diff options
Diffstat (limited to 'tools/perf')
102 files changed, 2619 insertions, 974 deletions
diff --git a/tools/perf/Build b/tools/perf/Build new file mode 100644 index 000000000000..b77370ef7005 --- /dev/null +++ b/tools/perf/Build @@ -0,0 +1,44 @@ +perf-y += builtin-bench.o +perf-y += builtin-annotate.o +perf-y += builtin-diff.o +perf-y += builtin-evlist.o +perf-y += builtin-help.o +perf-y += builtin-sched.o +perf-y += builtin-buildid-list.o +perf-y += builtin-buildid-cache.o +perf-y += builtin-list.o +perf-y += builtin-record.o +perf-y += builtin-report.o +perf-y += builtin-stat.o +perf-y += builtin-timechart.o +perf-y += builtin-top.o +perf-y += builtin-script.o +perf-y += builtin-kmem.o +perf-y += builtin-lock.o +perf-y += builtin-kvm.o +perf-y += builtin-inject.o +perf-y += builtin-mem.o +perf-y += builtin-data.o + +perf-$(CONFIG_AUDIT) += builtin-trace.o +perf-$(CONFIG_LIBELF) += builtin-probe.o + +perf-y += bench/ +perf-y += tests/ + +perf-y += perf.o + +paths += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" +paths += -DPERF_INFO_PATH="BUILD_STR($(infodir_SQ))" +paths += -DPERF_MAN_PATH="BUILD_STR($(mandir_SQ))" + +CFLAGS_builtin-help.o += $(paths) +CFLAGS_builtin-timechart.o += $(paths) +CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" -include $(OUTPUT)PERF-VERSION-FILE + +libperf-y += util/ +libperf-y += arch/ +libperf-y += ui/ +libperf-y += scripts/ + +gtk-y += ui/gtk/ diff --git a/tools/perf/Documentation/Build.txt b/tools/perf/Documentation/Build.txt new file mode 100644 index 000000000000..f6fc6507ba55 --- /dev/null +++ b/tools/perf/Documentation/Build.txt @@ -0,0 +1,49 @@ + +1) perf build +============= +The perf build process consists of several separated building blocks, +which are linked together to form the perf binary: + - libperf library (static) + - perf builtin commands + - traceevent library (static) + - GTK ui library + +Several makefiles govern the perf build: + + - Makefile + top level Makefile working as a wrapper that calls the main + Makefile.perf with a -j option to do parallel builds. + + - Makefile.perf + main makefile that triggers build of all perf objects including + installation and documentation processing. + + - tools/build/Makefile.build + main makefile of the build framework + + - tools/build/Build.include + build framework generic definitions + + - Build makefiles + makefiles that defines build objects + +Please refer to tools/build/Documentation/Build.txt for more +information about build framework. + + +2) perf build +============= +The Makefile.perf triggers the build framework for build objects: + perf, libperf, gtk + +resulting in following objects: + $ ls *-in.o + gtk-in.o libperf-in.o perf-in.o + +Those objects are then used in final linking: + libperf-gtk.so <- gtk-in.o libperf-in.o + perf <- perf-in.o libperf-in.o + + +NOTE this description is omitting other libraries involved, only + focusing on build framework outcomes diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 0294c57b1f5e..dd07b55f58d8 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -12,9 +12,9 @@ SYNOPSIS DESCRIPTION ----------- -This command manages the build-id cache. It can add and remove files to/from -the cache. In the future it should as well purge older entries, set upper -limits for the space used by the cache, etc. +This command manages the build-id cache. It can add, remove, update and purge +files to/from the cache. In the future it should as well set upper limits for +the space used by the cache, etc. OPTIONS ------- @@ -36,14 +36,24 @@ OPTIONS actually made. -r:: --remove=:: - Remove specified file from the cache. + Remove a cached binary which has same build-id of specified file + from the cache. +-p:: +--purge=:: + Purge all cached binaries including older caches which have specified + path 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. +--update=:: + Update specified file of the cache. Note that this doesn't remove + older entires since those may be still needed for annotating old + (or remote) perf.data. Only if there is already a cache which has + exactly same build-id, that is replaced by new one. It can be used + to update kallsyms and kernel dso to vmlinux in order to support + annotation. + -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt new file mode 100644 index 000000000000..be8fa1a0a97e --- /dev/null +++ b/tools/perf/Documentation/perf-data.txt @@ -0,0 +1,40 @@ +perf-data(1) +============== + +NAME +---- +perf-data - Data file related processing + +SYNOPSIS +-------- +[verse] +'perf data' [<common options>] <command> [<options>]", + +DESCRIPTION +----------- +Data file related processing. + +COMMANDS +-------- +convert:: + Converts perf data file into another format (only CTF [1] format is support by now). + It's possible to set data-convert debug variable to get debug messages from conversion, + like: + perf --debug data-convert data convert ... + +OPTIONS for 'convert' +--------------------- +--to-ctf:: + Triggers the CTF conversion, specify the path of CTF data directory. + +-i:: + Specify input perf data file path. + +-v:: +--verbose:: + Be more verbose (show counter open errors, etc). + +SEE ALSO +-------- +linkperf:perf[1] +[1] Common Trace Format - http://www.efficios.com/ctf diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index e463caa3eb49..518266192d67 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -20,6 +20,11 @@ If no parameters are passed it will assume perf.data.old and perf.data. The differential profile is displayed only for events matching both specified perf.data files. +If no parameters are passed the samples will be sorted by dso and symbol. +As the perf.data files could come from different binaries, the symbols addresses +could vary. So perf diff is based on the comparison of the files and +symbols name. + OPTIONS ------- -D:: diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 3e2aec94f806..4692d277980b 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -127,6 +127,12 @@ To limit the list use: One or more types can be used at the same time, listing the events for the types specified. +Support raw format: + +. '--raw-dump', shows the raw-dump of all the events. +. '--raw-dump [hw|sw|cache|tracepoint|pmu|event_glob]', shows the raw-dump of + a certain kind of events. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-top[1], diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index aaa869be3dc1..239609c09f83 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -47,6 +47,12 @@ OPTIONS -v:: --verbose:: Be more verbose (show parsed arguments, etc). + Can not use with -q. + +-q:: +--quiet:: + Be quiet (do not show any messages including errors). + Can not use with -v. -a:: --add=:: @@ -96,7 +102,7 @@ OPTIONS Dry run. With this option, --add and --del doesn't execute actual adding and removal operations. ---max-probes:: +--max-probes=NUM:: Set the maximum number of probe points for an event. Default is 128. -x:: @@ -104,8 +110,13 @@ OPTIONS Specify path to the executable or shared library file for user space tracing. Can also be used with --funcs option. +--demangle:: + Demangle application symbols. --no-demangle is also available + for disabling demangling. + --demangle-kernel:: - Demangle kernel symbols. + Demangle kernel symbols. --no-demangle-kernel is also available + for disabling kernel demangling. In absence of -m/-x options, perf probe checks if the first argument after the options is an absolute path name. If its an absolute path, perf probe @@ -137,6 +148,7 @@ Each probe argument follows below syntax. [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE] 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) +'$vars' special argument is also available for NAME, it is expanded to the local variables which can access at given probe point. 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 31e977459c51..cae75c11120f 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -115,13 +115,19 @@ OPTIONS implies -g. Allows specifying "fp" (frame pointer) or "dwarf" - (DWARF's CFI - Call Frame Information) as the method to collect + (DWARF's CFI - Call Frame Information) or "lbr" + (Hardware Last Branch Record facility) as the method to collect the information used to show the call graphs. In some systems, where binaries are build with gcc --fomit-frame-pointer, using the "fp" method will produce bogus call graphs, using "dwarf", if available (perf tools linked to the libunwind library) should be used instead. + Using the "lbr" method doesn't require any compiler options. It + will produce call graphs from the hardware LBR registers. The + main limition is that it is only available on new Intel + platforms, such as Haswell. It can only get user call chain. It + doesn't work with branch stack sampling at the same time. -q:: --quiet:: @@ -235,6 +241,9 @@ Capture machine state (registers) at interrupt, i.e., on counter overflows for each sample. List of captured registers depends on the architecture. This option is off by default. +--running-time:: +Record running and enabled time for read events (:S) + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 7e1b1f2bb83c..ba03fd5d1a54 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -55,6 +55,9 @@ OPTIONS --uid=:: Record events in threads owned by uid. Name or number. +--filter-pids=:: + Filter out events for these pids and for 'trace' itself (comma separated list). + -v:: --verbose=:: Verbosity level. @@ -115,6 +118,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --syscalls:: Trace system calls. This options is enabled by default. +--event:: + Trace other events, see 'perf list' for a complete list. + PAGEFAULTS ---------- diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 1e8e400b4493..2b131776363e 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -13,11 +13,16 @@ SYNOPSIS OPTIONS ------- --debug:: - Setup debug variable (just verbose for now) in value + Setup debug variable (see list below) in value range (0, 10). Use like: --debug verbose # sets verbose = 1 --debug verbose=2 # sets verbose = 2 + List of debug variables allowed to set: + verbose - general debug messages + ordered-events - ordered events object debug messages + data-convert - data convert command debug messages + --buildid-dir:: Setup buildid cache directory. It has higher priority than buildid.dir config file option. diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index fbbfdc39271d..11ccbb22ea2b 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,5 +1,6 @@ tools/perf tools/scripts +tools/build tools/lib/traceevent tools/lib/api tools/lib/symbol/kallsyms.c diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index aa6a50447c32..ec4c063ed9f3 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -68,7 +68,9 @@ include config/utilities.mak # for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode # # Define NO_ZLIB if you do not want to support compressed kernel modules - +# +# Define NO_LIBBABELTRACE if you do not want libbabeltrace support +# for CTF data format. ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(shell pwd))) @@ -82,13 +84,29 @@ endif ifneq ($(OUTPUT),) #$(info Determined 'OUTPUT' to be $(OUTPUT)) +# Adding $(OUTPUT) as a directory to look for source files, +# because use generated output files as sources dependency +# for flex/bison parsers. +VPATH += $(OUTPUT) +export VPATH +endif + +ifeq ($(V),1) + Q = +else + Q = @ endif +# Do not use make's built-in rules +# (this improves performance and avoids hard-to-debug behaviour); +MAKEFLAGS += -r + $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD - @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) - @touch $(OUTPUT)PERF-VERSION-FILE + $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) + $(Q)touch $(OUTPUT)PERF-VERSION-FILE CC = $(CROSS_COMPILE)gcc +LD = $(CROSS_COMPILE)ld AR = $(CROSS_COMPILE)ar PKG_CONFIG = $(CROSS_COMPILE)pkg-config @@ -127,10 +145,6 @@ export prefix bindir sharedir sysconfdir DESTDIR SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ # Guard against environment variables -BUILTIN_OBJS = -LIB_H = -LIB_OBJS = -GTK_OBJS = PYRF_OBJS = SCRIPT_SH = @@ -155,8 +169,8 @@ endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a export LIBTRACEEVENT -LIBAPIKFS = $(LIB_PATH)libapikfs.a -export LIBAPIKFS +LIBAPI = $(LIB_PATH)libapi.a +export LIBAPI # python extension build directories PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ @@ -167,7 +181,7 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(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 $(LIBTRACEEVENT) $(LIBAPIKFS) +PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI) $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \ @@ -206,297 +220,9 @@ endif export PERL_PATH -$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c - $(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l - -$(OUTPUT)util/parse-events-bison.c: util/parse-events.y - $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_ - -$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c - $(QUIET_FLEX)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l - -$(OUTPUT)util/pmu-bison.c: util/pmu.y - $(QUIET_BISON)$(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 $(OUTPUT)util/pmu-bison.c - LIB_FILE=$(OUTPUT)libperf.a -LIB_H += ../lib/symbol/kallsyms.h -LIB_H += ../../include/uapi/linux/perf_event.h -LIB_H += ../../include/linux/rbtree.h -LIB_H += ../../include/linux/list.h -LIB_H += ../../include/uapi/linux/const.h -LIB_H += ../include/linux/hash.h -LIB_H += ../../include/linux/stringify.h -LIB_H += util/include/linux/bitmap.h -LIB_H += ../include/linux/bitops.h -LIB_H += ../include/asm-generic/bitops/arch_hweight.h -LIB_H += ../include/asm-generic/bitops/atomic.h -LIB_H += ../include/asm-generic/bitops/const_hweight.h -LIB_H += ../include/asm-generic/bitops/find.h -LIB_H += ../include/asm-generic/bitops/fls64.h -LIB_H += ../include/asm-generic/bitops/fls.h -LIB_H += ../include/asm-generic/bitops/__ffs.h -LIB_H += ../include/asm-generic/bitops/__fls.h -LIB_H += ../include/asm-generic/bitops/hweight.h -LIB_H += ../include/asm-generic/bitops.h -LIB_H += ../include/linux/compiler.h -LIB_H += ../include/linux/log2.h -LIB_H += util/include/linux/const.h -LIB_H += util/include/linux/ctype.h -LIB_H += util/include/linux/kernel.h -LIB_H += util/include/linux/list.h -LIB_H += ../include/linux/export.h -LIB_H += util/include/linux/poison.h -LIB_H += util/include/linux/rbtree.h -LIB_H += util/include/linux/rbtree_augmented.h -LIB_H += util/include/linux/string.h -LIB_H += ../include/linux/types.h -LIB_H += util/include/linux/linkage.h -LIB_H += util/include/asm/asm-offsets.h -LIB_H += ../include/asm/bug.h -LIB_H += util/include/asm/byteorder.h -LIB_H += util/include/asm/swab.h -LIB_H += util/include/asm/system.h -LIB_H += util/include/asm/uaccess.h -LIB_H += util/include/dwarf-regs.h -LIB_H += util/include/asm/dwarf2.h -LIB_H += util/include/asm/cpufeature.h -LIB_H += util/include/asm/unistd_32.h -LIB_H += util/include/asm/unistd_64.h -LIB_H += perf.h -LIB_H += util/annotate.h -LIB_H += util/cache.h -LIB_H += util/callchain.h -LIB_H += util/build-id.h -LIB_H += util/db-export.h -LIB_H += util/debug.h -LIB_H += util/pmu.h -LIB_H += util/event.h -LIB_H += util/evsel.h -LIB_H += util/evlist.h -LIB_H += util/exec_cmd.h -LIB_H += util/find-vdso-map.c -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 -LIB_H += util/quote.h -LIB_H += util/util.h -LIB_H += util/xyarray.h -LIB_H += util/header.h -LIB_H += util/help.h -LIB_H += util/session.h -LIB_H += util/ordered-events.h -LIB_H += util/strbuf.h -LIB_H += util/strlist.h -LIB_H += util/strfilter.h -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 -LIB_H += util/sort.h -LIB_H += util/hist.h -LIB_H += util/comm.h -LIB_H += util/thread.h -LIB_H += util/thread_map.h -LIB_H += util/trace-event.h -LIB_H += util/probe-finder.h -LIB_H += util/dwarf-aux.h -LIB_H += util/probe-event.h -LIB_H += util/pstack.h -LIB_H += util/cpumap.h -LIB_H += util/top.h -LIB_H += $(ARCH_INCLUDE) -LIB_H += util/cgroup.h -LIB_H += $(LIB_INCLUDE)traceevent/event-parse.h -LIB_H += util/target.h -LIB_H += util/rblist.h -LIB_H += util/intlist.h -LIB_H += util/perf_regs.h -LIB_H += util/unwind.h -LIB_H += util/vdso.h -LIB_H += util/tsc.h -LIB_H += ui/helpline.h -LIB_H += ui/progress.h -LIB_H += ui/util.h -LIB_H += ui/ui.h -LIB_H += util/data.h -LIB_H += util/kvm-stat.h -LIB_H += util/thread-stack.h - -LIB_OBJS += $(OUTPUT)util/abspath.o -LIB_OBJS += $(OUTPUT)util/alias.o -LIB_OBJS += $(OUTPUT)util/annotate.o -LIB_OBJS += $(OUTPUT)util/build-id.o -LIB_OBJS += $(OUTPUT)util/config.o -LIB_OBJS += $(OUTPUT)util/ctype.o -LIB_OBJS += $(OUTPUT)util/db-export.o -LIB_OBJS += $(OUTPUT)util/pmu.o -LIB_OBJS += $(OUTPUT)util/environment.o -LIB_OBJS += $(OUTPUT)util/event.o -LIB_OBJS += $(OUTPUT)util/evlist.o -LIB_OBJS += $(OUTPUT)util/evsel.o -LIB_OBJS += $(OUTPUT)util/exec_cmd.o -LIB_OBJS += $(OUTPUT)util/find_next_bit.o -LIB_OBJS += $(OUTPUT)util/help.o -LIB_OBJS += $(OUTPUT)util/kallsyms.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/path.o -LIB_OBJS += $(OUTPUT)util/rbtree.o -LIB_OBJS += $(OUTPUT)util/bitmap.o -LIB_OBJS += $(OUTPUT)util/hweight.o -LIB_OBJS += $(OUTPUT)util/run-command.o -LIB_OBJS += $(OUTPUT)util/quote.o -LIB_OBJS += $(OUTPUT)util/strbuf.o -LIB_OBJS += $(OUTPUT)util/string.o -LIB_OBJS += $(OUTPUT)util/strlist.o -LIB_OBJS += $(OUTPUT)util/strfilter.o -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/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 -LIB_OBJS += $(OUTPUT)util/ordered-events.o -LIB_OBJS += $(OUTPUT)util/comm.o -LIB_OBJS += $(OUTPUT)util/thread.o -LIB_OBJS += $(OUTPUT)util/thread_map.o -LIB_OBJS += $(OUTPUT)util/trace-event-parse.o -LIB_OBJS += $(OUTPUT)util/parse-events-flex.o -LIB_OBJS += $(OUTPUT)util/parse-events-bison.o -LIB_OBJS += $(OUTPUT)util/pmu-flex.o -LIB_OBJS += $(OUTPUT)util/pmu-bison.o -LIB_OBJS += $(OUTPUT)util/trace-event-read.o -LIB_OBJS += $(OUTPUT)util/trace-event-info.o -LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o -LIB_OBJS += $(OUTPUT)util/trace-event.o -LIB_OBJS += $(OUTPUT)util/svghelper.o -LIB_OBJS += $(OUTPUT)util/sort.o -LIB_OBJS += $(OUTPUT)util/hist.o -LIB_OBJS += $(OUTPUT)util/probe-event.o -LIB_OBJS += $(OUTPUT)util/util.o -LIB_OBJS += $(OUTPUT)util/xyarray.o -LIB_OBJS += $(OUTPUT)util/cpumap.o -LIB_OBJS += $(OUTPUT)util/cgroup.o -LIB_OBJS += $(OUTPUT)util/target.o -LIB_OBJS += $(OUTPUT)util/rblist.o -LIB_OBJS += $(OUTPUT)util/intlist.o -LIB_OBJS += $(OUTPUT)util/vdso.o -LIB_OBJS += $(OUTPUT)util/stat.o -LIB_OBJS += $(OUTPUT)util/record.o -LIB_OBJS += $(OUTPUT)util/srcline.o -LIB_OBJS += $(OUTPUT)util/data.o -LIB_OBJS += $(OUTPUT)util/tsc.o -LIB_OBJS += $(OUTPUT)util/cloexec.o -LIB_OBJS += $(OUTPUT)util/thread-stack.