diff options
Diffstat (limited to 'tools/perf')
155 files changed, 6958 insertions, 2631 deletions
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index 7065cd6fbdfc..4464ad770d51 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -48,6 +48,12 @@ SUBSYSTEM 'mem':: Memory access performance. +'numa':: + NUMA scheduling and MM benchmarks. + +'futex':: + Futex stressing benchmarks. + 'all':: All benchmark subsystems. @@ -187,6 +193,22 @@ Show only the result with page faults before memset. --no-prefault:: Show only the result without page faults before memset. +SUITES FOR 'numa' +~~~~~~~~~~~~~~~~~ +*mem*:: +Suite for evaluating NUMA workloads. + +SUITES FOR 'futex' +~~~~~~~~~~~~~~~~~~ +*hash*:: +Suite for evaluating hash tables. + +*wake*:: +Suite for evaluating wake calls. + +*requeue*:: +Suite for evaluating requeue calls. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index fdfceee0ffd0..b3b8abae62b8 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -33,21 +33,25 @@ OPTIONS -d:: --dsos=:: Only consider symbols in these dsos. CSV that understands - file://filename entries. + file://filename entries. This option will affect the percentage + of the Baseline/Delta column. See --percentage for more info. -C:: --comms=:: Only consider symbols in these comms. CSV that understands - file://filename entries. + file://filename entries. This option will affect the percentage + of the Baseline/Delta column. See --percentage for more info. -S:: --symbols=:: Only consider these symbols. CSV that understands - file://filename entries. + file://filename entries. This option will affect the percentage + of the Baseline/Delta column. See --percentage for more info. -s:: --sort=:: - Sort by key(s): pid, comm, dso, symbol. + Sort by key(s): pid, comm, dso, symbol, cpu, parent, srcline. + Please see description of --sort in the perf-report man page. -t:: --field-separator=:: @@ -89,6 +93,14 @@ OPTIONS --order:: Specify compute sorting column number. +--percentage:: + Determine how to display the overhead percentage of filtered entries. + Filters can be applied by --comms, --dsos and/or --symbols options. + + "relative" means it's relative to filtered entries only so that the + sum of shown entries will be always 100%. "absolute" means it retains + the original value before and after the filter is applied. + COMPARISON ---------- The comparison is governed by the baseline file. The baseline perf.data @@ -157,6 +169,10 @@ with: - period_percent being the % of the hist entry period value within single data file + - with filtering by -C, -d and/or -S, period_percent might be changed + relative to how entries are filtered. Use --percentage=absolute to + prevent such fluctuation. + ratio ~~~~~ If specified the 'Ratio' column is displayed with value 'r' computed as: @@ -187,4 +203,4 @@ If specified the 'Weighted diff' column is displayed with value 'd' computed as: SEE ALSO -------- -linkperf:perf-record[1] +linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 888d51137fbe..1d78a4064da4 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -18,6 +18,10 @@ from it, into perf.data. Perf record options are accepted and are passed through "perf mem -t <TYPE> report" displays the result. It invokes perf report with the right set of options to display a memory access profile. +Note that on Intel systems the memory latency reported is the use-latency, +not the pure load (or store latency). Use latency includes any pipeline +queueing delays in addition to the memory subsystem latency. + OPTIONS ------- <command>...:: diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index b715cb71592b..1513935c399b 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -136,6 +136,8 @@ Each probe argument follows below syntax. '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'.) '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. + LINE SYNTAX ----------- Line range is described by following syntax. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 8eab8a4bdeb8..a1b5185402d5 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -25,10 +25,6 @@ OPTIONS --verbose:: Be more verbose. (show symbol address, etc) --d:: ---dsos=:: - Only consider symbols in these dsos. CSV that understands - file://filename entries. -n:: --show-nr-samples:: Show the number of samples for each symbol @@ -42,11 +38,18 @@ OPTIONS -c:: --comms=:: Only consider symbols in these comms. CSV that understands - file://filename entries. + file://filename entries. This option will affect the percentage of + the overhead column. See --percentage for more info. +-d:: +--dsos=:: + Only consider symbols in these dsos. CSV that understands + file://filename entries. This option will affect the percentage of + the overhead column. See --percentage for more info. -S:: --symbols=:: Only consider these symbols. CSV that understands - file://filename entries. + file://filename entries. This option will affect the percentage of + the overhead column. See --percentage for more info. --symbol-filter=:: Only show symbols that match (partially) with this filter. @@ -76,6 +79,15 @@ OPTIONS abort cost. This is the global weight. - local_weight: Local weight version of the weight above. - transaction: Transaction abort flags. + - overhead: Overhead percentage of sample + - overhead_sys: Overhead percentage of sample running in system mode + - overhead_us: Overhead percentage of sample running in user mode + - overhead_guest_sys: Overhead percentage of sample running in system mode + on guest machine + - overhead_guest_us: Overhead percentage of sample running in user mode on + guest machine + - sample: Number of sample + - period: Raw number of event count of sample By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol) @@ -95,6 +107,16 @@ OPTIONS And default sort keys are changed to comm, dso_from, symbol_from, dso_to and symbol_to, see '--branch-stack'. +-F:: +--fields=:: + Specify output field - multiple keys can be specified in CSV format. + Following fields are available: + overhead, overhead_sys, overhead_us, sample and period. + Also it can contain any sort key(s). + + By default, every sort keys not specified in -F will be appended + automatically. + -p:: --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this @@ -237,6 +259,15 @@ OPTIONS Do not show entries which have an overhead under that percent. (Default: 0). +--percentage:: + Determine how to display the overhead percentage of filtered entries. + Filters can be applied by --comms, --dsos and/or --symbols options and + Zoom operations on the TUI (thread, dso, etc). + + "relative" means it's relative to filtered entries only so that the + sum of shown entries will be always 100%. "absolute" means it retains + the original value before and after the filter is applied. + --header:: Show header information in the perf.data file. This includes various information like hostname, OS and perf version, cpu/mem diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index cdd8d4946dba..dcfa54c851e9 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -87,7 +87,6 @@ Default is to monitor all CPUS. --realtime=<priority>:: Collect data with this RT SCHED_FIFO priority. --s <symbol>:: --sym-annotate=<symbol>:: Annotate this symbol. @@ -114,7 +113,17 @@ Default is to monitor all CPUS. -s:: --sort:: Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, - local_weight, abort, in_tx, transaction + local_weight, abort, in_tx, transaction, overhead, sample, period. + Please see description of --sort in the perf-report man page. + +--fields=:: + Specify output field - multiple keys can be specified in CSV format. + Following fields are available: + overhead, overhead_sys, overhead_us, sample and period. + Also it can contain any sort key(s). + + By default, every sort keys not specified in --field will be appended + automatically. -n:: --show-nr-samples:: @@ -124,13 +133,16 @@ Default is to monitor all CPUS. Show a column with the sum of periods. --dsos:: - Only consider symbols in these dsos. + Only consider symbols in these dsos. This option will affect the + percentage of the overhead column. See --percentage for more info. --comms:: - Only consider symbols in these comms. + Only consider symbols in these comms. This option will affect the + percentage of the overhead column. See --percentage for more info. --symbols:: - Only consider these symbols. + Only consider these symbols. This option will affect the + percentage of the overhead column. See --percentage for more info. -M:: --disassembler-style=:: Set disassembler style for objdump. @@ -166,6 +178,15 @@ Default is to monitor all CPUS. Do not show entries which have an overhead under that percent. (Default: 0). +--percentage:: + Determine how to display the overhead percentage of filtered entries. + Filters can be applied by --comms, --dsos and/or --symbols options and + Zoom operations on the TUI (thread, dso, etc). + + "relative" means it's relative to filtered entries only so that the + sum of shown entries will be always 100%. "absolute" means it retains + the original value before and after the filter is applied. + INTERACTIVE PROMPTING KEYS -------------------------- @@ -201,4 +222,4 @@ Pressing any unmapped key displays a menu, and prompts for input. SEE ALSO -------- -linkperf:perf-stat[1], linkperf:perf-list[1] +linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-report[1] diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index f41572d0dd76..45da209b6ed3 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -6,6 +6,9 @@ tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h tools/include/asm/bug.h tools/include/linux/compiler.h +tools/include/linux/hash.h +tools/include/linux/export.h +tools/include/linux/types.h include/linux/const.h include/linux/perf_event.h include/linux/rbtree.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 7257e7e9e38a..02f0a4dd1a80 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -7,6 +7,8 @@ include config/utilities.mak # Define V to have a more verbose compile. # +# Define VF to have a more verbose feature check output. +# # Define O to save output files in a separate directory. # # Define ARCH as name of target architecture if you want cross-builds. @@ -55,6 +57,9 @@ include config/utilities.mak # Define NO_LIBAUDIT if you do not want libaudit support # # Define NO_LIBBIONIC if you do not want bionic support +# +# Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support +# for dwarf backtrace post unwind. ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(shell pwd))) @@ -187,13 +192,13 @@ endif export PERL_PATH $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c - $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c + $(QUIET_FLEX)$(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) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.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_ @@ -208,7 +213,7 @@ 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/hash.h LIB_H += ../../include/linux/stringify.h LIB_H += util/include/linux/bitmap.h LIB_H += util/include/linux/bitops.h @@ -217,14 +222,12 @@ 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 += util/include/linux/export.h -LIB_H += util/include/linux/magic.h +LIB_H += ../include/linux/export.h LIB_H += util/include/linux/poison.h -LIB_H += util/include/linux/prefetch.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 += util/include/linux/types.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 @@ -244,13 +247,11 @@ LIB_H += util/cache.h LIB_H += util/callchain.h LIB_H += util/build-id.h LIB_H += util/debug.h -LIB_H += util/fs.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/types.h LIB_H += util/levenshtein.h LIB_H += util/machine.h LIB_H += util/map.h @@ -306,7 +307,6 @@ LIB_OBJS += $(OUTPUT)util/annotate.o LIB_OBJS += $(OUTPUT)util/build-id.o LIB_OBJS += $(OUTPUT)util/config.o LIB_OBJS += $(OUTPUT)util/ctype.o -LIB_OBJS += $(OUTPUT)util/fs.o LIB_OBJS += $(OUTPUT)util/pmu.o LIB_OBJS += $(OUTPUT)util/environment.o LIB_OBJS += $(OUTPUT)util/event.o @@ -396,7 +396,10 @@ LIB_OBJS += $(OUTPUT)tests/rdpmc.o LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o LIB_OBJS += $(OUTPUT)tests/pmu.o +LIB_OBJS += $(OUTPUT)tests/hists_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/python-use.o LIB_OBJS += $(OUTPUT)tests/bp_signal.o LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o @@ -408,6 +411,13 @@ 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 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o @@ -420,6 +430,9 @@ BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o endif BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.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 @@ -475,8 +488,13 @@ ifndef NO_DWARF 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.o + LIB_OBJS += $(OUTPUT)util/unwind-libunwind.o endif LIB_OBJS += $(OUTPUT)tests/keep-tracking.o @@ -533,6 +551,7 @@ ifeq ($(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 @@ -574,7 +593,7 @@ $(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H) $(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $< $(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS) - $(QUIET_LINK)$(CC) -o $@ -shared $(ALL_LDFLAGS) $(filter %.o,$^) $(GTK_LIBS) + $(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS) $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ @@ -655,6 +674,9 @@ $(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS -DPYTHON='"$(PYTHON_WORD)"' \ $< +$(OUTPUT)tests/dwarf-unwind.o: tests/dwarf-unwind.c + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -fno-optimize-sibling-calls $< + $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< @@ -707,9 +729,15 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) # we depend the various files onto their directories. DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(GTK_OBJS) DIRECTORY_DEPS += $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h -$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS))) +# 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 + +OUTPUT_DIRECTORIES := $(sort $(dir $(DIRECTORY_DEPS))) + +$(DIRECTORY_DEPS): | $(OUTPUT_DIRECTORIES) # In the second step, we make a rule to actually create these directories -$(sort $(dir $(DIRECTORY_DEPS))): +$(OUTPUT_DIRECTORIES): $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null $(LIB_FILE): $(LIB_OBJS) @@ -886,7 +914,7 @@ config-clean: clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS) $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf - $(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)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-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile index fe9b61e322a5..09d62153d384 100644 --- a/tools/perf/arch/arm/Makefile +++ b/tools/perf/arch/arm/Makefile @@ -3,5 +3,12 @@ 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.o +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/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index 2a1cfde66b69..f619c9c5a4bf 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -2,10 +2,15 @@ #define ARCH_PERF_REGS_H #include <stdlib.h> -#include "../../util/types.h" +#include <linux/types.h> #include <asm/perf_regs.h> +void perf_regs_load(u64 *regs); + #define PERF_REGS_MASK ((1ULL << PERF_REG_ARM_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_ARM_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 + #define PERF_REG_IP PERF_REG_ARM_PC #define PERF_REG_SP PERF_REG_ARM_SP diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c new file mode 100644 index 000000000000..9f870d27cb39 --- /dev/null +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -0,0 +1,60 @@ +#include <string.h> +#include "perf_regs.h" +#include "thread.h" +#include "map.h" +#include "event.h" +#include "tests/tests.h" + +#define STACK_SIZE 8192 + +static int sample_ustack(struct perf_sample *sample, + struct thread *thread, u64 *regs) +{ + struct stack_dump *stack = &sample->user_stack; + struct map *map; + unsigned long sp; + u64 stack_size, *buf; + + buf = malloc(STACK_SIZE); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + sp = (unsigned long) regs[PERF_REG_ARM_SP]; + + map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + if (!map) { + pr_debug("failed to get stack map\n"); + free(buf); + return -1; + } + + stack_size = map->end - sp; + stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; + + memcpy(buf, (void *) sp, stack_size); + stack->data = (char *) buf; + stack->size = stack_size; + return 0; +} + +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread) +{ + struct regs_dump *regs = &sample->user_regs; + u64 *buf; + + buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + perf_regs_load(buf); + regs->abi = PERF_SAMPLE_REGS_ABI; + regs->regs = buf; + regs->mask = PERF_REGS_MASK; + + return sample_ustack(sample, thread, buf); +} diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S new file mode 100644 index 000000000000..e09e983946fe --- /dev/null +++ b/tools/perf/arch/arm/tests/regs_load.S @@ -0,0 +1,58 @@ +#include <linux/linkage.h> + +#define R0 0x00 +#define R1 0x08 +#define R2 0x10 +#define R3 0x18 +#define R4 0x20 +#define R5 0x28 +#define R6 0x30 +#define R7 0x38 +#define R8 0x40 +#define R9 0x48 +#define SL 0x50 +#define FP 0x58 +#define IP 0x60 +#define SP 0x68 +#define LR 0x70 +#define PC 0x78 + +/* + * Implementation of void perf_regs_load(u64 *regs); + * + * This functions fills in the 'regs' buffer from the actual registers values, + * in the way the perf built-in unwinding test expects them: + * - the PC at the time at the call to this function. Since this function + * is called using a bl instruction, the PC value is taken from LR. + * The built-in unwinding test then unwinds the call stack from the dwarf + * information in unwind__get_entries. + * + * Notes: + * - the 8 bytes stride in the registers offsets comes from the fact + * that the registers are stored in an u64 array (u64 *regs), + * - the regs buffer needs to be zeroed before the call to this function, + * in this case using a calloc in dwarf-unwind.c. + */ + +.text +.type perf_regs_load,%function +ENTRY(perf_regs_load) + str r0, [r0, #R0] + str r1, [r0, #R1] + str r2, [r0, #R2] + str r3, [r0, #R3] + str r4, [r0, #R4] + str r5, [r0, #R5] + str r6, [r0, #R6] + str r7, [r0, #R7] + str r8, [r0, #R8] + str r9, [r0, #R9] + str sl, [r0, #SL] + str fp, [r0, #FP] + str ip, [r0, #IP] + str sp, [r0, #SP] + str lr, [r0, #LR] + str lr, [r0, #PC] // store pc as lr in order to skip the call + // to this function + mov pc, lr +ENDPROC(perf_regs_load) diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c new file mode 100644 index 000000000000..b4176c60117a --- /dev/null +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -0,0 +1,36 @@ +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[PERF_REG_ARM_MAX]; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_ARM_##r); \ + val; \ +}) + + dwarf_regs[0] = REG(R0); + dwarf_regs[1] = REG(R1); + dwarf_regs[2] = REG(R2); + dwarf_regs[3] = REG(R3); + dwarf_regs[4] = REG(R4); + dwarf_regs[5] = REG(R5); + dwarf_regs[6] = REG(R6); + dwarf_regs[7] = REG(R7); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(FP); + dwarf_regs[12] = REG(IP); + dwarf_regs[13] = REG(SP); + dwarf_regs[14] = REG(LR); + dwarf_regs[15] = REG(PC); + + return dwfl_thread_state_registers(thread, 0, PERF_REG_ARM_MAX, + dwarf_regs); +} diff --git a/tools/perf/arch/arm/util/unwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index da3dc950550c..729ed69a6664 100644 --- a/tools/perf/arch/arm/util/unwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -4,7 +4,7 @@ #include "perf_regs.h" #include "../../util/unwind.h" -int unwind__arch_reg_id(int regnum) +int libunwind__arch_reg_id(int regnum) { switch (regnum) { case UNW_ARM_R0: diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile new file mode 100644 index 000000000000..67e9b3d38e89 --- /dev/null +++ b/tools/perf/arch/arm64/Makefile @@ -0,0 +1,7 @@ +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/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h new file mode 100644 index 000000000000..e9441b9e2a30 --- /dev/null +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -0,0 +1,88 @@ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include <linux/types.h> +#include <asm/perf_regs.h> + +#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM64_MAX) - 1) +#define PERF_REG_IP PERF_REG_ARM64_PC +#define PERF_REG_SP PERF_REG_ARM64_SP + +static inline const char *perf_reg_name(int id) +{ + switch (id) { + case PERF_REG_ARM64_X0: + return "x0"; + case PERF_REG_ARM64_X1: + return "x1"; + case PERF_REG_ARM64_X2: + return "x2"; + case PERF_REG_ARM64_X3: + return "x3"; + case PERF_REG_ARM64_X4: + return "x4"; + case PERF_REG_ARM64_X5: + return "x5"; + case PERF_REG_ARM64_X6: + return "x6"; + case PERF_REG_ARM64_X7: + return "x7"; + case PERF_REG_ARM64_X8: + return "x8"; + case PERF_REG_ARM64_X9: + return "x9"; + case PERF_REG_ARM64_X10: + return "x10"; + case PERF_REG_ARM64_X11: + return "x11"; + case PERF_REG_ARM64_X12: + return "x12"; + case PERF_REG_ARM64_X13: + return "x13"; + case PERF_REG_ARM64_X14: + return "x14"; + case PERF_REG_ARM64_X15: + return "x15"; + case PERF_REG_ARM64_X16: + return "x16"; + case PERF_REG_ARM64_X17: + return "x17"; + case PERF_REG_ARM64_X18: + return "x18"; + case PERF_REG_ARM64_X19: + return "x19"; + case PERF_REG_ARM64_X20: + return "x20"; + case PERF_REG_ARM64_X21: + return "x21"; + case PERF_REG_ARM64_X22: + return "x22"; + case PERF_REG_ARM64_X23: + return "x23"; + case PERF_REG_ARM64_X24: + return "x24"; + case PERF_REG_ARM64_X25: + return "x25"; + case PERF_REG_ARM64_X26: + return "x26"; + case PERF_REG_ARM64_X27: + return "x27"; + case PERF_REG_ARM64_X28: + return "x28"; + case PERF_REG_ARM64_X29: + return "x29"; + case PERF_REG_ARM64_SP: + return "sp"; + case PERF_REG_ARM64_LR: + return "lr"; + case PERF_REG_ARM64_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c new file mode 100644 index 000000000000..d49efeb8172e --- /dev/null +++ b/tools/perf/arch/arm64/util/dwarf-regs.c @@ -0,0 +1,80 @@ +/* + * Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2010 Will Deacon, ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <stddef.h> +#include <dwarf-regs.h> + +struct pt_regs_dwarfnum { + const char *name; + unsigned int dwarfnum; +}; + +#define STR(s) #s +#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} +#define GPR_DWARFNUM_NAME(num) \ + {.name = STR(%x##num), .dwarfnum = num} +#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} + +/* + * Reference: + * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0057b/IHI0057B_aadwarf64.pdf + */ +static const struct pt_regs_dwarfnum regdwarfnum_table[] = { + GPR_DWARFNUM_NAME(0), + GPR_DWARFNUM_NAME(1), + GPR_DWARFNUM_NAME(2), + GPR_DWARFNUM_NAME(3), + GPR_DWARFNUM_NAME(4), + GPR_DWARFNUM_NAME(5), + GPR_DWARFNUM_NAME(6), + GPR_DWARFNUM_NAME(7), + GPR_DWARFNUM_NAME(8), + GPR_DWARFNUM_NAME(9), + GPR_DWARFNUM_NAME(10), + GPR_DWARFNUM_NAME(11), + GPR_DWARFNUM_NAME(12), + GPR_DWARFNUM_NAME(13), + GPR_DWARFNUM_NAME(14), + GPR_DWARFNUM_NAME(15), + GPR_DWARFNUM_NAME(16), + GPR_DWARFNUM_NAME(17), + GPR_DWARFNUM_NAME(18), + GPR_DWARFNUM_NAME(19), + GPR_DWARFNUM_NAME(20), + GPR_DWARFNUM_NAME(21), + GPR_DWARFNUM_NAME(22), + GPR_DWARFNUM_NAME(23), + GPR_DWARFNUM_NAME(24), + GPR_DWARFNUM_NAME(25), + GPR_DWARFNUM_NAME(26), + GPR_DWARFNUM_NAME(27), + GPR_DWARFNUM_NAME(28), + GPR_DWARFNUM_NAME(29), + REG_DWARFNUM_NAME("%lr", 30), + REG_DWARFNUM_NAME("%sp", 31), + REG_DWARFNUM_END, +}; + +/** + * get_arch_regstr() - lookup register name from it's DWARF register number + * @n: the DWARF register number + * + * get_arch_regstr() returns the name of the register in struct + * regdwarfnum_table from it's DWARF register number. If the register is not + * found in the table, this returns NULL; + */ +const char *get_arch_regstr(unsigned int n) +{ + const struct pt_regs_dwarfnum *roff; + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (roff->dwarfnum == n) + return roff->name; + return NULL; +} diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c new file mode 100644 index 000000000000..436ee43859dc --- /dev/null +++ b/tools/perf/arch/arm64/util/unwind-libunwind.c @@ -0,0 +1,82 @@ + +#include <errno.h> +#include <libunwind.h> +#include "perf_regs.h" +#include "../../util/unwind.h" + +int libunwind__arch_reg_id(int regnum) +{ + switch (regnum) { + case UNW_AARCH64_X0: + return PERF_REG_ARM64_X0; + case UNW_AARCH64_X1: + return PERF_REG_ARM64_X1; + case UNW_AARCH64_X2: + return PERF_REG_ARM64_X2; + case UNW_AARCH64_X3: + return PERF_REG_ARM64_X3; + case UNW_AARCH64_X4: + return PERF_REG_ARM64_X4; + case UNW_AARCH64_X5: + return PERF_REG_ARM64_X5; + case UNW_AARCH64_X6: + return PERF_REG_ARM64_X6; + case UNW_AARCH64_X7: + return PERF_REG_ARM64_X7; + case UNW_AARCH64_X8: + return PERF_REG_ARM64_X8; + case UNW_AARCH64_X9: + return PERF_REG_ARM64_X9; + case UNW_AARCH64_X10: + return PERF_REG_ARM64_X10; + case UNW_AARCH64_X11: + return PERF_REG_ARM64_X11; + case UNW_AARCH64_X12: + return PERF_REG_ARM64_X12; + case UNW_AARCH64_X13: + return PERF_REG_ARM64_X13; + case UNW_AARCH64_X14: + return PERF_REG_ARM64_X14; + case UNW_AARCH64_X15: + return PERF_REG_ARM64_X15; + case UNW_AARCH64_X16: + return PERF_REG_ARM64_X16; + case UNW_AARCH64_X17: + return PERF_REG_ARM64_X17; + case UNW_AARCH64_X18: + return PERF_REG_ARM64_X18; + case UNW_AARCH64_X19: + return PERF_REG_ARM64_X19; + case UNW_AARCH64_X20: + return PERF_REG_ARM64_X20; + case UNW_AARCH64_X21: + return PERF_REG_ARM64_X21; + case UNW_AARCH64_X22: + return PERF_REG_ARM64_X22; + case UNW_AARCH64_X23: + return PERF_REG_ARM64_X23; + case UNW_AARCH64_X24: + return PERF_REG_ARM64_X24; + case UNW_AARCH64_X25: + return PERF_REG_ARM64_X25; + case UNW_AARCH64_X26: + return PERF_REG_ARM64_X26; + case UNW_AARCH64_X27: + return PERF_REG_ARM64_X27; + case UNW_AARCH64_X28: + return PERF_REG_ARM64_X28; + case UNW_AARCH64_X29: + return PERF_REG_ARM64_X29; + case UNW_AARCH64_X30: + return PERF_REG_ARM64_LR; + case UNW_AARCH64_SP: + return PERF_REG_ARM64_SP; + case UNW_AARCH64_PC: + return PERF_REG_ARM64_PC; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return -EINVAL; +} diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 8801fe02f206..1641542e3636 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -3,7 +3,14 @@ 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.o +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 diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index e84ca76aae77..7df517acfef8 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -2,17 +2,23 @@ #define ARCH_PERF_REGS_H #include <stdlib.h> -#include "../../util/types.h" +#include <linux/types.h> #include <asm/perf_regs.h> +void perf_regs_load(u64 *regs); + #ifndef HAVE_ARCH_X86_64_SUPPORT #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_X86_32_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 #else #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ (1ULL << PERF_REG_X86_ES) | \ (1ULL << PERF_REG_X86_FS) | \ (1ULL << PERF_REG_X86_GS)) #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT) +#define PERF_REGS_MAX PERF_REG_X86_64_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 #endif #define PERF_REG_IP PERF_REG_X86_IP #define PERF_REG_SP PERF_REG_X86_SP diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c new file mode 100644 index 000000000000..9f89f899ccc7 --- /dev/null +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -0,0 +1,60 @@ +#include <string.h> +#include "perf_regs.h" +#include "thread.h" +#include "map.h" +#include "event.h" +#include "tests/tests.h" + +#define STACK_SIZE 8192 + +static int sample_ustack(struct perf_sample *sample, + struct thread *thread, u64 *regs) +{ + struct stack_dump *stack = &sample->user_stack; + struct map *map; + unsigned long sp; + u64 stack_size, *buf; + + buf = malloc(STACK_SIZE); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + sp = (unsigned long) regs[PERF_REG_X86_SP]; + + map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + if (!map) { + pr_debug("failed to get stack map\n"); + free(buf); + return -1; + } + + stack_size = map->end - sp; + stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; + + memcpy(buf, (void *) sp, stack_size); + stack->data = (char *) buf; + stack->size = stack_size; + return 0; +} + +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread) +{ + struct regs_dump *regs = &sample->user_regs; + u64 *buf; + + buf = malloc(sizeof(u64) * PERF_REGS_MAX); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + perf_regs_load(buf); + regs->abi = PERF_SAMPLE_REGS_ABI; + regs->regs = buf; + regs->mask = PERF_REGS_MASK; + + return sample_ustack(sample, thread, buf); +} diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S new file mode 100644 index 000000000000..60875d5c556c --- /dev/null +++ b/tools/perf/arch/x86/tests/regs_load.S @@ -0,0 +1,98 @@ +#include <linux/linkage.h> + +#define AX 0 +#define BX 1 * 8 +#define CX 2 * 8 +#define DX 3 * 8 +#define SI 4 * 8 +#define DI 5 * 8 +#define BP 6 * 8 +#define SP 7 * 8 +#define IP 8 * 8 +#define FLAGS 9 * 8 +#define CS 10 * 8 +#define SS 11 * 8 +#define DS 12 * 8 +#define ES 13 * 8 +#define FS 14 * 8 +#define GS 15 * 8 +#define R8 16 * 8 +#define R9 17 * 8 +#define R10 18 * 8 +#define R11 19 * 8 +#define R12 20 * 8 +#define R13 21 * 8 +#define R14 22 * 8 +#define R15 23 * 8 + +.text +#ifdef HAVE_ARCH_X86_64_SUPPORT +ENTRY(perf_regs_load) + movq %rax, AX(%rdi) + movq %rbx, BX(%rdi) + movq %rcx, CX(%rdi) + movq %rdx, DX(%rdi) + movq %rsi, SI(%rdi) + movq %rdi, DI(%rdi) + movq %rbp, BP(%rdi) + + leaq 8(%rsp), %rax /* exclude this call. */ + movq %rax, SP(%rdi) + + movq 0(%rsp), %rax + movq %rax, IP(%rdi) + + movq $0, FLAGS(%rdi) + movq $0, CS(%rdi) + movq $0, SS(%rdi) + movq $0, DS(%rdi) + movq $0, ES(%rdi) + movq $0, FS(%rdi) + movq $0, GS(%rdi) + + movq %r8, R8(%rdi) + movq %r9, R9(%rdi) + movq %r10, R10(%rdi) + movq %r11, R11(%rdi) + movq %r12, R12(%rdi) + movq %r13, R13(%rdi) + movq %r14, R14(%rdi) + movq %r15, R15(%rdi) + ret +ENDPROC(perf_regs_load) +#else +ENTRY(perf_regs_load) + push %edi + movl 8(%esp), %edi + movl %eax, AX(%edi) + movl %ebx, BX(%edi) + movl %ecx, CX(%edi) + movl %edx, DX(%edi) + movl %esi, SI(%edi) + pop %eax + movl %eax, DI(%edi) + movl %ebp, BP(%edi) + + leal 4(%esp), %eax /* exclude this call. */ + movl %eax, SP(%edi) + + movl 0(%esp), %eax + movl %eax, IP(%edi) + + movl $0, FLAGS(%edi) + movl $0, CS(%edi) + movl $0, SS(%edi) + movl $0, DS(%edi) + movl $0, ES(%edi) + movl $0, FS(%edi) + movl $0, GS(%edi) + ret +ENDPROC(perf_regs_load) +#endif + +/* + * We need to provide note.GNU-stack section, saying that we want + * NOT executable stack. Otherwise the final linking will assume that + * the ELF stack should not be restricted at all and set it RWX. + */ +.section .note.GNU-stack,"",@progbits diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index b2519e49424f..40021fa3129b 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -4,7 +4,7 @@ #include <linux/perf_event.h> #include "../../perf.h" -#include "../../util/types.h" +#include <linux/types.h> #include "../../util/debug.h" #include "tsc.h" diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h index a24dec81c795..2affe0366b59 100644 --- a/tools/perf/arch/x86/util/tsc.h +++ b/tools/perf/arch/x86/util/tsc.h @@ -1,7 +1,7 @@ #ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ #define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ -#include "../../util/types.h" +#include <linux/types.h> struct perf_tsc_conversion { u16 time_shift; diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c new file mode 100644 index 000000000000..c4b72176ca83 --- /dev/null +++ b/tools/perf/arch/x86/util/unwind-libdw.c @@ -0,0 +1,51 @@ +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[17]; + unsigned nregs; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_X86_##r); \ + val; \ +}) + + if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) { + dwarf_regs[0] = REG(AX); + dwarf_regs[1] = REG(CX); + dwarf_regs[2] = REG(DX); + dwarf_regs[3] = REG(BX); + dwarf_regs[4] = REG(SP); + dwarf_regs[5] = REG(BP); + dwarf_regs[6] = REG(SI); + dwarf_regs[7] = REG(DI); + dwarf_regs[8] = REG(IP); + nregs = 9; + } else { + dwarf_regs[0] = REG(AX); + dwarf_regs[1] = REG(DX); + dwarf_regs[2] = REG(CX); + dwarf_regs[3] = REG(BX); + dwarf_regs[4] = REG(SI); + dwarf_regs[5] = REG(DI); + dwarf_regs[6] = REG(BP); + dwarf_regs[7] = REG(SP); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(IP); + nregs = 17; + } + + return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs); +} diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 456a88cf5b37..3261f68c6a7c 100644 --- a/tools/perf/arch/x86/util/unwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -5,7 +5,7 @@ #include "../../util/unwind.h" #ifdef HAVE_ARCH_X86_64_SUPPORT -int unwind__arch_reg_id(int regnum) +int libunwind__arch_reg_id(int regnum) { int id; @@ -69,7 +69,7 @@ int unwind__arch_reg_id(int regnum) return id; } #else -int unwind__arch_reg_id(int regnum) +int libunwind__arch_reg_id(int regnum) { int id; diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 0fdc85269c4d..eba46709b279 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -31,6 +31,9 @@ extern int bench_sched_pipe(int argc, const char **argv, const char *prefix); extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused); extern int bench_mem_memset(int argc, const char **argv, const char *prefix); +extern int bench_futex_hash(int argc, const char **argv, const char *prefix); +extern int bench_futex_wake(int argc, const char **argv, const char *prefix); +extern int bench_futex_requeue(int argc, const char **argv, const char *prefix); #define BENCH_FORMAT_DEFAULT_STR "default" #define BENCH_FORMAT_DEFAULT 0 diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c new file mode 100644 index 000000000000..a84206e9c4aa --- /dev/null +++ b/tools/perf/bench/futex-hash.c @@ -0,0 +1,212 @@ +/* + * Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com> + * + * futex-hash: Stress the hell out of the Linux kernel futex uaddr hashing. + * + * This program is particularly useful for measuring the kernel's futex hash + * table/function implementation. In order for it to make sense, use with as + * many threads and futexes as possible. + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/stat.h" +#include "../util/parse-options.h" +#include "../util/header.h" +#include "bench.h" +#include "futex.h" + +#include <err.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> + +static unsigned int nthreads = 0; +static unsigned int nsecs = 10; +/* amount of futexes per thread */ +static unsigned int nfutexes = 1024; +static bool fshared = false, done = false, silent = false; + +struct timeval start, end, runtime; +static pthread_mutex_t thread_lock; +static unsigned int threads_starting; +static struct stats throughput_stats; +static pthread_cond_t thread_parent, thread_worker; + +struct worker { + int tid; + u_int32_t *futex; + pthread_t thread; + unsigned long ops; +}; + +static const struct option options[] = { + OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), + OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"), + OPT_UINTEGER('f', "futexes", &nfutexes, "Specify amount of futexes per threads"), + OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"), + OPT_END() +}; + +static const char * const bench_futex_hash_usage[] = { + "perf bench futex hash <options>", + NULL +}; + +static void *workerfn(void *arg) +{ + int ret; + unsigned int i; + struct worker *w = (struct worker *) arg; + + pthread_mutex_lock(&thread_lock); + threads_starting--; + if (!threads_starting) + pthread_cond_signal(&thread_parent); + pthread_cond_wait(&thread_worker, &thread_lock); + pthread_mutex_unlock(&thread_lock); + + do { + for (i = 0; i < nfutexes; i++, w->ops++) { + /* + * We want the futex calls to fail in order to stress + * the hashing of uaddr and not measure other steps, + * such as internal waitqueue handling, thus enlarging + * the critical region protected by hb->lock. + */ + ret = futex_wait(&w->futex[i], 1234, NULL, + fshared ? 0 : FUTEX_PRIVATE_FLAG); + if (!silent && + (!ret || errno != EAGAIN || errno != EWOULDBLOCK)) + warn("Non-expected futex return call"); + } + } while (!done); + + return NULL; +} + +static void toggle_done(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + /* inform all threads that we're done for the day */ + done = true; + gettimeofday(&end, NULL); + timersub(&end, &start, &runtime); +} + +static void print_summary(void) +{ + unsigned long avg = avg_stats(&throughput_stats); + double stddev = stddev_stats(&throughput_stats); + + printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", + !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), + (int) runtime.tv_sec); +} + +int bench_futex_hash(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + int ret = 0; + cpu_set_t cpu; + struct sigaction act; + unsigned int i, ncpus; + pthread_attr_t thread_attr; + struct worker *worker = NULL; + + argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); + if (argc) { + usage_with_options(bench_futex_hash_usage, options); + exit(EXIT_FAILURE); + } + + ncpus = sysconf(_SC_NPROCESSORS_ONLN); + + sigfillset(&act.sa_mask); + act.sa_sigaction = toggle_done; + sigaction(SIGINT, &act, NULL); + + if (!nthreads) /* default to the number of CPUs */ + nthreads = ncpus; + + worker = calloc(nthreads, sizeof(*worker)); + if (!worker) + goto errmem; + + printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n", + getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs); + + init_stats(&throughput_stats); + pthread_mutex_init(&thread_lock, NULL); + pthread_cond_init(&thread_parent, NULL); + pthread_cond_init(&thread_worker, NULL); + + threads_starting = nthreads; + pthread_attr_init(&thread_attr); + gettimeofday(&start, NULL); + for (i = 0; i < nthreads; i++) { + worker[i].tid = i; + worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex)); + if (!worker[i].futex) + goto errmem; + + CPU_ZERO(&cpu); + CPU_SET(i % ncpus, &cpu); + + ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu); + if (ret) + err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + + ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, + (void *)(struct worker *) &worker[i]); + if (ret) + err(EXIT_FAILURE, "pthread_create"); + + } + pthread_attr_destroy(&thread_attr); + + pthread_mutex_lock(&thread_lock); + while (threads_starting) + pthread_cond_wait(&thread_parent, &thread_lock); + pthread_cond_broadcast(&thread_worker); + pthread_mutex_unlock(&thread_lock); + + sleep(nsecs); + toggle_done(0, NULL, NULL); + + for (i = 0; i < nthreads; i++) { + ret = pthread_join(worker[i].thread, NULL); + if (ret) + err(EXIT_FAILURE, "pthread_join"); + } + + /* cleanup & report results */ + pthread_cond_destroy(&thread_parent); + pthread_cond_destroy(&thread_worker); + pthread_mutex_destroy(&thread_lock); + + for (i = 0; i < nthreads; i++) { + unsigned long t = worker[i].ops/runtime.tv_sec; + update_stats(&throughput_stats, t); + if (!silent) { + if (nfutexes == 1) + printf("[thread %2d] futex: %p [ %ld ops/sec ]\n", + worker[i].tid, &worker[i].futex[0], t); + else + printf("[thread %2d] futexes: %p ... %p [ %ld ops/sec ]\n", + worker[i].tid, &worker[i].futex[0], + &worker[i].futex[nfutexes-1], t); + } + + free(worker[i].futex); + } + + print_summary(); + + free(worker); + return ret; +errmem: + err(EXIT_FAILURE, "calloc"); +} diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c new file mode 100644 index 000000000000..a16255876f1d --- /dev/null +++ b/tools/perf/bench/futex-requeue.c @@ -0,0 +1,211 @@ +/* + * Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com> + * + * futex-requeue: Block a bunch of threads on futex1 and requeue them + * on futex2, N at a time. + * + * This program is particularly useful to measure the latency of nthread + * requeues without waking up any tasks -- thus mimicking a regular futex_wait. + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/stat.h" +#include "../util/parse-options.h" +#include "../util/header.h" +#include "bench.h" +#include "futex.h" + +#include <err.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> + +static u_int32_t futex1 = 0, futex2 = 0; + +/* + * How many tasks to requeue at a time. + * Default to 1 in order to make the kernel work more. + */ +static unsigned int nrequeue = 1; + +/* + * There can be significant variance from run to run, + * the more repeats, the more exact the overall avg and + * the better idea of the futex latency. + */ +static unsigned int repeat = 10; + +static pthread_t *worker; +static bool done = 0, silent = 0; +static pthread_mutex_t thread_lock; +static pthread_cond_t thread_parent, thread_worker; +static struct stats requeuetime_stats, requeued_stats; +static unsigned int ncpus, threads_starting, nthreads = 0; + +static const struct option options[] = { + OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), + OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"), + OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), + OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_END() +}; + +static const char * const bench_futex_requeue_usage[] = { + "perf bench futex requeue <options>", + NULL +}; + +static void print_summary(void) +{ + double requeuetime_avg = avg_stats(&requeuetime_stats); + double requeuetime_stddev = stddev_stats(&requeuetime_stats); + unsigned int requeued_avg = avg_stats(&requeued_stats); + + printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n", + requeued_avg, + nthreads, + requeuetime_avg/1e3, + rel_stddev_stats(requeuetime_stddev, requeuetime_avg)); +} + +static void *workerfn(void *arg __maybe_unused) +{ + pthread_mutex_lock(&thread_lock); + threads_starting--; + if (!threads_starting) + pthread_cond_signal(&thread_parent); + pthread_cond_wait(&thread_worker, &thread_lock); + pthread_mutex_unlock(&thread_lock); + + futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG); + return NULL; +} + +static void block_threads(pthread_t *w, + pthread_attr_t thread_attr) +{ + cpu_set_t cpu; + unsigned int i; + + threads_starting = nthreads; + + /* create and block all threads */ + for (i = 0; i < nthreads; i++) { + CPU_ZERO(&cpu); + CPU_SET(i % ncpus, &cpu); + + if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu)) + err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + err(EXIT_FAILURE, "pthread_create"); + } +} + +static void toggle_done(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + done = true; +} + +int bench_futex_requeue(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + int ret = 0; + unsigned int i, j; + struct sigaction act; + pthread_attr_t thread_attr; + + argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0); + if (argc) + goto err; + + ncpus = sysconf(_SC_NPROCESSORS_ONLN); + + sigfillset(&act.sa_mask); + act.sa_sigaction = toggle_done; + sigaction(SIGINT, &act, NULL); + + if (!nthreads) + nthreads = ncpus; + + worker = calloc(nthreads, sizeof(*worker)); + if (!worker) + err(EXIT_FAILURE, "calloc"); + + printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), " + "%d at a time.