + [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', + [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', + [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', + [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', + [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', + }; + + if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND) + return '!'; + return origin[dso->symtab_type]; +} + +int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, + char *root_dir, char *file, size_t size) +{ + char build_id_hex[BUILD_ID_SIZE * 2 + 1]; + int ret = 0; + + switch (type) { + case DSO_BINARY_TYPE__DEBUGLINK: { + char *debuglink; + + strncpy(file, dso->long_name, size); + debuglink = file + dso->long_name_len; + while (debuglink != file && *debuglink != '/') + debuglink--; + if (*debuglink == '/') + debuglink++; + filename__read_debuglink(dso->long_name, debuglink, + size - (debuglink - file)); + } + break; + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + /* skip the locally configured cache if a symfs is given */ + if (symbol_conf.symfs[0] || + (dso__build_id_filename(dso, file, size) == NULL)) + ret = -1; + break; + + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + snprintf(file, size, "%s/usr/lib/debug%s.debug", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + snprintf(file, size, "%s/usr/lib/debug%s", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + if (!dso->has_build_id) { + ret = -1; + break; + } + + build_id__sprintf(dso->build_id, + sizeof(dso->build_id), + build_id_hex); + snprintf(file, size, + "%s/usr/lib/debug/.build-id/%.2s/%s.debug", + symbol_conf.symfs, build_id_hex, build_id_hex + 2); + break; + + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + snprintf(file, size, "%s%s", + symbol_conf.symfs, dso->long_name); + break; + + case DSO_BINARY_TYPE__GUEST_KMODULE: + snprintf(file, size, "%s%s%s", symbol_conf.symfs, + root_dir, dso->long_name); + break; + + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + snprintf(file, size, "%s%s", symbol_conf.symfs, + dso->long_name); + break; + + default: + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__NOT_FOUND: + ret = -1; + break; + } + + return ret; +} + +static int open_dso(struct dso *dso, struct machine *machine) +{ + char *root_dir = (char *) ""; + char *name; + int fd; + + name = malloc(PATH_MAX); + if (!name) + return -ENOMEM; + + if (machine) + root_dir = machine->root_dir; + + if (dso__binary_type_file(dso, dso->data_type, + root_dir, name, PATH_MAX)) { + free(name); + return -EINVAL; + } + + fd = open(name, O_RDONLY); + free(name); + return fd; +} + +int dso__data_fd(struct dso *dso, struct machine *machine) +{ + static enum dso_binary_type binary_type_data[] = { + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + DSO_BINARY_TYPE__NOT_FOUND, + }; + int i = 0; + + if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND) + return open_dso(dso, machine); + + do { + int fd; + + dso->data_type = binary_type_data[i++]; + + fd = open_dso(dso, machine); + if (fd >= 0) + return fd; + + } while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND); + + return -EINVAL; +} + +static void +dso_cache__free(struct rb_root *root) +{ + struct rb_node *next = rb_first(root); + + while (next) { + struct dso_cache *cache; + + cache = rb_entry(next, struct dso_cache, rb_node); + next = rb_next(&cache->rb_node); + rb_erase(&cache->rb_node, root); + free(cache); + } +} + +static struct dso_cache* +dso_cache__find(struct rb_root *root, u64 offset) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct dso_cache *cache; + + while (*p != NULL) { + u64 end; + + parent = *p; + cache = rb_entry(parent, struct dso_cache, rb_node); + end = cache->offset + DSO__DATA_CACHE_SIZE; + + if (offset < cache->offset) + p = &(*p)->rb_left; + else if (offset >= end) + p = &(*p)->rb_right; + else + return cache; + } + return NULL; +} + +static void +dso_cache__insert(struct rb_root *root, struct dso_cache *new) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct dso_cache *cache; + u64 offset = new->offset; + + while (*p != NULL) { + u64 end; + + parent = *p; + cache = rb_entry(parent, struct dso_cache, rb_node); + end = cache->offset + DSO__DATA_CACHE_SIZE; + + if (offset < cache->offset) + p = &(*p)->rb_left; + else if (offset >= end) + p = &(*p)->rb_right; + } + + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, root); +} + +static ssize_t +dso_cache__memcpy(struct dso_cache *cache, u64 offset, + u8 *data, u64 size) +{ + u64 cache_offset = offset - cache->offset; + u64 cache_size = min(cache->size - cache_offset, size); + + memcpy(data, cache->data + cache_offset, cache_size); + return cache_size; +} + +static ssize_t +dso_cache__read(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + struct dso_cache *cache; + ssize_t ret; + int fd; + + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -1; + + do { + u64 cache_offset; + + ret = -ENOMEM; + + cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE); + if (!cache) + break; + + cache_offset = offset & DSO__DATA_CACHE_MASK; + ret = -EINVAL; + + if (-1 == lseek(fd, cache_offset, SEEK_SET)) + break; + + ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE); + if (ret <= 0) + break; + + cache->offset = cache_offset; + cache->size = ret; + dso_cache__insert(&dso->cache, cache); + + ret = dso_cache__memcpy(cache, offset, data, size); + + } while (0); + + if (ret <= 0) + free(cache); + + close(fd); + return ret; +} + +static ssize_t dso_cache_read(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + struct dso_cache *cache; + + cache = dso_cache__find(&dso->cache, offset); + if (cache) + return dso_cache__memcpy(cache, offset, data, size); + else + return dso_cache__read(dso, machine, offset, data, size); +} + +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size) +{ + ssize_t r = 0; + u8 *p = data; + + do { + ssize_t ret; + + ret = dso_cache_read(dso, machine, offset, p, size); + if (ret < 0) + return ret; + + /* Reached EOF, return what we have. */ + if (!ret) + break; + + BUG_ON(ret > size); + + r += ret; + p += ret; + offset += ret; + size -= ret; + + } while (size); + + return r; +} + +ssize_t dso__data_read_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + u8 *data, ssize_t size) +{ + u64 offset = map->map_ip(map, addr); + return dso__data_read_offset(dso, machine, offset, data, size); +} + +struct map *dso__new_map(const char *name) +{ + struct map *map = NULL; + struct dso *dso = dso__new(name); + + if (dso) + map = map__new2(0, dso, MAP__FUNCTION); + + return map; +} + +struct dso *dso__kernel_findnew(struct machine *machine, const char *name, + const char *short_name, int dso_type) +{ + /* + * The kernel dso could be created by build_id processing. + */ + struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name); + + /* + * We need to run this in all cases, since during the build_id + * processing we had no idea this was the kernel dso. + */ + if (dso != NULL) { + dso__set_short_name(dso, short_name); + dso->kernel = dso_type; + } + + return dso; +} + +void dso__set_long_name(struct dso *dso, char *name) +{ + if (name == NULL) + return; + dso->long_name = name; + dso->long_name_len = strlen(name); +} + +void dso__set_short_name(struct dso *dso, const char *name) +{ + if (name == NULL) + return; + dso->short_name = name; + dso->short_name_len = strlen(name); +} + +static void dso__set_basename(struct dso *dso) +{ + dso__set_short_name(dso, basename(dso->long_name)); +} + +int dso__name_len(const struct dso *dso) +{ + if (!dso) + return strlen("[unknown]"); + if (verbose) + return dso->long_name_len; + + return dso->short_name_len; +} + +bool dso__loaded(const struct dso *dso, enum map_type type) +{ + return dso->loaded & (1 << type); +} + +bool dso__sorted_by_name(const struct dso *dso, enum map_type type) +{ + return dso->sorted_by_name & (1 << type); +} + +void dso__set_sorted_by_name(struct dso *dso, enum map_type type) +{ + dso->sorted_by_name |= (1 << type); +} + +struct dso *dso__new(const char *name) +{ + struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1); + + if (dso != NULL) { + int i; + strcpy(dso->name, name); + dso__set_long_name(dso, dso->name); + dso__set_short_name(dso, dso->name); + for (i = 0; i < MAP__NR_TYPES; ++i) + dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; + dso->cache = RB_ROOT; + dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; + dso->data_type = DSO_BINARY_TYPE__NOT_FOUND; + dso->loaded = 0; + dso->sorted_by_name = 0; + dso->has_build_id = 0; + dso->kernel = DSO_TYPE_USER; + dso->needs_swap = DSO_SWAP__UNSET; + INIT_LIST_HEAD(&dso->node); + } + + return dso; +} + +void dso__delete(struct dso *dso) +{ + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + symbols__delete(&dso->symbols[i]); + if (dso->sname_alloc) + free((char *)dso->short_name); + if (dso->lname_alloc) + free(dso->long_name); + dso_cache__free(&dso->cache); + free(dso); +} + +void dso__set_build_id(struct dso *dso, void *build_id) +{ + memcpy(dso->build_id, build_id, sizeof(dso->build_id)); + dso->has_build_id = 1; +} + +bool dso__build_id_equal(const struct dso *dso, u8 *build_id) +{ + return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0; +} + +void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine) +{ + char path[PATH_MAX]; + + if (machine__is_default_guest(machine)) + return; + sprintf(path, "%s/sys/kernel/notes", machine->root_dir); + if (sysfs__read_build_id(path, dso->build_id, + sizeof(dso->build_id)) == 0) + dso->has_build_id = true; +} + +int dso__kernel_module_get_build_id(struct dso *dso, + const char *root_dir) +{ + char filename[PATH_MAX]; + /* + * kernel module short names are of the form "[module]" and + * we need just "module" here. + */ + const char *name = dso->short_name + 1; + + snprintf(filename, sizeof(filename), + "%s/sys/module/%.*s/notes/.note.gnu.build-id", + root_dir, (int)strlen(name) - 1, name); + + if (sysfs__read_build_id(filename, dso->build_id, + sizeof(dso->build_id)) == 0) + dso->has_build_id = true; + + return 0; +} + +bool __dsos__read_build_ids(struct list_head *head, bool with_hits) +{ + bool have_build_id = false; + struct dso *pos; + + list_for_each_entry(pos, head, node) { + if (with_hits && !pos->hit) + continue; + if (pos->has_build_id) { + have_build_id = true; + continue; + } + if (filename__read_build_id(pos->long_name, pos->build_id, + sizeof(pos->build_id)) > 0) { + have_build_id = true; + pos->has_build_id = true; + } + } + + return have_build_id; +} + +void dsos__add(struct list_head *head, struct dso *dso) +{ + list_add_tail(&dso->node, head); +} + +struct dso *dsos__find(struct list_head *head, const char *name) +{ + struct dso *pos; + + list_for_each_entry(pos, head, node) + if (strcmp(pos->long_name, name) == 0) + return pos; + return NULL; +} + +struct dso *__dsos__findnew(struct list_head *head, const char *name) +{ + struct dso *dso = dsos__find(head, name); + + if (!dso) { + dso = dso__new(name); + if (dso != NULL) { + dsos__add(head, dso); + dso__set_basename(dso); + } + } + + return dso; +} + +size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + struct dso *pos; + size_t ret = 0; + + list_for_each_entry(pos, head, node) { + if (skip && skip(pos, parm)) + continue; + ret += dso__fprintf_buildid(pos, fp); + ret += fprintf(fp, " %s\n", pos->long_name); + } + return ret; +} + +size_t __dsos__fprintf(struct list_head *head, FILE *fp) +{ + struct dso *pos; + size_t ret = 0; + + list_for_each_entry(pos, head, node) { + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + ret += dso__fprintf(pos, i, fp); + } + + return ret; +} + +size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) +{ + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + return fprintf(fp, "%s", sbuild_id); +} + +size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) +{ + struct rb_node *nd; + size_t ret = fprintf(fp, "dso: %s (", dso->short_name); + + if (dso->short_name != dso->long_name) + ret += fprintf(fp, "%s, ", dso->long_name); + ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type], + dso__loaded(dso, type) ? "" : "NOT "); + ret += dso__fprintf_buildid(dso, fp); + ret += fprintf(fp, ")\n"); + for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) { + struct symbol *pos = rb_entry(nd, struct symbol, rb_node); + ret += symbol__fprintf(pos, fp); + } + + return ret; +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h new file mode 100644 index 00000000000..450199ab51b --- /dev/null +++ b/tools/perf/util/dso.h @@ -0,0 +1,148 @@ +#ifndef __PERF_DSO +#define __PERF_DSO + +#include <linux/types.h> +#include <linux/rbtree.h> +#include "types.h" +#include "map.h" + +enum dso_binary_type { + DSO_BINARY_TYPE__KALLSYMS = 0, + DSO_BINARY_TYPE__GUEST_KALLSYMS, + DSO_BINARY_TYPE__VMLINUX, + DSO_BINARY_TYPE__GUEST_VMLINUX, + DSO_BINARY_TYPE__JAVA_JIT, + DSO_BINARY_TYPE__DEBUGLINK, + DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + DSO_BINARY_TYPE__GUEST_KMODULE, + DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__NOT_FOUND, +}; + +enum dso_kernel_type { + DSO_TYPE_USER = 0, + DSO_TYPE_KERNEL, + DSO_TYPE_GUEST_KERNEL +}; + +enum dso_swap_type { + DSO_SWAP__UNSET, + DSO_SWAP__NO, + DSO_SWAP__YES, +}; + +#define DSO__SWAP(dso, type, val) \ +({ \ + type ____r = val; \ + BUG_ON(dso->needs_swap == DSO_SWAP__UNSET); \ + if (dso->needs_swap == DSO_SWAP__YES) { \ + switch (sizeof(____r)) { \ + case 2: \ + ____r = bswap_16(val); \ + break; \ + case 4: \ + ____r = bswap_32(val); \ + break; \ + case 8: \ + ____r = bswap_64(val); \ + break; \ + default: \ + BUG_ON(1); \ + } \ + } \ + ____r; \ +}) + +#define DSO__DATA_CACHE_SIZE 4096 +#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1) + +struct dso_cache { + struct rb_node rb_node; + u64 offset; + u64 size; + char data[0]; +}; + +struct dso { + struct list_head node; + struct rb_root symbols[MAP__NR_TYPES]; + struct rb_root symbol_names[MAP__NR_TYPES]; + struct rb_root cache; + enum dso_kernel_type kernel; + enum dso_swap_type needs_swap; + enum dso_binary_type symtab_type; + enum dso_binary_type data_type; + u8 adjust_symbols:1; + u8 has_build_id:1; + u8 hit:1; + u8 annotate_warned:1; + u8 sname_alloc:1; + u8 lname_alloc:1; + u8 sorted_by_name; + u8 loaded; + u8 build_id[BUILD_ID_SIZE]; + const char *short_name; + char *long_name; + u16 long_name_len; + u16 short_name_len; + char name[0]; +}; + +static inline void dso__set_loaded(struct dso *dso, enum map_type type) +{ + dso->loaded |= (1 << type); +} + +struct dso *dso__new(const char *name); +void dso__delete(struct dso *dso); + +void dso__set_short_name(struct dso *dso, const char *name); +void dso__set_long_name(struct dso *dso, char *name); + +int dso__name_len(const struct dso *dso); + +bool dso__loaded(const struct dso *dso, enum map_type type); + +bool dso__sorted_by_name(const struct dso *dso, enum map_type type); +void dso__set_sorted_by_name(struct dso *dso, enum map_type type); +void dso__sort_by_name(struct dso *dso, enum map_type type); + +void dso__set_build_id(struct dso *dso, void *build_id); +bool dso__build_id_equal(const struct dso *dso, u8 *build_id); +void dso__read_running_kernel_build_id(struct dso *dso, + struct machine *machine); +int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); + +char dso__symtab_origin(const struct dso *dso); +int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, + char *root_dir, char *file, size_t size); + +int dso__data_fd(struct dso *dso, struct machine *machine); +ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, + u64 offset, u8 *data, ssize_t size); +ssize_t dso__data_read_addr(struct dso *dso, struct map *map, + struct machine *machine, u64 addr, + u8 *data, ssize_t size); + +struct map *dso__new_map(const char *name); +struct dso *dso__kernel_findnew(struct machine *machine, const char *name, + const char *short_name, int dso_type); + +void dsos__add(struct list_head *head, struct dso *dso); +struct dso *dsos__find(struct list_head *head, const char *name); +struct dso *__dsos__findnew(struct list_head *head, const char *name); +bool __dsos__read_build_ids(struct list_head *head, bool with_hits); + +size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); +size_t __dsos__fprintf(struct list_head *head, FILE *fp); + +size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); +size_t dso__fprintf_symbols_by_name(struct dso *dso, + enum map_type type, FILE *fp); +size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp); +#endif /* __PERF_DSO */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 6715b193872..5cd13d768ce 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include "event.h" #include "debug.h" +#include "machine.h" #include "sort.h" #include "string.h" #include "strlist.h" @@ -192,55 +193,43 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, event->header.misc = PERF_RECORD_MISC_USER; while (1) { - char bf[BUFSIZ], *pbf = bf; - int n; + char bf[BUFSIZ]; + char prot[5]; + char execname[PATH_MAX]; + char anonstr[] = "//anon"; size_t size; + if (fgets(bf, sizeof(bf), fp) == NULL) break; + /* ensure null termination since stack will be reused. */ + strcpy(execname, ""); + /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = hex2u64(pbf, &event->mmap.start); - if (n < 0) - continue; - pbf += n + 1; - n = hex2u64(pbf, &event->mmap.len); - if (n < 0) + sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", + &event->mmap.start, &event->mmap.len, prot, + &event->mmap.pgoff, execname); + + if (prot[2] != 'x') continue; - pbf += n + 3; - if (*pbf == 'x') { /* vm_exec */ - char anonstr[] = "//anon\n"; - char *execname = strchr(bf, '/'); - - /* Catch VDSO */ - if (execname == NULL) - execname = strstr(bf, "[vdso]"); - - /* Catch anonymous mmaps */ - if ((execname == NULL) && !strstr(bf, "[")) - execname = anonstr; - - if (execname == NULL) - continue; - - pbf += 3; - n = hex2u64(pbf, &event->mmap.pgoff); - - size = strlen(execname); - execname[size - 1] = '\0'; /* Remove \n */ - memcpy(event->mmap.filename, execname, size); - size = PERF_ALIGN(size, sizeof(u64)); - event->mmap.len -= event->mmap.start; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.pid = tgid; - event->mmap.tid = pid; - - if (process(tool, event, &synth_sample, machine) != 0) { - rc = -1; - break; - } + + if (!strcmp(execname, "")) + strcpy(execname, anonstr); + + size = strlen(execname) + 1; + memcpy(event->mmap.filename, execname, size); + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap.len -= event->mmap.start; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; + event->mmap.pid = tgid; + event->mmap.tid = pid; + + if (process(tool, event, &synth_sample, machine) != 0) { + rc = -1; + break; } } @@ -404,16 +393,15 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (*end) /* only interested in proper numerical dirents */ continue; - - if (__event__synthesize_thread(comm_event, mmap_event, pid, 1, - process, tool, machine) != 0) { - err = -1; - goto out_closedir; - } + /* + * We may race with exiting thread, so don't stop just because + * one thread couldn't be synthesized. + */ + __event__synthesize_thread(comm_event, mmap_event, pid, 1, + process, tool, machine); } err = 0; -out_closedir: closedir(proc); out_free_mmap: free(mmap_event); @@ -488,8 +476,10 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, } } - if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) + if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) { + free(event); return -ENOENT; + } map = machine->vmlinux_maps[MAP__FUNCTION]; size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), @@ -519,134 +509,15 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused, struct perf_sample *sample __maybe_unused, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->comm.tid); - - if (dump_trace) - perf_event__fprintf_comm(event, stdout); - - if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { - dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); - return -1; - } - - return 0; + return machine__process_comm_event(machine, event); } int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, - struct machine *machine __maybe_unused) -{ - dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", - event->lost.id, event->lost.lost); - return 0; -} - -static void perf_event__set_kernel_mmap_len(union perf_event *event, - struct map **maps) + struct machine *machine) { - maps[MAP__FUNCTION]->start = event->mmap.start; - maps[MAP__FUNCTION]->end = event->mmap.start + event->mmap.len; - /* - * Be a bit paranoid here, some perf.data file came with - * a zero sized synthesized MMAP event for the kernel. - */ - if (maps[MAP__FUNCTION]->end == 0) - maps[MAP__FUNCTION]->end = ~0ULL; -} - -static int perf_event__process_kernel_mmap(struct perf_tool *tool - __maybe_unused, - union perf_event *event, - struct machine *machine) -{ - struct map *map; - char kmmap_prefix[PATH_MAX]; - enum dso_kernel_type kernel_type; - bool is_kernel_mmap; - - machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); - if (machine__is_host(machine)) - kernel_type = DSO_TYPE_KERNEL; - else - kernel_type = DSO_TYPE_GUEST_KERNEL; - - is_kernel_mmap = memcmp(event->mmap.filename, - kmmap_prefix, - strlen(kmmap_prefix) - 1) == 0; - if (event->mmap.filename[0] == '/' || - (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - - char short_module_name[1024]; - char *name, *dot; - - if (event->mmap.filename[0] == '/') { - name = strrchr(event->mmap.filename, '/'); - if (name == NULL) - goto out_problem; - - ++name; /* skip / */ - dot = strrchr(name, '.'); - if (dot == NULL) - goto out_problem; - snprintf(short_module_name, sizeof(short_module_name), - "[%.*s]", (int)(dot - name), name); - strxfrchar(short_module_name, '-', '_'); - } else - strcpy(short_module_name, event->mmap.filename); - - map = machine__new_module(machine, event->mmap.start, - event->mmap.filename); - if (map == NULL) - goto out_problem; - - name = strdup(short_module_name); - if (name == NULL) - goto out_problem; - - map->dso->short_name = name; - map->dso->sname_alloc = 1; - map->end = map->start + event->mmap.len; - } else if (is_kernel_mmap) { - const char *symbol_name = (event->mmap.filename + - strlen(kmmap_prefix)); - /* - * Should be there already, from the build-id table in - * the header. - */ - struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, - kmmap_prefix); - if (kernel == NULL) - goto out_problem; - - kernel->kernel = kernel_type; - if (__machine__create_kernel_maps(machine, kernel) < 0) - goto out_problem; - - perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps); - - /* - * Avoid using a zero address (kptr_restrict) for the ref reloc - * symbol. Effectively having zero here means that at record - * time /proc/sys/kernel/kptr_restrict was non zero. - */ - if (event->mmap.pgoff != 0) { - maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, - symbol_name, - event->mmap.pgoff); - } - - if (machine__is_default_guest(machine)) { - /* - * preload dso of guest kernel and modules - */ - dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION], - NULL); - } - } - return 0; -out_problem: - return -1; + return machine__process_lost_event(machine, event); } size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) @@ -656,43 +527,12 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) event->mmap.len, event->mmap.pgoff, event->mmap.filename); } -int perf_event__process_mmap(struct perf_tool *tool, +int perf_event__process_mmap(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, struct machine *machine) { - struct thread *thread; - struct map *map; - u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - int ret = 0; - - if (dump_trace) - perf_event__fprintf_mmap(event, stdout); - - if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || - cpumode == PERF_RECORD_MISC_KERNEL) { - ret = perf_event__process_kernel_mmap(tool, event, machine); - if (ret < 0) - goto out_problem; - return 0; - } - - thread = machine__findnew_thread(machine, event->mmap.pid); - if (thread == NULL) - goto out_problem; - map = map__new(&machine->user_dsos, event->mmap.start, - event->mmap.len, event->mmap.pgoff, - event->mmap.pid, event->mmap.filename, - MAP__FUNCTION); - if (map == NULL) - goto out_problem; - - thread__insert_map(thread, map); - return 0; - -out_problem: - dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); - return 0; + return machine__process_mmap_event(machine, event); } size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) @@ -702,29 +542,20 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) event->fork.ppid, event->fork.ptid); } -int perf_event__process_task(struct perf_tool *tool __maybe_unused, +int perf_event__process_fork(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, - struct machine *machine) + struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->fork.tid); - struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); - - if (dump_trace) - perf_event__fprintf_task(event, stdout); - - if (event->header.type == PERF_RECORD_EXIT) { - machine__remove_thread(machine, thread); - return 0; - } - - if (thread == NULL || parent == NULL || - thread__fork(thread, parent) < 0) { - dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); - return -1; - } + return machine__process_fork_event(machine, event); +} - return 0; +int perf_event__process_exit(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_exit_event(machine, event); } size_t perf_event__fprintf(union perf_event *event, FILE *fp) @@ -750,27 +581,12 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) return ret; } -int perf_event__process(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample, struct machine *machine) +int perf_event__process(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) { - switch (event->header.type) { - case PERF_RECORD_COMM: - perf_event__process_comm(tool, event, sample, machine); - break; - case PERF_RECORD_MMAP: - perf_event__process_mmap(tool, event, sample, machine); - break; - case PERF_RECORD_FORK: - case PERF_RECORD_EXIT: - perf_event__process_task(tool, event, sample, machine); - break; - case PERF_RECORD_LOST: - perf_event__process_lost(tool, event, sample, machine); - default: - break; - } - - return 0; + return machine__process_event(machine, event); } void thread__find_addr_map(struct thread *self, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 21b99e741a8..0d573ff4771 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -6,6 +6,7 @@ #include "../perf.h" #include "map.h" +#include "build-id.h" /* * PERF_SAMPLE_IP | PERF_SAMPLE_TID | * @@ -96,8 +97,6 @@ struct perf_sample { struct stack_dump user_stack; }; -#define BUILD_ID_SIZE 20 - struct build_id_event { struct perf_event_header header; pid_t pid; @@ -191,7 +190,11 @@ int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); -int perf_event__process_task(struct perf_tool *tool, +int perf_event__process_fork(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); +int perf_event__process_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 186b8773039..c8be0fbc514 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -49,21 +49,25 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, return evlist; } -void perf_evlist__config_attrs(struct perf_evlist *evlist, - struct perf_record_opts *opts) +void perf_evlist__config(struct perf_evlist *evlist, + struct perf_record_opts *opts) { - struct perf_evsel *evsel, *first; + struct perf_evsel *evsel; + /* + * Set the evsel leader links before we configure attributes, + * since some might depend on this info. + */ + if (opts->group) + perf_evlist__set_leader(evlist); if (evlist->cpus->map[0] < 0) opts->no_inherit = true; - first = perf_evlist__first(evlist); - list_for_each_entry(evsel, &evlist->entries, node) { - perf_evsel__config(evsel, opts, first); + perf_evsel__config(evsel, opts); if (evlist->nr_entries > 1) - evsel->attr.sample_type |= PERF_SAMPLE_ID; + perf_evsel__set_sample_id(evsel); } } @@ -113,18 +117,21 @@ void __perf_evlist__set_leader(struct list_head *list) struct perf_evsel *evsel, *leader; leader = list_entry(list->next, struct perf_evsel, node); - leader->leader = NULL; + evsel = list_entry(list->prev, struct perf_evsel, node); + + leader->nr_members = evsel->idx - leader->idx + 1; list_for_each_entry(evsel, list, node) { - if (evsel != leader) - evsel->leader = leader; + evsel->leader = leader; } } void perf_evlist__set_leader(struct perf_evlist *evlist) { - if (evlist->nr_entries) + if (evlist->nr_entries) { + evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; __perf_evlist__set_leader(&evlist->entries); + } } int perf_evlist__add_default(struct perf_evlist *evlist) @@ -224,6 +231,8 @@ void perf_evlist__disable(struct perf_evlist *evlist) for (cpu = 0; cpu < evlist->cpus->nr; 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++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE, 0); @@ -238,6 +247,8 @@ void perf_evlist__enable(struct perf_evlist *evlist) for (cpu = 0; cpu < cpu_map__nr(evlist->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++) ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); @@ -303,7 +314,6 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) { struct hlist_head *head; - struct hlist_node *pos; struct perf_sample_id *sid; int hash; @@ -313,7 +323,7 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) hash = hash_64(id, PERF_EVLIST__HLIST_BITS); head = &evlist->heads[hash]; - hlist_for_each_entry(sid, pos, head, node) + hlist_for_each_entry(sid, head, node) if (sid->id == id) return sid->evsel; @@ -325,8 +335,6 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { - /* XXX Move this to perf.c, making it generally available */ - unsigned int page_size = sysconf(_SC_PAGE_SIZE); struct perf_mmap *md = &evlist->mmap[idx]; unsigned int head = perf_mmap__read_head(md); unsigned int old = md->prev; @@ -366,7 +374,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) if ((old & md->mask) + size != ((old + size) & md->mask)) { unsigned int offset = old; unsigned int len = min(sizeof(*event), size), cpy; - void *dst = &evlist->event_copy; + void *dst = &md->event_copy; do { cpy = min(md->mask + 1 - (offset & md->mask), len); @@ -376,7 +384,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) len -= cpy; } while (len); - event = &evlist->event_copy; + event = &md->event_copy; } old += size; @@ -528,7 +536,6 @@ out_unmap: int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite) { - unsigned int page_size = sysconf(_SC_PAGE_SIZE); struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; const struct thread_map *threads = evlist->threads; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 56003f779e6..2dd07bd60b4 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -17,10 +17,18 @@ struct perf_record_opts; #define PERF_EVLIST__HLIST_BITS 8 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) +struct perf_mmap { + void *base; + int mask; + unsigned int prev; + union perf_event event_copy; +}; + struct perf_evlist { struct list_head entries; struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; int nr_entries; + int nr_groups; int nr_fds; int nr_mmaps; int mmap_len; @@ -29,7 +37,6 @@ struct perf_evlist { pid_t pid; } workload; bool overwrite; - union perf_event event_copy; struct perf_mmap *mmap; struct pollfd *pollfd; struct thread_map *threads; @@ -76,8 +83,8 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); int perf_evlist__open(struct perf_evlist *evlist); -void perf_evlist__config_attrs(struct perf_evlist *evlist, - struct perf_record_opts *opts); +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, @@ -135,4 +142,25 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) } size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); + +static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) +{ + struct perf_event_mmap_page *pc = mm->base; + int head = pc->data_head; + rmb(); + return head; +} + +static inline void perf_mmap__write_tail(struct perf_mmap *md, + unsigned long tail) +{ + struct perf_event_mmap_page *pc = md->base; + + /* + * ensure all reads are done before we write the tail out. + */ + /* mb(); */ + pc->data_tail = tail; +} + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 618d41140ab..9c82f98f26d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -18,10 +18,15 @@ #include "cpumap.h" #include "thread_map.h" #include "target.h" -#include "../../../include/linux/hw_breakpoint.h" -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/hw_breakpoint.h> +#include <linux/perf_event.h> #include "perf_regs.h" +static struct { + bool sample_id_all; + bool exclude_guest; +} perf_missing_features; + #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) static int __perf_evsel__sample_size(u64 sample_type) @@ -50,11 +55,36 @@ void hists__init(struct hists *hists) pthread_mutex_init(&hists->lock, NULL); } +void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit) +{ + if (!