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/fdarray.o -LIB_OBJS += $(OUTPUT)tests/pmu.o -LIB_OBJS += $(OUTPUT)tests/hists_common.o -LIB_OBJS += $(OUTPUT)tests/hists_link.o -LIB_OBJS += $(OUTPUT)tests/hists_filter.o -LIB_OBJS += $(OUTPUT)tests/hists_output.o -LIB_OBJS += $(OUTPUT)tests/hists_cumulate.o -LIB_OBJS += $(OUTPUT)tests/python-use.o -LIB_OBJS += $(OUTPUT)tests/bp_signal.o -LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o -LIB_OBJS += $(OUTPUT)tests/task-exit.o -LIB_OBJS += $(OUTPUT)tests/sw-clock.o -ifeq ($(ARCH),x86) -LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o -endif -LIB_OBJS += $(OUTPUT)tests/code-reading.o -LIB_OBJS += $(OUTPUT)tests/sample-parsing.o -LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o -ifndef NO_DWARF_UNWIND -ifeq ($(ARCH),$(filter $(ARCH),x86 arm)) -LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o -endif -endif -LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o -LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o -LIB_OBJS += $(OUTPUT)tests/switch-tracking.o - -BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o -BUILTIN_OBJS += $(OUTPUT)builtin-bench.o -# Benchmark modules -BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o -BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o -ifeq ($(ARCH), x86) -ifeq ($(IS_64_BIT), 1) -BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o -BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o -endif -endif -BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o -BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o -BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o -BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o - -BUILTIN_OBJS += $(OUTPUT)builtin-diff.o -BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o -BUILTIN_OBJS += $(OUTPUT)builtin-help.o -BUILTIN_OBJS += $(OUTPUT)builtin-sched.o -BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o -BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o -BUILTIN_OBJS += $(OUTPUT)builtin-list.o -BUILTIN_OBJS += $(OUTPUT)builtin-record.o -BUILTIN_OBJS += $(OUTPUT)builtin-report.o -BUILTIN_OBJS += $(OUTPUT)builtin-stat.o -BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o -BUILTIN_OBJS += $(OUTPUT)builtin-top.o -BUILTIN_OBJS += $(OUTPUT)builtin-script.o -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-inject.o -BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o -BUILTIN_OBJS += $(OUTPUT)builtin-mem.o - -PERFLIBS = $(LIB_FILE) $(LIBAPIKFS) $(LIBTRACEEVENT) +PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT) # We choose to avoid "if .. else if .. else .. endif endif" # because maintaining the nesting to match is a pain. If @@ -508,67 +234,9 @@ ifneq ($(OUTPUT),) CFLAGS += -I$(OUTPUT) endif -ifdef NO_LIBELF -# Remove ELF/DWARF dependent codes -LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS)) -LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS)) -LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS)) -LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS)) - -BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS)) - -# Use minimal symbol handling -LIB_OBJS += $(OUTPUT)util/symbol-minimal.o - -else # NO_LIBELF -ifndef NO_DWARF - LIB_OBJS += $(OUTPUT)util/probe-finder.o - LIB_OBJS += $(OUTPUT)util/dwarf-aux.o -endif # NO_DWARF -endif # NO_LIBELF - -ifndef NO_LIBDW_DWARF_UNWIND - LIB_OBJS += $(OUTPUT)util/unwind-libdw.o - LIB_H += util/unwind-libdw.h -endif - -ifndef NO_LIBUNWIND - LIB_OBJS += $(OUTPUT)util/unwind-libunwind.o -endif -LIB_OBJS += $(OUTPUT)tests/keep-tracking.o - -ifndef NO_LIBAUDIT - BUILTIN_OBJS += $(OUTPUT)builtin-trace.o -endif - -ifndef NO_SLANG - LIB_OBJS += $(OUTPUT)ui/browser.o - LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o - LIB_OBJS += $(OUTPUT)ui/browsers/hists.o - LIB_OBJS += $(OUTPUT)ui/browsers/map.o - LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o - LIB_OBJS += $(OUTPUT)ui/browsers/header.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/tui/tui.h - LIB_H += ui/browser.h - LIB_H += ui/browsers/map.h - LIB_H += ui/keysyms.h - LIB_H += ui/libslang.h -endif - ifndef NO_GTK2 ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so - - GTK_OBJS += $(OUTPUT)ui/gtk/browser.o - GTK_OBJS += $(OUTPUT)ui/gtk/hists.o - GTK_OBJS += $(OUTPUT)ui/gtk/setup.o - GTK_OBJS += $(OUTPUT)ui/gtk/util.o - GTK_OBJS += $(OUTPUT)ui/gtk/helpline.o - GTK_OBJS += $(OUTPUT)ui/gtk/progress.o - GTK_OBJS += $(OUTPUT)ui/gtk/annotate.o + GTK_IN := $(OUTPUT)gtk-in.o install-gtk: $(OUTPUT)libperf-gtk.so $(call QUIET_INSTALL, 'GTK UI') \ @@ -576,31 +244,6 @@ install-gtk: $(OUTPUT)libperf-gtk.so $(INSTALL) $(OUTPUT)libperf-gtk.so '$(DESTDIR_SQ)$(libdir_SQ)' endif -ifndef NO_LIBPERL - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o - LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o -endif - -ifndef NO_LIBPYTHON - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o - LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o -endif - -ifeq ($(NO_PERF_REGS),0) - ifeq ($(ARCH),x86) - LIB_H += arch/x86/include/perf_regs.h - endif - LIB_OBJS += $(OUTPUT)util/perf_regs.o -endif - -ifndef NO_LIBNUMA - BUILTIN_OBJS += $(OUTPUT)bench/numa.o -endif - -ifndef NO_ZLIB - LIB_OBJS += $(OUTPUT)util/zlib.o -endif - ifdef ASCIIDOC8 export ASCIIDOC8 endif @@ -616,39 +259,29 @@ SHELL = $(SHELL_PATH) all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) please_set_SHELL_PATH_to_a_more_modern_shell: - @$$(:) + $(Q)$$(:) shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell 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) -include $(OUTPUT)PERF-VERSION-FILE \ - '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - $(CFLAGS) -c $(filter %.c,$^) -o $@ +PERF_IN := $(OUTPUT)perf-in.o -$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \ - $(BUILTIN_OBJS) $(LIBS) -o $@ +export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX +build := -f $(srctree)/tools/build/Makefile.build dir=. obj -$(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H) - $(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $< +$(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE + $(Q)$(MAKE) $(build)=perf -$(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS) - $(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS) +$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(PERF_IN) $(LIBS) -o $@ -$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - '-DPERF_MAN_PATH="$(mandir_SQ)"' \ - '-DPERF_INFO_PATH="$(infodir_SQ)"' $< +$(GTK_IN): FORCE + $(Q)$(MAKE) $(build)=gtk -$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - '-DPERF_MAN_PATH="$(mandir_SQ)"' \ - '-DPERF_INFO_PATH="$(infodir_SQ)"' $< +$(OUTPUT)libperf-gtk.so: $(GTK_IN) $(PERFLIBS) + $(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS) $(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt @@ -659,8 +292,7 @@ $(SCRIPTS) : % : %.sh $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@' # These can record PERF_VERSION -$(OUTPUT)perf.o perf.spec \ - $(SCRIPTS) \ +perf.spec $(SCRIPTS) \ : $(OUTPUT)PERF-VERSION-FILE .SUFFIXES: @@ -683,90 +315,33 @@ endif # These two need to be here so that when O= is not used they take precedence # over the general rule for .o -$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $< - -$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $< - -$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< -$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< -$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $< -$(OUTPUT)%.o: %.S - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< -$(OUTPUT)%.s: %.S - $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< - -$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ - '-DPREFIX="$(prefix_SQ)"' \ - $< - -$(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \ - $< - -$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - -DPYTHONPATH='"$(OUTPUT)python"' \ - -DPYTHON='"$(PYTHON_WORD)"' \ - $< - -$(OUTPUT)tests/dwarf-unwind.o: tests/dwarf-unwind.c - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -fno-optimize-sibling-calls $< +# get relative building directory (to $(OUTPUT)) +# and '.' if it's $(OUTPUT) itself +__build-dir = $(subst $(OUTPUT),,$(dir $@)) +build-dir = $(if $(__build-dir),$(__build-dir),.) -$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +single_dep: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h -$(OUTPUT)ui/setup.o: ui/setup.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DLIBDIR='"$(libdir_SQ)"' $< +$(OUTPUT)%.o: %.c single_dep FORCE + $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ -$(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< +$(OUTPUT)%.i: %.c single_dep FORCE + $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ -$(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< +$(OUTPUT)%.s: %.c single_dep FORCE + $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ -$(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< +$(OUTPUT)%-bison.o: %.c single_dep FORCE + $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ -$(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< +$(OUTPUT)%-flex.o: %.c single_dep FORCE + $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ -$(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< +$(OUTPUT)%.o: %.S single_dep FORCE + $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ -$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< - -$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< - -$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< - -$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< - -$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $< - -$(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default $< - -$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default $< - -$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< - -$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< +$(OUTPUT)%.i: %.S single_dep FORCE + $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ $(OUTPUT)perf-%: %.o $(PERFLIBS) $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS) @@ -781,58 +356,34 @@ $(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c $(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c endif -$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) -$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) +$(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) -# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So -# we depend the various files onto their directories. -DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(GTK_OBJS) -DIRECTORY_DEPS += $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h -# no need to add flex objects, because they depend on bison ones -DIRECTORY_DEPS += $(OUTPUT)util/parse-events-bison.c -DIRECTORY_DEPS += $(OUTPUT)util/pmu-bison.c +LIBPERF_IN := $(OUTPUT)libperf-in.o -OUTPUT_DIRECTORIES := $(sort $(dir $(DIRECTORY_DEPS))) +$(LIBPERF_IN): FORCE + $(Q)$(MAKE) $(build)=libperf -$(DIRECTORY_DEPS): | $(OUTPUT_DIRECTORIES) -# In the second step, we make a rule to actually create these directories -$(OUTPUT_DIRECTORIES): - $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null +$(LIB_FILE): $(LIBPERF_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS) -$(LIB_FILE): $(LIB_OBJS) - $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS) - -# libtraceevent.a -TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch]) - -LIBTRACEEVENT_FLAGS = $(QUIET_SUBDIR1) O=$(OUTPUT) -LIBTRACEEVENT_FLAGS += CFLAGS="-g -Wall $(EXTRA_CFLAGS)" LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) -$(LIBTRACEEVENT): $(TE_SOURCES) $(OUTPUT)PERF-CFLAGS - $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) libtraceevent.a plugins +$(LIBTRACEEVENT): FORCE + $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a plugins $(LIBTRACEEVENT)-clean: $(call QUIET_CLEAN, libtraceevent) - @$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null + $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null install-traceevent-plugins: $(LIBTRACEEVENT) - $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins + $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins -LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch] $(LIB_PATH)fd/*.[ch]) - -# if subdir is set, we've been called from above so target has been built -# already -$(LIBAPIKFS): $(LIBAPIKFS_SOURCES) -ifeq ($(subdir),) - $(QUIET_SUBDIR0)$(LIB_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libapikfs.a -endif +$(LIBAPI): FORCE + $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) $(OUTPUT)libapi.a -$(LIBAPIKFS)-clean: -ifeq ($(subdir),) - $(call QUIET_CLEAN, libapikfs) - @$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null -endif +$(LIBAPI)-clean: + $(call QUIET_CLEAN, libapi) + $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null help: @echo 'Perf make targets:' @@ -888,17 +439,6 @@ cscope: $(QUIET_GEN)$(RM) cscope*; \ $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES) -### Detect prefix changes -TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\ - $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ):$(plugindir_SQ) - -$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS - @FLAGS='$(TRACK_CFLAGS)'; \ - if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \ - echo 1>&2 " FLAGS: * new build flags or prefix"; \ - echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \ - fi - ### Testing rules # GNU make supports exporting all variables by "export" without parameters. @@ -981,12 +521,14 @@ $(INSTALL_DOC_TARGETS): # config-clean: $(call QUIET_CLEAN, config) - @$(MAKE) -C config/feature-checks clean >/dev/null + $(Q)$(MAKE) -C config/feature-checks clean >/dev/null -clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean - $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS) +clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean + $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) + $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)$(RM) .config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 - $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* + $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) @@ -1000,7 +542,9 @@ else GIT-HEAD-PHONY = endif +FORCE: + .PHONY: all install clean config-clean strip install-gtk .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell -.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope .FORCE-PERF-CFLAGS +.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE single_dep diff --git a/tools/perf/arch/Build b/tools/perf/arch/Build new file mode 100644 index 000000000000..109eb75cf7de --- /dev/null +++ b/tools/perf/arch/Build @@ -0,0 +1,2 @@ +libperf-y += common.o +libperf-y += $(ARCH)/ diff --git a/tools/perf/arch/arm/Build b/tools/perf/arch/arm/Build new file mode 100644 index 000000000000..41bf61da476a --- /dev/null +++ b/tools/perf/arch/arm/Build @@ -0,0 +1,2 @@ +libperf-y += util/ +libperf-$(CONFIG_DWARF_UNWIND) += tests/ diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile index 09d62153d384..7fbca175099e 100644 --- a/tools/perf/arch/arm/Makefile +++ b/tools/perf/arch/arm/Makefile @@ -1,14 +1,3 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o -endif -ifndef NO_LIBUNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o -endif -ifndef NO_LIBDW_DWARF_UNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o -endif -ifndef NO_DWARF_UNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o endif diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build new file mode 100644 index 000000000000..b30eff9bcc83 --- /dev/null +++ b/tools/perf/arch/arm/tests/Build @@ -0,0 +1,2 @@ +libperf-y += regs_load.o +libperf-y += dwarf-unwind.o diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build new file mode 100644 index 000000000000..d22e3d07de3d --- /dev/null +++ b/tools/perf/arch/arm/util/Build @@ -0,0 +1,4 @@ +libperf-$(CONFIG_DWARF) += dwarf-regs.o + +libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/arm64/Build b/tools/perf/arch/arm64/Build new file mode 100644 index 000000000000..54afe4a467e7 --- /dev/null +++ b/tools/perf/arch/arm64/Build @@ -0,0 +1 @@ +libperf-y += util/ diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 67e9b3d38e89..7fbca175099e 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -1,7 +1,3 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o -endif -ifndef NO_LIBUNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o endif diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build new file mode 100644 index 000000000000..e58123a8912b --- /dev/null +++ b/tools/perf/arch/arm64/util/Build @@ -0,0 +1,2 @@ +libperf-$(CONFIG_DWARF) += dwarf-regs.o +libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o diff --git a/tools/perf/arch/powerpc/Build b/tools/perf/arch/powerpc/Build new file mode 100644 index 000000000000..54afe4a467e7 --- /dev/null +++ b/tools/perf/arch/powerpc/Build @@ -0,0 +1 @@ +libperf-y += util/ diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 6f7782bea5dd..7fbca175099e 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,6 +1,3 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o endif -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build new file mode 100644 index 000000000000..0af6e9b3f728 --- /dev/null +++ b/tools/perf/arch/powerpc/util/Build @@ -0,0 +1,4 @@ +libperf-y += header.o + +libperf-$(CONFIG_DWARF) += dwarf-regs.o +libperf-$(CONFIG_DWARF) += skip-callchain-idx.o diff --git a/tools/perf/arch/s390/Build b/tools/perf/arch/s390/Build new file mode 100644 index 000000000000..54afe4a467e7 --- /dev/null +++ b/tools/perf/arch/s390/Build @@ -0,0 +1 @@ +libperf-y += util/ diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 798ac7379c5f..21322e0385b8 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -1,7 +1,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o HAVE_KVM_STAT_SUPPORT := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build new file mode 100644 index 000000000000..8a61372bb47a --- /dev/null +++ b/tools/perf/arch/s390/util/Build @@ -0,0 +1,4 @@ +libperf-y += header.o +libperf-y += kvm-stat.o + +libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/sh/Build b/tools/perf/arch/sh/Build new file mode 100644 index 000000000000..54afe4a467e7 --- /dev/null +++ b/tools/perf/arch/sh/Build @@ -0,0 +1 @@ +libperf-y += util/ diff --git a/tools/perf/arch/sh/Makefile b/tools/perf/arch/sh/Makefile index 15130b50dfe3..7fbca175099e 100644 --- a/tools/perf/arch/sh/Makefile +++ b/tools/perf/arch/sh/Makefile @@ -1,4 +1,3 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif diff --git a/tools/perf/arch/sh/util/Build b/tools/perf/arch/sh/util/Build new file mode 100644 index 000000000000..954e287bbb89 --- /dev/null +++ b/tools/perf/arch/sh/util/Build @@ -0,0 +1 @@ +libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/sparc/Build b/tools/perf/arch/sparc/Build new file mode 100644 index 000000000000..54afe4a467e7 --- /dev/null +++ b/tools/perf/arch/sparc/Build @@ -0,0 +1 @@ +libperf-y += util/ diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile index 15130b50dfe3..7fbca175099e 100644 --- a/tools/perf/arch/sparc/Makefile +++ b/tools/perf/arch/sparc/Makefile @@ -1,4 +1,3 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif diff --git a/tools/perf/arch/sparc/util/Build b/tools/perf/arch/sparc/util/Build new file mode 100644 index 000000000000..954e287bbb89 --- /dev/null +++ b/tools/perf/arch/sparc/util/Build @@ -0,0 +1 @@ +libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/x86/Build b/tools/perf/arch/x86/Build new file mode 100644 index 000000000000..41bf61da476a --- /dev/null +++ b/tools/perf/arch/x86/Build @@ -0,0 +1,2 @@ +libperf-y += util/ +libperf-$(CONFIG_DWARF_UNWIND) += tests/ diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 9b21881db52f..21322e0385b8 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -1,19 +1,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif -ifndef NO_LIBUNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o -endif -ifndef NO_LIBDW_DWARF_UNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o -endif -ifndef NO_DWARF_UNWIND -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o -endif -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o -LIB_H += arch/$(ARCH)/util/tsc.h HAVE_KVM_STAT_SUPPORT := 1 -LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build new file mode 100644 index 000000000000..b30eff9bcc83 --- /dev/null +++ b/tools/perf/arch/x86/tests/Build @@ -0,0 +1,2 @@ +libperf-y += regs_load.o +libperf-y += dwarf-unwind.o diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build new file mode 100644 index 000000000000..cfbccc4e3187 --- /dev/null +++ b/tools/perf/arch/x86/util/Build @@ -0,0 +1,8 @@ +libperf-y += header.o +libperf-y += tsc.o +libperf-y += kvm-stat.o + +libperf-$(CONFIG_DWARF) += dwarf-regs.o + +libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build new file mode 100644 index 000000000000..5ce98023d518 --- /dev/null +++ b/tools/perf/bench/Build @@ -0,0 +1,11 @@ +perf-y += sched-messaging.o +perf-y += sched-pipe.o +perf-y += mem-memcpy.o +perf-y += futex-hash.o +perf-y += futex-wake.o +perf-y += futex-requeue.o + +perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o +perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o + +perf-$(CONFIG_NUMA) += numa.o diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 50e6b66aea1f..d47a0cdc71c9 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -125,8 +125,7 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir, return ret; } -static int build_id_cache__add_kcore(const char *filename, const char *debugdir, - bool force) +static int build_id_cache__add_kcore(const char *filename, bool force) { char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1]; char from_dir[PATH_MAX], to_dir[PATH_MAX]; @@ -143,7 +142,7 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir, return -1; scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s", - debugdir, sbuildid); + buildid_dir, sbuildid); if (!force && !