\n\n", + getpid(), nthreads, &futex1, &futex2, nrequeue); + + init_stats(&requeued_stats); + init_stats(&requeuetime_stats); + pthread_attr_init(&thread_attr); + pthread_mutex_init(&thread_lock, NULL); + pthread_cond_init(&thread_parent, NULL); + pthread_cond_init(&thread_worker, NULL); + + for (j = 0; j < repeat && !done; j++) { + unsigned int nrequeued = 0; + struct timeval start, end, runtime; + + /* create, launch & block all threads */ + block_threads(worker, thread_attr); + + /* make sure all threads are already blocked */ + pthread_mutex_lock(&thread_lock); + while (threads_starting) + pthread_cond_wait(&thread_parent, &thread_lock); + pthread_cond_broadcast(&thread_worker); + pthread_mutex_unlock(&thread_lock); + + usleep(100000); + + /* Ok, all threads are patiently blocked, start requeueing */ + gettimeofday(&start, NULL); + for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) + /* + * Do not wakeup any tasks blocked on futex1, allowing + * us to really measure futex_wait functionality. + */ + futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue, + FUTEX_PRIVATE_FLAG); + gettimeofday(&end, NULL); + timersub(&end, &start, &runtime); + + update_stats(&requeued_stats, nrequeued); + update_stats(&requeuetime_stats, runtime.tv_usec); + + if (!silent) { + printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n", + j + 1, nrequeued, nthreads, runtime.tv_usec/1e3); + } + + /* everybody should be blocked on futex2, wake'em up */ + nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG); + if (nthreads != nrequeued) + warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads); + + for (i = 0; i < nthreads; i++) { + ret = pthread_join(worker[i], NULL); + if (ret) + err(EXIT_FAILURE, "pthread_join"); + } + + } + + /* cleanup & report results */ + pthread_cond_destroy(&thread_parent); + pthread_cond_destroy(&thread_worker); + pthread_mutex_destroy(&thread_lock); + pthread_attr_destroy(&thread_attr); + + print_summary(); + + free(worker); + return ret; +err: + usage_with_options(bench_futex_requeue_usage, options); + exit(EXIT_FAILURE); +} diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c new file mode 100644 index 000000000000..d096169b161e --- /dev/null +++ b/tools/perf/bench/futex-wake.c @@ -0,0 +1,201 @@ +/* + * Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com> + * + * futex-wake: Block a bunch of threads on a futex and wake'em up, N at a time. + * + * This program is particularly useful to measure the latency of nthread wakeups + * in non-error situations: all waiters are queued and all wake calls wakeup + * one or more tasks, and thus the waitqueue is never empty. + */ + +#include "../perf.h" +#include "../util/util.h" +#include "../util/stat.h" +#include "../util/parse-options.h" +#include "../util/header.h" +#include "bench.h" +#include "futex.h" + +#include <err.h> +#include <stdlib.h> +#include <sys/time.h> +#include <pthread.h> + +/* all threads will block on the same futex */ +static u_int32_t futex1 = 0; + +/* + * How many wakeups to do at a time. + * Default to 1 in order to make the kernel work more. + */ +static unsigned int nwakes = 1; + +/* + * There can be significant variance from run to run, + * the more repeats, the more exact the overall avg and + * the better idea of the futex latency. + */ +static unsigned int repeat = 10; + +pthread_t *worker; +static bool done = 0, silent = 0; +static pthread_mutex_t thread_lock; +static pthread_cond_t thread_parent, thread_worker; +static struct stats waketime_stats, wakeup_stats; +static unsigned int ncpus, threads_starting, nthreads = 0; + +static const struct option options[] = { + OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"), + OPT_UINTEGER('w', "nwakes", &nwakes, "Specify amount of threads to wake at once"), + OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"), + OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), + OPT_END() +}; + +static const char * const bench_futex_wake_usage[] = { + "perf bench futex wake <options>", + NULL +}; + +static void *workerfn(void *arg __maybe_unused) +{ + pthread_mutex_lock(&thread_lock); + threads_starting--; + if (!threads_starting) + pthread_cond_signal(&thread_parent); + pthread_cond_wait(&thread_worker, &thread_lock); + pthread_mutex_unlock(&thread_lock); + + futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG); + return NULL; +} + +static void print_summary(void) +{ + double waketime_avg = avg_stats(&waketime_stats); + double waketime_stddev = stddev_stats(&waketime_stats); + unsigned int wakeup_avg = avg_stats(&wakeup_stats); + + printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n", + wakeup_avg, + nthreads, + waketime_avg/1e3, + rel_stddev_stats(waketime_stddev, waketime_avg)); +} + +static void block_threads(pthread_t *w, + pthread_attr_t thread_attr) +{ + cpu_set_t cpu; + unsigned int i; + + threads_starting = nthreads; + + /* create and block all threads */ + for (i = 0; i < nthreads; i++) { + CPU_ZERO(&cpu); + CPU_SET(i % ncpus, &cpu); + + if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu)) + err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + err(EXIT_FAILURE, "pthread_create"); + } +} + +static void toggle_done(int sig __maybe_unused, + siginfo_t *info __maybe_unused, + void *uc __maybe_unused) +{ + done = true; +} + +int bench_futex_wake(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + int ret = 0; + unsigned int i, j; + struct sigaction act; + pthread_attr_t thread_attr; + + argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0); + if (argc) { + usage_with_options(bench_futex_wake_usage, options); + exit(EXIT_FAILURE); + } + + ncpus = sysconf(_SC_NPROCESSORS_ONLN); + + sigfillset(&act.sa_mask); + act.sa_sigaction = toggle_done; + sigaction(SIGINT, &act, NULL); + + if (!nthreads) + nthreads = ncpus; + + worker = calloc(nthreads, sizeof(*worker)); + if (!worker) + err(EXIT_FAILURE, "calloc"); + + printf("Run summary [PID %d]: blocking on %d threads (at futex %p), " + "waking up %d at a time.\n\n", + getpid(), nthreads, &futex1, nwakes); + + init_stats(&wakeup_stats); + init_stats(&waketime_stats); + pthread_attr_init(&thread_attr); + pthread_mutex_init(&thread_lock, NULL); + pthread_cond_init(&thread_parent, NULL); + pthread_cond_init(&thread_worker, NULL); + + for (j = 0; j < repeat && !done; j++) { + unsigned int nwoken = 0; + struct timeval start, end, runtime; + + /* create, launch & block all threads */ + block_threads(worker, thread_attr); + + /* make sure all threads are already blocked */ + pthread_mutex_lock(&thread_lock); + while (threads_starting) + pthread_cond_wait(&thread_parent, &thread_lock); + pthread_cond_broadcast(&thread_worker); + pthread_mutex_unlock(&thread_lock); + + usleep(100000); + + /* Ok, all threads are patiently blocked, start waking folks up */ + gettimeofday(&start, NULL); + while (nwoken != nthreads) + nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG); + gettimeofday(&end, NULL); + timersub(&end, &start, &runtime); + + update_stats(&wakeup_stats, nwoken); + update_stats(&waketime_stats, runtime.tv_usec); + + if (!silent) { + printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n", + j + 1, nwoken, nthreads, runtime.tv_usec/1e3); + } + + for (i = 0; i < nthreads; i++) { + ret = pthread_join(worker[i], NULL); + if (ret) + err(EXIT_FAILURE, "pthread_join"); + } + + } + + /* cleanup & report results */ + pthread_cond_destroy(&thread_parent); + pthread_cond_destroy(&thread_worker); + pthread_mutex_destroy(&thread_lock); + pthread_attr_destroy(&thread_attr); + + print_summary(); + + free(worker); + return ret; +} diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h new file mode 100644 index 000000000000..71f2844cf97f --- /dev/null +++ b/tools/perf/bench/futex.h @@ -0,0 +1,71 @@ +/* + * Glibc independent futex library for testing kernel functionality. + * Shamelessly stolen from Darren Hart <dvhltc@us.ibm.com> + * http://git.kernel.org/cgit/linux/kernel/git/dvhart/futextest.git/ + */ + +#ifndef _FUTEX_H +#define _FUTEX_H + +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <linux/futex.h> + +/** + * futex() - SYS_futex syscall wrapper + * @uaddr: address of first futex + * @op: futex op code + * @val: typically expected value of uaddr, but varies by op + * @timeout: typically an absolute struct timespec (except where noted + * otherwise). Overloaded by some ops + * @uaddr2: address of second futex for some ops\ + * @val3: varies by op + * @opflags: flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG + * + * futex() is used by all the following futex op wrappers. It can also be + * used for misuse and abuse testing. Generally, the specific op wrappers + * should be used instead. It is a macro instead of an static inline function as + * some of the types over overloaded (timeout is used for nr_requeue for + * example). + * + * These argument descriptions are the defaults for all + * like-named arguments in the following wrappers except where noted below. + */ +#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \ + syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3) + +/** + * futex_wait() - block on uaddr with optional timeout + * @timeout: relative timeout + */ +static inline int +futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflags) +{ + return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags); +} + +/** + * futex_wake() - wake one or more tasks blocked on uaddr + * @nr_wake: wake up to this many tasks + */ +static inline int +futex_wake(u_int32_t *uaddr, int nr_wake, int opflags) +{ + return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags); +} + +/** +* futex_cmp_requeue() - requeue tasks from uaddr to uaddr2 +* @nr_wake: wake up to this many tasks +* @nr_requeue: requeue up to this many tasks +*/ +static inline int +futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake, + int nr_requeue, int opflags) +{ + return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2, + val, opflags); +} + +#endif /* _FUTEX_H */ diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 97d86d828190..ebfa163b80b5 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -1593,6 +1593,10 @@ static void init_params(struct params *p, const char *name, int argc, const char p->data_rand_walk = true; p->nr_loops = -1; p->init_random = true; + p->mb_global_str = "1"; + p->nr_proc = 1; + p->nr_threads = 1; + p->nr_secs = 5; p->run_all = argc == 1; } diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 0da603b79b61..d30d2c2e2a7a 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -46,7 +46,7 @@ struct perf_annotate { }; static int perf_evsel__add_sample(struct perf_evsel *evsel, - struct perf_sample *sample, + struct perf_sample *sample __maybe_unused, struct addr_location *al, struct perf_annotate *ann) { @@ -70,7 +70,6 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return -ENOMEM; ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - evsel->hists.stats.total_period += sample->period; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); return ret; } diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 8a987d252780..1e6e77710545 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -12,6 +12,7 @@ * sched ... scheduler and IPC performance * mem ... memory access performance * numa ... NUMA scheduling and MM performance + * futex ... Futex performance */ #include "perf.h" #include "util/util.h" @@ -54,6 +55,14 @@ static struct bench mem_benchmarks[] = { { NULL, NULL, NULL } }; +static struct bench futex_benchmarks[] = { + { "hash", "Benchmark for futex hash table", bench_futex_hash }, + { "wake", "Benchmark for futex wake calls", bench_futex_wake }, + { "requeue", "Benchmark for futex requeue calls", bench_futex_requeue }, + { "all", "Test all futex benchmarks", NULL }, + { NULL, NULL, NULL } +}; + struct collection { const char *name; const char *summary; @@ -61,11 +70,12 @@ struct collection { }; static struct collection collections[] = { - { "sched", "Scheduler and IPC benchmarks", sched_benchmarks }, + { "sched", "Scheduler and IPC benchmarks", sched_benchmarks }, { "mem", "Memory access benchmarks", mem_benchmarks }, #ifdef HAVE_LIBNUMA_SUPPORT { "numa", "NUMA scheduling and MM benchmarks", numa_benchmarks }, #endif + {"futex", "Futex stressing benchmarks", futex_benchmarks }, { "all", "All benchmarks", NULL }, { NULL, NULL, NULL } }; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index a77e31246c00..8bff543acaab 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -60,7 +60,6 @@ static int data__files_cnt; #define data__for_each_file(i, d) data__for_each_file_start(i, d, 0) #define data__for_each_file_new(i, d) data__for_each_file_start(i, d, 1) -static char diff__default_sort_order[] = "dso,symbol"; static bool force; static bool show_period; static bool show_formula; @@ -220,7 +219,8 @@ static int setup_compute(const struct option *opt, const char *str, static double period_percent(struct hist_entry *he, u64 period) { - u64 total = he->hists->stats.total_period; + u64 total = hists__total_period(he->hists); + return (period * 100.0) / total; } @@ -259,11 +259,18 @@ static s64 compute_wdiff(struct hist_entry *he, struct hist_entry *pair) static int formula_delta(struct hist_entry *he, struct hist_entry *pair, char *buf, size_t size) { + u64 he_total = he->hists->stats.total_period; + u64 pair_total = pair->hists->stats.total_period; + + if (symbol_conf.filter_relative) { + he_total = he->hists->stats.total_non_filtered_period; + pair_total = pair->hists->stats.total_non_filtered_period; + } return scnprintf(buf, size, "(%" PRIu64 " * 100 / %" PRIu64 ") - " "(%" PRIu64 " * 100 / %" PRIu64 ")", - pair->stat.period, pair->hists->stats.total_period, - he->stat.period, he->hists->stats.total_period); + pair->stat.period, pair_total, + he->stat.period, he_total); } static int formula_ratio(struct hist_entry *he, struct hist_entry *pair, @@ -327,16 +334,22 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (al.filtered) - return 0; - if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight, sample->transaction)) { pr_warning("problem incrementing symbol period, skipping event\n"); return -1; } + /* + * The total_period is updated here before going to the output + * tree since normally only the baseline hists will call + * hists__output_resort() and precompute needs the total + * period in order to sort entries by percentage delta. + */ evsel->hists.stats.total_period += sample->period; + if (!al.filtered) + evsel->hists.stats.total_non_filtered_period += sample->period; + return 0; } @@ -564,8 +577,7 @@ static void hists__compute_resort(struct hists *hists) hists->entries = RB_ROOT; next = rb_first(root); - hists->nr_entries = 0; - hists->stats.total_period = 0; + hists__reset_stats(hists); hists__reset_col_len(hists); while (next != NULL) { @@ -575,7 +587,10 @@ static void hists__compute_resort(struct hists *hists) next = rb_next(&he->rb_node_in); insert_hist_entry_by_compute(&hists->entries, he, compute); - hists__inc_nr_entries(hists, he); + hists__inc_stats(hists, he); + + if (!he->filtered) + hists__calc_col_len(hists, he); } } @@ -725,20 +740,24 @@ static const struct option options[] = { OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent"), + "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..." + " Please refer the man page for the complete list."), OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator", "separator for columns, no spaces will be added between " "columns '.' is reserved."), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."), + OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", + "How to display percentage of filtered entries", parse_filter_percentage), OPT_END() }; static double baseline_percent(struct hist_entry *he) { - struct hists *hists = he->hists; - return 100.0 * he->stat.period / hists->stats.total_period; + u64 total = hists__total_period(he->hists); + + return 100.0 * he->stat.period / total; } static int hpp__color_baseline(struct perf_hpp_fmt *fmt, @@ -952,8 +971,8 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp, dfmt->header_width, buf); } -static int hpp__header(struct perf_hpp_fmt *fmt, - struct perf_hpp *hpp) +static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel __maybe_unused) { struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt); @@ -963,7 +982,8 @@ static int hpp__header(struct perf_hpp_fmt *fmt, } static int hpp__width(struct perf_hpp_fmt *fmt, - struct perf_hpp *hpp __maybe_unused) + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel __maybe_unused) { struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt); @@ -1119,7 +1139,8 @@ static int data_init(int argc, const char **argv) int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) { - sort_order = diff__default_sort_order; + perf_config(perf_default_config, NULL); + argc = parse_options(argc, argv, options, diff_usage, 0); if (symbol__init() < 0) @@ -1130,6 +1151,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) ui_init(); + sort__mode = SORT_MODE__DIFF; + if (setup_sorting() < 0) usage_with_options(diff_usage, options); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index b3466018bbd7..6a3af0013d68 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -209,7 +209,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - thread = machine__findnew_thread(machine, sample->pid, sample->pid); + thread = machine__findnew_thread(machine, sample->pid, sample->tid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", event->header.type); @@ -312,7 +312,6 @@ found: sample_sw.period = sample->period; sample_sw.time = sample->time; perf_event__synthesize_sample(event_sw, evsel->attr.sample_type, - evsel->attr.sample_regs_user, evsel->attr.read_format, &sample_sw, false); build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 929462aa4943..bef3376bfaf3 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -14,6 +14,7 @@ #include "util/parse-options.h" #include "util/trace-event.h" #include "util/data.h" +#include "util/cpumap.h" #include "util/debug.h" @@ -31,9 +32,6 @@ static int caller_lines = -1; static bool raw_ip; -static int *cpunode_map; -static int max_cpu_num; - struct alloc_stat { u64 call_site; u64 ptr; @@ -55,76 +53,6 @@ static struct rb_root root_caller_sorted; static unsigned long total_requested, total_allocated; static unsigned long nr_allocs, nr_cross_allocs; -#define PATH_SYS_NODE "/sys/devices/system/node" - -static int init_cpunode_map(void) -{ - FILE *fp; - int i, err = -1; - - fp = fopen("/sys/devices/system/cpu/kernel_max", "r"); - if (!fp) { - max_cpu_num = 4096; - return 0; - } - - if (fscanf(fp, "%d", &max_cpu_num) < 1) { - pr_err("Failed to read 'kernel_max' from sysfs"); - goto out_close; - } - - max_cpu_num++; - - cpunode_map = calloc(max_cpu_num, sizeof(int)); - if (!cpunode_map) { - pr_err("%s: calloc failed\n", __func__); - goto out_close; - } - - for (i = 0; i < max_cpu_num; i++) - cpunode_map[i] = -1; - - err = 0; -out_close: - fclose(fp); - return err; -} - -static int setup_cpunode_map(void) -{ - struct dirent *dent1, *dent2; - DIR *dir1, *dir2; - unsigned int cpu, mem; - char buf[PATH_MAX]; - - if (init_cpunode_map()) - return -1; - - dir1 = opendir(PATH_SYS_NODE); - if (!dir1) - return 0; - - while ((dent1 = readdir(dir1)) != NULL) { - if (dent1->d_type != DT_DIR || - sscanf(dent1->d_name, "node%u", &mem) < 1) - continue; - - snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name); - dir2 = opendir(buf); - if (!dir2) - continue; - while ((dent2 = readdir(dir2)) != NULL) { - if (dent2->d_type != DT_LNK || - sscanf(dent2->d_name, "cpu%u", &cpu) < 1) - continue; - cpunode_map[cpu] = mem; - } - closedir(dir2); - } - closedir(dir1); - return 0; -} - static int insert_alloc_stat(unsigned long call_site, unsigned long ptr, int bytes_req, int bytes_alloc, int cpu) { @@ -235,7 +163,7 @@ static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel, int ret = perf_evsel__process_alloc_event(evsel, sample); if (!ret) { - int node1 = cpunode_map[sample->cpu], + int node1 = cpu__get_node(sample->cpu), node2 = perf_evsel__intval(evsel, sample, "node"); if (node1 != node2) @@ -307,7 +235,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct machine *machine) { struct thread *thread = machine__findnew_thread(machine, sample->pid, - sample->pid); + sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", @@ -756,11 +684,13 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"), OPT_END() }; - const char * const kmem_usage[] = { - "perf kmem [<options>] {record|stat}", + const char *const kmem_subcommands[] = { "record", "stat", NULL }; + const char *kmem_usage[] = { + NULL, NULL }; - argc = parse_options(argc, argv, kmem_options, kmem_usage, 0); + argc = parse_options_subcommand(argc, argv, kmem_options, + kmem_subcommands, kmem_usage, 0); if (!argc) usage_with_options(kmem_usage, kmem_options); @@ -770,7 +700,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); } else if (!strcmp(argv[0], "stat")) { - if (setup_cpunode_map()) + if (cpu__setup_cpunode_map()) return -1; if (list_empty(&caller_sort)) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index a7350519c63f..0f1e5a2f6ad7 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -404,6 +404,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key) } event->key = *key; + init_stats(&event->total.stats); return event; } @@ -1691,17 +1692,15 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) OPT_END() }; - - const char * const kvm_usage[] = { - "perf kvm [<options>] {top|record|report|diff|buildid-list|stat}", - NULL - }; + const char *const kvm_subcommands[] = { "top", "record", "report", "diff", + "buildid-list", "stat", NULL }; + const char *kvm_usage[] = { NULL, NULL }; perf_host = 0; perf_guest = 1; - argc = parse_options(argc, argv, kvm_options, kvm_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, kvm_options, kvm_subcommands, kvm_usage, + PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) usage_with_options(kvm_usage, kvm_options); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index c852c7a85d32..6148afc995c6 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -961,8 +961,10 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) "perf lock info [<options>]", NULL }; - const char * const lock_usage[] = { - "perf lock [<options>] {record|report|script|info}", + const char *const lock_subcommands[] = { "record", "report", "script", + "info", NULL }; + const char *lock_usage[] = { + NULL, NULL }; const char * const report_usage[] = { @@ -976,8 +978,8 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) for (i = 0; i < LOCKHASH_SIZE; i++) INIT_LIST_HEAD(lockhash_table + i); - argc = parse_options(argc, argv, lock_options, lock_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, lock_options, lock_subcommands, + lock_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) usage_with_options(lock_usage, lock_options); diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 2e3ade69a58e..4a1a6c94a5eb 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -21,11 +21,6 @@ struct perf_mem { DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; -static const char * const mem_usage[] = { - "perf mem [<options>] {record <command> |report}", - NULL -}; - static int __cmd_record(int argc, const char **argv) { int rec_argc, i = 0, j; @@ -220,9 +215,15 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) " between columns '.' is reserved."), OPT_END() }; + const char *const mem_subcommands[] = { "record", "report", NULL }; + const char *mem_usage[] = { + NULL, + NULL + }; + - argc = parse_options(argc, argv, mem_options, mem_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, + mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation)) usage_with_options(mem_usage, mem_options); diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 78948882e3de..cdcd4eb3a57d 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -268,9 +268,9 @@ static int opt_set_filter(const struct option *opt __maybe_unused, return 0; } -static void init_params(void) +static int init_params(void) { - line_range__init(¶ms.line_range); + return line_range__init(¶ms.line_range); } static void cleanup_params(void) @@ -515,9 +515,11 @@ int cmd_probe(int argc, const char **argv, const char *prefix) { int ret; - init_params(); - ret = __cmd_probe(argc, argv, prefix); - cleanup_params(); + ret = init_params(); + if (!ret) { + ret = __cmd_probe(argc, argv, prefix); + cleanup_params(); + } return ret; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index af47531b82ec..e4c85b8f46c2 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -30,37 +30,6 @@ #include <sched.h> #include <sys/mman.h> -#ifndef HAVE_ON_EXIT_SUPPORT -#ifndef ATEXIT_MAX -#define ATEXIT_MAX 32 -#endif -static int __on_exit_count = 0; -typedef void (*on_exit_func_t) (int, void *); -static on_exit_func_t __on_exit_funcs[ATEXIT_MAX]; -static void *__on_exit_args[ATEXIT_MAX]; -static int __exitcode = 0; -static void __handle_on_exit_funcs(void); -static int on_exit(on_exit_func_t function, void *arg); -#define exit(x) (exit)(__exitcode = (x)) - -static int on_exit(on_exit_func_t function, void *arg) -{ - if (__on_exit_count == ATEXIT_MAX) - return -ENOMEM; - else if (__on_exit_count == 0) - atexit(__handle_on_exit_funcs); - __on_exit_funcs[__on_exit_count] = function; - __on_exit_args[__on_exit_count++] = arg; - return 0; -} - -static void __handle_on_exit_funcs(void) -{ - int i; - for (i = 0; i < __on_exit_count; i++) - __on_exit_funcs[i] (__exitcode, __on_exit_args[i]); -} -#endif struct record { struct perf_tool tool; @@ -147,29 +116,19 @@ static void sig_handler(int sig) { if (sig == SIGCHLD) child_finished = 1; + else + signr = sig; done = 1; - signr = sig; } -static void record__sig_exit(int exit_status __maybe_unused, void *arg) +static void record__sig_exit(void) { - struct record *rec = arg; - int status; - - if (rec->evlist->workload.pid > 0) { - if (!child_finished) - kill(rec->evlist->workload.pid, SIGTERM); - - wait(&status); - if (WIFSIGNALED(status)) - psignal(WTERMSIG(status), rec->progname); - } - - if (signr == -1 || signr == SIGUSR1) + if (signr == -1) return; signal(signr, SIG_DFL); + raise(signr); } static int record__open(struct record *rec) @@ -243,27 +202,6 @@ static int process_buildids(struct record *rec) size, &build_id__mark_dso_hit_ops); } -static void record__exit(int status, void *arg) -{ - struct record *rec = arg; - struct perf_data_file *file = &rec->file; - - if (status != 0) - return; - - if (!file->is_pipe) { - rec->session->header.data_size += rec->bytes_written; - - if (!rec->no_buildid) - process_buildids(rec); - perf_session__write_header(rec->session, rec->evlist, - file->fd, true); - perf_session__delete(rec->session); - perf_evlist__delete(rec->evlist); - symbol__exit(); - } -} - static void perf_event__synthesize_guest_os(struct machine *machine, void *data) { int err; @@ -344,18 +282,19 @@ static volatile int workload_exec_errno; * if the fork fails, since we asked by setting its * want_signal to true. */ -static void workload_exec_failed_signal(int signo, siginfo_t *info, +static void workload_exec_failed_signal(int signo __maybe_unused, + siginfo_t *info, void *ucontext __maybe_unused) { workload_exec_errno = info->si_value.sival_int; done = 1; - signr = signo; child_finished = 1; } static int __cmd_record(struct record *rec, int argc, const char **argv) { int err; + int status = 0; unsigned long waking = 0; const bool forks = argc > 0; struct machine *machine; @@ -367,14 +306,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) rec->progname = argv[0]; - on_exit(record__sig_exit, rec); + atexit(record__sig_exit); signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); signal(SIGTERM, sig_handler); session = perf_session__new(file, false, NULL); if (session == NULL) { - pr_err("Not enough memory for reading perf file header\n"); + pr_err("Perf session creation failed.\n"); return -1; } @@ -388,32 +327,28 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) workload_exec_failed_signal); if (err < 0) { pr_err("Couldn't run the workload!\n"); + status = err; goto out_delete_session; } } if (record__open(rec) != 0) { err = -1; - goto out_delete_session; + goto out_child; } if (!rec->evlist->nr_groups) perf_header__clear_feat(&session->header, HEADER_GROUP_DESC); - /* - * perf_session__delete(session) will be called at record__exit() - */ - on_exit(record__exit, rec); - if (file->is_pipe) { err = perf_header__write_pipe(file->fd); if (err < 0) - goto out_delete_session; + goto out_child; } else { err = perf_session__write_header(session, rec->evlist, file->fd, false); if (err < 0) - goto out_delete_session; + goto out_child; } if (!rec->no_buildid @@ -421,7 +356,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) pr_err("Couldn't generate buildids. " "Use --no-buildid to profile anyway.\n"); err = -1; - goto out_delete_session; + goto out_child; } machine = &session->machines.host; @@ -431,7 +366,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) process_synthesized_event); if (err < 0) { pr_err("Couldn't synthesize attrs.\n"); - goto out_delete_session; + goto out_child; } if (have_tracepoints(&rec->evlist->entries)) { @@ -447,7 +382,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) process_synthesized_event); if (err <= 0) { pr_err("Couldn't record tracing data.\n"); - goto out_delete_session; + goto out_child; } rec->bytes_written += err; } @@ -475,7 +410,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads, process_synthesized_event, opts->sample_address); if (err != 0) - goto out_delete_session; + goto out_child; if (rec->realtime_prio) { struct sched_param param; @@ -484,7 +419,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { pr_err("Could not set realtime priority.\n"); err = -1; - goto out_delete_session; + goto out_child; } } @@ -512,13 +447,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (record__mmap_read_all(rec) < 0) { err = -1; - goto out_delete_session; + goto out_child; } if (hits == rec->samples) { if (done) break; err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1); + if (err < 0 && errno == EINTR) + err = 0; waking++; } @@ -538,28 +475,52 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg)); pr_err("Workload failed: %s\n", emsg); err = -1; - goto out_delete_session; + goto out_child; } - if (quiet || signr == SIGUSR1) - return 0; + if (!quiet) { + fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking); - fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking); + /* + * Approximate RIP event size: 24 bytes. + */ + fprintf(stderr, + "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n", + (double)rec->bytes_written / 1024.0 / 1024.0, + file->path, + rec->bytes_written / 24); + } - /* - * Approximate RIP event size: 24 bytes. - */ - fprintf(stderr, - "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n", - (double)rec->bytes_written / 1024.0 / 1024.0, - file->path, - rec->bytes_written / 24); +out_child: + if (forks) { + int exit_status; - return 0; + if (!child_finished) + kill(rec->evlist->workload.pid, SIGTERM); + + wait(&exit_status); + + if (err < 0) + status = err; + else if (WIFEXITED(exit_status)) + status = WEXITSTATUS(exit_status); + else if (WIFSIGNALED(exit_status)) + signr = WTERMSIG(exit_status); + } else + status = err; + + if (!err && !file->is_pipe) { + rec->session->header.data_size += rec->bytes_written; + + if (!rec->no_buildid) + process_buildids(rec); + perf_session__write_header(rec->session, rec->evlist, + file->fd, true); + } out_delete_session: perf_session__delete(session); - return err; + return status; } #define BRANCH_OPT(n, m) \ @@ -649,7 +610,7 @@ error: return ret; } -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT static int get_stack_size(char *str, unsigned long *_size) { char *endptr; @@ -675,7 +636,7 @@ static int get_stack_size(char *str, unsigned long *_size) max_size, str); return -1; } -#endif /* HAVE_LIBUNWIND_SUPPORT */ +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ int record_parse_callchain(const char *arg, struct record_opts *opts) { @@ -704,7 +665,7 @@ int record_parse_callchain(const char *arg, struct record_opts *opts) "needed for -g fp\n"); break; -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT /* Dwarf style */ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { const unsigned long default_stack_dump_size = 8192; @@ -720,7 +681,7 @@ int record_parse_callchain(const char *arg, struct record_opts *opts) ret = get_stack_size(tok, &size); opts->stack_dump_size = size; } -#endif /* HAVE_LIBUNWIND_SUPPORT */ +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ } else { pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); @@ -735,7 +696,9 @@ int record_parse_callchain(const char *arg, struct record_opts *opts) static void callchain_debug(struct record_opts *opts) { - pr_debug("callchain: type %d\n", opts->call_graph); + static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" }; + + pr_debug("callchain: type %s\n", str[opts->call_graph]); if (opts->call_graph == CALLCHAIN_DWARF) pr_debug("callchain: stack dump size %d\n", @@ -749,6 +712,8 @@ int record_parse_callchain_opt(const struct option *opt, struct record_opts *opts = opt->value; int ret; + opts->call_graph_enabled = !unset; + /* --no-call-graph */ if (unset) { opts->call_graph = CALLCHAIN_NONE; @@ -769,6 +734,8 @@ int record_callchain_opt(const struct option *opt, { struct record_opts *opts = opt->value; + opts->call_graph_enabled = !unset; + if (opts->call_graph == CALLCHAIN_NONE) opts->call_graph = CALLCHAIN_FP; @@ -776,6 +743,16 @@ int record_callchain_opt(const struct option *opt, return 0; } +static int perf_record_config(const char *var, const char *value, void *cb) +{ + struct record *rec = cb; + + if (!strcmp(var, "record.call-graph")) + return record_parse_callchain(value, &rec->opts); + + return perf_default_config(var, value, cb); +} + static const char * const record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -807,7 +784,7 @@ static struct record record = { #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf"; #else const char record_callchain_help[] = CALLCHAIN_HELP "fp"; @@ -907,6 +884,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->evlist == NULL) return -ENOMEM; + perf_config(perf_record_config, rec); + argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc && target__none(&rec->opts.target)) @@ -970,6 +949,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) err = __cmd_record(&record, argc, argv); out_symbol_exit: + perf_evlist__delete(rec->evlist); symbol__exit(); return err; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 02f985f3a396..bc0eec1ce4be 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -57,6 +57,7 @@ struct report { const char *cpu_list; const char *symbol_filter_str; float min_percent; + u64 nr_entries; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; @@ -75,13 +76,31 @@ static int report__config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al, - struct perf_sample *sample, struct perf_evsel *evsel, - union perf_event *event) +static void report__inc_stats(struct report *rep, struct hist_entry *he) +{ + /* + * The @he is either of a newly created one or an existing one + * merging current sample. We only want to count a new one so + * checking ->nr_events being 1. + */ + if (he->stat.nr_events == 1) + rep->nr_entries++; + + /* + * Only counts number of samples at this stage as it's more + * natural to do it here and non-sample events are also + * counted in perf_session_deliver_event(). The dump_trace + * requires this info is ready before going to the output tree. + */ + hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE); + if (!he->filtered) + he->hists->stats.nr_non_filtered_samples++; +} + +static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al, + struct perf_sample *sample, struct perf_evsel *evsel) { - struct report *rep = container_of(tool, struct report, tool); struct symbol *parent = NULL; - u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct hist_entry *he; struct mem_info *mi, *mx; uint64_t cost; @@ -90,7 +109,7 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati if (err) return err; - mi = machine__resolve_mem(al->machine, al->thread, sample, cpumode); + mi = sample__resolve_mem(sample, al); if (!mi) return -ENOMEM; @@ -124,17 +143,16 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati goto out; } - evsel->hists.stats.total_period += cost; - hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + report__inc_stats(rep, he); + err = hist_entry__append_callchain(he, sample); out: return err; } -static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al, +static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al, struct perf_sample *sample, struct perf_evsel *evsel) { - struct report *rep = container_of(tool, struct report, tool); struct symbol *parent = NULL; unsigned i; struct hist_entry *he; @@ -144,8 +162,7 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc if (err) return err; - bi = machine__resolve_bstack(al->machine, al->thread, - sample->branch_stack); + bi = sample__resolve_bstack(sample, al); if (!bi) return -ENOMEM; @@ -178,9 +195,7 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc if (err) goto out; } - - evsel->hists.stats.total_period += 1; - hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + report__inc_stats(rep, he); } else goto out; } @@ -190,10 +205,9 @@ out: return err; } -static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel, +static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel, struct addr_location *al, struct perf_sample *sample) { - struct report *rep = container_of(tool, struct report, tool); struct symbol *parent = NULL; struct hist_entry *he; int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack); @@ -214,8 +228,8 @@ static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evs if (ui__has_annotation()) err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - evsel->hists.stats.total_period += sample->period; - hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + report__inc_stats(rep, he); + out: return err; } @@ -237,25 +251,25 @@ static int process_sample_event(struct perf_tool *tool, return -1; } - if (al.filtered || (rep->hide_unresolved && al.sym == NULL)) + if (rep->hide_unresolved && al.sym == NULL) return 0; if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) return 0; if (sort__mode == SORT_MODE__BRANCH) { - ret = report__add_branch_hist_entry(tool, &al, sample, evsel); + ret = report__add_branch_hist_entry(rep, &al, sample, evsel); if (ret < 0) pr_debug("problem adding lbr entry, skipping event\n"); } else if (rep->mem_mode == 1) { - ret = report__add_mem_hist_entry(tool, &al, sample, evsel, event); + ret = report__add_mem_hist_entry(rep, &al, sample, evsel); if (ret < 0) pr_debug("problem adding mem entry, skipping event\n"); } else { if (al.map != NULL) al.map->dso->hit = 1; - ret = report__add_hist_entry(tool, evsel, &al, sample); + ret = report__add_hist_entry(rep, evsel, &al, sample); if (ret < 0) pr_debug("problem incrementing symbol period, skipping event\n"); } @@ -343,6 +357,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report char buf[512]; size_t size = sizeof(buf); + if (symbol_conf.filter_relative) { + nr_samples = hists->stats.nr_non_filtered_samples; + nr_events = hists->stats.total_non_filtered_period; + } + if (perf_evsel__is_group_event(evsel)) { struct perf_evsel *pos; @@ -350,8 +369,13 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report evname = buf; for_each_group_member(pos, evsel) { - nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; - nr_events += pos->hists.stats.total_period; + if (symbol_conf.filter_relative) { + nr_samples += pos->hists.stats.nr_non_filtered_samples; + nr_events += pos->hists.stats.total_non_filtered_period; + } else { + nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos->hists.stats.total_period; + } } } @@ -476,24 +500,12 @@ static int report__browse_hists(struct report *rep) return ret; } -static u64 report__collapse_hists(struct report *rep) +static void report__collapse_hists(struct report *rep) { struct ui_progress prog; struct perf_evsel *pos; - u64 nr_samples = 0; - /* - * Count number of histogram entries to use when showing progress, - * reusing nr_samples variable. - */ - evlist__for_each(rep->session->evlist, pos) - nr_samples += pos->hists.nr_entries; - ui_progress__init(&prog, nr_samples, "Merging related events..."); - /* - * Count total number of samples, will be used to check if this - * session had any. - */ - nr_samples = 0; + ui_progress__init(&prog, rep->nr_entries, "Merging related events..."); evlist__for_each(rep->session->evlist, pos) { struct hists *hists = &pos->hists; @@ -502,7 +514,6 @@ static u64 report__collapse_hists(struct report *rep) hists->symbol_filter_str = rep->symbol_filter_str; hists__collapse_resort(hists, &prog); - nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE]; /* Non-group events are considered as leader */ if (symbol_conf.event_group && @@ -515,14 +526,11 @@ static u64 report__collapse_hists(struct report *rep) } ui_progress__finish(); - - return nr_samples; } static int __cmd_report(struct report *rep) { int ret; - u64 nr_samples; struct perf_session *session = rep->session; struct perf_evsel *pos; struct perf_data_file *file = session->file; @@ -562,12 +570,12 @@ static int __cmd_report(struct report *rep) } } - nr_samples = report__collapse_hists(rep); + report__collapse_hists(rep); if (session_done()) return 0; - if (nr_samples == 0) { + if (rep->nr_entries == 0) { ui__error("The %s file has no samples!