(evsel->attr.sample_type & bit)) { + evsel->attr.sample_type |= bit; + evsel->sample_size += sizeof(u64); + } +} + +void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit) +{ + if (evsel->attr.sample_type & bit) { + evsel->attr.sample_type &= ~bit; + evsel->sample_size -= sizeof(u64); + } +} + +void perf_evsel__set_sample_id(struct perf_evsel *evsel) +{ + perf_evsel__set_sample_bit(evsel, ID); + evsel->attr.read_format |= PERF_FORMAT_ID; +} + void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { evsel->idx = idx; evsel->attr = *attr; + evsel->leader = evsel; INIT_LIST_HEAD(&evsel->node); hists__init(&evsel->hists); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); @@ -404,20 +434,70 @@ const char *perf_evsel__name(struct perf_evsel *evsel) return evsel->name ?: "unknown"; } -void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, - struct perf_evsel *first) +const char *perf_evsel__group_name(struct perf_evsel *evsel) +{ + return evsel->group_name ?: "anon group"; +} + +int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) +{ + int ret; + struct perf_evsel *pos; + const char *group_name = perf_evsel__group_name(evsel); + + ret = scnprintf(buf, size, "%s", group_name); + + ret += scnprintf(buf + ret, size - ret, " { %s", + perf_evsel__name(evsel)); + + for_each_group_member(pos, evsel) + ret += scnprintf(buf + ret, size - ret, ", %s", + perf_evsel__name(pos)); + + ret += scnprintf(buf + ret, size - ret, " }"); + + return ret; +} + +/* + * The enable_on_exec/disabled value strategy: + * + * 1) For any type of traced program: + * - all independent events and group leaders are disabled + * - all group members are enabled + * + * Group members are ruled by group leaders. They need to + * be enabled, because the group scheduling relies on that. + * + * 2) For traced programs executed by perf: + * - all independent events and group leaders have + * enable_on_exec set + * - we don't specifically enable or disable any event during + * the record command + * + * Independent events and group leaders are initially disabled + * and get enabled by exec. Group members are ruled by group + * leaders as stated in 1). + * + * 3) For traced programs attached by perf (pid/tid): + * - we specifically enable or disable all events during + * the record command + * + * When attaching events to already running traced we + * enable/disable events specifically, as there's no + * initial traced exec call. + */ +void perf_evsel__config(struct perf_evsel *evsel, + struct perf_record_opts *opts) { struct perf_event_attr *attr = &evsel->attr; int track = !evsel->idx; /* only the first counter needs these */ - attr->disabled = 1; - attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1; + attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; attr->inherit = !opts->no_inherit; - attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | - PERF_FORMAT_TOTAL_TIME_RUNNING | - PERF_FORMAT_ID; - attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID; + perf_evsel__set_sample_bit(evsel, IP); + perf_evsel__set_sample_bit(evsel, TID); /* * We default some events to a 1 default interval. But keep @@ -426,7 +506,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, if (!attr->sample_period || (opts->user_freq != UINT_MAX && opts->user_interval != ULLONG_MAX)) { if (opts->freq) { - attr->sample_type |= PERF_SAMPLE_PERIOD; + perf_evsel__set_sample_bit(evsel, PERIOD); attr->freq = 1; attr->sample_freq = opts->freq; } else { @@ -441,16 +521,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, attr->inherit_stat = 1; if (opts->sample_address) { - attr->sample_type |= PERF_SAMPLE_ADDR; + perf_evsel__set_sample_bit(evsel, ADDR); attr->mmap_data = track; } if (opts->call_graph) { - attr->sample_type |= PERF_SAMPLE_CALLCHAIN; + perf_evsel__set_sample_bit(evsel, CALLCHAIN); if (opts->call_graph == CALLCHAIN_DWARF) { - attr->sample_type |= PERF_SAMPLE_REGS_USER | - PERF_SAMPLE_STACK_USER; + perf_evsel__set_sample_bit(evsel, REGS_USER); + perf_evsel__set_sample_bit(evsel, STACK_USER); attr->sample_regs_user = PERF_REGS_MASK; attr->sample_stack_user = opts->stack_dump_size; attr->exclude_callchain_user = 1; @@ -458,20 +538,20 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, } if (perf_target__has_cpu(&opts->target)) - attr->sample_type |= PERF_SAMPLE_CPU; + perf_evsel__set_sample_bit(evsel, CPU); if (opts->period) - attr->sample_type |= PERF_SAMPLE_PERIOD; + perf_evsel__set_sample_bit(evsel, PERIOD); - if (!opts->sample_id_all_missing && + if (!perf_missing_features.sample_id_all && (opts->sample_time || !opts->no_inherit || perf_target__has_cpu(&opts->target))) - attr->sample_type |= PERF_SAMPLE_TIME; + perf_evsel__set_sample_bit(evsel, TIME); if (opts->raw_samples) { - attr->sample_type |= PERF_SAMPLE_TIME; - attr->sample_type |= PERF_SAMPLE_RAW; - attr->sample_type |= PERF_SAMPLE_CPU; + perf_evsel__set_sample_bit(evsel, TIME); + perf_evsel__set_sample_bit(evsel, RAW); + perf_evsel__set_sample_bit(evsel, CPU); } if (opts->no_delay) { @@ -479,17 +559,28 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, attr->wakeup_events = 1; } if (opts->branch_stack) { - attr->sample_type |= PERF_SAMPLE_BRANCH_STACK; + perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = opts->branch_stack; } attr->mmap = track; attr->comm = track; - if (perf_target__none(&opts->target) && - (!opts->group || evsel == first)) { + /* + * XXX see the function comment above + * + * Disabling only independent events or group leaders, + * keeping group members enabled. + */ + if (perf_evsel__is_group_leader(evsel)) + attr->disabled = 1; + + /* + * Setting enable_on_exec for independent events and + * group leaders for traced executed by perf. + */ + if (perf_target__none(&opts->target) && perf_evsel__is_group_leader(evsel)) attr->enable_on_exec = 1; - } } int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -574,6 +665,11 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) } } +void perf_evsel__free_counts(struct perf_evsel *evsel) +{ + free(evsel->counts); +} + void perf_evsel__exit(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); @@ -593,6 +689,28 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } +static inline void compute_deltas(struct perf_evsel *evsel, + int cpu, + struct perf_counts_values *count) +{ + struct perf_counts_values tmp; + + if (!evsel->prev_raw_counts) + return; + + if (cpu == -1) { + tmp = evsel->prev_raw_counts->aggr; + evsel->prev_raw_counts->aggr = *count; + } else { + tmp = evsel->prev_raw_counts->cpu[cpu]; + evsel->prev_raw_counts->cpu[cpu] = *count; + } + + count->val = count->val - tmp.val; + count->ena = count->ena - tmp.ena; + count->run = count->run - tmp.run; +} + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale) { @@ -608,6 +726,8 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) return -errno; + compute_deltas(evsel, cpu, &count); + if (scale) { if (count.run == 0) count.val = 0; @@ -646,6 +766,8 @@ int __perf_evsel__read(struct perf_evsel *evsel, } } + compute_deltas(evsel, -1, aggr); + evsel->counts->scaled = 0; if (scale) { if (aggr->run == 0) { @@ -669,7 +791,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) struct perf_evsel *leader = evsel->leader; int fd; - if (!leader) + if (perf_evsel__is_group_leader(evsel)) return -1; /* @@ -700,6 +822,13 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, pid = evsel->cgrp->fd; } +fallback_missing_features: + if (perf_missing_features.exclude_guest) + evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; +retry_sample_id: + if (perf_missing_features.sample_id_all) + evsel->attr.sample_id_all = 0; + for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < threads->nr; thread++) { @@ -716,13 +845,26 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, group_fd, flags); if (FD(evsel, cpu, thread) < 0) { err = -errno; - goto out_close; + goto try_fallback; } } } return 0; +try_fallback: + if (err != -EINVAL || cpu > 0 || thread > 0) + goto out_close; + + if (!perf_missing_features.exclude_guest && + (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { + perf_missing_features.exclude_guest = true; + goto fallback_missing_features; + } else if (!perf_missing_features.sample_id_all) { + perf_missing_features.sample_id_all = true; + goto retry_sample_id; + } + out_close: do { while (--thread >= 0) { @@ -1167,3 +1309,225 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return 0; } + +static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (!*first) { + ret += fprintf(fp, ","); + } else { + ret += fprintf(fp, ":"); + *first = false; + } + + va_start(args, fmt); + ret += vfprintf(fp, fmt, args); + va_end(args); + return ret; +} + +static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value) +{ + if (value == 0) + return 0; + + return comma_fprintf(fp, first, " %s: %" PRIu64, field, value); +} + +#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field) + +struct bit_names { + int bit; + const char *name; +}; + +static int bits__fprintf(FILE *fp, const char *field, u64 value, + struct bit_names *bits, bool *first) +{ + int i = 0, printed = comma_fprintf(fp, first, " %s: ", field); + bool first_bit = true; + + do { + if (value & bits[i].bit) { + printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name); + first_bit = false; + } + } while (bits[++i].name != NULL); + + return printed; +} + +static int sample_type__fprintf(FILE *fp, bool *first, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_##n, #n } + struct bit_names bits[] = { + bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), + bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), + bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), + bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + { .name = NULL, } + }; +#undef bit_name + return bits__fprintf(fp, "sample_type", value, bits, first); +} + +static int read_format__fprintf(FILE *fp, bool *first, u64 value) +{ +#define bit_name(n) { PERF_FORMAT_##n, #n } + struct bit_names bits[] = { + bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), + bit_name(ID), bit_name(GROUP), + { .name = NULL, } + }; +#undef bit_name + return bits__fprintf(fp, "read_format", value, bits, first); +} + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp) +{ + bool first = true; + int printed = 0; + + if (details->event_group) { + struct perf_evsel *pos; + + if (!perf_evsel__is_group_leader(evsel)) + return 0; + + if (evsel->nr_members > 1) + printed += fprintf(fp, "%s{", evsel->group_name ?: ""); + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + for_each_group_member(pos, evsel) + printed += fprintf(fp, ",%s", perf_evsel__name(pos)); + + if (evsel->nr_members > 1) + printed += fprintf(fp, "}"); + goto out; + } + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + + if (details->verbose || details->freq) { + printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64, + (u64)evsel->attr.sample_freq); + } + + if (details->verbose) { + if_print(type); + if_print(config); + if_print(config1); + if_print(config2); + if_print(size); + printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type); + if (evsel->attr.read_format) + printed += read_format__fprintf(fp, &first, evsel->attr.read_format); + if_print(disabled); + if_print(inherit); + if_print(pinned); + if_print(exclusive); + if_print(exclude_user); + if_print(exclude_kernel); + if_print(exclude_hv); + if_print(exclude_idle); + if_print(mmap); + if_print(comm); + if_print(freq); + if_print(inherit_stat); + if_print(enable_on_exec); + if_print(task); + if_print(watermark); + if_print(precise_ip); + if_print(mmap_data); + if_print(sample_id_all); + if_print(exclude_host); + if_print(exclude_guest); + if_print(__reserved_1); + if_print(wakeup_events); + if_print(bp_type); + if_print(branch_sample_type); + } +out: + fputc('\n', fp); + return ++printed; +} + +bool perf_evsel__fallback(struct perf_evsel *evsel, int err, + char *msg, size_t msgsize) +{ + if ((err == ENOENT || err == ENXIO) && + evsel->attr.type == PERF_TYPE_HARDWARE && + evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { + /* + * If it's cycles then fall back to hrtimer based + * cpu-clock-tick sw counter, which is always available even if + * no PMU support. + * + * PPC returns ENXIO until 2.6.37 (behavior changed with commit + * b0a873e). + */ + scnprintf(msg, msgsize, "%s", +"The cycles event is not supported, trying to fall back to cpu-clock-ticks"); + + evsel->attr.type = PERF_TYPE_SOFTWARE; + evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK; + + free(evsel->name); + evsel->name = NULL; + return true; + } + + return false; +} + +int perf_evsel__open_strerror(struct perf_evsel *evsel, + struct perf_target *target, + int err, char *msg, size_t size) +{ + switch (err) { + case EPERM: + case EACCES: + return scnprintf(msg, size, "%s", + "You may not have permission to collect %sstats.\n" + "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" + " -1 - Not paranoid at all\n" + " 0 - Disallow raw tracepoint access for unpriv\n" + " 1 - Disallow cpu events for unpriv\n" + " 2 - Disallow kernel profiling for unpriv", + target->system_wide ? "system-wide " : ""); + case ENOENT: + return scnprintf(msg, size, "The %s event is not supported.", + perf_evsel__name(evsel)); + case EMFILE: + return scnprintf(msg, size, "%s", + "Too many events are opened.\n" + "Try again after reducing the number of events."); + case ENODEV: + if (target->cpu_list) + return scnprintf(msg, size, "%s", + "No such device - did you specify an out-of-range profile CPU?\n"); + break; + case EOPNOTSUPP: + if (evsel->attr.precise_ip) + return scnprintf(msg, size, "%s", + "\'precise\' request may not be supported. Try removing 'p' modifier."); +#if defined(__i386__) || defined(__x86_64__) + if (evsel->attr.type == PERF_TYPE_HARDWARE) + return scnprintf(msg, size, "%s", + "No hardware sampling interrupt available.\n" + "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it."); +#endif + break; + default: + break; + } + + return scnprintf(msg, size, + "The sys_perf_event_open() syscall returned with %d (%s) for event (%s). \n" + "/bin/dmesg may provide additional information.\n" + "No CONFIG_PERF_EVENTS=y kernel support configured?\n", + err, strerror(err), perf_evsel__name(evsel)); +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 6f94d6dea00..52021c3087d 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -3,7 +3,8 @@ #include <linux/list.h> #include <stdbool.h> -#include "../../../include/uapi/linux/perf_event.h" +#include <stddef.h> +#include <linux/perf_event.h> #include "types.h" #include "xyarray.h" #include "cgroup.h" @@ -52,6 +53,7 @@ struct perf_evsel { struct xyarray *sample_id; u64 *id; struct perf_counts *counts; + struct perf_counts *prev_raw_counts; int idx; u32 ids; struct hists hists; @@ -72,10 +74,13 @@ struct perf_evsel { bool needs_swap; /* parse modifier helper */ int exclude_GH; + int nr_members; struct perf_evsel *leader; char *group_name; }; +#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists) + struct cpu_map; struct thread_map; struct perf_evlist; @@ -92,8 +97,7 @@ void perf_evsel__exit(struct perf_evsel *evsel); void perf_evsel__delete(struct perf_evsel *evsel); void perf_evsel__config(struct perf_evsel *evsel, - struct perf_record_opts *opts, - struct perf_evsel *first); + struct perf_record_opts *opts); bool perf_evsel__is_cache_op_valid(u8 type, u8 op); @@ -110,14 +114,30 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX]; int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *perf_evsel__name(struct perf_evsel *evsel); +const char *perf_evsel__group_name(struct perf_evsel *evsel); +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__free_fd(struct perf_evsel *evsel); void perf_evsel__free_id(struct perf_evsel *evsel); +void perf_evsel__free_counts(struct perf_evsel *evsel); void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit); +void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit); + +#define perf_evsel__set_sample_bit(evsel, bit) \ + __perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit) + +#define perf_evsel__reset_sample_bit(evsel, bit) \ + __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit) + +void perf_evsel__set_sample_id(struct perf_evsel *evsel); + int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, const char *filter); @@ -225,4 +245,35 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel) { return list_entry(evsel->node.next, struct perf_evsel, node); } + +static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) +{ + return evsel->leader == evsel; +} + +struct perf_attr_details { + bool freq; + bool verbose; + bool event_group; +}; + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp); + +bool perf_evsel__fallback(struct perf_evsel *evsel, int err, + char *msg, size_t msgsize); +int perf_evsel__open_strerror(struct perf_evsel *evsel, + struct perf_target *target, + int err, char *msg, size_t size); + +static inline int perf_evsel__group_idx(struct perf_evsel *evsel) +{ + return evsel->idx - evsel->leader->idx; +} + +#define for_each_group_member(_evsel, _leader) \ +for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ + (_evsel) && (_evsel)->leader == (_leader); \ + (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 7daad237dea..f4bfd79ef6a 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -23,6 +23,7 @@ #include "pmu.h" #include "vdso.h" #include "strbuf.h" +#include "build-id.h" static bool no_buildid_cache = false; @@ -147,7 +148,7 @@ static char *do_read_string(int fd, struct perf_header *ph) u32 len; char *buf; - sz = read(fd, &len, sizeof(len)); + sz = readn(fd, &len, sizeof(len)); if (sz < (ssize_t)sizeof(len)) return NULL; @@ -158,7 +159,7 @@ static char *do_read_string(int fd, struct perf_header *ph) if (!buf) return NULL; - ret = read(fd, buf, len); + ret = readn(fd, buf, len); if (ret == (ssize_t)len) { /* * strings are padded by zeroes @@ -286,12 +287,12 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd) struct perf_session *session = container_of(header, struct perf_session, header); struct rb_node *nd; - int err = machine__write_buildid_table(&session->host_machine, fd); + int err = machine__write_buildid_table(&session->machines.host, fd); if (err) return err; - for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); err = machine__write_buildid_table(pos, fd); if (err) @@ -312,7 +313,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, if (is_kallsyms) { if (symbol_conf.kptr_restrict) { pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); - return 0; + err = 0; + goto out_free; } realname = (char *) name; } else @@ -447,9 +449,9 @@ static int perf_session__cache_build_ids(struct perf_session *session) if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&session->host_machine, debugdir); + ret = machine__cache_build_ids(&session->machines.host, debugdir); - for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__cache_build_ids(pos, debugdir); } @@ -466,9 +468,9 @@ static bool machine__read_build_ids(struct machine *machine, bool with_hits) static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) { struct rb_node *nd; - bool ret = machine__read_build_ids(&session->host_machine, with_hits); + bool ret = machine__read_build_ids(&session->machines.host, with_hits); - for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__read_build_ids(pos, with_hits); } @@ -953,6 +955,7 @@ static int write_topo_node(int fd, int node) } fclose(fp); + fp = NULL; ret = do_write(fd, &mem_total, sizeof(u64)); if (ret) @@ -979,7 +982,8 @@ static int write_topo_node(int fd, int node) ret = do_write_string(fd, buf); done: free(buf); - fclose(fp); + if (fp) + fclose(fp); return ret; } @@ -1050,16 +1054,25 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, struct perf_pmu *pmu = NULL; off_t offset = lseek(fd, 0, SEEK_CUR); __u32 pmu_num = 0; + int ret; /* write real pmu_num later */ - do_write(fd, &pmu_num, sizeof(pmu_num)); + ret = do_write(fd, &pmu_num, sizeof(pmu_num)); + if (ret < 0) + return ret; while ((pmu = perf_pmu__scan(pmu))) { if (!pmu->name) continue; pmu_num++; - do_write(fd, &pmu->type, sizeof(pmu->type)); - do_write_string(fd, pmu->name); + + ret = do_write(fd, &pmu->type, sizeof(pmu->type)); + if (ret < 0) + return ret; + + ret = do_write_string(fd, pmu->name); + if (ret < 0) + return ret; } if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) { @@ -1072,6 +1085,52 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, } /* + * File format: + * + * struct group_descs { + * u32 nr_groups; + * struct group_desc { + * char name[]; + * u32 leader_idx; + * u32 nr_members; + * }[nr_groups]; + * }; + */ +static int write_group_desc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist) +{ + u32 nr_groups = evlist->nr_groups; + struct perf_evsel *evsel; + int ret; + + ret = do_write(fd, &nr_groups, sizeof(nr_groups)); + if (ret < 0) + return ret; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (perf_evsel__is_group_leader(evsel) && + evsel->nr_members > 1) { + const char *name = evsel->group_name ?: "{anon_group}"; + u32 leader_idx = evsel->idx; + u32 nr_members = evsel->nr_members; + + ret = do_write_string(fd, name); + if (ret < 0) + return ret; + + ret = do_write(fd, &leader_idx, sizeof(leader_idx)); + if (ret < 0) + return ret; + + ret = do_write(fd, &nr_members, sizeof(nr_members)); + if (ret < 0) + return ret; + } + } + return 0; +} + +/* * default get_cpuid(): nothing gets recorded * actual implementation must be in arch/$(ARCH)/util/header.c */ @@ -1208,14 +1267,14 @@ read_event_desc(struct perf_header *ph, int fd) size_t msz; /* number of events */ - ret = read(fd, &nre, sizeof(nre)); + ret = readn(fd, &nre, sizeof(nre)); if (ret != (ssize_t)sizeof(nre)) goto error; if (ph->needs_swap) nre = bswap_32(nre); - ret = read(fd, &sz, sizeof(sz)); + ret = readn(fd, &sz, sizeof(sz)); if (ret != (ssize_t)sizeof(sz)) goto error; @@ -1243,7 +1302,7 @@ read_event_desc(struct perf_header *ph, int fd) * must read entire on-file attr struct to * sync up with layout. */ - ret = read(fd, buf, sz); + ret = readn(fd, buf, sz); if (ret != (ssize_t)sz) goto error; @@ -1252,7 +1311,7 @@ read_event_desc(struct perf_header *ph, int fd) memcpy(&evsel->attr, buf, msz); - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != (ssize_t)sizeof(nr)) goto error; @@ -1273,7 +1332,7 @@ read_event_desc(struct perf_header *ph, int fd) evsel->id = id; for (j = 0 ; j < nr; j++) { - ret = read(fd, id, sizeof(*id)); + ret = readn(fd, id, sizeof(*id)); if (ret != (ssize_t)sizeof(*id)) goto error; if (ph->needs_swap) @@ -1378,6 +1437,8 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, str = tmp + 1; fprintf(fp, "# node%u cpu list : %s\n", c, str); + + str += strlen(str) + 1; } return; error: @@ -1432,6 +1493,31 @@ error: fprintf(fp, "# pmu mappings: unable to read\n"); } +static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + struct perf_session *session; + struct perf_evsel *evsel; + u32 nr = 0; + + session = container_of(ph, struct perf_session, header); + + list_for_each_entry(evsel, &session->evlist->entries, node) { + if (perf_evsel__is_group_leader(evsel) && + evsel->nr_members > 1) { + fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", + perf_evsel__name(evsel)); + + nr = evsel->nr_members - 1; + } else if (nr) { + fprintf(fp, ",%s", perf_evsel__name(evsel)); + + if (--nr == 0) + fprintf(fp, "}\n"); + } + } +} + static int __event_process_build_id(struct build_id_event *bev, char *filename, struct perf_session *session) @@ -1503,14 +1589,14 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, while (offset < limit) { ssize_t len; - if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) + if (readn(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) return -1; if (header->needs_swap) perf_event_header__bswap(&old_bev.header); len = old_bev.header.size - sizeof(old_bev); - if (read(input, filename, len) != len) + if (readn(input, filename, len) != len) return -1; bev.header = old_bev.header; @@ -1545,14 +1631,14 @@ static int perf_header__read_build_ids(struct perf_header *header, while (offset < limit) { ssize_t len; - if (read(input, &bev, sizeof(bev)) != sizeof(bev)) + if (readn(input, &bev, sizeof(bev)) != sizeof(bev)) goto out; if (header->needs_swap) perf_event_header__bswap(&bev.header); len = bev.header.size - sizeof(bev); - if (read(input, filename, len) != len) + if (readn(input, filename, len) != len) goto out; /* * The a1645ce1 changeset: @@ -1638,7 +1724,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, size_t ret; u32 nr; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1647,7 +1733,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, ph->env.nr_cpus_online = nr; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1681,7 +1767,7 @@ static int process_total_mem(struct perf_file_section *section __maybe_unused, uint64_t mem; size_t ret; - ret = read(fd, &mem, sizeof(mem)); + ret = readn(fd, &mem, sizeof(mem)); if (ret != sizeof(mem)) return -1; @@ -1753,7 +1839,7 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused, u32 nr, i; struct strbuf sb; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1789,7 +1875,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused char *str; struct strbuf sb; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1810,7 +1896,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused } ph->env.sibling_cores = strbuf_detach(&sb, NULL); - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1847,7 +1933,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse struct strbuf sb; /* nr nodes */ - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) goto error; @@ -1859,15 +1945,15 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse for (i = 0; i < nr; i++) { /* node number */ - ret = read(fd, &node, sizeof(node)); + ret = readn(fd, &node, sizeof(node)); if (ret != sizeof(node)) goto error; - ret = read(fd, &mem_total, sizeof(u64)); + ret = readn(fd, &mem_total, sizeof(u64)); if (ret != sizeof(u64)) goto error; - ret = read(fd, &mem_free, sizeof(u64)); + ret = readn(fd, &mem_free, sizeof(u64)); if (ret != sizeof(u64)) goto error; @@ -1906,7 +1992,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused u32 type; struct strbuf sb; - ret = read(fd, &pmu_num, sizeof(pmu_num)); + ret = readn(fd, &pmu_num, sizeof(pmu_num)); if (ret != sizeof(pmu_num)) return -1; @@ -1922,7 +2008,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused strbuf_init(&sb, 128); while (pmu_num) { - if (read(fd, &type, sizeof(type)) != sizeof(type)) + if (readn(fd, &type, sizeof(type)) != sizeof(type)) goto error; if (ph->needs_swap) type = bswap_32(type); @@ -1946,6 +2032,98 @@ error: return -1; } +static int process_group_desc(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret = -1; + u32 i, nr, nr_groups; + struct perf_session *session; + struct perf_evsel *evsel, *leader = NULL; + struct group_desc { + char *name; + u32 leader_idx; + u32 nr_members; + } *desc; + + if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups)) + return -1; + + if (ph->needs_swap) + nr_groups = bswap_32(nr_groups); + + ph->env.nr_groups = nr_groups; + if (!nr_groups) { + pr_debug("group desc not available\n"); + return 0; + } + + desc = calloc(nr_groups, sizeof(*desc)); + if (!desc) + return -1; + + for (i = 0; i < nr_groups; i++) { + desc[i].name = do_read_string(fd, ph); + if (!desc[i].name) + goto out_free; + + if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32)) + goto out_free; + + if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32)) + goto out_free; + + if (ph->needs_swap) { + desc[i].leader_idx = bswap_32(desc[i].leader_idx); + desc[i].nr_members = bswap_32(desc[i].nr_members); + } + } + + /* + * Rebuild group relationship based on the group_desc + */ + session = container_of(ph, struct perf_session, header); + session->evlist->nr_groups = nr_groups; + + i = nr = 0; + list_for_each_entry(evsel, &session->evlist->entries, node) { + if (evsel->idx == (int) desc[i].leader_idx) { + evsel->leader = evsel; + /* {anon_group} is a dummy name */ + if (strcmp(desc[i].name, "{anon_group}")) + evsel->group_name = desc[i].name; + evsel->nr_members = desc[i].nr_members; + + if (i >= nr_groups || nr > 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + leader = evsel; + nr = evsel->nr_members - 1; + i++; + } else if (nr) { + /* This is a group member */ + evsel->leader = leader; + + nr--; + } + } + + if (i != nr_groups || nr != 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + ret = 0; +out_free: + while ((int) --i >= 0) + free(desc[i].name); + free(desc); + + return ret; +} + struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); @@ -1985,6 +2163,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), FEAT_OPA(HEADER_BRANCH_STACK, branch_stack), FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings), + FEAT_OPP(HEADER_GROUP_DESC, group_desc), }; struct header_print_data { @@ -2074,7 +2253,7 @@ static int perf_header__adds_write(struct perf_header *header, if (!nr_sections) return 0; - feat_sec = p = calloc(sizeof(*feat_sec), nr_sections); + feat_sec = p = calloc(nr_sections, sizeof(*feat_sec)); if (feat_sec == NULL) return -ENOMEM; @@ -2246,7 +2425,7 @@ int perf_header__process_sections(struct perf_header *header, int fd, if (!nr_sections) return 0; - feat_sec = sec = calloc(sizeof(*feat_sec), nr_sections); + feat_sec = sec = calloc(nr_sections, sizeof(*feat_sec)); if (!feat_sec) return -1; @@ -2340,6 +2519,16 @@ static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph) return -1; } +bool is_perf_magic(u64 magic) +{ + if (!memcmp(&magic, __perf_magic1, sizeof(magic)) + || magic == __perf_magic2 + || magic == __perf_magic2_sw) + return true; + + return false; +} + static int check_magic_endian(u64 magic, uint64_t hdr_sz, bool is_pipe, struct perf_header *ph) { @@ -2899,16 +3088,22 @@ int perf_event__process_tracing_data(union perf_event *event, session->repipe); padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; - if (read(session->fd, buf, padding) < 0) - die("reading input file"); + if (readn(session->fd, buf, padding) < 0) { + pr_err("%s: reading input file", __func__); + return -1; + } if (session->repipe) { int retw = write(STDOUT_FILENO, buf, padding); - if (retw <= 0 || retw != padding) - die("repiping tracing data padding"); + if (retw <= 0 || retw != padding) { + pr_err("%s: repiping tracing data padding", __func__); + return -1; + } } - if (size_read + padding != size) - die("tracing data size mismatch"); + if (size_read + padding != size) { + pr_err("%s: tracing data size mismatch", __func__); + return -1; + } perf_evlist__prepare_tracepoint_events(session->evlist, session->pevent); diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 879d215cdac..c9fc55cada6 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -1,7 +1,7 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> #include "types.h" @@ -29,6 +29,7 @@ enum { HEADER_NUMA_TOPOLOGY, HEADER_BRANCH_STACK, HEADER_PMU_MAPPINGS, + HEADER_GROUP_DESC, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -79,6 +80,7 @@ struct perf_session_env { char *numa_nodes; int nr_pmu_mappings; char *pmu_mappings; + int nr_groups; }; struct perf_header { @@ -154,6 +156,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, int perf_event__process_build_id(struct perf_tool *tool, union perf_event *event, struct perf_session *session); +bool is_perf_magic(u64 magic); /* * arch specific callback diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 277947a669b..f855941bebe 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -4,6 +4,7 @@ #include "hist.h" #include "session.h" #include "sort.h" +#include "evsel.h" #include <math.h> static bool hists__filter_entry_by_dso(struct hists *hists, @@ -82,6 +83,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_DSO, len); } + if (h->parent) + hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen); + if (h->branch_info) { int symlen; /* @@ -242,14 +246,24 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) if (he->ms.map) he->ms.map->referenced = true; + + if (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 (symbol_conf.use_callchain) callchain_init(he->callchain); + + INIT_LIST_HEAD(&he->pairs.node); } return he; } -static void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) +void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) { if (!h->filtered) { hists__calc_col_len(hists, h); @@ -283,7 +297,13 @@ static struct hist_entry *add_hist_entry(struct hists *hists, parent = *p; he = rb_entry(parent, struct hist_entry, rb_node_in); - cmp = hist_entry__cmp(entry, he); + /* + * Make sure that it receives arguments in a same order as + * hist_entry__collapse() so that we can use an appropriate + * function when searching an entry regardless which sort + * keys were used. + */ + cmp = hist_entry__cmp(he, entry); if (!cmp) { he_stat__add_period(&he->stat, period); @@ -410,6 +430,7 @@ 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); } @@ -520,6 +541,62 @@ void hists__collapse_resort_threaded(struct hists *hists) * reverse the map, sort on period. */ +static int period_cmp(u64 period_a, u64 period_b) +{ + if (period_a > period_b) + return 1; + if (period_a < period_b) + return -1; + return 0; +} + +static int hist_entry__sort_on_period(struct hist_entry *a, + struct hist_entry *b) +{ + int ret; + int i, nr_members; + struct perf_evsel *evsel; + struct hist_entry *pair; + u64 *periods_a, *periods_b; + + ret = period_cmp(a->stat.period, b->stat.period); + if (ret || !symbol_conf.event_group) + return ret; + + evsel = hists_to_evsel(a->hists); + nr_members = evsel->nr_members; + if (nr_members <= 1) + return ret; + + periods_a = zalloc(sizeof(periods_a) * nr_members); + periods_b = zalloc(sizeof(periods_b) * nr_members); + + if (!periods_a || !periods_b) + goto out; + + list_for_each_entry(pair, &a->pairs.head, pairs.node) { + evsel = hists_to_evsel(pair->hists); + periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period; + } + + list_for_each_entry(pair, &b->pairs.head, pairs.node) { + evsel = hists_to_evsel(pair->hists); + periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period; + } + + for (i = 1; i < nr_members; i++) { + ret = period_cmp(periods_a[i], periods_b[i]); + if (ret) + break; + } + +out: + free(periods_a); + free(periods_b); + + return ret; +} + static void __hists__insert_output_entry(struct rb_root *entries, struct hist_entry *he, u64 min_callchain_hits) @@ -536,7 +613,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node); - if (he->stat.period > iter->stat.period) + if (hist_entry__sort_on_period(he, iter) > 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -708,8 +785,134 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize) return symbol__annotate(he->ms.sym, he->ms.map, privsize); } +void events_stats__inc(struct events_stats *stats, u32 type) +{ + ++stats->nr_events[0]; + ++stats->nr_events[type]; +} + void hists__inc_nr_events(struct hists *hists, u32 type) { - ++hists->stats.nr_events[0]; - ++hists->stats.nr_events[type]; + events_stats__inc(&hists->stats, type); +} + +static struct hist_entry *hists__add_dummy_entry(struct hists *hists, + struct hist_entry *pair) +{ + struct rb_root *root; + struct rb_node **p; + struct rb_node *parent = NULL; + struct hist_entry *he; + int cmp; + + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + p = &root->rb_node; + + while (*p != NULL) { + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node_in); + + cmp = hist_entry__collapse(he, pair); + + if (!cmp) + goto out; + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + he = hist_entry__new(pair); + if (he) { + memset(&he->stat, 0, sizeof(he->stat)); + he->hists = hists; + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, root); + hists__inc_nr_entries(hists, he); + } +out: + return he; +} + +static struct hist_entry *hists__find_entry(struct hists *hists, + struct hist_entry *he) +{ + struct rb_node *n; + + if (sort__need_collapse) + n = hists->entries_collapsed.rb_node; + else + n = hists->entries_in->rb_node; + + while (n) { + struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in); + int64_t cmp = hist_entry__collapse(iter, he); + + if (cmp < 0) + n = n->rb_left; + else if (cmp > 0) + n = n->rb_right; + else + return iter; + } + + return NULL; +} + +/* + * Look for pairs to link to the leader buckets (hist_entries): + */ +void hists__match(struct hists *leader, struct hists *other) +{ + struct rb_root *root; + struct rb_node *nd; + struct hist_entry *pos, *pair; + + if (sort__need_collapse) + root = &leader->entries_collapsed; + else + root = leader->entries_in; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); + pair = hists__find_entry(other, pos); + + if (pair) + hist_entry__add_pair(pair, pos); + } +} + +/* + * Look for entries in the other hists that are not present in the leader, if + * we find them, just add a dummy entry on the leader hists, with period=0, + * nr_events=0, to serve as the list header. + */ +int hists__link(struct hists *leader, struct hists *other) +{ + struct rb_root *root; + struct rb_node *nd; + struct hist_entry *pos, *pair; + + if (sort__need_collapse) + root = &other->entries_collapsed; + else + root = other->entries_in; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); + + if (!hist_entry__has_pairs(pos)) { + pair = hists__add_dummy_entry(leader, pos); + if (pair == NULL) + return -1; + hist_entry__add_pair(pos, pair); + } + } + + return 0; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 66cb31fe81d..38624686ee9 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <pthread.h> #include "callchain.h" +#include "header.h" extern struct callchain_param callchain_param; @@ -95,8 +96,10 @@ 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); void hists__inc_nr_events(struct hists *self, u32 type); -size_t hists__fprintf_nr_events(struct hists *self, FILE *fp); +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); @@ -114,6 +117,9 @@ bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len); void hists__reset_col_len(struct hists *hists); void hists__calc_col_len(struct hists *hists, struct hist_entry *he); +void hists__match(struct hists *leader, struct hists *other); +int hists__link(struct hists *leader, struct hists *other); + struct perf_hpp { char *buf; size_t size; @@ -122,13 +128,19 @@ struct perf_hpp { }; struct perf_hpp_fmt { - bool cond; int (*header)(struct perf_hpp *hpp); int (*width)(struct perf_hpp *hpp); int (*color)(struct perf_hpp *hpp, struct hist_entry *he); int (*entry)(struct perf_hpp *hpp, struct hist_entry *he); + + struct list_head list; }; +extern struct list_head perf_hpp__list; + +#define perf_hpp__for_each_format(format) \ + list_for_each_entry(format, &perf_hpp__list, list) + extern struct perf_hpp_fmt perf_hpp__format[]; enum { @@ -140,34 +152,44 @@ enum { PERF_HPP__OVERHEAD_GUEST_US, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, + PERF_HPP__PERIOD_BASELINE, PERF_HPP__DELTA, - PERF_HPP__DISPL, + PERF_HPP__RATIO, + PERF_HPP__WEIGHTED_DIFF, + PERF_HPP__FORMULA, PERF_HPP__MAX_INDEX }; void perf_hpp__init(void); -void perf_hpp__column_enable(unsigned col, bool enable); +void perf_hpp__column_register(struct perf_hpp_fmt *format); +void perf_hpp__column_enable(unsigned col); int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, bool color); struct perf_evlist; +struct hist_browser_timer { + void (*timer)(void *arg); + void *arg; + int refresh; +}; + #ifdef NEWT_SUPPORT #include "../ui/keysyms.h" int hist_entry__tui_annotate(struct hist_entry *he, int evidx, - void(*timer)(void *arg), void *arg, int delay_secs); + struct hist_browser_timer *hbt); int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, - void(*timer)(void *arg), void *arg, - int refresh); + struct hist_browser_timer *hbt, + struct perf_session_env *env); +int script_browse(const char *script_opt); #else static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, - void(*timer)(void *arg) __maybe_unused, - void *arg __maybe_unused, - int refresh __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + struct perf_session_env *env __maybe_unused) { return 0; } @@ -175,28 +197,29 @@ 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, - void(*timer)(void *arg) - __maybe_unused, - void *arg __maybe_unused, - int delay_secs __maybe_unused) + struct hist_browser_timer *hbt + __maybe_unused) +{ + return 0; +} + +static inline int script_browse(const char *script_opt __maybe_unused) { return 0; } + #define K_LEFT -1 #define K_RIGHT -2 #endif #ifdef GTK2_SUPPORT int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, - void(*timer)(void *arg), void *arg, - int refresh); + struct hist_browser_timer *hbt __maybe_unused); #else static inline int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, const char *help __maybe_unused, - void(*timer)(void *arg) __maybe_unused, - void *arg __maybe_unused, - int refresh __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused) { return 0; } @@ -204,4 +227,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, unsigned int hists__sort_list_width(struct hists *self); +double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair); +double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair); +s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair); +int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size); +double perf_diff__period_percent(struct hist_entry *he, u64 period); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index a55d8cf083c..45cf10a562b 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -14,6 +14,7 @@ #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) #define for_each_set_bit(bit, addr, size) \ for ((bit) = find_first_bit((addr), (size)); \ diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c index 9d0740024ba..11a8d86f7fe 100644 --- a/tools/perf/util/intlist.c +++ b/tools/perf/util/intlist.c @@ -59,16 +59,40 @@ void intlist__remove(struct intlist *ilist, struct int_node *node) struct int_node *intlist__find(struct intlist *ilist, int i) { - struct int_node *node = NULL; - struct rb_node *rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); + struct int_node *node; + struct rb_node *rb_node; + if (ilist == NULL) + return NULL; + + node = NULL; + rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); if (rb_node) node = container_of(rb_node, struct int_node, rb_node); return node; } -struct intlist *intlist__new(void) +static int intlist__parse_list(struct intlist *ilist, const char *s) +{ + char *sep; + int err; + + do { + long value = strtol(s, &sep, 10); + err = -EINVAL; + if (*sep != ',' && *sep != '\0') + break; + err = intlist__add(ilist, value); + if (err) + break; + s = sep + 1; + } while (*sep != '\0'); + + return err; +} + +struct intlist *intlist__new(const char *slist) { struct intlist *ilist = malloc(sizeof(*ilist)); @@ -77,9 +101,15 @@ struct intlist *intlist__new(void) ilist->rblist.node_cmp = intlist__node_cmp; ilist->rblist.node_new = intlist__node_new; ilist->rblist.node_delete = intlist__node_delete; + + if (slist && intlist__parse_list(ilist, slist)) + goto out_delete; } return ilist; +out_delete: + intlist__delete(ilist); + return NULL; } void intlist__delete(struct intlist *ilist) diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h index 6d63ab90db5..62351dad848 100644 --- a/tools/perf/util/intlist.h +++ b/tools/perf/util/intlist.h @@ -15,7 +15,7 @@ struct intlist { struct rblist rblist; }; -struct intlist *intlist__new(void); +struct intlist *intlist__new(const char *slist); void intlist__delete(struct intlist *ilist); void intlist__remove(struct intlist *ilist, struct int_node *in); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c new file mode 100644 index 00000000000..efdb38e65a9 --- /dev/null +++ b/tools/perf/util/machine.c @@ -0,0 +1,1226 @@ +#include "callchain.h" +#include "debug.h" +#include "event.h" +#include "evsel.h" +#include "hist.h" +#include "machine.h" +#include "map.h" +#include "sort.h" +#include "strlist.h" +#include "thread.h" +#include <stdbool.h> +#include "unwind.h" + +int machine__init(struct machine *machine, const char *root_dir, pid_t pid) +{ + map_groups__init(&machine->kmaps); + RB_CLEAR_NODE(&machine->rb_node); + INIT_LIST_HEAD(&machine->user_dsos); + INIT_LIST_HEAD(&machine->kernel_dsos); + + machine->threads = RB_ROOT; + INIT_LIST_HEAD(&machine->dead_threads); + machine->last_match = NULL; + + machine->kmaps.machine = machine; + machine->pid = pid; + + machine->root_dir = strdup(root_dir); + if (machine->root_dir == NULL) + return -ENOMEM; + + if (pid != HOST_KERNEL_ID) { + struct thread *thread = machine__findnew_thread(machine, pid); + char comm[64]; + + if (thread == NULL) + return -ENOMEM; + + snprintf(comm, sizeof(comm), "[guest/%d]", pid); + thread__set_comm(thread, comm); + } + + return 0; +} + +static void dsos__delete(struct list_head *dsos) +{ + struct dso *pos, *n; + + list_for_each_entry_safe(pos, n, dsos, node) { + list_del(&pos->node); + dso__delete(pos); + } +} + +void machine__delete_dead_threads(struct machine *machine) +{ + struct thread *n, *t; + + list_for_each_entry_safe(t, n, &machine->dead_threads, node) { + list_del(&t->node); + thread__delete(t); + } +} + +void machine__delete_threads(struct machine *machine) +{ + struct rb_node *nd = rb_first(&machine->threads); + + while (nd) { + struct thread *t = rb_entry(nd, struct thread, rb_node); + + rb_erase(&t->rb_node, &machine->threads); + nd = rb_next(nd); + thread__delete(t); + } +} + +void machine__exit(struct machine *machine) +{ + map_groups__exit(&machine->kmaps); + dsos__delete(&machine->user_dsos); + dsos__delete(&machine->kernel_dsos); + free(machine->root_dir); + machine->root_dir = NULL; +} + +void machine__delete(struct machine *machine) +{ + machine__exit(machine); + free(machine); +} + +void machines__init(struct machines *machines) +{ + machine__init(&machines->host, "", HOST_KERNEL_ID); + machines->guests = RB_ROOT; +} + +void machines__exit(struct machines *machines) +{ + machine__exit(&machines->host); + /* XXX exit guest */ +} + +struct machine *machines__add(struct machines *machines, pid_t pid, + const char *root_dir) +{ + struct rb_node **p = &machines->guests.rb_node; + struct rb_node *parent = NULL; + struct machine *pos, *machine = malloc(sizeof(*machine)); + + if (machine == NULL) + return NULL; + + if (machine__init(machine, root_dir, pid) != 0) { + free(machine); + return NULL; + } + + while (*p != NULL) { + parent = *p; + pos = rb_entry(parent, struct machine, rb_node); + if (pid < pos->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&machine->rb_node, parent, p); + rb_insert_color(&machine->rb_node, &machines->guests); + + return machine; +} + +struct machine *machines__find(struct machines *machines, pid_t pid) +{ + struct rb_node **p = &machines->guests.rb_node; + struct rb_node *parent = NULL; + struct machine *machine; + struct machine *default_machine = NULL; + + if (pid == HOST_KERNEL_ID) + return &machines->host; + + while (*p != NULL) { + parent = *p; + machine = rb_entry(parent, struct machine, rb_node); + if (pid < machine->pid) + p = &(*p)->rb_left; + else if (pid > machine->pid) + p = &(*p)->rb_right; + else + return machine; + if (!machine->pid) + default_machine = machine; + } + + return default_machine; +} + +struct machine *machines__findnew(struct machines *machines, pid_t pid) +{ + char path[PATH_MAX]; + const char *root_dir = ""; + struct machine *machine = machines__find(machines, pid); + + if (machine && (machine->pid == pid)) + goto out; + + if ((pid != HOST_KERNEL_ID) && + (pid != DEFAULT_GUEST_KERNEL_ID) && + (symbol_conf.guestmount)) { + sprintf(path, "%s/%d", symbol_conf.guestmount, pid); + if (access(path, R_OK)) { + static struct strlist *seen; + + if (!seen) + seen = strlist__new(true, NULL); + + if (!strlist__has_entry(seen, path)) { + pr_err("Can't access file %s\n", path); + strlist__add(seen, path); + } + machine = NULL; + goto out; + } + root_dir = path; + } + + machine = machines__add(machines, pid, root_dir); +out: + return machine; +} + +void machines__process_guests(struct machines *machines, + machine__process_t process, void *data) +{ + struct rb_node *nd; + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + process(pos, data); + } +} + +char *machine__mmap_name(struct machine *machine, char *bf, size_t size) +{ + if (machine__is_host(machine)) + snprintf(bf, size, "[%s]", "kernel.kallsyms"); + else if (machine__is_default_guest(machine)) + snprintf(bf, size, "[%s]", "guest.kernel.kallsyms"); + else { + snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", + machine->pid); + } + + return bf; +} + +void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) +{ + struct rb_node *node; + struct machine *machine; + + machines->host.id_hdr_size = id_hdr_size; + + for (node = rb_first(&machines->guests); node; node = rb_next(node)) { + machine = rb_entry(node, struct machine, rb_node); + machine->id_hdr_size = id_hdr_size; + } + + return; +} + +static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, + bool create) +{ + struct rb_node **p = &machine->threads.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + /* + * Font-end cache - PID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: + */ + if (machine->last_match && machine->last_match->pid == pid) + return machine->last_match; + + while (*p != NULL) { + parent = *p; + th = rb_entry(parent, struct thread, rb_node); + + if (th->pid == pid) { + machine->last_match = th; + return th; + } + + if (pid < th->pid) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + if (!create) + return NULL; + + th = thread__new(pid); + if (th != NULL) { + rb_link_node(&th->rb_node, parent, p); + rb_insert_color(&th->rb_node, &machine->threads); + machine->last_match = th; + } + + return th; +} + +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid) +{ + return __machine__findnew_thread(machine, pid, true); +} + +struct thread *machine__find_thread(struct machine *machine, pid_t pid) +{ + return __machine__findnew_thread(machine, pid, false); +} + +int machine__process_comm_event(struct machine *machine, union perf_event *event) +{ + struct thread *thread = machine__findnew_thread(machine, event->comm.tid); + + if (dump_trace) + perf_event__fprintf_comm(event, stdout); + + if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { + dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); + return -1; + } + + return 0; +} + +int machine__process_lost_event(struct machine *machine __maybe_unused, + union perf_event *event) +{ + dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", + event->lost.id, event->lost.lost); + return 0; +} + +struct map *machine__new_module(struct machine *machine, u64 start, + const char *filename) +{ + struct map *map; + struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); + + if (dso == NULL) + return NULL; + + map = map__new2(start, dso, MAP__FUNCTION); + if (map == NULL) + return NULL; + + if (machine__is_host(machine)) + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; + else + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + map_groups__insert(&machine->kmaps, map); + return map; +} + +size_t machines__fprintf_dsos(struct machines *machines, FILE *fp) +{ + struct rb_node *nd; + size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) + + __dsos__fprintf(&machines->host.user_dsos, fp); + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret += __dsos__fprintf(&pos->kernel_dsos, fp); + ret += __dsos__fprintf(&pos->user_dsos, fp); + } + + return ret; +} + +size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) + + __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm); +} + +size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + struct rb_node *nd; + size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm); + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm); + } + return ret; +} + +size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) +{ + int i; + size_t printed = 0; + struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso; + + if (kdso->has_build_id) { + char filename[PATH_MAX]; + if (dso__build_id_filename(kdso, filename, sizeof(filename))) + printed += fprintf(fp, "[0] %s\n", filename); + } + + for (i = 0; i < vmlinux_path__nr_entries; ++i) + printed += fprintf(fp, "[%d] %s\n", + i + kdso->has_build_id, vmlinux_path[i]); + + return printed; +} + +size_t machine__fprintf(struct machine *machine, FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); + + ret += thread__fprintf(pos, fp); + } + + return ret; +} + +static struct dso *machine__get_kernel(struct machine *machine) +{ + const char *vmlinux_name = NULL; + struct dso *kernel; + + if (machine__is_host(machine)) { + vmlinux_name = symbol_conf.vmlinux_name; + if (!vmlinux_name) + vmlinux_name = "[kernel.kallsyms]"; + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[kernel]", + DSO_TYPE_KERNEL); + } else { + char bf[PATH_MAX]; + + if (machine__is_default_guest(machine)) + vmlinux_name = symbol_conf.default_guest_vmlinux_name; + if (!vmlinux_name) + vmlinux_name = machine__mmap_name(machine, bf, + sizeof(bf)); + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[guest.kernel]", + DSO_TYPE_GUEST_KERNEL); + } + + if (kernel != NULL && (!kernel->has_build_id)) + dso__read_running_kernel_build_id(kernel, machine); + + return kernel; +} + +struct process_args { + u64 start; +}; + +static int symbol__in_kernel(void *arg, const char *name, + char type __maybe_unused, u64 start) +{ + struct process_args *args = arg; + + if (strchr(name, '[')) + return 0; + + args->start = start; + return 1; +} + +/* Figure out the start address of kernel map from /proc/kallsyms */ +static u64 machine__get_kernel_start_addr(struct machine *machine) +{ + const char *filename; + char path[PATH_MAX]; + struct process_args args; + + if (machine__is_host(machine)) { + filename = "/proc/kallsyms"; + } else { + if (machine__is_default_guest(machine)) + filename = (char *)symbol_conf.default_guest_kallsyms; + else { + sprintf(path, "%s/proc/kallsyms", machine->root_dir); + filename = path; + } + } + + if (symbol__restricted_filename(filename, "/proc/kallsyms")) + return 0; + + if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0) + return 0; + + return args.start; +} + +int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) +{ + enum map_type type; + u64 start = machine__get_kernel_start_addr(machine); + + for (type = 0; type < MAP__NR_TYPES; ++type) { + struct kmap *kmap; + + machine->vmlinux_maps[type] = map__new2(start, kernel, type); + if (machine->vmlinux_maps[type] == NULL) + return -1; + + machine->vmlinux_maps[type]->map_ip = + machine->vmlinux_maps[type]->unmap_ip = + identity__map_ip; + kmap = map__kmap(machine->vmlinux_maps[type]); + kmap->kmaps = &machine->kmaps; + map_groups__insert(&machine->kmaps, + machine->vmlinux_maps[type]); + } + + return 0; +} + +void machine__destroy_kernel_maps(struct machine *machine) +{ + enum map_type type; + + for (type = 0; type < MAP__NR_TYPES; ++type) { + struct kmap *kmap; + + if (machine->vmlinux_maps[type] == NULL) + continue; + + kmap = map__kmap(machine->vmlinux_maps[type]); + map_groups__remove(&machine->kmaps, + machine->vmlinux_maps[type]); + if (kmap->ref_reloc_sym) { + /* + * ref_reloc_sym is shared among all maps, so free just + * on one of them. + */ + if (type == MAP__FUNCTION) { + free((char *)kmap->ref_reloc_sym->name); + kmap->ref_reloc_sym->name = NULL; + free(kmap->ref_reloc_sym); + } + kmap->ref_reloc_sym = NULL; + } + + map__delete(machine->vmlinux_maps[type]); + machine->vmlinux_maps[type] = NULL; + } +} + +int machines__create_guest_kernel_maps(struct machines *machines) +{ + int ret = 0; + struct dirent **namelist = NULL; + int i, items = 0; + char path[PATH_MAX]; + pid_t pid; + char *endp; + + if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_modules || + symbol_conf.default_guest_kallsyms) { + machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID); + } + + if (symbol_conf.guestmount) { + items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); + if (items <= 0) + return -ENOENT; + for (i = 0; i < items; i++) { + if (!isdigit(namelist[i]->d_name[0])) { + /* Filter out . and .. */ + continue; + } + pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10); + if ((*endp != '\0') || + (endp == namelist[i]->d_name) || + (errno == ERANGE)) { + pr_debug("invalid directory (%s). Skipping.\n", + namelist[i]->d_name); + continue; + } + sprintf(path, "%s/%s/proc/kallsyms", + symbol_conf.guestmount, + namelist[i]->d_name); + ret = access(path, R_OK); + if (ret) { + pr_debug("Can't access file %s\n", path); + goto failure; + } + machines__create_kernel_maps(machines, pid); + } +failure: + free(namelist); + } + + return ret; +} + +void machines__destroy_kernel_maps(struct machines *machines) +{ + struct rb_node *next = rb_first(&machines->guests); + + machine__destroy_kernel_maps(&machines->host); + + while (next) { + struct machine *pos = rb_entry(next, struct machine, rb_node); + + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, &machines->guests); + machine__delete(pos); + } +} + +int machines__create_kernel_maps(struct machines *machines, pid_t pid) +{ + struct machine *machine = machines__findnew(machines, pid); + + if (machine == NULL) + return -1; + + return machine__create_kernel_maps(machine); +} + +int machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, symbol_filter_t filter) +{ + struct map *map = machine->vmlinux_maps[type]; + int ret = dso__load_kallsyms(map->dso, filename, map, filter); + + if (ret > 0) { + dso__set_loaded(map->dso, type); + /* + * Since /proc/kallsyms will have multiple sessions for the + * kernel, with modules between them, fixup the end of all + * sections. + */ + __map_groups__fixup_end(&machine->kmaps, type); + } + + return ret; +} + +int machine__load_vmlinux_path(struct machine *machine, enum map_type type, + symbol_filter_t filter) +{ + struct map *map = machine->vmlinux_maps[type]; + int ret = dso__load_vmlinux_path(map->dso, map, filter); + + if (ret > 0) { + dso__set_loaded(map->dso, type); + map__reloc_vmlinux(map); + } + + return ret; +} + +static void map_groups__fixup_end(struct map_groups *mg) +{ + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + __map_groups__fixup_end(mg, i); +} + +static char *get_kernel_version(const char *root_dir) +{ + char version[PATH_MAX]; + FILE *file; + char *name, *tmp; + const char *prefix = "Linux version "; + + sprintf(version, "%s/proc/version", root_dir); + file = fopen(version, "r"); + if (!file) + return NULL; + + version[0] = '\0'; + tmp = fgets(version, sizeof(version), file); + fclose(file); + + name = strstr(version, prefix); + if (!name) + return NULL; + name += strlen(prefix); + tmp = strchr(name, ' '); + if (tmp) + *tmp = '\0'; + + return strdup(name); +} + +static int map_groups__set_modules_path_dir(struct map_groups *mg, + const char *dir_name) +{ + struct dirent *dent; + DIR *dir = opendir(dir_name); + int ret = 0; + + if (!dir) { + pr_debug("%s: cannot open %s dir\n", __func__, dir_name); + return -1; + } + + while ((dent = readdir(dir)) != NULL) { + char path[PATH_MAX]; + struct stat st; + + /*sshfs might return bad dent->d_type, so we have to stat*/ + snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name); + if (stat(path, &st)) + continue; + + if (S_ISDIR(st.st_mode)) { + if (!strcmp(dent->d_name, ".") || + !strcmp(dent->d_name, "..")) + continue; + + ret = map_groups__set_modules_path_dir(mg, path); + if (ret < 0) + goto out; + } else { + char *dot = strrchr(dent->d_name, '.'), + dso_name[PATH_MAX]; + struct map *map; + char *long_name; + + if (dot == NULL || strcmp(dot, ".ko")) + continue; + snprintf(dso_name, sizeof(dso_name), "[%.