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) { @@ -155,7 +154,7 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir, return -1; scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s", - debugdir, sbuildid, dir); + buildid_dir, sbuildid, dir); if (mkdir_p(to_dir, 0755)) return -1; @@ -183,7 +182,7 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir, return 0; } -static int build_id_cache__add_file(const char *filename, const char *debugdir) +static int build_id_cache__add_file(const char *filename) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; u8 build_id[BUILD_ID_SIZE]; @@ -195,16 +194,14 @@ static int build_id_cache__add_file(const char *filename, const char *debugdir) } build_id__sprintf(build_id, sizeof(build_id), sbuild_id); - err = build_id_cache__add_s(sbuild_id, debugdir, filename, + err = build_id_cache__add_s(sbuild_id, filename, false, false); - if (verbose) - pr_info("Adding %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + pr_debug("Adding %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); return err; } -static int build_id_cache__remove_file(const char *filename, - const char *debugdir) +static int build_id_cache__remove_file(const char *filename) { u8 build_id[BUILD_ID_SIZE]; char sbuild_id[BUILD_ID_SIZE * 2 + 1]; @@ -217,10 +214,34 @@ static int build_id_cache__remove_file(const char *filename, } build_id__sprintf(build_id, sizeof(build_id), sbuild_id); - err = build_id_cache__remove_s(sbuild_id, debugdir); - if (verbose) - pr_info("Removing %s %s: %s\n", sbuild_id, filename, - err ? "FAIL" : "Ok"); + err = build_id_cache__remove_s(sbuild_id); + pr_debug("Removing %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); + + return err; +} + +static int build_id_cache__purge_path(const char *pathname) +{ + struct strlist *list; + struct str_node *pos; + int err; + + err = build_id_cache__list_build_ids(pathname, &list); + if (err) + goto out; + + strlist__for_each(pos, list) { + err = build_id_cache__remove_s(pos->s); + pr_debug("Removing %s %s: %s\n", pos->s, pathname, + err ? "FAIL" : "Ok"); + if (err) + break; + } + strlist__delete(list); + +out: + pr_debug("Purging %s: %s\n", pathname, err ? "FAIL" : "Ok"); return err; } @@ -252,13 +273,12 @@ static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *f return 0; } -static int build_id_cache__update_file(const char *filename, - const char *debugdir) +static int build_id_cache__update_file(const char *filename) { u8 build_id[BUILD_ID_SIZE]; char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - int err; + int err = 0; if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); @@ -266,14 +286,14 @@ static int build_id_cache__update_file(const char *filename, } 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"); + if (build_id_cache__cached(sbuild_id)) + err = build_id_cache__remove_s(sbuild_id); + + if (!err) + err = build_id_cache__add_s(sbuild_id, filename, false, false); + + pr_debug("Updating %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); return err; } @@ -287,6 +307,7 @@ int cmd_buildid_cache(int argc, const char **argv, bool force = false; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, + *purge_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, *kcore_filename = NULL; @@ -304,6 +325,8 @@ int cmd_buildid_cache(int argc, const char **argv, "file", "kcore file to add"), OPT_STRING('r', "remove", &remove_name_list_str, "file list", "file(s) to remove"), + OPT_STRING('p', "purge", &purge_name_list_str, "path list", + "path(s) to remove (remove old caches too)"), 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"), @@ -320,6 +343,11 @@ int cmd_buildid_cache(int argc, const char **argv, argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); + if (argc || (!add_name_list_str && !kcore_filename && + !remove_name_list_str && !purge_name_list_str && + !missing_filename && !update_name_list_str)) + usage_with_options(buildid_cache_usage, buildid_cache_options); + if (missing_filename) { file.path = missing_filename; file.force = force; @@ -338,7 +366,7 @@ int cmd_buildid_cache(int argc, const char **argv, list = strlist__new(true, add_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__add_file(pos->s, buildid_dir)) { + if (build_id_cache__add_file(pos->s)) { if (errno == EEXIST) { pr_debug("%s already in the cache\n", pos->s); @@ -356,7 +384,25 @@ int cmd_buildid_cache(int argc, const char **argv, list = strlist__new(true, remove_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__remove_file(pos->s, buildid_dir)) { + if (build_id_cache__remove_file(pos->s)) { + if (errno == ENOENT) { + pr_debug("%s wasn't in the cache\n", + pos->s); + continue; + } + pr_warning("Couldn't remove %s: %s\n", + pos->s, strerror_r(errno, sbuf, sizeof(sbuf))); + } + + strlist__delete(list); + } + } + + if (purge_name_list_str) { + list = strlist__new(true, purge_name_list_str); + if (list) { + strlist__for_each(pos, list) + if (build_id_cache__purge_path(pos->s)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -377,7 +423,7 @@ int cmd_buildid_cache(int argc, const char **argv, list = strlist__new(true, update_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__update_file(pos->s, buildid_dir)) { + if (build_id_cache__update_file(pos->s)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -391,8 +437,7 @@ int cmd_buildid_cache(int argc, const char **argv, } } - if (kcore_filename && - build_id_cache__add_kcore(kcore_filename, buildid_dir, force)) + if (kcore_filename && build_id_cache__add_kcore(kcore_filename, force)) pr_warning("Couldn't add %s\n", kcore_filename); out: diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c new file mode 100644 index 000000000000..155cf75b8199 --- /dev/null +++ b/tools/perf/builtin-data.c @@ -0,0 +1,119 @@ +#include <linux/compiler.h> +#include "builtin.h" +#include "perf.h" +#include "debug.h" +#include "parse-options.h" +#include "data-convert-bt.h" + +typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix); + +struct data_cmd { + const char *name; + const char *summary; + data_cmd_fn_t fn; +}; + +static struct data_cmd data_cmds[]; + +#define for_each_cmd(cmd) \ + for (cmd = data_cmds; cmd && cmd->name; cmd++) + +static const struct option data_options[] = { + OPT_END() +}; + +static const char * const data_usage[] = { + "perf data [<common options>] <command> [<options>]", + NULL +}; + +static void print_usage(void) +{ + struct data_cmd *cmd; + + printf("Usage:\n"); + printf("\t%s\n\n", data_usage[0]); + printf("\tAvailable commands:\n"); + + for_each_cmd(cmd) { + printf("\t %s\t- %s\n", cmd->name, cmd->summary); + } + + printf("\n"); +} + +static const char * const data_convert_usage[] = { + "perf data convert [<options>]", + NULL +}; + +static int cmd_data_convert(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + const char *to_ctf = NULL; + const struct option options[] = { + OPT_INCR('v', "verbose", &verbose, "be more verbose"), + OPT_STRING('i', "input", &input_name, "file", "input file name"), +#ifdef HAVE_LIBBABELTRACE_SUPPORT + OPT_STRING(0, "to-ctf", &to_ctf, NULL, "Convert to CTF format"), +#endif + OPT_END() + }; + +#ifndef HAVE_LIBBABELTRACE_SUPPORT + pr_err("No conversion support compiled in.\n"); + return -1; +#endif + + argc = parse_options(argc, argv, options, + data_convert_usage, 0); + if (argc) { + usage_with_options(data_convert_usage, options); + return -1; + } + + if (to_ctf) { +#ifdef HAVE_LIBBABELTRACE_SUPPORT + return bt_convert__perf2ctf(input_name, to_ctf); +#else + pr_err("The libbabeltrace support is not compiled in.\n"); + return -1; +#endif + } + + return 0; +} + +static struct data_cmd data_cmds[] = { + { "convert", "converts data file between formats", cmd_data_convert }, + { .name = NULL, }, +}; + +int cmd_data(int argc, const char **argv, const char *prefix) +{ + struct data_cmd *cmd; + const char *cmdstr; + + /* No command specified. */ + if (argc < 2) + goto usage; + + argc = parse_options(argc, argv, data_options, data_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (argc < 1) + goto usage; + + cmdstr = argv[0]; + + for_each_cmd(cmd) { + if (strcmp(cmd->name, cmdstr)) + continue; + + return cmd->fn(argc, argv, prefix); + } + + pr_err("Unknown command: %s\n", cmdstr); +usage: + print_usage(); + return -1; +} diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 198f3c3aff95..af5bd0514108 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -36,38 +36,36 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) setup_pager(); - if (raw_dump) { - print_events(NULL, true); - return 0; - } + if (!raw_dump) + printf("\nList of pre-defined events (to be used in -e):\n\n"); if (argc == 0) { - print_events(NULL, false); + print_events(NULL, raw_dump); return 0; } for (i = 0; i < argc; ++i) { - if (i) - putchar('\n'); - if (strncmp(argv[i], "tracepoint", 10) == 0) - print_tracepoint_events(NULL, NULL, false); + if (strcmp(argv[i], "tracepoint") == 0) + print_tracepoint_events(NULL, NULL, raw_dump); else if (strcmp(argv[i], "hw") == 0 || strcmp(argv[i], "hardware") == 0) - print_events_type(PERF_TYPE_HARDWARE); + print_symbol_events(NULL, PERF_TYPE_HARDWARE, + event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); else if (strcmp(argv[i], "sw") == 0 || strcmp(argv[i], "software") == 0) - print_events_type(PERF_TYPE_SOFTWARE); + print_symbol_events(NULL, PERF_TYPE_SOFTWARE, + event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); else if (strcmp(argv[i], "cache") == 0 || strcmp(argv[i], "hwcache") == 0) - print_hwcache_events(NULL, false); + print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) - print_pmu_events(NULL, false); + print_pmu_events(NULL, raw_dump); else { char *sep = strchr(argv[i], ':'), *s; int sep_idx; if (sep == NULL) { - print_events(argv[i], false); + print_events(argv[i], raw_dump); continue; } sep_idx = sep - argv[i]; @@ -76,7 +74,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) return -1; s[sep_idx] = '\0'; - print_tracepoint_events(s, s + sep_idx + 1, false); + print_tracepoint_events(s, s + sep_idx + 1, raw_dump); free(s); } } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 404ab3434052..4fdad06d37db 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -658,7 +658,7 @@ error: static void callchain_debug(void) { - static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" }; + static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" }; pr_debug("callchain: type %s\n", str[callchain_param.record_mode]); @@ -751,9 +751,9 @@ static struct record record = { #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " #ifdef HAVE_DWARF_UNWIND_SUPPORT -const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf lbr"; #else -const char record_callchain_help[] = CALLCHAIN_HELP "fp"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp lbr"; #endif /* @@ -839,6 +839,8 @@ struct option __record_options[] = { "use per-thread mmaps"), OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs, "Sample machine registers on interrupt"), + OPT_BOOLEAN(0, "running-time", &record.opts.running_time, + "Record running/enabled time of read (:S) events"), OPT_END() }; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 2f91094e228b..fb350343b1d7 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -249,6 +249,8 @@ static int report__setup_sample_type(struct report *rep) if ((sample_type & PERF_SAMPLE_REGS_USER) && (sample_type & PERF_SAMPLE_STACK_USER)) callchain_param.record_mode = CALLCHAIN_DWARF; + else if (sample_type & PERF_SAMPLE_BRANCH_STACK) + callchain_param.record_mode = CALLCHAIN_LBR; else callchain_param.record_mode = CALLCHAIN_FP; } @@ -766,7 +768,7 @@ repeat: * 0/1 means the user chose a mode. */ if (((branch_mode == -1 && has_br_stack) || branch_mode == 1) && - branch_call_mode == -1) { + !branch_call_mode) { sort__mode = SORT_MODE__BRANCH; symbol_conf.cumulate_callchain = false; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 891c3930080e..7ce296618717 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1473,9 +1473,9 @@ static int perf_sched__read_events(struct perf_sched *sched, goto out_delete; } - 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]; + sched->nr_events = session->evlist->stats.nr_events[0]; + sched->nr_lost_events = session->evlist->stats.total_lost; + sched->nr_lost_chunks = session->evlist->stats.nr_events[PERF_RECORD_LOST]; } if (psession) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c4c7eac69de4..5fb8723c7128 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -716,7 +716,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (!machine) { pr_err("%u unprocessable samples recorded.\r", - top->session->stats.nr_unprocessable_samples++); + top->session->evlist->stats.nr_unprocessable_samples++); return; } @@ -856,7 +856,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) hists__inc_nr_events(evsel__hists(evsel), event->header.type); machine__process_event(machine, event, &sample); } else - ++session->stats.nr_unknown_events; + ++session->evlist->stats.nr_unknown_events; next_event: perf_evlist__mmap_consume(top->evlist, idx); } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 7e935f1083ec..d95a8f4d988c 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -52,7 +52,9 @@ struct tp_field { #define TP_UINT_FIELD(bits) \ static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \ { \ - return *(u##bits *)(sample->raw_data + field->offset); \ + u##bits value; \ + memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \ + return value; \ } TP_UINT_FIELD(8); @@ -63,7 +65,8 @@ TP_UINT_FIELD(64); #define TP_UINT_FIELD__SWAPPED(bits) \ static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \ { \ - u##bits value = *(u##bits *)(sample->raw_data + field->offset); \ + u##bits value; \ + memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \ return bswap_##bits(value);\ } @@ -1219,7 +1222,9 @@ struct trace { struct syscall *table; } syscalls; struct record_opts opts; + struct perf_evlist *evlist; struct machine *host; + struct thread *current; u64 base_time; FILE *output; unsigned long nr_events; @@ -1227,6 +1232,10 @@ struct trace { const char *last_vfs_getname; struct intlist *tid_list; struct intlist *pid_list; + struct { + size_t nr; + pid_t *entries; + } filter_pids; double duration_filter; double runtime_ms; struct { @@ -1511,11 +1520,22 @@ static int trace__read_syscall_info(struct trace *trace, int id) return syscall__set_arg_fmts(sc); } +/* + * args is to be interpreted as a series of longs but we need to handle + * 8-byte unaligned accesses. args points to raw_data within the event + * and raw_data is guaranteed to be 8-byte unaligned because it is + * preceded by raw_size which is a u32. So we need to copy args to a temp + * variable to read it. Most notably this avoids extended load instructions + * on unaligned addresses + */ + static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, - unsigned long *args, struct trace *trace, + unsigned char *args, struct trace *trace, struct thread *thread) { size_t printed = 0; + unsigned char *p; + unsigned long val; if (sc->tp_format != NULL) { struct format_field *field; @@ -1531,12 +1551,17 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, field = field->next, ++arg.idx, bit <<= 1) { if (arg.mask & bit) continue; + + /* special care for unaligned accesses */ + p = args + sizeof(unsigned long) * arg.idx; + memcpy(&val, p, sizeof(val)); + /* * Suppress this argument if its value is zero and * and we don't have a string associated in an * strarray for it. */ - if (args[arg.idx] == 0 && + if (val == 0 && !(sc->arg_scnprintf && sc->arg_scnprintf[arg.idx] == SCA_STRARRAY && sc->arg_parm[arg.idx])) @@ -1545,23 +1570,26 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, printed += scnprintf(bf + printed, size - printed, "%s%s: ", printed ? ", " : "", field->name); if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) { - arg.val = args[arg.idx]; + arg.val = val; if (sc->arg_parm) arg.parm = sc->arg_parm[arg.idx]; printed += sc->arg_scnprintf[arg.idx](bf + printed, size - printed, &arg); } else { printed += scnprintf(bf + printed, size - printed, - "%ld", args[arg.idx]); + "%ld", val); } } } else { int i = 0; while (i < 6) { + /* special care for unaligned accesses */ + p = args + sizeof(unsigned long) * i; + memcpy(&val, p, sizeof(val)); printed += scnprintf(bf + printed, size - printed, "%sarg%d: %ld", - printed ? ", " : "", i, args[i]); + printed ? ", " : "", i, val); ++i; } } @@ -1642,6 +1670,29 @@ static void thread__update_stats(struct thread_trace *ttrace, update_stats(stats, duration); } +static int trace__printf_interrupted_entry(struct trace *trace, struct perf_sample *sample) +{ + struct thread_trace *ttrace; + u64 duration; + size_t printed; + + if (trace->current == NULL) + return 0; + + ttrace = thread__priv(trace->current); + + if (!ttrace->entry_pending) + return 0; + + duration = sample->time - ttrace->entry_time; + + printed = trace__fprintf_entry_head(trace, trace->current, duration, sample->time, trace->output); + printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str); + ttrace->entry_pending = false; + + return printed; +} + static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -1673,6 +1724,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, return -1; } + printed += trace__printf_interrupted_entry(trace, sample); + ttrace->entry_time = sample->time; msg = ttrace->entry_str; printed += scnprintf(msg + printed, 1024 - printed, "%s(", sc->name); @@ -1688,6 +1741,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, } else ttrace->entry_pending = true; + trace->current = thread; + return 0; } @@ -1805,6 +1860,28 @@ out_dump: return 0; } +static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, + union perf_event *event __maybe_unused, + struct perf_sample *sample) +{ + trace__printf_interrupted_entry(trace, sample); + trace__fprintf_tstamp(trace, sample->time, trace->output); + + if (trace->trace_syscalls) + fprintf(trace->output, "( ): "); + + fprintf(trace->output, "%s:", evsel->name); + + if (evsel->tp_format) { + event_format__fprintf(evsel->tp_format, sample->cpu, + sample->raw_data, sample->raw_size, + trace->output); + } + + fprintf(trace->output, ")\n"); + return 0; +} + static void print_location(FILE *f, struct perf_sample *sample, struct addr_location *al, bool print_dso, bool print_sym) @@ -2037,10 +2114,39 @@ static int perf_evlist__add_pgfault(struct perf_evlist *evlist, return 0; } -static int trace__run(struct trace *trace, int argc, const char **argv) +static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample) { - struct perf_evlist *evlist = perf_evlist__new(); + const u32 type = event->header.type; struct perf_evsel *evsel; + + if (!trace->full_time && trace->base_time == 0) + trace->base_time = sample->time; + + if (type != PERF_RECORD_SAMPLE) { + trace__process_event(trace, trace->host, event, sample); + return; + } + + evsel = perf_evlist__id2evsel(trace->evlist, sample->id); + if (evsel == NULL) { + fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id); + return; + } + + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + sample->raw_data == NULL) { + fprintf(trace->output, "%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); + } else { + tracepoint_handler handler = evsel->handler; + handler(trace, evsel, event, sample); + } +} + +static int trace__run(struct trace *trace, int argc, const char **argv) +{ + struct perf_evlist *evlist = trace->evlist; int err = -1, i; unsigned long before; const bool forks = argc > 0; @@ -2048,11 +2154,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) trace->live = true; - if (evlist == NULL) { - fprintf(trace->output, "Not enough memory to run!