\n", file->path); return 0; } @@ -579,11 +587,9 @@ static int __cmd_report(struct report *rep) } static int -parse_callchain_opt(const struct option *opt, const char *arg, int unset) +report_parse_callchain_opt(const struct option *opt, const char *arg, int unset) { struct report *rep = (struct report *)opt->value; - char *tok, *tok2; - char *endptr; /* * --no-call-graph @@ -593,80 +599,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) return 0; } - symbol_conf.use_callchain = true; - - if (!arg) - return 0; - - tok = strtok((char *)arg, ","); - if (!tok) - return -1; - - /* get the output mode */ - if (!strncmp(tok, "graph", strlen(arg))) - callchain_param.mode = CHAIN_GRAPH_ABS; - - else if (!strncmp(tok, "flat", strlen(arg))) - callchain_param.mode = CHAIN_FLAT; - - else if (!strncmp(tok, "fractal", strlen(arg))) - callchain_param.mode = CHAIN_GRAPH_REL; - - else if (!strncmp(tok, "none", strlen(arg))) { - callchain_param.mode = CHAIN_NONE; - symbol_conf.use_callchain = false; - - return 0; - } - - else - return -1; - - /* get the min percentage */ - tok = strtok(NULL, ","); - if (!tok) - goto setup; - - callchain_param.min_percent = strtod(tok, &endptr); - if (tok == endptr) - return -1; - - /* get the print limit */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - - if (tok2[0] != 'c') { - callchain_param.print_limit = strtoul(tok2, &endptr, 0); - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - } - - /* get the call chain order */ - if (!strncmp(tok2, "caller", strlen("caller"))) - callchain_param.order = ORDER_CALLER; - else if (!strncmp(tok2, "callee", strlen("callee"))) - callchain_param.order = ORDER_CALLEE; - else - return -1; - - /* Get the sort key */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - if (!strncmp(tok2, "function", strlen("function"))) - callchain_param.key = CCKEY_FUNCTION; - else if (!strncmp(tok2, "address", strlen("address"))) - callchain_param.key = CCKEY_ADDRESS; - else - return -1; -setup: - if (callchain_register_param(&callchain_param) < 0) { - pr_err("Can't register callchain params\n"); - return -1; - } - return 0; + return parse_callchain_report_opt(arg); } int @@ -766,10 +699,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "header-only", &report.header_only, "Show only data header."), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline," - " dso_to, dso_from, symbol_to, symbol_from, mispredict," - " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, " - "snoop, locked, abort, in_tx, transaction"), + "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..." + " Please refer the man page for the complete list."), + OPT_STRING('F', "fields", &field_order, "key[,keys...]", + "output field(s): overhead, period, sample plus all of sort keys"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", @@ -778,7 +711,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Only display entries with parent-match"), OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order", "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). " - "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt), + "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt), OPT_INTEGER(0, "max-stack", &report.max_stack, "Set the maximum stack depth when parsing the callchain, " "anything beyond the specified depth will be ignored. " @@ -829,6 +762,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), OPT_CALLBACK(0, "percent-limit", &report, "percent", "Don't show entries under that percent", parse_percent_limit), + OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", + "how to display percentage of filtered entries", parse_filter_percentage), OPT_END() }; struct perf_data_file file = { @@ -872,52 +807,31 @@ repeat: if (branch_mode == -1 && has_br_stack) sort__mode = SORT_MODE__BRANCH; - /* sort__mode could be NORMAL if --no-branch-stack */ - if (sort__mode == SORT_MODE__BRANCH) { - /* - * if no sort_order is provided, then specify - * branch-mode specific order - */ - if (sort_order == default_sort_order) - sort_order = "comm,dso_from,symbol_from," - "dso_to,symbol_to"; - - } if (report.mem_mode) { if (sort__mode == SORT_MODE__BRANCH) { pr_err("branch and mem mode incompatible\n"); goto error; } sort__mode = SORT_MODE__MEMORY; - - /* - * if no sort_order is provided, then specify - * branch-mode specific order - */ - if (sort_order == default_sort_order) - sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; } if (setup_sorting() < 0) { - parse_options_usage(report_usage, options, "s", 1); + if (sort_order) + parse_options_usage(report_usage, options, "s", 1); + if (field_order) + parse_options_usage(sort_order ? NULL : report_usage, + options, "F", 1); goto error; } - if (parent_pattern != default_parent_pattern) { - if (sort_dimension__add("parent") < 0) - goto error; - } - /* Force tty output for header output. */ if (report.header || report.header_only) use_browser = 0; if (strcmp(input_name, "-") != 0) setup_browser(true); - else { + else use_browser = 0; - perf_hpp__init(); - } if (report.header || report.header_only) { perf_session__fprintf_info(session, stdout, @@ -934,7 +848,7 @@ repeat: * so don't allocate extra space that won't be used in the stdio * implementation. */ - if (use_browser == 1 && sort__has_sym) { + if (ui__has_annotation()) { symbol_conf.priv_size = sizeof(struct annotation); machines__set_symbol_filter(&session->machines, symbol__annotate_init); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 6a76a07b6789..d7176830b9b2 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -66,7 +66,7 @@ struct sched_atom { struct task_desc *wakee; }; -#define TASK_STATE_TO_CHAR_STR "RSDTtZX" +#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" enum thread_state { THREAD_SLEEPING = 0, @@ -149,7 +149,6 @@ struct perf_sched { unsigned long nr_runs; unsigned long nr_timestamps; unsigned long nr_unordered_timestamps; - unsigned long nr_state_machine_bugs; unsigned long nr_context_switch_bugs; unsigned long nr_events; unsigned long nr_lost_chunks; @@ -1007,17 +1006,12 @@ static int latency_wakeup_event(struct perf_sched *sched, struct perf_sample *sample, struct machine *machine) { - const u32 pid = perf_evsel__intval(evsel, sample, "pid"), - success = perf_evsel__intval(evsel, sample, "success"); + const u32 pid = perf_evsel__intval(evsel, sample, "pid"); struct work_atoms *atoms; struct work_atom *atom; struct thread *wakee; u64 timestamp = sample->time; - /* Note for later, it may be interesting to observe the failing cases */ - if (!success) - return 0; - wakee = machine__findnew_thread(machine, 0, pid); atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { @@ -1037,12 +1031,18 @@ static int latency_wakeup_event(struct perf_sched *sched, atom = list_entry(atoms->work_list.prev, struct work_atom, list); /* + * As we do not guarantee the wakeup event happens when + * task is out of run queue, also may happen when task is + * on run queue and wakeup only change ->state to TASK_RUNNING, + * then we should not set the ->wake_up_time when wake up a + * task which is on run queue. + * * You WILL be missing events if you've recorded only * one CPU, or are only looking at only one, so don't - * make useless noise. + * skip in this case. */ if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING) - sched->nr_state_machine_bugs++; + return 0; sched->nr_timestamps++; if (atom->sched_out_time > timestamp) { @@ -1124,7 +1124,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ avg = work_list->total_lat / work_list->nb_atoms; - printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n", + printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13.6f s\n", (double)work_list->total_runtime / 1e6, work_list->nb_atoms, (double)avg / 1e6, (double)work_list->max_lat / 1e6, @@ -1266,9 +1266,8 @@ static int process_sched_wakeup_event(struct perf_tool *tool, static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine) { - const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"), - next_pid = perf_evsel__intval(evsel, sample, "next_pid"); - struct thread *sched_out __maybe_unused, *sched_in; + const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid"); + struct thread *sched_in; int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; @@ -1291,7 +1290,6 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_out = machine__findnew_thread(machine, 0, prev_pid); sched_in = machine__findnew_thread(machine, 0, next_pid); sched->curr_thread[this_cpu] = sched_in; @@ -1300,17 +1298,25 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, new_shortname = 0; if (!sched_in->shortname[0]) { - sched_in->shortname[0] = sched->next_shortname1; - sched_in->shortname[1] = sched->next_shortname2; - - if (sched->next_shortname1 < 'Z') { - sched->next_shortname1++; + if (!strcmp(thread__comm_str(sched_in), "swapper")) { + /* + * Don't allocate a letter-number for swapper:0 + * as a shortname. Instead, we use '.' for it. + */ + sched_in->shortname[0] = '.'; + sched_in->shortname[1] = ' '; } else { - sched->next_shortname1='A'; - if (sched->next_shortname2 < '9') { - sched->next_shortname2++; + sched_in->shortname[0] = sched->next_shortname1; + sched_in->shortname[1] = sched->next_shortname2; + + if (sched->next_shortname1 < 'Z') { + sched->next_shortname1++; } else { - sched->next_shortname2='0'; + sched->next_shortname1 = 'A'; + if (sched->next_shortname2 < '9') + sched->next_shortname2++; + else + sched->next_shortname2 = '0'; } } new_shortname = 1; @@ -1322,12 +1328,9 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, else printf("*"); - if (sched->curr_thread[cpu]) { - if (sched->curr_thread[cpu]->tid) - printf("%2s ", sched->curr_thread[cpu]->shortname); - else - printf(". "); - } else + if (sched->curr_thread[cpu]) + printf("%2s ", sched->curr_thread[cpu]->shortname); + else printf(" "); } @@ -1496,14 +1499,6 @@ static void print_bad_events(struct perf_sched *sched) (double)sched->nr_lost_events/(double)sched->nr_events * 100.0, sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks); } - if (sched->nr_state_machine_bugs && sched->nr_timestamps) { - printf(" INFO: %.3f%% state machine bugs (%ld out of %ld)", - (double)sched->nr_state_machine_bugs/(double)sched->nr_timestamps*100.0, - sched->nr_state_machine_bugs, sched->nr_timestamps); - if (sched->nr_lost_events) - printf(" (due to lost events?)"); - printf("\n"); - } if (sched->nr_context_switch_bugs && sched->nr_timestamps) { printf(" INFO: %.3f%% context switch bugs (%ld out of %ld)", (double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0, @@ -1527,9 +1522,9 @@ static int perf_sched__lat(struct perf_sched *sched) perf_sched__sort_lat(sched); - printf("\n ---------------------------------------------------------------------------------------------------------------\n"); - printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); - printf(" ---------------------------------------------------------------------------------------------------------------\n"); + printf("\n -----------------------------------------------------------------------------------------------------------------\n"); + printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n"); + printf(" -----------------------------------------------------------------------------------------------------------------\n"); next = rb_first(&sched->sorted_atom_root); @@ -1541,7 +1536,7 @@ static int perf_sched__lat(struct perf_sched *sched) next = rb_next(next); } - printf(" -----------------------------------------------------------------------------------------\n"); + printf(" -----------------------------------------------------------------------------------------------------------------\n"); printf(" TOTAL: |%11.3f ms |%9" PRIu64 " |\n", (double)sched->all_runtime / 1e6, sched->all_count); @@ -1635,6 +1630,7 @@ static int __cmd_record(int argc, const char **argv) "-e", "sched:sched_stat_runtime", "-e", "sched:sched_process_fork", "-e", "sched:sched_wakeup", + "-e", "sched:sched_wakeup_new", "-e", "sched:sched_migrate_task", }; @@ -1713,8 +1709,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) "perf sched replay [<options>]", NULL }; - const char * const sched_usage[] = { - "perf sched [<options>] {record|latency|map|replay|script}", + const char *const sched_subcommands[] = { "record", "latency", "map", + "replay", "script", NULL }; + const char *sched_usage[] = { + NULL, NULL }; struct trace_sched_handler lat_ops = { @@ -1736,8 +1734,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++) sched.curr_pid[i] = -1; - argc = parse_options(argc, argv, sched_options, sched_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands, + sched_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc) usage_with_options(sched_usage, sched_options); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 8b0e1c9234d9..65a151e36067 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -174,13 +174,20 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) { - memset(evsel->priv, 0, sizeof(struct perf_stat)); + int i; + struct perf_stat *ps = evsel->priv; + + for (i = 0; i < 3; i++) + init_stats(&ps->res_stats[i]); } static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat)); - return evsel->priv == NULL ? -ENOMEM : 0; + if (evsel == NULL) + return -ENOMEM; + perf_evsel__reset_stat_priv(evsel); + return 0; } static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 25526d6eae59..74db2568b867 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -494,7 +494,7 @@ static const char *cat_backtrace(union perf_event *event, continue; } - tal.filtered = false; + tal.filtered = 0; thread__find_addr_location(al.thread, machine, cpumode, MAP__FUNCTION, ip, &tal); @@ -1238,7 +1238,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar for (i = 0; i < old_power_args_nr; i++) *p++ = strdup(old_power_args[i]); - for (j = 1; j < (unsigned int)argc; j++) + for (j = 0; j < (unsigned int)argc; j++) *p++ = argv[j]; return cmd_record(rec_argc, rec_argv, NULL); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 5f989a7d8bc2..5b389ce4cd15 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -253,6 +253,9 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel, return NULL; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + if (!he->filtered) + evsel->hists.stats.nr_non_filtered_samples++; + return he; } @@ -694,8 +697,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (event->header.misc & PERF_RECORD_MISC_EXACT_IP) top->exact_samples++; - if (perf_event__preprocess_sample(event, machine, &al, sample) < 0 || - al.filtered) + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) return; if (!top->kptr_restrict_warned && @@ -993,6 +995,16 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) return record_parse_callchain_opt(opt, arg, unset); } +static int perf_top_config(const char *var, const char *value, void *cb) +{ + struct perf_top *top = cb; + + if (!strcmp(var, "top.call-graph")) + return record_parse_callchain(value, &top->record_opts); + + return perf_default_config(var, value, cb); +} + static int parse_percent_limit(const struct option *opt, const char *arg, int unset __maybe_unused) @@ -1071,8 +1083,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight," - " abort, in_tx, transaction"), + "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..." + " Please refer the man page for the complete list."), + OPT_STRING(0, "fields", &field_order, "key[,keys...]", + "output field(s): overhead, period, sample plus all of sort keys"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts, @@ -1106,6 +1120,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_CALLBACK(0, "percent-limit", &top, "percent", "Don't show entries under that percent", parse_percent_limit), + OPT_CALLBACK(0, "percentage", NULL, "relative|absolute", + "How to display percentage of filtered entries", parse_filter_percentage), OPT_END() }; const char * const top_usage[] = { @@ -1117,21 +1133,25 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.evlist == NULL) return -ENOMEM; + perf_config(perf_top_config, &top); + argc = parse_options(argc, argv, options, top_usage, 0); if (argc) usage_with_options(top_usage, options); - if (sort_order == default_sort_order) - sort_order = "dso,symbol"; + sort__mode = SORT_MODE__TOP; + /* display thread wants entries to be collapsed in a different tree */ + sort__need_collapse = 1; if (setup_sorting() < 0) { - parse_options_usage(top_usage, options, "s", 1); + if (sort_order) + parse_options_usage(top_usage, options, "s", 1); + if (field_order) + parse_options_usage(sort_order ? NULL : top_usage, + options, "fields", 0); goto out_delete_evlist; } - /* display thread wants entries to be collapsed in a different tree */ - sort__need_collapse = 1; - if (top.use_stdio) use_browser = 0; else if (top.use_tui) diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 0331ea2701a3..729bbdf5cec7 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -29,11 +29,25 @@ ifeq ($(ARCH),x86) endif NO_PERF_REGS := 0 endif + ifeq ($(ARCH),arm) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-arm endif +ifeq ($(ARCH),arm64) + NO_PERF_REGS := 0 + LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 +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 +# to the check. +ifneq ($(ARCH),$(filter $(ARCH),x86 arm)) + NO_LIBDW_DWARF_UNWIND := 1 +endif + ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 else @@ -59,6 +73,17 @@ ifeq ($(NO_PERF_REGS),0) CFLAGS += -DHAVE_PERF_REGS_SUPPORT endif +ifndef NO_LIBELF + # for linking with debug library, run like: + # make DEBUG=1 LIBDW_DIR=/opt/libdw/ + ifdef LIBDW_DIR + LIBDW_CFLAGS := -I$(LIBDW_DIR)/include + LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib + endif + FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) + FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw +endif + # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile @@ -98,6 +123,10 @@ CFLAGS += -Wall CFLAGS += -Wextra CFLAGS += -std=gnu99 +# Enforce a non-executable stack, as we may regress (again) in the future by +# adding assembler files missing the .GNU-stack linker note. +LDFLAGS += -Wl,-z,noexecstack + EXTLIBS = -lelf -lpthread -lrt -lm -ldl ifneq ($(OUTPUT),) @@ -145,9 +174,38 @@ CORE_FEATURE_TESTS = \ libpython-version \ libslang \ libunwind \ - on-exit \ stackprotector-all \ - timerfd + timerfd \ + libdw-dwarf-unwind + +LIB_FEATURE_TESTS = \ + dwarf \ + glibc \ + gtk2 \ + libaudit \ + libbfd \ + libelf \ + libnuma \ + libperl \ + libpython \ + libslang \ + libunwind \ + libdw-dwarf-unwind + +VF_FEATURE_TESTS = \ + backtrace \ + fortify-source \ + gtk2-infobar \ + libelf-getphdrnum \ + libelf-mmap \ + libpython-version \ + stackprotector-all \ + timerfd \ + libunwind-debug-frame \ + bionic \ + liberty \ + liberty-z \ + cplus-demangle # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features. # If in the future we need per-feature checks/flags for features not @@ -161,17 +219,6 @@ endef $(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat))) # -# So here we detect whether test-all was rebuilt, to be able -# to skip the print-out of the long features list if the file -# existed before and after it was built: -# -ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all.bin),) - test-all-failed := 1 -else - test-all-failed := 0 -endif - -# # Special fast-path for the 'all features are available' case: # $(call feature_check,all,$(MSG)) @@ -180,15 +227,6 @@ $(call feature_check,all,$(MSG)) # Just in case the build freshly failed, make sure we print the # feature matrix: # -ifeq ($(feature-all), 0) - test-all-failed := 1 -endif - -ifeq ($(test-all-failed),1) - $(info ) - $(info Auto-detecting system features:) -endif - ifeq ($(feature-all), 1) # # test-all.c passed - just set all the core feature flags to 1: @@ -199,27 +237,6 @@ else $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat))) endif -# -# Print the result of the feature test: -# -feature_print = $(eval $(feature_print_code)) $(info $(MSG)) - -define feature_print_code - ifeq ($(feature-$(1)), 1) - MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1)) - else - MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1)) - endif -endef - -# -# Only print out our features if we rebuilt the testcases or if a test failed: -# -ifeq ($(test-all-failed), 1) - $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_print,$(feat))) - $(info ) -endif - ifeq ($(feature-stackprotector-all), 1) CFLAGS += -fstack-protector-all endif @@ -264,6 +281,7 @@ ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 NO_LIBUNWIND := 1 + NO_LIBDW_DWARF_UNWIND := 1 else ifeq ($(feature-libelf), 0) ifeq ($(feature-glibc), 1) @@ -278,17 +296,18 @@ else NO_LIBELF := 1 NO_DWARF := 1 NO_DEMANGLE := 1 + NO_LIBUNWIND := 1 + NO_LIBDW_DWARF_UNWIND := 1 else msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); endif else - # for linking with debug library, run like: - # make DEBUG=1 LIBDW_DIR=/opt/libdw/ - ifdef LIBDW_DIR - LIBDW_CFLAGS := -I$(LIBDW_DIR)/include - LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib + ifndef NO_LIBDW_DWARF_UNWIND + ifneq ($(feature-libdw-dwarf-unwind),1) + NO_LIBDW_DWARF_UNWIND := 1 + msg := $(warning No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR); + endif endif - ifneq ($(feature-dwarf), 1) msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); NO_DWARF := 1 @@ -324,25 +343,51 @@ endif # NO_LIBELF ifndef NO_LIBUNWIND ifneq ($(feature-libunwind), 1) - msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1); + msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR); NO_LIBUNWIND := 1 + endif +endif + +dwarf-post-unwind := 1 +dwarf-post-unwind-text := BUG + +# setup DWARF post unwinder +ifdef NO_LIBUNWIND + ifdef NO_LIBDW_DWARF_UNWIND + msg := $(warning Disabling post unwind, no support found.); + dwarf-post-unwind := 0 else - ifeq ($(ARCH),arm) - $(call feature_check,libunwind-debug-frame) - ifneq ($(feature-libunwind-debug-frame), 1) - msg := $(warning No debug_frame support found in libunwind); - CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME - endif - else - # non-ARM has no dwarf_find_debug_frame() function: + dwarf-post-unwind-text := libdw + endif +else + dwarf-post-unwind-text := libunwind + # Enable libunwind support by default. + ifndef NO_LIBDW_DWARF_UNWIND + NO_LIBDW_DWARF_UNWIND := 1 + endif +endif + +ifeq ($(dwarf-post-unwind),1) + CFLAGS += -DHAVE_DWARF_UNWIND_SUPPORT +else + NO_DWARF_UNWIND := 1 +endif + +ifndef NO_LIBUNWIND + ifeq ($(ARCH),$(filter $(ARCH),arm arm64)) + $(call feature_check,libunwind-debug-frame) + ifneq ($(feature-libunwind-debug-frame), 1) + msg := $(warning No debug_frame support found in libunwind); CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME endif - - CFLAGS += -DHAVE_LIBUNWIND_SUPPORT - EXTLIBS += $(LIBUNWIND_LIBS) - CFLAGS += $(LIBUNWIND_CFLAGS) - LDFLAGS += $(LIBUNWIND_LDFLAGS) - endif # ifneq ($(feature-libunwind), 1) + else + # non-ARM has no dwarf_find_debug_frame() function: + CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME + endif + CFLAGS += -DHAVE_LIBUNWIND_SUPPORT + EXTLIBS += $(LIBUNWIND_LIBS) + CFLAGS += $(LIBUNWIND_CFLAGS) + LDFLAGS += $(LIBUNWIND_LDFLAGS) endif ifndef NO_LIBAUDIT @@ -478,7 +523,21 @@ else endif ifeq ($(feature-libbfd), 1) - EXTLIBS += -lbfd -lz -liberty + EXTLIBS += -lbfd + + # call all detections now so we get correct + # status in VF output + $(call feature_check,liberty) + $(call feature_check,liberty-z) + $(call feature_check,cplus-demangle) + + ifeq ($(feature-liberty), 1) + EXTLIBS += -liberty + else + ifeq ($(feature-liberty-z), 1) + EXTLIBS += -liberty -lz + endif + endif endif ifdef NO_DEMANGLE @@ -489,15 +548,10 @@ else CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT else ifneq ($(feature-libbfd), 1) - $(call feature_check,liberty) - ifeq ($(feature-liberty), 1) - EXTLIBS += -lbfd -liberty - else - $(call feature_check,liberty-z) - ifeq ($(feature-liberty-z), 1) - EXTLIBS += -lbfd -liberty -lz - else - $(call feature_check,cplus-demangle) + ifneq ($(feature-liberty), 1) + ifneq ($(feature-liberty-z), 1) + # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT + # or any of 'bfd iberty z' trinity ifeq ($(feature-cplus-demangle), 1) EXTLIBS += -liberty CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT @@ -515,12 +569,6 @@ ifneq ($(filter -lbfd,$(EXTLIBS)),) CFLAGS += -DHAVE_LIBBFD_SUPPORT endif -ifndef NO_ON_EXIT - ifeq ($(feature-on-exit), 1) - CFLAGS += -DHAVE_ON_EXIT_SUPPORT - endif -endif - ifndef NO_BACKTRACE ifeq ($(feature-backtrace), 1) CFLAGS += -DHAVE_BACKTRACE_SUPPORT @@ -602,3 +650,84 @@ ifdef DESTDIR plugindir=$(libdir)/traceevent/plugins plugindir_SQ= $(subst ','\'',$(plugindir)) endif + +# +# Print the result of the feature test: +# +feature_print_status = $(eval $(feature_print_status_code)) $(info $(MSG)) + +define feature_print_status_code + ifeq ($(feature-$(1)), 1) + MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1)) + else + MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1)) + endif +endef + +feature_print_var = $(eval $(feature_print_var_code)) $(info $(MSG)) +define feature_print_var_code + MSG = $(shell printf '...%30s: %s' $(1) $($(1))) +endef + +feature_print_text = $(eval $(feature_print_text_code)) $(info $(MSG)) +define feature_print_text_code + MSG = $(shell printf '...%30s: %s' $(1) $(2)) +endef + +PERF_FEATURES := $(foreach feat,$(LIB_FEATURE_TESTS),feature-$(feat)($(feature-$(feat)))) +PERF_FEATURES_FILE := $(shell touch $(OUTPUT)PERF-FEATURES; cat $(OUTPUT)PERF-FEATURES) + +ifeq ($(dwarf-post-unwind),1) + PERF_FEATURES += dwarf-post-unwind($(dwarf-post-unwind-text)) +endif + +# The $(display_lib) controls the default detection message +# output. It's set if: +# - detected features differes from stored features from +# last build (in PERF-FEATURES file) +# - one of the $(LIB_FEATURE_TESTS) is not detected +# - VF is enabled + +ifneq ("$(PERF_FEATURES)","$(PERF_FEATURES_FILE)") + $(shell echo "$(PERF_FEATURES)" > $(OUTPUT)PERF-FEATURES) + display_lib := 1 +endif + +feature_check = $(eval $(feature_check_code)) +define feature_check_code + ifneq ($(feature-$(1)), 1) + display_lib := 1 + endif +endef + +$(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_check,$(feat))) + +ifeq ($(VF),1) + display_lib := 1 + display_vf := 1 +endif + +ifeq ($(display_lib),1) + $(info ) + $(info Auto-detecting system features:) + $(foreach feat,$(LIB_FEATURE_TESTS),$(call feature_print_status,$(feat),)) + + ifeq ($(dwarf-post-unwind),1) + $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) + endif +endif + +ifeq ($(display_vf),1) + $(foreach feat,$(VF_FEATURE_TESTS),$(call feature_print_status,$(feat),)) + $(info ) + $(call feature_print_var,prefix) + $(call feature_print_var,bindir) + $(call feature_print_var,libdir) + $(call feature_print_var,sysconfdir) + $(call feature_print_var,LIBUNWIND_DIR) + $(call feature_print_var,LIBDW_DIR) +endif + +ifeq ($(display_lib),1) + $(info ) +endif diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch index fef8ae922800..4b06719ee984 100644 --- a/tools/perf/config/Makefile.arch +++ b/tools/perf/config/Makefile.arch @@ -5,7 +5,8 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ - -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ ) + -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ + -e s/tile.*/tile/ ) # Additional ARCH settings for x86 ifeq ($(ARCH),i386) diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 523b7bc10553..64c84e5f0514 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -24,9 +24,9 @@ FILES= \ test-libslang.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ - test-on-exit.bin \ test-stackprotector-all.bin \ - test-timerfd.bin + test-timerfd.bin \ + test-libdw-dwarf-unwind.bin CC := $(CROSS_COMPILE)gcc -MD PKG_CONFIG := $(CROSS_COMPILE)pkg-config @@ -132,15 +132,15 @@ test-liberty-z.bin: test-cplus-demangle.bin: $(BUILD) -liberty -test-on-exit.bin: - $(BUILD) - test-backtrace.bin: $(BUILD) test-timerfd.bin: $(BUILD) +test-libdw-dwarf-unwind.bin: + $(BUILD) + -include *.d ############################### diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c index 9b8a544155bb..fe5c1e5c952f 100644 --- a/tools/perf/config/feature-checks/test-all.c +++ b/tools/perf/config/feature-checks/test-all.c @@ -69,10 +69,6 @@ # include "test-libbfd.c" #undef main -#define main main_test_on_exit -# include "test-on-exit.c" -#undef main - #define main main_test_backtrace # include "test-backtrace.c" #undef main @@ -89,6 +85,10 @@ # include "test-stackprotector-all.c" #undef main +#define main main_test_libdw_dwarf_unwind +# include "test-libdw-dwarf-unwind.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -106,11 +106,11 @@ int main(int argc, char *argv[]) main_test_gtk2(argc, argv); main_test_gtk2_infobar(argc, argv); main_test_libbfd(); - main_test_on_exit(); main_test_backtrace(); main_test_libnuma(); main_test_timerfd(); main_test_stackprotector_all(); + main_test_libdw_dwarf_unwind(); return 0; } diff --git a/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c new file mode 100644 index 000000000000..f676a3ff442a --- /dev/null +++ b/tools/perf/config/feature-checks/test-libdw-dwarf-unwind.c @@ -0,0 +1,13 @@ + +#include <elfutils/libdwfl.h> + +int main(void) +{ + /* + * This function is guarded via: __nonnull_attribute__ (1, 2). + * Passing '1' as arguments value. This code is never executed, + * only compiled. + */ + dwfl_thread_getframes((void *) 1, (void *) 1, NULL); + return 0; +} diff --git a/tools/perf/config/feature-checks/test-on-exit.c b/tools/perf/config/feature-checks/test-on-exit.c deleted file mode 100644 index 8e88b16e6ded..000000000000 --- a/tools/perf/config/feature-checks/test-on-exit.c +++ /dev/null @@ -1,16 +0,0 @@ -#include <stdio.h> -#include <stdlib.h> - -static void exit_fn(int status, void *__data) -{ - printf("exit status: %d, data: %d\n", status, *(int *)__data); -} - -static int data = 123; - -int main(void) -{ - on_exit(exit_fn, &data); - - return 321; -} diff --git a/tools/perf/design.txt b/tools/perf/design.txt index 63a0e6f04a01..a28dca2582aa 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -18,7 +18,7 @@ underlying hardware counters. Performance counters are accessed via special file descriptors. There's one file descriptor per virtual counter used. -The special file descriptor is opened via the perf_event_open() +The special file descriptor is opened via the sys_perf_event_open() system call: int sys_perf_event_open(struct perf_event_attr *hw_event_uptr, @@ -82,7 +82,7 @@ machine-specific. If 'raw_type' is 0, then the 'type' field says what kind of counter this is, with the following encoding: -enum perf_event_types { +enum perf_type_id { PERF_TYPE_HARDWARE = 0, PERF_TYPE_SOFTWARE = 1, PERF_TYPE_TRACEPOINT = 2, @@ -95,7 +95,7 @@ specified by 'event_id': * Generalized performance counter event types, used by the hw_event.event_id * parameter of the sys_perf_event_open() syscall: */ -enum hw_event_ids { +enum perf_hw_id { /* * Common hardware events, generalized by the kernel: */ @@ -129,7 +129,7 @@ software events, selected by 'event_id': * physical and sw events of the kernel (and allow the profiling of them as * well): */ -enum sw_event_ids { +enum perf_sw_ids { PERF_COUNT_SW_CPU_CLOCK = 0, PERF_COUNT_SW_TASK_CLOCK = 1, PERF_COUNT_SW_PAGE_FAULTS = 2, @@ -230,7 +230,7 @@ these events are recorded in the ring-buffer (see below). The 'comm' bit allows tracking of process comm data on process creation. This too is recorded in the ring-buffer (see below). -The 'pid' parameter to the perf_event_open() system call allows the +The 'pid' parameter to the sys_perf_event_open() system call allows the counter to be specific to a task: pid == 0: if the pid parameter is zero, the counter is attached to the @@ -260,7 +260,7 @@ The 'flags' parameter is currently unused and must be zero. The 'group_fd' parameter allows counter "groups" to be set up. A counter group has one counter which is the group "leader". The leader -is created first, with group_fd = -1 in the perf_event_open call +is created first, with group_fd = -1 in the sys_perf_event_open call that creates it. The rest of the group members are created subsequently, with group_fd giving the fd of the group leader. (A single counter on its own is created with group_fd = -1 and is diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index 496e2abb5482..33569847fdcc 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -121,9 +121,9 @@ __perf_main () elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then evts=$($cmd list --raw-dump) __perfcomp_colon "$evts" "$cur" - # List subcommands for 'perf kvm' - elif [[ $prev == "kvm" ]]; then - subcmds="top record report diff buildid-list stat" + # List subcommands for perf commands + elif [[ $prev == @(kvm|kmem|mem|lock|sched) ]]; then + subcmds=$($cmd $prev --list-cmds) __perfcomp_colon "$subcmds" "$cur" # List long option names elif [[ $cur == --* ]]; then diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h new file mode 100644 index 000000000000..5268a1481d23 --- /dev/null +++ b/tools/perf/perf-sys.h @@ -0,0 +1,190 @@ +#ifndef _PERF_SYS_H +#define _PERF_SYS_H + +#include <unistd.h> +#include <sys/types.h> +#include <sys/syscall.h> +#include <linux/types.h> +#include <linux/perf_event.h> +#include <asm/unistd.h> + +#if defined(__i386__) +#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") +#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") +#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") +#define cpu_relax() asm volatile("rep; nop" ::: "memory"); +#define CPUINFO_PROC "model name" +#ifndef __NR_perf_event_open +# define __NR_perf_event_open 336 +#endif +#ifndef __NR_futex +# define __NR_futex 240 +#endif +#ifndef __NR_gettid +# define __NR_gettid 224 +#endif +#endif + +#if defined(__x86_64__) +#define mb() asm volatile("mfence" ::: "memory") +#define wmb() asm volatile("sfence" ::: "memory") +#define rmb() asm volatile("lfence" ::: "memory") +#define cpu_relax() asm volatile("rep; nop" ::: "memory"); +#define CPUINFO_PROC "model name" +#ifndef __NR_perf_event_open +# define __NR_perf_event_open 298 +#endif +#ifndef __NR_futex +# define __NR_futex 202 +#endif +#ifndef __NR_gettid +# define __NR_gettid 186 +#endif +#endif + +#ifdef __powerpc__ +#include "../../arch/powerpc/include/uapi/asm/unistd.h" +#define mb() asm volatile ("sync" ::: "memory") +#define wmb() asm volatile ("sync" ::: "memory") +#define rmb() asm volatile ("sync" ::: "memory") +#define CPUINFO_PROC "cpu" +#endif + +#ifdef __s390__ +#define mb() asm volatile("bcr 15,0" ::: "memory") +#define wmb() asm volatile("bcr 15,0" ::: "memory") +#define rmb() asm volatile("bcr 15,0" ::: "memory") +#endif + +#ifdef __sh__ +#if defined(__SH4A__) || defined(__SH5__) +# define mb() asm volatile("synco" ::: "memory") +# define wmb() asm volatile("synco" ::: "memory") +# define rmb() asm volatile("synco" ::: "memory") +#else +# define mb() asm volatile("" ::: "memory") +# define wmb() asm volatile("" ::: "memory") +# define rmb() asm volatile("" ::: "memory") +#endif +#define CPUINFO_PROC "cpu type" +#endif + +#ifdef __hppa__ +#define mb() asm volatile("" ::: "memory") +#define wmb() asm volatile("" ::: "memory") +#define rmb() asm volatile("" ::: "memory") +#define CPUINFO_PROC "cpu" +#endif + +#ifdef __sparc__ +#ifdef __LP64__ +#define mb() asm volatile("ba,pt %%xcc, 1f\n" \ + "membar #StoreLoad\n" \ + "1:\n":::"memory") +#else +#define mb() asm volatile("":::"memory") +#endif +#define wmb() asm volatile("":::"memory") +#define rmb() asm volatile("":::"memory") +#define CPUINFO_PROC "cpu" +#endif + +#ifdef __alpha__ +#define mb() asm volatile("mb" ::: "memory") +#define wmb() asm volatile("wmb" ::: "memory") +#define rmb() asm volatile("mb" ::: "memory") +#define CPUINFO_PROC "cpu model" +#endif + +#ifdef __ia64__ +#define mb() asm volatile ("mf" ::: "memory") +#define wmb() asm volatile ("mf" ::: "memory") +#define rmb() asm volatile ("mf" ::: "memory") +#define cpu_relax() asm volatile ("hint @pause" ::: "memory") +#define CPUINFO_PROC "model name" +#endif + +#ifdef __arm__ +/* + * Use the __kuser_memory_barrier helper in the CPU helper page. See + * arch/arm/kernel/entry-armv.S in the kernel source for details. + */ +#define mb() ((void(*)(void))0xffff0fa0)() +#define wmb() ((void(*)(void))0xffff0fa0)() +#define rmb() ((void(*)(void))0xffff0fa0)() +#define CPUINFO_PROC "Processor" +#endif + +#ifdef __aarch64__ +#define mb() asm volatile("dmb ish" ::: "memory") +#define wmb() asm volatile("dmb ishst" ::: "memory") +#define rmb() asm volatile("dmb ishld" ::: "memory") +#define cpu_relax() asm volatile("yield" ::: "memory") +#endif + +#ifdef __mips__ +#define mb() asm volatile( \ + ".set mips2\n\t" \ + "sync\n\t" \ + ".set mips0" \ + : /* no output */ \ + : /* no input */ \ + : "memory") +#define wmb() mb() +#define rmb() mb() +#define CPUINFO_PROC "cpu model" +#endif + +#ifdef __arc__ +#define mb() asm volatile("" ::: "memory") +#define wmb() asm volatile("" ::: "memory") +#define rmb() asm volatile("" ::: "memory") +#define CPUINFO_PROC "Processor" +#endif + +#ifdef __metag__ +#define mb() asm volatile("" ::: "memory") +#define wmb() asm volatile("" ::: "memory") +#define rmb() asm volatile("" ::: "memory") +#define CPUINFO_PROC "CPU" +#endif + +#ifdef __xtensa__ +#define mb() asm volatile("memw" ::: "memory") +#define wmb() asm volatile("memw" ::: "memory") +#define rmb() asm volatile("" ::: "memory") +#define CPUINFO_PROC "core ID" +#endif + +#ifdef __tile__ +#define mb() asm volatile ("mf" ::: "memory") +#define wmb() asm volatile ("mf" ::: "memory") +#define rmb() asm volatile ("mf" ::: "memory") +#define cpu_relax() asm volatile ("mfspr zero, PASS" ::: "memory") +#define CPUINFO_PROC "model name" +#endif + +#define barrier() asm volatile ("" ::: "memory") + +#ifndef cpu_relax +#define cpu_relax() barrier() +#endif + +static inline int +sys_perf_event_open(struct perf_event_attr *attr, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + int fd; + + fd = syscall(__NR_perf_event_open, attr, pid, cpu, + group_fd, flags); + +#ifdef HAVE_ATTR_TEST + if (unlikely(test_attr__enabled)) + test_attr__open(attr, pid, cpu, fd, group_fd, flags); +#endif + return fd; +} + +#endif /* _PERF_SYS_H */ diff --git a/tools/perf/perf.h b/tools/perf/perf.h index e84fa26bc1be..510c65f72858 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -1,168 +1,18 @@ #ifndef _PERF_PERF_H #define _PERF_PERF_H -#include <asm/unistd.h> - -#if defined(__i386__) -#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") -#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") -#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") -#define cpu_relax() asm volatile("rep; nop" ::: "memory"); -#define CPUINFO_PROC "model name" -#ifndef __NR_perf_event_open -# define __NR_perf_event_open 336 -#endif -#endif - -#if defined(__x86_64__) -#define mb() asm volatile("mfence" ::: "memory") -#define wmb() asm volatile("sfence" ::: "memory") -#define rmb() asm volatile("lfence" ::: "memory") -#define cpu_relax() asm volatile("rep; nop" ::: "memory"); -#define CPUINFO_PROC "model name" -#ifndef __NR_perf_event_open -# define __NR_perf_event_open 298 -#endif -#endif - -#ifdef __powerpc__ -#include "../../arch/powerpc/include/uapi/asm/unistd.h" -#define mb() asm volatile ("sync" ::: "memory") -#define wmb() asm volatile ("sync" ::: "memory") -#define rmb() asm volatile ("sync" ::: "memory") -#define CPUINFO_PROC "cpu" -#endif - -#ifdef __s390__ -#define mb() asm volatile("bcr 15,0" ::: "memory") -#define wmb() asm volatile("bcr 15,0" ::: "memory") -#define rmb() asm volatile("bcr 15,0" ::: "memory") -#endif - -#ifdef __sh__ -#if defined(__SH4A__) || defined(__SH5__) -# define mb() asm volatile("synco" ::: "memory") -# define wmb() asm volatile("synco" ::: "memory") -# define rmb() asm volatile("synco" ::: "memory") -#else -# define mb() asm volatile("" ::: "memory") -# define wmb() asm volatile("" ::: "memory") -# define rmb() asm volatile("" ::: "memory") -#endif -#define CPUINFO_PROC "cpu type" -#endif - -#ifdef __hppa__ -#define mb() asm volatile("" ::: "memory") -#define wmb() asm volatile("" ::: "memory") -#define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "cpu" -#endif - -#ifdef __sparc__ -#ifdef __LP64__ -#define mb() asm volatile("ba,pt %%xcc, 1f\n" \ - "membar #StoreLoad\n" \ - "1:\n":::"memory") -#else -#define mb() asm volatile("":::"memory") -#endif -#define wmb() asm volatile("":::"memory") -#define rmb() asm volatile("":::"memory") -#define CPUINFO_PROC "cpu" -#endif - -#ifdef __alpha__ -#define mb() asm volatile("mb" ::: "memory") -#define wmb() asm volatile("wmb" ::: "memory") -#define rmb() asm volatile("mb" ::: "memory") -#define CPUINFO_PROC "cpu model" -#endif - -#ifdef __ia64__ -#define mb() asm volatile ("mf" ::: "memory") -#define wmb() asm volatile ("mf" ::: "memory") -#define rmb() asm volatile ("mf" ::: "memory") -#define cpu_relax() asm volatile ("hint @pause" ::: "memory") -#define CPUINFO_PROC "model name" -#endif - -#ifdef __arm__ -/* - * Use the __kuser_memory_barrier helper in the CPU helper page. See - * arch/arm/kernel/entry-armv.S in the kernel source for details. - */ -#define mb() ((void(*)(void))0xffff0fa0)() -#define wmb() ((void(*)(void))0xffff0fa0)() -#define rmb() ((void(*)(void))0xffff0fa0)() -#define CPUINFO_PROC "Processor" -#endif - -#ifdef __aarch64__ -#define mb() asm volatile("dmb ish" ::: "memory") -#define wmb() asm volatile("dmb ishst" ::: "memory") -#define rmb() asm volatile("dmb ishld" ::: "memory") -#define cpu_relax() asm volatile("yield" ::: "memory") -#endif - -#ifdef __mips__ -#define mb() asm volatile( \ - ".set mips2\n\t" \ - "sync\n\t" \ - ".set mips0" \ - : /* no output */ \ - : /* no input */ \ - : "memory") -#define wmb() mb() -#define rmb() mb() -#define CPUINFO_PROC "cpu model" -#endif - -#ifdef __arc__ -#define mb() asm volatile("" ::: "memory") -#define wmb() asm volatile("" ::: "memory") -#define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "Processor" -#endif - -#ifdef __metag__ -#define mb() asm volatile("" ::: "memory") -#define wmb() asm volatile("" ::: "memory") -#define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "CPU" -#endif - -#ifdef __xtensa__ -#define mb() asm volatile("memw" ::: "memory") -#define wmb() asm volatile("memw" ::: "memory") -#define rmb() asm volatile("" ::: "memory") -#define CPUINFO_PROC "core ID" -#endif - -#define barrier() asm volatile ("" ::: "memory") - -#ifndef cpu_relax -#define cpu_relax() barrier() -#endif - -#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) - - #include <time.h> -#include <unistd.h> -#include <sys/types.h> -#include <sys/syscall.h> - -#include <linux/perf_event.h> -#include "util/types.h" #include <stdbool.h> +#include <linux/types.h> +#include <linux/perf_event.h> + +extern bool test_attr__enabled; +void test_attr__init(void); +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags); -/* - * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all - * counters in the current task. - */ -#define PR_TASK_PERF_EVENTS_DISABLE 31 -#define PR_TASK_PERF_EVENTS_ENABLE 32 +#define HAVE_ATTR_TEST +#include "perf-sys.h" #ifndef NSEC_PER_SEC # define NSEC_PER_SEC 1000000000ULL @@ -179,67 +29,8 @@ static inline unsigned long long rdclock(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } -/* - * Pick up some kernel type conventions: - */ -#define __user -#define asmlinkage - -#define unlikely(x) __builtin_expect(!!