*s]", + (int)(dot - dent->d_name), dent->d_name); + + strxfrchar(dso_name, '-', '_'); + map = map_groups__find_by_name(mg, MAP__FUNCTION, + dso_name); + if (map == NULL) + continue; + + long_name = strdup(path); + if (long_name == NULL) { + ret = -1; + goto out; + } + dso__set_long_name(map->dso, long_name); + map->dso->lname_alloc = 1; + dso__kernel_module_get_build_id(map->dso, ""); + } + } + +out: + closedir(dir); + return ret; +} + +static int machine__set_modules_path(struct machine *machine) +{ + char *version; + char modules_path[PATH_MAX]; + + version = get_kernel_version(machine->root_dir); + if (!version) + return -1; + + snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", + machine->root_dir, version); + free(version); + + return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); +} + +static int machine__create_modules(struct machine *machine) +{ + char *line = NULL; + size_t n; + FILE *file; + struct map *map; + const char *modules; + char path[PATH_MAX]; + + if (machine__is_default_guest(machine)) + modules = symbol_conf.default_guest_modules; + else { + sprintf(path, "%s/proc/modules", machine->root_dir); + modules = path; + } + + if (symbol__restricted_filename(path, "/proc/modules")) + return -1; + + file = fopen(modules, "r"); + if (file == NULL) + return -1; + + while (!feof(file)) { + char name[PATH_MAX]; + u64 start; + char *sep; + int line_len; + + line_len = getline(&line, &n, file); + if (line_len < 0) + break; + + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + sep = strrchr(line, 'x'); + if (sep == NULL) + continue; + + hex2u64(sep + 1, &start); + + sep = strchr(line, ' '); + if (sep == NULL) + continue; + + *sep = '\0'; + + snprintf(name, sizeof(name), "[%s]", line); + map = machine__new_module(machine, start, name); + if (map == NULL) + goto out_delete_line; + dso__kernel_module_get_build_id(map->dso, machine->root_dir); + } + + free(line); + fclose(file); + + return machine__set_modules_path(machine); + +out_delete_line: + free(line); +out_failure: + return -1; +} + +int machine__create_kernel_maps(struct machine *machine) +{ + struct dso *kernel = machine__get_kernel(machine); + + if (kernel == NULL || + __machine__create_kernel_maps(machine, kernel) < 0) + return -1; + + if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { + if (machine__is_host(machine)) + pr_debug("Problems creating module maps, " + "continuing anyway...\n"); + else + pr_debug("Problems creating module maps for guest %d, " + "continuing anyway...\n", machine->pid); + } + + /* + * Now that we have all the maps created, just set the ->end of them: + */ + map_groups__fixup_end(&machine->kmaps); + return 0; +} + +static void machine__set_kernel_mmap_len(struct machine *machine, + union perf_event *event) +{ + int i; + + for (i = 0; i < MAP__NR_TYPES; i++) { + machine->vmlinux_maps[i]->start = event->mmap.start; + machine->vmlinux_maps[i]->end = (event->mmap.start + + event->mmap.len); + /* + * Be a bit paranoid here, some perf.data file came with + * a zero sized synthesized MMAP event for the kernel. + */ + if (machine->vmlinux_maps[i]->end == 0) + machine->vmlinux_maps[i]->end = ~0ULL; + } +} + +static int machine__process_kernel_mmap_event(struct machine *machine, + union perf_event *event) +{ + struct map *map; + char kmmap_prefix[PATH_MAX]; + enum dso_kernel_type kernel_type; + bool is_kernel_mmap; + + machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); + if (machine__is_host(machine)) + kernel_type = DSO_TYPE_KERNEL; + else + kernel_type = DSO_TYPE_GUEST_KERNEL; + + is_kernel_mmap = memcmp(event->mmap.filename, + kmmap_prefix, + strlen(kmmap_prefix) - 1) == 0; + if (event->mmap.filename[0] == '/' || + (!is_kernel_mmap && event->mmap.filename[0] == '[')) { + + char short_module_name[1024]; + char *name, *dot; + + if (event->mmap.filename[0] == '/') { + name = strrchr(event->mmap.filename, '/'); + if (name == NULL) + goto out_problem; + + ++name; /* skip / */ + dot = strrchr(name, '.'); + if (dot == NULL) + goto out_problem; + snprintf(short_module_name, sizeof(short_module_name), + "[%.*s]", (int)(dot - name), name); + strxfrchar(short_module_name, '-', '_'); + } else + strcpy(short_module_name, event->mmap.filename); + + map = machine__new_module(machine, event->mmap.start, + event->mmap.filename); + if (map == NULL) + goto out_problem; + + name = strdup(short_module_name); + if (name == NULL) + goto out_problem; + + map->dso->short_name = name; + map->dso->sname_alloc = 1; + map->end = map->start + event->mmap.len; + } else if (is_kernel_mmap) { + const char *symbol_name = (event->mmap.filename + + strlen(kmmap_prefix)); + /* + * Should be there already, from the build-id table in + * the header. + */ + struct dso *kernel = __dsos__findnew(&machine->kernel_dsos, + kmmap_prefix); + if (kernel == NULL) + goto out_problem; + + kernel->kernel = kernel_type; + if (__machine__create_kernel_maps(machine, kernel) < 0) + goto out_problem; + + machine__set_kernel_mmap_len(machine, event); + + /* + * Avoid using a zero address (kptr_restrict) for the ref reloc + * symbol. Effectively having zero here means that at record + * time /proc/sys/kernel/kptr_restrict was non zero. + */ + if (event->mmap.pgoff != 0) { + maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, + symbol_name, + event->mmap.pgoff); + } + + if (machine__is_default_guest(machine)) { + /* + * preload dso of guest kernel and modules + */ + dso__load(kernel, machine->vmlinux_maps[MAP__FUNCTION], + NULL); + } + } + return 0; +out_problem: + return -1; +} + +int machine__process_mmap_event(struct machine *machine, union perf_event *event) +{ + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct thread *thread; + struct map *map; + int ret = 0; + + if (dump_trace) + perf_event__fprintf_mmap(event, stdout); + + if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || + cpumode == PERF_RECORD_MISC_KERNEL) { + ret = machine__process_kernel_mmap_event(machine, event); + if (ret < 0) + goto out_problem; + return 0; + } + + thread = machine__findnew_thread(machine, event->mmap.pid); + if (thread == NULL) + goto out_problem; + map = map__new(&machine->user_dsos, event->mmap.start, + event->mmap.len, event->mmap.pgoff, + event->mmap.pid, event->mmap.filename, + MAP__FUNCTION); + if (map == NULL) + goto out_problem; + + thread__insert_map(thread, map); + return 0; + +out_problem: + dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); + return 0; +} + +int machine__process_fork_event(struct machine *machine, union perf_event *event) +{ + struct thread *thread = machine__findnew_thread(machine, event->fork.tid); + struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); + + if (dump_trace) + perf_event__fprintf_task(event, stdout); + + if (thread == NULL || parent == NULL || + thread__fork(thread, parent) < 0) { + dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); + return -1; + } + + return 0; +} + +int machine__process_exit_event(struct machine *machine, union perf_event *event) +{ + struct thread *thread = machine__find_thread(machine, event->fork.tid); + + if (dump_trace) + perf_event__fprintf_task(event, stdout); + + if (thread != NULL) + machine__remove_thread(machine, thread); + + return 0; +} + +int machine__process_event(struct machine *machine, union perf_event *event) +{ + int ret; + + switch (event->header.type) { + case PERF_RECORD_COMM: + ret = machine__process_comm_event(machine, event); break; + case PERF_RECORD_MMAP: + ret = machine__process_mmap_event(machine, event); break; + case PERF_RECORD_FORK: + ret = machine__process_fork_event(machine, event); break; + case PERF_RECORD_EXIT: + ret = machine__process_exit_event(machine, event); break; + case PERF_RECORD_LOST: + ret = machine__process_lost_event(machine, event); break; + default: + ret = -1; + break; + } + + return ret; +} + +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)) + return 1; + + return 0; +} + +static const u8 cpumodes[] = { + PERF_RECORD_MISC_USER, + PERF_RECORD_MISC_KERNEL, + PERF_RECORD_MISC_GUEST_USER, + PERF_RECORD_MISC_GUEST_KERNEL +}; +#define NCPUMODES (sizeof(cpumodes)/sizeof(u8)) + +static void ip__resolve_ams(struct machine *machine, struct thread *thread, + struct addr_map_symbol *ams, + u64 ip) +{ + struct addr_location al; + size_t i; + u8 m; + + memset(&al, 0, sizeof(al)); + + for (i = 0; i < NCPUMODES; i++) { + m = cpumodes[i]; + /* + * We cannot use the header.misc hint to determine whether a + * branch stack address is user, kernel, guest, hypervisor. + * Branches may straddle the kernel/user/hypervisor boundaries. + * Thus, we have to try consecutively until we find a match + * or else, the symbol is unknown + */ + thread__find_addr_location(thread, machine, m, MAP__FUNCTION, + ip, &al, NULL); + if (al.sym) + goto found; + } +found: + ams->addr = ip; + ams->al_addr = al.addr; + ams->sym = al.sym; + ams->map = al.map; +} + +struct branch_info *machine__resolve_bstack(struct machine *machine, + struct thread *thr, + struct branch_stack *bs) +{ + struct branch_info *bi; + unsigned int i; + + bi = calloc(bs->nr, sizeof(struct branch_info)); + if (!bi) + return NULL; + + for (i = 0; i < bs->nr; i++) { + ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from); + bi[i].flags = bs->entries[i].flags; + } + return bi; +} + +static int machine__resolve_callchain_sample(struct machine *machine, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent) + +{ + u8 cpumode = PERF_RECORD_MISC_USER; + unsigned int i; + int err; + + callchain_cursor_reset(&callchain_cursor); + + if (chain->nr > PERF_MAX_STACK_DEPTH) { + pr_warning("corrupted callchain. skipping...\n"); + return 0; + } + + for (i = 0; i < chain->nr; i++) { + u64 ip; + struct addr_location al; + + if (callchain_param.order == ORDER_CALLEE) + ip = chain->ips[i]; + else + ip = chain->ips[chain->nr - i - 1]; + + if (ip >= PERF_CONTEXT_MAX) { + switch (ip) { + case PERF_CONTEXT_HV: + cpumode = PERF_RECORD_MISC_HYPERVISOR; + break; + case PERF_CONTEXT_KERNEL: + cpumode = PERF_RECORD_MISC_KERNEL; + break; + case PERF_CONTEXT_USER: + cpumode = PERF_RECORD_MISC_USER; + break; + default: + pr_debug("invalid callchain context: " + "%"PRId64"\n", (s64) ip); + /* + * It seems the callchain is corrupted. + * Discard all. + */ + callchain_cursor_reset(&callchain_cursor); + return 0; + } + continue; + } + + al.filtered = false; + thread__find_addr_location(thread, machine, cpumode, + MAP__FUNCTION, ip, &al, NULL); + if (al.sym != NULL) { + if (sort__has_parent && !*parent && + symbol__match_parent_regex(al.sym)) + *parent = al.sym; + if (!symbol_conf.use_callchain) + break; + } + + err = callchain_cursor_append(&callchain_cursor, + ip, al.map, al.sym); + if (err) + return err; + } + + return 0; +} + +static int unwind_entry(struct unwind_entry *entry, void *arg) +{ + struct callchain_cursor *cursor = arg; + return callchain_cursor_append(cursor, entry->ip, + entry->map, entry->sym); +} + +int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, + struct thread *thread, + struct perf_sample *sample, + struct symbol **parent) + +{ + int ret; + + callchain_cursor_reset(&callchain_cursor); + + ret = machine__resolve_callchain_sample(machine, thread, + sample->callchain, parent); + if (ret) + return ret; + + /* Can we do dwarf post unwind? */ + if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && + (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) + return 0; + + /* Bail out if nothing was captured. */ + if ((!sample->user_regs.regs) || + (!sample->user_stack.size)) + return 0; + + return unwind__get_entries(unwind_entry, &callchain_cursor, machine, + thread, evsel->attr.sample_regs_user, + sample); + +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h new file mode 100644 index 00000000000..5ac5892f232 --- /dev/null +++ b/tools/perf/util/machine.h @@ -0,0 +1,157 @@ +#ifndef __PERF_MACHINE_H +#define __PERF_MACHINE_H + +#include <sys/types.h> +#include <linux/rbtree.h> +#include "map.h" + +struct branch_stack; +struct perf_evsel; +struct perf_sample; +struct symbol; +struct thread; +union perf_event; + +/* Native host kernel uses -1 as pid index in machine */ +#define HOST_KERNEL_ID (-1) +#define DEFAULT_GUEST_KERNEL_ID (0) + +struct machine { + struct rb_node rb_node; + pid_t pid; + u16 id_hdr_size; + char *root_dir; + struct rb_root threads; + struct list_head dead_threads; + struct thread *last_match; + struct list_head user_dsos; + struct list_head kernel_dsos; + struct map_groups kmaps; + struct map *vmlinux_maps[MAP__NR_TYPES]; +}; + +static inline +struct map *machine__kernel_map(struct machine *machine, enum map_type type) +{ + return machine->vmlinux_maps[type]; +} + +struct thread *machine__find_thread(struct machine *machine, pid_t pid); + +int machine__process_comm_event(struct machine *machine, union perf_event *event); +int machine__process_exit_event(struct machine *machine, union perf_event *event); +int machine__process_fork_event(struct machine *machine, union perf_event *event); +int machine__process_lost_event(struct machine *machine, union perf_event *event); +int machine__process_mmap_event(struct machine *machine, union perf_event *event); +int machine__process_event(struct machine *machine, union perf_event *event); + +typedef void (*machine__process_t)(struct machine *machine, void *data); + +struct machines { + struct machine host; + struct rb_root guests; +}; + +void machines__init(struct machines *machines); +void machines__exit(struct machines *machines); + +void machines__process_guests(struct machines *machines, + machine__process_t process, void *data); + +struct machine *machines__add(struct machines *machines, pid_t pid, + const char *root_dir); +struct machine *machines__find_host(struct machines *machines); +struct machine *machines__find(struct machines *machines, pid_t pid); +struct machine *machines__findnew(struct machines *machines, pid_t pid); + +void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size); +char *machine__mmap_name(struct machine *machine, char *bf, size_t size); + +int machine__init(struct machine *machine, const char *root_dir, pid_t pid); +void machine__exit(struct machine *machine); +void machine__delete_dead_threads(struct machine *machine); +void machine__delete_threads(struct machine *machine); +void machine__delete(struct machine *machine); + +struct branch_info *machine__resolve_bstack(struct machine *machine, + struct thread *thread, + struct branch_stack *bs); +int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, + struct thread *thread, + struct perf_sample *sample, + struct symbol **parent); + +/* + * Default guest kernel is defined by parameter --guestkallsyms + * and --guestmodules + */ +static inline bool machine__is_default_guest(struct machine *machine) +{ + return machine ? machine->pid == DEFAULT_GUEST_KERNEL_ID : false; +} + +static inline bool machine__is_host(struct machine *machine) +{ + return machine ? machine->pid == HOST_KERNEL_ID : false; +} + +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); + +static inline +struct symbol *machine__find_kernel_symbol(struct machine *machine, + enum map_type type, u64 addr, + struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_symbol(&machine->kmaps, type, addr, + mapp, filter); +} + +static inline +struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, + struct map **mapp, + symbol_filter_t filter) +{ + return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr, + mapp, filter); +} + +static inline +struct symbol *machine__find_kernel_function_by_name(struct machine *machine, + const char *name, + struct map **mapp, + symbol_filter_t filter) +{ + return map_groups__find_function_by_name(&machine->kmaps, name, mapp, + filter); +} + +struct map *machine__new_module(struct machine *machine, u64 start, + const char *filename); + +int machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, symbol_filter_t filter); +int machine__load_vmlinux_path(struct machine *machine, enum map_type type, + symbol_filter_t filter); + +size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); +size_t machines__fprintf_dsos(struct machines *machines, FILE *fp); +size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); + +void machine__destroy_kernel_maps(struct machine *machine); +int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel); +int machine__create_kernel_maps(struct machine *machine); + +int machines__create_kernel_maps(struct machines *machines, pid_t pid); +int machines__create_guest_kernel_maps(struct machines *machines); +void machines__destroy_kernel_maps(struct machines *machines); + +size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); + +#endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 6109fa4d14c..6fcb9de6234 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -10,6 +10,8 @@ #include "thread.h" #include "strlist.h" #include "vdso.h" +#include "build-id.h" +#include <linux/string.h> const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", @@ -18,38 +20,39 @@ const char *map_type__name[MAP__NR_TYPES] = { static inline int is_anon_memory(const char *filename) { - return strcmp(filename, "//anon") == 0; + return !strcmp(filename, "//anon") || + !strcmp(filename, "/anon_hugepage (deleted)"); } static inline int is_no_dso_memory(const char *filename) { - return !strcmp(filename, "[stack]") || + return !strncmp(filename, "[stack", 6) || !strcmp(filename, "[heap]"); } -void map__init(struct map *self, enum map_type type, +void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso) { - self->type = type; - self->start = start; - self->end = end; - self->pgoff = pgoff; - self->dso = dso; - self->map_ip = map__map_ip; - self->unmap_ip = map__unmap_ip; - RB_CLEAR_NODE(&self->rb_node); - self->groups = NULL; - self->referenced = false; - self->erange_warned = false; + map->type = type; + map->start = start; + map->end = end; + map->pgoff = pgoff; + map->dso = dso; + map->map_ip = map__map_ip; + map->unmap_ip = map__unmap_ip; + RB_CLEAR_NODE(&map->rb_node); + map->groups = NULL; + map->referenced = false; + map->erange_warned = false; } struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, char *filename, enum map_type type) { - struct map *self = malloc(sizeof(*self)); + struct map *map = malloc(sizeof(*map)); - if (self != NULL) { + if (map != NULL) { char newfilename[PATH_MAX]; struct dso *dso; int anon, no_dso, vdso; @@ -72,10 +75,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, if (dso == NULL) goto out_delete; - map__init(self, type, start, start + len, pgoff, dso); + map__init(map, type, start, start + len, pgoff, dso); if (anon || no_dso) { - self->map_ip = self->unmap_ip = identity__map_ip; + map->map_ip = map->unmap_ip = identity__map_ip; /* * Set memory without DSO as loaded. All map__find_* @@ -83,12 +86,12 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, * unnecessary map__load warning. */ if (no_dso) - dso__set_loaded(dso, self->type); + dso__set_loaded(dso, map->type); } } - return self; + return map; out_delete: - free(self); + free(map); return NULL; } @@ -111,48 +114,48 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type) return map; } -void map__delete(struct map *self) +void map__delete(struct map *map) { - free(self); + free(map); } -void map__fixup_start(struct map *self) +void map__fixup_start(struct map *map) { - struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_root *symbols = &map->dso->symbols[map->type]; struct rb_node *nd = rb_first(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - self->start = sym->start; + map->start = sym->start; } } -void map__fixup_end(struct map *self) +void map__fixup_end(struct map *map) { - struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_root *symbols = &map->dso->symbols[map->type]; struct rb_node *nd = rb_last(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - self->end = sym->end; + map->end = sym->end; } } #define DSO__DELETED "(deleted)" -int map__load(struct map *self, symbol_filter_t filter) +int map__load(struct map *map, symbol_filter_t filter) { - const char *name = self->dso->long_name; + const char *name = map->dso->long_name; int nr; - if (dso__loaded(self->dso, self->type)) + if (dso__loaded(map->dso, map->type)) return 0; - nr = dso__load(self->dso, self, filter); + nr = dso__load(map->dso, map, filter); if (nr < 0) { - if (self->dso->has_build_id) { + if (map->dso->has_build_id) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - build_id__sprintf(self->dso->build_id, - sizeof(self->dso->build_id), + build_id__sprintf(map->dso->build_id, + sizeof(map->dso->build_id), sbuild_id); pr_warning("%s with build id %s not found", name, sbuild_id); @@ -182,43 +185,36 @@ int map__load(struct map *self, symbol_filter_t filter) * Only applies to the kernel, as its symtabs aren't relative like the * module ones. */ - if (self->dso->kernel) - map__reloc_vmlinux(self); + if (map->dso->kernel) + map__reloc_vmlinux(map); return 0; } -struct symbol *map__find_symbol(struct map *self, u64 addr, +struct symbol *map__find_symbol(struct map *map, u64 addr, symbol_filter_t filter) { - if (map__load(self, filter) < 0) + if (map__load(map, filter) < 0) return NULL; - return dso__find_symbol(self->dso, self->type, addr); + return dso__find_symbol(map->dso, map->type, addr); } -struct symbol *map__find_symbol_by_name(struct map *self, const char *name, +struct symbol *map__find_symbol_by_name(struct map *map, const char *name, symbol_filter_t filter) { - if (map__load(self, filter) < 0) + if (map__load(map, filter) < 0) return NULL; - if (!dso__sorted_by_name(self->dso, self->type)) - dso__sort_by_name(self->dso, self->type); + if (!dso__sorted_by_name(map->dso, map->type)) + dso__sort_by_name(map->dso, map->type); - return dso__find_symbol_by_name(self->dso, self->type, name); + return dso__find_symbol_by_name(map->dso, map->type, name); } -struct map *map__clone(struct map *self) +struct map *map__clone(struct map *map) { - struct map *map = malloc(sizeof(*self)); - - if (!map) - return NULL; - - memcpy(map, self, sizeof(*self)); - - return map; + return memdup(map, sizeof(*map)); } int map__overlap(struct map *l, struct map *r) @@ -235,10 +231,10 @@ int map__overlap(struct map *l, struct map *r) return 0; } -size_t map__fprintf(struct map *self, FILE *fp) +size_t map__fprintf(struct map *map, FILE *fp) { return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", - self->start, self->end, self->pgoff, self->dso->name); + map->start, map->end, map->pgoff, map->dso->name); } size_t map__fprintf_dsoname(struct map *map, FILE *fp) @@ -526,9 +522,9 @@ static u64 map__reloc_unmap_ip(struct map *map, u64 ip) return ip - (s64)map->pgoff; } -void map__reloc_vmlinux(struct map *self) +void map__reloc_vmlinux(struct map *map) { - struct kmap *kmap = map__kmap(self); + struct kmap *kmap = map__kmap(map); s64 reloc; if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr) @@ -540,9 +536,9 @@ void map__reloc_vmlinux(struct map *self) if (!reloc) return; - self->map_ip = map__reloc_map_ip; - self->unmap_ip = map__reloc_unmap_ip; - self->pgoff = reloc; + map->map_ip = map__reloc_map_ip; + map->unmap_ip = map__reloc_unmap_ip; + map->pgoff = reloc; } void maps__insert(struct rb_root *maps, struct map *map) @@ -565,9 +561,9 @@ void maps__insert(struct rb_root *maps, struct map *map) rb_insert_color(&map->rb_node, maps); } -void maps__remove(struct rb_root *self, struct map *map) +void maps__remove(struct rb_root *maps, struct map *map) { - rb_erase(&map->rb_node, self); + rb_erase(&map->rb_node, maps); } struct map *maps__find(struct rb_root *maps, u64 ip) @@ -589,182 +585,3 @@ struct map *maps__find(struct rb_root *maps, u64 ip) return NULL; } - -int machine__init(struct machine *self, const char *root_dir, pid_t pid) -{ - map_groups__init(&self->kmaps); - RB_CLEAR_NODE(&self->rb_node); - INIT_LIST_HEAD(&self->user_dsos); - INIT_LIST_HEAD(&self->kernel_dsos); - - self->threads = RB_ROOT; - INIT_LIST_HEAD(&self->dead_threads); - self->last_match = NULL; - - self->kmaps.machine = self; - self->pid = pid; - self->root_dir = strdup(root_dir); - if (self->root_dir == NULL) - return -ENOMEM; - - if (pid != HOST_KERNEL_ID) { - struct thread *thread = machine__findnew_thread(self, pid); - char comm[64]; - - if (thread == NULL) - return -ENOMEM; - - snprintf(comm, sizeof(comm), "[guest/%d]", pid); - thread__set_comm(thread, comm); - } - - return 0; -} - -static void dsos__delete(struct list_head *self) -{ - struct dso *pos, *n; - - list_for_each_entry_safe(pos, n, self, node) { - list_del(&pos->node); - dso__delete(pos); - } -} - -void machine__exit(struct machine *self) -{ - map_groups__exit(&self->kmaps); - dsos__delete(&self->user_dsos); - dsos__delete(&self->kernel_dsos); - free(self->root_dir); - self->root_dir = NULL; -} - -void machine__delete(struct machine *self) -{ - machine__exit(self); - free(self); -} - -struct machine *machines__add(struct rb_root *self, pid_t pid, - const char *root_dir) -{ - struct rb_node **p = &self->rb_node; - struct rb_node *parent = NULL; - struct machine *pos, *machine = malloc(sizeof(*machine)); - - if (!machine) - return NULL; - - if (machine__init(machine, root_dir, pid) != 0) { - free(machine); - return NULL; - } - - while (*p != NULL) { - parent = *p; - pos = rb_entry(parent, struct machine, rb_node); - if (pid < pos->pid) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&machine->rb_node, parent, p); - rb_insert_color(&machine->rb_node, self); - - return machine; -} - -struct machine *machines__find(struct rb_root *self, pid_t pid) -{ - struct rb_node **p = &self->rb_node; - struct rb_node *parent = NULL; - struct machine *machine; - struct machine *default_machine = NULL; - - while (*p != NULL) { - parent = *p; - machine = rb_entry(parent, struct machine, rb_node); - if (pid < machine->pid) - p = &(*p)->rb_left; - else if (pid > machine->pid) - p = &(*p)->rb_right; - else - return machine; - if (!machine->pid) - default_machine = machine; - } - - return default_machine; -} - -struct machine *machines__findnew(struct rb_root *self, pid_t pid) -{ - char path[PATH_MAX]; - const char *root_dir = ""; - struct machine *machine = machines__find(self, pid); - - if (machine && (machine->pid == pid)) - goto out; - - if ((pid != HOST_KERNEL_ID) && - (pid != DEFAULT_GUEST_KERNEL_ID) && - (symbol_conf.guestmount)) { - sprintf(path, "%s/%d", symbol_conf.guestmount, pid); - if (access(path, R_OK)) { - static struct strlist *seen; - - if (!seen) - seen = strlist__new(true, NULL); - - if (!strlist__has_entry(seen, path)) { - pr_err("Can't access file %s\n", path); - strlist__add(seen, path); - } - machine = NULL; - goto out; - } - root_dir = path; - } - - machine = machines__add(self, pid, root_dir); - -out: - return machine; -} - -void machines__process(struct rb_root *self, machine__process_t process, void *data) -{ - struct rb_node *nd; - - for (nd = rb_first(self); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - process(pos, data); - } -} - -char *machine__mmap_name(struct machine *self, char *bf, size_t size) -{ - if (machine__is_host(self)) - snprintf(bf, size, "[%s]", "kernel.kallsyms"); - else if (machine__is_default_guest(self)) - snprintf(bf, size, "[%s]", "guest.kernel.kallsyms"); - else - snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", self->pid); - - return bf; -} - -void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size) -{ - struct rb_node *node; - struct machine *machine; - - for (node = rb_first(machines); node; node = rb_next(node)) { - machine = rb_entry(node, struct machine, rb_node); - machine->id_hdr_size = id_hdr_size; - } - - return; -} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index d2250fc97e2..a887f2c9dfb 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -57,33 +57,9 @@ struct map_groups { struct machine *machine; }; -/* Native host kernel uses -1 as pid index in machine */ -#define HOST_KERNEL_ID (-1) -#define DEFAULT_GUEST_KERNEL_ID (0) - -struct machine { - struct rb_node rb_node; - pid_t pid; - u16 id_hdr_size; - char *root_dir; - struct rb_root threads; - struct list_head dead_threads; - struct thread *last_match; - struct list_head user_dsos; - struct list_head kernel_dsos; - struct map_groups kmaps; - struct map *vmlinux_maps[MAP__NR_TYPES]; -}; - -static inline -struct map *machine__kernel_map(struct machine *self, enum map_type type) -{ - return self->vmlinux_maps[type]; -} - -static inline struct kmap *map__kmap(struct map *self) +static inline struct kmap *map__kmap(struct map *map) { - return (struct kmap *)(self + 1); + return (struct kmap *)(map + 1); } static inline u64 map__map_ip(struct map *map, u64 ip) @@ -109,27 +85,27 @@ struct symbol; typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); -void map__init(struct map *self, enum map_type type, +void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, char *filename, enum map_type type); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); -void map__delete(struct map *self); -struct map *map__clone(struct map *self); +void map__delete(struct map *map); +struct map *map__clone(struct map *map); int map__overlap(struct map *l, struct map *r); -size_t map__fprintf(struct map *self, FILE *fp); +size_t map__fprintf(struct map *map, FILE *fp); size_t map__fprintf_dsoname(struct map *map, FILE *fp); -int map__load(struct map *self, symbol_filter_t filter); -struct symbol *map__find_symbol(struct map *self, +int map__load(struct map *map, symbol_filter_t filter); +struct symbol *map__find_symbol(struct map *map, u64 addr, symbol_filter_t filter); -struct symbol *map__find_symbol_by_name(struct map *self, const char *name, +struct symbol *map__find_symbol_by_name(struct map *map, const char *name, symbol_filter_t filter); -void map__fixup_start(struct map *self); -void map__fixup_end(struct map *self); +void map__fixup_start(struct map *map); +void map__fixup_end(struct map *map); -void map__reloc_vmlinux(struct map *self); +void map__reloc_vmlinux(struct map *map); size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp); @@ -143,44 +119,9 @@ int map_groups__clone(struct map_groups *mg, size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp); size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp); -typedef void (*machine__process_t)(struct machine *self, void *data); - -void machines__process(struct rb_root *self, machine__process_t process, void *data); -struct machine *machines__add(struct rb_root *self, pid_t pid, - const char *root_dir); -struct machine *machines__find_host(struct rb_root *self); -struct machine *machines__find(struct rb_root *self, pid_t pid); -struct machine *machines__findnew(struct rb_root *self, pid_t pid); -void machines__set_id_hdr_size(struct rb_root *self, u16 id_hdr_size); -char *machine__mmap_name(struct machine *self, char *bf, size_t size); -int machine__init(struct machine *self, const char *root_dir, pid_t pid); -void machine__exit(struct machine *self); -void machine__delete(struct machine *self); - -struct perf_evsel; -struct perf_sample; -int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, - struct thread *thread, - struct perf_sample *sample, - struct symbol **parent); int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr); -/* - * Default guest kernel is defined by parameter --guestkallsyms - * and --guestmodules - */ -static inline bool machine__is_default_guest(struct machine *self) -{ - return self ? self->pid == DEFAULT_GUEST_KERNEL_ID : false; -} - -static inline bool machine__is_host(struct machine *self) -{ - return self ? self->pid == HOST_KERNEL_ID : false; -} - static inline void map_groups__insert(struct map_groups *mg, struct map *map) { maps__insert(&mg->maps[map->type], map); @@ -209,29 +150,6 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, struct map **mapp, symbol_filter_t filter); - -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); - -static inline -struct symbol *machine__find_kernel_symbol(struct machine *self, - enum map_type type, u64 addr, - struct map **mapp, - symbol_filter_t filter) -{ - return map_groups__find_symbol(&self->kmaps, type, addr, mapp, filter); -} - -static inline -struct symbol *machine__find_kernel_function(struct machine *self, u64 addr, - struct map **mapp, - symbol_filter_t filter) -{ - return machine__find_kernel_symbol(self, MAP__FUNCTION, addr, mapp, filter); -} - static inline struct symbol *map_groups__find_function_by_name(struct map_groups *mg, const char *name, struct map **mapp, @@ -240,22 +158,11 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg, return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter); } -static inline -struct symbol *machine__find_kernel_function_by_name(struct machine *self, - const char *name, - struct map **mapp, - symbol_filter_t filter) -{ - return map_groups__find_function_by_name(&self->kmaps, name, mapp, - filter); -} - int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, int verbose, FILE *fp); struct map *map_groups__find_by_name(struct map_groups *mg, enum map_type type, const char *name); -struct map *machine__new_module(struct machine *self, u64 start, const char *filename); void map_groups__flush(struct map_groups *mg); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 75c7b0fca6d..c84f48cf967 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,4 +1,4 @@ -#include "../../../include/linux/hw_breakpoint.h" +#include <linux/hw_breakpoint.h> #include "util.h" #include "../perf.h" #include "evlist.h" @@ -380,8 +380,8 @@ static int add_tracepoint(struct list_head **listp, int *idx, return 0; } -static int add_tracepoint_multi(struct list_head **list, int *idx, - char *sys_name, char *evt_name) +static int add_tracepoint_multi_event(struct list_head **list, int *idx, + char *sys_name, char *evt_name) { char evt_path[MAXPATHLEN]; struct dirent *evt_ent; @@ -408,6 +408,47 @@ static int add_tracepoint_multi(struct list_head **list, int *idx, ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name); } + closedir(evt_dir); + return ret; +} + +static int add_tracepoint_event(struct list_head **list, int *idx, + char *sys_name, char *evt_name) +{ + return strpbrk(evt_name, "*?") ? + add_tracepoint_multi_event(list, idx, sys_name, evt_name) : + add_tracepoint(list, idx, sys_name, evt_name); +} + +static int add_tracepoint_multi_sys(struct list_head **list, int *idx, + char *sys_name, char *evt_name) +{ + struct dirent *events_ent; + DIR *events_dir; + int ret = 0; + + events_dir = opendir(tracing_events_path); + if (!events_dir) { + perror("Can't open event dir"); + return -1; + } + + while (!ret && (events_ent = readdir(events_dir))) { + if (!strcmp(events_ent->d_name, ".") + || !strcmp(events_ent->d_name, "..") + || !strcmp(events_ent->d_name, "enable") + || !strcmp(events_ent->d_name, "header_event") + || !strcmp(events_ent->d_name, "header_page")) + continue; + + if (!strglobmatch(events_ent->d_name, sys_name)) + continue; + + ret = add_tracepoint_event(list, idx, events_ent->d_name, + evt_name); + } + + closedir(events_dir); return ret; } @@ -420,9 +461,10 @@ int parse_events_add_tracepoint(struct list_head **list, int *idx, if (ret) return ret; - return strpbrk(event, "*?") ? - add_tracepoint_multi(list, idx, sys, event) : - add_tracepoint(list, idx, sys, event); + if (strpbrk(sys, "*?")) + return add_tracepoint_multi_sys(list, idx, sys, event); + else + return add_tracepoint_event(list, idx, sys, event); } static int @@ -492,7 +534,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, } static int config_term(struct perf_event_attr *attr, - struct parse_events__term *term) + struct parse_events_term *term) { #define CHECK_TYPE_VAL(type) \ do { \ @@ -537,7 +579,7 @@ do { \ static int config_attr(struct perf_event_attr *attr, struct list_head *head, int fail) { - struct parse_events__term *term; + struct parse_events_term *term; list_for_each_entry(term, head, list) if (config_term(attr, term) && fail) @@ -563,14 +605,14 @@ int parse_events_add_numeric(struct list_head **list, int *idx, return add_event(list, idx, &attr, NULL); } -static int parse_events__is_name_term(struct parse_events__term *term) +static int parse_events__is_name_term(struct parse_events_term *term) { return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; } static char *pmu_event_name(struct list_head *head_terms) { - struct parse_events__term *term; + struct parse_events_term *term; list_for_each_entry(term, head_terms, list) if (parse_events__is_name_term(term)) @@ -657,14 +699,6 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; - /* - * We are here for group and 'GH' was not set as event - * modifier and whatever event/group modifier override - * default 'GH' setup. - */ - if (evsel && !exclude_GH) - eH = eG = 0; - memset(mod, 0, sizeof(*mod)); while (*str) { @@ -722,6 +756,27 @@ static int get_event_modifier(struct event_modifier *mod, char *str, return 0; } +/* + * Basic modifier sanity check to validate it contains only one + * instance of any modifier (apart from 'p') present. + */ +static int check_modifier(char *str) +{ + char *p = str; + + /* The sizeof includes 0 byte as well. */ + if (strlen(str) > (sizeof("ukhGHppp") - 1)) + return -1; + + while (*p) { + if (*p != 'p' && strchr(p + 1, *p)) + return -1; + p++; + } + + return 0; +} + int parse_events__modifier_event(struct list_head *list, char *str, bool add) { struct perf_evsel *evsel; @@ -730,6 +785,9 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) if (str == NULL) return 0; + if (check_modifier(str)) + return -EINVAL; + if (!add && get_event_modifier(&mod, str, NULL)) return -EINVAL; @@ -790,7 +848,7 @@ static int parse_events__scanner(const char *str, void *data, int start_token) */ int parse_events_terms(struct list_head *terms, const char *str) { - struct parse_events_data__terms data = { + struct parse_events_terms data = { .terms = NULL, }; int ret; @@ -806,10 +864,9 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } -int parse_events(struct perf_evlist *evlist, const char *str, - int unset __maybe_unused) +int parse_events(struct perf_evlist *evlist, const char *str) { - struct parse_events_data__events data = { + struct parse_events_evlist data = { .list = LIST_HEAD_INIT(data.list), .idx = evlist->nr_entries, }; @@ -819,6 +876,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, if (!ret) { int entries = data.idx - evlist->nr_entries; perf_evlist__splice_list_tail(evlist, &data.list, entries); + evlist->nr_groups += data.nr_groups; return 0; } @@ -827,8 +885,6 @@ int parse_events(struct perf_evlist *evlist, const char *str, * Both call perf_evlist__delete in case of error, so we dont * need to bother. */ - fprintf(stderr, "invalid or unsupported event: '%s'\n", str); - fprintf(stderr, "Run 'perf list' for a list of valid events\n"); return ret; } @@ -836,7 +892,13 @@ int parse_events_option(const struct option *opt, const char *str, int unset __maybe_unused) { struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; - return parse_events(evlist, str, unset); + int ret = parse_events(evlist, str); + + if (ret) { + fprintf(stderr, "invalid or unsupported event: '%s'\n", str); + fprintf(stderr, "Run 'perf list' for a list of valid events\n"); + } + return ret; } int parse_filter(const struct option *opt, const char *str, @@ -1081,7 +1143,7 @@ void print_events(const char *event_glob, bool name_only) printf(" %-50s [%s]\n", "cpu/t1=v1[,t2=v2,t3 ...]/modifier", event_type_descriptors[PERF_TYPE_RAW]); - printf(" (see 'perf list --help' on how to encode it)\n"); + printf(" (see 'man perf-list' on how to encode it)\n"); printf("\n"); printf(" %-50s [%s]\n", @@ -1093,16 +1155,16 @@ void print_events(const char *event_glob, bool name_only) print_tracepoint_events(NULL, NULL, name_only); } -int parse_events__is_hardcoded_term(struct parse_events__term *term) +int parse_events__is_hardcoded_term(struct parse_events_term *term) { return term->type_term != PARSE_EVENTS__TERM_TYPE_USER; } -static int new_term(struct parse_events__term **_term, int type_val, +static int new_term(struct parse_events_term **_term, int type_val, int type_term, char *config, char *str, u64 num) { - struct parse_events__term *term; + struct parse_events_term *term; term = zalloc(sizeof(*term)); if (!term) @@ -1128,22 +1190,40 @@ static int new_term(struct parse_events__term **_term, int type_val, return 0; } -int parse_events__term_num(struct parse_events__term **term, +int parse_events_term__num(struct parse_events_term **term, int type_term, char *config, u64 num) { return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term, config, NULL, num); } -int parse_events__term_str(struct parse_events__term **term, +int parse_events_term__str(struct parse_events_term **term, int type_term, char *config, char *str) { return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term, config, str, 0); } -int parse_events__term_clone(struct parse_events__term **new, - struct parse_events__term *term) +int parse_events_term__sym_hw(struct parse_events_term **term, + char *config, unsigned idx) +{ + struct event_symbol *sym; + + BUG_ON(idx >= PERF_COUNT_HW_MAX); + sym = &event_symbols_hw[idx]; + + if (config) + return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, + PARSE_EVENTS__TERM_TYPE_USER, config, + (char *) sym->symbol, 0); + else + return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, + PARSE_EVENTS__TERM_TYPE_USER, + (char *) "event", (char *) sym->symbol, 0); +} + +int parse_events_term__clone(struct parse_events_term **new, + struct parse_events_term *term) { return new_term(new, term->type_val, term->type_term, term->config, term->val.str, term->val.num); @@ -1151,7 +1231,7 @@ int parse_events__term_clone(struct parse_events__term **new, void parse_events__free_terms(struct list_head *terms) { - struct parse_events__term *term, *h; + struct parse_events_term *term, *h; list_for_each_entry_safe(term, h, terms, list) free(term); diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 839230ceb18..8a4859315fd 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -7,7 +7,7 @@ #include <linux/list.h> #include <stdbool.h> #include "types.h" -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> #include "types.h" struct list_head; @@ -29,8 +29,7 @@ const char *event_type(int type); extern int parse_events_option(const struct option *opt, const char *str, int unset); -extern int parse_events(struct perf_evlist *evlist, const char *str, - int unset); +extern int parse_events(struct perf_evlist *evlist, const char *str); extern int parse_events_terms(struct list_head *terms, const char *str); extern int parse_filter(const struct option *opt, const char *str, int unset); @@ -51,7 +50,7 @@ enum { PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE, }; -struct parse_events__term { +struct parse_events_term { char *config; union { char *str; @@ -62,22 +61,25 @@ struct parse_events__term { struct list_head list; }; -struct parse_events_data__events { +struct parse_events_evlist { struct list_head list; int idx; + int nr_groups; }; -struct parse_events_data__terms { +struct parse_events_terms { struct list_head *terms; }; -int parse_events__is_hardcoded_term(struct parse_events__term *term); -int parse_events__term_num(struct parse_events__term **_term, +int parse_events__is_hardcoded_term(struct parse_events_term *term); +int parse_events_term__num(struct parse_events_term **_term, int type_term, char *config, u64 num); -int parse_events__term_str(struct parse_events__term **_term, +int parse_events_term__str(struct parse_events_term **_term, int type_term, char *config, char *str); -int parse_events__term_clone(struct parse_events__term **new, - struct parse_events__term *term); +int parse_events_term__sym_hw(struct parse_events_term **term, + char *config, unsigned idx); +int parse_events_term__clone(struct parse_events_term **new, + struct parse_events_term *term); void parse_events__free_terms(struct list_head *terms); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); @@ -97,7 +99,6 @@ void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); void parse_events_error(void *data, void *scanner, char const *msg); -int parse_events__test(void); void print_events(const char *event_glob, bool name_only); void print_events_type(u8 type); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index c87efc12579..e9d1134c2c6 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -81,7 +81,8 @@ num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?]* -modifier_event [ukhpGH]{1,8} +name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?]* +modifier_event [ukhpGH]+ modifier_bp [rwx]{1,3} %% @@ -168,6 +169,7 @@ period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } +{name_minus} { return str(yyscanner, PE_NAME); } } mem: { BEGIN(mem); return PE_PREFIX_MEM; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index cd88209e3c5..afc44c18dfe 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,5 +1,4 @@ %pure-parser -%name-prefix "parse_events_" %parse-param {void *_data} %parse-param {void *scanner} %lex-param {void* scanner} @@ -23,6 +22,14 @@ do { \ YYABORT; \ } while (0) +static inc_group_count(struct list_head *list, + struct parse_events_evlist *data) +{ + /* Count groups only have more than 1 members */ + if (!list_is_last(list->next, list)) + data->nr_groups++; +} + %} %token PE_START_EVENTS PE_START_TERMS @@ -68,7 +75,7 @@ do { \ char *str; u64 num; struct list_head *head; - struct parse_events__term *term; + struct parse_events_term *term; } %% @@ -79,7 +86,7 @@ PE_START_TERMS start_terms start_events: groups { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; parse_events_update_lists($1, &data->list); } @@ -123,6 +130,7 @@ PE_NAME '{' events '}' { struct list_head *list = $3; + inc_group_count(list, _data); parse_events__set_leader($1, list); $$ = list; } @@ -131,6 +139,7 @@ PE_NAME '{' events '}' { struct list_head *list = $2; + inc_group_count(list, _data); parse_events__set_leader(NULL, list); $$ = list; } @@ -186,7 +195,7 @@ event_def: event_pmu | event_pmu: PE_NAME '/' event_config '/' { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3)); @@ -202,7 +211,7 @@ PE_VALUE_SYM_SW event_legacy_symbol: value_sym '/' event_config '/' { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; @@ -215,7 +224,7 @@ value_sym '/' event_config '/' | value_sym sep_slash_dc { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; @@ -228,7 +237,7 @@ value_sym sep_slash_dc event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5)); @@ -237,7 +246,7 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL)); @@ -246,7 +255,7 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT | PE_NAME_CACHE_TYPE { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL)); @@ -256,7 +265,7 @@ PE_NAME_CACHE_TYPE event_legacy_mem: PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, @@ -266,7 +275,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc | PE_PREFIX_MEM PE_VALUE sep_dc { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, @@ -277,7 +286,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc event_legacy_tracepoint: PE_NAME ':' PE_NAME { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3)); @@ -287,7 +296,7 @@ PE_NAME ':' PE_NAME event_legacy_numeric: PE_VALUE ':' PE_VALUE { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL)); @@ -297,7 +306,7 @@ PE_VALUE ':' PE_VALUE event_legacy_raw: PE_RAW { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_numeric(&list, &data->idx, @@ -307,7 +316,7 @@ PE_RAW start_terms: event_config { - struct parse_events_data__terms *data = _data; + struct parse_events_terms *data = _data; data->terms = $1; } @@ -315,7 +324,7 @@ event_config: event_config ',' event_term { struct list_head *head = $1; - struct parse_events__term *term = $3; + struct parse_events_term *term = $3; ABORT_ON(!head); list_add_tail(&term->list, head); @@ -325,7 +334,7 @@ event_config ',' event_term event_term { struct list_head *head = malloc(sizeof(*head)); - struct parse_events__term *term = $1; + struct parse_events_term *term = $1; ABORT_ON(!head); INIT_LIST_HEAD(head); @@ -336,52 +345,70 @@ event_term event_term: PE_NAME '=' PE_NAME { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_str(&term, PARSE_EVENTS__TERM_TYPE_USER, + ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3)); $$ = term; } | PE_NAME '=' PE_VALUE { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER, + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3)); $$ = term; } | +PE_NAME '=' PE_VALUE_SYM_HW +{ + struct parse_events_term *term; + int config = $3 & 255; + + ABORT_ON(parse_events_term__sym_hw(&term, $1, config)); + $$ = term; +} +| PE_NAME { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER, + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, 1)); $$ = term; } | +PE_VALUE_SYM_HW +{ + struct parse_events_term *term; + int config = $1 & 255; + + ABORT_ON(parse_events_term__sym_hw(&term, NULL, config)); + $$ = term; +} +| PE_TERM '=' PE_NAME { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_str(&term, (int)$1, NULL, $3)); + ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3)); $$ = term; } | PE_TERM '=' PE_VALUE { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, $3)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3)); $$ = term; } | PE_TERM { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, 1)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1)); $$ = term; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 8a2229da594..4c6f9c490a8 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1,4 +1,3 @@ - #include <linux/list.h> #include <sys/types.h> #include <sys/stat.h> @@ -11,6 +10,19 @@ #include "parse-events.h" #include "cpumap.h" +struct perf_pmu_alias { + char *name; + struct list_head terms; + struct list_head list; +}; + +struct perf_pmu_format { + char *name; + int value; + DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); + struct list_head list; +}; + #define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/" int perf_pmu_parse(struct list_head *list, char *name); @@ -22,7 +34,7 @@ static LIST_HEAD(pmus); * Parse & process all the sysfs attributes located under * the directory specified in 'dir' parameter. */ -static int pmu_format_parse(char *dir, struct list_head *head) +int perf_pmu__format_parse(char *dir, struct list_head *head) { struct dirent *evt_ent; DIR *format_dir; @@ -77,7 +89,7 @@ static int pmu_format(char *name, struct list_head *format) if (stat(path, &st) < 0) return 0; /* no error if format does not exist */ - if (pmu_format_parse(path, format)) + if (perf_pmu__format_parse(path, format)) return -1; return 0; @@ -85,7 +97,7 @@ static int pmu_format(char *name, struct list_head *format) static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file) { - struct perf_pmu__alias *alias; + struct perf_pmu_alias *alias; char buf[256]; int ret; @@ -164,7 +176,7 @@ static int pmu_aliases(char *name, struct list_head *head) "%s/bus/event_source/devices/%s/events", sysfs, name); if (stat(path, &st) < 0) - return -1; + return 0; /* no error if 'events' does not exist */ if (pmu_aliases_parse(path, head)) return -1; @@ -172,15 +184,15 @@ static int pmu_aliases(char *name, struct list_head *head) return 0; } -static int pmu_alias_terms(struct perf_pmu__alias *alias, +static int pmu_alias_terms(struct perf_pmu_alias *alias, struct list_head *terms) { - struct parse_events__term *term, *clone; + struct parse_events_term *term, *clone; LIST_HEAD(list); int ret; list_for_each_entry(term, &alias->terms, list) { - ret = parse_events__term_clone(&clone, term); + ret = parse_events_term__clone(&clone, term); if (ret) { parse_events__free_terms(&list); return ret; @@ -296,6 +308,9 @@ static struct perf_pmu *pmu_lookup(char *name) if (pmu_format(name, &format)) return NULL; + if (pmu_aliases(name, &aliases)) + return NULL; + if (pmu_type(name, &type)) return NULL; @@ -305,8 +320,6 @@ static struct perf_pmu *pmu_lookup(char *name) pmu->cpus = pmu_cpumask(name); - pmu_aliases(name, &aliases); - INIT_LIST_HEAD(&pmu->format); INIT_LIST_HEAD(&pmu->aliases); list_splice(&format, &pmu->format); @@ -359,10 +372,10 @@ struct perf_pmu *perf_pmu__find(char *name) return pmu_lookup(name); } -static struct perf_pmu__format* +static struct perf_pmu_format * pmu_find_format(struct list_head *formats, char *name) { - struct perf_pmu__format *format; + struct perf_pmu_format *format; list_for_each_entry(format, formats, list) if (!strcmp(format->name, name)) @@ -402,9 +415,9 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value) */ static int pmu_config_term(struct list_head *formats, struct perf_event_attr *attr, - struct parse_events__term *term) + struct parse_events_term *term) { - struct perf_pmu__format *format; + struct perf_pmu_format *format; __u64 *vp; /* @@ -445,10 +458,11 @@ static int pmu_config_term(struct list_head *formats, return 0; } -static int pmu_config(struct list_head *formats, struct perf_event_attr *attr, - struct list_head *head_terms) +int perf_pmu__config_terms(struct list_head *formats, + struct perf_event_attr *attr, + struct list_head *head_terms) { - struct parse_events__term *term; + struct parse_events_term *term; list_for_each_entry(term, head_terms, list) if (pmu_config_term(formats, attr, term)) @@ -466,13 +480,13 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms) { attr->type = pmu->type; - return pmu_config(&pmu->format, attr, head_terms); + return perf_pmu__config_terms(&pmu->format, attr, head_terms); } -static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu, - struct parse_events__term *term) +static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, + struct parse_events_term *term) { - struct perf_pmu__alias *alias; + struct perf_pmu_alias *alias; char *name; if (parse_events__is_hardcoded_term(term)) @@ -505,8 +519,8 @@ static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu, */ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms) { - struct parse_events__term *term, *h; - struct perf_pmu__alias *alias; + struct parse_events_term *term, *h; + struct perf_pmu_alias *alias; int ret; list_for_each_entry_safe(term, h, head_terms, list) { @@ -525,7 +539,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms) int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits) { - struct perf_pmu__format *format; + struct perf_pmu_format *format; format = zalloc(sizeof(*format)); if (!format) @@ -546,181 +560,7 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to) if (!to) to = from; - memset(bits, 0, BITS_TO_LONGS(PERF_PMU_FORMAT_BITS)); + memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS)); for (b = from; b <= to; b++) set_bit(b, bits); } - -/* Simulated format definitions. */ -static struct test_format { - const char *name; - const char *value; -} test_formats[] = { - { "krava01", "config:0-1,62-63\n", }, - { "krava02", "config:10-17\n", }, - { "krava03", "config:5\n", }, - { "krava11", "config1:0,2,4,6,8,20-28\n", }, - { "krava12", "config1:63\n", }, - { "krava13", "config1:45-47\n", }, - { "krava21", "config2:0-3,10-13,20-23,30-33,40-43,50-53,60-63\n", }, - { "krava22", "config2:8,18,48,58\n", }, - { "krava23", "config2:28-29,38\n", }, -}; - -#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format)) - -/* Simulated users input. */ -static struct parse_events__term test_terms[] = { - { - .config = (char *) "krava01", - .val.num = 15, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava02", - .val.num = 170, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava03", - .val.num = 1, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava11", - .val.num = 27, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava12", - .val.num = 1, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava13", - .val.num = 2, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava21", - .val.num = 119, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava22", - .val.num = 11, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, - { - .config = (char *) "krava23", - .val.num = 2, - .type_val = PARSE_EVENTS__TERM_TYPE_NUM, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - }, -}; -#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term)) - -/* - * Prepare format directory data, exported by kernel - * at /sys/bus/event_source/devices/<dev>/format. - */ -static char *test_format_dir_get(void) -{ - static char dir[PATH_MAX]; - unsigned int i; - - snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX"); - if (!mkdtemp(dir)) - return NULL; - - for (i = 0; i < TEST_FORMATS_CNT; i++) { - static char name[PATH_MAX]; - struct test_format *format = &test_formats[i]; - FILE *file; - - snprintf(name, PATH_MAX, "%s/%s", dir, format->name); - - file = fopen(name, "w"); - if (!file) - return NULL; - - if (1 != fwrite(format->value, strlen(format->value), 1, file)) - break; - - fclose(file); - } - - return dir; -} - -/* Cleanup format directory. */ -static int test_format_dir_put(char *dir) -{ - char buf[PATH_MAX]; - snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir); - if (system(buf)) - return -1; - - snprintf(buf, PATH_MAX, "rmdir %s\n", dir); - return system(buf); -} - -static struct list_head *test_terms_list(void) -{ - static LIST_HEAD(terms); - unsigned int i; - - for (i = 0; i < TERMS_CNT; i++) - list_add_tail(&test_terms[i].list, &terms); - - return &terms; -} - -#undef TERMS_CNT - -int perf_pmu__test(void) -{ - char *format = test_format_dir_get(); - LIST_HEAD(formats); - struct list_head *terms = test_terms_list(); - int ret; - - if (!format) - return -EINVAL; - - do { - struct perf_event_attr attr; - - memset(&attr, 0, sizeof(attr)); - - ret = pmu_format_parse(format, &formats); - if (ret) - break; - - ret = pmu_config(&formats, &attr, terms); - if (ret) - break; - - ret = -EINVAL; - - if (attr.config != 0xc00000000002a823) - break; - if (attr.config1 != 0x8000400000000145) - break; - if (attr.config2 != 0x0400000020041d07) - break; - - ret = 0; - } while (0); - - test_format_dir_put(format); - return ret; -} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 39f3abac774..32fe55b659f 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -2,7 +2,7 @@ #define __PMU_H #include <linux/bitops.h> -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> enum { PERF_PMU_FORMAT_VALUE_CONFIG, @@ -12,19 +12,6 @@ enum { #define PERF_PMU_FORMAT_BITS 64 -struct perf_pmu__format { - char *name; - int value; - DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); - struct list_head list; -}; - -struct perf_pmu__alias { - char *name; - struct list_head terms; - struct list_head list; -}; - struct perf_pmu { char *name; __u32 type; @@ -37,15 +24,19 @@ struct perf_pmu { struct perf_pmu *perf_pmu__find(char *name); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); +int perf_pmu__config_terms(struct list_head *formats, + struct perf_event_attr *attr, + struct list_head *head_terms); int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, - struct list_head *head_terms); + struct list_head *head_terms); int perf_pmu_wrap(void); void perf_pmu_error(struct list_head *list, char *name, char const *msg); int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits); void perf_pmu__set_format(unsigned long *bits, long from, long to); +int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index ec898047ebb..bfd7e850986 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -1,5 +1,4 @@ -%name-prefix "perf_pmu_" %parse-param {struct list_head *format} %parse-param {char *name} diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1daf5c14e75..be0329394d5 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -413,12 +413,12 @@ static int convert_variable_type(Dwarf_Die *vr_die, dwarf_diename(vr_die), dwarf_diename(&type)); return -EINVAL; } + if (die_get_real_type(&type, &type) == NULL) { + pr_warning("Failed to get a type" + " information.