\n"); - goto out; - } - if (trace->trace_syscalls && perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit)) @@ -2105,16 +2206,34 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (err < 0) goto out_error_open; + /* + * Better not use !target__has_task() here because we need to cover the + * case where no threads were specified in the command line, but a + * workload was, and in that case we will fill in the thread_map when + * we fork the workload in perf_evlist__prepare_workload. + */ + if (trace->filter_pids.nr > 0) + err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries); + else if (evlist->threads->map[0] == -1) + err = perf_evlist__set_filter_pid(evlist, getpid()); + + if (err < 0) { + printf("err=%d,%s\n", -err, strerror(-err)); + exit(1); + } + err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false); if (err < 0) goto out_error_mmap; - perf_evlist__enable(evlist); - if (forks) perf_evlist__start_workload(evlist); + else + perf_evlist__enable(evlist); - trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1; + trace->multiple_threads = evlist->threads->map[0] == -1 || + evlist->threads->nr > 1 || + perf_evlist__first(evlist)->attr.inherit; again: before = trace->nr_events; @@ -2122,8 +2241,6 @@ again: union perf_event *event; while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { - const u32 type = event->header.type; - tracepoint_handler handler; struct perf_sample sample; ++trace->nr_events; @@ -2134,30 +2251,7 @@ again: goto next_event; } - if (!trace->full_time && trace->base_time == 0) - trace->base_time = sample.time; - - if (type != PERF_RECORD_SAMPLE) { - trace__process_event(trace, trace->host, event, &sample); - continue; - } - - evsel = perf_evlist__id2evsel(evlist, sample.id); - if (evsel == NULL) { - fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); - goto next_event; - } - - if (evsel->attr.type == PERF_TYPE_TRACEPOINT && - sample.raw_data == NULL) { - fprintf(trace->output, "%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); - goto next_event; - } - - handler = evsel->handler; - handler(trace, evsel, event, &sample); + trace__handle_event(trace, event, &sample); next_event: perf_evlist__mmap_consume(evlist, i); @@ -2197,7 +2291,7 @@ out_disable: out_delete_evlist: perf_evlist__delete(evlist); -out: + trace->evlist = NULL; trace->live = false; return err; { @@ -2434,6 +2528,38 @@ static int trace__set_duration(const struct option *opt, const char *str, return 0; } +static int trace__set_filter_pids(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + int ret = -1; + size_t i; + struct trace *trace = opt->value; + /* + * FIXME: introduce a intarray class, plain parse csv and create a + * { int nr, int entries[] } struct... + */ + struct intlist *list = intlist__new(str); + + if (list == NULL) + return -1; + + i = trace->filter_pids.nr = intlist__nr_entries(list) + 1; + trace->filter_pids.entries = calloc(i, sizeof(pid_t)); + + if (trace->filter_pids.entries == NULL) + goto out; + + trace->filter_pids.entries[0] = getpid(); + + for (i = 1; i < trace->filter_pids.nr; ++i) + trace->filter_pids.entries[i] = intlist__entry(list, i - 1)->i; + + intlist__delete(list); + ret = 0; +out: + return ret; +} + static int trace__open_output(struct trace *trace, const char *filename) { struct stat st; @@ -2468,6 +2594,14 @@ static int parse_pagefaults(const struct option *opt, const char *str, return 0; } +static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) + evsel->handler = handler; +} + int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const trace_usage[] = { @@ -2502,6 +2636,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) const char *output_name = NULL; const char *ev_qualifier_str = NULL; const struct option trace_options[] = { + OPT_CALLBACK(0, "event", &trace.evlist, "event", + "event selector. use 'perf list' to list available events", + parse_events_option), OPT_BOOLEAN(0, "comm", &trace.show_comm, "show the thread COMM next to its id"), OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"), @@ -2513,6 +2650,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) "trace events on existing process id"), OPT_STRING('t', "tid", &trace.opts.target.tid, "tid", "trace events on existing thread id"), + OPT_CALLBACK(0, "filter-pids", &trace, "float", + "show only events with duration > N.M ms", trace__set_filter_pids), OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide, "system-wide collection from all CPUs"), OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu", @@ -2543,6 +2682,18 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) int err; char bf[BUFSIZ]; + signal(SIGSEGV, sighandler_dump_stack); + signal(SIGFPE, sighandler_dump_stack); + + trace.evlist = perf_evlist__new(); + if (trace.evlist == NULL) + return -ENOMEM; + + if (trace.evlist == NULL) { + pr_err("Not enough memory to run!\n"); + goto out; + } + argc = parse_options(argc, argv, trace_options, trace_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -2551,6 +2702,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) trace.opts.sample_time = true; } + if (trace.evlist->nr_entries > 0) + evlist__set_evsel_handler(trace.evlist, trace__event_handler); + if ((argc >= 1) && (strcmp(argv[0], "record") == 0)) return trace__record(&trace, argc-1, &argv[1]); @@ -2558,7 +2712,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) if (trace.summary_only) trace.summary = trace.summary_only; - if (!trace.trace_syscalls && !trace.trace_pgfaults) { + if (!trace.trace_syscalls && !trace.trace_pgfaults && + trace.evlist->nr_entries == 0 /* Was --events used? */) { pr_err("Please specify something to trace.\n"); return -1; } diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index b210d62907e4..3688ad29085f 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -37,6 +37,7 @@ extern int cmd_test(int argc, const char **argv, const char *prefix); extern int cmd_trace(int argc, const char **argv, const char *prefix); extern int cmd_inject(int argc, const char **argv, const char *prefix); extern int cmd_mem(int argc, const char **argv, const char *prefix); +extern int cmd_data(int argc, const char **argv, const char *prefix); extern int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 0906fc401c52..00fcaf8a5b8d 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -7,6 +7,7 @@ perf-archive mainporcelain common perf-bench mainporcelain common perf-buildid-cache mainporcelain common perf-buildid-list mainporcelain common +perf-data mainporcelain common perf-diff mainporcelain common perf-evlist mainporcelain common perf-inject mainporcelain common diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index cc224080b525..c3570b5f3bf3 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -11,19 +11,27 @@ ifneq ($(obj-perf),) obj-perf := $(abspath $(obj-perf))/ endif +$(shell echo -n > .config-detected) +detected = $(shell echo "$(1)=y" >> .config-detected) +detected_var = $(shell echo "$(1)=$($(1))" >> .config-detected) + LIB_INCLUDE := $(srctree)/tools/lib/ CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) include $(src-perf)/config/Makefile.arch +$(call detected_var,ARCH) + NO_PERF_REGS := 1 # Additional ARCH settings for x86 ifeq ($(ARCH),x86) + $(call detected,CONFIG_X86) ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 + $(call detected,CONFIG_X86_64) else LIBUNWIND_LIBS = -lunwind -lunwind-x86 endif @@ -40,6 +48,10 @@ ifeq ($(ARCH),arm64) LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif +ifeq ($(NO_PERF_REGS),0) + $(call detected,CONFIG_PERF_REGS) +endif + # So far there's only x86 and arm libdw unwind support merged in perf. # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures @@ -84,6 +96,17 @@ ifndef NO_LIBELF FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw endif +ifndef NO_LIBBABELTRACE + # for linking with debug library, run like: + # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/ + ifdef LIBBABELTRACE_DIR + LIBBABELTRACE_CFLAGS := -I$(LIBBABELTRACE_DIR)/include + LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib + endif + FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) + FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf +endif + # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile @@ -114,6 +137,8 @@ ifdef PARSER_DEBUG PARSER_DEBUG_BISON := -t PARSER_DEBUG_FLEX := -d CFLAGS += -DPARSER_DEBUG + $(call detected_var,PARSER_DEBUG_BISON) + $(call detected_var,PARSER_DEBUG_FLEX) endif ifndef NO_LIBPYTHON @@ -202,6 +227,7 @@ CORE_FEATURE_TESTS = \ stackprotector-all \ timerfd \ libdw-dwarf-unwind \ + libbabeltrace \ zlib LIB_FEATURE_TESTS = \ @@ -217,6 +243,7 @@ LIB_FEATURE_TESTS = \ libslang \ libunwind \ libdw-dwarf-unwind \ + libbabeltrace \ zlib VF_FEATURE_TESTS = \ @@ -361,6 +388,7 @@ endif # NO_LIBELF ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT EXTLIBS += -lelf + $(call detected,CONFIG_LIBELF) ifeq ($(feature-libelf-mmap), 1) CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT @@ -381,6 +409,7 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) LDFLAGS += $(LIBDW_LDFLAGS) EXTLIBS += -ldw + $(call detected,CONFIG_DWARF) endif # PERF_HAVE_DWARF_REGS endif # NO_DWARF endif # NO_LIBELF @@ -408,9 +437,11 @@ ifdef NO_LIBUNWIND dwarf-post-unwind := 0 else dwarf-post-unwind-text := libdw + $(call detected,CONFIG_LIBDW_DWARF_UNWIND) endif else dwarf-post-unwind-text := libunwind + $(call detected,CONFIG_LIBUNWIND) # Enable libunwind support by default. ifndef NO_LIBDW_DWARF_UNWIND NO_LIBDW_DWARF_UNWIND := 1 @@ -419,6 +450,7 @@ endif ifeq ($(dwarf-post-unwind),1) CFLAGS += -DHAVE_DWARF_UNWIND_SUPPORT + $(call detected,CONFIG_DWARF_UNWIND) else NO_DWARF_UNWIND := 1 endif @@ -447,6 +479,7 @@ ifndef NO_LIBAUDIT else CFLAGS += -DHAVE_LIBAUDIT_SUPPORT EXTLIBS += -laudit + $(call detected,CONFIG_AUDIT) endif endif @@ -463,6 +496,7 @@ ifndef NO_SLANG CFLAGS += -I/usr/include/slang CFLAGS += -DHAVE_SLANG_SUPPORT EXTLIBS += -lslang + $(call detected,CONFIG_SLANG) endif endif @@ -501,6 +535,7 @@ else else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) + $(call detected,CONFIG_LIBPERL) endif endif @@ -560,6 +595,7 @@ else LDFLAGS += $(PYTHON_EMBED_LDFLAGS) EXTLIBS += $(PYTHON_EMBED_LIBADD) LANG_BINDINGS += $(obj-perf)python/perf.so + $(call detected,CONFIG_LIBPYTHON) endif endif endif @@ -617,6 +653,7 @@ ifndef NO_ZLIB ifeq ($(feature-zlib), 1) CFLAGS += -DHAVE_ZLIB_SUPPORT EXTLIBS += -lz + $(call detected,CONFIG_ZLIB) else NO_ZLIB := 1 endif @@ -635,6 +672,7 @@ ifndef NO_LIBNUMA else CFLAGS += -DHAVE_LIBNUMA_SUPPORT EXTLIBS += -lnuma + $(call detected,CONFIG_NUMA) endif endif @@ -667,6 +705,18 @@ else NO_PERF_READ_VDSOX32 := 1 endif +ifndef NO_LIBBABELTRACE + ifeq ($(feature-libbabeltrace), 0) + msg := $(warning No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-devel/libbabeltrace-ctf-dev); + NO_LIBBABELTRACE := 1 + else + CFLAGS += -DHAVE_LIBBABELTRACE_SUPPORT $(LIBBABELTRACE_CFLAGS) + LDFLAGS += $(LIBBABELTRACE_LDFLAGS) + EXTLIBS += -lbabeltrace-ctf + $(call detected,CONFIG_LIBBABELTRACE) + endif +endif + # Among the variables below, these: # perfexecdir # template_dir @@ -815,3 +865,19 @@ endif ifeq ($(display_lib),1) $(info ) endif + +$(call detected_var,bindir_SQ) +$(call detected_var,PYTHON_WORD) +ifneq ($(OUTPUT),) +$(call detected_var,OUTPUT) +endif +$(call detected_var,htmldir_SQ) +$(call detected_var,infodir_SQ) +$(call detected_var,mandir_SQ) +$(call detected_var,ETC_PERFCONFIG_SQ) +$(call detected_var,prefix_SQ) +$(call detected_var,perfexecdir_SQ) +$(call detected_var,LIBDIR) +$(call detected_var,GTK_CFLAGS) +$(call detected_var,PERL_EMBED_CCOPTS) +$(call detected_var,PYTHON_EMBED_CCOPTS) diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index b32ff3372514..70c9aebe9da3 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -29,6 +29,7 @@ FILES= \ test-stackprotector-all.bin \ test-timerfd.bin \ test-libdw-dwarf-unwind.bin \ + test-libbabeltrace.bin \ test-compile-32.bin \ test-compile-x32.bin \ test-zlib.bin @@ -43,7 +44,7 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS) ############################### test-all.bin: - $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz + $(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -lbabeltrace test-hello.bin: $(BUILD) @@ -133,7 +134,10 @@ test-timerfd.bin: $(BUILD) test-libdw-dwarf-unwind.bin: - $(BUILD) + $(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind) + +test-libbabeltrace.bin: + $(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace) test-sync-compare-and-swap.bin: $(BUILD) -Werror diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c index 6d4d09323922..1ffc3da5ca10 100644 --- a/tools/perf/config/feature-checks/test-all.c +++ b/tools/perf/config/feature-checks/test-all.c @@ -101,6 +101,10 @@ # include "test-pthread_attr_setaffinity_np.c" #undef main +#define main main_test_libbabeltrace +# include "test-libbabeltrace.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -126,6 +130,7 @@ int main(int argc, char *argv[]) main_test_sync_compare_and_swap(argc, argv); main_test_zlib(); main_test_pthread_attr_setaffinity_np(); + main_test_libbabeltrace(); return 0; } diff --git a/tools/perf/config/feature-checks/test-libbabeltrace.c b/tools/perf/config/feature-checks/test-libbabeltrace.c new file mode 100644 index 000000000000..3b7dd68a4d52 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libbabeltrace.c @@ -0,0 +1,8 @@ + +#include <babeltrace/ctf-writer/writer.h> + +int main(void) +{ + bt_ctf_stream_class_get_packet_context_type((void *) 0); + return 0; +} diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index 33569847fdcc..c2595e9bd69b 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -110,13 +110,11 @@ __perf_main () # List perf subcommands or long options if [ $cword -eq 1 ]; then if [[ $cur == --* ]]; then - __perfcomp '--help --version \ - --exec-path --html-path --paginate --no-pager \ - --perf-dir --work-tree --debugfs-dir' -- "$cur" + cmds=$($cmd --list-opts) else cmds=$($cmd --list-cmds) - __perfcomp "$cmds" "$cur" fi + __perfcomp "$cmds" "$cur" # List possible events for -e option elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then evts=$($cmd list --raw-dump) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 3700a7faca6c..b857fcbd00cf 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -13,6 +13,7 @@ #include "util/quote.h" #include "util/run-command.h" #include "util/parse-events.h" +#include "util/parse-options.h" #include "util/debug.h" #include <api/fs/debugfs.h> #include <pthread.h> @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { #endif { "inject", cmd_inject, 0 }, { "mem", cmd_mem, 0 }, + { "data", cmd_data, 0 }, }; struct pager_config { @@ -124,6 +126,23 @@ static void commit_pager_choice(void) } } +struct option options[] = { + OPT_ARGUMENT("help", "help"), + OPT_ARGUMENT("version", "version"), + OPT_ARGUMENT("exec-path", "exec-path"), + OPT_ARGUMENT("html-path", "html-path"), + OPT_ARGUMENT("paginate", "paginate"), + OPT_ARGUMENT("no-pager", "no-pager"), + OPT_ARGUMENT("perf-dir", "perf-dir"), + OPT_ARGUMENT("work-tree", "work-tree"), + OPT_ARGUMENT("debugfs-dir", "debugfs-dir"), + OPT_ARGUMENT("buildid-dir", "buildid-dir"), + OPT_ARGUMENT("list-cmds", "list-cmds"), + OPT_ARGUMENT("list-opts", "list-opts"), + OPT_ARGUMENT("debug", "debug"), + OPT_END() +}; + static int handle_options(const char ***argv, int *argc, int *envchanged) { int handled = 0; @@ -222,6 +241,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) struct cmd_struct *p = commands+i; printf("%s ", p->cmd); } + putchar('\n'); + exit(0); + } else if (!strcmp(cmd, "--list-opts")) { + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(options)-1; i++) { + struct option *p = options+i; + printf("--%s ", p->long_name); + } + putchar('\n'); exit(0); } else if (!strcmp(cmd, "--debug")) { if (*argc < 2) { diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 1dabb8553499..1caa70a4a9e1 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -53,6 +53,7 @@ struct record_opts { bool sample_time; bool period; bool sample_intr_regs; + bool running_time; unsigned int freq; unsigned int mmap_pages; unsigned int user_freq; diff --git a/tools/perf/scripts/Build b/tools/perf/scripts/Build new file mode 100644 index 000000000000..41efd7e368b3 --- /dev/null +++ b/tools/perf/scripts/Build @@ -0,0 +1,2 @@ +libperf-$(CONFIG_LIBPERL) += perl/Perf-Trace-Util/ +libperf-$(CONFIG_LIBPYTHON) += python/Perf-Trace-Util/ diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Build b/tools/perf/scripts/perl/Perf-Trace-Util/Build new file mode 100644 index 000000000000..928e110179cb --- /dev/null +++ b/tools/perf/scripts/perl/Perf-Trace-Util/Build @@ -0,0 +1,3 @@ +libperf-y += Context.o + +CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Build b/tools/perf/scripts/python/Perf-Trace-Util/Build new file mode 100644 index 000000000000..aefc15c9444a --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/Build @@ -0,0 +1,3 @@ +libperf-y += Context.o + +CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build new file mode 100644 index 000000000000..2de01a4b4084 --- /dev/null +++ b/tools/perf/tests/Build @@ -0,0 +1,42 @@ +perf-y += builtin-test.o +perf-y += parse-events.o +perf-y += dso-data.o +perf-y += attr.o +perf-y += vmlinux-kallsyms.o +perf-y += open-syscall.o +perf-y += open-syscall-all-cpus.o +perf-y += open-syscall-tp-fields.o +perf-y += mmap-basic.o +perf-y += perf-record.o +perf-y += rdpmc.o +perf-y += evsel-roundtrip-name.o +perf-y += evsel-tp-sched.o +perf-y += fdarray.o +perf-y += pmu.o +perf-y += hists_common.o +perf-y += hists_link.o +perf-y += hists_filter.o +perf-y += hists_output.o +perf-y += hists_cumulate.o +perf-y += python-use.o +perf-y += bp_signal.o +perf-y += bp_signal_overflow.o +perf-y += task-exit.o +perf-y += sw-clock.o +perf-y += mmap-thread-lookup.o +perf-y += thread-mg-share.o +perf-y += switch-tracking.o +perf-y += keep-tracking.o +perf-y += code-reading.o +perf-y += sample-parsing.o +perf-y += parse-no-sample-id-all.o + +perf-$(CONFIG_X86) += perf-time-to-tsc.o + +ifeq ($(ARCH),$(filter $(ARCH),x86 arm)) +perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o +endif + +CFLAGS_attr.o += -DBINDIR="BUILD_STR($(bindir_SQ))" -DPYTHON="BUILD_STR($(PYTHON_WORD))" +CFLAGS_python-use.o += -DPYTHONPATH="BUILD_STR($(OUTPUT)python)" -DPYTHON="BUILD_STR($(PYTHON_WORD))" +CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index caaf37f079b1..513e5febbe5a 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -112,6 +112,9 @@ int test__dso_data(void) dso = dso__new((const char *)file); + TEST_ASSERT_VAL("Failed to access to dso", + dso__data_fd(dso, &machine) >= 0); + /* Basic 10 bytes tests. */ for (i = 0; i < ARRAY_SIZE(offsets); i++) { struct test_data_offset *data = &offsets[i]; @@ -243,8 +246,8 @@ int test__dso_data_cache(void) limit = nr * 4; TEST_ASSERT_VAL("failed to set file limit", !set_fd_limit(limit)); - /* and this is now our dso open FDs limit + 1 extra */ - dso_cnt = limit / 2 + 1; + /* and this is now our dso open FDs limit */ + dso_cnt = limit / 2; TEST_ASSERT_VAL("failed to create dsos\n", !dsos__create(dso_cnt, TEST_FILE_SIZE)); @@ -252,13 +255,13 @@ int test__dso_data_cache(void) struct dso *dso = dsos[i]; /* - * Open dsos via dso__data_fd or dso__data_read_offset. - * Both opens the data file and keep it open. + * Open dsos via dso__data_fd(), it opens the data + * file and keep it open (unless open file limit). */ + fd = dso__data_fd(dso, &machine); + TEST_ASSERT_VAL("failed to get fd", fd > 0); + if (i % 2) { - fd = dso__data_fd(dso, &machine); - TEST_ASSERT_VAL("failed to get fd", fd > 0); - } else { #define BUFSIZE 10 u8 buf[BUFSIZE]; ssize_t n; @@ -268,7 +271,10 @@ int test__dso_data_cache(void) } } - /* open +1 dso over the allowed limit */ + /* verify the first one is already open */ + TEST_ASSERT_VAL("dsos[0] is not open", dsos[0]->data.fd != -1); + + /* open +1 dso to reach the allowed limit */ fd = dso__data_fd(dsos[i], &machine); TEST_ASSERT_VAL("failed to get fd", fd > 0); diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c index 8fa82d1700c7..3ec885c48f8f 100644 --- a/tools/perf/tests/open-syscall-all-cpus.c +++ b/tools/perf/tests/open-syscall-all-cpus.c @@ -29,7 +29,12 @@ int test__open_syscall_event_on_all_cpus(void) evsel = perf_evsel__newtp("syscalls", "sys_enter_open"); if (evsel == NULL) { - pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); + if (tracefs_configured()) + pr_debug("is tracefs mounted on /sys/kernel/tracing?