(x), 0) -#define min(x, y) ({ \ - typeof(x) _min1 = (x); \ - typeof(y) _min2 = (y); \ - (void) (&_min1 == &_min2); \ - _min1 < _min2 ? _min1 : _min2; }) - -extern bool test_attr__enabled; -void test_attr__init(void); -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, - int fd, int group_fd, unsigned long flags); - -static inline int -sys_perf_event_open(struct perf_event_attr *attr, - pid_t pid, int cpu, int group_fd, - unsigned long flags) -{ - int fd; - - fd = syscall(__NR_perf_event_open, attr, pid, cpu, - group_fd, flags); - - if (unlikely(test_attr__enabled)) - test_attr__open(attr, pid, cpu, fd, group_fd, flags); - - return fd; -} - -#define MAX_COUNTERS 256 #define MAX_NR_CPUS 256 -struct ip_callchain { - u64 nr; - u64 ips[0]; -}; - -struct branch_flags { - u64 mispred:1; - u64 predicted:1; - u64 in_tx:1; - u64 abort:1; - u64 reserved:60; -}; - -struct branch_entry { - u64 from; - u64 to; - struct branch_flags flags; -}; - -struct branch_stack { - u64 nr; - struct branch_entry entries[0]; -}; - extern const char *input_name; extern bool perf_host, perf_guest; extern const char perf_version_string[]; @@ -248,15 +39,10 @@ void pthread__unblock_sigwinch(void); #include "util/target.h" -enum perf_call_graph_mode { - CALLCHAIN_NONE, - CALLCHAIN_FP, - CALLCHAIN_DWARF -}; - struct record_opts { struct target target; int call_graph; + bool call_graph_enabled; bool group; bool inherit_stat; bool no_buffering; diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 00218f503b2e..2dfc9ad0e6f2 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -1,4 +1,3 @@ - /* * The struct perf_event_attr test support. * @@ -19,14 +18,8 @@ * permissions. All the event text files are stored there. */ -/* - * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select - * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu. - */ -#define __SANE_USERSPACE_TYPES__ #include <stdlib.h> #include <stdio.h> -#include <inttypes.h> #include <linux/types.h> #include <linux/kernel.h> #include "../perf.h" diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 1e67437fb4ca..831f52cae197 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -115,6 +115,30 @@ static struct test { .desc = "Test parsing with no sample_id_all bit set", .func = test__parse_no_sample_id_all, }, +#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "Test dwarf unwind", + .func = test__dwarf_unwind, + }, +#endif +#endif + { + .desc = "Test filtering hist entries", + .func = test__hists_filter, + }, + { + .desc = "Test mmap thread lookup", + .func = test__mmap_thread_lookup, + }, + { + .desc = "Test thread mg sharing", + .func = test__thread_mg_share, + }, + { + .desc = "Test output sorting of hist entries", + .func = test__hists_output, + }, { .func = NULL, }, diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 653a8fe2db95..67f2d6323558 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -1,8 +1,7 @@ -#include <sys/types.h> +#include <linux/types.h> #include <stdlib.h> #include <unistd.h> #include <stdio.h> -#include <inttypes.h> #include <ctype.h> #include <string.h> @@ -257,7 +256,7 @@ static int process_sample_event(struct machine *machine, return -1; } - thread = machine__findnew_thread(machine, sample.pid, sample.pid); + thread = machine__findnew_thread(machine, sample.pid, sample.tid); if (!thread) { pr_debug("machine__findnew_thread failed\n"); return -1; @@ -504,6 +503,7 @@ static int do_test_code_reading(bool try_kcore) if (ret < 0) { if (!excl_kernel) { excl_kernel = true; + perf_evlist__set_maps(evlist, NULL, NULL); perf_evlist__delete(evlist); evlist = NULL; continue; diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 9cc81a3eb9b4..3e6cb171e3d3 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -1,7 +1,7 @@ #include "util.h" #include <stdlib.h> -#include <sys/types.h> +#include <linux/types.h> #include <sys/stat.h> #include <fcntl.h> #include <string.h> diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c new file mode 100644 index 000000000000..108f0cd49f4e --- /dev/null +++ b/tools/perf/tests/dwarf-unwind.c @@ -0,0 +1,144 @@ +#include <linux/compiler.h> +#include <linux/types.h> +#include <unistd.h> +#include "tests.h" +#include "debug.h" +#include "machine.h" +#include "event.h" +#include "unwind.h" +#include "perf_regs.h" +#include "map.h" +#include "thread.h" + +static int mmap_handler(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_mmap_event(machine, event, NULL); +} + +static int init_live_machine(struct machine *machine) +{ + union perf_event event; + pid_t pid = getpid(); + + return perf_event__synthesize_mmap_events(NULL, &event, pid, pid, + mmap_handler, machine, true); +} + +#define MAX_STACK 6 + +static int unwind_entry(struct unwind_entry *entry, void *arg) +{ + unsigned long *cnt = (unsigned long *) arg; + char *symbol = entry->sym ? entry->sym->name : NULL; + static const char *funcs[MAX_STACK] = { + "test__arch_unwind_sample", + "unwind_thread", + "krava_3", + "krava_2", + "krava_1", + "test__dwarf_unwind" + }; + + if (*cnt >= MAX_STACK) { + pr_debug("failed: crossed the max stack value %d\n", MAX_STACK); + return -1; + } + + if (!symbol) { + pr_debug("failed: got unresolved address 0x%" PRIx64 "\n", + entry->ip); + return -1; + } + + pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip); + return strcmp((const char *) symbol, funcs[(*cnt)++]); +} + +__attribute__ ((noinline)) +static int unwind_thread(struct thread *thread, struct machine *machine) +{ + struct perf_sample sample; + unsigned long cnt = 0; + int err = -1; + + memset(&sample, 0, sizeof(sample)); + + if (test__arch_unwind_sample(&sample, thread)) { + pr_debug("failed to get unwind sample\n"); + goto out; + } + + err = unwind__get_entries(unwind_entry, &cnt, machine, thread, + &sample, MAX_STACK); + if (err) + pr_debug("unwind failed\n"); + else if (cnt != MAX_STACK) { + pr_debug("got wrong number of stack entries %lu != %d\n", + cnt, MAX_STACK); + err = -1; + } + + out: + free(sample.user_stack.data); + free(sample.user_regs.regs); + return err; +} + +__attribute__ ((noinline)) +static int krava_3(struct thread *thread, struct machine *machine) +{ + return unwind_thread(thread, machine); +} + +__attribute__ ((noinline)) +static int krava_2(struct thread *thread, struct machine *machine) +{ + return krava_3(thread, machine); +} + +__attribute__ ((noinline)) +static int krava_1(struct thread *thread, struct machine *machine) +{ + return krava_2(thread, machine); +} + +int test__dwarf_unwind(void) +{ + struct machines machines; + struct machine *machine; + struct thread *thread; + int err = -1; + + machines__init(&machines); + + machine = machines__find(&machines, HOST_KERNEL_ID); + if (!machine) { + pr_err("Could not get machine\n"); + return -1; + } + + if (init_live_machine(machine)) { + pr_err("Could not init machine\n"); + goto out; + } + + if (verbose > 1) + machine__fprintf(machine, stderr); + + thread = machine__find_thread(machine, getpid(), getpid()); + if (!thread) { + pr_err("Could not get thread\n"); + goto out; + } + + err = krava_1(thread, machine); + + out: + machine__delete_threads(machine); + machine__exit(machine); + machines__exit(&machines); + return err; +} diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 4774f7fbb758..35d7fdb2328d 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -74,9 +74,6 @@ int test__perf_evsel__tp_sched_test(void) if (perf_evsel__test_field(evsel, "prio", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "success", 4, true)) - ret = -1; - if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) ret = -1; diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c new file mode 100644 index 000000000000..e4e01aadc3be --- /dev/null +++ b/tools/perf/tests/hists_common.c @@ -0,0 +1,205 @@ +#include "perf.h" +#include "util/debug.h" +#include "util/symbol.h" +#include "util/sort.h" +#include "util/evsel.h" +#include "util/evlist.h" +#include "util/machine.h" +#include "util/thread.h" +#include "tests/hists_common.h" + +static struct { + u32 pid; + const char *comm; +} fake_threads[] = { + { 100, "perf" }, + { 200, "perf" }, + { 300, "bash" }, +}; + +static struct { + u32 pid; + u64 start; + const char *filename; +} fake_mmap_info[] = { + { 100, 0x40000, "perf" }, + { 100, 0x50000, "libc" }, + { 100, 0xf0000, "[kernel]" }, + { 200, 0x40000, "perf" }, + { 200, 0x50000, "libc" }, + { 200, 0xf0000, "[kernel]" }, + { 300, 0x40000, "bash" }, + { 300, 0x50000, "libc" }, + { 300, 0xf0000, "[kernel]" }, +}; + +struct fake_sym { + u64 start; + u64 length; + const char *name; +}; + +static struct fake_sym perf_syms[] = { + { 700, 100, "main" }, + { 800, 100, "run_command" }, + { 900, 100, "cmd_record" }, +}; + +static struct fake_sym bash_syms[] = { + { 700, 100, "main" }, + { 800, 100, "xmalloc" }, + { 900, 100, "xfree" }, +}; + +static struct fake_sym libc_syms[] = { + { 700, 100, "malloc" }, + { 800, 100, "free" }, + { 900, 100, "realloc" }, +}; + +static struct fake_sym kernel_syms[] = { + { 700, 100, "schedule" }, + { 800, 100, "page_fault" }, + { 900, 100, "sys_perf_event_open" }, +}; + +static struct { + const char *dso_name; + struct fake_sym *syms; + size_t nr_syms; +} fake_symbols[] = { + { "perf", perf_syms, ARRAY_SIZE(perf_syms) }, + { "bash", bash_syms, ARRAY_SIZE(bash_syms) }, + { "libc", libc_syms, ARRAY_SIZE(libc_syms) }, + { "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) }, +}; + +struct machine *setup_fake_machine(struct machines *machines) +{ + struct machine *machine = machines__find(machines, HOST_KERNEL_ID); + size_t i; + + if (machine == NULL) { + pr_debug("Not enough memory for machine setup\n"); + return NULL; + } + + for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { + struct thread *thread; + + thread = machine__findnew_thread(machine, fake_threads[i].pid, + fake_threads[i].pid); + if (thread == NULL) + goto out; + + thread__set_comm(thread, fake_threads[i].comm, 0); + } + + for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) { + union perf_event fake_mmap_event = { + .mmap = { + .header = { .misc = PERF_RECORD_MISC_USER, }, + .pid = fake_mmap_info[i].pid, + .tid = fake_mmap_info[i].pid, + .start = fake_mmap_info[i].start, + .len = 0x1000ULL, + .pgoff = 0ULL, + }, + }; + + strcpy(fake_mmap_event.mmap.filename, + fake_mmap_info[i].filename); + + machine__process_mmap_event(machine, &fake_mmap_event, NULL); + } + + for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) { + size_t k; + struct dso *dso; + + dso = __dsos__findnew(&machine->user_dsos, + fake_symbols[i].dso_name); + if (dso == NULL) + goto out; + + /* emulate dso__load() */ + dso__set_loaded(dso, MAP__FUNCTION); + + for (k = 0; k < fake_symbols[i].nr_syms; k++) { + struct symbol *sym; + struct fake_sym *fsym = &fake_symbols[i].syms[k]; + + sym = symbol__new(fsym->start, fsym->length, + STB_GLOBAL, fsym->name); + if (sym == NULL) + goto out; + + symbols__insert(&dso->symbols[MAP__FUNCTION], sym); + } + } + + return machine; + +out: + pr_debug("Not enough memory for machine setup\n"); + machine__delete_threads(machine); + machine__delete(machine); + return NULL; +} + +void print_hists_in(struct hists *hists) +{ + int i = 0; + struct rb_root *root; + struct rb_node *node; + + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + pr_info("----- %s --------\n", __func__); + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node_in); + + if (!he->filtered) { + pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n", + i, thread__comm_str(he->thread), + he->ms.map->dso->short_name, + he->ms.sym->name, he->stat.period); + } + + i++; + node = rb_next(node); + } +} + +void print_hists_out(struct hists *hists) +{ + int i = 0; + struct rb_root *root; + struct rb_node *node; + + root = &hists->entries; + + pr_info("----- %s --------\n", __func__); + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node); + + if (!he->filtered) { + pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"\n", + i, thread__comm_str(he->thread), he->thread->tid, + he->ms.map->dso->short_name, + he->ms.sym->name, he->stat.period); + } + + i++; + node = rb_next(node); + } +} diff --git a/tools/perf/tests/hists_common.h b/tools/perf/tests/hists_common.h new file mode 100644 index 000000000000..1415ae69d7b6 --- /dev/null +++ b/tools/perf/tests/hists_common.h @@ -0,0 +1,47 @@ +#ifndef __PERF_TESTS__HISTS_COMMON_H__ +#define __PERF_TESTS__HISTS_COMMON_H__ + +struct machine; +struct machines; + +/* + * The setup_fake_machine() provides a test environment which consists + * of 3 processes that have 3 mappings and in turn, have 3 symbols + * respectively. See below table: + * + * Command: Pid Shared Object Symbol + * ............. ............. ................... + * perf: 100 perf main + * perf: 100 perf run_command + * perf: 100 perf comd_record + * perf: 100 libc malloc + * perf: 100 libc free + * perf: 100 libc realloc + * perf: 100 [kernel] schedule + * perf: 100 [kernel] page_fault + * perf: 100 [kernel] sys_perf_event_open + * perf: 200 perf main + * perf: 200 perf run_command + * perf: 200 perf comd_record + * perf: 200 libc malloc + * perf: 200 libc free + * perf: 200 libc realloc + * perf: 200 [kernel] schedule + * perf: 200 [kernel] page_fault + * perf: 200 [kernel] sys_perf_event_open + * bash: 300 bash main + * bash: 300 bash xmalloc + * bash: 300 bash xfree + * bash: 300 libc malloc + * bash: 300 libc free + * bash: 300 libc realloc + * bash: 300 [kernel] schedule + * bash: 300 [kernel] page_fault + * bash: 300 [kernel] sys_perf_event_open + */ +struct machine *setup_fake_machine(struct machines *machines); + +void print_hists_in(struct hists *hists); +void print_hists_out(struct hists *hists); + +#endif /* __PERF_TESTS__HISTS_COMMON_H__ */ diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c new file mode 100644 index 000000000000..c5ba924a3581 --- /dev/null +++ b/tools/perf/tests/hists_filter.c @@ -0,0 +1,290 @@ +#include "perf.h" +#include "util/debug.h" +#include "util/symbol.h" +#include "util/sort.h" +#include "util/evsel.h" +#include "util/evlist.h" +#include "util/machine.h" +#include "util/thread.h" +#include "util/parse-events.h" +#include "tests/tests.h" +#include "tests/hists_common.h" + +struct sample { + u32 pid; + u64 ip; + struct thread *thread; + struct map *map; + struct symbol *sym; +}; + +/* For the numbers, see hists_common.c */ +static struct sample fake_samples[] = { + /* perf [kernel] schedule() */ + { .pid = 100, .ip = 0xf0000 + 700, }, + /* perf [perf] main() */ + { .pid = 100, .ip = 0x40000 + 700, }, + /* perf [libc] malloc() */ + { .pid = 100, .ip = 0x50000 + 700, }, + /* perf [perf] main() */ + { .pid = 200, .ip = 0x40000 + 700, }, /* will be merged */ + /* perf [perf] cmd_record() */ + { .pid = 200, .ip = 0x40000 + 900, }, + /* perf [kernel] page_fault() */ + { .pid = 200, .ip = 0xf0000 + 800, }, + /* bash [bash] main() */ + { .pid = 300, .ip = 0x40000 + 700, }, + /* bash [bash] xmalloc() */ + { .pid = 300, .ip = 0x40000 + 800, }, + /* bash [libc] malloc() */ + { .pid = 300, .ip = 0x50000 + 700, }, + /* bash [kernel] page_fault() */ + { .pid = 300, .ip = 0xf0000 + 800, }, +}; + +static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) +{ + struct perf_evsel *evsel; + struct addr_location al; + struct hist_entry *he; + struct perf_sample sample = { .cpu = 0, }; + size_t i; + + /* + * each evsel will have 10 samples but the 4th sample + * (perf [perf] main) will be collapsed to an existing entry + * so total 9 entries will be in the tree. + */ + evlist__for_each(evlist, evsel) { + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { + const union perf_event event = { + .header = { + .misc = PERF_RECORD_MISC_USER, + }, + }; + + /* make sure it has no filter at first */ + evsel->hists.thread_filter = NULL; + evsel->hists.dso_filter = NULL; + evsel->hists.symbol_filter_str = NULL; + + sample.pid = fake_samples[i].pid; + sample.tid = fake_samples[i].pid; + sample.ip = fake_samples[i].ip; + + if (perf_event__preprocess_sample(&event, machine, &al, + &sample) < 0) + goto out; + + he = __hists__add_entry(&evsel->hists, &al, NULL, + NULL, NULL, 100, 1, 0); + if (he == NULL) + goto out; + + fake_samples[i].thread = al.thread; + fake_samples[i].map = al.map; + fake_samples[i].sym = al.sym; + + hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE); + if (!he->filtered) + he->hists->stats.nr_non_filtered_samples++; + } + } + + return 0; + +out: + pr_debug("Not enough memory for adding a hist entry\n"); + return TEST_FAIL; +} + +int test__hists_filter(void) +{ + int err = TEST_FAIL; + struct machines machines; + struct machine *machine; + struct perf_evsel *evsel; + struct perf_evlist *evlist = perf_evlist__new(); + + TEST_ASSERT_VAL("No memory", evlist); + + err = parse_events(evlist, "cpu-clock"); + if (err) + goto out; + err = parse_events(evlist, "task-clock"); + if (err) + goto out; + + /* default sort order (comm,dso,sym) will be used */ + if (setup_sorting() < 0) + goto out; + + machines__init(&machines); + + /* setup threads/dso/map/symbols also */ + machine = setup_fake_machine(&machines); + if (!machine) + goto out; + + if (verbose > 1) + machine__fprintf(machine, stderr); + + /* process sample events */ + err = add_hist_entries(evlist, machine); + if (err < 0) + goto out; + + evlist__for_each(evlist, evsel) { + struct hists *hists = &evsel->hists; + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + if (verbose > 2) { + pr_info("Normal histogram\n"); + print_hists_out(hists); + } + + TEST_ASSERT_VAL("Invalid nr samples", + hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10); + TEST_ASSERT_VAL("Invalid nr hist entries", + hists->nr_entries == 9); + TEST_ASSERT_VAL("Invalid total period", + hists->stats.total_period == 1000); + TEST_ASSERT_VAL("Unmatched nr samples", + hists->stats.nr_events[PERF_RECORD_SAMPLE] == + hists->stats.nr_non_filtered_samples); + TEST_ASSERT_VAL("Unmatched nr hist entries", + hists->nr_entries == hists->nr_non_filtered_entries); + TEST_ASSERT_VAL("Unmatched total period", + hists->stats.total_period == + hists->stats.total_non_filtered_period); + + /* now applying thread filter for 'bash' */ + evsel->hists.thread_filter = fake_samples[9].thread; + hists__filter_by_thread(hists); + + if (verbose > 2) { + pr_info("Histogram for thread filter\n"); + print_hists_out(hists); + } + + /* normal stats should be invariant */ + TEST_ASSERT_VAL("Invalid nr samples", + hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10); + TEST_ASSERT_VAL("Invalid nr hist entries", + hists->nr_entries == 9); + TEST_ASSERT_VAL("Invalid total period", + hists->stats.total_period == 1000); + + /* but filter stats are changed */ + TEST_ASSERT_VAL("Unmatched nr samples for thread filter", + hists->stats.nr_non_filtered_samples == 4); + TEST_ASSERT_VAL("Unmatched nr hist entries for thread filter", + hists->nr_non_filtered_entries == 4); + TEST_ASSERT_VAL("Unmatched total period for thread filter", + hists->stats.total_non_filtered_period == 400); + + /* remove thread filter first */ + evsel->hists.thread_filter = NULL; + hists__filter_by_thread(hists); + + /* now applying dso filter for 'kernel' */ + evsel->hists.dso_filter = fake_samples[0].map->dso; + hists__filter_by_dso(hists); + + if (verbose > 2) { + pr_info("Histogram for dso filter\n"); + print_hists_out(hists); + } + + /* normal stats should be invariant */ + TEST_ASSERT_VAL("Invalid nr samples", + hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10); + TEST_ASSERT_VAL("Invalid nr hist entries", + hists->nr_entries == 9); + TEST_ASSERT_VAL("Invalid total period", + hists->stats.total_period == 1000); + + /* but filter stats are changed */ + TEST_ASSERT_VAL("Unmatched nr samples for dso filter", + hists->stats.nr_non_filtered_samples == 3); + TEST_ASSERT_VAL("Unmatched nr hist entries for dso filter", + hists->nr_non_filtered_entries == 3); + TEST_ASSERT_VAL("Unmatched total period for dso filter", + hists->stats.total_non_filtered_period == 300); + + /* remove dso filter first */ + evsel->hists.dso_filter = NULL; + hists__filter_by_dso(hists); + + /* + * now applying symbol filter for 'main'. Also note that + * there's 3 samples that have 'main' symbol but the 4th + * entry of fake_samples was collapsed already so it won't + * be counted as a separate entry but the sample count and + * total period will be remained. + */ + evsel->hists.symbol_filter_str = "main"; + hists__filter_by_symbol(hists); + + if (verbose > 2) { + pr_info("Histogram for symbol filter\n"); + print_hists_out(hists); + } + + /* normal stats should be invariant */ + TEST_ASSERT_VAL("Invalid nr samples", + hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10); + TEST_ASSERT_VAL("Invalid nr hist entries", + hists->nr_entries == 9); + TEST_ASSERT_VAL("Invalid total period", + hists->stats.total_period == 1000); + + /* but filter stats are changed */ + TEST_ASSERT_VAL("Unmatched nr samples for symbol filter", + hists->stats.nr_non_filtered_samples == 3); + TEST_ASSERT_VAL("Unmatched nr hist entries for symbol filter", + hists->nr_non_filtered_entries == 2); + TEST_ASSERT_VAL("Unmatched total period for symbol filter", + hists->stats.total_non_filtered_period == 300); + + /* now applying all filters at once. */ + evsel->hists.thread_filter = fake_samples[1].thread; + evsel->hists.dso_filter = fake_samples[1].map->dso; + hists__filter_by_thread(hists); + hists__filter_by_dso(hists); + + if (verbose > 2) { + pr_info("Histogram for all filters\n"); + print_hists_out(hists); + } + + /* normal stats should be invariant */ + TEST_ASSERT_VAL("Invalid nr samples", + hists->stats.nr_events[PERF_RECORD_SAMPLE] == 10); + TEST_ASSERT_VAL("Invalid nr hist entries", + hists->nr_entries == 9); + TEST_ASSERT_VAL("Invalid total period", + hists->stats.total_period == 1000); + + /* but filter stats are changed */ + TEST_ASSERT_VAL("Unmatched nr samples for all filter", + hists->stats.nr_non_filtered_samples == 2); + TEST_ASSERT_VAL("Unmatched nr hist entries for all filter", + hists->nr_non_filtered_entries == 1); + TEST_ASSERT_VAL("Unmatched total period for all filter", + hists->stats.total_non_filtered_period == 200); + } + + + err = TEST_OK; + +out: + /* tear down everything */ + perf_evlist__delete(evlist); + reset_output_field(); + machines__exit(&machines); + + return err; +} diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 2b6519e0e36f..5ffa2c3eb77d 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -8,144 +8,7 @@ #include "machine.h" #include "thread.h" #include "parse-events.h" - -static struct { - u32 pid; - const char *comm; -} fake_threads[] = { - { 100, "perf" }, - { 200, "perf" }, - { 300, "bash" }, -}; - -static struct { - u32 pid; - u64 start; - const char *filename; -} fake_mmap_info[] = { - { 100, 0x40000, "perf" }, - { 100, 0x50000, "libc" }, - { 100, 0xf0000, "[kernel]" }, - { 200, 0x40000, "perf" }, - { 200, 0x50000, "libc" }, - { 200, 0xf0000, "[kernel]" }, - { 300, 0x40000, "bash" }, - { 300, 0x50000, "libc" }, - { 300, 0xf0000, "[kernel]" }, -}; - -struct fake_sym { - u64 start; - u64 length; - const char *name; -}; - -static struct fake_sym perf_syms[] = { - { 700, 100, "main" }, - { 800, 100, "run_command" }, - { 900, 100, "cmd_record" }, -}; - -static struct fake_sym bash_syms[] = { - { 700, 100, "main" }, - { 800, 100, "xmalloc" }, - { 900, 100, "xfree" }, -}; - -static struct fake_sym libc_syms[] = { - { 700, 100, "malloc" }, - { 800, 100, "free" }, - { 900, 100, "realloc" }, -}; - -static struct fake_sym kernel_syms[] = { - { 700, 100, "schedule" }, - { 800, 100, "page_fault" }, - { 900, 100, "sys_perf_event_open" }, -}; - -static struct { - const char *dso_name; - struct fake_sym *syms; - size_t nr_syms; -} fake_symbols[] = { - { "perf", perf_syms, ARRAY_SIZE(perf_syms) }, - { "bash", bash_syms, ARRAY_SIZE(bash_syms) }, - { "libc", libc_syms, ARRAY_SIZE(libc_syms) }, - { "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) }, -}; - -static struct machine *setup_fake_machine(struct machines *machines) -{ - struct machine *machine = machines__find(machines, HOST_KERNEL_ID); - size_t i; - - if (machine == NULL) { - pr_debug("Not enough memory for machine setup\n"); - return NULL; - } - - for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { - struct thread *thread; - - thread = machine__findnew_thread(machine, fake_threads[i].pid, - fake_threads[i].pid); - if (thread == NULL) - goto out; - - thread__set_comm(thread, fake_threads[i].comm, 0); - } - - for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) { - union perf_event fake_mmap_event = { - .mmap = { - .header = { .misc = PERF_RECORD_MISC_USER, }, - .pid = fake_mmap_info[i].pid, - .start = fake_mmap_info[i].start, - .len = 0x1000ULL, - .pgoff = 0ULL, - }, - }; - - strcpy(fake_mmap_event.mmap.filename, - fake_mmap_info[i].filename); - - machine__process_mmap_event(machine, &fake_mmap_event, NULL); - } - - for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) { - size_t k; - struct dso *dso; - - dso = __dsos__findnew(&machine->user_dsos, - fake_symbols[i].dso_name); - if (dso == NULL) - goto out; - - /* emulate dso__load() */ - dso__set_loaded(dso, MAP__FUNCTION); - - for (k = 0; k < fake_symbols[i].nr_syms; k++) { - struct symbol *sym; - struct fake_sym *fsym = &fake_symbols[i].syms[k]; - - sym = symbol__new(fsym->start, fsym->length, - STB_GLOBAL, fsym->name); - if (sym == NULL) - goto out; - - symbols__insert(&dso->symbols[MAP__FUNCTION], sym); - } - } - - return machine; - -out: - pr_debug("Not enough memory for machine setup\n"); - machine__delete_threads(machine); - machine__delete(machine); - return NULL; -} +#include "hists_common.h" struct sample { u32 pid; @@ -155,6 +18,7 @@ struct sample { struct symbol *sym; }; +/* For the numbers, see hists_common.c */ static struct sample fake_common_samples[] = { /* perf [kernel] schedule() */ { .pid = 100, .ip = 0xf0000 + 700, }, @@ -217,6 +81,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) }; sample.pid = fake_common_samples[k].pid; + sample.tid = fake_common_samples[k].pid; sample.ip = fake_common_samples[k].ip; if (perf_event__preprocess_sample(&event, machine, &al, &sample) < 0) @@ -240,6 +105,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) }; sample.pid = fake_samples[i][k].pid; + sample.tid = fake_samples[i][k].pid; sample.ip = fake_samples[i][k].ip; if (perf_event__preprocess_sample(&event, machine, &al, &sample) < 0) @@ -402,33 +268,6 @@ static int validate_link(struct hists *leader, struct hists *other) return __validate_link(leader, 0) || __validate_link(other, 1); } -static void print_hists(struct hists *hists) -{ - int i = 0; - struct rb_root *root; - struct rb_node *node; - - if (sort__need_collapse) - root = &hists->entries_collapsed; - else - root = hists->entries_in; - - pr_info("----- %s --------\n", __func__); - node = rb_first(root); - while (node) { - struct hist_entry *he; - - he = rb_entry(node, struct hist_entry, rb_node_in); - - pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n", - i, thread__comm_str(he->thread), he->ms.map->dso->short_name, - he->ms.sym->name, he->stat.period); - - i++; - node = rb_next(node); - } -} - int test__hists_link(void) { int err = -1; @@ -470,7 +309,7 @@ int test__hists_link(void) hists__collapse_resort(&evsel->hists, NULL); if (verbose > 2) - print_hists(&evsel->hists); + print_hists_in(&evsel->hists); } first = perf_evlist__first(evlist); @@ -493,6 +332,7 @@ int test__hists_link(void) out: /* tear down everything */ perf_evlist__delete(evlist); + reset_output_field(); machines__exit(&machines); return err; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c new file mode 100644 index 000000000000..a16850551797 --- /dev/null +++ b/tools/perf/tests/hists_output.c @@ -0,0 +1,618 @@ +#include "perf.h" +#include "util/debug.h" +#include "util/symbol.h" +#include "util/sort.h" +#include "util/evsel.h" +#include "util/evlist.h" +#include "util/machine.h" +#include "util/thread.h" +#include "util/parse-events.h" +#include "tests/tests.h" +#include "tests/hists_common.h" + +struct sample { + u32 cpu; + u32 pid; + u64 ip; + struct thread *thread; + struct map *map; + struct symbol *sym; +}; + +/* For the numbers, see hists_common.c */ +static struct sample fake_samples[] = { + /* perf [kernel] schedule() */ + { .cpu = 0, .pid = 100, .ip = 0xf0000 + 700, }, + /* perf [perf] main() */ + { .cpu = 1, .pid = 100, .ip = 0x40000 + 700, }, + /* perf [perf] cmd_record() */ + { .cpu = 1, .pid = 100, .ip = 0x40000 + 900, }, + /* perf [libc] malloc() */ + { .cpu = 1, .pid = 100, .ip = 0x50000 + 700, }, + /* perf [libc] free() */ + { .cpu = 2, .pid = 100, .ip = 0x50000 + 800, }, + /* perf [perf] main() */ + { .cpu = 2, .pid = 200, .ip = 0x40000 + 700, }, + /* perf [kernel] page_fault() */ + { .cpu = 2, .pid = 200, .ip = 0xf0000 + 800, }, + /* bash [bash] main() */ + { .cpu = 3, .pid = 300, .ip = 0x40000 + 700, }, + /* bash [bash] xmalloc() */ + { .cpu = 0, .pid = 300, .ip = 0x40000 + 800, }, + /* bash [kernel] page_fault() */ + { .cpu = 1, .pid = 300, .ip = 0xf0000 + 800, }, +}; + +static int add_hist_entries(struct hists *hists, struct machine *machine) +{ + struct addr_location al; + struct hist_entry *he; + struct perf_sample sample = { .period = 100, }; + size_t i; + + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { + const union perf_event event = { + .header = { + .misc = PERF_RECORD_MISC_USER, + }, + }; + + sample.cpu = fake_samples[i].cpu; + sample.pid = fake_samples[i].pid; + sample.tid = fake_samples[i].pid; + sample.ip = fake_samples[i].ip; + + if (perf_event__preprocess_sample(&event, machine, &al, + &sample) < 0) + goto out; + + he = __hists__add_entry(hists, &al, NULL, NULL, NULL, + sample.period, 1, 0); + if (he == NULL) + goto out; + + fake_samples[i].thread = al.thread; + fake_samples[i].map = al.map; + fake_samples[i].sym = al.sym; + } + + return TEST_OK; + +out: + pr_debug("Not enough memory for adding a hist entry\n"); + return TEST_FAIL; +} + +static void del_hist_entries(struct hists *hists) +{ + struct hist_entry *he; + struct rb_root *root_in; + struct rb_root *root_out; + struct rb_node *node; + + if (sort__need_collapse) + root_in = &hists->entries_collapsed; + else + root_in = hists->entries_in; + + root_out = &hists->entries; + + while (!RB_EMPTY_ROOT(root_out)) { + node = rb_first(root_out); + + he = rb_entry(node, struct hist_entry, rb_node); + rb_erase(node, root_out); + rb_erase(&he->rb_node_in, root_in); + hist_entry__free(he); + } +} + +typedef int (*test_fn_t)(struct perf_evsel *, struct machine *); + +#define COMM(he) (thread__comm_str(he->thread)) +#define DSO(he) (he->ms.map->dso->short_name) +#define SYM(he) (he->ms.sym->name) +#define CPU(he) (he->cpu) +#define PID(he) (he->thread->tid) + +/* default sort keys (no field) */ +static int test1(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + struct hist_entry *he; + struct rb_root *root; + struct rb_node *node; + + field_order = NULL; + sort_order = NULL; /* equivalent to sort_order = "comm,dso,sym" */ + + setup_sorting(); + + /* + * expected output: + * + * Overhead Command Shared Object Symbol + * ======== ======= ============= ============== + * 20.00% perf perf [.] main + * 10.00% bash [kernel] [k] page_fault + * 10.00% bash bash [.] main + * 10.00% bash bash [.] xmalloc + * 10.00% perf [kernel] [k] page_fault + * 10.00% perf [kernel] [k] schedule + * 10.00% perf libc [.] free + * 10.00% perf libc [.] malloc + * 10.00% perf perf [.] cmd_record + */ + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + if (verbose > 2) { + pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); + print_hists_out(hists); + } + + root = &evsel->hists.entries; + node = rb_first(root); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") && + !strcmp(SYM(he), "main") && he->stat.period == 200); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") && + !strcmp(SYM(he), "page_fault") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") && + !strcmp(SYM(he), "main") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") && + !strcmp(SYM(he), "xmalloc") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") && + !strcmp(SYM(he), "page_fault") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") && + !strcmp(SYM(he), "schedule") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") && + !strcmp(SYM(he), "free") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") && + !strcmp(SYM(he), "malloc") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") && + !strcmp(SYM(he), "cmd_record") && he->stat.period == 100); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +/* mixed fields and sort keys */ +static int test2(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + struct hist_entry *he; + struct rb_root *root; + struct rb_node *node; + + field_order = "overhead,cpu"; + sort_order = "pid"; + + setup_sorting(); + + /* + * expected output: + * + * Overhead CPU Command: Pid + * ======== === ============= + * 30.00% 1 perf : 100 + * 10.00% 0 perf : 100 + * 10.00% 2 perf : 100 + * 20.00% 2 perf : 200 + * 10.00% 0 bash : 300 + * 10.00% 1 bash : 300 + * 10.00% 3 bash : 300 + */ + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + if (verbose > 2) { + pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); + print_hists_out(hists); + } + + root = &evsel->hists.entries; + node = rb_first(root); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 1 && PID(he) == 100 && he->stat.period == 300); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 0 && PID(he) == 100 && he->stat.period == 100); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +/* fields only (no sort key) */ +static int test3(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + struct hist_entry *he; + struct rb_root *root; + struct rb_node *node; + + field_order = "comm,overhead,dso"; + sort_order = NULL; + + setup_sorting(); + + /* + * expected output: + * + * Command Overhead Shared Object + * ======= ======== ============= + * bash 20.00% bash + * bash 10.00% [kernel] + * perf 30.00% perf + * perf 20.00% [kernel] + * perf 20.00% libc + */ + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + if (verbose > 2) { + pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); + print_hists_out(hists); + } + + root = &evsel->hists.entries; + node = rb_first(root); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") && + he->stat.period == 200); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") && + he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") && + he->stat.period == 300); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") && + he->stat.period == 200); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") && + he->stat.period == 200); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +/* handle duplicate 'dso' field */ +static int test4(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + struct hist_entry *he; + struct rb_root *root; + struct rb_node *node; + + field_order = "dso,sym,comm,overhead,dso"; + sort_order = "sym"; + + setup_sorting(); + + /* + * expected output: + * + * Shared Object Symbol Command Overhead + * ============= ============== ======= ======== + * perf [.] cmd_record perf 10.00% + * libc [.] free perf 10.00% + * bash [.] main bash 10.00% + * perf [.] main perf 20.00% + * libc [.] malloc perf 10.00% + * [kernel] [k] page_fault bash 10.00% + * [kernel] [k] page_fault perf 10.00% + * [kernel] [k] schedule perf 10.00% + * bash [.] xmalloc bash 10.00% + */ + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + if (verbose > 2) { + pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); + print_hists_out(hists); + } + + root = &evsel->hists.entries; + node = rb_first(root); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "perf") && !strcmp(SYM(he), "cmd_record") && + !strcmp(COMM(he), "perf") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "libc") && !strcmp(SYM(he), "free") && + !strcmp(COMM(he), "perf") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "bash") && !strcmp(SYM(he), "main") && + !strcmp(COMM(he), "bash") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "perf") && !strcmp(SYM(he), "main") && + !strcmp(COMM(he), "perf") && he->stat.period == 200); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "libc") && !strcmp(SYM(he), "malloc") && + !strcmp(COMM(he), "perf") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "page_fault") && + !strcmp(COMM(he), "bash") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "page_fault") && + !strcmp(COMM(he), "perf") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "[kernel]") && !strcmp(SYM(he), "schedule") && + !strcmp(COMM(he), "perf") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + !strcmp(DSO(he), "bash") && !strcmp(SYM(he), "xmalloc") && + !strcmp(COMM(he), "bash") && he->stat.period == 100); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +/* full sort keys w/o overhead field */ +static int test5(struct perf_evsel *evsel, struct machine *machine) +{ + int err; + struct hists *hists = &evsel->hists; + struct hist_entry *he; + struct rb_root *root; + struct rb_node *node; + + field_order = "cpu,pid,comm,dso,sym"; + sort_order = "dso,pid"; + + setup_sorting(); + + /* + * expected output: + * + * CPU Command: Pid Command Shared Object Symbol + * === ============= ======= ============= ============== + * 0 perf: 100 perf [kernel] [k] schedule + * 2 perf: 200 perf [kernel] [k] page_fault + * 1 bash: 300 bash [kernel] [k] page_fault + * 0 bash: 300 bash bash [.] xmalloc + * 3 bash: 300 bash bash [.] main + * 1 perf: 100 perf libc [.] malloc + * 2 perf: 100 perf libc [.] free + * 1 perf: 100 perf perf [.] cmd_record + * 1 perf: 100 perf perf [.] main + * 2 perf: 200 perf perf [.] main + */ + err = add_hist_entries(hists, machine); + if (err < 0) + goto out; + + hists__collapse_resort(hists, NULL); + hists__output_resort(hists); + + if (verbose > 2) { + pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); + print_hists_out(hists); + } + + root = &evsel->hists.entries; + node = rb_first(root); + he = rb_entry(node, struct hist_entry, rb_node); + + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 0 && PID(he) == 100 && + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") && + !strcmp(SYM(he), "schedule") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 2 && PID(he) == 200 && + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "[kernel]") && + !strcmp(SYM(he), "page_fault") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 1 && PID(he) == 300 && + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "[kernel]") && + !strcmp(SYM(he), "page_fault") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 0 && PID(he) == 300 && + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") && + !strcmp(SYM(he), "xmalloc") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 3 && PID(he) == 300 && + !strcmp(COMM(he), "bash") && !strcmp(DSO(he), "bash") && + !strcmp(SYM(he), "main") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 1 && PID(he) == 100 && + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") && + !strcmp(SYM(he), "malloc") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 2 && PID(he) == 100 && + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "libc") && + !strcmp(SYM(he), "free") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 1 && PID(he) == 100 && + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") && + !strcmp(SYM(he), "cmd_record") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 1 && PID(he) == 100 && + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") && + !strcmp(SYM(he), "main") && he->stat.period == 100); + + node = rb_next(node); + he = rb_entry(node, struct hist_entry, rb_node); + TEST_ASSERT_VAL("Invalid hist entry", + CPU(he) == 2 && PID(he) == 200 && + !strcmp(COMM(he), "perf") && !strcmp(DSO(he), "perf") && + !strcmp(SYM(he), "main") && he->stat.period == 100); + +out: + del_hist_entries(hists); + reset_output_field(); + return err; +} + +int test__hists_output(void) +{ + int err = TEST_FAIL; + struct machines machines; + struct machine *machine; + struct perf_evsel *evsel; + struct perf_evlist *evlist = perf_evlist__new(); + size_t i; + test_fn_t testcases[] = { + test1, + test2, + test3, + test4, + test5, + }; + + TEST_ASSERT_VAL("No memory", evlist); + + err = parse_events(evlist, "cpu-clock"); + if (err) + goto out; + + machines__init(&machines); + + /* setup threads/dso/map/symbols also */ + machine = setup_fake_machine(&machines); + if (!machine) + goto out; + + if (verbose > 1) + machine__fprintf(machine, stderr); + + evsel = perf_evlist__first(evlist); + + for (i = 0; i < ARRAY_SIZE(testcases); i++) { + err = testcases[i](evsel, machine); + if (err < 0) + break; + } + +out: + /* tear down everything */ + perf_evlist__delete(evlist); + machines__exit(&machines); + + return err; +} diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 497957f269d8..7a5ab7b0b8f6 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -1,4 +1,4 @@ -#include <sys/types.h> +#include <linux/types.h> #include <unistd.h> #include <sys/prctl.h> diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 00544b8b644b..2f92d6e7ee00 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -27,6 +27,7 @@ make_no_ui := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 make_no_demangle := NO_DEMANGLE=1 make_no_libelf := NO_LIBELF=1 make_no_libunwind := NO_LIBUNWIND=1 +make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1 make_no_backtrace := NO_BACKTRACE=1 make_no_libnuma := NO_LIBNUMA=1 make_no_libaudit := NO_LIBAUDIT=1 @@ -35,8 +36,9 @@ make_tags := tags make_cscope := cscope make_help := help make_doc := doc -make_perf_o := perf.o -make_util_map_o := util/map.o +make_perf_o := perf.o +make_util_map_o := util/map.o +make_util_pmu_bison_o := util/pmu-bison.o make_install := install make_install_bin := install-bin make_install_doc := install-doc @@ -44,11 +46,13 @@ make_install_man := install-man make_install_html := install-html make_install_info := install-info make_install_pdf := install-pdf +make_static := LDFLAGS=-static # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 +make_minimal += NO_LIBDW_DWARF_UNWIND=1 # $(run) contains all available tests run := make_pure @@ -65,6 +69,7 @@ run += make_no_ui run += make_no_demangle run += make_no_libelf run += make_no_libunwind +run += make_no_libdw_dwarf_unwind run += make_no_backtrace run += make_no_libnuma run += make_no_libaudit @@ -73,6 +78,7 @@ run += make_help run += make_doc run += make_perf_o run += make_util_map_o +run += make_util_pmu_bison_o run += make_install run += make_install_bin # FIXME 'install-*' commented out till they're fixed @@ -82,6 +88,7 @@ run += make_install_bin # run += make_install_info # run += make_install_pdf run += make_minimal +run += make_static ifneq ($(call has,ctags),) run += make_tags @@ -113,8 +120,9 @@ test_make_doc_O := $(test_ok) test_make_python_perf_so := test -f $(PERF)/python/perf.so -test_make_perf_o := test -f $(PERF)/perf.o -test_make_util_map_o := test -f $(PERF)/util/map.o +test_make_perf_o := test -f $(PERF)/perf.o +test_make_util_map_o := test -f $(PERF)/util/map.o +test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o define test_dest_files for file in $(1); do \ @@ -167,13 +175,10 @@ test_make_install_info_O := $(test_ok) test_make_install_pdf := $(test_ok) test_make_install_pdf_O := $(test_ok) -# Kbuild tests only -#test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so -#test_make_perf_o_O := test -f $$TMP/tools/perf/perf.o -#test_make_util_map_o_O := test -f $$TMP/tools/perf/util/map.o - -test_make_perf_o_O := true -test_make_util_map_o_O := true +test_make_python_perf_so_O := test -f $$TMP_O/python/perf.so +test_make_perf_o_O := test -f $$TMP_O/perf.o +test_make_util_map_o_O := test -f $$TMP_O/util/map.o +test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o test_default = test -x $(PERF)/perf test = $(if $(test_$1),$(test_$1),$(test_default)) diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c new file mode 100644 index 000000000000..4a456fef66ca --- /dev/null +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -0,0 +1,233 @@ +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/mman.h> +#include <pthread.h> +#include <stdlib.h> +#include <stdio.h> +#include "debug.h" +#include "tests.h" +#include "machine.h" +#include "thread_map.h" +#include "symbol.h" +#include "thread.h" + +#define THREADS 4 + +static int go_away; + +struct thread_data { + pthread_t pt; + pid_t tid; + void *map; + int ready[2]; +}; + +static struct thread_data threads[THREADS]; + +static int thread_init(struct thread_data *td) +{ + void *map; + + map = mmap(NULL, page_size, + PROT_READ|PROT_WRITE|PROT_EXEC, + MAP_SHARED|MAP_ANONYMOUS, -1, 0); + + if (map == MAP_FAILED) { + perror("mmap failed"); + return -1; + } + + td->map = map; + td->tid = syscall(SYS_gettid); + + pr_debug("tid = %d, map = %p\n", td->tid, map); + return 0; +} + +static void *thread_fn(void *arg) +{ + struct thread_data *td = arg; + ssize_t ret; + int go; + + if (thread_init(td)) + return NULL; + + /* Signal thread_create thread is initialized. */ + ret = write(td->ready[1], &go, sizeof(int)); + if (ret != sizeof(int)) { + pr_err("failed to notify\n"); + return NULL; + } + + while (!go_away) { + /* Waiting for main thread to kill us. */ + usleep(100); + } + + munmap(td->map, page_size); + return NULL; +} + +static int thread_create(int i) +{ + struct thread_data *td = &threads[i]; + int err, go; + + if (pipe(td->ready)) + return -1; + + err = pthread_create(&td->pt, NULL, thread_fn, td); + if (!err) { + /* Wait for thread initialization. */ + ssize_t ret = read(td->ready[0], &go, sizeof(int)); + err = ret != sizeof(int); + } + + close(td->ready[0]); + close(td->ready[1]); + return err; +} + +static int threads_create(void) +{ + struct thread_data *td0 = &threads[0]; + int i, err = 0; + + go_away = 0; + + /* 0 is main thread */ + if (thread_init(td0)) + return -1; + + for (i = 1; !err && i < THREADS; i++) + err = thread_create(i); + + return err; +} + +static int threads_destroy(void) +{ + struct thread_data *td0 = &threads[0]; + int i, err = 0; + + /* cleanup the main thread */ + munmap(td0->map, page_size); + + go_away = 1; + + for (i = 1; !err && i < THREADS; i++) + err = pthread_join(threads[i].pt, NULL); + + return err; +} + +typedef int (*synth_cb)(struct machine *machine); + +static int synth_all(struct machine *machine) +{ + return perf_event__synthesize_threads(NULL, + perf_event__process, + machine, 0); +} + +static int synth_process(struct machine *machine) +{ + struct thread_map *map; + int err; + + map = thread_map__new_by_pid(getpid()); + + err = perf_event__synthesize_thread_map(NULL, map, + perf_event__process, + machine, 0); + + thread_map__delete(map); + return err; +} + +static int mmap_events(synth_cb synth) +{ + struct machines machines; + struct machine *machine; + int err, i; + + /* + * The threads_create will not return before all threads + * are spawned and all created memory map. + * + * They will loop until threads_destroy is called, so we + * can safely run synthesizing function. + */ + TEST_ASSERT_VAL("failed to create threads", !threads_create()); + + machines__init(&machines); + machine = &machines.host; + + dump_trace = verbose > 1 ? 