\n"); + return -ENOENT; + } if (ret == DW_TAG_pointer_type) { - if (die_get_real_type(&type, &type) == NULL) { - pr_warning("Failed to get a type" - " information.\n"); - return -ENOENT; - } while (*ref_ptr) ref_ptr = &(*ref_ptr)->next; /* Add new reference with offset +0 */ diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index 13d36faf64e..daa17aeb6c6 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -17,59 +17,59 @@ struct pstack { struct pstack *pstack__new(unsigned short max_nr_entries) { - struct pstack *self = zalloc((sizeof(*self) + - max_nr_entries * sizeof(void *))); - if (self != NULL) - self->max_nr_entries = max_nr_entries; - return self; + struct pstack *pstack = zalloc((sizeof(*pstack) + + max_nr_entries * sizeof(void *))); + if (pstack != NULL) + pstack->max_nr_entries = max_nr_entries; + return pstack; } -void pstack__delete(struct pstack *self) +void pstack__delete(struct pstack *pstack) { - free(self); + free(pstack); } -bool pstack__empty(const struct pstack *self) +bool pstack__empty(const struct pstack *pstack) { - return self->top == 0; + return pstack->top == 0; } -void pstack__remove(struct pstack *self, void *key) +void pstack__remove(struct pstack *pstack, void *key) { - unsigned short i = self->top, last_index = self->top - 1; + unsigned short i = pstack->top, last_index = pstack->top - 1; while (i-- != 0) { - if (self->entries[i] == key) { + if (pstack->entries[i] == key) { if (i < last_index) - memmove(self->entries + i, - self->entries + i + 1, + memmove(pstack->entries + i, + pstack->entries + i + 1, (last_index - i) * sizeof(void *)); - --self->top; + --pstack->top; return; } } pr_err("%s: %p not on the pstack!\n", __func__, key); } -void pstack__push(struct pstack *self, void *key) +void pstack__push(struct pstack *pstack, void *key) { - if (self->top == self->max_nr_entries) { - pr_err("%s: top=%d, overflow!\n", __func__, self->top); + if (pstack->top == pstack->max_nr_entries) { + pr_err("%s: top=%d, overflow!\n", __func__, pstack->top); return; } - self->entries[self->top++] = key; + pstack->entries[pstack->top++] = key; } -void *pstack__pop(struct pstack *self) +void *pstack__pop(struct pstack *pstack) { void *ret; - if (self->top == 0) { + if (pstack->top == 0) { pr_err("%s: underflow!\n", __func__); return NULL; } - ret = self->entries[--self->top]; - self->entries[self->top] = NULL; + ret = pstack->entries[--pstack->top]; + pstack->entries[pstack->top] = NULL; return ret; } diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index c40c2d33199..64536a993f4 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -18,4 +18,5 @@ util/cgroup.c util/debugfs.c util/rblist.c util/strlist.c +util/sysfs.c ../../lib/rbtree.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 9181bf212fb..925e0c3e6d9 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -1015,6 +1015,8 @@ PyMODINIT_FUNC initperf(void) pyrf_cpu_map__setup_types() < 0) return; + page_size = sysconf(_SC_PAGE_SIZE); + Py_INCREF(&pyrf_evlist__type); PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type); @@ -1043,3 +1045,12 @@ error: if (PyErr_Occurred()) PyErr_SetString(PyExc_ImportError, "perf: Init failed!"); } + +/* + * Dummy, to avoid dragging all the test_attr infrastructure in the python + * binding. + */ +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags) +{ +} diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c index 0171fb61100..a16cdd2625a 100644 --- a/tools/perf/util/rblist.c +++ b/tools/perf/util/rblist.c @@ -44,6 +44,7 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry) void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node) { rb_erase(rb_node, &rblist->entries); + --rblist->nr_entries; rblist->node_delete(rblist, rb_node); } @@ -87,8 +88,7 @@ void rblist__delete(struct rblist *rblist) while (next) { pos = next; next = rb_next(pos); - rb_erase(pos, &rblist->entries); - rblist->node_delete(rblist, pos); + rblist__remove_node(rblist, pos); } free(rblist); } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index f80605eb185..eacec859f29 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -292,6 +292,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, ns = nsecs - s * NSECS_PER_SEC; scripting_context->event_data = data; + scripting_context->pevent = evsel->tp_format->pevent; ENTER; SAVETMPS; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 730c6630cba..e87aa5d9696 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -32,7 +32,6 @@ #include "../event.h" #include "../thread.h" #include "../trace-event.h" -#include "../evsel.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -266,6 +265,7 @@ static void python_process_tracepoint(union perf_event *perf_event ns = nsecs - s * NSECS_PER_SEC; scripting_context->event_data = data; + scripting_context->pevent = evsel->tp_format->pevent; context = PyCObject_FromVoidPtr(scripting_context, NULL); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 8cdd23239c9..bd85280bb6e 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -16,7 +16,6 @@ #include "cpumap.h" #include "event-parse.h" #include "perf_regs.h" -#include "unwind.h" #include "vdso.h" static int perf_session__open(struct perf_session *self, bool force) @@ -87,13 +86,12 @@ void perf_session__set_id_hdr_size(struct perf_session *session) { u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist); - session->host_machine.id_hdr_size = id_hdr_size; machines__set_id_hdr_size(&session->machines, id_hdr_size); } int perf_session__create_kernel_maps(struct perf_session *self) { - int ret = machine__create_kernel_maps(&self->host_machine); + int ret = machine__create_kernel_maps(&self->machines.host); if (ret >= 0) ret = machines__create_guest_kernel_maps(&self->machines); @@ -102,8 +100,7 @@ int perf_session__create_kernel_maps(struct perf_session *self) static void perf_session__destroy_kernel_maps(struct perf_session *self) { - machine__destroy_kernel_maps(&self->host_machine); - machines__destroy_guest_kernel_maps(&self->machines); + machines__destroy_kernel_maps(&self->machines); } struct perf_session *perf_session__new(const char *filename, int mode, @@ -128,22 +125,11 @@ struct perf_session *perf_session__new(const char *filename, int mode, goto out; memcpy(self->filename, filename, len); - /* - * On 64bit we can mmap the data file in one go. No need for tiny mmap - * slices. On 32bit we use 32MB. - */ -#if BITS_PER_LONG == 64 - self->mmap_window = ULLONG_MAX; -#else - self->mmap_window = 32 * 1024 * 1024ULL; -#endif - self->machines = RB_ROOT; self->repipe = repipe; INIT_LIST_HEAD(&self->ordered_samples.samples); INIT_LIST_HEAD(&self->ordered_samples.sample_cache); INIT_LIST_HEAD(&self->ordered_samples.to_free); - machine__init(&self->host_machine, "", HOST_KERNEL_ID); - hists__init(&self->hists); + machines__init(&self->machines); if (mode == O_RDONLY) { if (perf_session__open(self, force) < 0) @@ -171,37 +157,30 @@ out_delete: return NULL; } -static void machine__delete_dead_threads(struct machine *machine) -{ - struct thread *n, *t; - - list_for_each_entry_safe(t, n, &machine->dead_threads, node) { - list_del(&t->node); - thread__delete(t); - } -} - static void perf_session__delete_dead_threads(struct perf_session *session) { - machine__delete_dead_threads(&session->host_machine); + machine__delete_dead_threads(&session->machines.host); } -static void machine__delete_threads(struct machine *self) +static void perf_session__delete_threads(struct perf_session *session) { - struct rb_node *nd = rb_first(&self->threads); - - while (nd) { - struct thread *t = rb_entry(nd, struct thread, rb_node); - - rb_erase(&t->rb_node, &self->threads); - nd = rb_next(nd); - thread__delete(t); - } + machine__delete_threads(&session->machines.host); } -static void perf_session__delete_threads(struct perf_session *session) +static void perf_session_env__delete(struct perf_session_env *env) { - machine__delete_threads(&session->host_machine); + free(env->hostname); + free(env->os_release); + free(env->version); + free(env->arch); + free(env->cpu_desc); + free(env->cpuid); + + free(env->cmdline); + free(env->sibling_cores); + free(env->sibling_threads); + free(env->numa_nodes); + free(env->pmu_mappings); } void perf_session__delete(struct perf_session *self) @@ -209,198 +188,13 @@ void perf_session__delete(struct perf_session *self) perf_session__destroy_kernel_maps(self); perf_session__delete_dead_threads(self); perf_session__delete_threads(self); - machine__exit(&self->host_machine); + perf_session_env__delete(&self->header.env); + machines__exit(&self->machines); close(self->fd); free(self); vdso__exit(); } -void machine__remove_thread(struct machine *self, struct thread *th) -{ - self->last_match = NULL; - rb_erase(&th->rb_node, &self->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, &self->dead_threads); -} - -static bool symbol__match_parent_regex(struct symbol *sym) -{ - if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) - return 1; - - return 0; -} - -static const u8 cpumodes[] = { - PERF_RECORD_MISC_USER, - PERF_RECORD_MISC_KERNEL, - PERF_RECORD_MISC_GUEST_USER, - PERF_RECORD_MISC_GUEST_KERNEL -}; -#define NCPUMODES (sizeof(cpumodes)/sizeof(u8)) - -static void ip__resolve_ams(struct machine *self, struct thread *thread, - struct addr_map_symbol *ams, - u64 ip) -{ - struct addr_location al; - size_t i; - u8 m; - - memset(&al, 0, sizeof(al)); - - for (i = 0; i < NCPUMODES; i++) { - m = cpumodes[i]; - /* - * We cannot use the header.misc hint to determine whether a - * branch stack address is user, kernel, guest, hypervisor. - * Branches may straddle the kernel/user/hypervisor boundaries. - * Thus, we have to try consecutively until we find a match - * or else, the symbol is unknown - */ - thread__find_addr_location(thread, self, m, MAP__FUNCTION, - ip, &al, NULL); - if (al.sym) - goto found; - } -found: - ams->addr = ip; - ams->al_addr = al.addr; - ams->sym = al.sym; - ams->map = al.map; -} - -struct branch_info *machine__resolve_bstack(struct machine *self, - struct thread *thr, - struct branch_stack *bs) -{ - struct branch_info *bi; - unsigned int i; - - bi = calloc(bs->nr, sizeof(struct branch_info)); - if (!bi) - return NULL; - - for (i = 0; i < bs->nr; i++) { - ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to); - ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from); - bi[i].flags = bs->entries[i].flags; - } - return bi; -} - -static int machine__resolve_callchain_sample(struct machine *machine, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent) - -{ - u8 cpumode = PERF_RECORD_MISC_USER; - unsigned int i; - int err; - - callchain_cursor_reset(&callchain_cursor); - - if (chain->nr > PERF_MAX_STACK_DEPTH) { - pr_warning("corrupted callchain. skipping...\n"); - return 0; - } - - for (i = 0; i < chain->nr; i++) { - u64 ip; - struct addr_location al; - - if (callchain_param.order == ORDER_CALLEE) - ip = chain->ips[i]; - else - ip = chain->ips[chain->nr - i - 1]; - - if (ip >= PERF_CONTEXT_MAX) { - switch (ip) { - case PERF_CONTEXT_HV: - cpumode = PERF_RECORD_MISC_HYPERVISOR; - break; - case PERF_CONTEXT_KERNEL: - cpumode = PERF_RECORD_MISC_KERNEL; - break; - case PERF_CONTEXT_USER: - cpumode = PERF_RECORD_MISC_USER; - break; - default: - pr_debug("invalid callchain context: " - "%"PRId64"\n", (s64) ip); - /* - * It seems the callchain is corrupted. - * Discard all. - */ - callchain_cursor_reset(&callchain_cursor); - return 0; - } - continue; - } - - al.filtered = false; - thread__find_addr_location(thread, machine, cpumode, - MAP__FUNCTION, ip, &al, NULL); - if (al.sym != NULL) { - if (sort__has_parent && !*parent && - symbol__match_parent_regex(al.sym)) - *parent = al.sym; - if (!symbol_conf.use_callchain) - break; - } - - err = callchain_cursor_append(&callchain_cursor, - ip, al.map, al.sym); - if (err) - return err; - } - - return 0; -} - -static int unwind_entry(struct unwind_entry *entry, void *arg) -{ - struct callchain_cursor *cursor = arg; - return callchain_cursor_append(cursor, entry->ip, - entry->map, entry->sym); -} - -int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, - struct thread *thread, - struct perf_sample *sample, - struct symbol **parent) - -{ - int ret; - - callchain_cursor_reset(&callchain_cursor); - - ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent); - if (ret) - return ret; - - /* Can we do dwarf post unwind? */ - if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && - (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) - return 0; - - /* Bail out if nothing was captured. */ - if ((!sample->user_regs.regs) || - (!sample->user_stack.size)) - return 0; - - return unwind__get_entries(unwind_entry, &callchain_cursor, machine, - thread, evsel->attr.sample_regs_user, - sample); - -} - static int process_event_synth_tracing_data_stub(union perf_event *event __maybe_unused, struct perf_session *session @@ -1027,7 +821,7 @@ static struct machine * return perf_session__findnew_machine(session, pid); } - return perf_session__find_host_machine(session); + return &session->machines.host; } static int perf_session_deliver_event(struct perf_session *session, @@ -1065,11 +859,11 @@ static int perf_session_deliver_event(struct perf_session *session, case PERF_RECORD_SAMPLE: dump_sample(evsel, event, sample); if (evsel == NULL) { - ++session->hists.stats.nr_unknown_id; + ++session->stats.nr_unknown_id; return 0; } if (machine == NULL) { - ++session->hists.stats.nr_unprocessable_samples; + ++session->stats.nr_unprocessable_samples; return 0; } return tool->sample(tool, event, sample, evsel, machine); @@ -1083,7 +877,7 @@ static int perf_session_deliver_event(struct perf_session *session, return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: if (tool->lost == perf_event__process_lost) - session->hists.stats.total_lost += event->lost.lost; + session->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); case PERF_RECORD_READ: return tool->read(tool, event, sample, evsel, machine); @@ -1092,7 +886,7 @@ static int perf_session_deliver_event(struct perf_session *session, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); default: - ++session->hists.stats.nr_unknown_events; + ++session->stats.nr_unknown_events; return -1; } } @@ -1106,8 +900,8 @@ static int perf_session__preprocess_sample(struct perf_session *session, if (!ip_callchain__valid(sample->callchain, event)) { pr_debug("call-chain problem with event, skipping it.\n"); - ++session->hists.stats.nr_invalid_chains; - session->hists.stats.total_invalid_chains += sample->period; + ++session->stats.nr_invalid_chains; + session->stats.total_invalid_chains += sample->period; return -EINVAL; } return 0; @@ -1165,7 +959,7 @@ static int perf_session__process_event(struct perf_session *session, if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; - hists__inc_nr_events(&session->hists, event->header.type); + events_stats__inc(&session->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, file_offset); @@ -1201,7 +995,7 @@ void perf_event_header__bswap(struct perf_event_header *self) struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->host_machine, pid); + return machine__findnew_thread(&session->machines.host, pid); } static struct thread *perf_session__register_idle_thread(struct perf_session *self) @@ -1220,39 +1014,39 @@ static void perf_session__warn_about_errors(const struct perf_session *session, const struct perf_tool *tool) { if (tool->lost == perf_event__process_lost && - session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) { + session->stats.nr_events[PERF_RECORD_LOST] != 0) { ui__warning("Processed %d events and lost %d chunks!\n\n" "Check IO/CPU overload!\n\n", - session->hists.stats.nr_events[0], - session->hists.stats.nr_events[PERF_RECORD_LOST]); + session->stats.nr_events[0], + session->stats.nr_events[PERF_RECORD_LOST]); } - if (session->hists.stats.nr_unknown_events != 0) { + if (session->stats.nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " "file generated by a more recent tool?\n\n" "If that is not the case, consider " "reporting to linux-kernel@vger.kernel.org.\n\n", - session->hists.stats.nr_unknown_events); + session->stats.nr_unknown_events); } - if (session->hists.stats.nr_unknown_id != 0) { + if (session->stats.nr_unknown_id != 0) { ui__warning("%u samples with id not present in the header\n", - session->hists.stats.nr_unknown_id); + session->stats.nr_unknown_id); } - if (session->hists.stats.nr_invalid_chains != 0) { + if (session->stats.nr_invalid_chains != 0) { ui__warning("Found invalid callchains!\n\n" "%u out of %u events were discarded for this reason.\n\n" "Consider reporting to linux-kernel@vger.kernel.org.\n\n", - session->hists.stats.nr_invalid_chains, - session->hists.stats.nr_events[PERF_RECORD_SAMPLE]); + session->stats.nr_invalid_chains, + session->stats.nr_events[PERF_RECORD_SAMPLE]); } - if (session->hists.stats.nr_unprocessable_samples != 0) { + if (session->stats.nr_unprocessable_samples != 0) { ui__warning("%u unprocessable samples recorded.\n" "Do you have a KVM guest running and not using 'perf kvm'?\n", - session->hists.stats.nr_unprocessable_samples); + session->stats.nr_unprocessable_samples); } } @@ -1369,21 +1163,31 @@ fetch_mmaped_event(struct perf_session *session, return event; } +/* + * On 64bit we can mmap the data file in one go. No need for tiny mmap + * slices. On 32bit we use 32MB. + */ +#if BITS_PER_LONG == 64 +#define MMAP_SIZE ULLONG_MAX +#define NUM_MMAPS 1 +#else +#define MMAP_SIZE (32 * 1024 * 1024ULL) +#define NUM_MMAPS 128 +#endif + int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 file_size, struct perf_tool *tool) { u64 head, page_offset, file_offset, file_pos, progress_next; int err, mmap_prot, mmap_flags, map_idx = 0; - size_t page_size, mmap_size; - char *buf, *mmaps[8]; + size_t mmap_size; + char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; uint32_t size; perf_tool__fill_defaults(tool); - page_size = sysconf(_SC_PAGESIZE); - page_offset = page_size * (data_offset / page_size); file_offset = page_offset; head = data_offset - page_offset; @@ -1393,7 +1197,7 @@ int __perf_session__process_events(struct perf_session *session, progress_next = file_size / 16; - mmap_size = session->mmap_window; + mmap_size = MMAP_SIZE; if (mmap_size > file_size) mmap_size = file_size; @@ -1460,6 +1264,7 @@ more: session->ordered_samples.next_flush = ULLONG_MAX; err = flush_sample_queue(session, tool); out_err: + ui_progress__finish(); perf_session__warn_about_errors(session, tool); perf_session_free_sample_buffers(session); return err; @@ -1527,16 +1332,13 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp) { - return __dsos__fprintf(&self->host_machine.kernel_dsos, fp) + - __dsos__fprintf(&self->host_machine.user_dsos, fp) + - machines__fprintf_dsos(&self->machines, fp); + return machines__fprintf_dsos(&self->machines, fp); } size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, - bool with_hits) + bool (skip)(struct dso *dso, int parm), int parm) { - size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits); - return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits); + return machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm); } size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) @@ -1544,11 +1346,11 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) struct perf_evsel *pos; size_t ret = fprintf(fp, "Aggregated stats:\n"); - ret += hists__fprintf_nr_events(&session->hists, fp); + ret += events_stats__fprintf(&session->stats, fp); list_for_each_entry(pos, &session->evlist->entries, node) { ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); - ret += hists__fprintf_nr_events(&pos->hists, fp); + ret += events_stats__fprintf(&pos->hists.stats, fp); } return ret; @@ -1560,7 +1362,7 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp) * FIXME: Here we have to actually print all the machines in this * session, not just the host... */ - return machine__fprintf(&session->host_machine, fp); + return machine__fprintf(&session->machines.host, fp); } void perf_session__remove_thread(struct perf_session *session, @@ -1569,10 +1371,10 @@ void perf_session__remove_thread(struct perf_session *session, /* * 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 ->host_machine is wrong. Fix when auditing all + * doing it always on ->machines.host is wrong. Fix when auditing all * the 'perf kvm' code. */ - machine__remove_thread(&session->host_machine, th); + machine__remove_thread(&session->machines.host, th); } struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index dd6426163ba..b5c0847edfa 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -4,10 +4,11 @@ #include "hist.h" #include "event.h" #include "header.h" +#include "machine.h" #include "symbol.h" #include "thread.h" #include <linux/rbtree.h> -#include "../../../include/uapi/linux/perf_event.h" +#include <linux/perf_event.h> struct sample_queue; struct ip_callchain; @@ -29,16 +30,10 @@ struct ordered_samples { struct perf_session { struct perf_header header; unsigned long size; - unsigned long mmap_window; - struct machine host_machine; - struct rb_root machines; + struct machines machines; struct perf_evlist *evlist; struct pevent *pevent; - /* - * FIXME: Need to split this up further, we need global - * stats + per event stats. - */ - struct hists hists; + struct events_stats stats; int fd; bool fd_pipe; bool repipe; @@ -53,7 +48,7 @@ struct perf_tool; struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe, struct perf_tool *tool); -void perf_session__delete(struct perf_session *self); +void perf_session__delete(struct perf_session *session); void perf_event_header__bswap(struct perf_event_header *self); @@ -68,10 +63,6 @@ int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel struct ip_callchain *chain, struct symbol **parent); -struct branch_info *machine__resolve_bstack(struct machine *self, - struct thread *thread, - struct branch_stack *bs); - bool perf_session__has_traces(struct perf_session *self, const char *msg); void mem_bswap_64(void *src, int byte_size); @@ -84,43 +75,24 @@ 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_host_machine(struct perf_session *self) -{ - return &self->host_machine; -} - -static inline struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid) { - if (pid == HOST_KERNEL_ID) - return &self->host_machine; return machines__find(&self->machines, pid); } static inline struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid) { - if (pid == HOST_KERNEL_ID) - return &self->host_machine; return machines__findnew(&self->machines, pid); } -static inline -void perf_session__process_machines(struct perf_session *self, - struct perf_tool *tool, - machine__process_t process) -{ - process(&self->host_machine, tool); - return machines__process(&self->machines, process, tool); -} - struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); size_t perf_session__fprintf(struct perf_session *self, FILE *fp); size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp); -size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, - FILE *fp, bool with_hits); +size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, + bool (fn)(struct dso *dso, int parm), int parm); size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index cfd1c0feb32..d41926cb9e3 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -60,7 +60,7 @@ sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*s:%5d", width, + return repsep_snprintf(bf, size, "%*s:%5d", width - 6, self->thread->comm ?: "", self->thread->pid); } @@ -97,6 +97,16 @@ static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, return repsep_snprintf(bf, size, "%*s", width, self->thread->comm); } +struct sort_entry sort_comm = { + .se_header = "Command", + .se_cmp = sort__comm_cmp, + .se_collapse = sort__comm_collapse, + .se_snprintf = hist_entry__comm_snprintf, + .se_width_idx = HISTC_COMM, +}; + +/* --sort dso */ + static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) { struct dso *dso_l = map_l ? map_l->dso : NULL; @@ -117,40 +127,12 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) return strcmp(dso_name_l, dso_name_r); } -struct sort_entry sort_comm = { - .se_header = "Command", - .se_cmp = sort__comm_cmp, - .se_collapse = sort__comm_collapse, - .se_snprintf = hist_entry__comm_snprintf, - .se_width_idx = HISTC_COMM, -}; - -/* --sort dso */ - static int64_t sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) { return _sort__dso_cmp(left->ms.map, right->ms.map); } - -static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r, - u64 ip_l, u64 ip_r) -{ - if (!sym_l || !sym_r) - return cmp_null(sym_l, sym_r); - - if (sym_l == sym_r) - return 0; - - if (sym_l) - ip_l = sym_l->start; - if (sym_r) - ip_r = sym_r->start; - - return (int64_t)(ip_r - ip_l); -} - static int _hist_entry__dso_snprintf(struct map *map, char *bf, size_t size, unsigned int width) { @@ -169,9 +151,43 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, return _hist_entry__dso_snprintf(self->ms.map, bf, size, width); } +struct sort_entry sort_dso = { + .se_header = "Shared Object", + .se_cmp = sort__dso_cmp, + .se_snprintf = hist_entry__dso_snprintf, + .se_width_idx = HISTC_DSO, +}; + +/* --sort symbol */ + +static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r) +{ + u64 ip_l, ip_r; + + if (!sym_l || !sym_r) + return cmp_null(sym_l, sym_r); + + if (sym_l == sym_r) + return 0; + + ip_l = sym_l->start; + ip_r = sym_r->start; + + return (int64_t)(ip_r - ip_l); +} + +static int64_t +sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->ms.sym && !right->ms.sym) + return right->level - left->level; + + return _sort__sym_cmp(left->ms.sym, right->ms.sym); +} + static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, u64 ip, char level, char *bf, size_t size, - unsigned int width __maybe_unused) + unsigned int width) { size_t ret = 0; @@ -197,43 +213,13 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, return ret; } - -struct sort_entry sort_dso = { - .se_header = "Shared Object", - .se_cmp = sort__dso_cmp, - .se_snprintf = hist_entry__dso_snprintf, - .se_width_idx = HISTC_DSO, -}; - static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip, self->level, bf, size, width); } -/* --sort symbol */ -static int64_t -sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) -{ - u64 ip_l, ip_r; - - if (!left->ms.sym && !right->ms.sym) - return right->level - left->level; - - if (!left->ms.sym || !right->ms.sym) - return cmp_null(left->ms.sym, right->ms.sym); - - if (left->ms.sym == right->ms.sym) - return 0; - - ip_l = left->ms.sym->start; - ip_r = right->ms.sym->start; - - return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r); -} - struct sort_entry sort_sym = { .se_header = "Symbol", .se_cmp = sort__sym_cmp, @@ -253,7 +239,7 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width __maybe_unused) { - FILE *fp; + FILE *fp = NULL; char cmd[PATH_MAX + 2], *path = self->srcline, *nl; size_t line_len; @@ -274,7 +260,6 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, if (getline(&path, &line_len, fp) < 0 || !line_len) goto out_ip; - fclose(fp); self->srcline = strdup(path); if (self->srcline == NULL) goto out_ip; @@ -284,8 +269,12 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, *nl = '\0'; path = self->srcline; out_path: + if (fp) + pclose(fp); return repsep_snprintf(bf, size, "%s", path); out_ip: + if (fp) + pclose(fp); return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip); } @@ -335,7 +324,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*d", width, self->cpu); + return repsep_snprintf(bf, size, "%*d", width, self->cpu); } struct sort_entry sort_cpu = { @@ -345,6 +334,8 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; +/* sort keys for branch stacks */ + static int64_t sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -359,13 +350,6 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf, bf, size, width); } -struct sort_entry sort_dso_from = { - .se_header = "Source Shared Object", - .se_cmp = sort__dso_from_cmp, - .se_snprintf = hist_entry__dso_from_snprintf, - .se_width_idx = HISTC_DSO_FROM, -}; - static int64_t sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -389,8 +373,7 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) if (!from_l->sym && !from_r->sym) return right->level - left->level; - return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr, - from_r->addr); + return _sort__sym_cmp(from_l->sym, from_r->sym); } static int64_t @@ -402,12 +385,11 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) if (!to_l->sym && !to_r->sym) return right->level - left->level; - return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr); + return _sort__sym_cmp(to_l->sym, to_r->sym); } static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { struct addr_map_symbol *from = &self->branch_info->from; return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, @@ -416,8 +398,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, } static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { struct addr_map_symbol *to = &self->branch_info->to; return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, @@ -425,6 +406,13 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, } +struct sort_entry sort_dso_from = { + .se_header = "Source Shared Object", + .se_cmp = sort__dso_from_cmp, + .se_snprintf = hist_entry__dso_from_snprintf, + .se_width_idx = HISTC_DSO_FROM, +}; + struct sort_entry sort_dso_to = { .se_header = "Target Shared Object", .se_cmp = sort__dso_to_cmp, @@ -484,30 +472,40 @@ struct sort_dimension { #define DIM(d, n, func) [d] = { .name = n, .entry = &(func) } -static struct sort_dimension sort_dimensions[] = { +static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PID, "pid", sort_thread), DIM(SORT_COMM, "comm", sort_comm), DIM(SORT_DSO, "dso", sort_dso), - DIM(SORT_DSO_FROM, "dso_from", sort_dso_from), - DIM(SORT_DSO_TO, "dso_to", sort_dso_to), DIM(SORT_SYM, "symbol", sort_sym), - DIM(SORT_SYM_TO, "symbol_from", sort_sym_from), - DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to), DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), - DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), DIM(SORT_SRCLINE, "srcline", sort_srcline), }; +#undef