\n"); + else if (debugfs_configured()) + pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); + else + pr_debug("Neither tracefs or debugfs is enabled in this kernel\n"); goto out_thread_map_delete; } diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c index a33b2daae40f..07aa319bf334 100644 --- a/tools/perf/tests/open-syscall.c +++ b/tools/perf/tests/open-syscall.c @@ -18,7 +18,12 @@ int test__open_syscall_event(void) evsel = perf_evsel__newtp("syscalls", "sys_enter_open"); if (evsel == NULL) { - pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); + if (tracefs_configured()) + pr_debug("is tracefs mounted on /sys/kernel/tracing?\n"); + else if (debugfs_configured()) + pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); + else + pr_debug("Neither tracefs or debugfs is enabled in this kernel\n"); goto out_thread_map_delete; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 1cdab0ce00e2..ac243ebcb20a 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -3,6 +3,7 @@ #include "evsel.h" #include "evlist.h" #include <api/fs/fs.h> +#include <api/fs/tracefs.h> #include <api/fs/debugfs.h> #include "tests.h" #include "debug.h" @@ -1192,11 +1193,19 @@ static int count_tracepoints(void) { char events_path[PATH_MAX]; struct dirent *events_ent; + const char *mountpoint; DIR *events_dir; int cnt = 0; - scnprintf(events_path, PATH_MAX, "%s/tracing/events", - debugfs_find_mountpoint()); + mountpoint = tracefs_find_mountpoint(); + if (mountpoint) { + scnprintf(events_path, PATH_MAX, "%s/events", + mountpoint); + } else { + mountpoint = debugfs_find_mountpoint(); + scnprintf(events_path, PATH_MAX, "%s/tracing/events", + mountpoint); + } events_dir = opendir(events_path); diff --git a/tools/perf/ui/Build b/tools/perf/ui/Build new file mode 100644 index 000000000000..0a73538c0441 --- /dev/null +++ b/tools/perf/ui/Build @@ -0,0 +1,14 @@ +libperf-y += setup.o +libperf-y += helpline.o +libperf-y += progress.o +libperf-y += util.o +libperf-y += hist.o +libperf-y += stdio/hist.o + +CFLAGS_setup.o += -DLIBDIR="BUILD_STR($(LIBDIR))" + +libperf-$(CONFIG_SLANG) += browser.o +libperf-$(CONFIG_SLANG) += browsers/ +libperf-$(CONFIG_SLANG) += tui/ + +CFLAGS_browser.o += -DENABLE_SLFUTURE_CONST diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build new file mode 100644 index 000000000000..de223f5bed58 --- /dev/null +++ b/tools/perf/ui/browsers/Build @@ -0,0 +1,10 @@ +libperf-y += annotate.o +libperf-y += hists.o +libperf-y += map.o +libperf-y += scripts.o +libperf-y += header.o + +CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST +CFLAGS_hists.o += -DENABLE_SLFUTURE_CONST +CFLAGS_map.o += -DENABLE_SLFUTURE_CONST +CFLAGS_scripts.o += -DENABLE_SLFUTURE_CONST diff --git a/tools/perf/ui/gtk/Build b/tools/perf/ui/gtk/Build new file mode 100644 index 000000000000..ec22e899a224 --- /dev/null +++ b/tools/perf/ui/gtk/Build @@ -0,0 +1,9 @@ +CFLAGS_gtk += -fPIC $(GTK_CFLAGS) + +gtk-y += browser.o +gtk-y += hists.o +gtk-y += setup.o +gtk-y += util.o +gtk-y += helpline.o +gtk-y += progress.o +gtk-y += annotate.o diff --git a/tools/perf/ui/tui/Build b/tools/perf/ui/tui/Build new file mode 100644 index 000000000000..9e4c6ca41a9f --- /dev/null +++ b/tools/perf/ui/tui/Build @@ -0,0 +1,4 @@ +libperf-y += setup.o +libperf-y += util.o +libperf-y += helpline.o +libperf-y += progress.o diff --git a/tools/perf/util/Build b/tools/perf/util/Build new file mode 100644 index 000000000000..a2c8047d25f7 --- /dev/null +++ b/tools/perf/util/Build @@ -0,0 +1,144 @@ +libperf-y += abspath.o +libperf-y += alias.o +libperf-y += annotate.o +libperf-y += build-id.o +libperf-y += config.o +libperf-y += ctype.o +libperf-y += db-export.o +libperf-y += environment.o +libperf-y += event.o +libperf-y += evlist.o +libperf-y += evsel.o +libperf-y += exec_cmd.o +libperf-y += find_next_bit.o +libperf-y += help.o +libperf-y += kallsyms.o +libperf-y += levenshtein.o +libperf-y += parse-options.o +libperf-y += parse-events.o +libperf-y += path.o +libperf-y += rbtree.o +libperf-y += bitmap.o +libperf-y += hweight.o +libperf-y += run-command.o +libperf-y += quote.o +libperf-y += strbuf.o +libperf-y += string.o +libperf-y += strlist.o +libperf-y += strfilter.o +libperf-y += top.o +libperf-y += usage.o +libperf-y += wrapper.o +libperf-y += sigchain.o +libperf-y += dso.o +libperf-y += symbol.o +libperf-y += color.o +libperf-y += pager.o +libperf-y += header.o +libperf-y += callchain.o +libperf-y += values.o +libperf-y += debug.o +libperf-y += machine.o +libperf-y += map.o +libperf-y += pstack.o +libperf-y += session.o +libperf-y += ordered-events.o +libperf-y += comm.o +libperf-y += thread.o +libperf-y += thread_map.o +libperf-y += trace-event-parse.o +libperf-y += parse-events-flex.o +libperf-y += parse-events-bison.o +libperf-y += pmu.o +libperf-y += pmu-flex.o +libperf-y += pmu-bison.o +libperf-y += trace-event-read.o +libperf-y += trace-event-info.o +libperf-y += trace-event-scripting.o +libperf-y += trace-event.o +libperf-y += svghelper.o +libperf-y += sort.o +libperf-y += hist.o +libperf-y += util.o +libperf-y += xyarray.o +libperf-y += cpumap.o +libperf-y += cgroup.o +libperf-y += target.o +libperf-y += rblist.o +libperf-y += intlist.o +libperf-y += vdso.o +libperf-y += stat.o +libperf-y += record.o +libperf-y += srcline.o +libperf-y += data.o +libperf-y += tsc.o +libperf-y += cloexec.o +libperf-y += thread-stack.o + +libperf-$(CONFIG_LIBELF) += symbol-elf.o +libperf-$(CONFIG_LIBELF) += probe-event.o + +ifndef CONFIG_LIBELF +libperf-y += symbol-minimal.o +endif + +libperf-$(CONFIG_DWARF) += probe-finder.o +libperf-$(CONFIG_DWARF) += dwarf-aux.o + +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o +libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o + +libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o + +libperf-y += scripting-engines/ + +libperf-$(CONFIG_PERF_REGS) += perf_regs.o +libperf-$(CONFIG_ZLIB) += zlib.o + +CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" + +$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c + $(call rule_mkdir) + @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l + +$(OUTPUT)util/parse-events-bison.c: util/parse-events.y + $(call rule_mkdir) + @$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_ + +$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c + $(call rule_mkdir) + @$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l + +$(OUTPUT)util/pmu-bison.c: util/pmu.y + $(call rule_mkdir) + @$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_ + +CFLAGS_parse-events-flex.o += -w +CFLAGS_pmu-flex.o += -w +CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w +CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w + +$(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 $(OUTPUT)util/pmu-bison.c + +CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_parse-events.o += -Wno-redundant-decls + +$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 0c72680a977f..ffdc338df925 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -93,6 +93,35 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf) return raw - build_id; } +/* asnprintf consolidates asprintf and snprintf */ +static int asnprintf(char **strp, size_t size, const char *fmt, ...) +{ + va_list ap; + int ret; + + if (!strp) + return -EINVAL; + + va_start(ap, fmt); + if (*strp) + ret = vsnprintf(*strp, size, fmt, ap); + else + ret = vasprintf(strp, fmt, ap); + va_end(ap); + + return ret; +} + +static char *build_id__filename(const char *sbuild_id, char *bf, size_t size) +{ + char *tmp = bf; + int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir, + sbuild_id, sbuild_id + 2); + if (ret < 0 || (tmp && size < (unsigned int)ret)) + return NULL; + return bf; +} + char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; @@ -101,14 +130,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) return NULL; build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex); - if (bf == NULL) { - if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir, - build_id_hex, build_id_hex + 2) < 0) - return NULL; - } else - snprintf(bf, size, "%s/.build-id/%.2s/%s", buildid_dir, - build_id_hex, build_id_hex + 2); - return bf; + return build_id__filename(build_id_hex, bf, size); } #define dsos__for_each_with_build_id(pos, head) \ @@ -259,35 +281,93 @@ void disable_buildid_cache(void) no_buildid_cache = true; } -int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, - const char *name, bool is_kallsyms, bool is_vdso) +static char *build_id_cache__dirname_from_path(const char *name, + bool is_kallsyms, bool is_vdso) { - const size_t size = PATH_MAX; - char *realname, *filename = zalloc(size), - *linkname = zalloc(size), *targetname; - int len, err = -1; + char *realname = (char *)name, *filename; bool slash = is_kallsyms || is_vdso; - if (is_kallsyms) { - if (symbol_conf.kptr_restrict) { - pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); - err = 0; - goto out_free; - } - realname = (char *) name; - } else + if (!slash) { + realname = realpath(name, NULL); + if (!realname) + return NULL; + } + + if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "", + is_vdso ? DSO__NAME_VDSO : realname) < 0) + filename = NULL; + + if (!slash) + free(realname); + + return filename; +} + +int build_id_cache__list_build_ids(const char *pathname, + struct strlist **result) +{ + struct strlist *list; + char *dir_name; + DIR *dir; + struct dirent *d; + int ret = 0; + + list = strlist__new(true, NULL); + dir_name = build_id_cache__dirname_from_path(pathname, false, false); + if (!list || !dir_name) { + ret = -ENOMEM; + goto out; + } + + /* List up all dirents */ + dir = opendir(dir_name); + if (!dir) { + ret = -errno; + goto out; + } + + while ((d = readdir(dir)) != NULL) { + if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, "..")) + continue; + strlist__add(list, d->d_name); + } + closedir(dir); + +out: + free(dir_name); + if (ret) + strlist__delete(list); + else + *result = list; + + return ret; +} + +int build_id_cache__add_s(const char *sbuild_id, const char *name, + bool is_kallsyms, bool is_vdso) +{ + const size_t size = PATH_MAX; + char *realname = NULL, *filename = NULL, *dir_name = NULL, + *linkname = zalloc(size), *targetname, *tmp; + int err = -1; + + if (!is_kallsyms) { realname = realpath(name, NULL); + if (!realname) + goto out_free; + } - if (realname == NULL || filename == NULL || linkname == NULL) + dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso); + if (!dir_name) goto out_free; - len = scnprintf(filename, size, "%s%s%s", - debugdir, slash ? "/" : "", - is_vdso ? DSO__NAME_VDSO : realname); - if (mkdir_p(filename, 0755)) + if (mkdir_p(dir_name, 0755)) goto out_free; - snprintf(filename + len, size - len, "/%s", sbuild_id); + if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) { + filename = NULL; + goto out_free; + } if (access(filename, F_OK)) { if (is_kallsyms) { @@ -297,14 +377,16 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, goto out_free; } - len = scnprintf(linkname, size, "%s/.build-id/%.2s", - debugdir, sbuild_id); + if (!build_id__filename(sbuild_id, linkname, size)) + goto out_free; + tmp = strrchr(linkname, '/'); + *tmp = '\0'; if (access(linkname, X_OK) && mkdir_p(linkname, 0755)) goto out_free; - snprintf(linkname + len, size - len, "/%s", sbuild_id + 2); - targetname = filename + strlen(debugdir) - 5; + *tmp = '/'; + targetname = filename + strlen(buildid_dir) - 5; memcpy(targetname, "../..", 5); if (symlink(targetname, linkname) == 0) @@ -313,34 +395,46 @@ out_free: if (!is_kallsyms) free(realname); free(filename); + free(dir_name); free(linkname); return err; } static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, - const char *name, const char *debugdir, - bool is_kallsyms, bool is_vdso) + const char *name, bool is_kallsyms, + bool is_vdso) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; build_id__sprintf(build_id, build_id_size, sbuild_id); - return build_id_cache__add_s(sbuild_id, debugdir, name, - is_kallsyms, is_vdso); + return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso); +} + +bool build_id_cache__cached(const char *sbuild_id) +{ + bool ret = false; + char *filename = build_id__filename(sbuild_id, NULL, 0); + + if (filename && !access(filename, F_OK)) + ret = true; + free(filename); + + return ret; } -int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) +int build_id_cache__remove_s(const char *sbuild_id) { const size_t size = PATH_MAX; char *filename = zalloc(size), - *linkname = zalloc(size); + *linkname = zalloc(size), *tmp; int err = -1; if (filename == NULL || linkname == NULL) goto out_free; - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, sbuild_id + 2); + if (!build_id__filename(sbuild_id, linkname, size)) + goto out_free; if (access(linkname, F_OK)) goto out_free; @@ -354,8 +448,8 @@ int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir) /* * Since the link is relative, we must make it absolute: */ - snprintf(linkname, size, "%s/.build-id/%.2s/%s", - debugdir, sbuild_id, filename); + tmp = strrchr(linkname, '/') + 1; + snprintf(tmp, size - (tmp - linkname), "%s", filename); if (unlink(linkname)) goto out_free; @@ -367,8 +461,7 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, struct machine *machine, - const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; bool is_vdso = dso__is_vdso(dso); @@ -381,28 +474,26 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine, name = nm; } return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, - debugdir, is_kallsyms, is_vdso); + is_kallsyms, is_vdso); } static int __dsos__cache_build_ids(struct list_head *head, - struct machine *machine, const char *debugdir) + struct machine *machine) { struct dso *pos; int err = 0; dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, machine, debugdir)) + if (dso__cache_build_id(pos, machine)) err = -1; return err; } -static int machine__cache_build_ids(struct machine *machine, const char *debugdir) +static int machine__cache_build_ids(struct machine *machine) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine, - debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine, - debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine); + ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine); return ret; } @@ -417,11 +508,11 @@ int perf_session__cache_build_ids(struct perf_session *session) if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&session->machines.host, buildid_dir); + ret = machine__cache_build_ids(&session->machines.host); 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, buildid_dir); + ret |= machine__cache_build_ids(pos); } return ret ? -1 : 0; } diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 8236319514d5..85011222cc14 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -4,6 +4,7 @@ #define BUILD_ID_SIZE 20 #include "tool.h" +#include "strlist.h" #include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; @@ -22,9 +23,12 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, int fd); int perf_session__cache_build_ids(struct perf_session *session); -int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, +int build_id_cache__list_build_ids(const char *pathname, + struct strlist **result); +bool build_id_cache__cached(const char *sbuild_id); +int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); -int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); +int build_id_cache__remove_s(const char *sbuild_id); void disable_buildid_cache(void); #endif diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index d04d770d90f6..fbcca21d66ab 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -17,6 +17,7 @@ #define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH" #define DEFAULT_PERF_DIR_ENVIRONMENT ".perf" #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR" +#define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR" typedef int (*config_fn_t)(const char *, const char *, void *); extern int perf_default_config(const char *, const char *, void *); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 14e7a123d43b..9f643ee77001 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -97,6 +97,14 @@ int parse_callchain_record_opt(const char *arg) callchain_param.dump_size = size; } #endif /* HAVE_DWARF_UNWIND_SUPPORT */ + } else if (!strncmp(name, "lbr", sizeof("lbr"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + callchain_param.record_mode = CALLCHAIN_LBR; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph lbr\n"); + break; } else { pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c0ec1acc38e4..6033a0a212ca 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -11,6 +11,7 @@ enum perf_call_graph_mode { CALLCHAIN_NONE, CALLCHAIN_FP, CALLCHAIN_DWARF, + CALLCHAIN_LBR, CALLCHAIN_MAX }; diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c new file mode 100644 index 000000000000..e372e03ff480 --- /dev/null +++ b/tools/perf/util/data-convert-bt.c @@ -0,0 +1,614 @@ +/* + * CTF writing support via babeltrace. + * + * Copyright (C) 2014, Jiri Olsa <jolsa@redhat.com> + * Copyright (C) 2014, Sebastian Andrzej Siewior <bigeasy@linutronix.de> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include <linux/compiler.h> +#include <babeltrace/ctf-writer/writer.h> +#include <babeltrace/ctf-writer/clock.h> +#include <babeltrace/ctf-writer/stream.h> +#include <babeltrace/ctf-writer/event.h> +#include <babeltrace/ctf-writer/event-types.h> +#include <babeltrace/ctf-writer/event-fields.h> +#include <babeltrace/ctf/events.h> +#include <traceevent/event-parse.h> +#include "asm/bug.h" +#include "data-convert-bt.h" +#include "session.h" +#include "util.h" +#include "debug.h" +#include "tool.h" +#include "evlist.h" +#include "evsel.h" +#include "machine.h" + +#define pr_N(n, fmt, ...) \ + eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) + +#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__) +#define pr2(fmt, ...) pr_N(2, pr_fmt(fmt), ##__VA_ARGS__) + +#define pr_time2(t, fmt, ...) pr_time_N(2, debug_data_convert, t, pr_fmt(fmt), ##__VA_ARGS__) + +struct evsel_priv { + struct bt_ctf_event_class *event_class; +}; + +struct ctf_writer { + /* writer primitives */ + struct bt_ctf_writer *writer; + struct bt_ctf_stream *stream; + struct bt_ctf_stream_class *stream_class; + struct bt_ctf_clock *clock; + + /* data types */ + union { + struct { + struct bt_ctf_field_type *s64; + struct bt_ctf_field_type *u64; + struct bt_ctf_field_type *s32; + struct bt_ctf_field_type *u32; + struct bt_ctf_field_type *string; + struct bt_ctf_field_type *u64_hex; + }; + struct bt_ctf_field_type *array[6]; + } data; +}; + +struct convert { + struct perf_tool tool; + struct ctf_writer writer; + + u64 events_size; + u64 events_count; +}; + +static int value_set(struct bt_ctf_field_type *type, + struct bt_ctf_event *event, + const char *name, u64 val) +{ + struct bt_ctf_field *field; + bool sign = bt_ctf_field_type_integer_get_signed(type); + int ret; + + field = bt_ctf_field_create(type); + if (!field) { + pr_err("failed to create a field %s\n", name); + return -1; + } + + if (sign) { + ret = bt_ctf_field_signed_integer_set_value(field, val); + if (ret) { + pr_err("failed to set field value %s\n", name); + goto err; + } + } else { + ret = bt_ctf_field_unsigned_integer_set_value(field, val); + if (ret) { + pr_err("failed to set field value %s\n", name); + goto err; + } + } + + ret = bt_ctf_event_set_payload(event, name, field); + if (ret) { + pr_err("failed to set payload %s\n", name); + goto err; + } + + pr2(" SET [%s = %" PRIu64 "]\n", name, val); + +err: + bt_ctf_field_put(field); + return ret; +} + +#define __FUNC_VALUE_SET(_name, _val_type) \ +static __maybe_unused int value_set_##_name(struct ctf_writer *cw, \ + struct bt_ctf_event *event, \ + const char *name, \ + _val_type val) \ +{ \ + struct bt_ctf_field_type *type = cw->data._name; \ + return value_set(type, event, name, (u64) val); \ +} + +#define FUNC_VALUE_SET(_name) __FUNC_VALUE_SET(_name, _name) + +FUNC_VALUE_SET(s32) +FUNC_VALUE_SET(u32) +FUNC_VALUE_SET(s64) +FUNC_VALUE_SET(u64) +__FUNC_VALUE_SET(u64_hex, u64) + +static int add_generic_values(struct ctf_writer *cw, + struct bt_ctf_event *event, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + u64 type = evsel->attr.sample_type; + int ret; + + /* + * missing: + * PERF_SAMPLE_TIME - not needed as we have it in + * ctf event header + * PERF_SAMPLE_READ - TODO + * PERF_SAMPLE_CALLCHAIN - TODO + * PERF_SAMPLE_RAW - tracepoint fields are handled separately + * PERF_SAMPLE_BRANCH_STACK - TODO + * PERF_SAMPLE_REGS_USER - TODO + * PERF_SAMPLE_STACK_USER - TODO + */ + + if (type & PERF_SAMPLE_IP) { + ret = value_set_u64_hex(cw, event, "perf_ip", sample->ip); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_TID) { + ret = value_set_s32(cw, event, "perf_tid", sample->tid); + if (ret) + return -1; + + ret = value_set_s32(cw, event, "perf_pid", sample->pid); + if (ret) + return -1; + } + + if ((type & PERF_SAMPLE_ID) || + (type & PERF_SAMPLE_IDENTIFIER)) { + ret = value_set_u64(cw, event, "perf_id", sample->id); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + ret = value_set_u64(cw, event, "perf_stream_id", sample->stream_id); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_CPU) { + ret = value_set_u32(cw, event, "perf_cpu", sample->cpu); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_PERIOD) { + ret = value_set_u64(cw, event, "perf_period", sample->period); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_WEIGHT) { + ret = value_set_u64(cw, event, "perf_weight", sample->weight); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_DATA_SRC) { + ret = value_set_u64(cw, event, "perf_data_src", + sample->data_src); + if (ret) + return -1; + } + + if (type & PERF_SAMPLE_TRANSACTION) { + ret = value_set_u64(cw, event, "perf_transaction", + sample->transaction); + if (ret) + return -1; + } + + return 0; +} + +static int process_sample_event(struct perf_tool *tool, + union perf_event *_event __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine __maybe_unused) +{ + struct convert *c = container_of(tool, struct convert, tool); + struct evsel_priv *priv = evsel->priv; + struct ctf_writer *cw = &c->writer; + struct bt_ctf_event_class *event_class; + struct bt_ctf_event *event; + int ret; + + if (WARN_ONCE(!priv, "Failed to setup all events.