1 : 0; + + err = synth(machine); + + dump_trace = 0; + + TEST_ASSERT_VAL("failed to destroy threads", !threads_destroy()); + TEST_ASSERT_VAL("failed to synthesize maps", !err); + + /* + * All data is synthesized, try to find map for each + * thread object. + */ + for (i = 0; i < THREADS; i++) { + struct thread_data *td = &threads[i]; + struct addr_location al; + struct thread *thread; + + thread = machine__findnew_thread(machine, getpid(), td->tid); + + pr_debug("looking for map %p\n", td->map); + + thread__find_addr_map(thread, machine, + PERF_RECORD_MISC_USER, MAP__FUNCTION, + (unsigned long) (td->map + 1), &al); + + if (!al.map) { + pr_debug("failed, couldn't find map\n"); + err = -1; + break; + } + + pr_debug("map %p, addr %" PRIx64 "\n", al.map, al.map->start); + } + + machine__delete_threads(machine); + machines__exit(&machines); + return err; +} + +/* + * This test creates 'THREADS' number of threads (including + * main thread) and each thread creates memory map. + * + * When threads are created, we synthesize them with both + * (separate tests): + * perf_event__synthesize_thread_map (process based) + * perf_event__synthesize_threads (global) + * + * We test we can find all memory maps via: + * thread__find_addr_map + * + * by using all thread objects. + */ +int test__mmap_thread_lookup(void) +{ + /* perf_event__synthesize_threads synthesize */ + TEST_ASSERT_VAL("failed with sythesizing all", + !mmap_events(synth_all)); + + /* perf_event__synthesize_thread_map synthesize */ + TEST_ASSERT_VAL("failed with sythesizing process", + !mmap_events(synth_process)); + + return 0; +} diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 4db0ae617d70..deba66955f8c 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -2,7 +2,7 @@ #include "parse-events.h" #include "evsel.h" #include "evlist.h" -#include "fs.h" +#include <api/fs/fs.h> #include <api/fs/debugfs.h> #include "tests.h" #include <linux/hw_breakpoint.h> @@ -1174,188 +1174,240 @@ static int test__all_tracepoints(struct perf_evlist *evlist) struct evlist_test { const char *name; __u32 type; + const int id; int (*check)(struct perf_evlist *evlist); }; static struct evlist_test test__events[] = { - [0] = { + { .name = "syscalls:sys_enter_open", .check = test__checkevent_tracepoint, + .id = 0, }, - [1] = { + { .name = "syscalls:*", .check = test__checkevent_tracepoint_multi, + .id = 1, }, - [2] = { + { .name = "r1a", .check = test__checkevent_raw, + .id = 2, }, - [3] = { + { .name = "1:1", .check = test__checkevent_numeric, + .id = 3, }, - [4] = { + { .name = "instructions", .check = test__checkevent_symbolic_name, + .id = 4, }, - [5] = { + { .name = "cycles/period=100000,config2/", .check = test__checkevent_symbolic_name_config, + .id = 5, }, - [6] = { + { .name = "faults", .check = test__checkevent_symbolic_alias, + .id = 6, }, - [7] = { + { .name = "L1-dcache-load-miss", .check = test__checkevent_genhw, + .id = 7, }, - [8] = { + { .name = "mem:0", .check = test__checkevent_breakpoint, + .id = 8, }, - [9] = { + { .name = "mem:0:x", .check = test__checkevent_breakpoint_x, + .id = 9, }, - [10] = { + { .name = "mem:0:r", .check = test__checkevent_breakpoint_r, + .id = 10, }, - [11] = { + { .name = "mem:0:w", .check = test__checkevent_breakpoint_w, + .id = 11, }, - [12] = { + { .name = "syscalls:sys_enter_open:k", .check = test__checkevent_tracepoint_modifier, + .id = 12, }, - [13] = { + { .name = "syscalls:*:u", .check = test__checkevent_tracepoint_multi_modifier, + .id = 13, }, - [14] = { + { .name = "r1a:kp", .check = test__checkevent_raw_modifier, + .id = 14, }, - [15] = { + { .name = "1:1:hp", .check = test__checkevent_numeric_modifier, + .id = 15, }, - [16] = { + { .name = "instructions:h", .check = test__checkevent_symbolic_name_modifier, + .id = 16, }, - [17] = { + { .name = "faults:u", .check = test__checkevent_symbolic_alias_modifier, + .id = 17, }, - [18] = { + { .name = "L1-dcache-load-miss:kp", .check = test__checkevent_genhw_modifier, + .id = 18, }, - [19] = { + { .name = "mem:0:u", .check = test__checkevent_breakpoint_modifier, + .id = 19, }, - [20] = { + { .name = "mem:0:x:k", .check = test__checkevent_breakpoint_x_modifier, + .id = 20, }, - [21] = { + { .name = "mem:0:r:hp", .check = test__checkevent_breakpoint_r_modifier, + .id = 21, }, - [22] = { + { .name = "mem:0:w:up", .check = test__checkevent_breakpoint_w_modifier, + .id = 22, }, - [23] = { + { .name = "r1,syscalls:sys_enter_open:k,1:1:hp", .check = test__checkevent_list, + .id = 23, }, - [24] = { + { .name = "instructions:G", .check = test__checkevent_exclude_host_modifier, + .id = 24, }, - [25] = { + { .name = "instructions:H", .check = test__checkevent_exclude_guest_modifier, + .id = 25, }, - [26] = { + { .name = "mem:0:rw", .check = test__checkevent_breakpoint_rw, + .id = 26, }, - [27] = { + { .name = "mem:0:rw:kp", .check = test__checkevent_breakpoint_rw_modifier, + .id = 27, }, - [28] = { + { .name = "{instructions:k,cycles:upp}", .check = test__group1, + .id = 28, }, - [29] = { + { .name = "{faults:k,cache-references}:u,cycles:k", .check = test__group2, + .id = 29, }, - [30] = { + { .name = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u", .check = test__group3, + .id = 30, }, - [31] = { + { .name = "{cycles:u,instructions:kp}:p", .check = test__group4, + .id = 31, }, - [32] = { + { .name = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles", .check = test__group5, + .id = 32, }, - [33] = { + { .name = "*:*", .check = test__all_tracepoints, + .id = 33, }, - [34] = { + { .name = "{cycles,cache-misses:G}:H", .check = test__group_gh1, + .id = 34, }, - [35] = { + { .name = "{cycles,cache-misses:H}:G", .check = test__group_gh2, + .id = 35, }, - [36] = { + { .name = "{cycles:G,cache-misses:H}:u", .check = test__group_gh3, + .id = 36, }, - [37] = { + { .name = "{cycles:G,cache-misses:H}:uG", .check = test__group_gh4, + .id = 37, }, - [38] = { + { .name = "{cycles,cache-misses,branch-misses}:S", .check = test__leader_sample1, + .id = 38, }, - [39] = { + { .name = "{instructions,branch-misses}:Su", .check = test__leader_sample2, + .id = 39, }, - [40] = { + { .name = "instructions:uDp", .check = test__checkevent_pinned_modifier, + .id = 40, }, - [41] = { + { .name = "{cycles,cache-misses,branch-misses}:D", .check = test__pinned_group, + .id = 41, + }, +#if defined(__s390x__) + { + .name = "kvm-s390:kvm_s390_create_vm", + .check = test__checkevent_tracepoint, + .id = 100, }, +#endif }; static struct evlist_test test__events_pmu[] = { - [0] = { + { .name = "cpu/config=10,config1,config2=3,period=1000/u", .check = test__checkevent_pmu, + .id = 0, }, - [1] = { + { .name = "cpu/config=1,name=krava/u,cpu/config=2/u", .check = test__checkevent_pmu_name, + .id = 1, }, }; @@ -1402,7 +1454,7 @@ static int test_events(struct evlist_test *events, unsigned cnt) for (i = 0; i < cnt; i++) { struct evlist_test *e = &events[i]; - pr_debug("running test %d '%s'\n", i, e->name); + pr_debug("running test %d '%s'\n", e->id, e->name); ret1 = test_event(e); if (ret1) ret2 = ret1; diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index e117b6c6a248..905019f9b740 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -1,4 +1,4 @@ -#include <sys/types.h> +#include <linux/types.h> #include <stddef.h> #include "tests.h" diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 47146d388dbf..3b7cd4d32dcb 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -1,7 +1,6 @@ #include <stdio.h> -#include <sys/types.h> #include <unistd.h> -#include <inttypes.h> +#include <linux/types.h> #include <sys/prctl.h> #include "parse-events.h" diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c index 46649c25fa5e..e59143fd9e71 100644 --- a/tools/perf/tests/rdpmc.c +++ b/tools/perf/tests/rdpmc.c @@ -2,7 +2,7 @@ #include <stdlib.h> #include <signal.h> #include <sys/mman.h> -#include "types.h" +#include <linux/types.h> #include "perf.h" #include "debug.h" #include "tests.h" diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 1b677202638d..7ae8d17db3d9 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -1,5 +1,5 @@ #include <stdbool.h> -#include <inttypes.h> +#include <linux/types.h> #include "util.h" #include "event.h" @@ -22,8 +22,8 @@ } while (0) static bool samples_same(const struct perf_sample *s1, - const struct perf_sample *s2, u64 type, u64 regs_user, - u64 read_format) + const struct perf_sample *s2, + u64 type, u64 read_format) { size_t i; @@ -95,8 +95,9 @@ static bool samples_same(const struct perf_sample *s1, } if (type & PERF_SAMPLE_REGS_USER) { - size_t sz = hweight_long(regs_user) * sizeof(u64); + size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64); + COMP(user_regs.mask); COMP(user_regs.abi); if (s1->user_regs.abi && (!s1->user_regs.regs || !s2->user_regs.regs || @@ -174,6 +175,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) .branch_stack = &branch_stack.branch_stack, .user_regs = { .abi = PERF_SAMPLE_REGS_ABI_64, + .mask = sample_regs_user, .regs = user_regs, }, .user_stack = { @@ -201,8 +203,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) sample.read.one.id = 99; } - sz = perf_event__sample_event_size(&sample, sample_type, - sample_regs_user, read_format); + sz = perf_event__sample_event_size(&sample, sample_type, read_format); bufsz = sz + 4096; /* Add a bit for overrun checking */ event = malloc(bufsz); if (!event) { @@ -215,8 +216,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) event->header.misc = 0; event->header.size = sz; - err = perf_event__synthesize_sample(event, sample_type, - sample_regs_user, read_format, + err = perf_event__synthesize_sample(event, sample_type, read_format, &sample, false); if (err) { pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", @@ -244,8 +244,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) goto out_free; } - if (!samples_same(&sample, &sample_out, sample_type, - sample_regs_user, read_format)) { + if (!samples_same(&sample, &sample_out, sample_type, read_format)) { pr_debug("parsing failed for sample_type %#"PRIx64"\n", sample_type); goto out_free; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index e0ac713857ba..d76c0e2e6635 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -40,5 +40,18 @@ int test__code_reading(void); int test__sample_parsing(void); int test__keep_tracking(void); int test__parse_no_sample_id_all(void); +int test__dwarf_unwind(void); +int test__hists_filter(void); +int test__mmap_thread_lookup(void); +int test__thread_mg_share(void); +int test__hists_output(void); +#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread); +#endif +#endif #endif /* TESTS_H */ diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c new file mode 100644 index 000000000000..2b2e0dbe114f --- /dev/null +++ b/tools/perf/tests/thread-mg-share.c @@ -0,0 +1,90 @@ +#include "tests.h" +#include "machine.h" +#include "thread.h" +#include "map.h" + +int test__thread_mg_share(void) +{ + struct machines machines; + struct machine *machine; + + /* thread group */ + struct thread *leader; + struct thread *t1, *t2, *t3; + struct map_groups *mg; + + /* other process */ + struct thread *other, *other_leader; + struct map_groups *other_mg; + + /* + * This test create 2 processes abstractions (struct thread) + * with several threads and checks they properly share and + * maintain map groups info (struct map_groups). + * + * thread group (pid: 0, tids: 0, 1, 2, 3) + * other group (pid: 4, tids: 4, 5) + */ + + machines__init(&machines); + machine = &machines.host; + + /* create process with 4 threads */ + leader = machine__findnew_thread(machine, 0, 0); + t1 = machine__findnew_thread(machine, 0, 1); + t2 = machine__findnew_thread(machine, 0, 2); + t3 = machine__findnew_thread(machine, 0, 3); + + /* and create 1 separated process, without thread leader */ + other = machine__findnew_thread(machine, 4, 5); + + TEST_ASSERT_VAL("failed to create threads", + leader && t1 && t2 && t3 && other); + + mg = leader->mg; + TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4); + + /* test the map groups pointer is shared */ + TEST_ASSERT_VAL("map groups don't match", mg == t1->mg); + TEST_ASSERT_VAL("map groups don't match", mg == t2->mg); + TEST_ASSERT_VAL("map groups don't match", mg == t3->mg); + + /* + * Verify the other leader was created by previous call. + * It should have shared map groups with no change in + * refcnt. + */ + other_leader = machine__find_thread(machine, 4, 4); + TEST_ASSERT_VAL("failed to find other leader", other_leader); + + other_mg = other->mg; + TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2); + + TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg); + + /* release thread group */ + thread__delete(leader); + TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3); + + thread__delete(t1); + TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2); + + thread__delete(t2); + TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1); + + thread__delete(t3); + + /* release other group */ + thread__delete(other_leader); + TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1); + + thread__delete(other); + + /* + * Cannot call machine__delete_threads(machine) now, + * because we've already released all the threads. + */ + + machines__exit(&machines); + return 0; +} diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 118cca29dd26..03d4d6295f10 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -1,9 +1,7 @@ #ifndef _PERF_UI_BROWSER_H_ #define _PERF_UI_BROWSER_H_ 1 -#include <stdbool.h> -#include <sys/types.h> -#include "../types.h" +#include <linux/types.h> #define HE_COLORSET_TOP 50 #define HE_COLORSET_MEDIUM 51 diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index b720b92eba6e..1c331b934ffc 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -26,13 +26,36 @@ struct hist_browser { int print_seq; bool show_dso; float min_pcnt; - u64 nr_pcnt_entries; + u64 nr_non_filtered_entries; + u64 nr_callchain_rows; }; extern void hist_browser__init_hpp(void); static int hists__browser_title(struct hists *hists, char *bf, size_t size, const char *ev_name); +static void hist_browser__update_nr_entries(struct hist_browser *hb); + +static struct rb_node *hists__filter_entries(struct rb_node *nd, + struct hists *hists, + float min_pcnt); + +static bool hist_browser__has_filter(struct hist_browser *hb) +{ + return hists__has_filter(hb->hists) || hb->min_pcnt; +} + +static u32 hist_browser__nr_entries(struct hist_browser *hb) +{ + u32 nr_entries; + + if (hist_browser__has_filter(hb)) + nr_entries = hb->nr_non_filtered_entries; + else + nr_entries = hb->hists->nr_entries; + + return nr_entries + hb->nr_callchain_rows; +} static void hist_browser__refresh_dimensions(struct hist_browser *browser) { @@ -43,7 +66,14 @@ static void hist_browser__refresh_dimensions(struct hist_browser *browser) static void hist_browser__reset(struct hist_browser *browser) { - browser->b.nr_entries = browser->hists->nr_entries; + /* + * The hists__remove_entry_filter() already folds non-filtered + * entries so we can assume it has 0 callchain rows. + */ + browser->nr_callchain_rows = 0; + + hist_browser__update_nr_entries(browser); + browser->b.nr_entries = hist_browser__nr_entries(browser); hist_browser__refresh_dimensions(browser); ui_browser__reset_index(&browser->b); } @@ -198,14 +228,16 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser) struct hist_entry *he = browser->he_selection; hist_entry__init_have_children(he); - browser->hists->nr_entries -= he->nr_rows; + browser->b.nr_entries -= he->nr_rows; + browser->nr_callchain_rows -= he->nr_rows; if (he->ms.unfolded) he->nr_rows = callchain__count_rows(&he->sorted_chain); else he->nr_rows = 0; - browser->hists->nr_entries += he->nr_rows; - browser->b.nr_entries = browser->hists->nr_entries; + + browser->b.nr_entries += he->nr_rows; + browser->nr_callchain_rows += he->nr_rows; return true; } @@ -280,23 +312,27 @@ static void hist_entry__set_folding(struct hist_entry *he, bool unfold) he->nr_rows = 0; } -static void hists__set_folding(struct hists *hists, bool unfold) +static void +__hist_browser__set_folding(struct hist_browser *browser, bool unfold) { struct rb_node *nd; + struct hists *hists = browser->hists; - hists->nr_entries = 0; - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + for (nd = rb_first(&hists->entries); + (nd = hists__filter_entries(nd, hists, browser->min_pcnt)) != NULL; + nd = rb_next(nd)) { struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); hist_entry__set_folding(he, unfold); - hists->nr_entries += 1 + he->nr_rows; + browser->nr_callchain_rows += he->nr_rows; } } static void hist_browser__set_folding(struct hist_browser *browser, bool unfold) { - hists__set_folding(browser->hists, unfold); - browser->b.nr_entries = browser->hists->nr_entries; + browser->nr_callchain_rows = 0; + __hist_browser__set_folding(browser, unfold); + + browser->b.nr_entries = hist_browser__nr_entries(browser); /* Go to the start, we may be way after valid entries after a collapse */ ui_browser__reset_index(&browser->b); } @@ -310,8 +346,6 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser) "Or reduce the sampling frequency."); } -static void hist_browser__update_pcnt_entries(struct hist_browser *hb); - static int hist_browser__run(struct hist_browser *browser, const char *ev_name, struct hist_browser_timer *hbt) { @@ -320,9 +354,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, int delay_secs = hbt ? hbt->refresh : 0; browser->b.entries = &browser->hists->entries; - browser->b.nr_entries = browser->hists->nr_entries; - if (browser->min_pcnt) - browser->b.nr_entries = browser->nr_pcnt_entries; + browser->b.nr_entries = hist_browser__nr_entries(browser); hist_browser__refresh_dimensions(browser); hists__browser_title(browser->hists, title, sizeof(title), ev_name); @@ -339,13 +371,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name, u64 nr_entries; hbt->timer(hbt->arg); - if (browser->min_pcnt) { - hist_browser__update_pcnt_entries(browser); - nr_entries = browser->nr_pcnt_entries; - } else { - nr_entries = browser->hists->nr_entries; - } + if (hist_browser__has_filter(browser)) + hist_browser__update_nr_entries(browser); + nr_entries = hist_browser__nr_entries(browser); ui_browser__update_nr_entries(&browser->b, nr_entries); if (browser->hists->stats.nr_lost_warned != @@ -587,99 +616,27 @@ struct hpp_arg { bool current_entry; }; -static int __hpp__color_callchain(struct hpp_arg *arg) +static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...) { - if (!symbol_conf.use_callchain) - return 0; - - slsmg_printf("%c ", arg->folded_sign); - return 2; -} - -static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, - u64 (*get_field)(struct hist_entry *), - int (*callchain_cb)(struct hpp_arg *)) -{ - int ret = 0; - double percent = 0.0; - struct hists *hists = he->hists; struct hpp_arg *arg = hpp->ptr; + int ret; + va_list args; + double percent; - if (hists->stats.total_period) - percent = 100.0 * get_field(he) / hists->stats.total_period; + va_start(args, fmt); + percent = va_arg(args, double); + va_end(args); ui_browser__set_percent_color(arg->b, percent, arg->current_entry); - if (callchain_cb) - ret += callchain_cb(arg); - - ret += scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); + ret = scnprintf(hpp->buf, hpp->size, fmt, percent); slsmg_printf("%s", hpp->buf); - if (symbol_conf.event_group) { - int prev_idx, idx_delta; - struct perf_evsel *evsel = hists_to_evsel(hists); - struct hist_entry *pair; - int nr_members = evsel->nr_members; - - if (nr_members <= 1) - goto out; - - prev_idx = perf_evsel__group_idx(evsel); - - list_for_each_entry(pair, &he->pairs.head, pairs.node) { - u64 period = get_field(pair); - u64 total = pair->hists->stats.total_period; - - if (!total) - continue; - - evsel = hists_to_evsel(pair->hists); - idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; - - while (idx_delta--) { - /* - * zero-fill group members in the middle which - * have no sample - */ - ui_browser__set_percent_color(arg->b, 0.0, - arg->current_entry); - ret += scnprintf(hpp->buf, hpp->size, - " %6.2f%%", 0.0); - slsmg_printf("%s", hpp->buf); - } - - percent = 100.0 * period / total; - ui_browser__set_percent_color(arg->b, percent, - arg->current_entry); - ret += scnprintf(hpp->buf, hpp->size, - " %6.2f%%", percent); - slsmg_printf("%s", hpp->buf); - - prev_idx = perf_evsel__group_idx(evsel); - } - - idx_delta = nr_members - prev_idx - 1; - - while (idx_delta--) { - /* - * zero-fill group members at last which have no sample - */ - ui_browser__set_percent_color(arg->b, 0.0, - arg->current_entry); - ret += scnprintf(hpp->buf, hpp->size, - " %6.2f%%", 0.0); - slsmg_printf("%s", hpp->buf); - } - } -out: - if (!arg->current_entry || !arg->b->navkeypressed) - ui_browser__set_color(arg->b, HE_COLORSET_NORMAL); - + advance_hpp(hpp, ret); return ret; } -#define __HPP_COLOR_PERCENT_FN(_type, _field, _cb) \ +#define __HPP_COLOR_PERCENT_FN(_type, _field) \ static u64 __hpp_get_##_field(struct hist_entry *he) \ { \ return he->stat._field; \ @@ -690,21 +647,20 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\ struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb); \ + return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%", \ + __hpp__slsmg_color_printf, true); \ } -__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__color_callchain) -__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, NULL) -__HPP_COLOR_PERCENT_FN(overhead_us, period_us, NULL) -__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, NULL) -__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL) +__HPP_COLOR_PERCENT_FN(overhead, period) +__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys) +__HPP_COLOR_PERCENT_FN(overhead_us, period_us) +__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys) +__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us) #undef __HPP_COLOR_PERCENT_FN void hist_browser__init_hpp(void) { - perf_hpp__init(); - perf_hpp__format[PERF_HPP__OVERHEAD].color = hist_browser__hpp_color_overhead; perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = @@ -742,7 +698,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, if (row_offset == 0) { struct hpp_arg arg = { - .b = &browser->b, + .b = &browser->b, .folded_sign = folded_sign, .current_entry = current_entry, }; @@ -755,11 +711,27 @@ static int hist_browser__show_entry(struct hist_browser *browser, ui_browser__gotorc(&browser->b, row, 0); perf_hpp__for_each_format(fmt) { - if (!first) { + if (perf_hpp__should_skip(fmt)) + continue; + + if (current_entry && browser->b.navkeypressed) { + ui_browser__set_color(&browser->b, + HE_COLORSET_SELECTED); + } else { + ui_browser__set_color(&browser->b, + HE_COLORSET_NORMAL); + } + + if (first) { + if (symbol_conf.use_callchain) { + slsmg_printf("%c ", folded_sign); + width -= 2; + } + first = false; + } else { slsmg_printf(" "); width -= 2; } - first = false; if (fmt->color) { width -= fmt->color(fmt, &hpp, entry); @@ -773,8 +745,8 @@ static int hist_browser__show_entry(struct hist_browser *browser, if (!browser->b.navkeypressed) width += 1; - hist_entry__sort_snprintf(entry, s, sizeof(s), browser->hists); - slsmg_write_nstring(s, width); + slsmg_write_nstring("", width); + ++row; ++printed; } else @@ -811,12 +783,15 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) for (nd = browser->top; nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - float percent = h->stat.period * 100.0 / - hb->hists->stats.total_period; + u64 total = hists__total_period(h->hists); + float percent = 0.0; if (h->filtered) continue; + if (total) + percent = h->stat.period * 100.0 / total; + if (percent < hb->min_pcnt) continue; @@ -834,13 +809,13 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd, { while (nd != NULL) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - float percent = h->stat.period * 100.0 / - hists->stats.total_period; + u64 total = hists__total_period(hists); + float percent = 0.0; - if (percent < min_pcnt) - return NULL; + if (total) + percent = h->stat.period * 100.0 / total; - if (!h->filtered) + if (!h->filtered && percent >= min_pcnt) return nd; nd = rb_next(nd); @@ -855,8 +830,11 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd, { while (nd != NULL) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - float percent = h->stat.period * 100.0 / - hists->stats.total_period; + u64 total = hists__total_period(hists); + float percent = 0.0; + + if (total) + percent = h->stat.period * 100.0 / total; if (!h->filtered && percent >= min_pcnt) return nd; @@ -1108,27 +1086,35 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, struct hist_entry *he, FILE *fp) { char s[8192]; - double percent; int printed = 0; char folded_sign = ' '; + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + }; + struct perf_hpp_fmt *fmt; + bool first = true; + int ret; if (symbol_conf.use_callchain) folded_sign = hist_entry__folded(he); - hist_entry__sort_snprintf(he, s, sizeof(s), browser->hists); - percent = (he->stat.period * 100.0) / browser->hists->stats.total_period; - if (symbol_conf.use_callchain) printed += fprintf(fp, "%c ", folded_sign); - printed += fprintf(fp, " %5.2f%%", percent); - - if (symbol_conf.show_nr_samples) - printed += fprintf(fp, " %11u", he->stat.nr_events); + perf_hpp__for_each_format(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; - if (symbol_conf.show_total_period) - printed += fprintf(fp, " %12" PRIu64, he->stat.period); + if (!first) { + ret = scnprintf(hpp.buf, hpp.size, " "); + advance_hpp(&hpp, ret); + } else + first = false; + ret = fmt->entry(fmt, &hpp, he); + advance_hpp(&hpp, ret); + } printed += fprintf(fp, "%s\n", rtrim(s)); if (folded_sign == '-') @@ -1231,6 +1217,11 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, char buf[512]; size_t buflen = sizeof(buf); + if (symbol_conf.filter_relative) { + nr_samples = hists->stats.nr_non_filtered_samples; + nr_events = hists->stats.total_non_filtered_period; + } + if (perf_evsel__is_group_event(evsel)) { struct perf_evsel *pos; @@ -1238,8 +1229,13 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, ev_name = buf; for_each_group_member(pos, evsel) { - nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; - nr_events += pos->hists.stats.total_period; + if (symbol_conf.filter_relative) { + nr_samples += pos->hists.stats.nr_non_filtered_samples; + nr_events += pos->hists.stats.total_non_filtered_period; + } else { + nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos->hists.stats.total_period; + } } } @@ -1366,18 +1362,23 @@ close_file_and_continue: return ret; } -static void hist_browser__update_pcnt_entries(struct hist_browser *hb) +static void hist_browser__update_nr_entries(struct hist_browser *hb) { u64 nr_entries = 0; struct rb_node *nd = rb_first(&hb->hists->entries); - while (nd) { + if (hb->min_pcnt == 0) { + hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries; + return; + } + + while ((nd = hists__filter_entries(nd, hb->hists, + hb->min_pcnt)) != NULL) { nr_entries++; - nd = hists__filter_entries(rb_next(nd), hb->hists, - hb->min_pcnt); + nd = rb_next(nd); } - hb->nr_pcnt_entries = nr_entries; + hb->nr_non_filtered_entries = nr_entries; } static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, @@ -1412,6 +1413,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "C Collapse all callchains\n" \ "d Zoom into current DSO\n" \ "E Expand all callchains\n" \ + "F Toggle percentage of filtered entries\n" \ /* help messages are sorted by lexical order of the hotkey */ const char report_help[] = HIST_BROWSER_HELP_COMMON @@ -1433,7 +1435,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (min_pcnt) { browser->min_pcnt = min_pcnt; - hist_browser__update_pcnt_entries(browser); + hist_browser__update_nr_entries(browser); } fstack = pstack__new(2); @@ -1517,6 +1519,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (env->arch) tui__header_window(env); continue; + case 'F': + symbol_conf.filter_relative ^= 1; + continue; case K_F1: case 'h': case '?': diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 5b95c44f3435..9d90683914d4 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -8,16 +8,24 @@ #define MAX_COLUMNS 32 -static int __percent_color_snprintf(char *buf, size_t size, double percent) +static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...) { int ret = 0; + va_list args; + double percent; const char *markup; + char *buf = hpp->buf; + size_t size = hpp->size; + + va_start(args, fmt); + percent = va_arg(args, double); + va_end(args); markup = perf_gtk__get_percent_color(percent); if (markup) ret += scnprintf(buf, size, markup); - ret += scnprintf(buf + ret, size - ret, " %6.2f%%", percent); + ret += scnprintf(buf + ret, size - ret, fmt, percent); if (markup) ret += scnprintf(buf + ret, size - ret, "</span>"); @@ -25,66 +33,6 @@ static int __percent_color_snprintf(char *buf, size_t size, double percent) return ret; } - -static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, - u64 (*get_field)(struct hist_entry *)) -{ - int ret; - double percent = 0.0; - struct hists *hists = he->hists; - struct perf_evsel *evsel = hists_to_evsel(hists); - - if (hists->stats.total_period) - percent = 100.0 * get_field(he) / hists->stats.total_period; - - ret = __percent_color_snprintf(hpp->buf, hpp->size, percent); - - if (perf_evsel__is_group_event(evsel)) { - int prev_idx, idx_delta; - struct hist_entry *pair; - int nr_members = evsel->nr_members; - - prev_idx = perf_evsel__group_idx(evsel); - - list_for_each_entry(pair, &he->pairs.head, pairs.node) { - u64 period = get_field(pair); - u64 total = pair->hists->stats.total_period; - - evsel = hists_to_evsel(pair->hists); - idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; - - while (idx_delta--) { - /* - * zero-fill group members in the middle which - * have no sample - */ - ret += __percent_color_snprintf(hpp->buf + ret, - hpp->size - ret, - 0.0); - } - - percent = 100.0 * period / total; - ret += __percent_color_snprintf(hpp->buf + ret, - hpp->size - ret, - percent); - - prev_idx = perf_evsel__group_idx(evsel); - } - - idx_delta = nr_members - prev_idx - 1; - - while (idx_delta--) { - /* - * zero-fill group members at last which have no sample - */ - ret += __percent_color_snprintf(hpp->buf + ret, - hpp->size - ret, - 0.0); - } - } - return ret; -} - #define __HPP_COLOR_PERCENT_FN(_type, _field) \ static u64 he_get_##_field(struct hist_entry *he) \ { \ @@ -95,7 +43,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ - return __hpp__color_fmt(hpp, he, he_get_##_field); \ + return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ + __percent_color_snprintf, true); \ } __HPP_COLOR_PERCENT_FN(overhead, period) @@ -109,8 +58,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us) void perf_gtk__init_hpp(void) { - perf_hpp__init(); - perf_hpp__format[PERF_HPP__OVERHEAD].color = perf_gtk__hpp_color_overhead; perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = @@ -204,7 +151,6 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, struct perf_hpp_fmt *fmt; GType col_types[MAX_COLUMNS]; GtkCellRenderer *renderer; - struct sort_entry *se; GtkTreeStore *store; struct rb_node *nd; GtkWidget *view; @@ -216,7 +162,6 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, struct perf_hpp hpp = { .buf = s, .size = sizeof(s), - .ptr = hists_to_evsel(hists), }; nr_cols = 0; @@ -224,16 +169,6 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, perf_hpp__for_each_format(fmt) col_types[nr_cols++] = G_TYPE_STRING; - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - if (se == &sort_sym) - sym_col = nr_cols; - - col_types[nr_cols++] = G_TYPE_STRING; - } - store = gtk_tree_store_newv(nr_cols, col_types); view = gtk_tree_view_new(); @@ -243,7 +178,10 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { - fmt->header(fmt, &hpp); + if (perf_hpp__should_skip(fmt)) + continue; + + fmt->header(fmt, &hpp, hists_to_evsel(hists)); gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), -1, ltrim(s), @@ -251,16 +189,6 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx++, NULL); } - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), - -1, se->se_header, - renderer, "text", - col_idx++, NULL); - } - for (col_idx = 0; col_idx < nr_cols; col_idx++) { GtkTreeViewColumn *column; @@ -280,12 +208,15 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); GtkTreeIter iter; - float percent = h->stat.period * 100.0 / - hists->stats.total_period; + u64 total = hists__total_period(h->hists); + float percent = 0.0; if (h->filtered) continue; + if (total) + percent = h->stat.period * 100.0 / total; + if (percent < min_pcnt) continue; @@ -294,6 +225,9 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; + if (fmt->color) fmt->color(fmt, &hpp, h); else @@ -302,23 +236,9 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, gtk_tree_store_set(store, &iter, col_idx++, s, -1); } - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - se->se_snprintf(h, s, ARRAY_SIZE(s), - hists__col_len(hists, se->se_width_idx)); - - gtk_tree_store_set(store, &iter, col_idx++, s, -1); - } - if (symbol_conf.use_callchain && sort__has_sym) { - u64 total; - if (callchain_param.mode == CHAIN_GRAPH_REL) total = h->stat.period; - else - total = hists->stats.total_period; perf_gtk__add_callchain(&h->sorted_chain, store, &iter, sym_col, total); diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 78f4c92e9b73..4484f5bd1b14 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -8,27 +8,33 @@ /* hist period print (hpp) functions */ -typedef int (*hpp_snprint_fn)(char *buf, size_t size, const char *fmt, ...); - -static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, - u64 (*get_field)(struct hist_entry *), - const char *fmt, hpp_snprint_fn print_fn, - bool fmt_percent) +#define hpp__call_print_fn(hpp, fn, fmt, ...) \ +({ \ + int __ret = fn(hpp, fmt, ##__VA_ARGS__); \ + advance_hpp(hpp, __ret); \ + __ret; \ +}) + +int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, const char *fmt, + hpp_snprint_fn print_fn, bool fmt_percent) { int ret; struct hists *hists = he->hists; struct perf_evsel *evsel = hists_to_evsel(hists); + char *buf = hpp->buf; + size_t size = hpp->size; if (fmt_percent) { double percent = 0.0; + u64 total = hists__total_period(hists); - if (hists->stats.total_period) - percent = 100.0 * get_field(he) / - hists->stats.total_period; + if (total) + percent = 100.0 * get_field(he) / total; - ret = print_fn(hpp->buf, hpp->size, fmt, percent); + ret = hpp__call_print_fn(hpp, print_fn, fmt, percent); } else - ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he)); + ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he)); if (perf_evsel__is_group_event(evsel)) { int prev_idx, idx_delta; @@ -39,7 +45,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, list_for_each_entry(pair, &he->pairs.head, pairs.node) { u64 period = get_field(pair); - u64 total = pair->hists->stats.total_period; + u64 total = hists__total_period(pair->hists); if (!total) continue; @@ -52,16 +58,22 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, * zero-fill group members in the middle which * have no sample */ - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, 0); + if (fmt_percent) { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0.0); + } else { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0ULL); + } } - if (fmt_percent) - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, 100.0 * period / total); - else - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, period); + if (fmt_percent) { + ret += hpp__call_print_fn(hpp, print_fn, fmt, + 100.0 * period / total); + } else { + ret += hpp__call_print_fn(hpp, print_fn, fmt, + period); + } prev_idx = perf_evsel__group_idx(evsel); } @@ -72,41 +84,136 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, /* * zero-fill group members at last which have no sample */ - ret += print_fn(hpp->buf + ret, hpp->size - ret, - fmt, 0); + if (fmt_percent) { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0.0); + } else { + ret += hpp__call_print_fn(hpp, print_fn, + fmt, 0ULL); + } } } + + /* + * Restore original buf and size as it's where caller expects + * the result will be saved. + */ + hpp->buf = buf; + hpp->size = size; + + return ret; +} + +static int field_cmp(u64 field_a, u64 field_b) +{ + if (field_a > field_b) + return 1; + if (field_a < field_b) + return -1; + return 0; +} + +static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, + hpp_field_fn get_field) +{ + s64 ret; + int i, nr_members; + struct perf_evsel *evsel; + struct hist_entry *pair; + u64 *fields_a, *fields_b; + + ret = field_cmp(get_field(a), get_field(b)); + if (ret || !symbol_conf.event_group) + return ret; + + evsel = hists_to_evsel(a->hists); + if (!perf_evsel__is_group_event(evsel)) + return ret; + + nr_members = evsel->nr_members; + fields_a = calloc(sizeof(*fields_a), nr_members); + fields_b = calloc(sizeof(*fields_b), nr_members); + + if (!fields_a || !fields_b) + goto out; + + list_for_each_entry(pair, &a->pairs.head, pairs.node) { + evsel = hists_to_evsel(pair->hists); + fields_a[perf_evsel__group_idx(evsel)] = get_field(pair); + } + + list_for_each_entry(pair, &b->pairs.head, pairs.node) { + evsel = hists_to_evsel(pair->hists); + fields_b[perf_evsel__group_idx(evsel)] = get_field(pair); + } + + for (i = 1; i < nr_members; i++) { + ret = field_cmp(fields_a[i], fields_b[i]); + if (ret) + break; + } + +out: + free(fields_a); + free(fields_b); + return ret; } #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ - struct perf_hpp *hpp) \ + struct perf_hpp *hpp, \ + struct perf_evsel *evsel) \ { \ int len = _min_width; \ \ - if (symbol_conf.event_group) { \ - struct perf_evsel *evsel = hpp->ptr; \ - \ + if (symbol_conf.event_group) \ len = max(len, evsel->nr_members * _unit_width); \ - } \ + \ return scnprintf(hpp->buf, hpp->size, "%*s", len, _str); \ } #define __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ - struct perf_hpp *hpp __maybe_unused) \ + struct perf_hpp *hpp __maybe_unused, \ + struct perf_evsel *evsel) \ { \ int len = _min_width; \ \ - if (symbol_conf.event_group) { \ - struct perf_evsel *evsel = hpp->ptr; \ - \ + if (symbol_conf.event_group) \ len = max(len, evsel->nr_members * _unit_width); \ - } \ + \ return len; \ } +static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...) +{ + va_list args; + ssize_t ssize = hpp->size; + double percent; + int ret; + + va_start(args, fmt); + percent = va_arg(args, double); + ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent); + va_end(args); + + return (ret >= ssize) ? (ssize - 1) : ret; +} + +static int hpp_entry_scnprintf(struct perf_hpp *hpp, const char *fmt, ...) +{ + va_list args; + ssize_t ssize = hpp->size; + int ret; + + va_start(args, fmt); + ret = vsnprintf(hpp->buf, hpp->size, fmt, args); + va_end(args); + + return (ret >= ssize) ? (ssize - 1) : ret; +} + #define __HPP_COLOR_PERCENT_FN(_type, _field) \ static u64 he_get_##_field(struct hist_entry *he) \ { \ @@ -117,7 +224,7 @@ static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ - percent_color_snprintf, true); \ + hpp_color_scnprintf, true); \ } #define __HPP_ENTRY_PERCENT_FN(_type, _field) \ @@ -126,7 +233,13 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ { \ const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ - scnprintf, true); \ + hpp_entry_scnprintf, true); \ +} + +#define __HPP_SORT_FN(_type, _field) \ +static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +{ \ + return __hpp__sort(a, b, he_get_##_field); \ } #define __HPP_ENTRY_RAW_FN(_type, _field) \ @@ -139,19 +252,29 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64; \ - return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \ + return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, \ + hpp_entry_scnprintf, false); \ } +#define __HPP_SORT_RAW_FN(_type, _field) \ +static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +{ \ + return __hpp__sort(a, b, he_get_raw_##_field); \ +} + + #define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width) \ __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ __HPP_COLOR_PERCENT_FN(_type, _field) \ -__HPP_ENTRY_PERCENT_FN(_type, _field) +__HPP_ENTRY_PERCENT_FN(_type, _field) \ +__HPP_SORT_FN(_type, _field) #define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width) \ __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ -__HPP_ENTRY_RAW_FN(_type, _field) +__HPP_ENTRY_RAW_FN(_type, _field) \ +__HPP_SORT_RAW_FN(_type, _field) HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8) @@ -163,19 +286,31 @@ HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8) HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12) HPP_RAW_FNS(period, "Period", period, 12, 12) +static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused, + struct hist_entry *b __maybe_unused) +{ + return 0; +} + #define HPP__COLOR_PRINT_FNS(_name) \ { \ .header = hpp__header_ ## _name, \ .width = hpp__width_ ## _name, \ .color = hpp__color_ ## _name, \ - .entry = hpp__entry_ ## _name \ + .entry = hpp__entry_ ## _name, \ + .cmp = hpp__nop_cmp, \ + .collapse = hpp__nop_cmp, \ + .sort = hpp__sort_ ## _name, \ } #define HPP__PRINT_FNS(_name) \ { \ .header = hpp__header_ ## _name, \ .width = hpp__width_ ## _name, \ - .entry = hpp__entry_ ## _name \ + .entry = hpp__entry_ ## _name, \ + .cmp = hpp__nop_cmp, \ + .collapse = hpp__nop_cmp, \ + .sort = hpp__sort_ ## _name, \ } struct perf_hpp_fmt perf_hpp__format[] = { @@ -189,6 +324,7 @@ struct perf_hpp_fmt perf_hpp__format[] = { }; LIST_HEAD(perf_hpp__list); +LIST_HEAD(perf_hpp__sort_list); #undef HPP__COLOR_PRINT_FNS @@ -206,6 +342,25 @@ LIST_HEAD(perf_hpp__list); void perf_hpp__init(void) { + struct list_head *list; + int i; + + for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { + struct perf_hpp_fmt *fmt = &perf_hpp__format[i]; + + INIT_LIST_HEAD(&fmt->list); + + /* sort_list may be linked by setup_sorting() */ + if (fmt->sort_list.next == NULL) + INIT_LIST_HEAD(&fmt->sort_list); + } + + /* + * If user specified field order, no need to setup default fields. + */ + if (field_order) + return; + perf_hpp__column_enable(PERF_HPP__OVERHEAD); if (symbol_conf.show_cpu_utilization) { @@ -223,6 +378,11 @@ void perf_hpp__init(void) if (symbol_conf.show_total_period) perf_hpp__column_enable(PERF_HPP__PERIOD); + + /* prepend overhead field for backward compatiblity. */ + list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list; + if (list_empty(list)) + list_add(list, &perf_hpp__sort_list); } void perf_hpp__column_register(struct perf_hpp_fmt *format) @@ -230,29 +390,90 @@ void perf_hpp__column_register(struct perf_hpp_fmt *format) list_add_tail(&format->list, &perf_hpp__list); } +void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) +{ + list_add_tail(&format->sort_list, &perf_hpp__sort_list); +} + void perf_hpp__column_enable(unsigned col) { BUG_ON(col >= PERF_HPP__MAX_INDEX); perf_hpp__column_register(&perf_hpp__format[col]); } -int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size, - struct hists *hists) +void perf_hpp__setup_output_field(void) { - const char *sep = symbol_conf.field_sep; - struct sort_entry *se; - int ret = 0; + struct perf_hpp_fmt *fmt; - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) + /* append sort keys to output field */ + perf_hpp__for_each_sort_list(fmt) { + if (!list_empty(&fmt->list)) continue; - ret += scnprintf(s + ret, size - ret, "%s", sep ?: " "); - ret += se->se_snprintf(he, s + ret, size - ret, - hists__col_len(hists, se->se_width_idx)); + /* + * sort entry fields are dynamically created, + * so they can share a same sort key even though + * the list is empty. + */ + if (perf_hpp__is_sort_entry(fmt)) { + struct perf_hpp_fmt *pos; + + perf_hpp__for_each_format(pos) { + if (perf_hpp__same_sort_entry(pos, fmt)) + goto next; + } + } + + perf_hpp__column_register(fmt); +next: + continue; } +} - return ret; +void perf_hpp__append_sort_keys(void) +{ + struct perf_hpp_fmt *fmt; + + /* append output fields to sort keys */ + perf_hpp__for_each_format(fmt) { + if (!list_empty(&fmt->sort_list)) + continue; + + /* + * sort entry fields are dynamically created, + * so they can share a same sort key even though + * the list is empty. + */ + if (perf_hpp__is_sort_entry(fmt)) { + struct perf_hpp_fmt *pos; + + perf_hpp__for_each_sort_list(pos) { + if (perf_hpp__same_sort_entry(pos, fmt)) + goto next; + } + } + + perf_hpp__register_sort_field(fmt); +next: + continue; + } +} + +void perf_hpp__reset_output_field(void) +{ + struct perf_hpp_fmt *fmt, *tmp; + + /* reset output fields */ + perf_hpp__for_each_format_safe(fmt, tmp) { + list_del_init(&fmt->list); + list_del_init(&fmt->sort_list); + } + + /* reset sort keys */ + perf_hpp__for_each_sort_list_safe(fmt, tmp) { + list_del_init(&fmt->list); + list_del_init(&fmt->sort_list); + } } /* @@ -261,24 +482,23 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size, unsigned int hists__sort_list_width(struct hists *hists) { struct perf_hpp_fmt *fmt; - struct sort_entry *se; - int i = 0, ret = 0; - struct perf_hpp dummy_hpp = { - .ptr = hists_to_evsel(hists), - }; + int ret = 0; + bool first = true; + struct perf_hpp dummy_hpp; perf_hpp__for_each_format(fmt) { - if (i) + if (perf_hpp__should_skip(fmt)) + continue; + + if (first) + first = false; + else ret += 2; - ret += fmt->width(fmt, &dummy_hpp); + ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists)); } - list_for_each_entry(se, &hist_entry__sort_list, list) - if (!se->elide) - ret += 2 + hists__col_len(hists, se->se_width_idx); - - if (verbose) /* Addr + origin */ + if (verbose && sort__has_sym) /* Addr + origin */ ret += 3 + BITS_PER_LONG / 4; return ret; diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h index 29ec8efffefb..f34f89eb607c 100644 --- a/tools/perf/ui/progress.h +++ b/tools/perf/ui/progress.h @@ -1,7 +1,7 @@ #ifndef _PERF_UI_PROGRESS_H_ #define _PERF_UI_PROGRESS_H_ 1 -#include <../types.h> +#include <linux/types.h> void ui_progress__finish(void); diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 5df5140a9f29..ba51fa8a1176 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -86,8 +86,6 @@ void setup_browser(bool fallback_to_pager) use_browser = 0; if (fallback_to_pager) setup_pager(); - - perf_hpp__init(); break; } } diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 831fbb77d1ff..9f57991025a9 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -183,7 +183,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, * the symbol. No need to print it otherwise it appears as * displayed twice. */ - if (!i++ && sort__first_dimension == SORT_SYM) + if (!i++ && field_order == NULL && + sort_order && !prefixcmp(sort_order, "sym")) continue; if (!printed) { ret += callchain__fprintf_left_margin(fp, left_margin); @@ -296,24 +297,24 @@ static size_t hist_entry__callchain_fprintf(struct hist_entry *he, int left_margin = 0; u64 total_period = hists->stats.total_period; - if (sort__first_dimension == SORT_COMM) { - struct sort_entry *se = list_first_entry(&hist_entry__sort_list, - typeof(*se), list); - left_margin = hists__col_len(hists, se->se_width_idx); - left_margin -= thread__comm_len(he->thread); - } + if (field_order == NULL && (sort_order == NULL || + !prefixcmp(sort_order, "comm"))) { + struct perf_hpp_fmt *fmt; - return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); -} + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; -static inline void advance_hpp(struct perf_hpp *hpp, int inc) -{ - hpp->buf += inc; - hpp->size -= inc; + /* must be 'comm' sort entry */ + left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists)); + left_margin -= thread__comm_len(he->thread); + break; + } + } + return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); } -static int hist_entry__period_snprintf(struct perf_hpp *hpp, - struct hist_entry *he) +static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) { const char *sep = symbol_conf.field_sep; struct perf_hpp_fmt *fmt; @@ -325,6 +326,9 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp, return 0; perf_hpp__for_each_format(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; + /* * If there's no field_sep, we still need * to display initial ' '. @@ -359,8 +363,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, if (size == 0 || size > bfsz) size = hpp.size = bfsz; - ret = hist_entry__period_snprintf(&hpp, he); - hist_entry__sort_snprintf(he, bf + ret, size - ret, hists); + hist_entry__snprintf(he, &hpp); ret = fprintf(fp, "%s\n", bf); @@ -374,18 +377,15 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp) { struct perf_hpp_fmt *fmt; - struct sort_entry *se; struct rb_node *nd; size_t ret = 0; unsigned int width; const char *sep = symbol_conf.field_sep; - const char *col_width = symbol_conf.col_width_list_str; int nr_rows = 0; char bf[96]; struct perf_hpp dummy_hpp = { .buf = bf, .size = sizeof(bf), - .ptr = hists_to_evsel(hists), }; bool first = true; size_t linesz; @@ -393,43 +393,28 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, init_rem_hits(); + + perf_hpp__for_each_format(fmt) + perf_hpp__reset_width(fmt, hists); + if (!show_header) goto print_entries; fprintf(fp, "# "); perf_hpp__for_each_format(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; + if (!first) fprintf(fp, "%s", sep ?: " "); else first = false; - fmt->header(fmt, &dummy_hpp); + fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); fprintf(fp, "%s", bf); } - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - if (sep) { - fprintf(fp, "%c%s", *sep, se->se_header); - continue; - } - width = strlen(se->se_header); - if (symbol_conf.col_width_list_str) { - if (col_width) { - hists__set_col_len(hists, se->se_width_idx, - atoi(col_width)); - col_width = strchr(col_width, ','); - if (col_width) - ++col_width; - } - } - if (!hists__new_col_len(hists, se->se_width_idx, width)) - width = hists__col_len(hists, se->se_width_idx); - fprintf(fp, " %*s", width, se->se_header); - } - fprintf(fp, "\n"); if (max_rows && ++nr_rows >= max_rows) goto out; @@ -444,26 +429,15 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, perf_hpp__for_each_format(fmt) { unsigned int i; + if (perf_hpp__should_skip(fmt)) + continue; + if (!first) fprintf(fp, "%s", sep ?: " "); else first = false; - width = fmt->width(fmt, &dummy_hpp); - for (i = 0; i < width; i++) - fprintf(fp, "."); - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - unsigned int i; - - if (se->elide) - continue; - - fprintf(fp, " "); - width = hists__col_len(hists, se->se_width_idx); - if (width == 0) - width = strlen(se->se_header); + width = fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists)); for (i = 0; i < width; i++) fprintf(fp, "."); } @@ -502,7 +476,7 @@ print_entries: break; if (h->ms.map == NULL && verbose > 1) { - __map_groups__fprintf_maps(&h->thread->mg, + __map_groups__fprintf_maps(h->thread->mg, MAP__FUNCTION, verbose, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 3aa555ff9d89..809b4c50beae 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1236,6 +1236,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, struct dso *dso = map->dso; char *filename; const char *d_filename; + const char *evsel_name = perf_evsel__name(evsel); struct annotation *notes = symbol__annotation(sym); struct disasm_line *pos, *queue = NULL; u64 start = map__rip_2objdump(map, sym->start); @@ -1243,7 +1244,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int more = 0; u64 len; int width = 8; - int namelen; + int namelen, evsel_name_len, graph_dotted_len; filename = strdup(dso->long_name); if (!filename) @@ -1256,14 +1257,17 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, len = symbol__size(sym); namelen = strlen(d_filename); + evsel_name_len = strlen(evsel_name); if (perf_evsel__is_group_event(evsel)) width *= evsel->nr_members; - printf(" %-*.