DIM + +#define DIM(d, n, func) [d - __SORT_BRANCH_STACK] = { .name = n, .entry = &(func) } + +static struct sort_dimension bstack_sort_dimensions[] = { + DIM(SORT_DSO_FROM, "dso_from", sort_dso_from), + DIM(SORT_DSO_TO, "dso_to", sort_dso_to), + DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from), + DIM(SORT_SYM_TO, "symbol_to", sort_sym_to), + DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), +}; + +#undef DIM + int sort_dimension__add(const char *tok) { unsigned int i; - for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { - struct sort_dimension *sd = &sort_dimensions[i]; + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sd->entry == &sort_parent) { int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); if (ret) { @@ -518,9 +516,7 @@ int sort_dimension__add(const char *tok) return -EINVAL; } sort__has_parent = 1; - } else if (sd->entry == &sort_sym || - sd->entry == &sort_sym_from || - sd->entry == &sort_sym_to) { + } else if (sd->entry == &sort_sym) { sort__has_sym = 1; } @@ -530,52 +526,69 @@ int sort_dimension__add(const char *tok) if (sd->entry->se_collapse) sort__need_collapse = 1; - if (list_empty(&hist_entry__sort_list)) { - if (!strcmp(sd->name, "pid")) - sort__first_dimension = SORT_PID; - else if (!strcmp(sd->name, "comm")) - sort__first_dimension = SORT_COMM; - else if (!strcmp(sd->name, "dso")) - sort__first_dimension = SORT_DSO; - else if (!strcmp(sd->name, "symbol")) - sort__first_dimension = SORT_SYM; - else if (!strcmp(sd->name, "parent")) - sort__first_dimension = SORT_PARENT; - else if (!strcmp(sd->name, "cpu")) - sort__first_dimension = SORT_CPU; - else if (!strcmp(sd->name, "symbol_from")) - sort__first_dimension = SORT_SYM_FROM; - else if (!strcmp(sd->name, "symbol_to")) - sort__first_dimension = SORT_SYM_TO; - else if (!strcmp(sd->name, "dso_from")) - sort__first_dimension = SORT_DSO_FROM; - else if (!strcmp(sd->name, "dso_to")) - sort__first_dimension = SORT_DSO_TO; - else if (!strcmp(sd->name, "mispredict")) - sort__first_dimension = SORT_MISPREDICT; - } + if (list_empty(&hist_entry__sort_list)) + sort__first_dimension = i; list_add_tail(&sd->entry->list, &hist_entry__sort_list); sd->taken = 1; return 0; } + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { + struct sort_dimension *sd = &bstack_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sort__branch_mode != 1) + return -EINVAL; + + if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) + 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 + __SORT_BRANCH_STACK; + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; + + return 0; + } + return -ESRCH; } -void setup_sorting(const char * const usagestr[], const struct option *opts) +int setup_sorting(void) { char *tmp, *tok, *str = strdup(sort_order); + int ret = 0; + + if (str == NULL) { + error("Not enough memory to setup sort keys"); + return -ENOMEM; + } for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - if (sort_dimension__add(tok) < 0) { + ret = sort_dimension__add(tok); + if (ret == -EINVAL) { + error("Invalid --sort key: `%s'", tok); + break; + } else if (ret == -ESRCH) { error("Unknown --sort key: `%s'", tok); - usage_with_options(usagestr, opts); + break; } } free(str); + return ret; } void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 5786f323b59..b13e56f6ccb 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -52,6 +52,19 @@ struct he_stat { u32 nr_events; }; +struct hist_entry_diff { + bool computed; + + /* PERF_HPP__DELTA */ + double period_ratio_delta; + + /* PERF_HPP__RATIO */ + double period_ratio; + + /* HISTC_WEIGHTED_DIFF */ + s64 wdiff; +}; + /** * struct hist_entry - histogram entry * @@ -61,12 +74,18 @@ struct he_stat { struct hist_entry { struct rb_node rb_node_in; struct rb_node rb_node; + union { + struct list_head node; + struct list_head head; + } pairs; struct he_stat stat; struct map_symbol ms; struct thread *thread; u64 ip; s32 cpu; + struct hist_entry_diff diff; + /* XXX These two should move to some tree widget lib */ u16 row_offset; u16 nr_rows; @@ -78,28 +97,47 @@ struct hist_entry { char *srcline; struct symbol *parent; unsigned long position; - union { - struct hist_entry *pair; - struct rb_root sorted_chain; - }; + struct rb_root sorted_chain; struct branch_info *branch_info; struct hists *hists; struct callchain_root callchain[0]; }; +static inline bool hist_entry__has_pairs(struct hist_entry *he) +{ + return !list_empty(&he->pairs.node); +} + +static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he) +{ + if (hist_entry__has_pairs(he)) + return list_entry(he->pairs.node.next, struct hist_entry, pairs.node); + return NULL; +} + +static inline void hist_entry__add_pair(struct hist_entry *he, + struct hist_entry *pair) +{ + list_add_tail(&he->pairs.head, &pair->pairs.node); +} + enum sort_type { + /* common sort keys */ SORT_PID, SORT_COMM, SORT_DSO, SORT_SYM, SORT_PARENT, SORT_CPU, - SORT_DSO_FROM, + SORT_SRCLINE, + + /* branch stack specific sort keys */ + __SORT_BRANCH_STACK, + SORT_DSO_FROM = __SORT_BRANCH_STACK, SORT_DSO_TO, SORT_SYM_FROM, SORT_SYM_TO, SORT_MISPREDICT, - SORT_SRCLINE, }; /* @@ -122,7 +160,7 @@ struct sort_entry { extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; -void setup_sorting(const char * const usagestr[], const struct option *opts); +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); diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 2eeb51baf07..cfa906882e2 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -90,17 +90,17 @@ void strbuf_addf(struct strbuf *sb, const char *fmt, ...) if (!strbuf_avail(sb)) strbuf_grow(sb, 64); va_start(ap, fmt); - len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); va_end(ap); if (len < 0) - die("your vscnprintf is broken"); + die("your vsnprintf is broken"); if (len > strbuf_avail(sb)) { strbuf_grow(sb, len); va_start(ap, fmt); - len = vscnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); + len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap); va_end(ap); if (len > strbuf_avail(sb)) { - die("this should not happen, your snprintf is broken"); + die("this should not happen, your vsnprintf is broken"); } } strbuf_setlen(sb, sb->len + len); diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 32170590892..29c7b2cb252 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -314,6 +314,42 @@ int strtailcmp(const char *s1, const char *s2) } /** + * strxfrchar - Locate and replace character in @s + * @s: The string to be searched/changed. + * @from: Source character to be replaced. + * @to: Destination character. + * + * Return pointer to the changed string. + */ +char *strxfrchar(char *s, char from, char to) +{ + char *p = s; + + while ((p = strchr(p, from)) != NULL) + *p++ = to; + + return s; +} + +/** + * ltrim - Removes leading whitespace from @s. + * @s: The string to be stripped. + * + * Return pointer to the first non-whitespace character in @s. + */ +char *ltrim(char *s) +{ + int len = strlen(s); + + while (len && isspace(*s)) { + len--; + s++; + } + + return s; +} + +/** * rtrim - Removes trailing whitespace from @s. * @s: The string to be stripped. * diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index 155d8b7078a..55433aa42c8 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -35,11 +35,11 @@ out_delete: return NULL; } -static void str_node__delete(struct str_node *self, bool dupstr) +static void str_node__delete(struct str_node *snode, bool dupstr) { if (dupstr) - free((void *)self->s); - free(self); + free((void *)snode->s); + free(snode); } static @@ -59,12 +59,12 @@ static int strlist__node_cmp(struct rb_node *rb_node, const void *entry) return strcmp(snode->s, str); } -int strlist__add(struct strlist *self, const char *new_entry) +int strlist__add(struct strlist *slist, const char *new_entry) { - return rblist__add_node(&self->rblist, new_entry); + return rblist__add_node(&slist->rblist, new_entry); } -int strlist__load(struct strlist *self, const char *filename) +int strlist__load(struct strlist *slist, const char *filename) { char entry[1024]; int err; @@ -80,7 +80,7 @@ int strlist__load(struct strlist *self, const char *filename) continue; entry[len - 1] = '\0'; - err = strlist__add(self, entry); + err = strlist__add(slist, entry); if (err != 0) goto out; } @@ -107,56 +107,56 @@ struct str_node *strlist__find(struct strlist *slist, const char *entry) return snode; } -static int strlist__parse_list_entry(struct strlist *self, const char *s) +static int strlist__parse_list_entry(struct strlist *slist, const char *s) { if (strncmp(s, "file://", 7) == 0) - return strlist__load(self, s + 7); + return strlist__load(slist, s + 7); - return strlist__add(self, s); + return strlist__add(slist, s); } -int strlist__parse_list(struct strlist *self, const char *s) +int strlist__parse_list(struct strlist *slist, const char *s) { char *sep; int err; while ((sep = strchr(s, ',')) != NULL) { *sep = '\0'; - err = strlist__parse_list_entry(self, s); + err = strlist__parse_list_entry(slist, s); *sep = ','; if (err != 0) return err; s = sep + 1; } - return *s ? strlist__parse_list_entry(self, s) : 0; + return *s ? strlist__parse_list_entry(slist, s) : 0; } -struct strlist *strlist__new(bool dupstr, const char *slist) +struct strlist *strlist__new(bool dupstr, const char *list) { - struct strlist *self = malloc(sizeof(*self)); + struct strlist *slist = malloc(sizeof(*slist)); - if (self != NULL) { - rblist__init(&self->rblist); - self->rblist.node_cmp = strlist__node_cmp; - self->rblist.node_new = strlist__node_new; - self->rblist.node_delete = strlist__node_delete; + if (slist != NULL) { + rblist__init(&slist->rblist); + slist->rblist.node_cmp = strlist__node_cmp; + slist->rblist.node_new = strlist__node_new; + slist->rblist.node_delete = strlist__node_delete; - self->dupstr = dupstr; - if (slist && strlist__parse_list(self, slist) != 0) + slist->dupstr = dupstr; + if (slist && strlist__parse_list(slist, list) != 0) goto out_error; } - return self; + return slist; out_error: - free(self); + free(slist); return NULL; } -void strlist__delete(struct strlist *self) +void strlist__delete(struct strlist *slist) { - if (self != NULL) - rblist__delete(&self->rblist); + if (slist != NULL) + rblist__delete(&slist->rblist); } struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx) diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index dd9f922ec67..5c7f87069d9 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -17,34 +17,34 @@ struct strlist { }; struct strlist *strlist__new(bool dupstr, const char *slist); -void strlist__delete(struct strlist *self); +void strlist__delete(struct strlist *slist); -void strlist__remove(struct strlist *self, struct str_node *sn); -int strlist__load(struct strlist *self, const char *filename); -int strlist__add(struct strlist *self, const char *str); +void strlist__remove(struct strlist *slist, struct str_node *sn); +int strlist__load(struct strlist *slist, const char *filename); +int strlist__add(struct strlist *slist, const char *str); -struct str_node *strlist__entry(const struct strlist *self, unsigned int idx); -struct str_node *strlist__find(struct strlist *self, const char *entry); +struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx); +struct str_node *strlist__find(struct strlist *slist, const char *entry); -static inline bool strlist__has_entry(struct strlist *self, const char *entry) +static inline bool strlist__has_entry(struct strlist *slist, const char *entry) { - return strlist__find(self, entry) != NULL; + return strlist__find(slist, entry) != NULL; } -static inline bool strlist__empty(const struct strlist *self) +static inline bool strlist__empty(const struct strlist *slist) { - return rblist__empty(&self->rblist); + return rblist__empty(&slist->rblist); } -static inline unsigned int strlist__nr_entries(const struct strlist *self) +static inline unsigned int strlist__nr_entries(const struct strlist *slist) { - return rblist__nr_entries(&self->rblist); + return rblist__nr_entries(&slist->rblist); } /* For strlist iteration */ -static inline struct str_node *strlist__first(struct strlist *self) +static inline struct str_node *strlist__first(struct strlist *slist) { - struct rb_node *rn = rb_first(&self->rblist.entries); + struct rb_node *rn = rb_first(&slist->rblist.entries); return rn ? rb_entry(rn, struct str_node, rb_node) : NULL; } static inline struct str_node *strlist__next(struct str_node *sn) @@ -59,21 +59,21 @@ static inline struct str_node *strlist__next(struct str_node *sn) /** * strlist_for_each - iterate over a strlist * @pos: the &struct str_node to use as a loop cursor. - * @self: the &struct strlist for loop. + * @slist: the &struct strlist for loop. */ -#define strlist__for_each(pos, self) \ - for (pos = strlist__first(self); pos; pos = strlist__next(pos)) +#define strlist__for_each(pos, slist) \ + for (pos = strlist__first(slist); pos; pos = strlist__next(pos)) /** * strlist_for_each_safe - iterate over a strlist safe against removal of * str_node * @pos: the &struct str_node to use as a loop cursor. * @n: another &struct str_node to use as temporary storage. - * @self: the &struct strlist for loop. + * @slist: the &struct strlist for loop. */ -#define strlist__for_each_safe(pos, n, self) \ - for (pos = strlist__first(self), n = strlist__next(pos); pos;\ +#define strlist__for_each_safe(pos, n, slist) \ + for (pos = strlist__first(slist), n = strlist__next(pos); pos;\ pos = n, n = strlist__next(n)) -int strlist__parse_list(struct strlist *self, const char *s); +int strlist__parse_list(struct strlist *slist, const char *s); #endif /* __PERF_STRLIST_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index db0cc92cf2e..54efcb5659a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1,6 +1,3 @@ -#include <libelf.h> -#include <gelf.h> -#include <elf.h> #include <fcntl.h> #include <stdio.h> #include <errno.h> @@ -718,6 +715,17 @@ int dso__load_sym(struct dso *dso, struct map *map, sym.st_value); used_opd = true; } + /* + * When loading symbols in a data mapping, ABS symbols (which + * has a value of SHN_ABS in its st_shndx) failed at + * elf_getscn(). And it marks the loading as a failure so + * already loaded symbols cannot be fixed up. + * + * I'm not sure what should be done. Just ignore them for now. + * - Namhyung Kim + */ + if (sym.st_shndx == SHN_ABS) + continue; sec = elf_getscn(runtime_ss->elf, sym.st_shndx); if (!sec) diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 259f8f2ea9c..a7390cde63b 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -1,6 +1,5 @@ #include "symbol.h" -#include <elf.h> #include <stdio.h> #include <fcntl.h> #include <string.h> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e2e8c697cff..e6432d85b43 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -12,6 +12,7 @@ #include "build-id.h" #include "util.h" #include "debug.h" +#include "machine.h" #include "symbol.h" #include "strlist.h" @@ -23,13 +24,12 @@ #define KSYM_NAME_LEN 256 #endif -static void dso_cache__free(struct rb_root *root); static int dso__load_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter); static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter); -static int vmlinux_path__nr_entries; -static char **vmlinux_path; +int vmlinux_path__nr_entries; +char **vmlinux_path; struct symbol_conf symbol_conf = { .exclude_other = true, @@ -56,39 +56,6 @@ static enum dso_binary_type binary_type_symtab[] = { #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab) -static enum dso_binary_type binary_type_data[] = { - DSO_BINARY_TYPE__BUILD_ID_CACHE, - DSO_BINARY_TYPE__SYSTEM_PATH_DSO, - DSO_BINARY_TYPE__NOT_FOUND, -}; - -#define DSO_BINARY_TYPE__DATA_CNT ARRAY_SIZE(binary_type_data) - -int dso__name_len(const struct dso *dso) -{ - if (!dso) - return strlen("[unknown]"); - if (verbose) - return dso->long_name_len; - - return dso->short_name_len; -} - -bool dso__loaded(const struct dso *dso, enum map_type type) -{ - return dso->loaded & (1 << type); -} - -bool dso__sorted_by_name(const struct dso *dso, enum map_type type) -{ - return dso->sorted_by_name & (1 << type); -} - -static void dso__set_sorted_by_name(struct dso *dso, enum map_type type) -{ - dso->sorted_by_name |= (1 << type); -} - bool symbol_type__is_a(char symbol_type, enum map_type map_type) { symbol_type = toupper(symbol_type); @@ -235,13 +202,6 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) curr->end = ~0ULL; } -static void map_groups__fixup_end(struct map_groups *mg) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - __map_groups__fixup_end(mg, i); -} - struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) { size_t namelen = strlen(name) + 1; @@ -270,7 +230,7 @@ void symbol__delete(struct symbol *sym) free(((void *)sym) - symbol_conf.priv_size); } -static size_t symbol__fprintf(struct symbol *sym, FILE *fp) +size_t symbol__fprintf(struct symbol *sym, FILE *fp) { return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n", sym->start, sym->end, @@ -301,53 +261,7 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) return symbol__fprintf_symname_offs(sym, NULL, fp); } -void dso__set_long_name(struct dso *dso, char *name) -{ - if (name == NULL) - return; - dso->long_name = name; - dso->long_name_len = strlen(name); -} - -static void dso__set_short_name(struct dso *dso, const char *name) -{ - if (name == NULL) - return; - dso->short_name = name; - dso->short_name_len = strlen(name); -} - -static void dso__set_basename(struct dso *dso) -{ - dso__set_short_name(dso, basename(dso->long_name)); -} - -struct dso *dso__new(const char *name) -{ - struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1); - - if (dso != NULL) { - int i; - strcpy(dso->name, name); - dso__set_long_name(dso, dso->name); - dso__set_short_name(dso, dso->name); - for (i = 0; i < MAP__NR_TYPES; ++i) - dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; - dso->cache = RB_ROOT; - dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; - dso->data_type = DSO_BINARY_TYPE__NOT_FOUND; - dso->loaded = 0; - dso->sorted_by_name = 0; - dso->has_build_id = 0; - dso->kernel = DSO_TYPE_USER; - dso->needs_swap = DSO_SWAP__UNSET; - INIT_LIST_HEAD(&dso->node); - } - - return dso; -} - -static void symbols__delete(struct rb_root *symbols) +void symbols__delete(struct rb_root *symbols) { struct symbol *pos; struct rb_node *next = rb_first(symbols); @@ -360,25 +274,6 @@ static void symbols__delete(struct rb_root *symbols) } } -void dso__delete(struct dso *dso) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - symbols__delete(&dso->symbols[i]); - if (dso->sname_alloc) - free((char *)dso->short_name); - if (dso->lname_alloc) - free(dso->long_name); - dso_cache__free(&dso->cache); - free(dso); -} - -void dso__set_build_id(struct dso *dso, void *build_id) -{ - memcpy(dso->build_id, build_id, sizeof(dso->build_id)); - dso->has_build_id = 1; -} - void symbols__insert(struct rb_root *symbols, struct symbol *sym) { struct rb_node **p = &symbols->rb_node; @@ -504,29 +399,6 @@ void dso__sort_by_name(struct dso *dso, enum map_type type) &dso->symbols[type]); } -int build_id__sprintf(const u8 *build_id, int len, char *bf) -{ - char *bid = bf; - const u8 *raw = build_id; - int i; - - for (i = 0; i < len; ++i) { - sprintf(bid, "%02x", *raw); - ++raw; - bid += 2; - } - - return raw - build_id; -} - -size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) -{ - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); - return fprintf(fp, "%s", sbuild_id); -} - size_t dso__fprintf_symbols_by_name(struct dso *dso, enum map_type type, FILE *fp) { @@ -542,25 +414,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso, return ret; } -size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) -{ - struct rb_node *nd; - size_t ret = fprintf(fp, "dso: %s (", dso->short_name); - - if (dso->short_name != dso->long_name) - ret += fprintf(fp, "%s, ", dso->long_name); - ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type], - dso->loaded ? "" : "NOT "); - ret += dso__fprintf_buildid(dso, fp); - ret += fprintf(fp, ")\n"); - for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) { - struct symbol *pos = rb_entry(nd, struct symbol, rb_node); - ret += symbol__fprintf(pos, fp); - } - - return ret; -} - int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)) @@ -792,8 +645,8 @@ discard_symbol: rb_erase(&pos->rb_node, root); return count + moved; } -static bool symbol__restricted_filename(const char *filename, - const char *restricted_filename) +bool symbol__restricted_filename(const char *filename, + const char *restricted_filename) { bool restricted = false; @@ -892,136 +745,6 @@ out_failure: return -1; } -bool dso__build_id_equal(const struct dso *dso, u8 *build_id) -{ - return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0; -} - -bool __dsos__read_build_ids(struct list_head *head, bool with_hits) -{ - bool have_build_id = false; - struct dso *pos; - - list_for_each_entry(pos, head, node) { - if (with_hits && !pos->hit) - continue; - if (pos->has_build_id) { - have_build_id = true; - continue; - } - if (filename__read_build_id(pos->long_name, pos->build_id, - sizeof(pos->build_id)) > 0) { - have_build_id = true; - pos->has_build_id = true; - } - } - - return have_build_id; -} - -char dso__symtab_origin(const struct dso *dso) -{ - static const char origin[] = { - [DSO_BINARY_TYPE__KALLSYMS] = 'k', - [DSO_BINARY_TYPE__VMLINUX] = 'v', - [DSO_BINARY_TYPE__JAVA_JIT] = 'j', - [DSO_BINARY_TYPE__DEBUGLINK] = 'l', - [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', - [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', - [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', - [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', - [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', - [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', - [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', - [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', - [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', - }; - - if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND) - return '!'; - return origin[dso->symtab_type]; -} - -int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, - char *root_dir, char *file, size_t size) -{ - char build_id_hex[BUILD_ID_SIZE * 2 + 1]; - int ret = 0; - - switch (type) { - case DSO_BINARY_TYPE__DEBUGLINK: { - char *debuglink; - - strncpy(file, dso->long_name, size); - debuglink = file + dso->long_name_len; - while (debuglink != file && *debuglink != '/') - debuglink--; - if (*debuglink == '/') - debuglink++; - filename__read_debuglink(dso->long_name, debuglink, - size - (debuglink - file)); - } - break; - case DSO_BINARY_TYPE__BUILD_ID_CACHE: - /* skip the locally configured cache if a symfs is given */ - if (symbol_conf.symfs[0] || - (dso__build_id_filename(dso, file, size) == NULL)) - ret = -1; - break; - - case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: - snprintf(file, size, "%s/usr/lib/debug%s.debug", - symbol_conf.symfs, dso->long_name); - break; - - case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: - snprintf(file, size, "%s/usr/lib/debug%s", - symbol_conf.symfs, dso->long_name); - break; - - case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: - if (!dso->has_build_id) { - ret = -1; - break; - } - - build_id__sprintf(dso->build_id, - sizeof(dso->build_id), - build_id_hex); - snprintf(file, size, - "%s/usr/lib/debug/.build-id/%.2s/%s.debug", - symbol_conf.symfs, build_id_hex, build_id_hex + 2); - break; - - case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: - snprintf(file, size, "%s%s", - symbol_conf.symfs, dso->long_name); - break; - - case DSO_BINARY_TYPE__GUEST_KMODULE: - snprintf(file, size, "%s%s%s", symbol_conf.symfs, - root_dir, dso->long_name); - break; - - case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: - snprintf(file, size, "%s%s", symbol_conf.symfs, - dso->long_name); - break; - - default: - case DSO_BINARY_TYPE__KALLSYMS: - case DSO_BINARY_TYPE__VMLINUX: - case DSO_BINARY_TYPE__GUEST_KALLSYMS: - case DSO_BINARY_TYPE__GUEST_VMLINUX: - case DSO_BINARY_TYPE__JAVA_JIT: - case DSO_BINARY_TYPE__NOT_FOUND: - ret = -1; - break; - } - - return ret; -} - int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) { char *name; @@ -1045,10 +768,6 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) else machine = NULL; - name = malloc(PATH_MAX); - if (!name) - return -1; - dso->adjust_symbols = 0; if (strncmp(dso->name, "/tmp/perf-", 10) == 0) { @@ -1072,6 +791,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (machine) root_dir = machine->root_dir; + name = malloc(PATH_MAX); + if (!name) + return -1; + /* Iterate over candidate debug images. * Keep track of "interesting" ones (those which have a symtab, dynsym, * and/or opd section) for processing. @@ -1157,221 +880,6 @@ struct map *map_groups__find_by_name(struct map_groups *mg, return NULL; } -static int dso__kernel_module_get_build_id(struct dso *dso, - const char *root_dir) -{ - char filename[PATH_MAX]; - /* - * kernel module short names are of the form "[module]" and - * we need just "module" here. - */ - const char *name = dso->short_name + 1; - - snprintf(filename, sizeof(filename), - "%s/sys/module/%.*s/notes/.note.gnu.build-id", - root_dir, (int)strlen(name) - 1, name); - - if (sysfs__read_build_id(filename, dso->build_id, - sizeof(dso->build_id)) == 0) - dso->has_build_id = true; - - return 0; -} - -static int map_groups__set_modules_path_dir(struct map_groups *mg, - const char *dir_name) -{ - struct dirent *dent; - DIR *dir = opendir(dir_name); - int ret = 0; - - if (!dir) { - pr_debug("%s: cannot open %s dir\n", __func__, dir_name); - return -1; - } - - while ((dent = readdir(dir)) != NULL) { - char path[PATH_MAX]; - struct stat st; - - /*sshfs might return bad dent->d_type, so we have to stat*/ - snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name); - if (stat(path, &st)) - continue; - - if (S_ISDIR(st.st_mode)) { - if (!strcmp(dent->d_name, ".") || - !strcmp(dent->d_name, "..")) - continue; - - ret = map_groups__set_modules_path_dir(mg, path); - if (ret < 0) - goto out; - } else { - char *dot = strrchr(dent->d_name, '.'), - dso_name[PATH_MAX]; - struct map *map; - char *long_name; - - if (dot == NULL || strcmp(dot, ".ko")) - continue; - snprintf(dso_name, sizeof(dso_name), "[%.