\n")) + return 0; + + event_class = priv->event_class; + + /* update stats */ + c->events_count++; + c->events_size += _event->header.size; + + pr_time2(sample->time, "sample %" PRIu64 "\n", c->events_count); + + event = bt_ctf_event_create(event_class); + if (!event) { + pr_err("Failed to create an CTF event\n"); + return -1; + } + + bt_ctf_clock_set_time(cw->clock, sample->time); + + ret = add_generic_values(cw, event, evsel, sample); + if (ret) + return -1; + + bt_ctf_stream_append_event(cw->stream, event); + bt_ctf_event_put(event); + return 0; +} + +static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, + struct bt_ctf_event_class *event_class) +{ + u64 type = evsel->attr.sample_type; + + /* + * missing: + * PERF_SAMPLE_TIME - not needed as we have it in + * ctf event header + * PERF_SAMPLE_READ - TODO + * PERF_SAMPLE_CALLCHAIN - TODO + * PERF_SAMPLE_RAW - tracepoint fields are handled separately + * PERF_SAMPLE_BRANCH_STACK - TODO + * PERF_SAMPLE_REGS_USER - TODO + * PERF_SAMPLE_STACK_USER - TODO + */ + +#define ADD_FIELD(cl, t, n) \ + do { \ + pr2(" field '%s'\n", n); \ + if (bt_ctf_event_class_add_field(cl, t, n)) { \ + pr_err("Failed to add field '%s;\n", n); \ + return -1; \ + } \ + } while (0) + + if (type & PERF_SAMPLE_IP) + ADD_FIELD(event_class, cw->data.u64_hex, "perf_ip"); + + if (type & PERF_SAMPLE_TID) { + ADD_FIELD(event_class, cw->data.s32, "perf_tid"); + ADD_FIELD(event_class, cw->data.s32, "perf_pid"); + } + + if ((type & PERF_SAMPLE_ID) || + (type & PERF_SAMPLE_IDENTIFIER)) + ADD_FIELD(event_class, cw->data.u64, "perf_id"); + + if (type & PERF_SAMPLE_STREAM_ID) + ADD_FIELD(event_class, cw->data.u64, "perf_stream_id"); + + if (type & PERF_SAMPLE_CPU) + ADD_FIELD(event_class, cw->data.u32, "perf_cpu"); + + if (type & PERF_SAMPLE_PERIOD) + ADD_FIELD(event_class, cw->data.u64, "perf_period"); + + if (type & PERF_SAMPLE_WEIGHT) + ADD_FIELD(event_class, cw->data.u64, "perf_weight"); + + if (type & PERF_SAMPLE_DATA_SRC) + ADD_FIELD(event_class, cw->data.u64, "perf_data_src"); + + if (type & PERF_SAMPLE_TRANSACTION) + ADD_FIELD(event_class, cw->data.u64, "perf_transaction"); + +#undef ADD_FIELD + return 0; +} + +static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel) +{ + struct bt_ctf_event_class *event_class; + struct evsel_priv *priv; + const char *name = perf_evsel__name(evsel); + int ret; + + pr("Adding event '%s' (type %d)\n", name, evsel->attr.type); + + event_class = bt_ctf_event_class_create(name); + if (!event_class) + return -1; + + ret = add_generic_types(cw, evsel, event_class); + if (ret) + goto err; + + ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class); + if (ret) { + pr("Failed to add event class into stream.\n"); + goto err; + } + + priv = malloc(sizeof(*priv)); + if (!priv) + goto err; + + priv->event_class = event_class; + evsel->priv = priv; + return 0; + +err: + bt_ctf_event_class_put(event_class); + pr_err("Failed to add event '%s'.\n", name); + return -1; +} + +static int setup_events(struct ctf_writer *cw, struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_evsel *evsel; + int ret; + + evlist__for_each(evlist, evsel) { + ret = add_event(cw, evsel); + if (ret) + return ret; + } + return 0; +} + +static int ctf_writer__setup_env(struct ctf_writer *cw, + struct perf_session *session) +{ + struct perf_header *header = &session->header; + struct bt_ctf_writer *writer = cw->writer; + +#define ADD(__n, __v) \ +do { \ + if (bt_ctf_writer_add_environment_field(writer, __n, __v)) \ + return -1; \ +} while (0) + + ADD("host", header->env.hostname); + ADD("sysname", "Linux"); + ADD("release", header->env.os_release); + ADD("version", header->env.version); + ADD("machine", header->env.arch); + ADD("domain", "kernel"); + ADD("tracer_name", "perf"); + +#undef ADD + return 0; +} + +static int ctf_writer__setup_clock(struct ctf_writer *cw) +{ + struct bt_ctf_clock *clock = cw->clock; + + bt_ctf_clock_set_description(clock, "perf clock"); + +#define SET(__n, __v) \ +do { \ + if (bt_ctf_clock_set_##__n(clock, __v)) \ + return -1; \ +} while (0) + + SET(frequency, 1000000000); + SET(offset_s, 0); + SET(offset, 0); + SET(precision, 10); + SET(is_absolute, 0); + +#undef SET + return 0; +} + +static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex) +{ + struct bt_ctf_field_type *type; + + type = bt_ctf_field_type_integer_create(size); + if (!type) + return NULL; + + if (sign && + bt_ctf_field_type_integer_set_signed(type, 1)) + goto err; + + if (hex && + bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL)) + goto err; + + pr2("Created type: INTEGER %d-bit %ssigned %s\n", + size, sign ? "un" : "", hex ? "hex" : ""); + return type; + +err: + bt_ctf_field_type_put(type); + return NULL; +} + +static void ctf_writer__cleanup_data(struct ctf_writer *cw) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(cw->data.array); i++) + bt_ctf_field_type_put(cw->data.array[i]); +} + +static int ctf_writer__init_data(struct ctf_writer *cw) +{ +#define CREATE_INT_TYPE(type, size, sign, hex) \ +do { \ + (type) = create_int_type(size, sign, hex); \ + if (!(type)) \ + goto err; \ +} while (0) + + CREATE_INT_TYPE(cw->data.s64, 64, true, false); + CREATE_INT_TYPE(cw->data.u64, 64, false, false); + CREATE_INT_TYPE(cw->data.s32, 32, true, false); + CREATE_INT_TYPE(cw->data.u32, 32, false, false); + CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true); + + cw->data.string = bt_ctf_field_type_string_create(); + if (cw->data.string) + return 0; + +err: + ctf_writer__cleanup_data(cw); + pr_err("Failed to create data types.\n"); + return -1; +} + +static void ctf_writer__cleanup(struct ctf_writer *cw) +{ + ctf_writer__cleanup_data(cw); + + bt_ctf_clock_put(cw->clock); + bt_ctf_stream_put(cw->stream); + bt_ctf_stream_class_put(cw->stream_class); + bt_ctf_writer_put(cw->writer); + + /* and NULL all the pointers */ + memset(cw, 0, sizeof(*cw)); +} + +static int ctf_writer__init(struct ctf_writer *cw, const char *path) +{ + struct bt_ctf_writer *writer; + struct bt_ctf_stream_class *stream_class; + struct bt_ctf_stream *stream; + struct bt_ctf_clock *clock; + + /* CTF writer */ + writer = bt_ctf_writer_create(path); + if (!writer) + goto err; + + cw->writer = writer; + + /* CTF clock */ + clock = bt_ctf_clock_create("perf_clock"); + if (!clock) { + pr("Failed to create CTF clock.\n"); + goto err_cleanup; + } + + cw->clock = clock; + + if (ctf_writer__setup_clock(cw)) { + pr("Failed to setup CTF clock.\n"); + goto err_cleanup; + } + + /* CTF stream class */ + stream_class = bt_ctf_stream_class_create("perf_stream"); + if (!stream_class) { + pr("Failed to create CTF stream class.\n"); + goto err_cleanup; + } + + cw->stream_class = stream_class; + + /* CTF clock stream setup */ + if (bt_ctf_stream_class_set_clock(stream_class, clock)) { + pr("Failed to assign CTF clock to stream class.\n"); + goto err_cleanup; + } + + if (ctf_writer__init_data(cw)) + goto err_cleanup; + + /* CTF stream instance */ + stream = bt_ctf_writer_create_stream(writer, stream_class); + if (!stream) { + pr("Failed to create CTF stream.\n"); + goto err_cleanup; + } + + cw->stream = stream; + + /* CTF clock writer setup */ + if (bt_ctf_writer_add_clock(writer, clock)) { + pr("Failed to assign CTF clock to writer.\n"); + goto err_cleanup; + } + + return 0; + +err_cleanup: + ctf_writer__cleanup(cw); +err: + pr_err("Failed to setup CTF writer.\n"); + return -1; +} + +int bt_convert__perf2ctf(const char *input, const char *path) +{ + struct perf_session *session; + struct perf_data_file file = { + .path = input, + .mode = PERF_DATA_MODE_READ, + }; + struct convert c = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + .comm = perf_event__process_comm, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, + .lost = perf_event__process_lost, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .ordered_events = true, + .ordering_requires_timestamps = true, + }, + }; + struct ctf_writer *cw = &c.writer; + int err = -1; + + /* CTF writer */ + if (ctf_writer__init(cw, path)) + return -1; + + /* perf.data session */ + session = perf_session__new(&file, 0, NULL); + if (!session) + goto free_writer; + + /* CTF writer env/clock setup */ + if (ctf_writer__setup_env(cw, session)) + goto free_session; + + /* CTF events setup */ + if (setup_events(cw, session)) + goto free_session; + + err = perf_session__process_events(session, &c.tool); + if (!err) + err = bt_ctf_stream_flush(cw->stream); + + fprintf(stderr, + "[ perf data convert: Converted '%s' into CTF data '%s' ]\n", + file.path, path); + + fprintf(stderr, + "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n", + (double) c.events_size / 1024.0 / 1024.0, + c.events_count); + + /* its all good */ +free_session: + perf_session__delete(session); + +free_writer: + ctf_writer__cleanup(cw); + return err; +} diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h new file mode 100644 index 000000000000..dda30c5d0792 --- /dev/null +++ b/tools/perf/util/data-convert-bt.h @@ -0,0 +1,8 @@ +#ifndef __DATA_CONVERT_BT_H +#define __DATA_CONVERT_BT_H +#ifdef HAVE_LIBBABELTRACE_SUPPORT + +int bt_convert__perf2ctf(const char *input_name, const char *to_ctf); + +#endif /* HAVE_LIBBABELTRACE_SUPPORT */ +#endif /* __DATA_CONVERT_BT_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index ad60b2f20258..2da5581ec74d 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -20,6 +20,7 @@ int verbose; bool dump_trace = false, quiet = false; int debug_ordered_events; static int redirect_to_stderr; +int debug_data_convert; static int _eprintf(int level, int var, const char *fmt, va_list args) { @@ -147,6 +148,7 @@ static struct debug_variable { { .name = "verbose", .ptr = &verbose }, { .name = "ordered-events", .ptr = &debug_ordered_events}, { .name = "stderr", .ptr = &redirect_to_stderr}, + { .name = "data-convert", .ptr = &debug_data_convert }, { .name = NULL, } }; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index be264d6f3b30..caac2fdc6105 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -12,6 +12,7 @@ extern int verbose; extern bool quiet, dump_trace; extern int debug_ordered_events; +extern int debug_data_convert; #ifndef pr_fmt #define pr_fmt(fmt) fmt diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index c2f7d3b90966..814554d1b857 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -45,13 +45,13 @@ int dso__read_binary_type_filename(const struct dso *dso, case DSO_BINARY_TYPE__DEBUGLINK: { char *debuglink; - strncpy(filename, dso->long_name, size); - debuglink = filename + dso->long_name_len; + len = __symbol__join_symfs(filename, size, dso->long_name); + debuglink = filename + len; while (debuglink != filename && *debuglink != '/') debuglink--; if (*debuglink == '/') debuglink++; - ret = filename__read_debuglink(dso->long_name, debuglink, + ret = filename__read_debuglink(filename, debuglink, size - (debuglink - filename)); } break; @@ -240,7 +240,7 @@ static int do_open(char *name) if (fd >= 0) return fd; - pr_debug("dso open failed, mmap: %s\n", + pr_debug("dso open failed: %s\n", strerror_r(errno, sbuf, sizeof(sbuf))); if (!dso__data_open_cnt || errno != EMFILE) break; diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index cc66c4049e09..780b2bc11128 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -278,6 +278,21 @@ bool die_is_func_def(Dwarf_Die *dw_die) } /** + * die_is_func_instance - Ensure that this DIE is an instance of a subprogram + * @dw_die: a DIE + * + * Ensure that this DIE is an instance (which has an entry address). + * This returns true if @dw_die is a function instance. If not, you need to + * call die_walk_instances() to find actual instances. + **/ +bool die_is_func_instance(Dwarf_Die *dw_die) +{ + Dwarf_Addr tmp; + + /* Actually gcc optimizes non-inline as like as inlined */ + return !dwarf_func_inline(dw_die) && dwarf_entrypc(dw_die, &tmp) == 0; +} +/** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure * @offs: The offset of the member in the data structure diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index b4fe90c6cb2d..af7dbcd5f929 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -41,6 +41,9 @@ extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, /* Ensure that this DIE is a subprogram and definition (not declaration) */ extern bool die_is_func_def(Dwarf_Die *dw_die); +/* Ensure that this DIE is an instance of a subprogram */ +extern bool die_is_func_instance(Dwarf_Die *dw_die); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 6c6d044e959a..9e806d855b04 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -615,7 +615,7 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) else s = ""; - return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid); + return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid); } int perf_event__process_comm(struct perf_tool *tool __maybe_unused, diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 28b8ce86bf12..8d0b62361129 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -7,7 +7,6 @@ * Released under the GPL v2. (and only v2, not any later version) */ #include "util.h" -#include <api/fs/debugfs.h> #include <api/fs/fs.h> #include <poll.h> #include "cpumap.h" @@ -1086,6 +1085,38 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) return err; } +int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids) +{ + char *filter; + int ret = -1; + size_t i; + + for (i = 0; i < npids; ++i) { + if (i == 0) { + if (asprintf(&filter, "common_pid != %d", pids[i]) < 0) + return -1; + } else { + char *tmp; + + if (asprintf(&tmp, "%s && common_pid != %d", filter, pids[i]) < 0) + goto out_free; + + free(filter); + filter = tmp; + } + } + + ret = perf_evlist__set_filter(evlist, filter); +out_free: + free(filter); + return ret; +} + +int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid) +{ + return perf_evlist__set_filter_pids(evlist, 1, &pid); +} + bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) { struct perf_evsel *pos; @@ -1329,7 +1360,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar * writing exactly one byte, in workload.cork_fd, usually via * perf_evlist__start_workload(). * - * For cancelling the workload without actuallin running it, + * For cancelling the workload without actually running it, * the parent will just close workload.cork_fd, without writing * anything, i.e. read will return zero and we just exit() * here. diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index e99a67632831..f07c984465f0 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -51,6 +51,7 @@ struct perf_evlist { struct thread_map *threads; struct cpu_map *cpus; struct perf_evsel *selected; + struct events_stats stats; }; struct perf_evsel_str_handler { @@ -77,6 +78,8 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); +int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid); +int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids); struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ea51a90e20a0..bb4eff28869e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -537,13 +537,30 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) } static void -perf_evsel__config_callgraph(struct perf_evsel *evsel) +perf_evsel__config_callgraph(struct perf_evsel *evsel, + struct record_opts *opts) { bool function = perf_evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->attr; perf_evsel__set_sample_bit(evsel, CALLCHAIN); + if (callchain_param.record_mode == CALLCHAIN_LBR) { + if (!opts->branch_stack) { + if (attr->exclude_user) { + pr_warning("LBR callstack option is only available " + "to get user callchain information. " + "Falling back to framepointers.\n"); + } else { + perf_evsel__set_sample_bit(evsel, BRANCH_STACK); + attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_CALL_STACK; + } + } else + pr_warning("Cannot use LBR callstack with branch stack. " + "Falling back to framepointers.\n"); + } + if (callchain_param.record_mode == CALLCHAIN_DWARF) { if (!function) { perf_evsel__set_sample_bit(evsel, REGS_USER); @@ -667,7 +684,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) evsel->attr.exclude_callchain_user = 1; if (callchain_param.enabled && !evsel->no_aux_samples) - perf_evsel__config_callgraph(evsel); + perf_evsel__config_callgraph(evsel, opts); if (opts->sample_intr_regs) { attr->sample_regs_intr = PERF_REGS_MASK; @@ -717,6 +734,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->sample_transaction) perf_evsel__set_sample_bit(evsel, TRANSACTION); + if (opts->running_time) { + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + } + /* * XXX see the function comment above * diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 38622747d130..dcf202aebe9f 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -355,4 +355,8 @@ 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)) +static inline bool has_branch_callstack(struct perf_evsel *evsel) +{ + return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; +} #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 1bca3a9f2b16..9e0f60a7e7b3 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1502,18 +1502,100 @@ static int remove_loops(struct branch_entry *l, int nr) return nr; } -static int thread__resolve_callchain_sample(struct thread *thread, - struct ip_callchain *chain, - struct branch_stack *branch, - struct symbol **parent, - struct addr_location *root_al, - int max_stack) +/* + * Recolve LBR callstack chain sample + * Return: + * 1 on success get LBR callchain information + * 0 no available LBR callchain information, should try fp + * negative error code on other errors. + */ +static int resolve_lbr_callchain_sample(struct thread *thread, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { + struct ip_callchain *chain = sample->callchain; + int chain_nr = min(max_stack, (int)chain->nr); + int i, j, err; + u64 ip; + + for (i = 0; i < chain_nr; i++) { + if (chain->ips[i] == PERF_CONTEXT_USER) + break; + } + + /* LBR only affects the user callchain */ + if (i != chain_nr) { + struct branch_stack *lbr_stack = sample->branch_stack; + int lbr_nr = lbr_stack->nr; + /* + * LBR callstack can only get user call chain. + * The mix_chain_nr is kernel call chain + * number plus LBR user call chain number. + * i is kernel call chain number, + * 1 is PERF_CONTEXT_USER, + * lbr_nr + 1 is the user call chain number. + * For details, please refer to the comments + * in callchain__printf + */ + int mix_chain_nr = i + 1 + lbr_nr + 1; + + if (mix_chain_nr > PERF_MAX_STACK_DEPTH + PERF_MAX_BRANCH_DEPTH) { + pr_warning("corrupted callchain. skipping...