*s| Source code & Disassembly of %s\n", - width, width, "Percent", d_filename); - printf("-%-*.*s-------------------------------------\n", - width+namelen, width+namelen, graph_dotted_line); + printf(" %-*.*s| Source code & Disassembly of %s for %s\n", + width, width, "Percent", d_filename, evsel_name); + + graph_dotted_len = width + namelen + evsel_name_len; + printf("-%-*.*s-----------------------------------------\n", + graph_dotted_len, graph_dotted_len, graph_dotted_line); if (verbose) symbol__annotate_hits(sym, evsel); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 56ad4f5287de..112d6e268150 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -3,7 +3,7 @@ #include <stdbool.h> #include <stdint.h> -#include "types.h" +#include <linux/types.h> #include "symbol.h" #include "hist.h" #include "sort.h" diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 6baabe63182b..a904a4cfe7d3 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -25,7 +25,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread = machine__findnew_thread(machine, sample->pid, - sample->pid); + sample->tid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 845ef865eced..ae392561470b 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -4,7 +4,7 @@ #define BUILD_ID_SIZE 20 #include "tool.h" -#include "types.h" +#include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8d9db454f1a9..9a42382b3921 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -25,6 +25,84 @@ __thread struct callchain_cursor callchain_cursor; +int +parse_callchain_report_opt(const char *arg) +{ + char *tok, *tok2; + char *endptr; + + symbol_conf.use_callchain = true; + + if (!arg) + return 0; + + tok = strtok((char *)arg, ","); + if (!tok) + return -1; + + /* get the output mode */ + if (!strncmp(tok, "graph", strlen(arg))) { + callchain_param.mode = CHAIN_GRAPH_ABS; + + } else if (!strncmp(tok, "flat", strlen(arg))) { + callchain_param.mode = CHAIN_FLAT; + } else if (!strncmp(tok, "fractal", strlen(arg))) { + callchain_param.mode = CHAIN_GRAPH_REL; + } else if (!strncmp(tok, "none", strlen(arg))) { + callchain_param.mode = CHAIN_NONE; + symbol_conf.use_callchain = false; + return 0; + } else { + return -1; + } + + /* get the min percentage */ + tok = strtok(NULL, ","); + if (!tok) + goto setup; + + callchain_param.min_percent = strtod(tok, &endptr); + if (tok == endptr) + return -1; + + /* get the print limit */ + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + + if (tok2[0] != 'c') { + callchain_param.print_limit = strtoul(tok2, &endptr, 0); + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + } + + /* get the call chain order */ + if (!strncmp(tok2, "caller", strlen("caller"))) + callchain_param.order = ORDER_CALLER; + else if (!strncmp(tok2, "callee", strlen("callee"))) + callchain_param.order = ORDER_CALLEE; + else + return -1; + + /* Get the sort key */ + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + if (!strncmp(tok2, "function", strlen("function"))) + callchain_param.key = CCKEY_FUNCTION; + else if (!strncmp(tok2, "address", strlen("address"))) + callchain_param.key = CCKEY_ADDRESS; + else + return -1; +setup: + if (callchain_register_param(&callchain_param) < 0) { + pr_err("Can't register callchain params\n"); + return -1; + } + return 0; +} + static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, enum chain_mode mode) diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 8ad97e9b119f..bde2b0cc24cf 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -7,6 +7,13 @@ #include "event.h" #include "symbol.h" +enum perf_call_graph_mode { + CALLCHAIN_NONE, + CALLCHAIN_FP, + CALLCHAIN_DWARF, + CALLCHAIN_MAX +}; + enum chain_mode { CHAIN_NONE, CHAIN_FLAT, @@ -157,4 +164,5 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); extern const char record_callchain_help[]; +int parse_callchain_report_opt(const char *arg); #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 3e0fdd369ccb..24519e14ac56 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -11,6 +11,7 @@ #include "util.h" #include "cache.h" #include "exec_cmd.h" +#include "util/hist.h" /* perf_hist_config */ #define MAXNAME (256) @@ -355,6 +356,9 @@ int perf_default_config(const char *var, const char *value, if (!prefixcmp(var, "core.")) return perf_default_core_config(var, value); + if (!prefixcmp(var, "hist.")) + return perf_hist_config(var, value); + /* Add other config variables here. */ return 0; } diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index a9b48c42e81e..c4e55b71010c 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,5 +1,5 @@ #include "util.h" -#include "fs.h" +#include <api/fs/fs.h> #include "../perf.h" #include "cpumap.h" #include <assert.h> @@ -317,3 +317,163 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep) { return cpu_map__build_map(cpus, corep, cpu_map__get_core); } + +/* setup simple routines to easily access node numbers given a cpu number */ +static int get_max_num(char *path, int *max) +{ + size_t num; + char *buf; + int err = 0; + + if (filename__read_str(path, &buf, &num)) + return -1; + + buf[num] = '\0'; + + /* start on the right, to find highest node num */ + while (--num) { + if ((buf[num] == ',') || (buf[num] == '-')) { + num++; + break; + } + } + if (sscanf(&buf[num], "%d", max) < 1) { + err = -1; + goto out; + } + + /* convert from 0-based to 1-based */ + (*max)++; + +out: + free(buf); + return err; +} + +/* Determine highest possible cpu in the system for sparse allocation */ +static void set_max_cpu_num(void) +{ + const char *mnt; + char path[PATH_MAX]; + int ret = -1; + + /* set up default */ + max_cpu_num = 4096; + + mnt = sysfs__mountpoint(); + if (!mnt) + goto out; + + /* get the highest possible cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_cpu_num); + +out: + if (ret) + pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num); +} + +/* Determine highest possible node in the system for sparse allocation */ +static void set_max_node_num(void) +{ + const char *mnt; + char path[PATH_MAX]; + int ret = -1; + + /* set up default */ + max_node_num = 8; + + mnt = sysfs__mountpoint(); + if (!mnt) + goto out; + + /* get the highest possible cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_node_num); + +out: + if (ret) + pr_err("Failed to read max nodes, using default of %d\n", max_node_num); +} + +static int init_cpunode_map(void) +{ + int i; + + set_max_cpu_num(); + set_max_node_num(); + + cpunode_map = calloc(max_cpu_num, sizeof(int)); + if (!cpunode_map) { + pr_err("%s: calloc failed\n", __func__); + return -1; + } + + for (i = 0; i < max_cpu_num; i++) + cpunode_map[i] = -1; + + return 0; +} + +int cpu__setup_cpunode_map(void) +{ + struct dirent *dent1, *dent2; + DIR *dir1, *dir2; + unsigned int cpu, mem; + char buf[PATH_MAX]; + char path[PATH_MAX]; + const char *mnt; + int n; + + /* initialize globals */ + if (init_cpunode_map()) + return -1; + + mnt = sysfs__mountpoint(); + if (!mnt) + return 0; + + n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt); + if (n == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + return -1; + } + + dir1 = opendir(path); + if (!dir1) + return 0; + + /* walk tree and setup map */ + while ((dent1 = readdir(dir1)) != NULL) { + if (dent1->d_type != DT_DIR || sscanf(dent1->d_name, "node%u", &mem) < 1) + continue; + + n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name); + if (n == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + continue; + } + + dir2 = opendir(buf); + if (!dir2) + continue; + while ((dent2 = readdir(dir2)) != NULL) { + if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1) + continue; + cpunode_map[cpu] = mem; + } + closedir(dir2); + } + closedir(dir1); + return 0; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index b123bb9d6f55..61a654849002 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -4,6 +4,9 @@ #include <stdio.h> #include <stdbool.h> +#include "perf.h" +#include "util/debug.h" + struct cpu_map { int nr; int map[]; @@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map) return map ? map->map[0] == -1 : true; } +int max_cpu_num; +int max_node_num; +int *cpunode_map; + +int cpu__setup_cpunode_map(void); + +static inline int cpu__max_node(void) +{ + if (unlikely(!max_node_num)) + pr_debug("cpu_map not initialized\n"); + + return max_node_num; +} + +static inline int cpu__max_cpu(void) +{ + if (unlikely(!max_cpu_num)) + pr_debug("cpu_map not initialized\n"); + + return max_cpu_num; +} + +static inline int cpu__get_node(int cpu) +{ + if (unlikely(cpunode_map == NULL)) { + pr_debug("cpu_map not initialized\n"); + return -1; + } + + return cpunode_map[cpu]; +} + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 1fbcd8bdc11b..55de44ecebef 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -86,10 +86,17 @@ static int open_file_read(struct perf_data_file *file) static int open_file_write(struct perf_data_file *file) { + int fd; + if (check_backup(file)) return -1; - return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); + fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); + + if (fd < 0) + pr_err("failed to open %s : %s\n", file->path, strerror(errno)); + + return fd; } static int open_file(struct perf_data_file *file) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 4045d086d9d9..64453d63b971 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -45,8 +45,8 @@ int dso__read_binary_type_filename(const struct dso *dso, debuglink--; if (*debuglink == '/') debuglink++; - filename__read_debuglink(dso->long_name, debuglink, - size - (debuglink - filename)); + ret = filename__read_debuglink(dso->long_name, debuglink, + size - (debuglink - filename)); } break; case DSO_BINARY_TYPE__BUILD_ID_CACHE: diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index cd7d6f078cdd..38efe95a7fdd 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -4,7 +4,7 @@ #include <linux/types.h> #include <linux/rbtree.h> #include <stdbool.h> -#include "types.h" +#include <linux/types.h> #include "map.h" #include "build-id.h" @@ -102,6 +102,16 @@ struct dso { char name[0]; }; +/* dso__for_each_symbol - iterate over the symbols of given type + * + * @dso: the 'struct dso *' in which symbols itereated + * @pos: the 'struct symbol *' to use as a loop cursor + * @n: the 'struct rb_node *' to use as a temporary storage + * @type: the 'enum map_type' type of symbols + */ +#define dso__for_each_symbol(dso, pos, n, type) \ + symbols__for_each_entry(&(dso)->symbols[(type)], pos, n) + static inline void dso__set_loaded(struct dso *dso, enum map_type type) { dso->loaded |= (1 << type); diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 7defd77105d0..cc66c4049e09 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -747,14 +747,17 @@ struct __find_variable_param { static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) { struct __find_variable_param *fvp = data; + Dwarf_Attribute attr; int tag; tag = dwarf_tag(die_mem); if ((tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) && - die_compare_name(die_mem, fvp->name)) + die_compare_name(die_mem, fvp->name) && + /* Does the DIE have location information or external instance? */ + (dwarf_attr(die_mem, DW_AT_external, &attr) || + dwarf_attr(die_mem, DW_AT_location, &attr))) return DIE_FIND_CB_END; - if (dwarf_haspc(die_mem, fvp->addr)) return DIE_FIND_CB_CONTINUE; else diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index b0f3ca850e9e..65795b835b39 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include "event.h" #include "debug.h" +#include "hist.h" #include "machine.h" #include "sort.h" #include "string.h" @@ -94,14 +95,10 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len) static pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, - int full, perf_event__handler_t process, struct machine *machine) { - char filename[PATH_MAX]; size_t size; - DIR *tasks; - struct dirent dirent, *next; pid_t tgid; memset(&event->comm, 0, sizeof(event->comm)); @@ -124,55 +121,35 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool, event->comm.header.size = (sizeof(event->comm) - (sizeof(event->comm.comm) - size) + machine->id_hdr_size); - if (!full) { - event->comm.tid = pid; + event->comm.tid = pid; - if (process(tool, event, &synth_sample, machine) != 0) - return -1; - - goto out; - } - - if (machine__is_default_guest(machine)) - return 0; - - snprintf(filename, sizeof(filename), "%s/proc/%d/task", - machine->root_dir, pid); - - tasks = opendir(filename); - if (tasks == NULL) { - pr_debug("couldn't open %s\n", filename); - return 0; - } + if (process(tool, event, &synth_sample, machine) != 0) + return -1; - while (!readdir_r(tasks, &dirent, &next) && next) { - char *end; - pid = strtol(dirent.d_name, &end, 10); - if (*end) - continue; +out: + return tgid; +} - /* already have tgid; jut want to update the comm */ - (void) perf_event__get_comm_tgid(pid, event->comm.comm, - sizeof(event->comm.comm)); +static int perf_event__synthesize_fork(struct perf_tool *tool, + union perf_event *event, pid_t pid, + pid_t tgid, perf_event__handler_t process, + struct machine *machine) +{ + memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size); - size = strlen(event->comm.comm) + 1; - size = PERF_ALIGN(size, sizeof(u64)); - memset(event->comm.comm + size, 0, machine->id_hdr_size); - event->comm.header.size = (sizeof(event->comm) - - (sizeof(event->comm.comm) - size) + - machine->id_hdr_size); + /* this is really a clone event but we use fork to synthesize it */ + event->fork.ppid = tgid; + event->fork.ptid = tgid; + event->fork.pid = tgid; + event->fork.tid = pid; + event->fork.header.type = PERF_RECORD_FORK; - event->comm.tid = pid; + event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); - if (process(tool, event, &synth_sample, machine) != 0) { - tgid = -1; - break; - } - } + if (process(tool, event, &synth_sample, machine) != 0) + return -1; - closedir(tasks); -out: - return tgid; + return 0; } int perf_event__synthesize_mmap_events(struct perf_tool *tool, @@ -324,17 +301,71 @@ int perf_event__synthesize_modules(struct perf_tool *tool, static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *mmap_event, + union perf_event *fork_event, pid_t pid, int full, perf_event__handler_t process, struct perf_tool *tool, struct machine *machine, bool mmap_data) { - pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full, + char filename[PATH_MAX]; + DIR *tasks; + struct dirent dirent, *next; + pid_t tgid; + + /* special case: only send one comm event using passed in pid */ + if (!full) { + tgid = perf_event__synthesize_comm(tool, comm_event, pid, + process, machine); + + if (tgid == -1) + return -1; + + return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + } + + if (machine__is_default_guest(machine)) + return 0; + + snprintf(filename, sizeof(filename), "%s/proc/%d/task", + machine->root_dir, pid); + + tasks = opendir(filename); + if (tasks == NULL) { + pr_debug("couldn't open %s\n", filename); + return 0; + } + + while (!readdir_r(tasks, &dirent, &next) && next) { + char *end; + int rc = 0; + pid_t _pid; + + _pid = strtol(dirent.d_name, &end, 10); + if (*end) + continue; + + tgid = perf_event__synthesize_comm(tool, comm_event, _pid, + process, machine); + if (tgid == -1) + return -1; + + if (_pid == pid) { + /* process the parent's maps too */ + rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data); + } else { + /* only fork the tid's map, to save time */ + rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid, process, machine); - if (tgid == -1) - return -1; - return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data); + } + + if (rc) + return rc; + } + + closedir(tasks); + return 0; } int perf_event__synthesize_thread_map(struct perf_tool *tool, @@ -343,7 +374,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, struct machine *machine, bool mmap_data) { - union perf_event *comm_event, *mmap_event; + union perf_event *comm_event, *mmap_event, *fork_event; int err = -1, thread, j; comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); @@ -354,9 +385,14 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, if (mmap_event == NULL) goto out_free_comm; + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; + err = 0; for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, + fork_event, threads->map[thread], 0, process, tool, machine, mmap_data)) { @@ -382,6 +418,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, /* if not, generate events for it */ if (need_leader && __event__synthesize_thread(comm_event, mmap_event, + fork_event, comm_event->comm.pid, 0, process, tool, machine, mmap_data)) { @@ -390,6 +427,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, } } } + free(fork_event); +out_free_mmap: free(mmap_event); out_free_comm: free(comm_event); @@ -404,9 +443,12 @@ int perf_event__synthesize_threads(struct perf_tool *tool, DIR *proc; char proc_path[PATH_MAX]; struct dirent dirent, *next; - union perf_event *comm_event, *mmap_event; + union perf_event *comm_event, *mmap_event, *fork_event; int err = -1; + if (machine__is_default_guest(machine)) + return 0; + comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); if (comm_event == NULL) goto out; @@ -415,14 +457,15 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (mmap_event == NULL) goto out_free_comm; - if (machine__is_default_guest(machine)) - return 0; + fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size); + if (fork_event == NULL) + goto out_free_mmap; snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); proc = opendir(proc_path); if (proc == NULL) - goto out_free_mmap; + goto out_free_fork; while (!readdir_r(proc, &dirent, &next) && next) { char *end; @@ -434,12 +477,14 @@ int perf_event__synthesize_threads(struct perf_tool *tool, * We may race with exiting thread, so don't stop just because * one thread couldn't be synthesized. */ - __event__synthesize_thread(comm_event, mmap_event, pid, 1, - process, tool, machine, mmap_data); + __event__synthesize_thread(comm_event, mmap_event, fork_event, pid, + 1, process, tool, machine, mmap_data); } err = 0; closedir(proc); +out_free_fork: + free(fork_event); out_free_mmap: free(mmap_event); out_free_comm: @@ -654,14 +699,14 @@ void thread__find_addr_map(struct thread *thread, enum map_type type, u64 addr, struct addr_location *al) { - struct map_groups *mg = &thread->mg; + struct map_groups *mg = thread->mg; bool load_map = false; al->machine = machine; al->thread = thread; al->addr = addr; al->cpumode = cpumode; - al->filtered = false; + al->filtered = 0; if (machine == NULL) { al->map = NULL; @@ -687,11 +732,11 @@ void thread__find_addr_map(struct thread *thread, if ((cpumode == PERF_RECORD_MISC_GUEST_USER || cpumode == PERF_RECORD_MISC_GUEST_KERNEL) && !perf_guest) - al->filtered = true; + al->filtered |= (1 << HIST_FILTER__GUEST); if ((cpumode == PERF_RECORD_MISC_USER || cpumode == PERF_RECORD_MISC_KERNEL) && !perf_host) - al->filtered = true; + al->filtered |= (1 << HIST_FILTER__HOST); return; } @@ -743,14 +788,11 @@ int perf_event__preprocess_sample(const union perf_event *event, { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread = machine__findnew_thread(machine, sample->pid, - sample->pid); + sample->tid); if (thread == NULL) return -1; - if (thread__is_filtered(thread)) - goto out_filtered; - dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); /* * Have we already created the kernel maps for this machine? @@ -768,6 +810,10 @@ int perf_event__preprocess_sample(const union perf_event *event, dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); + + if (thread__is_filtered(thread)) + al->filtered |= (1 << HIST_FILTER__THREAD); + al->sym = NULL; al->cpu = sample->cpu; @@ -779,8 +825,9 @@ int perf_event__preprocess_sample(const union perf_event *event, dso->short_name) || (dso->short_name != dso->long_name && strlist__has_entry(symbol_conf.dso_list, - dso->long_name))))) - goto out_filtered; + dso->long_name))))) { + al->filtered |= (1 << HIST_FILTER__DSO); + } al->sym = map__find_symbol(al->map, al->addr, machine->symbol_filter); @@ -788,12 +835,9 @@ int perf_event__preprocess_sample(const union perf_event *event, if (symbol_conf.sym_list && (!al->sym || !strlist__has_entry(symbol_conf.sym_list, - al->sym->name))) - goto out_filtered; - - return 0; + al->sym->name))) { + al->filtered |= (1 << HIST_FILTER__SYMBOL); + } -out_filtered: - al->filtered = true; return 0; } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 851fa06f4a42..d970232cb270 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -85,6 +85,7 @@ struct sample_event { struct regs_dump { u64 abi; + u64 mask; u64 *regs; }; @@ -111,6 +112,30 @@ struct sample_read { }; }; +struct ip_callchain { + u64 nr; + u64 ips[0]; +}; + +struct branch_flags { + u64 mispred:1; + u64 predicted:1; + u64 in_tx:1; + u64 abort:1; + u64 reserved:60; +}; + +struct branch_entry { + u64 from; + u64 to; + struct branch_flags flags; +}; + +struct branch_stack { + u64 nr; + struct branch_entry entries[0]; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -259,9 +284,9 @@ int perf_event__preprocess_sample(const union perf_event *event, const char *perf_event__name(unsigned int id); size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 sample_regs_user, u64 read_format); + u64 read_format); int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 sample_regs_user, u64 read_format, + u64 read_format, const struct perf_sample *sample, bool swapped); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 55407c594b87..5c28d82b76c4 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -500,6 +500,34 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) return ret; } +static void +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 (opts->call_graph == CALLCHAIN_DWARF) { + if (!function) { + perf_evsel__set_sample_bit(evsel, REGS_USER); + perf_evsel__set_sample_bit(evsel, STACK_USER); + attr->sample_regs_user = PERF_REGS_MASK; + attr->sample_stack_user = opts->stack_dump_size; + attr->exclude_callchain_user = 1; + } else { + pr_info("Cannot use DWARF unwind for function trace event," + " falling back to framepointers.\n"); + } + } + + if (function) { + pr_info("Disabling user space callchains for function trace event.\n"); + attr->exclude_callchain_user = 1; + } +} + /* * The enable_on_exec/disabled value strategy: * @@ -595,17 +623,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } - if (opts->call_graph) { - perf_evsel__set_sample_bit(evsel, CALLCHAIN); - - if (opts->call_graph == CALLCHAIN_DWARF) { - perf_evsel__set_sample_bit(evsel, REGS_USER); - perf_evsel__set_sample_bit(evsel, STACK_USER); - attr->sample_regs_user = PERF_REGS_MASK; - attr->sample_stack_user = opts->stack_dump_size; - attr->exclude_callchain_user = 1; - } - } + if (opts->call_graph_enabled) + perf_evsel__config_callgraph(evsel, opts); if (target__has_cpu(&opts->target)) perf_evsel__set_sample_bit(evsel, CPU); @@ -1004,7 +1023,7 @@ retry_sample_id: group_fd = get_group_fd(evsel, cpu, thread); retry_open: - pr_debug2("perf_event_open: pid %d cpu %d group_fd %d flags %#lx\n", + pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx\n", pid, cpus->map[cpu], group_fd, flags); FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, @@ -1013,7 +1032,7 @@ retry_open: group_fd, flags); if (FD(evsel, cpu, thread) < 0) { err = -errno; - pr_debug2("perf_event_open failed, error %d\n", + pr_debug2("sys_perf_event_open failed, error %d\n", err); goto try_fallback; } @@ -1220,7 +1239,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, memset(data, 0, sizeof(*data)); data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; - data->period = 1; + data->period = evsel->attr.sample_period; data->weight = 0; if (event->header.type != PERF_RECORD_SAMPLE) { @@ -1396,10 +1415,11 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; if (data->user_regs.abi) { - u64 regs_user = evsel->attr.sample_regs_user; + u64 mask = evsel->attr.sample_regs_user; - sz = hweight_long(regs_user) * sizeof(u64); + sz = hweight_long(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); + data->user_regs.mask = mask; data->user_regs.regs = (u64 *)array; array = (void *)array + sz; } @@ -1451,7 +1471,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, - u64 sample_regs_user, u64 read_format) + u64 read_format) { size_t sz, result = sizeof(struct sample_event); @@ -1517,7 +1537,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample_regs_user) * sizeof(u64); + sz = hweight_long(sample->user_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -1546,7 +1566,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, } int perf_event__synthesize_sample(union perf_event *event, u64 type, - u64 sample_regs_user, u64 read_format, + u64 read_format, const struct perf_sample *sample, bool swapped) { @@ -1687,7 +1707,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { *array++ = sample->user_regs.abi; - sz = hweight_long(sample_regs_user) * sizeof(u64); + sz = hweight_long(sample->user_regs.mask) * sizeof(u64); memcpy(array, sample->user_regs.regs, sz); array = (void *)array + sz; } else { diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index f1b325665aae..a52e9a5bb2d0 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -5,12 +5,12 @@ #include <stdbool.h> #include <stddef.h> #include <linux/perf_event.h> -#include "types.h" +#include <linux/types.h> #include "xyarray.h" #include "cgroup.h" #include "hist.h" #include "symbol.h" - + struct perf_counts_values { union { struct { @@ -91,6 +91,11 @@ struct perf_evsel { char *group_name; }; +union u64_swap { + u64 val64; + u32 val32[2]; +}; + #define hists_to_evsel(h) container_of(h, struct perf_evsel, hists) struct cpu_map; @@ -315,6 +320,24 @@ static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel) return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1; } +/** + * perf_evsel__is_function_event - Return whether given evsel is a function + * trace event + * + * @evsel - evsel selector to be tested + * + * Return %true if event is function trace event + */ +static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel) +{ +#define FUNCTION_EVENT "ftrace:function" + + return evsel->name && + !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT)); + +#undef FUNCTION_EVENT +} + struct perf_attr_details { bool freq; bool verbose; diff --git a/tools/perf/util/fs.c b/tools/perf/util/fs.c deleted file mode 100644 index f5be1f26e724..000000000000 --- a/tools/perf/util/fs.c +++ /dev/null @@ -1,119 +0,0 @@ - -/* TODO merge/factor into tools/lib/lk/debugfs.c */ - -#include "util.h" -#include "util/fs.h" - -static const char * const sysfs__fs_known_mountpoints[] = { - "/sys", - 0, -}; - -static const char * const procfs__known_mountpoints[] = { - "/proc", - 0, -}; - -struct fs { - const char *name; - const char * const *mounts; - char path[PATH_MAX + 1]; - bool found; - long magic; -}; - -enum { - FS__SYSFS = 0, - FS__PROCFS = 1, -}; - -static struct fs fs__entries[] = { - [FS__SYSFS] = { - .name = "sysfs", - .mounts = sysfs__fs_known_mountpoints, - .magic = SYSFS_MAGIC, - }, - [FS__PROCFS] = { - .name = "proc", - .mounts = procfs__known_mountpoints, - .magic = PROC_SUPER_MAGIC, - }, -}; - -static bool fs__read_mounts(struct fs *fs) -{ - bool found = false; - char type[100]; - FILE *fp; - - fp = fopen("/proc/mounts", "r"); - if (fp == NULL) - return NULL; - - while (!found && - fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", - fs->path, type) == 2) { - - if (strcmp(type, fs->name) == 0) - found = true; - } - - fclose(fp); - return fs->found = found; -} - -static int fs__valid_mount(const char *fs, long magic) -{ - struct statfs st_fs; - - if (statfs(fs, &st_fs) < 0) - return -ENOENT; - else if (st_fs.f_type != magic) - return -ENOENT; - - return 0; -} - -static bool fs__check_mounts(struct fs *fs) -{ - const char * const *ptr; - - ptr = fs->mounts; - while (*ptr) { - if (fs__valid_mount(*ptr, fs->magic) == 0) { - fs->found = true; - strcpy(fs->path, *ptr); - return true; - } - ptr++; - } - - return false; -} - -static const char *fs__get_mountpoint(struct fs *fs) -{ - if (fs__check_mounts(fs)) - return fs->path; - - return fs__read_mounts(fs) ? fs->path : NULL; -} - -static const char *fs__mountpoint(int idx) -{ - struct fs *fs = &fs__entries[idx]; - - if (fs->found) - return (const char *)fs->path; - - return fs__get_mountpoint(fs); -} - -#define FS__MOUNTPOINT(name, idx) \ -const char *name##__mountpoint(void) \ -{ \ - return fs__mountpoint(idx); \ -} - -FS__MOUNTPOINT(sysfs, FS__SYSFS); -FS__MOUNTPOINT(procfs, FS__PROCFS); diff --git a/tools/perf/util/fs.h b/tools/perf/util/fs.h deleted file mode 100644 index 5e09ce1bab0e..000000000000 --- a/tools/perf/util/fs.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef __PERF_FS -#define __PERF_FS - -const char *sysfs__mountpoint(void); -const char *procfs__mountpoint(void); - -#endif /* __PERF_FS */ diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index a2d047bdf4ef..d08cfe499404 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -4,10 +4,10 @@ #include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> -#include "types.h" +#include <linux/bitmap.h> +#include <linux/types.h> #include "event.h" -#include <linux/bitmap.h> enum { HEADER_RESERVED = 0, /* always cleared */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index e4e6249b87d4..b262b44b7a65 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -13,13 +13,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists, static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he); -enum hist_filter { - HIST_FILTER__DSO, - HIST_FILTER__THREAD, - HIST_FILTER__PARENT, - HIST_FILTER__SYMBOL, -}; - struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_REL, .min_percent = 0.5, @@ -232,14 +225,18 @@ static void he_stat__decay(struct he_stat *he_stat) static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) { u64 prev_period = he->stat.period; + u64 diff; if (prev_period == 0) return true; he_stat__decay(&he->stat); + diff = prev_period - he->stat.period; + + hists->stats.total_period -= diff; if (!he->filtered) - hists->stats.total_period -= prev_period - he->stat.period; + hists->stats.total_non_filtered_period -= diff; return he->stat.period == 0; } @@ -266,8 +263,11 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) if (sort__need_collapse) rb_erase(&n->rb_node_in, &hists->entries_collapsed); - hist_entry__free(n); --hists->nr_entries; + if (!n->filtered) + --hists->nr_non_filtered_entries; + + hist_entry__free(n); } } } @@ -290,7 +290,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) if (he->branch_info) { /* * This branch info is (a part of) allocated from - * machine__resolve_bstack() and will be freed after + * sample__resolve_bstack() and will be freed after * adding new entries. So we need to save a copy. */ he->branch_info = malloc(sizeof(*he->branch_info)); @@ -324,15 +324,6 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) return he; } -void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) -{ - if (!h->filtered) { - hists__calc_col_len(hists, h); - ++hists->nr_entries; - hists->stats.total_period += h->stat.period; - } -} - static u8 symbol__parent_filter(const struct symbol *parent) { if (symbol_conf.exclude_other && parent == NULL) @@ -369,7 +360,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, he_stat__add_period(&he->stat, period, weight); /* - * This mem info was allocated from machine__resolve_mem + * This mem info was allocated from sample__resolve_mem * and will not be used anymore. */ zfree(&entry->mem_info); @@ -398,7 +389,6 @@ static struct hist_entry *add_hist_entry(struct hists *hists, if (!he) return NULL; - hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: @@ -429,7 +419,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .weight = weight, }, .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), + .filtered = symbol__parent_filter(sym_parent) | al->filtered, .hists = hists, .branch_info = bi, .mem_info = mi, @@ -442,11 +432,14 @@ struct hist_entry *__hists__add_entry(struct hists *hists, int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { - struct sort_entry *se; + struct perf_hpp_fmt *fmt; int64_t cmp = 0; - list_for_each_entry(se, &hist_entry__sort_list, list) { - cmp = se->se_cmp(left, right); + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; + + cmp = fmt->cmp(left, right); if (cmp) break; } @@ -457,15 +450,14 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) { - struct sort_entry *se; + struct perf_hpp_fmt *fmt; int64_t cmp = 0; - list_for_each_entry(se, &hist_entry__sort_list, list) { - int64_t (*f)(struct hist_entry *, struct hist_entry *); - - f = se->se_collapse ?: se->se_cmp; + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; - cmp = f(left, right); + cmp = fmt->collapse(left, right); if (cmp) break; } @@ -578,64 +570,50 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) } } -/* - * reverse the map, sort on period. - */ - -static int period_cmp(u64 period_a, u64 period_b) -{ - if (period_a > period_b) - return 1; - if (period_a < period_b) - return -1; - return 0; -} - -static int hist_entry__sort_on_period(struct hist_entry *a, - struct hist_entry *b) +static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) { - int ret; - int i, nr_members; - struct perf_evsel *evsel; - struct hist_entry *pair; - u64 *periods_a, *periods_b; + struct perf_hpp_fmt *fmt; + int64_t cmp = 0; - ret = period_cmp(a->stat.period, b->stat.period); - if (ret || !symbol_conf.event_group) - return ret; + perf_hpp__for_each_sort_list(fmt) { + if (perf_hpp__should_skip(fmt)) + continue; - evsel = hists_to_evsel(a->hists); - nr_members = evsel->nr_members; - if (nr_members <= 1) - return ret; + cmp = fmt->sort(a, b); + if (cmp) + break; + } - periods_a = zalloc(sizeof(periods_a) * nr_members); - periods_b = zalloc(sizeof(periods_b) * nr_members); + return cmp; +} - if (!periods_a || !periods_b) - goto out; +static void hists__reset_filter_stats(struct hists *hists) +{ + hists->nr_non_filtered_entries = 0; + hists->stats.total_non_filtered_period = 0; +} - list_for_each_entry(pair, &a->pairs.head, pairs.node) { - evsel = hists_to_evsel(pair->hists); - periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period; - } +void hists__reset_stats(struct hists *hists) +{ + hists->nr_entries = 0; + hists->stats.total_period = 0; - list_for_each_entry(pair, &b->pairs.head, pairs.node) { - evsel = hists_to_evsel(pair->hists); - periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period; - } + hists__reset_filter_stats(hists); +} - for (i = 1; i < nr_members; i++) { - ret = period_cmp(periods_a[i], periods_b[i]); - if (ret) - break; - } +static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h) +{ + hists->nr_non_filtered_entries++; + hists->stats.total_non_filtered_period += h->stat.period; +} -out: - free(periods_a); - free(periods_b); +void hists__inc_stats(struct hists *hists, struct hist_entry *h) +{ + if (!h->filtered) + hists__inc_filter_stats(hists, h); - return ret; + hists->nr_entries++; + hists->stats.total_period += h->stat.period; } static void __hists__insert_output_entry(struct rb_root *entries, @@ -654,7 +632,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node); - if (hist_entry__sort_on_period(he, iter) > 0) + if (hist_entry__sort(he, iter) > 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -681,8 +659,7 @@ void hists__output_resort(struct hists *hists) next = rb_first(root); hists->entries = RB_ROOT; - hists->nr_entries = 0; - hists->stats.total_period = 0; + hists__reset_stats(hists); hists__reset_col_len(hists); while (next) { @@ -690,7 +667,10 @@ void hists__output_resort(struct hists *hists) next = rb_next(&n->rb_node_in); __hists__insert_output_entry(&hists->entries, n, min_callchain_hits); - hists__inc_nr_entries(hists, n); + hists__inc_stats(hists, n); + + if (!n->filtered) + hists__calc_col_len(hists, n); } } @@ -701,13 +681,13 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h if (h->filtered) return; - ++hists->nr_entries; - if (h->ms.unfolded) - hists->nr_entries += h->nr_rows; + /* force fold unfiltered entry for simplicity */ + h->ms.unfolded = false; h->row_offset = 0; - hists->stats.total_period += h->stat.period; - hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events; + hists->stats.nr_non_filtered_samples += h->stat.nr_events; + + hists__inc_filter_stats(hists, h); hists__calc_col_len(hists, h); } @@ -728,8 +708,9 @@ void hists__filter_by_dso(struct hists *hists) { struct rb_node *nd; - hists->nr_entries = hists->stats.total_period = 0; - hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists->stats.nr_non_filtered_samples = 0; + + hists__reset_filter_stats(hists); hists__reset_col_len(hists); for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { @@ -761,8 +742,9 @@ void hists__filter_by_thread(struct hists *hists) { struct rb_node *nd; - hists->nr_entries = hists->stats.total_period = 0; - hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists->stats.nr_non_filtered_samples = 0; + + hists__reset_filter_stats(hists); hists__reset_col_len(hists); for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { @@ -792,8 +774,9 @@ void hists__filter_by_symbol(struct hists *hists) { struct rb_node *nd; - hists->nr_entries = hists->stats.total_period = 0; - hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0; + hists->stats.nr_non_filtered_samples = 0; + + hists__reset_filter_stats(hists); hists__reset_col_len(hists); for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { @@ -854,7 +837,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, he->hists = hists; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); - hists__inc_nr_entries(hists, he); + hists__inc_stats(hists, he); he->dummy = true; } out: @@ -938,3 +921,30 @@ int hists__link(struct hists *leader, struct hists *other) return 0; } + +u64 hists__total_period(struct hists *hists) +{ + return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period : + hists->stats.total_period; +} + +int parse_filter_percentage(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (!strcmp(arg, "relative")) + symbol_conf.filter_relative = true; + else if (!strcmp(arg, "absolute")) + symbol_conf.filter_relative = false; + else + return -1; + + return 0; +} + +int perf_hist_config(const char *var, const char *value) +{ + if (!strcmp(var, "hist.percentage")) + return parse_filter_percentage(NULL, value, 0); + + return 0; +} diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index a59743fa3ef7..a8418d19808d 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -14,6 +14,15 @@ struct hist_entry; struct addr_location; struct symbol; +enum hist_filter { + HIST_FILTER__DSO, + HIST_FILTER__THREAD, + HIST_FILTER__PARENT, + HIST_FILTER__SYMBOL, + HIST_FILTER__GUEST, + HIST_FILTER__HOST, +}; + /* * The kernel collects the number of events it couldn't send in a stretch and * when possible sends this number in a PERF_RECORD_LOST event. The number of @@ -28,9 +37,11 @@ struct symbol; */ struct events_stats { u64 total_period; + u64 total_non_filtered_period; u64 total_lost; u64 total_invalid_chains; u32 nr_events[PERF_RECORD_HEADER_MAX]; + u32 nr_non_filtered_samples; u32 nr_lost_warned; u32 nr_unknown_events; u32 nr_invalid_chains; @@ -74,6 +85,7 @@ struct hists { struct rb_root entries; struct rb_root entries_collapsed; u64 nr_entries; + u64 nr_non_filtered_entries; const struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; @@ -103,7 +115,9 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); void hists__output_recalc_col_len(struct hists *hists, int max_rows); -void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h); +u64 hists__total_period(struct hists *hists); +void hists__reset_stats(struct hists *hists); +void hists__inc_stats(struct hists *hists, struct hist_entry *h); void hists__inc_nr_events(struct hists *hists, u32 type); void events_stats__inc(struct events_stats *stats, u32 type); size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); @@ -115,6 +129,12 @@ void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); void hists__filter_by_symbol(struct hists *hists); +static inline bool hists__has_filter(struct hists *hists) +{ + return hists->thread_filter || hists->dso_filter || + hists->symbol_filter_str; +} + u16 hists__col_len(struct hists *hists, enum hist_column col); void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len); bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len); @@ -132,21 +152,37 @@ struct perf_hpp { }; struct perf_hpp_fmt { - int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); - int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); + int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel); + int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel); int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); + int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b); + int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b); + int64_t (*sort)(struct hist_entry *a, struct hist_entry *b); struct list_head list; + struct list_head sort_list; }; extern struct list_head perf_hpp__list; +extern struct list_head perf_hpp__sort_list; #define perf_hpp__for_each_format(format) \ list_for_each_entry(format, &perf_hpp__list, list) +#define perf_hpp__for_each_format_safe(format, tmp) \ + list_for_each_entry_safe(format, tmp, &perf_hpp__list, list) + +#define perf_hpp__for_each_sort_list(format) \ + list_for_each_entry(format, &perf_hpp__sort_list, sort_list) + +#define perf_hpp__for_each_sort_list_safe(format, tmp) \ + list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list) + extern struct perf_hpp_fmt perf_hpp__format[]; enum { @@ -165,6 +201,29 @@ enum { void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); +void perf_hpp__register_sort_field(struct perf_hpp_fmt *format); +void perf_hpp__setup_output_field(void); +void perf_hpp__reset_output_field(void); +void perf_hpp__append_sort_keys(void); + +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); +bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); +bool perf_hpp__should_skip(struct perf_hpp_fmt *format); +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); + +typedef u64 (*hpp_field_fn)(struct hist_entry *he); +typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front); +typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...); + +int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + hpp_field_fn get_field, const char *fmt, + hpp_snprint_fn print_fn, bool fmt_percent); + +static inline void advance_hpp(struct perf_hpp *hpp, int inc) +{ + hpp->buf += inc; + hpp->size -= inc; +} static inline size_t perf_hpp__use_color(void) { @@ -225,4 +284,10 @@ static inline int script_browse(const char *script_opt __maybe_unused) #endif unsigned int hists__sort_list_width(struct hists *hists); + +struct option; +int parse_filter_percentage(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused); +int perf_hist_config(const char *var, const char *value); + #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h index bb162e40c76c..01ffd12dc791 100644 --- a/tools/perf/util/include/linux/bitmap.h +++ b/tools/perf/util/include/linux/bitmap.h @@ -4,6 +4,9 @@ #include <string.h> #include <linux/bitops.h> +#define DECLARE_BITMAP(name,bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); diff --git a/tools/perf/util/include/linux/export.h b/tools/perf/util/include/linux/export.h deleted file mode 100644 index b43e2dc21e04..000000000000 --- a/tools/perf/util/include/linux/export.