*s]", - (int)(dot - dent->d_name), dent->d_name); - - strxfrchar(dso_name, '-', '_'); - map = map_groups__find_by_name(mg, MAP__FUNCTION, - dso_name); - if (map == NULL) - continue; - - long_name = strdup(path); - if (long_name == NULL) { - ret = -1; - goto out; - } - dso__set_long_name(map->dso, long_name); - map->dso->lname_alloc = 1; - dso__kernel_module_get_build_id(map->dso, ""); - } - } - -out: - closedir(dir); - return ret; -} - -static char *get_kernel_version(const char *root_dir) -{ - char version[PATH_MAX]; - FILE *file; - char *name, *tmp; - const char *prefix = "Linux version "; - - sprintf(version, "%s/proc/version", root_dir); - file = fopen(version, "r"); - if (!file) - return NULL; - - version[0] = '\0'; - tmp = fgets(version, sizeof(version), file); - fclose(file); - - name = strstr(version, prefix); - if (!name) - return NULL; - name += strlen(prefix); - tmp = strchr(name, ' '); - if (tmp) - *tmp = '\0'; - - return strdup(name); -} - -static int machine__set_modules_path(struct machine *machine) -{ - char *version; - char modules_path[PATH_MAX]; - - version = get_kernel_version(machine->root_dir); - if (!version) - return -1; - - snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", - machine->root_dir, version); - free(version); - - return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); -} - -struct map *machine__new_module(struct machine *machine, u64 start, - const char *filename) -{ - struct map *map; - struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); - - if (dso == NULL) - return NULL; - - map = map__new2(start, dso, MAP__FUNCTION); - if (map == NULL) - return NULL; - - if (machine__is_host(machine)) - dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; - else - dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; - map_groups__insert(&machine->kmaps, map); - return map; -} - -static int machine__create_modules(struct machine *machine) -{ - char *line = NULL; - size_t n; - FILE *file; - struct map *map; - const char *modules; - char path[PATH_MAX]; - - if (machine__is_default_guest(machine)) - modules = symbol_conf.default_guest_modules; - else { - sprintf(path, "%s/proc/modules", machine->root_dir); - modules = path; - } - - if (symbol__restricted_filename(path, "/proc/modules")) - return -1; - - file = fopen(modules, "r"); - if (file == NULL) - return -1; - - while (!feof(file)) { - char name[PATH_MAX]; - u64 start; - char *sep; - int line_len; - - line_len = getline(&line, &n, file); - if (line_len < 0) - break; - - if (!line) - goto out_failure; - - line[--line_len] = '\0'; /* \n */ - - sep = strrchr(line, 'x'); - if (sep == NULL) - continue; - - hex2u64(sep + 1, &start); - - sep = strchr(line, ' '); - if (sep == NULL) - continue; - - *sep = '\0'; - - snprintf(name, sizeof(name), "[%s]", line); - map = machine__new_module(machine, start, name); - if (map == NULL) - goto out_delete_line; - dso__kernel_module_get_build_id(map->dso, machine->root_dir); - } - - free(line); - fclose(file); - - return machine__set_modules_path(machine); - -out_delete_line: - free(line); -out_failure: - return -1; -} - int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, symbol_filter_t filter) { @@ -1415,8 +923,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, filename = dso__build_id_filename(dso, NULL, 0); if (filename != NULL) { err = dso__load_vmlinux(dso, map, filename, filter); - if (err > 0) + if (err > 0) { + dso->lname_alloc = 1; goto out; + } free(filename); } @@ -1424,6 +934,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter); if (err > 0) { dso__set_long_name(dso, strdup(vmlinux_path[i])); + dso->lname_alloc = 1; break; } } @@ -1463,6 +974,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map, if (err > 0) { dso__set_long_name(dso, strdup(symbol_conf.vmlinux_name)); + dso->lname_alloc = 1; goto out_fixup; } return err; @@ -1591,287 +1103,6 @@ out_try_fixup: return err; } -void dsos__add(struct list_head *head, struct dso *dso) -{ - list_add_tail(&dso->node, head); -} - -struct dso *dsos__find(struct list_head *head, const char *name) -{ - struct dso *pos; - - list_for_each_entry(pos, head, node) - if (strcmp(pos->long_name, name) == 0) - return pos; - return NULL; -} - -struct dso *__dsos__findnew(struct list_head *head, const char *name) -{ - struct dso *dso = dsos__find(head, name); - - if (!dso) { - dso = dso__new(name); - if (dso != NULL) { - dsos__add(head, dso); - dso__set_basename(dso); - } - } - - return dso; -} - -size_t __dsos__fprintf(struct list_head *head, FILE *fp) -{ - struct dso *pos; - size_t ret = 0; - - list_for_each_entry(pos, head, node) { - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - ret += dso__fprintf(pos, i, fp); - } - - return ret; -} - -size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp) -{ - struct rb_node *nd; - size_t ret = 0; - - for (nd = rb_first(machines); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += __dsos__fprintf(&pos->kernel_dsos, fp); - ret += __dsos__fprintf(&pos->user_dsos, fp); - } - - return ret; -} - -static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, - bool with_hits) -{ - struct dso *pos; - size_t ret = 0; - - list_for_each_entry(pos, head, node) { - if (with_hits && !pos->hit) - continue; - ret += dso__fprintf_buildid(pos, fp); - ret += fprintf(fp, " %s\n", pos->long_name); - } - return ret; -} - -size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, - bool with_hits) -{ - return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) + - __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits); -} - -size_t machines__fprintf_dsos_buildid(struct rb_root *machines, - FILE *fp, bool with_hits) -{ - struct rb_node *nd; - size_t ret = 0; - - for (nd = rb_first(machines); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += machine__fprintf_dsos_buildid(pos, fp, with_hits); - } - return ret; -} - -static struct dso* -dso__kernel_findnew(struct machine *machine, const char *name, - const char *short_name, int dso_type) -{ - /* - * The kernel dso could be created by build_id processing. - */ - struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name); - - /* - * We need to run this in all cases, since during the build_id - * processing we had no idea this was the kernel dso. - */ - if (dso != NULL) { - dso__set_short_name(dso, short_name); - dso->kernel = dso_type; - } - - return dso; -} - -void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine) -{ - char path[PATH_MAX]; - - if (machine__is_default_guest(machine)) - return; - sprintf(path, "%s/sys/kernel/notes", machine->root_dir); - if (sysfs__read_build_id(path, dso->build_id, - sizeof(dso->build_id)) == 0) - dso->has_build_id = true; -} - -static struct dso *machine__get_kernel(struct machine *machine) -{ - const char *vmlinux_name = NULL; - struct dso *kernel; - - if (machine__is_host(machine)) { - vmlinux_name = symbol_conf.vmlinux_name; - if (!vmlinux_name) - vmlinux_name = "[kernel.kallsyms]"; - - kernel = dso__kernel_findnew(machine, vmlinux_name, - "[kernel]", - DSO_TYPE_KERNEL); - } else { - char bf[PATH_MAX]; - - if (machine__is_default_guest(machine)) - vmlinux_name = symbol_conf.default_guest_vmlinux_name; - if (!vmlinux_name) - vmlinux_name = machine__mmap_name(machine, bf, - sizeof(bf)); - - kernel = dso__kernel_findnew(machine, vmlinux_name, - "[guest.kernel]", - DSO_TYPE_GUEST_KERNEL); - } - - if (kernel != NULL && (!kernel->has_build_id)) - dso__read_running_kernel_build_id(kernel, machine); - - return kernel; -} - -struct process_args { - u64 start; -}; - -static int symbol__in_kernel(void *arg, const char *name, - char type __maybe_unused, u64 start) -{ - struct process_args *args = arg; - - if (strchr(name, '[')) - return 0; - - args->start = start; - return 1; -} - -/* Figure out the start address of kernel map from /proc/kallsyms */ -static u64 machine__get_kernel_start_addr(struct machine *machine) -{ - const char *filename; - char path[PATH_MAX]; - struct process_args args; - - if (machine__is_host(machine)) { - filename = "/proc/kallsyms"; - } else { - if (machine__is_default_guest(machine)) - filename = (char *)symbol_conf.default_guest_kallsyms; - else { - sprintf(path, "%s/proc/kallsyms", machine->root_dir); - filename = path; - } - } - - if (symbol__restricted_filename(filename, "/proc/kallsyms")) - return 0; - - if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0) - return 0; - - return args.start; -} - -int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) -{ - enum map_type type; - u64 start = machine__get_kernel_start_addr(machine); - - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - - machine->vmlinux_maps[type] = map__new2(start, kernel, type); - if (machine->vmlinux_maps[type] == NULL) - return -1; - - machine->vmlinux_maps[type]->map_ip = - machine->vmlinux_maps[type]->unmap_ip = - identity__map_ip; - kmap = map__kmap(machine->vmlinux_maps[type]); - kmap->kmaps = &machine->kmaps; - map_groups__insert(&machine->kmaps, - machine->vmlinux_maps[type]); - } - - return 0; -} - -void machine__destroy_kernel_maps(struct machine *machine) -{ - enum map_type type; - - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - - if (machine->vmlinux_maps[type] == NULL) - continue; - - kmap = map__kmap(machine->vmlinux_maps[type]); - map_groups__remove(&machine->kmaps, - machine->vmlinux_maps[type]); - if (kmap->ref_reloc_sym) { - /* - * ref_reloc_sym is shared among all maps, so free just - * on one of them. - */ - if (type == MAP__FUNCTION) { - free((char *)kmap->ref_reloc_sym->name); - kmap->ref_reloc_sym->name = NULL; - free(kmap->ref_reloc_sym); - } - kmap->ref_reloc_sym = NULL; - } - - map__delete(machine->vmlinux_maps[type]); - machine->vmlinux_maps[type] = NULL; - } -} - -int machine__create_kernel_maps(struct machine *machine) -{ - struct dso *kernel = machine__get_kernel(machine); - - if (kernel == NULL || - __machine__create_kernel_maps(machine, kernel) < 0) - return -1; - - if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { - if (machine__is_host(machine)) - pr_debug("Problems creating module maps, " - "continuing anyway...\n"); - else - pr_debug("Problems creating module maps for guest %d, " - "continuing anyway...\n", machine->pid); - } - - /* - * Now that we have all the maps created, just set the ->end of them: - */ - map_groups__fixup_end(&machine->kmaps); - return 0; -} - static void vmlinux_path__exit(void) { while (--vmlinux_path__nr_entries >= 0) { @@ -1932,25 +1163,6 @@ out_fail: return -1; } -size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) -{ - int i; - size_t printed = 0; - struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso; - - if (kdso->has_build_id) { - char filename[PATH_MAX]; - if (dso__build_id_filename(kdso, filename, sizeof(filename))) - printed += fprintf(fp, "[0] %s\n", filename); - } - - for (i = 0; i < vmlinux_path__nr_entries; ++i) - printed += fprintf(fp, "[%d] %s\n", - i + kdso->has_build_id, vmlinux_path[i]); - - return printed; -} - static int setup_list(struct strlist **list, const char *list_str, const char *list_name) { @@ -2054,377 +1266,3 @@ void symbol__exit(void) symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; symbol_conf.initialized = false; } - -int machines__create_kernel_maps(struct rb_root *machines, pid_t pid) -{ - struct machine *machine = machines__findnew(machines, pid); - - if (machine == NULL) - return -1; - - return machine__create_kernel_maps(machine); -} - -static int hex(char ch) -{ - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - -/* - * While we find nice hex chars, build a long_val. - * Return number of chars processed. - */ -int hex2u64(const char *ptr, u64 *long_val) -{ - const char *p = ptr; - *long_val = 0; - - while (*p) { - const int hex_val = hex(*p); - - if (hex_val < 0) - break; - - *long_val = (*long_val << 4) | hex_val; - p++; - } - - return p - ptr; -} - -char *strxfrchar(char *s, char from, char to) -{ - char *p = s; - - while ((p = strchr(p, from)) != NULL) - *p++ = to; - - return s; -} - -int machines__create_guest_kernel_maps(struct rb_root *machines) -{ - int ret = 0; - struct dirent **namelist = NULL; - int i, items = 0; - char path[PATH_MAX]; - pid_t pid; - char *endp; - - if (symbol_conf.default_guest_vmlinux_name || - symbol_conf.default_guest_modules || - symbol_conf.default_guest_kallsyms) { - machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID); - } - - if (symbol_conf.guestmount) { - items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); - if (items <= 0) - return -ENOENT; - for (i = 0; i < items; i++) { - if (!isdigit(namelist[i]->d_name[0])) { - /* Filter out . and .. */ - continue; - } - pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10); - if ((*endp != '\0') || - (endp == namelist[i]->d_name) || - (errno == ERANGE)) { - pr_debug("invalid directory (%s). Skipping.\n", - namelist[i]->d_name); - continue; - } - sprintf(path, "%s/%s/proc/kallsyms", - symbol_conf.guestmount, - namelist[i]->d_name); - ret = access(path, R_OK); - if (ret) { - pr_debug("Can't access file %s\n", path); - goto failure; - } - machines__create_kernel_maps(machines, pid); - } -failure: - free(namelist); - } - - return ret; -} - -void machines__destroy_guest_kernel_maps(struct rb_root *machines) -{ - struct rb_node *next = rb_first(machines); - - while (next) { - struct machine *pos = rb_entry(next, struct machine, rb_node); - - next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, machines); - machine__delete(pos); - } -} - -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, symbol_filter_t filter) -{ - struct map *map = machine->vmlinux_maps[type]; - int ret = dso__load_kallsyms(map->dso, filename, map, filter); - - if (ret > 0) { - dso__set_loaded(map->dso, type); - /* - * Since /proc/kallsyms will have multiple sessions for the - * kernel, with modules between them, fixup the end of all - * sections. - */ - __map_groups__fixup_end(&machine->kmaps, type); - } - - return ret; -} - -int machine__load_vmlinux_path(struct machine *machine, enum map_type type, - symbol_filter_t filter) -{ - struct map *map = machine->vmlinux_maps[type]; - int ret = dso__load_vmlinux_path(map->dso, map, filter); - - if (ret > 0) { - dso__set_loaded(map->dso, type); - map__reloc_vmlinux(map); - } - - return ret; -} - -struct map *dso__new_map(const char *name) -{ - struct map *map = NULL; - struct dso *dso = dso__new(name); - - if (dso) - map = map__new2(0, dso, MAP__FUNCTION); - - return map; -} - -static int open_dso(struct dso *dso, struct machine *machine) -{ - char *root_dir = (char *) ""; - char *name; - int fd; - - name = malloc(PATH_MAX); - if (!name) - return -ENOMEM; - - if (machine) - root_dir = machine->root_dir; - - if (dso__binary_type_file(dso, dso->data_type, - root_dir, name, PATH_MAX)) { - free(name); - return -EINVAL; - } - - fd = open(name, O_RDONLY); - free(name); - return fd; -} - -int dso__data_fd(struct dso *dso, struct machine *machine) -{ - int i = 0; - - if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND) - return open_dso(dso, machine); - - do { - int fd; - - dso->data_type = binary_type_data[i++]; - - fd = open_dso(dso, machine); - if (fd >= 0) - return fd; - - } while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND); - - return -EINVAL; -} - -static void -dso_cache__free(struct rb_root *root) -{ - struct rb_node *next = rb_first(root); - - while (next) { - struct dso_cache *cache; - - cache = rb_entry(next, struct dso_cache, rb_node); - next = rb_next(&cache->rb_node); - rb_erase(&cache->rb_node, root); - free(cache); - } -} - -static struct dso_cache* -dso_cache__find(struct rb_root *root, u64 offset) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct dso_cache *cache; - - while (*p != NULL) { - u64 end; - - parent = *p; - cache = rb_entry(parent, struct dso_cache, rb_node); - end = cache->offset + DSO__DATA_CACHE_SIZE; - - if (offset < cache->offset) - p = &(*p)->rb_left; - else if (offset >= end) - p = &(*p)->rb_right; - else - return cache; - } - return NULL; -} - -static void -dso_cache__insert(struct rb_root *root, struct dso_cache *new) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct dso_cache *cache; - u64 offset = new->offset; - - while (*p != NULL) { - u64 end; - - parent = *p; - cache = rb_entry(parent, struct dso_cache, rb_node); - end = cache->offset + DSO__DATA_CACHE_SIZE; - - if (offset < cache->offset) - p = &(*p)->rb_left; - else if (offset >= end) - p = &(*p)->rb_right; - } - - rb_link_node(&new->rb_node, parent, p); - rb_insert_color(&new->rb_node, root); -} - -static ssize_t -dso_cache__memcpy(struct dso_cache *cache, u64 offset, - u8 *data, u64 size) -{ - u64 cache_offset = offset - cache->offset; - u64 cache_size = min(cache->size - cache_offset, size); - - memcpy(data, cache->data + cache_offset, cache_size); - return cache_size; -} - -static ssize_t -dso_cache__read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) -{ - struct dso_cache *cache; - ssize_t ret; - int fd; - - fd = dso__data_fd(dso, machine); - if (fd < 0) - return -1; - - do { - u64 cache_offset; - - ret = -ENOMEM; - - cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE); - if (!cache) - break; - - cache_offset = offset & DSO__DATA_CACHE_MASK; - ret = -EINVAL; - - if (-1 == lseek(fd, cache_offset, SEEK_SET)) - break; - - ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE); - if (ret <= 0) - break; - - cache->offset = cache_offset; - cache->size = ret; - dso_cache__insert(&dso->cache, cache); - - ret = dso_cache__memcpy(cache, offset, data, size); - - } while (0); - - if (ret <= 0) - free(cache); - - close(fd); - return ret; -} - -static ssize_t dso_cache_read(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) -{ - struct dso_cache *cache; - - cache = dso_cache__find(&dso->cache, offset); - if (cache) - return dso_cache__memcpy(cache, offset, data, size); - else - return dso_cache__read(dso, machine, offset, data, size); -} - -ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size) -{ - ssize_t r = 0; - u8 *p = data; - - do { - ssize_t ret; - - ret = dso_cache_read(dso, machine, offset, p, size); - if (ret < 0) - return ret; - - /* Reached EOF, return what we have. */ - if (!ret) - break; - - BUG_ON(ret > size); - - r += ret; - p += ret; - offset += ret; - size -= ret; - - } while (size); - - return r; -} - -ssize_t dso__data_read_addr(struct dso *dso, struct map *map, - struct machine *machine, u64 addr, - u8 *data, ssize_t size) -{ - u64 offset = map->map_ip(map, addr); - return dso__data_read_offset(dso, machine, offset, data, size); -} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 8b6ef7fac74..b62ca37c4b7 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -11,12 +11,15 @@ #include <stdio.h> #include <byteswap.h> #include <libgen.h> +#include "build-id.h" #ifdef LIBELF_SUPPORT #include <libelf.h> #include <gelf.h> -#include <elf.h> #endif +#include <elf.h> + +#include "dso.h" #ifdef HAVE_CPLUS_DEMANGLE extern char *cplus_demangle(const char *, int); @@ -39,9 +42,6 @@ static inline char *bfd_demangle(void __maybe_unused *v, #endif #endif -int hex2u64(const char *ptr, u64 *val); -char *strxfrchar(char *s, char from, char to); - /* * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: @@ -57,8 +57,6 @@ char *strxfrchar(char *s, char from, char to); #define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ #endif -#define BUILD_ID_SIZE 20 - /** struct symbol - symtab entry * * @ignore - resolvable but tools ignore it (e.g. idle routines) @@ -74,6 +72,7 @@ struct symbol { }; void symbol__delete(struct symbol *sym); +void symbols__delete(struct rb_root *symbols); static inline size_t symbol__size(const struct symbol *sym) { @@ -97,7 +96,8 @@ struct symbol_conf { initialized, kptr_restrict, annotate_asm_raw, - annotate_src; + annotate_src, + event_group; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -121,6 +121,8 @@ struct symbol_conf { }; extern struct symbol_conf symbol_conf; +extern int vmlinux_path__nr_entries; +extern char **vmlinux_path; static inline void *symbol__priv(struct symbol *sym) { @@ -164,70 +166,6 @@ struct addr_location { s32 cpu; }; -enum dso_binary_type { - DSO_BINARY_TYPE__KALLSYMS = 0, - DSO_BINARY_TYPE__GUEST_KALLSYMS, - DSO_BINARY_TYPE__VMLINUX, - DSO_BINARY_TYPE__GUEST_VMLINUX, - DSO_BINARY_TYPE__JAVA_JIT, - DSO_BINARY_TYPE__DEBUGLINK, - DSO_BINARY_TYPE__BUILD_ID_CACHE, - DSO_BINARY_TYPE__FEDORA_DEBUGINFO, - DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, - DSO_BINARY_TYPE__BUILDID_DEBUGINFO, - DSO_BINARY_TYPE__SYSTEM_PATH_DSO, - DSO_BINARY_TYPE__GUEST_KMODULE, - DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, - DSO_BINARY_TYPE__NOT_FOUND, -}; - -enum dso_kernel_type { - DSO_TYPE_USER = 0, - DSO_TYPE_KERNEL, - DSO_TYPE_GUEST_KERNEL -}; - -enum dso_swap_type { - DSO_SWAP__UNSET, - DSO_SWAP__NO, - DSO_SWAP__YES, -}; - -#define DSO__DATA_CACHE_SIZE 4096 -#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1) - -struct dso_cache { - struct rb_node rb_node; - u64 offset; - u64 size; - char data[0]; -}; - -struct dso { - struct list_head node; - struct rb_root symbols[MAP__NR_TYPES]; - struct rb_root symbol_names[MAP__NR_TYPES]; - struct rb_root cache; - enum dso_kernel_type kernel; - enum dso_swap_type needs_swap; - enum dso_binary_type symtab_type; - enum dso_binary_type data_type; - u8 adjust_symbols:1; - u8 has_build_id:1; - u8 hit:1; - u8 annotate_warned:1; - u8 sname_alloc:1; - u8 lname_alloc:1; - u8 sorted_by_name; - u8 loaded; - u8 build_id[BUILD_ID_SIZE]; - const char *short_name; - char *long_name; - u16 long_name_len; - u16 short_name_len; - char name[0]; -}; - struct symsrc { char *name; int fd; @@ -258,47 +196,6 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, bool symsrc__has_symtab(struct symsrc *ss); bool symsrc__possibly_runtime(struct symsrc *ss); -#define DSO__SWAP(dso, type, val) \ -({ \ - type ____r = val; \ - BUG_ON(dso->needs_swap == DSO_SWAP__UNSET); \ - if (dso->needs_swap == DSO_SWAP__YES) { \ - switch (sizeof(____r)) { \ - case 2: \ - ____r = bswap_16(val); \ - break; \ - case 4: \ - ____r = bswap_32(val); \ - break; \ - case 8: \ - ____r = bswap_64(val); \ - break; \ - default: \ - BUG_ON(1); \ - } \ - } \ - ____r; \ -}) - -struct dso *dso__new(const char *name); -void dso__delete(struct dso *dso); - -int dso__name_len(const struct dso *dso); - -bool dso__loaded(const struct dso *dso, enum map_type type); -bool dso__sorted_by_name(const struct dso *dso, enum map_type type); - -static inline void dso__set_loaded(struct dso *dso, enum map_type type) -{ - dso->loaded |= (1 << type); -} - -void dso__sort_by_name(struct dso *dso, enum map_type type); - -void dsos__add(struct list_head *head, struct dso *dso); -struct dso *dsos__find(struct list_head *head, const char *name); -struct dso *__dsos__findnew(struct list_head *head, const char *name); - int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter); int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, symbol_filter_t filter); @@ -306,30 +203,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, symbol_filter_t filter); int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, symbol_filter_t filter); -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, symbol_filter_t filter); -int machine__load_vmlinux_path(struct machine *machine, enum map_type type, - symbol_filter_t filter); - -size_t __dsos__fprintf(struct list_head *head, FILE *fp); - -size_t machine__fprintf_dsos_buildid(struct machine *machine, - FILE *fp, bool with_hits); -size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp); -size_t machines__fprintf_dsos_buildid(struct rb_root *machines, - FILE *fp, bool with_hits); -size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); -size_t dso__fprintf_symbols_by_name(struct dso *dso, - enum map_type type, FILE *fp); -size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp); - -char dso__symtab_origin(const struct dso *dso); -void dso__set_long_name(struct dso *dso, char *name); -void dso__set_build_id(struct dso *dso, void *build_id); -bool dso__build_id_equal(const struct dso *dso, u8 *build_id); -void dso__read_running_kernel_build_id(struct dso *dso, - struct machine *machine); -struct map *dso__new_map(const char *name); + struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, @@ -337,22 +211,12 @@ struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); -bool __dsos__read_build_ids(struct list_head *head, bool with_hits); -int build_id__sprintf(const u8 *build_id, int len, char *bf); int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); int filename__read_debuglink(const char *filename, char *debuglink, size_t size); -void machine__destroy_kernel_maps(struct machine *machine); -int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel); -int machine__create_kernel_maps(struct machine *machine); - -int machines__create_kernel_maps(struct rb_root *machines, pid_t pid); -int machines__create_guest_kernel_maps(struct rb_root *machines); -void machines__destroy_guest_kernel_maps(struct rb_root *machines); - int symbol__init(void); void symbol__exit(void); void symbol__elf_init(void); @@ -360,20 +224,11 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); size_t symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, FILE *fp); size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); +size_t symbol__fprintf(struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); +bool symbol__restricted_filename(const char *filename, + const char *restricted_filename); -size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); - -int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, - char *root_dir, char *file, size_t size); - -int dso__data_fd(struct dso *dso, struct machine *machine); -ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, - u64 offset, u8 *data, ssize_t size); -ssize_t dso__data_read_addr(struct dso *dso, struct map *map, - struct machine *machine, u64 addr, - u8 *data, ssize_t size); -int dso__test_data(void); int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, symbol_filter_t filter, int kmodule); diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c index 48c6902e749..f71e9eafe15 100644 --- a/tools/perf/util/sysfs.c +++ b/tools/perf/util/sysfs.c @@ -8,7 +8,7 @@ static const char * const sysfs_known_mountpoints[] = { }; static int sysfs_found; -char sysfs_mountpoint[PATH_MAX]; +char sysfs_mountpoint[PATH_MAX + 1]; static int sysfs_valid_mountpoint(const char *sysfs) { diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 8b3e5939afb..632e40e5cec 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -7,7 +7,7 @@ #include "util.h" #include "debug.h" -static struct thread *thread__new(pid_t pid) +struct thread *thread__new(pid_t pid) { struct thread *self = zalloc(sizeof(*self)); @@ -54,49 +54,10 @@ int thread__comm_len(struct thread *self) return self->comm_len; } -static size_t thread__fprintf(struct thread *self, FILE *fp) +size_t thread__fprintf(struct thread *thread, FILE *fp) { - return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) + - map_groups__fprintf(&self->mg, verbose, fp); -} - -struct thread *machine__findnew_thread(struct machine *self, pid_t pid) -{ - struct rb_node **p = &self->threads.rb_node; - struct rb_node *parent = NULL; - struct thread *th; - - /* - * Font-end cache - PID lookups come in blocks, - * so most of the time we dont have to look up - * the full rbtree: - */ - if (self->last_match && self->last_match->pid == pid) - return self->last_match; - - while (*p != NULL) { - parent = *p; - th = rb_entry(parent, struct thread, rb_node); - - if (th->pid == pid) { - self->last_match = th; - return th; - } - - if (pid < th->pid) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - th = thread__new(pid); - if (th != NULL) { - rb_link_node(&th->rb_node, parent, p); - rb_insert_color(&th->rb_node, &self->threads); - self->last_match = th; - } - - return th; + return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) + + map_groups__fprintf(&thread->mg, verbose, fp); } void thread__insert_map(struct thread *self, struct map *map) @@ -123,17 +84,3 @@ int thread__fork(struct thread *self, struct thread *parent) return -ENOMEM; return 0; } - -size_t machine__fprintf(struct machine *machine, FILE *fp) -{ - size_t ret = 0; - struct rb_node *nd; - - for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { - struct thread *pos = rb_entry(nd, struct thread, rb_node); - - ret += thread__fprintf(pos, fp); - } - - return ret; -} diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index f66610b7bac..5ad26640309 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -3,6 +3,7 @@ #include <linux/rbtree.h> #include <unistd.h> +#include <sys/types.h> #include "symbol.h" struct thread { @@ -22,12 +23,14 @@ struct thread { struct machine; +struct thread *thread__new(pid_t pid); void thread__delete(struct thread *self); int thread__set_comm(struct thread *self, const char *comm); int thread__comm_len(struct thread *self); void thread__insert_map(struct thread *self, struct map *map); int thread__fork(struct thread *self, struct thread *parent); +size_t thread__fprintf(struct thread *thread, FILE *fp); static inline struct map *thread__find_map(struct thread *self, enum map_type type, u64 addr) diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 884dde9b9bc..54d37a4753c 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -26,6 +26,8 @@ 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; + struct perf_record_opts *opts = &top->record_opts; + struct perf_target *target = &opts->target; size_t ret = 0; if (!perf_guest) { @@ -61,31 +63,31 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) struct perf_evsel *first = perf_evlist__first(top->evlist); ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", (uint64_t)first->attr.sample_period, - top->freq ? "Hz" : ""); + opts->freq ? "Hz" : ""); } ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel)); ret += SNPRINTF(bf + ret, size - ret, "], "); - if (top->target.pid) + if (target->pid) ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s", - top->target.pid); - else if (top->target.tid) + target->pid); + else if (target->tid) ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s", - top->target.tid); - else if (top->target.uid_str != NULL) + target->tid); + else if (target->uid_str != NULL) ret += SNPRINTF(bf + ret, size - ret, " (uid: %s", - top->target.uid_str); + target->uid_str); else ret += SNPRINTF(bf + ret, size - ret, " (all"); - if (top->target.cpu_list) + if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", top->evlist->cpus->nr > 1 ? "s" : "", - top->target.cpu_list); + target->cpu_list); else { - if (top->target.tid) + if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 86ff1b15059..7ebf357dc9e 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -14,7 +14,7 @@ struct perf_session; struct perf_top { struct perf_tool tool; struct perf_evlist *evlist; - struct perf_target target; + struct perf_record_opts record_opts; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. @@ -24,24 +24,16 @@ struct perf_top { u64 exact_samples; u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; - int freq; bool hide_kernel_symbols, hide_user_symbols, zero; bool use_tui, use_stdio; bool sort_has_symbols; - bool dont_use_callchains; bool kptr_restrict_warned; bool vmlinux_warned; - bool inherit; - bool group; - bool sample_id_all_missing; - bool exclude_guest_missing; bool dump_symtab; struct hist_entry *sym_filter_entry; struct perf_evsel *sym_evsel; struct perf_session *session; struct winsize winsize; - unsigned int mmap_pages; - int default_interval; int realtime_prio; int sym_pcnt_filter; const char *sym_filter; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 719ed74a856..3741572696a 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -47,8 +47,6 @@ int file_bigendian; int host_bigendian; static int long_size; -static unsigned long page_size; - static ssize_t calc_data_size; static bool repipe; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 99664598bc1..805d1f52c5b 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -10,6 +10,10 @@ /* * XXX We need to find a better place for these things... */ +unsigned int page_size; + +bool test_attr__enabled; + bool perf_host = true; bool perf_guest = false; @@ -164,6 +168,39 @@ size_t hex_width(u64 v) return n; } +static int hex(char ch) +{ + if ((ch >= '0') && (ch <= '9')) + return ch - '0'; + if ((ch >= 'a') && (ch <= 'f')) + return ch - 'a' + 10; + if ((ch >= 'A') && (ch <= 'F')) + return ch - 'A' + 10; + return -1; +} + +/* + * While we find nice hex chars, build a long_val. + * Return number of chars processed. + */ +int hex2u64(const char *ptr, u64 *long_val) +{ + const char *p = ptr; + *long_val = 0; + + while (*p) { + const int hex_val = hex(*p); + + if (hex_val < 0) + break; + + *long_val = (*long_val << 4) | hex_val; + p++; + } + + return p - ptr; +} + /* Obtain a backtrace and print it to stdout. */ #ifdef BACKTRACE_SUPPORT void dump_stack(void) @@ -183,3 +220,25 @@ void dump_stack(void) #else void dump_stack(void) {} #endif + +void get_term_dimensions(struct winsize *ws) +{ + char *s = getenv("LINES"); + + if (s != NULL) { + ws->ws_row = atoi(s); + s = getenv("COLUMNS"); + if (s != NULL) { + ws->ws_col = atoi(s); + if (ws->ws_row && ws->ws_col) + return; + } + } +#ifdef TIOCGWINSZ + if (ioctl(1, TIOCGWINSZ, ws) == 0 && + ws->ws_row && ws->ws_col) + return; +#endif + ws->ws_row = 25; + ws->ws_col = 80; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 70fa70b535b..09b4c26b71a 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -198,6 +198,10 @@ static inline int has_extension(const char *filename, const char *ext) #undef tolower #undef toupper +#ifndef NSEC_PER_MSEC +#define NSEC_PER_MSEC 1000000L +#endif + extern unsigned char sane_ctype[256]; #define GIT_SPACE 0x01 #define GIT_DIGIT 0x02 @@ -236,6 +240,7 @@ void argv_free(char **argv); bool strglobmatch(const char *str, const char *pat); bool strlazymatch(const char *str, const char *pat); int strtailcmp(const char *s1, const char *s2); +char *strxfrchar(char *s, char from, char to); unsigned long convert_unit(unsigned long value, char *unit); int readn(int fd, void *buf, size_t size); @@ -258,9 +263,16 @@ bool is_power_of_2(unsigned long n) } size_t hex_width(u64 v); +int hex2u64(const char *ptr, u64 *val); +char *ltrim(char *s); char *rtrim(char *s); void dump_stack(void); +extern unsigned int page_size; + +struct winsize; +void get_term_dimensions(struct winsize *ws); + #endif |