\n"); + return 0; + } + + for (j = 0; j < mix_chain_nr; j++) { + if (callchain_param.order == ORDER_CALLEE) { + if (j < i + 1) + ip = chain->ips[j]; + else if (j > i + 1) + ip = lbr_stack->entries[j - i - 2].from; + else + ip = lbr_stack->entries[0].to; + } else { + if (j < lbr_nr) + ip = lbr_stack->entries[lbr_nr - j - 1].from; + else if (j > lbr_nr) + ip = chain->ips[i + 1 - (j - lbr_nr)]; + else + ip = lbr_stack->entries[0].to; + } + + err = add_callchain_ip(thread, parent, root_al, false, ip); + if (err) + return (err < 0) ? err : 0; + } + return 1; + } + + return 0; +} + +static int thread__resolve_callchain_sample(struct thread *thread, + struct perf_evsel *evsel, + struct perf_sample *sample, + struct symbol **parent, + struct addr_location *root_al, + int max_stack) +{ + struct branch_stack *branch = sample->branch_stack; + struct ip_callchain *chain = sample->callchain; int chain_nr = min(max_stack, (int)chain->nr); int i, j, err; int skip_idx = -1; int first_call = 0; + callchain_cursor_reset(&callchain_cursor); + + if (has_branch_callstack(evsel)) { + err = resolve_lbr_callchain_sample(thread, sample, parent, + root_al, max_stack); + if (err) + return (err < 0) ? err : 0; + } + /* * Based on DWARF debug information, some architectures skip * a callchain entry saved by the kernel. @@ -1521,8 +1603,6 @@ static int thread__resolve_callchain_sample(struct thread *thread, if (chain->nr < PERF_MAX_STACK_DEPTH) skip_idx = arch_skip_callchain_idx(thread, chain); - callchain_cursor_reset(&callchain_cursor); - /* * Add branches to call stack for easier browsing. This gives * more context for a sample than just the callers. @@ -1623,9 +1703,9 @@ int thread__resolve_callchain(struct thread *thread, struct addr_location *root_al, int max_stack) { - int ret = thread__resolve_callchain_sample(thread, sample->callchain, - sample->branch_stack, - parent, root_al, max_stack); + int ret = thread__resolve_callchain_sample(thread, evsel, + sample, parent, + root_al, max_stack); if (ret) return ret; diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index fd4be94125fb..077ddd25189f 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -166,7 +166,7 @@ static int __ordered_events__flush(struct perf_session *s, struct ui_progress prog; int ret; - if (!tool->ordered_events || !limit) + if (!limit) return 0; if (show_progress) @@ -216,6 +216,9 @@ int ordered_events__flush(struct perf_session *s, struct perf_tool *tool, }; int err; + if (oe->nr_events == 0) + return 0; + switch (how) { case OE_FLUSH__FINAL: oe->next_flush = ULLONG_MAX; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 7f8ec6ce2823..fe07573d5ed4 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -20,11 +20,6 @@ #define MAX_NAME_LEN 100 -struct event_symbol { - const char *symbol; - const char *alias; -}; - #ifdef PARSER_DEBUG extern int parse_events_debug; #endif @@ -39,7 +34,7 @@ static struct perf_pmu_event_symbol *perf_pmu_events_list; */ static int perf_pmu_events_list_num; -static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { +struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { .symbol = "cpu-cycles", .alias = "cycles", @@ -82,7 +77,7 @@ static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { }, }; -static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { +struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { [PERF_COUNT_SW_CPU_CLOCK] = { .symbol = "cpu-clock", .alias = "", @@ -175,9 +170,6 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(tracing_events_path)) - return NULL; - sys_dir = opendir(tracing_events_path); if (!sys_dir) return NULL; @@ -473,12 +465,6 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, int parse_events_add_tracepoint(struct list_head *list, int *idx, char *sys, char *event) { - int ret; - - ret = debugfs_valid_mountpoint(tracing_events_path); - if (ret) - return ret; - if (strpbrk(sys, "*?")) return add_tracepoint_multi_sys(list, idx, sys, event); else @@ -1098,6 +1084,14 @@ static const char * const event_type_descriptors[] = { "Hardware breakpoint", }; +static int cmp_string(const void *a, const void *b) +{ + const char * const *as = a; + const char * const *bs = b; + + return strcmp(*as, *bs); +} + /* * Print the events from <debugfs_mount_point>/tracing/events */ @@ -1109,18 +1103,21 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - char sbuf[STRERR_BUFSIZE]; - - if (debugfs_valid_mountpoint(tracing_events_path)) { - printf(" [ Tracepoints not available: %s ]\n", - strerror_r(errno, sbuf, sizeof(sbuf))); - return; - } + char **evt_list = NULL; + unsigned int evt_i = 0, evt_num = 0; + bool evt_num_known = false; +restart: sys_dir = opendir(tracing_events_path); if (!sys_dir) return; + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_close_sys_dir; + } + for_each_subsystem(sys_dir, sys_dirent, sys_next) { if (subsys_glob != NULL && !strglobmatch(sys_dirent.d_name, subsys_glob)) @@ -1137,19 +1134,56 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, !strglobmatch(evt_dirent.d_name, event_glob)) continue; - if (name_only) { - printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name); + if (!evt_num_known) { + evt_num++; continue; } snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); - printf(" %-50s [%s]\n", evt_path, - event_type_descriptors[PERF_TYPE_TRACEPOINT]); + + evt_list[evt_i] = strdup(evt_path); + if (evt_list[evt_i] == NULL) + goto out_close_evt_dir; + evt_i++; } closedir(evt_dir); } closedir(sys_dir); + + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], + event_type_descriptors[PERF_TYPE_TRACEPOINT]); + } + if (evt_num) + printf("\n"); + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return; + +out_close_evt_dir: + closedir(evt_dir); +out_close_sys_dir: + closedir(sys_dir); + + printf("FATAL: not enough memory to print %s\n", + event_type_descriptors[PERF_TYPE_TRACEPOINT]); + if (evt_list) + goto out_free; } /* @@ -1163,9 +1197,6 @@ int is_valid_tracepoint(const char *event_string) char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(tracing_events_path)) - return 0; - sys_dir = opendir(tracing_events_path); if (!sys_dir) return 0; @@ -1233,38 +1264,19 @@ static bool is_event_supported(u8 type, unsigned config) return ret; } -static void __print_events_type(u8 type, struct event_symbol *syms, - unsigned max) -{ - char name[64]; - unsigned i; - - for (i = 0; i < max ; i++, syms++) { - if (!is_event_supported(type, i)) - continue; - - if (strlen(syms->alias)) - snprintf(name, sizeof(name), "%s OR %s", - syms->symbol, syms->alias); - else - snprintf(name, sizeof(name), "%s", syms->symbol); - - printf(" %-50s [%s]\n", name, event_type_descriptors[type]); - } -} - -void print_events_type(u8 type) -{ - if (type == PERF_TYPE_SOFTWARE) - __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX); - else - __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX); -} - int print_hwcache_events(const char *event_glob, bool name_only) { - unsigned int type, op, i, printed = 0; + unsigned int type, op, i, evt_i = 0, evt_num = 0; char name[64]; + char **evt_list = NULL; + bool evt_num_known = false; + +restart: + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_enomem; + } for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { @@ -1282,27 +1294,66 @@ int print_hwcache_events(const char *event_glob, bool name_only) type | (op << 8) | (i << 16))) continue; - if (name_only) - printf("%s ", name); - else - printf(" %-50s [%s]\n", name, - event_type_descriptors[PERF_TYPE_HW_CACHE]); - ++printed; + if (!evt_num_known) { + evt_num++; + continue; + } + + evt_list[evt_i] = strdup(name); + if (evt_list[evt_i] == NULL) + goto out_enomem; + evt_i++; } } } - if (printed) + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], + event_type_descriptors[PERF_TYPE_HW_CACHE]); + } + if (evt_num) printf("\n"); - return printed; + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return evt_num; + +out_enomem: + printf("FATAL: not enough memory to print %s\n", event_type_descriptors[PERF_TYPE_HW_CACHE]); + if (evt_list) + goto out_free; + return evt_num; } -static void print_symbol_events(const char *event_glob, unsigned type, +void print_symbol_events(const char *event_glob, unsigned type, struct event_symbol *syms, unsigned max, bool name_only) { - unsigned i, printed = 0; + unsigned int i, evt_i = 0, evt_num = 0; char name[MAX_NAME_LEN]; + char **evt_list = NULL; + bool evt_num_known = false; + +restart: + if (evt_num_known) { + evt_list = zalloc(sizeof(char *) * evt_num); + if (!evt_list) + goto out_enomem; + syms -= max; + } for (i = 0; i < max; i++, syms++) { @@ -1314,23 +1365,49 @@ static void print_symbol_events(const char *event_glob, unsigned type, if (!is_event_supported(type, i)) continue; - if (name_only) { - printf("%s ", syms->symbol); + if (!evt_num_known) { + evt_num++; continue; } - if (strlen(syms->alias)) + if (!name_only && strlen(syms->alias)) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else strncpy(name, syms->symbol, MAX_NAME_LEN); - printf(" %-50s [%s]\n", name, event_type_descriptors[type]); - - printed++; + evt_list[evt_i] = strdup(name); + if (evt_list[evt_i] == NULL) + goto out_enomem; + evt_i++; } - if (printed) + if (!evt_num_known) { + evt_num_known = true; + goto restart; + } + qsort(evt_list, evt_num, sizeof(char *), cmp_string); + evt_i = 0; + while (evt_i < evt_num) { + if (name_only) { + printf("%s ", evt_list[evt_i++]); + continue; + } + printf(" %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]); + } + if (evt_num) printf("\n"); + +out_free: + evt_num = evt_i; + for (evt_i = 0; evt_i < evt_num; evt_i++) + zfree(&evt_list[evt_i]); + zfree(&evt_list); + return; + +out_enomem: + printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]); + if (evt_list) + goto out_free; } /* @@ -1338,11 +1415,6 @@ static void print_symbol_events(const char *event_glob, unsigned type, */ void print_events(const char *event_glob, bool name_only) { - if (!name_only) { - printf("\n"); - printf("List of pre-defined events (to be used in -e):\n"); - } - print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index ff6e1fa4111e..52a2dda4f954 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -116,12 +116,21 @@ void parse_events_update_lists(struct list_head *list_event, void parse_events_error(void *data, void *scanner, char const *msg); void print_events(const char *event_glob, bool name_only); -void print_events_type(u8 type); + +struct event_symbol { + const char *symbol; + const char *alias; +}; +extern struct event_symbol event_symbols_hw[]; +extern struct event_symbol event_symbols_sw[]; +void print_symbol_events(const char *event_glob, unsigned type, + struct event_symbol *syms, unsigned max, + bool name_only); void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only); int print_hwcache_events(const char *event_glob, bool name_only); extern int is_valid_tracepoint(const char *event_string); -extern int valid_debugfs_mount(const char *debugfs); +int valid_event_mount(const char *eventfs); #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 4a015f77e2b5..1457d6639b60 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -505,13 +505,18 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o break; case PARSE_OPT_LIST_OPTS: while (options->type != OPTION_END) { - printf("--%s ", options->long_name); + if (options->long_name) + printf("--%s ", options->long_name); options++; } + putchar('\n'); exit(130); case PARSE_OPT_LIST_SUBCMDS: - for (int i = 0; subcommands[i]; i++) - printf("%s ", subcommands[i]); + if (subcommands) { + for (int i = 0; subcommands[i]; i++) + printf("%s ", subcommands[i]); + } + putchar('\n'); exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 919937eb0be2..7c0e765fa2e3 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -41,6 +41,7 @@ #include "symbol.h" #include "thread.h" #include <api/fs/debugfs.h> +#include <api/fs/tracefs.h> #include "trace-event.h" /* For __maybe_unused */ #include "probe-event.h" #include "probe-finder.h" @@ -150,7 +151,7 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc) sym = __find_kernel_function_by_name(name, &map); if (sym) return map->unmap_ip(map, sym->start) - - (reloc) ? 0 : map->reloc; + ((reloc) ? 0 : map->reloc); } return 0; } @@ -532,7 +533,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir, else { if (access(raw_path, R_OK) == 0) { *new_path = strdup(raw_path); - return 0; + return *new_path ? 0 : -ENOMEM; } else return -errno; } @@ -548,9 +549,11 @@ static int get_real_path(const char *raw_path, const char *comp_dir, if (access(*new_path, R_OK) == 0) return 0; - if (!symbol_conf.source_prefix) + if (!symbol_conf.source_prefix) { /* In case of searching comp_dir, don't retry */ + zfree(new_path); return -errno; + } switch (errno) { case ENAMETOOLONG: @@ -1805,7 +1808,7 @@ static void print_open_warning(int err, bool is_kprobe) " - please rebuild kernel with %s.\n", is_kprobe ? 'k' : 'u', config); } else if (err == -ENOTSUP) - pr_warning("Debugfs is not mounted.\n"); + pr_warning("Tracefs or debugfs is not mounted.\n"); else pr_warning("Failed to open %cprobe_events: %s\n", is_kprobe ? 'k' : 'u', @@ -1816,7 +1819,7 @@ static void print_both_open_warning(int kerr, int uerr) { /* Both kprobes and uprobes are disabled, warn it. */ if (kerr == -ENOTSUP && uerr == -ENOTSUP) - pr_warning("Debugfs is not mounted.\n"); + pr_warning("Tracefs or debugfs is not mounted.\n"); else if (kerr == -ENOENT && uerr == -ENOENT) pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS " "or/and CONFIG_UPROBE_EVENTS.\n"); @@ -1833,13 +1836,20 @@ static int open_probe_events(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; const char *__debugfs; + const char *tracing_dir = ""; int ret; - __debugfs = debugfs_find_mountpoint(); - if (__debugfs == NULL) - return -ENOTSUP; + __debugfs = tracefs_find_mountpoint(); + if (__debugfs == NULL) { + tracing_dir = "tracing/"; - ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file); + __debugfs = debugfs_find_mountpoint(); + if (__debugfs == NULL) + return -ENOTSUP; + } + + ret = e_snprintf(buf, PATH_MAX, "%s/%s%s", + __debugfs, tracing_dir, trace_file); if (ret >= 0) { pr_debug("Opening %s write=%d\n", buf, readwrite); if (readwrite && !probe_event_dry_run) @@ -1855,12 +1865,12 @@ static int open_probe_events(const char *trace_file, bool readwrite) static int open_kprobe_events(bool readwrite) { - return open_probe_events("tracing/kprobe_events", readwrite); + return open_probe_events("kprobe_events", readwrite); } static int open_uprobe_events(bool readwrite) { - return open_probe_events("tracing/uprobe_events", readwrite); + return open_probe_events("uprobe_events", readwrite); } /* Get raw string list of current kprobe_events or uprobe_events */ @@ -1895,6 +1905,95 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) return sl; } +struct kprobe_blacklist_node { + struct list_head list; + unsigned long start; + unsigned long end; + char *symbol; +}; + +static void kprobe_blacklist__delete(struct list_head *blacklist) +{ + struct kprobe_blacklist_node *node; + + while (!list_empty(blacklist)) { + node = list_first_entry(blacklist, + struct kprobe_blacklist_node, list); + list_del(&node->list); + free(node->symbol); + free(node); + } +} + +static int kprobe_blacklist__load(struct list_head *blacklist) +{ + struct kprobe_blacklist_node *node; + const char *__debugfs = debugfs_find_mountpoint(); + char buf[PATH_MAX], *p; + FILE *fp; + int ret; + + if (__debugfs == NULL) + return -ENOTSUP; + + ret = e_snprintf(buf, PATH_MAX, "%s/kprobes/blacklist", __debugfs); + if (ret < 0) + return ret; + + fp = fopen(buf, "r"); + if (!fp) + return -errno; + + ret = 0; + while (fgets(buf, PATH_MAX, fp)) { + node = zalloc(sizeof(*node)); + if (!node) { + ret = -ENOMEM; + break; + } + INIT_LIST_HEAD(&node->list); + list_add_tail(&node->list, blacklist); + if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) { + ret = -EINVAL; + break; + } + p = strchr(buf, '\t'); + if (p) { + p++; + if (p[strlen(p) - 1] == '\n') + p[strlen(p) - 1] = '\0'; + } else + p = (char *)"unknown"; + node->symbol = strdup(p); + if (!node->symbol) { + ret = -ENOMEM; + break; + } + pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n", + node->start, node->end, node->symbol); + ret++; + } + if (ret < 0) + kprobe_blacklist__delete(blacklist); + fclose(fp); + + return ret; +} + +static struct kprobe_blacklist_node * +kprobe_blacklist__find_by_address(struct list_head *blacklist, + unsigned long address) +{ + struct kprobe_blacklist_node *node; + + list_for_each_entry(node, blacklist, list) { + if (node->start <= address && address <= node->end) + return node; + } + + return NULL; +} + /* Show an event */ static int show_perf_probe_event(struct perf_probe_event *pev, const char *module) @@ -2109,6 +2208,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, char buf[64]; const char *event, *group; struct strlist *namelist; + LIST_HEAD(blacklist); + struct kprobe_blacklist_node *node; if (pev->uprobes) fd = open_uprobe_events(true); @@ -2126,11 +2227,25 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, pr_debug("Failed to get current event list.\n"); return -EIO; } + /* Get kprobe blacklist if exists */ + if (!pev->uprobes) { + ret = kprobe_blacklist__load(&blacklist); + if (ret < 0) + pr_debug("No kprobe blacklist support, ignored\n"); + } ret = 0; pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":"); for (i = 0; i < ntevs; i++) { tev = &tevs[i]; + /* Ensure that the address is NOT blacklisted */ + node = kprobe_blacklist__find_by_address(&blacklist, + tev->point.address); + if (node) { + pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol); + continue; + } + if (pev->event) event = pev->event; else @@ -2181,13 +2296,15 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, allow_suffix = true; } - if (ret >= 0) { + /* Note that it is possible to skip all events because of blacklist */ + if (ret >= 0 && tev->event) { /* Show how to use the event. */ pr_info("\nYou can now use it in all perf tools, such as:\n\n"); pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group, tev->event); } + kprobe_blacklist__delete(&blacklist); strlist__delete(namelist); close(fd); return ret; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index b5247d777f0e..d14193518e4d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -915,17 +915,13 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) dwarf_decl_line(sp_die, &pf->lno); pf->lno += pp->line; param->retval = find_probe_point_by_line(pf); - } else if (!dwarf_func_inline(sp_die)) { + } else if (die_is_func_instance(sp_die)) { + /* Instances always have the entry address */ + dwarf_entrypc(sp_die, &pf->addr); /* Real function */ if (pp->lazy_line) param->retval = find_probe_point_lazy(sp_die, pf); else { - if (dwarf_entrypc(sp_die, &pf->addr) != 0) { - pr_warning("Failed to get entry address of " - "%s.