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef PERF_LINUX_MODULE_H -#define PERF_LINUX_MODULE_H - -#define EXPORT_SYMBOL(name) - -#endif diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h deleted file mode 100644 index 201f57397997..000000000000 --- a/tools/perf/util/include/linux/hash.h +++ /dev/null @@ -1,5 +0,0 @@ -#include "../../../../include/linux/hash.h" - -#ifndef PERF_HASH_H -#define PERF_HASH_H -#endif diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index d8c927c868ee..9844c31b7c2b 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -94,12 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) return (i >= ssize) ? (ssize - 1) : i; } -static inline unsigned long -simple_strtoul(const char *nptr, char **endptr, int base) -{ - return strtoul(nptr, endptr, base); -} - int eprintf(int level, const char *fmt, ...) __attribute__((format(printf, 2, 3))); diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h index 1d928a0ce997..76ddbc726343 100644 --- a/tools/perf/util/include/linux/list.h +++ b/tools/perf/util/include/linux/list.h @@ -1,5 +1,5 @@ #include <linux/kernel.h> -#include <linux/prefetch.h> +#include <linux/types.h> #include "../../../../include/linux/list.h" diff --git a/tools/perf/util/include/linux/magic.h b/tools/perf/util/include/linux/magic.h deleted file mode 100644 index 07d63cf3e0f6..000000000000 --- a/tools/perf/util/include/linux/magic.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef _PERF_LINUX_MAGIC_H_ -#define _PERF_LINUX_MAGIC_H_ - -#ifndef DEBUGFS_MAGIC -#define DEBUGFS_MAGIC 0x64626720 -#endif - -#ifndef SYSFS_MAGIC -#define SYSFS_MAGIC 0x62656572 -#endif - -#ifndef PROC_SUPER_MAGIC -#define PROC_SUPER_MAGIC 0x9fa0 -#endif - -#endif diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h deleted file mode 100644 index 7841e485d8c3..000000000000 --- a/tools/perf/util/include/linux/prefetch.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef PERF_LINUX_PREFETCH_H -#define PERF_LINUX_PREFETCH_H - -static inline void prefetch(void *a __attribute__((unused))) { } - -#endif diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h deleted file mode 100644 index eb464786c084..000000000000 --- a/tools/perf/util/include/linux/types.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef _PERF_LINUX_TYPES_H_ -#define _PERF_LINUX_TYPES_H_ - -#include <asm/types.h> - -#ifndef __bitwise -#define __bitwise -#endif - -#ifndef __le32 -typedef __u32 __bitwise __le32; -#endif - -#define DECLARE_BITMAP(name,bits) \ - unsigned long name[BITS_TO_LONGS(bits)] - -struct list_head { - struct list_head *next, *prev; -}; - -struct hlist_head { - struct hlist_node *first; -}; - -struct hlist_node { - struct hlist_node *next, **pprev; -}; - -#endif diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 620a1983b76b..7409ac8de51c 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -316,6 +316,17 @@ static struct thread *__machine__findnew_thread(struct machine *machine, rb_link_node(&th->rb_node, parent, p); rb_insert_color(&th->rb_node, &machine->threads); machine->last_match = th; + + /* + * We have to initialize map_groups separately + * after rb tree is updated. + * + * The reason is that we call machine__findnew_thread + * within thread__init_map_groups to find the thread + * leader and that would screwed the rb tree. + */ + if (thread__init_map_groups(th, machine)) + return NULL; } return th; @@ -327,9 +338,10 @@ struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, return __machine__findnew_thread(machine, pid, tid, true); } -struct thread *machine__find_thread(struct machine *machine, pid_t tid) +struct thread *machine__find_thread(struct machine *machine, pid_t pid, + pid_t tid) { - return __machine__findnew_thread(machine, 0, tid, false); + return __machine__findnew_thread(machine, pid, tid, false); } int machine__process_comm_event(struct machine *machine, union perf_event *event, @@ -716,7 +728,7 @@ static char *get_kernel_version(const char *root_dir) } static int map_groups__set_modules_path_dir(struct map_groups *mg, - const char *dir_name) + const char *dir_name, int depth) { struct dirent *dent; DIR *dir = opendir(dir_name); @@ -741,7 +753,15 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg, !strcmp(dent->d_name, "..")) continue; - ret = map_groups__set_modules_path_dir(mg, path); + /* Do not follow top-level source and build symlinks */ + if (depth == 0) { + if (!strcmp(dent->d_name, "source") || + !strcmp(dent->d_name, "build")) + continue; + } + + ret = map_groups__set_modules_path_dir(mg, path, + depth + 1); if (ret < 0) goto out; } else { @@ -785,11 +805,11 @@ static int machine__set_modules_path(struct machine *machine) if (!version) return -1; - snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", + snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s", machine->root_dir, version); free(version); - return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); + return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); } static int machine__create_module(void *arg, const char *name, u64 start) @@ -1026,7 +1046,7 @@ int machine__process_mmap2_event(struct machine *machine, } thread = machine__findnew_thread(machine, event->mmap2.pid, - event->mmap2.pid); + event->mmap2.tid); if (thread == NULL) goto out_problem; @@ -1074,7 +1094,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event } thread = machine__findnew_thread(machine, event->mmap.pid, - event->mmap.pid); + event->mmap.tid); if (thread == NULL) goto out_problem; @@ -1114,7 +1134,9 @@ static void machine__remove_thread(struct machine *machine, struct thread *th) int machine__process_fork_event(struct machine *machine, union perf_event *event, struct perf_sample *sample) { - struct thread *thread = machine__find_thread(machine, event->fork.tid); + struct thread *thread = machine__find_thread(machine, + event->fork.pid, + event->fork.tid); struct thread *parent = machine__findnew_thread(machine, event->fork.ppid, event->fork.ptid); @@ -1140,7 +1162,9 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event int machine__process_exit_event(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) { - struct thread *thread = machine__find_thread(machine, event->fork.tid); + struct thread *thread = machine__find_thread(machine, + event->fork.pid, + event->fork.tid); if (dump_trace) perf_event__fprintf_task(event, stdout); @@ -1184,39 +1208,22 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex) return 0; } -static const u8 cpumodes[] = { - PERF_RECORD_MISC_USER, - PERF_RECORD_MISC_KERNEL, - PERF_RECORD_MISC_GUEST_USER, - PERF_RECORD_MISC_GUEST_KERNEL -}; -#define NCPUMODES (sizeof(cpumodes)/sizeof(u8)) - static void ip__resolve_ams(struct machine *machine, struct thread *thread, struct addr_map_symbol *ams, u64 ip) { struct addr_location al; - size_t i; - u8 m; memset(&al, 0, sizeof(al)); + /* + * We cannot use the header.misc hint to determine whether a + * branch stack address is user, kernel, guest, hypervisor. + * Branches may straddle the kernel/user/hypervisor boundaries. + * Thus, we have to try consecutively until we find a match + * or else, the symbol is unknown + */ + thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al); - for (i = 0; i < NCPUMODES; i++) { - m = cpumodes[i]; - /* - * We cannot use the header.misc hint to determine whether a - * branch stack address is user, kernel, guest, hypervisor. - * Branches may straddle the kernel/user/hypervisor boundaries. - * Thus, we have to try consecutively until we find a match - * or else, the symbol is unknown - */ - thread__find_addr_location(thread, machine, m, MAP__FUNCTION, - ip, &al); - if (al.map) - goto found; - } -found: ams->addr = ip; ams->al_addr = al.addr; ams->sym = al.sym; @@ -1238,37 +1245,35 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread, ams->map = al.map; } -struct mem_info *machine__resolve_mem(struct machine *machine, - struct thread *thr, - struct perf_sample *sample, - u8 cpumode) +struct mem_info *sample__resolve_mem(struct perf_sample *sample, + struct addr_location *al) { struct mem_info *mi = zalloc(sizeof(*mi)); if (!mi) return NULL; - ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip); - ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr); + ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip); + ip__resolve_data(al->machine, al->thread, al->cpumode, + &mi->daddr, sample->addr); mi->data_src.val = sample->data_src; return mi; } -struct branch_info *machine__resolve_bstack(struct machine *machine, - struct thread *thr, - struct branch_stack *bs) +struct branch_info *sample__resolve_bstack(struct perf_sample *sample, + struct addr_location *al) { - struct branch_info *bi; unsigned int i; + const struct branch_stack *bs = sample->branch_stack; + struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info)); - bi = calloc(bs->nr, sizeof(struct branch_info)); if (!bi) return NULL; for (i = 0; i < bs->nr; i++) { - ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to); - ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from); + ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from); bi[i].flags = bs->entries[i].flags; } return bi; @@ -1326,7 +1331,7 @@ static int machine__resolve_callchain_sample(struct machine *machine, continue; } - al.filtered = false; + al.filtered = 0; thread__find_addr_location(thread, machine, cpumode, MAP__FUNCTION, ip, &al); if (al.sym != NULL) { @@ -1385,8 +1390,7 @@ int machine__resolve_callchain(struct machine *machine, return 0; return unwind__get_entries(unwind_entry, &callchain_cursor, machine, - thread, evsel->attr.sample_regs_user, - sample, max_stack); + thread, sample, max_stack); } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index f77e91e483dc..c8c74a119398 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -41,7 +41,8 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type) return machine->vmlinux_maps[type]; } -struct thread *machine__find_thread(struct machine *machine, pid_t tid); +struct thread *machine__find_thread(struct machine *machine, pid_t pid, + pid_t tid); int machine__process_comm_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); @@ -91,12 +92,10 @@ void machine__delete_dead_threads(struct machine *machine); void machine__delete_threads(struct machine *machine); void machine__delete(struct machine *machine); -struct branch_info *machine__resolve_bstack(struct machine *machine, - struct thread *thread, - struct branch_stack *bs); -struct mem_info *machine__resolve_mem(struct machine *machine, - struct thread *thread, - struct perf_sample *sample, u8 cpumode); +struct branch_info *sample__resolve_bstack(struct perf_sample *sample, + struct addr_location *al); +struct mem_info *sample__resolve_mem(struct perf_sample *sample, + struct addr_location *al); int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 39cd2d0faff6..8ccbb32eda25 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -32,6 +32,93 @@ static inline int is_no_dso_memory(const char *filename) !strcmp(filename, "[heap]"); } +static inline int is_android_lib(const char *filename) +{ + return !strncmp(filename, "/data/app-lib", 13) || + !strncmp(filename, "/system/lib", 11); +} + +static inline bool replace_android_lib(const char *filename, char *newfilename) +{ + const char *libname; + char *app_abi; + size_t app_abi_length, new_length; + size_t lib_length = 0; + + libname = strrchr(filename, '/'); + if (libname) + lib_length = strlen(libname); + + app_abi = getenv("APP_ABI"); + if (!app_abi) + return false; + + app_abi_length = strlen(app_abi); + + if (!strncmp(filename, "/data/app-lib", 13)) { + char *apk_path; + + if (!app_abi_length) + return false; + + new_length = 7 + app_abi_length + lib_length; + + apk_path = getenv("APK_PATH"); + if (apk_path) { + new_length += strlen(apk_path) + 1; + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "%s/libs/%s/%s", apk_path, app_abi, libname); + } else { + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "libs/%s/%s", app_abi, libname); + } + return true; + } + + if (!strncmp(filename, "/system/lib/", 11)) { + char *ndk, *app; + const char *arch; + size_t ndk_length; + size_t app_length; + + ndk = getenv("NDK_ROOT"); + app = getenv("APP_PLATFORM"); + + if (!(ndk && app)) + return false; + + ndk_length = strlen(ndk); + app_length = strlen(app); + + if (!(ndk_length && app_length && app_abi_length)) + return false; + + arch = !strncmp(app_abi, "arm", 3) ? "arm" : + !strncmp(app_abi, "mips", 4) ? "mips" : + !strncmp(app_abi, "x86", 3) ? "x86" : NULL; + + if (!arch) + return false; + + new_length = 27 + ndk_length + + app_length + lib_length + + strlen(arch); + + if (new_length > PATH_MAX) + return false; + snprintf(newfilename, new_length, + "%s/platforms/%s/arch-%s/usr/lib/%s", + ndk, app, arch, libname); + + return true; + } + return false; +} + void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso) { @@ -59,8 +146,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, if (map != NULL) { char newfilename[PATH_MAX]; struct dso *dso; - int anon, no_dso, vdso; + int anon, no_dso, vdso, android; + android = is_android_lib(filename); anon = is_anon_memory(filename); vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); @@ -75,6 +163,11 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, filename = newfilename; } + if (android) { + if (replace_android_lib(filename, newfilename)) + filename = newfilename; + } + if (vdso) { pgoff = 0; dso = vdso__dso_findnew(dsos__list); @@ -323,6 +416,7 @@ void map_groups__init(struct map_groups *mg) INIT_LIST_HEAD(&mg->removed_maps[i]); } mg->machine = NULL; + mg->refcnt = 1; } static void maps__delete(struct rb_root *maps) @@ -358,6 +452,28 @@ void map_groups__exit(struct map_groups *mg) } } +struct map_groups *map_groups__new(void) +{ + struct map_groups *mg = malloc(sizeof(*mg)); + + if (mg != NULL) + map_groups__init(mg); + + return mg; +} + +void map_groups__delete(struct map_groups *mg) +{ + map_groups__exit(mg); + free(mg); +} + +void map_groups__put(struct map_groups *mg) +{ + if (--mg->refcnt == 0) + map_groups__delete(mg); +} + void map_groups__flush(struct map_groups *mg) { int type; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 257e513205ce..ae2d45110588 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -6,7 +6,7 @@ #include <linux/rbtree.h> #include <stdio.h> #include <stdbool.h> -#include "types.h" +#include <linux/types.h> enum map_type { MAP__FUNCTION = 0, @@ -59,8 +59,20 @@ struct map_groups { struct rb_root maps[MAP__NR_TYPES]; struct list_head removed_maps[MAP__NR_TYPES]; struct machine *machine; + int refcnt; }; +struct map_groups *map_groups__new(void); +void map_groups__delete(struct map_groups *mg); + +static inline struct map_groups *map_groups__get(struct map_groups *mg) +{ + ++mg->refcnt; + return mg; +} + +void map_groups__put(struct map_groups *mg); + static inline struct kmap *map__kmap(struct map *map) { return (struct kmap *)(map + 1); @@ -90,6 +102,16 @@ u64 map__objdump_2mem(struct map *map, u64 ip); struct symbol; +/* map__for_each_symbol - iterate over the symbols in the given map + * + * @map: the 'struct map *' in which symbols itereated + * @pos: the 'struct symbol *' to use as a loop cursor + * @n: the 'struct rb_node *' to use as a temporary storage + * Note: caller must ensure map->dso is not NULL (map is loaded). + */ +#define map__for_each_symbol(map, pos, n) \ + dso__for_each_symbol(map->dso, pos, n, map->type) + typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c index 3322b8446e89..31ee02d4e988 100644 --- a/tools/perf/util/pager.c +++ b/tools/perf/util/pager.c @@ -57,13 +57,13 @@ void setup_pager(void) } if (!pager) pager = getenv("PAGER"); - if (!pager) { - if (!access("/usr/bin/pager", X_OK)) - pager = "/usr/bin/pager"; - } + if (!(pager || access("/usr/bin/pager", X_OK))) + pager = "/usr/bin/pager"; + if (!(pager || access("/usr/bin/less", X_OK))) + pager = "/usr/bin/less"; if (!pager) - pager = "less"; - else if (!*pager || !strcmp(pager, "cat")) + pager = "cat"; + if (!*pager || !strcmp(pager, "cat")) return; spawned_pager = 1; /* means we are emitting to terminal */ diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index f1cb4c4b3c70..df094b4ed5ed 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -6,9 +6,8 @@ #include <linux/list.h> #include <stdbool.h> -#include "types.h" +#include <linux/types.h> #include <linux/perf_event.h> -#include "types.h" struct list_head; struct perf_evsel; diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 4eb67ec333f1..0bc87ba46bf3 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -9,7 +9,7 @@ #include <linux/compiler.h> #include <linux/list.h> -#include "types.h" +#include <linux/types.h> #include "util.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -299,6 +299,18 @@ PE_PREFIX_MEM PE_VALUE sep_dc } event_legacy_tracepoint: +PE_NAME '-' PE_NAME ':' PE_NAME +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + char sys_name[128]; + snprintf(&sys_name, 128, "%s-%s", $1, $3); + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tracepoint(list, &data->idx, &sys_name, $5)); + $$ = list; +} +| PE_NAME ':' PE_NAME { struct parse_events_evlist *data = _data; diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index d22e3f8017dc..bf48092983c6 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -407,7 +407,9 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, if (internal_help && !strcmp(arg + 2, "help")) return usage_with_options_internal(usagestr, options, 0); if (!strcmp(arg + 2, "list-opts")) - return PARSE_OPT_LIST; + return PARSE_OPT_LIST_OPTS; + if (!strcmp(arg + 2, "list-cmds")) + return PARSE_OPT_LIST_SUBCMDS; switch (parse_long_opt(ctx, arg + 2, options)) { case -1: return parse_options_usage(usagestr, options, arg + 2, 0); @@ -433,25 +435,45 @@ int parse_options_end(struct parse_opt_ctx_t *ctx) return ctx->cpidx + ctx->argc; } -int parse_options(int argc, const char **argv, const struct option *options, - const char * const usagestr[], int flags) +int parse_options_subcommand(int argc, const char **argv, const struct option *options, + const char *const subcommands[], const char *usagestr[], int flags) { struct parse_opt_ctx_t ctx; perf_header__set_cmdline(argc, argv); + /* build usage string if it's not provided */ + if (subcommands && !usagestr[0]) { + struct strbuf buf = STRBUF_INIT; + + strbuf_addf(&buf, "perf %s [<options>] {", argv[0]); + for (int i = 0; subcommands[i]; i++) { + if (i) + strbuf_addstr(&buf, "|"); + strbuf_addstr(&buf, subcommands[i]); + } + strbuf_addstr(&buf, "}"); + + usagestr[0] = strdup(buf.buf); + strbuf_release(&buf); + } + parse_options_start(&ctx, argc, argv, flags); switch (parse_options_step(&ctx, options, usagestr)) { case PARSE_OPT_HELP: exit(129); case PARSE_OPT_DONE: break; - case PARSE_OPT_LIST: + case PARSE_OPT_LIST_OPTS: while (options->type != OPTION_END) { printf("--%s ", options->long_name); options++; } exit(130); + case PARSE_OPT_LIST_SUBCMDS: + for (int i = 0; subcommands[i]; i++) + printf("%s ", subcommands[i]); + exit(130); default: /* PARSE_OPT_UNKNOWN */ if (ctx.argv[0][1] == '-') { error("unknown option `%s'", ctx.argv[0] + 2); @@ -464,6 +486,13 @@ int parse_options(int argc, const char **argv, const struct option *options, return parse_options_end(&ctx); } +int parse_options(int argc, const char **argv, const struct option *options, + const char * const usagestr[], int flags) +{ + return parse_options_subcommand(argc, argv, options, NULL, + (const char **) usagestr, flags); +} + #define USAGE_OPTS_WIDTH 24 #define USAGE_GAP 2 diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index cbf0149cf221..d8dac8ac5f37 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -140,6 +140,11 @@ extern int parse_options(int argc, const char **argv, const struct option *options, const char * const usagestr[], int flags); +extern int parse_options_subcommand(int argc, const char **argv, + const struct option *options, + const char *const subcommands[], + const char *usagestr[], int flags); + extern NORETURN void usage_with_options(const char * const *usagestr, const struct option *options); @@ -148,7 +153,8 @@ extern NORETURN void usage_with_options(const char * const *usagestr, enum { PARSE_OPT_HELP = -1, PARSE_OPT_DONE, - PARSE_OPT_LIST, + PARSE_OPT_LIST_OPTS, + PARSE_OPT_LIST_SUBCMDS, PARSE_OPT_UNKNOWN, }; diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c new file mode 100644 index 000000000000..a3539ef30b15 --- /dev/null +++ b/tools/perf/util/perf_regs.c @@ -0,0 +1,19 @@ +#include <errno.h> +#include "perf_regs.h" + +int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) +{ + int i, idx = 0; + u64 mask = regs->mask; + + if (!(mask & (1 << id))) + return -EINVAL; + + for (i = 0; i < id; i++) { + if (mask & (1 << i)) + idx++; + } + + *valp = regs->regs[idx]; + return 0; +} diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index a3d42cd74919..79c78f74e0cf 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -1,8 +1,14 @@ #ifndef __PERF_REGS_H #define __PERF_REGS_H +#include <linux/types.h> +#include "event.h" + #ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> + +int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); + #else #define PERF_REGS_MASK 0 @@ -10,5 +16,12 @@ static inline const char *perf_reg_name(int id __maybe_unused) { return NULL; } + +static inline int perf_reg_value(u64 *valp __maybe_unused, + struct regs_dump *regs __maybe_unused, + int id __maybe_unused) +{ + return 0; +} #endif /* HAVE_PERF_REGS_SUPPORT */ #endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index b752ecb40d86..7a811eb61f75 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -3,7 +3,7 @@ #include <unistd.h> #include <stdio.h> #include <dirent.h> -#include "fs.h" +#include <api/fs/fs.h> #include <locale.h> #include "util.h" #include "pmu.h" @@ -284,17 +284,17 @@ static int pmu_aliases(const char *name, struct list_head *head) static int pmu_alias_terms(struct perf_pmu_alias *alias, struct list_head *terms) { - struct parse_events_term *term, *clone; + struct parse_events_term *term, *cloned; LIST_HEAD(list); int ret; list_for_each_entry(term, &alias->terms, list) { - ret = parse_events_term__clone(&clone, term); + ret = parse_events_term__clone(&cloned, term); if (ret) { parse_events__free_terms(&list); return ret; } - list_add_tail(&clone->list, &list); + list_add_tail(&cloned->list, &list); } list_splice(&list, terms); return 0; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 8b64125a9281..c14a543ce1f3 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -1,7 +1,7 @@ #ifndef __PMU_H #define __PMU_H -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/perf_event.h> #include <stdbool.h> diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index d8b048c20cde..0d1542f33d87 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -70,34 +70,32 @@ static int e_snprintf(char *str, size_t size, const char *format, ...) } static char *synthesize_perf_probe_point(struct perf_probe_point *pp); -static int convert_name_to_addr(struct perf_probe_event *pev, - const char *exec); static void clear_probe_trace_event(struct probe_trace_event *tev); -static struct machine machine; +static struct machine *host_machine; /* Initialize symbol maps and path of vmlinux/modules */ -static int init_vmlinux(void) +static int init_symbol_maps(bool user_only) { int ret; symbol_conf.sort_by_name = true; - if (symbol_conf.vmlinux_name == NULL) - symbol_conf.try_vmlinux_path = true; - else - pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); ret = symbol__init(); if (ret < 0) { pr_debug("Failed to init symbol map.\n"); goto out; } - ret = machine__init(&machine, "", HOST_KERNEL_ID); - if (ret < 0) - goto out; + if (host_machine || user_only) /* already initialized */ + return 0; - if (machine__create_kernel_maps(&machine) < 0) { - pr_debug("machine__create_kernel_maps() failed.\n"); - goto out; + if (symbol_conf.vmlinux_name) + pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); + + host_machine = machine__new_host(); + if (!host_machine) { + pr_debug("machine__new_host() failed.\n"); + symbol__exit(); + ret = -1; } out: if (ret < 0) @@ -105,21 +103,66 @@ out: return ret; } +static void exit_symbol_maps(void) +{ + if (host_machine) { + machine__delete(host_machine); + host_machine = NULL; + } + symbol__exit(); +} + static struct symbol *__find_kernel_function_by_name(const char *name, struct map **mapp) { - return machine__find_kernel_function_by_name(&machine, name, mapp, + return machine__find_kernel_function_by_name(host_machine, name, mapp, NULL); } +static struct symbol *__find_kernel_function(u64 addr, struct map **mapp) +{ + return machine__find_kernel_function(host_machine, addr, mapp, NULL); +} + +static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) +{ + /* kmap->ref_reloc_sym should be set if host_machine is initialized */ + struct kmap *kmap; + + if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0) + return NULL; + + kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]); + return kmap->ref_reloc_sym; +} + +static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc) +{ + struct ref_reloc_sym *reloc_sym; + struct symbol *sym; + struct map *map; + + /* ref_reloc_sym is just a label. Need a special fix*/ + reloc_sym = kernel_get_ref_reloc_sym(); + if (reloc_sym && strcmp(name, reloc_sym->name) == 0) + return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; + else { + sym = __find_kernel_function_by_name(name, &map); + if (sym) + return map->unmap_ip(map, sym->start) - + (reloc) ? 0 : map->reloc; + } + return 0; +} + static struct map *kernel_get_module_map(const char *module) { struct rb_node *nd; - struct map_groups *grp = &machine.kmaps; + struct map_groups *grp = &host_machine->kmaps; /* A file path -- this is an offline module */ if (module && strchr(module, '/')) - return machine__new_module(&machine, 0, module); + return machine__new_module(host_machine, 0, module); if (!module) module = "kernel"; @@ -141,7 +184,7 @@ static struct dso *kernel_get_module_dso(const char *module) const char *vmlinux_name; if (module) { - list_for_each_entry(dso, &machine.kernel_dsos, node) { + list_for_each_entry(dso, &host_machine->kernel_dsos, node) { if (strncmp(dso->short_name + 1, module, dso->short_name_len - 2) == 0) goto found; @@ -150,7 +193,7 @@ static struct dso *kernel_get_module_dso(const char *module) return NULL; } - map = machine.vmlinux_maps[MAP__FUNCTION]; + map = host_machine->vmlinux_maps[MAP__FUNCTION]; dso = map->dso; vmlinux_name = symbol_conf.vmlinux_name; @@ -173,20 +216,6 @@ const char *kernel_get_module_path(const char *module) return (dso) ? dso->long_name : NULL; } -static int init_user_exec(void) -{ - int ret = 0; - - symbol_conf.try_vmlinux_path = false; - symbol_conf.sort_by_name = true; - ret = symbol__init(); - - if (ret < 0) - pr_debug("Failed to init symbol map.\n"); - - return ret; -} - static int convert_exec_to_group(const char *exec, char **result) { char *ptr1, *ptr2, *exec_copy; @@ -218,32 +247,23 @@ out: return ret; } -static int convert_to_perf_probe_point(struct probe_trace_point *tp, - struct perf_probe_point *pp) +static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) { - pp->function = strdup(tp->symbol); - - if (pp->function == NULL) - return -ENOMEM; - - pp->offset = tp->offset; - pp->retprobe = tp->retprobe; + int i; - return 0; + for (i = 0; i < ntevs; i++) + clear_probe_trace_event(tevs + i); } #ifdef HAVE_DWARF_SUPPORT + /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module) { - const char *path; + const char *path = module; - /* A file path -- this is an offline module */ - if (module && strchr(module, '/')) - path = module; - else { + if (!module || !strchr(module, '/')) { path = kernel_get_module_path(module); - if (!path) { pr_err("Failed to find path of %s module.\n", module ?: "kernel"); @@ -253,46 +273,6 @@ static struct debuginfo *open_debuginfo(const char *module) return debuginfo__new(path); } -/* - * Convert trace point to probe point with debuginfo - * Currently only handles kprobes. - */ -static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, - struct perf_probe_point *pp) -{ - struct symbol *sym; - struct map *map; - u64 addr; - int ret = -ENOENT; - struct debuginfo *dinfo; - - sym = __find_kernel_function_by_name(tp->symbol, &map); - if (sym) { - addr = map->unmap_ip(map, sym->start + tp->offset); - pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol, - tp->offset, addr); - - dinfo = debuginfo__new_online_kernel(addr); - if (dinfo) { - ret = debuginfo__find_probe_point(dinfo, - (unsigned long)addr, pp); - debuginfo__delete(dinfo); - } else { - pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", - addr); - ret = -ENOENT; - } - } - if (ret <= 0) { - pr_debug("Failed to find corresponding probes from " - "debuginfo. Use kprobe event information.\n"); - return convert_to_perf_probe_point(tp, pp); - } - pp->retprobe = tp->retprobe; - - return 0; -} - static int get_text_start_address(const char *exec, unsigned long *address) { Elf *elf; @@ -321,12 +301,62 @@ out: return ret; } +/* + * Convert trace point to probe point with debuginfo + */ +static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + struct debuginfo *dinfo = NULL; + unsigned long stext = 0; + u64 addr = tp->address; + int ret = -ENOENT; + + /* convert the address to dwarf address */ + if (!is_kprobe) { + if (!addr) { + ret = -EINVAL; + goto error; + } + ret = get_text_start_address(tp->module, &stext); + if (ret < 0) + goto error; + addr += stext; + } else { + addr = kernel_get_symbol_address_by_name(tp->symbol, false); + if (addr == 0) + goto error; + addr += tp->offset; + } + + pr_debug("try to find information at %" PRIx64 " in %s\n", addr, + tp->module ? : "kernel"); + + dinfo = open_debuginfo(tp->module); + if (dinfo) { + ret = debuginfo__find_probe_point(dinfo, + (unsigned long)addr, pp); + debuginfo__delete(dinfo); + } else { + pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr); + ret = -ENOENT; + } + + if (ret > 0) { + pp->retprobe = tp->retprobe; + return 0; + } +error: + pr_debug("Failed to find corresponding probes from debuginfo.\n"); + return ret ? : -ENOENT; +} + static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, int ntevs, const char *exec) { int i, ret = 0; - unsigned long offset, stext = 0; - char buf[32]; + unsigned long stext = 0; if (!exec) return 0; @@ -337,15 +367,9 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, for (i = 0; i < ntevs && ret >= 0; i++) { /* point.address is the addres of point.symbol + point.offset */ - offset = tevs[i].point.address - stext; - tevs[i].point.offset = 0; - zfree(&tevs[i].point.symbol); - ret = e_snprintf(buf, 32, "0x%lx", offset); - if (ret < 0) - break; + tevs[i].point.address -= stext; tevs[i].point.module = strdup(exec); - tevs[i].point.symbol = strdup(buf); - if (!tevs[i].point.symbol || !tevs[i].point.module) { + if (!tevs[i].point.module) { ret = -ENOMEM; break; } @@ -388,12 +412,40 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, return ret; } -static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) +/* Post processing the probe events */ +static int post_process_probe_trace_events(struct probe_trace_event *tevs, + int ntevs, const char *module, + bool uprobe) { + struct ref_reloc_sym *reloc_sym; + char *tmp; int i; - for (i = 0; i < ntevs; i++) - clear_probe_trace_event(tevs + i); + if (uprobe) + return add_exec_to_probe_trace_events(tevs, ntevs, module); + + /* Note that currently ref_reloc_sym based probe is not for drivers */ + if (module) + return add_module_to_probe_trace_events(tevs, ntevs, module); + + reloc_sym = kernel_get_ref_reloc_sym(); + if (!reloc_sym) { + pr_warning("Relocated base symbol is not found!\n"); + return -EINVAL; + } + + for (i = 0; i < ntevs; i++) { + if (tevs[i].point.address) { + tmp = strdup(reloc_sym->name); + if (!tmp) + return -ENOMEM; + free(tevs[i].point.symbol); + tevs[i].point.symbol = tmp; + tevs[i].point.offset = tevs[i].point.address - + reloc_sym->unrelocated_addr; + } + } + return 0; } /* Try to find perf_probe_event with debuginfo */ @@ -416,21 +468,16 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, return 0; } + pr_debug("Try to find probe point from debuginfo.\n"); /* Searching trace events corresponding to a probe event */ ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs); debuginfo__delete(dinfo); if (ntevs > 0) { /* Succeeded to find trace events */ - pr_debug("find %d probe_trace_events.\n", ntevs); - if (target) { - if (pev->uprobes) - ret = add_exec_to_probe_trace_events(*tevs, - ntevs, target); - else - ret = add_module_to_probe_trace_events(*tevs, - ntevs, target); - } + pr_debug("Found %d probe_trace_events.\n", ntevs); + ret = post_process_probe_trace_events(*tevs, ntevs, + target, pev->uprobes); if (ret < 0) { clear_probe_trace_events(*tevs, ntevs); zfree(tevs); @@ -563,20 +610,16 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num) * Show line-range always requires debuginfo to find source file and * line number. */ -int show_line_range(struct line_range *lr, const char *module) +static int __show_line_range(struct line_range *lr, const char *module) { int l = 1; - struct line_node *ln; + struct int_node *ln; struct debuginfo *dinfo; FILE *fp; int ret; char *tmp; /* Search a line range */ - ret = init_vmlinux(); - if (ret < 0) - return ret; - dinfo = open_debuginfo(module); if (!dinfo) { pr_warning("Failed to open debuginfo file.\n"); @@ -623,8 +666,8 @@ int show_line_range(struct line_range *lr, const char *module) goto end; } - list_for_each_entry(ln, &lr->line_list, list) { - for (; ln->line > l; l++) { + intlist__for_each(ln, lr->line_list) { + for (; ln->i > l; l++) { ret = show_one_line(fp, l - lr->offset); if (ret < 0) goto end; @@ -646,6 +689,19 @@ end: return ret; } +int show_line_range(struct line_range *lr, const char *module) +{ + int ret; + + ret = init_symbol_maps(false); + if (ret < 0) + return ret; + ret = __show_line_range(lr, module); + exit_symbol_maps(); + + return ret; +} + static int show_available_vars_at(struct debuginfo *dinfo, struct perf_probe_event *pev, int max_vls, struct strfilter *_filter, @@ -707,14 +763,15 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, int i, ret = 0; struct debuginfo *dinfo; - ret = init_vmlinux(); + ret = init_symbol_maps(false); if (ret < 0) return ret; dinfo = open_debuginfo(module); if (!dinfo) { pr_warning("Failed to open debuginfo file.\n"); - return -ENOENT; + ret = -ENOENT; + goto out; } setup_pager(); @@ -724,23 +781,19 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, externs); debuginfo__delete(dinfo); +out: + exit_symbol_maps(); return ret; } #else /* !HAVE_DWARF_SUPPORT */ -static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, - struct perf_probe_point *pp) +static int +find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused, + struct perf_probe_point *pp __maybe_unused, + bool is_kprobe __maybe_unused) { - struct symbol *sym; - - sym = __find_kernel_function_by_name(tp->symbol, NULL); - if (!sym) { - pr_err("Failed to find symbol %s in kernel.\n", tp->symbol); - return -ENOENT; - } - - return convert_to_perf_probe_point(tp, pp); + return -ENOSYS; } static int try_to_find_probe_trace_events(struct perf_probe_event *pev, @@ -776,24 +829,22 @@ int show_available_vars(struct perf_probe_event *pevs __maybe_unused, void line_range__clear(struct line_range *lr) { - struct line_node *ln; - free(lr->function); free(lr->file); free(lr->path); free(lr->comp_dir); - while (!list_empty(&lr->line_list)) { - ln = list_first_entry(&lr->line_list, struct line_node, list); - list_del(&ln->list); - free(ln); - } + intlist__delete(lr->line_list); memset(lr, 0, sizeof(*lr)); } -void line_range__init(struct line_range *lr) +int line_range__init(struct line_range *lr) { memset(lr, 0, sizeof(*lr)); - INIT_LIST_HEAD(&lr->line_list); + lr->line_list = intlist__new(NULL); + if (!lr->line_list) + return -ENOMEM; + else + return 0; } static int parse_line_num(char **ptr, int *val, const char *what) @@ -1267,16 +1318,21 @@ static int parse_probe_trace_command(const char *cmd, } else p = argv[1]; fmt1_str = strtok_r(p, "+", &fmt); - tp->symbol = strdup(fmt1_str); - if (tp->symbol == NULL) { - ret = -ENOMEM; - goto out; + if (fmt1_str[0] == '0') /* only the address started with 0x */ + tp->address = strtoul(fmt1_str, NULL, 0); + else { + /* Only the symbol-based probe has offset */ + tp->symbol = strdup(fmt1_str); + if (tp->symbol == NULL) { + ret = -ENOMEM; + goto out; + } + fmt2_str = strtok_r(NULL, "", &fmt); + if (fmt2_str == NULL) + tp->offset = 0; + else + tp->offset = strtoul(fmt2_str, NULL, 10); } - fmt2_str = strtok_r(NULL, "", &fmt); - if (fmt2_str == NULL) - tp->offset = 0; - else - tp->offset = strtoul(fmt2_str, NULL, 10); tev->nargs = argc - 2; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); @@ -1518,20 +1574,27 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev) if (buf == NULL) return NULL; + len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p', + tev->group, tev->event); + if (len <= 0) + goto error; + + /* Uprobes must have tp->address and tp->module */ + if (tev->uprobes && (!tp->address || !tp->module)) + goto error; + + /* Use the tp->address for uprobes */ if (tev->uprobes) - len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s:%s", - tp->retprobe ? 'r' : 'p', - tev->group, tev->event, - tp->module, tp->symbol); + ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx", + tp->module, tp->address); else - len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s%s%s+%lu", - tp->retprobe ? 'r' : 'p', - tev->group, tev->event, + ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu", tp->module ?: "", tp->module ? ":" : "", tp->symbol, tp->offset); - if (len <= 0) + if (ret <= 0) goto error; + len += ret; for (i = 0; i < tev->nargs; i++) { ret = synthesize_probe_trace_arg(&tev->args[i], buf + len, @@ -1547,6 +1610,79 @@ error: return NULL; } +static int find_perf_probe_point_from_map(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + struct symbol *sym = NULL; + struct map *map; + u64 addr; + int ret = -ENOENT; + + if (!is_kprobe) { + map = dso__new_map(tp->module); + if (!map) + goto out; + addr = tp->address; + sym = map__find_symbol(map, addr, NULL); + } else { + addr = kernel_get_symbol_address_by_name(tp->symbol, true); + if (addr) { + addr += tp->offset; + sym = __find_kernel_function(addr, &map); + } + } + if (!sym) + goto out; + + pp->retprobe = tp->retprobe; + pp->offset = addr - map->unmap_ip(map, sym->start); + pp->function = strdup(sym->name); + ret = pp->function ? 0 : -ENOMEM; + +out: + if (map && !is_kprobe) { + dso__delete(map->dso); + map__delete(map); + } + + return ret; +} + +static int convert_to_perf_probe_point(struct probe_trace_point *tp, + struct perf_probe_point *pp, + bool is_kprobe) +{ + char buf[128]; + int ret; + + ret = find_perf_probe_point_from_dwarf(tp, pp, is_kprobe); + if (!ret) + return 0; + ret = find_perf_probe_point_from_map(tp, pp, is_kprobe); + if (!ret) + return 0; + + pr_debug("Failed to find probe point from both of dwarf and map.\n"); + + if (tp->symbol) { + pp->function = strdup(tp->symbol); + pp->offset = tp->offset; + } else if (!tp->module && !is_kprobe) { + ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address); + if (ret < 0) + return ret; + pp->function = strdup(buf); + pp->offset = 0; + } + if (pp->function == NULL) + return -ENOMEM; + + pp->retprobe = tp->retprobe; + + return 0; +} + static int convert_to_perf_probe_event(struct probe_trace_event *tev, struct perf_probe_event *pev, bool is_kprobe) { @@ -1560,11 +1696,7 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev, return -ENOMEM; /* Convert trace_point to probe_point */ - if (is_kprobe) - ret = kprobe_convert_to_perf_probe(&tev->point, &pev->point); - else - ret = convert_to_perf_probe_point(&tev->point, &pev->point); - + ret = convert_to_perf_probe_point(&tev->point, &pev->point, is_kprobe); if (ret < 0) return ret; @@ -1731,7 +1863,8 @@ static struct strlist *get_probe_trace_command_rawlist(int fd) } /* Show an event */ -static int show_perf_probe_event(struct perf_probe_event *pev) +static int show_perf_probe_event(struct perf_probe_event *pev, + const char *module) { int i, ret; char buf[128]; @@ -1747,6 +1880,8 @@ static int show_perf_probe_event(struct perf_probe_event *pev) return ret; printf(" %-20s (on %s", buf, place); + if (module) + printf(" in %s", module); if (pev->nargs > 0) { printf(" with"); @@ -1784,7 +1919,8 @@ static int __show_perf_probe_events(int fd, bool is_kprobe) ret = convert_to_perf_probe_event(&tev, &pev, is_kprobe); if (ret >= 0) - ret = show_perf_probe_event(&pev); + ret = show_perf_probe_event(&pev, + tev.point.module); } clear_perf_probe_event(&pev); clear_probe_trace_event(&tev); @@ -1807,7 +1943,7 @@ int show_perf_probe_events(void) if (fd < 0) return fd; - ret = init_vmlinux(); + ret = init_symbol_maps(false); if (ret < 0) return ret; @@ -1820,6 +1956,7 @@ int show_perf_probe_events(void) close(fd); } + exit_symbol_maps(); return ret; } @@ -1982,7 +2119,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, group = pev->group; pev->event = tev->event; pev->group = tev->group; - show_perf_probe_event(pev); + show_perf_probe_event(pev, tev->point.module); /* Trick here - restore current event/group */ pev->event = (char *)event; pev->group = (char *)group; @@ -2008,113 +2145,175 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, return ret; } -static int convert_to_probe_trace_events(struct perf_probe_event *pev, - struct probe_trace_event **tevs, - int max_tevs, const char *target) +static char *looking_function_name; +static int num_matched_functions; + +static int probe_function_filter(struct map *map __maybe_unused, + struct symbol *sym) { + if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && + strcmp(looking_function_name, sym->name) == 0) { + num_matched_functions++; + return 0; + } + return 1; +} + +#define strdup_or_goto(str, label) \ + ({ char *__p = strdup(str); if (!__p) goto label; __p; }) + +/* + * Find probe function addresses from map. + * Return an error or the number of found probe_trace_event + */ +static int find_probe_trace_events_from_map(struct perf_probe_event *pev, + struct probe_trace_event **tevs, + int max_tevs, const char *target) +{ + struct map *map = NULL; + struct kmap *kmap = NULL; + struct ref_reloc_sym *reloc_sym = NULL; struct symbol *sym; - int ret, i; + struct rb_node *nd; struct probe_trace_event *tev; + struct perf_probe_point *pp = &pev->point; + struct probe_trace_point *tp; + int ret, i; - if (pev->uprobes && !pev->group) { - /* Replace group name if not given */ - ret = convert_exec_to_group(target, &pev->group); - if (ret != 0) { - pr_warning("Failed to make a group name.