\n", dwarf_diename(sp_die)); - param->retval = -ENOENT; - return DWARF_CB_ABORT; - } pf->addr += pp->offset; /* TODO: Check the address in this function */ param->retval = call_probe_finder(sp_die, pf); @@ -1536,7 +1532,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e); lr->start = lf->lno_s; lr->end = lf->lno_e; - if (dwarf_func_inline(sp_die)) + if (!die_is_func_instance(sp_die)) param->retval = die_walk_instances(sp_die, line_range_inline_cb, lf); else diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 6c6a6953fa93..4d28624a1eca 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -17,6 +17,5 @@ util/xyarray.c util/cgroup.c util/rblist.c util/strlist.c -../lib/api/fs/fs.c util/trace-event.c ../../lib/rbtree.c diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build new file mode 100644 index 000000000000..6516e220c247 --- /dev/null +++ b/tools/perf/util/scripting-engines/Build @@ -0,0 +1,6 @@ +libperf-$(CONFIG_LIBPERL) += trace-event-perl.o +libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o + +CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default + +CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0baf75f12b7c..e4f166981ff0 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -537,7 +537,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n", oe->last_flush_type); - s->stats.nr_unordered_events++; + s->evlist->stats.nr_unordered_events++; } new = ordered_events__new(oe, timestamp, event); @@ -553,15 +553,67 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event, return 0; } -static void callchain__printf(struct perf_sample *sample) +static void callchain__lbr_callstack_printf(struct perf_sample *sample) { + struct ip_callchain *callchain = sample->callchain; + struct branch_stack *lbr_stack = sample->branch_stack; + u64 kernel_callchain_nr = callchain->nr; unsigned int i; - printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr); + for (i = 0; i < kernel_callchain_nr; i++) { + if (callchain->ips[i] == PERF_CONTEXT_USER) + break; + } + + if ((i != kernel_callchain_nr) && lbr_stack->nr) { + u64 total_nr; + /* + * LBR callstack can only get user call chain, + * i is kernel call chain number, + * 1 is PERF_CONTEXT_USER. + * + * The user call chain is stored in LBR registers. + * LBR are pair registers. The caller is stored + * in "from" register, while the callee is stored + * in "to" register. + * For example, there is a call stack + * "A"->"B"->"C"->"D". + * The LBR registers will recorde like + * "C"->"D", "B"->"C", "A"->"B". + * So only the first "to" register and all "from" + * registers are needed to construct the whole stack. + */ + total_nr = i + 1 + lbr_stack->nr + 1; + kernel_callchain_nr = i + 1; + + printf("... LBR call chain: nr:%" PRIu64 "\n", total_nr); + + for (i = 0; i < kernel_callchain_nr; i++) + printf("..... %2d: %016" PRIx64 "\n", + i, callchain->ips[i]); + + printf("..... %2d: %016" PRIx64 "\n", + (int)(kernel_callchain_nr), lbr_stack->entries[0].to); + for (i = 0; i < lbr_stack->nr; i++) + printf("..... %2d: %016" PRIx64 "\n", + (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from); + } +} + +static void callchain__printf(struct perf_evsel *evsel, + struct perf_sample *sample) +{ + unsigned int i; + struct ip_callchain *callchain = sample->callchain; + + if (has_branch_callstack(evsel)) + callchain__lbr_callstack_printf(sample); - for (i = 0; i < sample->callchain->nr; i++) + printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr); + + for (i = 0; i < callchain->nr; i++) printf("..... %2d: %016" PRIx64 "\n", - i, sample->callchain->ips[i]); + i, callchain->ips[i]); } static void branch_stack__printf(struct perf_sample *sample) @@ -636,14 +688,14 @@ static void stack_user__printf(struct stack_dump *dump) dump->size, dump->offset); } -static void perf_session__print_tstamp(struct perf_session *session, +static void perf_evlist__print_tstamp(struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = __perf_evlist__combined_sample_type(session->evlist); + u64 sample_type = __perf_evlist__combined_sample_type(evlist); if (event->header.type != PERF_RECORD_SAMPLE && - !perf_evlist__sample_id_all(session->evlist)) { + !perf_evlist__sample_id_all(evlist)) { fputs("-1 -1 ", stdout); return; } @@ -685,7 +737,7 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format) sample->read.one.id, sample->read.one.value); } -static void dump_event(struct perf_session *session, union perf_event *event, +static void dump_event(struct perf_evlist *evlist, union perf_event *event, u64 file_offset, struct perf_sample *sample) { if (!dump_trace) @@ -697,7 +749,7 @@ static void dump_event(struct perf_session *session, union perf_event *event, trace_event(event); if (sample) - perf_session__print_tstamp(session, event, sample); + perf_evlist__print_tstamp(evlist, event, sample); printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, event->header.size, perf_event__name(event->header.type)); @@ -718,9 +770,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_type = evsel->attr.sample_type; if (sample_type & PERF_SAMPLE_CALLCHAIN) - callchain__printf(sample); + callchain__printf(evsel, sample); - if (sample_type & PERF_SAMPLE_BRANCH_STACK) + if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !has_branch_callstack(evsel)) branch_stack__printf(sample); if (sample_type & PERF_SAMPLE_REGS_USER) @@ -745,8 +797,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_read__printf(sample, evsel->attr.read_format); } -static struct machine * - perf_session__find_machine_for_cpumode(struct perf_session *session, +static struct machine *machines__find_for_cpumode(struct machines *machines, union perf_event *event, struct perf_sample *sample) { @@ -764,26 +815,24 @@ static struct machine * else pid = sample->pid; - machine = perf_session__find_machine(session, pid); + machine = machines__find(machines, pid); if (!machine) - machine = perf_session__findnew_machine(session, - DEFAULT_GUEST_KERNEL_ID); + machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } - return &session->machines.host; + return &machines->host; } -static int deliver_sample_value(struct perf_session *session, +static int deliver_sample_value(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct sample_read_value *v, struct machine *machine) { - struct perf_sample_id *sid; + struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); - sid = perf_evlist__id2sid(session->evlist, v->id); if (sid) { sample->id = v->id; sample->period = v->value - sid->period; @@ -791,14 +840,14 @@ static int deliver_sample_value(struct perf_session *session, } if (!sid || sid->evsel == NULL) { - ++session->stats.nr_unknown_id; + ++evlist->stats.nr_unknown_id; return 0; } return tool->sample(tool, event, sample, sid->evsel, machine); } -static int deliver_sample_group(struct perf_session *session, +static int deliver_sample_group(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -808,7 +857,7 @@ static int deliver_sample_group(struct perf_session *session, u64 i; for (i = 0; i < sample->read.group.nr; i++) { - ret = deliver_sample_value(session, tool, event, sample, + ret = deliver_sample_value(evlist, tool, event, sample, &sample->read.group.values[i], machine); if (ret) @@ -819,7 +868,7 @@ static int deliver_sample_group(struct perf_session *session, } static int -perf_session__deliver_sample(struct perf_session *session, + perf_evlist__deliver_sample(struct perf_evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -836,10 +885,10 @@ perf_session__deliver_sample(struct perf_session *session, /* For PERF_SAMPLE_READ we have either single or group mode. */ if (read_format & PERF_FORMAT_GROUP) - return deliver_sample_group(session, tool, event, sample, + return deliver_sample_group(evlist, tool, event, sample, machine); else - return deliver_sample_value(session, tool, event, sample, + return deliver_sample_value(evlist, tool, event, sample, &sample->read.one, machine); } @@ -848,29 +897,28 @@ int perf_session__deliver_event(struct perf_session *session, struct perf_sample *sample, struct perf_tool *tool, u64 file_offset) { + struct perf_evlist *evlist = session->evlist; struct perf_evsel *evsel; struct machine *machine; - dump_event(session, event, file_offset, sample); + dump_event(evlist, event, file_offset, sample); - evsel = perf_evlist__id2evsel(session->evlist, sample->id); + evsel = perf_evlist__id2evsel(evlist, sample->id); - machine = perf_session__find_machine_for_cpumode(session, event, - sample); + machine = machines__find_for_cpumode(&session->machines, event, sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: dump_sample(evsel, event, sample); if (evsel == NULL) { - ++session->stats.nr_unknown_id; + ++evlist->stats.nr_unknown_id; return 0; } if (machine == NULL) { - ++session->stats.nr_unprocessable_samples; + ++evlist->stats.nr_unprocessable_samples; return 0; } - return perf_session__deliver_sample(session, tool, event, - sample, evsel, machine); + return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); case PERF_RECORD_MMAP2: @@ -883,7 +931,7 @@ 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->stats.total_lost += event->lost.lost; + evlist->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); @@ -892,7 +940,7 @@ int perf_session__deliver_event(struct perf_session *session, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); default: - ++session->stats.nr_unknown_events; + ++evlist->stats.nr_unknown_events; return -1; } } @@ -905,7 +953,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, int fd = perf_data_file__fd(session->file); int err; - dump_event(session, event, file_offset, NULL); + dump_event(session->evlist, event, file_offset, NULL); /* These events are processed right away */ switch (event->header.type) { @@ -942,7 +990,7 @@ int perf_session__deliver_synth_event(struct perf_session *session, struct perf_sample *sample, struct perf_tool *tool) { - events_stats__inc(&session->stats, event->header.type); + events_stats__inc(&session->evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, 0); @@ -1019,16 +1067,17 @@ static s64 perf_session__process_event(struct perf_session *session, struct perf_tool *tool, u64 file_offset) { + struct perf_evlist *evlist = session->evlist; struct perf_sample sample; int ret; if (session->header.needs_swap) - event_swap(event, perf_evlist__sample_id_all(session->evlist)); + event_swap(event, perf_evlist__sample_id_all(evlist)); if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; - events_stats__inc(&session->stats, event->header.type); + events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, file_offset); @@ -1036,7 +1085,7 @@ static s64 perf_session__process_event(struct perf_session *session, /* * For all kernel events we get the sample data */ - ret = perf_evlist__parse_sample(session->evlist, event, &sample); + ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) return ret; @@ -1076,47 +1125,47 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se return thread; } -static void perf_session__warn_about_errors(const struct perf_session *session, - const struct perf_tool *tool) +static void perf_tool__warn_about_errors(const struct perf_tool *tool, + const struct events_stats *stats) { if (tool->lost == perf_event__process_lost && - session->stats.nr_events[PERF_RECORD_LOST] != 0) { + 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->stats.nr_events[0], - session->stats.nr_events[PERF_RECORD_LOST]); + stats->nr_events[0], + stats->nr_events[PERF_RECORD_LOST]); } - if (session->stats.nr_unknown_events != 0) { + if (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->stats.nr_unknown_events); + stats->nr_unknown_events); } - if (session->stats.nr_unknown_id != 0) { + if (stats->nr_unknown_id != 0) { ui__warning("%u samples with id not present in the header\n", - session->stats.nr_unknown_id); + stats->nr_unknown_id); } - 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->stats.nr_invalid_chains, - session->stats.nr_events[PERF_RECORD_SAMPLE]); - } + if (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", + stats->nr_invalid_chains, + stats->nr_events[PERF_RECORD_SAMPLE]); + } - if (session->stats.nr_unprocessable_samples != 0) { + if (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->stats.nr_unprocessable_samples); + stats->nr_unprocessable_samples); } - if (session->stats.nr_unordered_events != 0) - ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events); + if (stats->nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", stats->nr_unordered_events); } volatile int session_done; @@ -1206,7 +1255,7 @@ done: err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: free(buf); - perf_session__warn_about_errors(session, tool); + perf_tool__warn_about_errors(tool, &session->evlist->stats); ordered_events__free(&session->ordered_events); return err; } @@ -1351,7 +1400,7 @@ out: err = ordered_events__flush(session, tool, OE_FLUSH__FINAL); out_err: ui_progress__finish(); - perf_session__warn_about_errors(session, tool); + perf_tool__warn_about_errors(tool, &session->evlist->stats); ordered_events__free(&session->ordered_events); session->one_mmap = false; return err; @@ -1436,7 +1485,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) { size_t ret = fprintf(fp, "Aggregated stats:\n"); - ret += events_stats__fprintf(&session->stats, fp); + ret += events_stats__fprintf(&session->evlist->stats, fp); return ret; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 6d663dc76404..fe859f379ca7 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -20,7 +20,6 @@ struct perf_session { struct machines machines; struct perf_evlist *evlist; struct trace_event tevent; - struct events_stats stats; bool repipe; bool one_mmap; void *one_mmap_addr; diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index d0aee4b9dfd4..1833103768cb 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -25,7 +25,7 @@ cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') -libapikfs = getenv('LIBAPIKFS') +libapikfs = getenv('LIBAPI') ext_sources = [f.strip() for f in file('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 7a39c1ed8d37..4593f36ecc4c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1463,6 +1463,15 @@ int sort_dimension__add(const char *tok) sort__has_parent = 1; } else if (sd->entry == &sort_sym) { sort__has_sym = 1; + /* + * perf diff displays the performance difference amongst + * two or more perf.data files. Those files could come + * from different binaries. So we should not compare + * their ips, but the name of symbol. + */ + if (sort__mode == SORT_MODE__DIFF) + sd->entry->se_collapse = sort__sym_sort; + } else if (sd->entry == &sort_dso) { sort__has_dso = 1; } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 33b7a2aef713..ada16762fac2 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -74,6 +74,10 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +#ifndef STT_GNU_IFUNC +#define STT_GNU_IFUNC 10 +#endif + static inline int elf_sym__is_function(const GElf_Sym *sym) { return (elf_sym__type(sym) == STT_FUNC || @@ -864,10 +868,9 @@ int dso__load_sym(struct dso *dso, struct map *map, /* Reject ARM ELF "mapping symbols": these aren't unique and * don't identify functions, so will confuse the profile * output: */ - if (ehdr.e_machine == EM_ARM) { - if (!strcmp(elf_name, "$a") || - !strcmp(elf_name, "$d") || - !strcmp(elf_name, "$t")) + if (ehdr.e_machine == EM_ARM || ehdr.e_machine == EM_AARCH64) { + if (elf_name[0] == '$' && strchr("adtx", elf_name[1]) + && (elf_name[2] == '\0' || elf_name[2] == '.')) continue; } diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index c36636fd825b..25d6c737be3e 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -112,8 +112,8 @@ unsigned long long read_size(struct event_format *event, void *ptr, int size) return pevent_read_number(event->pevent, ptr, size); } -void event_format__print(struct event_format *event, - int cpu, void *data, int size) +void event_format__fprintf(struct event_format *event, + int cpu, void *data, int size, FILE *fp) { struct pevent_record record; struct trace_seq s; @@ -125,10 +125,16 @@ void event_format__print(struct event_format *event, trace_seq_init(&s); pevent_event_info(&s, event, &record); - trace_seq_do_printf(&s); + trace_seq_do_fprintf(&s, fp); trace_seq_destroy(&s); } +void event_format__print(struct event_format *event, + int cpu, void *data, int size) +{ + return event_format__fprintf(event, cpu, data, size, stdout); +} + void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size __maybe_unused) { diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 52aaa19e1eb1..356629a30ca9 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -23,6 +23,9 @@ trace_event__tp_format(const char *sys, const char *name); int bigendian(void); +void event_format__fprintf(struct event_format *event, + int cpu, void *data, int size, FILE *fp); + void event_format__print(struct event_format *event, int cpu, void *data, int size); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index b86744f29eef..4ee6d0d4c993 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -269,6 +269,13 @@ void dump_stack(void) void dump_stack(void) {} #endif +void sighandler_dump_stack(int sig) +{ + psignal(sig, "perf"); + dump_stack(); + exit(sig); +} + void get_term_dimensions(struct winsize *ws) { char *s = getenv("LINES"); @@ -303,13 +310,26 @@ void set_term_quiet_input(struct termios *old) tcsetattr(0, TCSANOW, &tc); } -static void set_tracing_events_path(const char *mountpoint) +static void set_tracing_events_path(const char *tracing, const char *mountpoint) { - snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s", - mountpoint, "tracing/events"); + snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s", + mountpoint, tracing, "events"); } -const char *perf_debugfs_mount(const char *mountpoint) +static const char *__perf_tracefs_mount(const char *mountpoint) +{ + const char *mnt; + + mnt = tracefs_mount(mountpoint); + if (!mnt) + return NULL; + + set_tracing_events_path("", mnt); + + return mnt; +} + +static const char *__perf_debugfs_mount(const char *mountpoint) { const char *mnt; @@ -317,7 +337,20 @@ const char *perf_debugfs_mount(const char *mountpoint) if (!mnt) return NULL; - set_tracing_events_path(mnt); + set_tracing_events_path("tracing/", mnt); + + return mnt; +} + +const char *perf_debugfs_mount(const char *mountpoint) +{ + const char *mnt; + + mnt = __perf_tracefs_mount(mountpoint); + if (mnt) + return mnt; + + mnt = __perf_debugfs_mount(mountpoint); return mnt; } @@ -325,12 +358,19 @@ const char *perf_debugfs_mount(const char *mountpoint) void perf_debugfs_set_path(const char *mntpt) { snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt); - set_tracing_events_path(mntpt); + set_tracing_events_path("tracing/", mntpt); +} + +static const char *find_tracefs(void) +{ + const char *path = __perf_tracefs_mount(NULL); + + return path; } static const char *find_debugfs(void) { - const char *path = perf_debugfs_mount(NULL); + const char *path = __perf_debugfs_mount(NULL); if (!path) fprintf(stderr, "Your kernel does not support the debugfs filesystem"); @@ -344,6 +384,7 @@ static const char *find_debugfs(void) */ const char *find_tracing_dir(void) { + const char *tracing_dir = ""; static char *tracing; static int tracing_found; const char *debugfs; @@ -351,11 +392,15 @@ const char *find_tracing_dir(void) if (tracing_found) return tracing; - debugfs = find_debugfs(); - if (!debugfs) - return NULL; + debugfs = find_tracefs(); + if (!debugfs) { + tracing_dir = "/tracing"; + debugfs = find_debugfs(); + if (!debugfs) + return NULL; + } - if (asprintf(&tracing, "%s/tracing", debugfs) < 0) + if (asprintf(&tracing, "%s%s", debugfs, tracing_dir) < 0) return NULL; tracing_found = 1; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 027a5153495c..fbd598afc606 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -75,6 +75,7 @@ #include <linux/types.h> #include <sys/ttydefaults.h> #include <api/fs/debugfs.h> +#include <api/fs/tracefs.h> #include <termios.h> #include <linux/bitops.h> #include <termios.h> @@ -276,6 +277,7 @@ char *ltrim(char *s); char *rtrim(char *s); void dump_stack(void); +void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; |