\n"); - return ret; - } + /* Init maps of given executable or kernel */ + if (pev->uprobes) + map = dso__new_map(target); + else + map = kernel_get_module_map(target); + if (!map) { + ret = -EINVAL; + goto out; } - /* Convert perf_probe_event with debuginfo */ - ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target); - if (ret != 0) - return ret; /* Found in debuginfo or got an error */ - - if (pev->uprobes) { - ret = convert_name_to_addr(pev, target); - if (ret < 0) - return ret; + /* + * Load matched symbols: Since the different local symbols may have + * same name but different addresses, this lists all the symbols. + */ + num_matched_functions = 0; + looking_function_name = pp->function; + ret = map__load(map, probe_function_filter); + if (ret || num_matched_functions == 0) { + pr_err("Failed to find symbol %s in %s\n", pp->function, + target ? : "kernel"); + ret = -ENOENT; + goto out; + } else if (num_matched_functions > max_tevs) { + pr_err("Too many functions matched in %s\n", + target ? : "kernel"); + ret = -E2BIG; + goto out; } - /* Allocate trace event buffer */ - tev = *tevs = zalloc(sizeof(struct probe_trace_event)); - if (tev == NULL) - return -ENOMEM; + if (!pev->uprobes) { + kmap = map__kmap(map); + reloc_sym = kmap->ref_reloc_sym; + if (!reloc_sym) { + pr_warning("Relocated base symbol is not found!\n"); + ret = -EINVAL; + goto out; + } + } - /* Copy parameters */ - tev->point.symbol = strdup(pev->point.function); - if (tev->point.symbol == NULL) { + /* Setup result trace-probe-events */ + *tevs = zalloc(sizeof(*tev) * num_matched_functions); + if (!*tevs) { ret = -ENOMEM; - goto error; + goto out; } - if (target) { - tev->point.module = strdup(target); - if (tev->point.module == NULL) { - ret = -ENOMEM; - goto error; + ret = 0; + map__for_each_symbol(map, sym, nd) { + tev = (*tevs) + ret; + tp = &tev->point; + if (ret == num_matched_functions) { + pr_warning("Too many symbols are listed. Skip it.\n"); + break; } - } - - tev->point.offset = pev->point.offset; - tev->point.retprobe = pev->point.retprobe; - tev->nargs = pev->nargs; - tev->uprobes = pev->uprobes; + ret++; - if (tev->nargs) { - tev->args = zalloc(sizeof(struct probe_trace_arg) - * tev->nargs); - if (tev->args == NULL) { - ret = -ENOMEM; - goto error; + if (pp->offset > sym->end - sym->start) { + pr_warning("Offset %ld is bigger than the size of %s\n", + pp->offset, sym->name); + ret = -ENOENT; + goto err_out; + } + /* Add one probe point */ + tp->address = map->unmap_ip(map, sym->start) + pp->offset; + if (reloc_sym) { + tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out); + tp->offset = tp->address - reloc_sym->addr; + } else { + tp->symbol = strdup_or_goto(sym->name, nomem_out); + tp->offset = pp->offset; + } + tp->retprobe = pp->retprobe; + if (target) + tev->point.module = strdup_or_goto(target, nomem_out); + tev->uprobes = pev->uprobes; + tev->nargs = pev->nargs; + if (tev->nargs) { + tev->args = zalloc(sizeof(struct probe_trace_arg) * + tev->nargs); + if (tev->args == NULL) + goto nomem_out; } for (i = 0; i < tev->nargs; i++) { - if (pev->args[i].name) { - tev->args[i].name = strdup(pev->args[i].name); - if (tev->args[i].name == NULL) { - ret = -ENOMEM; - goto error; - } - } - tev->args[i].value = strdup(pev->args[i].var); - if (tev->args[i].value == NULL) { - ret = -ENOMEM; - goto error; - } - if (pev->args[i].type) { - tev->args[i].type = strdup(pev->args[i].type); - if (tev->args[i].type == NULL) { - ret = -ENOMEM; - goto error; - } - } + if (pev->args[i].name) + tev->args[i].name = + strdup_or_goto(pev->args[i].name, + nomem_out); + + tev->args[i].value = strdup_or_goto(pev->args[i].var, + nomem_out); + if (pev->args[i].type) + tev->args[i].type = + strdup_or_goto(pev->args[i].type, + nomem_out); } } - if (pev->uprobes) - return 1; +out: + if (map && pev->uprobes) { + /* Only when using uprobe(exec) map needs to be released */ + dso__delete(map->dso); + map__delete(map); + } + return ret; - /* Currently just checking function name from symbol map */ - sym = __find_kernel_function_by_name(tev->point.symbol, NULL); - if (!sym) { - pr_warning("Kernel symbol \'%s\' not found.\n", - tev->point.symbol); - ret = -ENOENT; - goto error; - } else if (tev->point.offset > sym->end - sym->start) { - pr_warning("Offset specified is greater than size of %s\n", - tev->point.symbol); - ret = -ENOENT; - goto error; +nomem_out: + ret = -ENOMEM; +err_out: + clear_probe_trace_events(*tevs, num_matched_functions); + zfree(tevs); + goto out; +} + +static int convert_to_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event **tevs, + int max_tevs, const char *target) +{ + int ret; + if (pev->uprobes && !pev->group) { + /* Replace group name if not given */ + ret = convert_exec_to_group(target, &pev->group); + if (ret != 0) { + pr_warning("Failed to make a group name.\n"); + return ret; + } } - return 1; -error: - clear_probe_trace_event(tev); - free(tev); - *tevs = NULL; - return ret; + /* Convert perf_probe_event with debuginfo */ + ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target); + if (ret != 0) + return ret; /* Found in debuginfo or got an error */ + + return find_probe_trace_events_from_map(pev, tevs, max_tevs, target); } struct __event_package { @@ -2135,12 +2334,7 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, if (pkgs == NULL) return -ENOMEM; - if (!pevs->uprobes) - /* Init vmlinux path */ - ret = init_vmlinux(); - else - ret = init_user_exec(); - + ret = init_symbol_maps(pevs->uprobes); if (ret < 0) { free(pkgs); return ret; @@ -2174,6 +2368,7 @@ end: zfree(&pkgs[i].tevs); } free(pkgs); + exit_symbol_maps(); return ret; } @@ -2323,159 +2518,51 @@ static struct strfilter *available_func_filter; static int filter_available_functions(struct map *map __maybe_unused, struct symbol *sym) { - if (sym->binding == STB_GLOBAL && + if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) && strfilter__compare(available_func_filter, sym->name)) return 0; return 1; } -static int __show_available_funcs(struct map *map) -{ - if (map__load(map, filter_available_functions)) { - pr_err("Failed to load map.\n"); - return -EINVAL; - } - if (!dso__sorted_by_name(map->dso, map->type)) - dso__sort_by_name(map->dso, map->type); - - dso__fprintf_symbols_by_name(map->dso, map->type, stdout); - return 0; -} - -static int available_kernel_funcs(const char *module) +int show_available_funcs(const char *target, struct strfilter *_filter, + bool user) { struct map *map; int ret; - ret = init_vmlinux(); + ret = init_symbol_maps(user); if (ret < 0) return ret; - map = kernel_get_module_map(module); + /* Get a symbol map */ + if (user) + map = dso__new_map(target); + else + map = kernel_get_module_map(target); if (!map) { - pr_err("Failed to find %s map.\n", (module) ? : "kernel"); + pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); return -EINVAL; } - return __show_available_funcs(map); -} - -static int available_user_funcs(const char *target) -{ - struct map *map; - int ret; - - ret = init_user_exec(); - if (ret < 0) - return ret; - - map = dso__new_map(target); - ret = __show_available_funcs(map); - dso__delete(map->dso); - map__delete(map); - return ret; -} -int show_available_funcs(const char *target, struct strfilter *_filter, - bool user) -{ - setup_pager(); + /* Load symbols with given filter */ available_func_filter = _filter; - - if (!user) - return available_kernel_funcs(target); - - return available_user_funcs(target); -} - -/* - * uprobe_events only accepts address: - * Convert function and any offset to address - */ -static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec) -{ - struct perf_probe_point *pp = &pev->point; - struct symbol *sym; - struct map *map = NULL; - char *function = NULL; - int ret = -EINVAL; - unsigned long long vaddr = 0; - - if (!pp->function) { - pr_warning("No function specified for uprobes"); - goto out; - } - - function = strdup(pp->function); - if (!function) { - pr_warning("Failed to allocate memory by strdup.\n"); - ret = -ENOMEM; - goto out; - } - - map = dso__new_map(exec); - if (!map) { - pr_warning("Cannot find appropriate DSO for %s.\n", exec); - goto out; - } - available_func_filter = strfilter__new(function, NULL); if (map__load(map, filter_available_functions)) { - pr_err("Failed to load map.\n"); - goto out; - } - - sym = map__find_symbol_by_name(map, function, NULL); - if (!sym) { - pr_warning("Cannot find %s in DSO %s\n", function, exec); - goto out; - } - - if (map->start > sym->start) - vaddr = map->start; - vaddr += sym->start + pp->offset + map->pgoff; - pp->offset = 0; - - if (!pev->event) { - pev->event = function; - function = NULL; - } - if (!pev->group) { - char *ptr1, *ptr2, *exec_copy; - - pev->group = zalloc(sizeof(char *) * 64); - exec_copy = strdup(exec); - if (!exec_copy) { - ret = -ENOMEM; - pr_warning("Failed to copy exec string.\n"); - goto out; - } - - ptr1 = strdup(basename(exec_copy)); - if (ptr1) { - ptr2 = strpbrk(ptr1, "-._"); - if (ptr2) - *ptr2 = '\0'; - e_snprintf(pev->group, 64, "%s_%s", PERFPROBE_GROUP, - ptr1); - free(ptr1); - } - free(exec_copy); - } - free(pp->function); - pp->function = zalloc(sizeof(char *) * MAX_PROBE_ARGS); - if (!pp->function) { - ret = -ENOMEM; - pr_warning("Failed to allocate memory by zalloc.\n"); - goto out; + pr_err("Failed to load symbols in %s\n", (target) ? : "kernel"); + goto end; } - e_snprintf(pp->function, MAX_PROBE_ARGS, "0x%llx", vaddr); - ret = 0; + if (!dso__sorted_by_name(map->dso, map->type)) + dso__sort_by_name(map->dso, map->type); -out: - if (map) { + /* Show all (filtered) symbols */ + setup_pager(); + dso__fprintf_symbols_by_name(map->dso, map->type, stdout); +end: + if (user) { dso__delete(map->dso); map__delete(map); } - if (function) - free(function); + exit_symbol_maps(); + return ret; } + diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index fcaf7273e85a..776c9347a3b6 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -2,6 +2,7 @@ #define _PROBE_EVENT_H #include <stdbool.h> +#include "intlist.h" #include "strlist.h" #include "strfilter.h" @@ -76,13 +77,6 @@ struct perf_probe_event { struct perf_probe_arg *args; /* Arguments */ }; - -/* Line number container */ -struct line_node { - struct list_head list; - int line; -}; - /* Line range */ struct line_range { char *file; /* File name */ @@ -92,7 +86,7 @@ struct line_range { int offset; /* Start line offset */ char *path; /* Real path name */ char *comp_dir; /* Compile directory */ - struct list_head line_list; /* Visible lines */ + struct intlist *line_list; /* Visible lines */ }; /* List of variables */ @@ -124,7 +118,7 @@ extern int parse_line_range_desc(const char *cmd, struct line_range *lr); extern void line_range__clear(struct line_range *lr); /* Initialize line range */ -extern void line_range__init(struct line_range *lr); +extern int line_range__init(struct line_range *lr); /* Internal use: Return kernel/module path */ extern const char *kernel_get_module_path(const char *module); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 061edb162b5b..9d8eb26f0533 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -34,7 +34,9 @@ #include <linux/bitops.h> #include "event.h" +#include "dso.h" #include "debug.h" +#include "intlist.h" #include "util.h" #include "symbol.h" #include "probe-finder.h" @@ -42,65 +44,6 @@ /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 -/* Line number list operations */ - -/* Add a line to line number list */ -static int line_list__add_line(struct list_head *head, int line) -{ - struct line_node *ln; - struct list_head *p; - - /* Reverse search, because new line will be the last one */ - list_for_each_entry_reverse(ln, head, list) { - if (ln->line < line) { - p = &ln->list; - goto found; - } else if (ln->line == line) /* Already exist */ - return 1; - } - /* List is empty, or the smallest entry */ - p = head; -found: - pr_debug("line list: add a line %u\n", line); - ln = zalloc(sizeof(struct line_node)); - if (ln == NULL) - return -ENOMEM; - ln->line = line; - INIT_LIST_HEAD(&ln->list); - list_add(&ln->list, p); - return 0; -} - -/* Check if the line in line number list */ -static int line_list__has_line(struct list_head *head, int line) -{ - struct line_node *ln; - - /* Reverse search, because new line will be the last one */ - list_for_each_entry(ln, head, list) - if (ln->line == line) - return 1; - - return 0; -} - -/* Init line number list */ -static void line_list__init(struct list_head *head) -{ - INIT_LIST_HEAD(head); -} - -/* Free line number list */ -static void line_list__free(struct list_head *head) -{ - struct line_node *ln; - while (!list_empty(head)) { - ln = list_first_entry(head, struct line_node, list); - list_del(&ln->list); - free(ln); - } -} - /* Dwarf FL wrappers */ static char *debuginfo_path; /* Currently dummy */ @@ -147,80 +90,7 @@ error: return -ENOENT; } -#if _ELFUTILS_PREREQ(0, 148) -/* This method is buggy if elfutils is older than 0.148 */ -static int __linux_kernel_find_elf(Dwfl_Module *mod, - void **userdata, - const char *module_name, - Dwarf_Addr base, - char **file_name, Elf **elfp) -{ - int fd; - const char *path = kernel_get_module_path(module_name); - - pr_debug2("Use file %s for %s\n", path, module_name); - if (path) { - fd = open(path, O_RDONLY); - if (fd >= 0) { - *file_name = strdup(path); - return fd; - } - } - /* If failed, try to call standard method */ - return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base, - file_name, elfp); -} - -static const Dwfl_Callbacks kernel_callbacks = { - .find_debuginfo = dwfl_standard_find_debuginfo, - .debuginfo_path = &debuginfo_path, - - .find_elf = __linux_kernel_find_elf, - .section_address = dwfl_linux_kernel_module_section_address, -}; - -/* Get a Dwarf from live kernel image */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, - Dwarf_Addr addr) -{ - dbg->dwfl = dwfl_begin(&kernel_callbacks); - if (!dbg->dwfl) - return -EINVAL; - - /* Load the kernel dwarves: Don't care the result here */ - dwfl_linux_kernel_report_kernel(dbg->dwfl); - dwfl_linux_kernel_report_modules(dbg->dwfl); - - dbg->dbg = dwfl_addrdwarf(dbg->dwfl, addr, &dbg->bias); - /* Here, check whether we could get a real dwarf */ - if (!dbg->dbg) { - pr_debug("Failed to find kernel dwarf at %lx\n", - (unsigned long)addr); - dwfl_end(dbg->dwfl); - memset(dbg, 0, sizeof(*dbg)); - return -ENOENT; - } - - return 0; -} -#else -/* With older elfutils, this just support kernel module... */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, - Dwarf_Addr addr __maybe_unused) -{ - const char *path = kernel_get_module_path("kernel"); - - if (!path) { - pr_err("Failed to find vmlinux path\n"); - return -ENOENT; - } - - pr_debug2("Use file %s for debuginfo\n", path); - return debuginfo__init_offline_dwarf(dbg, path); -} -#endif - -struct debuginfo *debuginfo__new(const char *path) +static struct debuginfo *__debuginfo__new(const char *path) { struct debuginfo *dbg = zalloc(sizeof(*dbg)); if (!dbg) @@ -228,21 +98,44 @@ struct debuginfo *debuginfo__new(const char *path) if (debuginfo__init_offline_dwarf(dbg, path) < 0) zfree(&dbg); - + if (dbg) + pr_debug("Open Debuginfo file: %s\n", path); return dbg; } -struct debuginfo *debuginfo__new_online_kernel(unsigned long addr) -{ - struct debuginfo *dbg = zalloc(sizeof(*dbg)); +enum dso_binary_type distro_dwarf_types[] = { + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__NOT_FOUND, +}; - if (!dbg) - return NULL; +struct debuginfo *debuginfo__new(const char *path) +{ + enum dso_binary_type *type; + char buf[PATH_MAX], nil = '\0'; + struct dso *dso; + struct debuginfo *dinfo = NULL; + + /* Try to open distro debuginfo files */ + dso = dso__new(path); + if (!dso) + goto out; - if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0) - zfree(&dbg); + for (type = distro_dwarf_types; + !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND; + type++) { + if (dso__read_binary_type_filename(dso, *type, &nil, + buf, PATH_MAX) < 0) + continue; + dinfo = __debuginfo__new(buf); + } + dso__delete(dso); - return dbg; +out: + /* if failed to open all distro debuginfo, open given binary */ + return dinfo ? : __debuginfo__new(path); } void debuginfo__delete(struct debuginfo *dbg) @@ -618,12 +511,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops, &pf->sp_die, pf->tvar); - if (ret == -ENOENT) + if (ret == -ENOENT || ret == -EINVAL) pr_err("Failed to find the location of %s at this address.\n" " Perhaps, it has been optimized out.\n", pf->pvar->var); else if (ret == -ENOTSUP) pr_err("Sorry, we don't support this variable location yet.\n"); - else if (pf->pvar->field) { + else if (ret == 0 && pf->pvar->field) { ret = convert_variable_fields(vr_die, pf->pvar->var, pf->pvar->field, &pf->tvar->ref, &die_mem); @@ -880,7 +773,7 @@ static int find_probe_point_by_line(struct probe_finder *pf) } /* Find lines which match lazy pattern */ -static int find_lazy_match_lines(struct list_head *head, +static int find_lazy_match_lines(struct intlist *list, const char *fname, const char *pat) { FILE *fp; @@ -901,7 +794,7 @@ static int find_lazy_match_lines(struct list_head *head, line[len - 1] = '\0'; if (strlazymatch(line, pat)) { - line_list__add_line(head, linenum); + intlist__add(list, linenum); count++; } linenum++; @@ -924,7 +817,7 @@ static int probe_point_lazy_walker(const char *fname, int lineno, Dwarf_Die *sc_die, die_mem; int ret; - if (!line_list__has_line(&pf->lcache, lineno) || + if (!intlist__has_entry(pf->lcache, lineno) || strtailcmp(fname, pf->fname) != 0) return 0; @@ -952,9 +845,9 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) { int ret = 0; - if (list_empty(&pf->lcache)) { + if (intlist__empty(pf->lcache)) { /* Matching lazy line pattern */ - ret = find_lazy_match_lines(&pf->lcache, pf->fname, + ret = find_lazy_match_lines(pf->lcache, pf->fname, pf->pev->point.lazy_line); if (ret <= 0) return ret; @@ -1092,11 +985,13 @@ static int debuginfo__find_probes(struct debuginfo *dbg, #if _ELFUTILS_PREREQ(0, 142) /* Get the call frame information from this dwarf */ - pf->cfi = dwarf_getcfi(dbg->dbg); + pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg)); #endif off = 0; - line_list__init(&pf->lcache); + pf->lcache = intlist__new(NULL); + if (!pf->lcache) + return -ENOMEM; /* Fastpath: lookup by function name from .debug_pubnames section */ if (pp->function) { @@ -1149,7 +1044,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg, } found: - line_list__free(&pf->lcache); + intlist__delete(pf->lcache); + pf->lcache = NULL; return ret; } @@ -1537,7 +1433,7 @@ static int line_range_add_line(const char *src, unsigned int lineno, if (lr->path == NULL) return -ENOMEM; } - return line_list__add_line(&lr->line_list, lineno); + return intlist__add(lr->line_list, lineno); } static int line_range_walk_cb(const char *fname, int lineno, @@ -1545,13 +1441,15 @@ static int line_range_walk_cb(const char *fname, int lineno, void *data) { struct line_finder *lf = data; + int err; if ((strtailcmp(fname, lf->fname) != 0) || (lf->lno_s > lineno || lf->lno_e < lineno)) return 0; - if (line_range_add_line(fname, lineno, lf->lr) < 0) - return -EINVAL; + err = line_range_add_line(fname, lineno, lf->lr); + if (err < 0 && err != -EEXIST) + return err; return 0; } @@ -1565,7 +1463,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) /* Update status */ if (ret >= 0) - if (!list_empty(&lf->lr->line_list)) + if (!intlist__empty(lf->lr->line_list)) ret = lf->found = 1; else ret = 0; /* Lines are not found */ @@ -1577,14 +1475,15 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) static int line_range_inline_cb(Dwarf_Die *in_die, void *data) { - find_line_range_by_line(in_die, data); + int ret = find_line_range_by_line(in_die, data); /* * We have to check all instances of inlined function, because * some execution paths can be optimized out depends on the - * function argument of instances + * function argument of instances. However, if an error occurs, + * it should be handled by the caller. */ - return 0; + return ret < 0 ? ret : 0; } /* Search function definition from function name */ diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index ffc33cdd25cc..92590b2c7e1c 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -3,6 +3,7 @@ #include <stdbool.h> #include "util.h" +#include "intlist.h" #include "probe-event.h" #define MAX_PROBE_BUFFER 1024 @@ -29,8 +30,8 @@ struct debuginfo { Dwarf_Addr bias; }; +/* This also tries to open distro debuginfo */ extern struct debuginfo *debuginfo__new(const char *path); -extern struct debuginfo *debuginfo__new_online_kernel(unsigned long addr); extern void debuginfo__delete(struct debuginfo *dbg); /* Find probe_trace_events specified by perf_probe_event from debuginfo */ @@ -66,7 +67,7 @@ struct probe_finder { const char *fname; /* Real file name */ Dwarf_Die cu_die; /* Current CU */ Dwarf_Die sp_die; - struct list_head lcache; /* Line cache for lazy match */ + struct intlist *lcache; /* Line cache for lazy match */ /* For variable searching */ #if _ELFUTILS_PREREQ(0, 142) diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 595bfc73d2ed..16a475a7d492 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -17,6 +17,6 @@ util/xyarray.c util/cgroup.c util/rblist.c util/strlist.c -util/fs.c +../lib/api/fs/fs.c util/trace-event.c ../../lib/rbtree.c diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 373762501dad..049e0a09ccd3 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -2,7 +2,7 @@ #include "evsel.h" #include "cpumap.h" #include "parse-events.h" -#include "fs.h" +#include <api/fs/fs.h> #include "util.h" typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5da6ce74c676..64a186edc7be 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -702,11 +702,12 @@ static void regs_dump__printf(u64 mask, u64 *regs) } } -static void regs_user__printf(struct perf_sample *sample, u64 mask) +static void regs_user__printf(struct perf_sample *sample) { struct regs_dump *user_regs = &sample->user_regs; if (user_regs->regs) { + u64 mask = user_regs->mask; printf("... user regs: mask 0x%" PRIx64 "\n", mask); regs_dump__printf(mask, user_regs->regs); } @@ -793,7 +794,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (!dump_trace) return; - printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", + printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", event->header.misc, sample->pid, sample->tid, sample->ip, sample->period, sample->addr); @@ -806,7 +807,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, branch_stack__printf(sample); if (sample_type & PERF_SAMPLE_REGS_USER) - regs_user__printf(sample, evsel->attr.sample_regs_user); + regs_user__printf(sample); if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); @@ -1624,13 +1625,14 @@ out_delete_map: void perf_session__fprintf_info(struct perf_session *session, FILE *fp, bool full) { - int fd = perf_data_file__fd(session->file); struct stat st; - int ret; + int fd, ret; if (session == NULL || fp == NULL) return; + fd = perf_data_file__fd(session->file); + ret = fstat(fd, &st); if (ret == -1) return; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 635cd8f8b22e..901b9bece2ee 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2,12 +2,18 @@ #include "hist.h" #include "comm.h" #include "symbol.h" +#include "evsel.h" regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char default_sort_order[] = "comm,dso,symbol"; -const char *sort_order = default_sort_order; +const char default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to"; +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; +const char default_top_sort_order[] = "dso,symbol"; +const char default_diff_sort_order[] = "dso,symbol"; +const char *sort_order; +const char *field_order; regex_t ignore_callees_regex; int have_ignore_callees = 0; int sort__need_collapse = 0; @@ -16,9 +22,6 @@ int sort__has_sym = 0; int sort__has_dso = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; -enum sort_type sort__first_dimension; - -LIST_HEAD(hist_entry__sort_list); static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) { @@ -93,6 +96,12 @@ sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) return comm__str(right->comm) - comm__str(left->comm); } +static int64_t +sort__comm_sort(struct hist_entry *left, struct hist_entry *right) +{ + return strcmp(comm__str(right->comm), comm__str(left->comm)); +} + static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { @@ -103,6 +112,7 @@ struct sort_entry sort_comm = { .se_header = "Command", .se_cmp = sort__comm_cmp, .se_collapse = sort__comm_collapse, + .se_sort = sort__comm_sort, .se_snprintf = hist_entry__comm_snprintf, .se_width_idx = HISTC_COMM, }; @@ -116,7 +126,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) const char *dso_name_l, *dso_name_r; if (!dso_l || !dso_r) - return cmp_null(dso_l, dso_r); + return cmp_null(dso_r, dso_l); if (verbose) { dso_name_l = dso_l->long_name; @@ -132,7 +142,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) static int64_t sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) { - return _sort__dso_cmp(left->ms.map, right->ms.map); + return _sort__dso_cmp(right->ms.map, left->ms.map); } static int _hist_entry__dso_snprintf(struct map *map, char *bf, @@ -204,6 +214,15 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) return _sort__sym_cmp(left->ms.sym, right->ms.sym); } +static int64_t +sort__sym_sort(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->ms.sym || !right->ms.sym) + return cmp_null(left->ms.sym, right->ms.sym); + + return strcmp(right->ms.sym->name, left->ms.sym->name); +} + static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, u64 ip, char level, char *bf, size_t size, unsigned int width) @@ -250,6 +269,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, struct sort_entry sort_sym = { .se_header = "Symbol", .se_cmp = sort__sym_cmp, + .se_sort = sort__sym_sort, .se_snprintf = hist_entry__sym_snprintf, .se_width_idx = HISTC_SYMBOL, }; @@ -277,7 +297,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) map__rip_2objdump(map, right->ip)); } } - return strcmp(left->srcline, right->srcline); + return strcmp(right->srcline, left->srcline); } static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, @@ -305,7 +325,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) if (!sym_l || !sym_r) return cmp_null(sym_l, sym_r); - return strcmp(sym_l->name, sym_r->name); + return strcmp(sym_r->name, sym_l->name); } static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf, @@ -1027,19 +1047,192 @@ static struct sort_dimension memory_sort_dimensions[] = { #undef DIM -static void __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx) +struct hpp_dimension { + const char *name; + struct perf_hpp_fmt *fmt; + int taken; +}; + +#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], } + +static struct hpp_dimension hpp_sort_dimensions[] = { + DIM(PERF_HPP__OVERHEAD, "overhead"), + DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"), + DIM(PERF_HPP__OVERHEAD_US, "overhead_us"), + DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"), + DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"), + DIM(PERF_HPP__SAMPLES, "sample"), + DIM(PERF_HPP__PERIOD, "period"), +}; + +#undef DIM + +struct hpp_sort_entry { + struct perf_hpp_fmt hpp; + struct sort_entry *se; +}; + +bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) { - if (sd->taken) + struct hpp_sort_entry *hse_a; + struct hpp_sort_entry *hse_b; + + if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b)) + return false; + + hse_a = container_of(a, struct hpp_sort_entry, hpp); + hse_b = container_of(b, struct hpp_sort_entry, hpp); + + return hse_a->se == hse_b->se; +} + +void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) +{ + struct hpp_sort_entry *hse; + + if (!perf_hpp__is_sort_entry(fmt)) return; + hse = container_of(fmt, struct hpp_sort_entry, hpp); + hists__new_col_len(hists, hse->se->se_width_idx, + strlen(hse->se->se_header)); +} + +static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel) +{ + struct hpp_sort_entry *hse; + size_t len; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + len = hists__col_len(&evsel->hists, hse->se->se_width_idx); + + return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header); +} + +static int __sort__hpp_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel) +{ + struct hpp_sort_entry *hse; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + + return hists__col_len(&evsel->hists, hse->se->se_width_idx); +} + +static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct hpp_sort_entry *hse; + size_t len; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + len = hists__col_len(he->hists, hse->se->se_width_idx); + + return hse->se->se_snprintf(he, hpp->buf, hpp->size, len); +} + +static struct hpp_sort_entry * +__sort_dimension__alloc_hpp(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse; + + hse = malloc(sizeof(*hse)); + if (hse == NULL) { + pr_err("Memory allocation failed\n"); + return NULL; + } + + hse->se = sd->entry; + hse->hpp.header = __sort__hpp_header; + hse->hpp.width = __sort__hpp_width; + hse->hpp.entry = __sort__hpp_entry; + hse->hpp.color = NULL; + + hse->hpp.cmp = sd->entry->se_cmp; + hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp; + hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse; + + INIT_LIST_HEAD(&hse->hpp.list); + INIT_LIST_HEAD(&hse->hpp.sort_list); + + return hse; +} + +bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format) +{ + return format->header == __sort__hpp_header; +} + +static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + + if (hse == NULL) + return -1; + + perf_hpp__register_sort_field(&hse->hpp); + return 0; +} + +static int __sort_dimension__add_hpp_output(struct sort_dimension *sd) +{ + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd); + + if (hse == NULL) + return -1; + + perf_hpp__column_register(&hse->hpp); + return 0; +} + +static int __sort_dimension__add(struct sort_dimension *sd) +{ + if (sd->taken) + return 0; + + if (__sort_dimension__add_hpp_sort(sd) < 0) + return -1; + if (sd->entry->se_collapse) sort__need_collapse = 1; - if (list_empty(&hist_entry__sort_list)) - sort__first_dimension = idx; + sd->taken = 1; + + return 0; +} + +static int __hpp_dimension__add(struct hpp_dimension *hd) +{ + if (!hd->taken) { + hd->taken = 1; + + perf_hpp__register_sort_field(hd->fmt); + } + return 0; +} + +static int __sort_dimension__add_output(struct sort_dimension *sd) +{ + if (sd->taken) + return 0; + + if (__sort_dimension__add_hpp_output(sd) < 0) + return -1; - list_add_tail(&sd->entry->list, &hist_entry__sort_list); sd->taken = 1; + return 0; +} + +static int __hpp_dimension__add_output(struct hpp_dimension *hd) +{ + if (!hd->taken) { + hd->taken = 1; + + perf_hpp__column_register(hd->fmt); + } + return 0; } int sort_dimension__add(const char *tok) @@ -1068,8 +1261,16 @@ int sort_dimension__add(const char *tok) sort__has_dso = 1; } - __sort_dimension__add(sd, i); - return 0; + return __sort_dimension__add(sd); + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (strncasecmp(tok, hd->name, strlen(tok))) + continue; + + return __hpp_dimension__add(hd); } for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { @@ -1084,7 +1285,7 @@ int sort_dimension__add(const char *tok) if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) sort__has_sym = 1; - __sort_dimension__add(sd, i + __SORT_BRANCH_STACK); + __sort_dimension__add(sd); return 0; } @@ -1100,18 +1301,47 @@ int sort_dimension__add(const char *tok) if (sd->entry == &sort_mem_daddr_sym) sort__has_sym = 1; - __sort_dimension__add(sd, i + __SORT_MEMORY_MODE); + __sort_dimension__add(sd); return 0; } return -ESRCH; } -int setup_sorting(void) +static const char *get_default_sort_order(void) { - char *tmp, *tok, *str = strdup(sort_order); + const char *default_sort_orders[] = { + default_sort_order, + default_branch_sort_order, + default_mem_sort_order, + default_top_sort_order, + default_diff_sort_order, + }; + + BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); + + return default_sort_orders[sort__mode]; +} + +static int __setup_sorting(void) +{ + char *tmp, *tok, *str; + const char *sort_keys = sort_order; int ret = 0; + if (sort_keys == NULL) { + if (field_order) { + /* + * If user specified field order but no sort order, + * we'll honor it and not add default sort orders. + */ + return 0; + } + + sort_keys = get_default_sort_order(); + } + + str = strdup(sort_keys); if (str == NULL) { error("Not enough memory to setup sort keys"); return -ENOMEM; @@ -1133,6 +1363,17 @@ int setup_sorting(void) return ret; } +bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +{ + if (perf_hpp__is_sort_entry(format)) { + struct hpp_sort_entry *hse; + + hse = container_of(format, struct hpp_sort_entry, hpp); + return hse->se->elide; + } + return false; +} + static void sort_entry__setup_elide(struct sort_entry *se, struct strlist *list, const char *list_name, FILE *fp) @@ -1147,7 +1388,8 @@ static void sort_entry__setup_elide(struct sort_entry *se, void sort__setup_elide(FILE *output) { - struct sort_entry *se; + struct perf_hpp_fmt *fmt; + struct hpp_sort_entry *hse; sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", output); @@ -1188,11 +1430,157 @@ void sort__setup_elide(FILE *output) * It makes no sense to elide all of sort entries. * Just revert them to show up again. */ - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (!se->elide) + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + if (!hse->se->elide) return; } - list_for_each_entry(se, &hist_entry__sort_list, list) - se->elide = false; + perf_hpp__for_each_format(fmt) { + if (!perf_hpp__is_sort_entry(fmt)) + continue; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + hse->se->elide = false; + } +} + +static int output_field_add(char *tok) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (strncasecmp(tok, hd->name, strlen(tok))) + continue; + + return __hpp_dimension__add_output(hd); + } + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { + struct sort_dimension *sd = &bstack_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { + struct sort_dimension *sd = &memory_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + return __sort_dimension__add_output(sd); + } + + return -ESRCH; +} + +static void reset_dimensions(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) + common_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) + hpp_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) + bstack_sort_dimensions[i].taken = 0; + + for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) + memory_sort_dimensions[i].taken = 0; +} + +static int __setup_output_field(void) +{ + char *tmp, *tok, *str; + int ret = 0; + + if (field_order == NULL) + return 0; + + reset_dimensions(); + + str = strdup(field_order); + if (str == NULL) { + error("Not enough memory to setup output fields"); + return -ENOMEM; + } + + for (tok = strtok_r(str, ", ", &tmp); + tok; tok = strtok_r(NULL, ", ", &tmp)) { + ret = output_field_add(tok); + if (ret == -EINVAL) { + error("Invalid --fields key: `%s'", tok); + break; + } else if (ret == -ESRCH) { + error("Unknown --fields key: `%s'", tok); + break; + } + } + + free(str); + return ret; +} + +int setup_sorting(void) +{ + int err; + + err = __setup_sorting(); + if (err < 0) + return err; + + if (parent_pattern != default_parent_pattern) { + err = sort_dimension__add("parent"); + if (err < 0) + return err; + } + + reset_dimensions(); + + /* + * perf diff doesn't use default hpp output fields. + */ + if (sort__mode != SORT_MODE__DIFF) + perf_hpp__init(); + + err = __setup_output_field(); + if (err < 0) + return err; + + /* copy sort keys to output fields */ + perf_hpp__setup_output_field(); + /* and then copy output fields to sort keys */ + perf_hpp__append_sort_keys(); + + return 0; +} + +void reset_output_field(void) +{ + sort__need_collapse = 0; + sort__has_parent = 0; + sort__has_sym = 0; + sort__has_dso = 0; + + reset_dimensions(); + perf_hpp__reset_output_field(); } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 43e5ff42a609..5f38d925e92f 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -25,6 +25,7 @@ extern regex_t parent_regex; extern const char *sort_order; +extern const char *field_order; extern const char default_parent_pattern[]; extern const char *parent_pattern; extern const char default_sort_order[]; @@ -133,6 +134,8 @@ enum sort_mode { SORT_MODE__NORMAL, SORT_MODE__BRANCH, SORT_MODE__MEMORY, + SORT_MODE__TOP, + SORT_MODE__DIFF, }; enum sort_type { @@ -179,6 +182,7 @@ struct sort_entry { int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *); int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *); + int64_t (*se_sort)(struct hist_entry *, struct hist_entry *); int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); u8 se_width_idx; @@ -189,6 +193,8 @@ extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; int setup_sorting(void); +int setup_output_field(void); +void reset_output_field(void); extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index ae8ccd7227cf..5667fc3e39cf 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -1,7 +1,7 @@ #ifndef __PERF_STATS_H #define __PERF_STATS_H -#include "types.h" +#include <linux/types.h> struct stats { diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 43262b83c541..6a0a13d07a28 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -17,7 +17,7 @@ #include <stdlib.h> #include <unistd.h> #include <string.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include "perf.h" #include "svghelper.h" diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h index f7b4d6e699ea..e3aff5332e30 100644 --- a/tools/perf/util/svghelper.h +++ b/tools/perf/util/svghelper.h @@ -1,7 +1,7 @@ #ifndef __PERF_SVGHELPER_H #define __PERF_SVGHELPER_H -#include "types.h" +#include <linux/types.h> extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end); extern void svg_box(int Yslot, u64 start, u64 end, const char *type); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 516d19fb999b..6864661a79dd 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -6,6 +6,7 @@ #include <inttypes.h> #include "symbol.h" +#include "vdso.h" #include <symbol/kallsyms.h> #include "debug.h" @@ -506,6 +507,8 @@ int filename__read_debuglink(const char *filename, char *debuglink, /* the start of this section is a zero-terminated string */ strncpy(debuglink, data->d_buf, size); + err = 0; + out_elf_end: elf_end(elf); out_close: @@ -616,6 +619,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, GElf_Shdr shdr; ss->adjust_symbols = (ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL || + is_vdso_map(dso->short_name) || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", NULL) != NULL); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e89afc097d8a..95e249779931 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -410,7 +410,7 @@ struct symbol *dso__find_symbol(struct dso *dso, return symbols__find(&dso->symbols[type], addr); } -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) { return symbols__first(&dso->symbols[type]); } @@ -1251,6 +1251,46 @@ out_failure: return -1; } +static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, + enum dso_binary_type type) +{ + switch (type) { + case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__DEBUGLINK: + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + return !kmod && dso->kernel == DSO_TYPE_USER; + + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__KCORE: + return dso->kernel == DSO_TYPE_KERNEL; + + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__GUEST_KCORE: + return dso->kernel == DSO_TYPE_GUEST_KERNEL; + + case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + /* + * kernel modules know their symtab type - it's set when + * creating a module dso in machine__new_module(). + */ + return kmod && dso->symtab_type == type; + + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + return true; + + case DSO_BINARY_TYPE__NOT_FOUND: + default: + return false; + } +} + int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) { char *name; @@ -1261,6 +1301,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) int ss_pos = 0; struct symsrc ss_[2]; struct symsrc *syms_ss = NULL, *runtime_ss = NULL; + bool kmod; dso__set_loaded(dso, map->type); @@ -1301,7 +1342,11 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (!name) return -1; - /* Iterate over candidate debug images. + kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; + + /* + * Iterate over candidate debug images. * Keep track of "interesting" ones (those which have a symtab, dynsym, * and/or opd section) for processing. */ @@ -1311,6 +1356,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) enum dso_binary_type symtab_type = binary_type_symtab[i]; + if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type)) + continue; + if (dso__read_binary_type_filename(dso, symtab_type, root_dir, name, PATH_MAX)) continue; @@ -1353,15 +1401,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (!runtime_ss && syms_ss) runtime_ss = syms_ss; - if (syms_ss) { - int km; - - km = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; - ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, km); - } else { + if (syms_ss) + ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod); + else ret = -1; - } if (ret > 0) { int nr_plt; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fffe2888a1c7..33ede53fa6b9 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -12,6 +12,7 @@ #include <byteswap.h> #include <libgen.h> #include "build-id.h" +#include "event.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -79,6 +80,17 @@ struct symbol { void symbol__delete(struct symbol *sym); void symbols__delete(struct rb_root *symbols); +/* symbols__for_each_entry - iterate over symbols (rb_root) + * + * @symbols: the rb_root of symbols + * @pos: the 'struct symbol *' to use as a loop cursor + * @nd: the 'struct rb_node *' to use as a temporary storage + */ +#define symbols__for_each_entry(symbols, pos, nd) \ + for (nd = rb_first(symbols); \ + nd && (pos = rb_entry(nd, struct symbol, rb_node)); \ + nd = rb_next(nd)) + static inline size_t symbol__size(const struct symbol *sym) { return sym->end - sym->start + 1; @@ -104,7 +116,8 @@ struct symbol_conf { annotate_asm_raw, annotate_src, event_group, - demangle; + demangle, + filter_relative; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -175,7 +188,7 @@ struct addr_location { struct symbol *sym; u64 addr; char level; - bool filtered; + u8 filtered; u8 cpumode; s32 cpu; }; @@ -223,7 +236,6 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr); struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name); -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0358882c8910..2fde0d5e40b5 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -8,6 +8,22 @@ #include "debug.h" #include "comm.h" +int thread__init_map_groups(struct thread *thread, struct machine *machine) +{ + struct thread *leader; + pid_t pid = thread->pid_; + + if (pid == thread->tid) { + thread->mg = map_groups__new(); + } else { + leader = machine__findnew_thread(machine, pid, pid); + if (leader) + thread->mg = map_groups__get(leader->mg); + } + + return thread->mg ? 0 : -1; +} + struct thread *thread__new(pid_t pid, pid_t tid) { char *comm_str; @@ -15,7 +31,6 @@ struct thread *thread__new(pid_t pid, pid_t tid) struct thread *thread = zalloc(sizeof(*thread)); if (thread != NULL) { - map_groups__init(&thread->mg); thread->pid_ = pid; thread->tid = tid; thread->ppid = -1; @@ -45,7 +60,8 @@ void thread__delete(struct thread *thread) { struct comm *comm, *tmp; - map_groups__exit(&thread->mg); + map_groups__put(thread->mg); + thread->mg = NULL; list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); @@ -111,18 +127,35 @@ int thread__comm_len(struct thread *thread) size_t thread__fprintf(struct thread *thread, FILE *fp) { return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + - map_groups__fprintf(&thread->mg, verbose, fp); + map_groups__fprintf(thread->mg, verbose, fp); } void thread__insert_map(struct thread *thread, struct map *map) { - map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr); - map_groups__insert(&thread->mg, map); + map_groups__fixup_overlappings(thread->mg, map, verbose, stderr); + map_groups__insert(thread->mg, map); +} + +static int thread__clone_map_groups(struct thread *thread, + struct thread *parent) +{ + int i; + + /* This is new thread, we share map groups for process. */ + if (thread->pid_ == parent->pid_) + return 0; + + /* But this one is new process, copy maps. */ + for (i = 0; i < MAP__NR_TYPES; ++i) + if (map_groups__clone(thread->mg, parent->mg, i) < 0) + return -ENOMEM; + + return 0; } int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) { - int i, err; + int err; if (parent->comm_set) { const char *comm = thread__comm_str(parent); @@ -134,11 +167,27 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) thread->comm_set = true; } - for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(&thread->mg, &parent->mg, i) < 0) - return -ENOMEM; - thread->ppid = parent->tid; + return thread__clone_map_groups(thread, parent); +} - return 0; +void thread__find_cpumode_addr_location(struct thread *thread, + struct machine *machine, + enum map_type type, u64 addr, + struct addr_location *al) +{ + size_t i; + const u8 const cpumodes[] = { + PERF_RECORD_MISC_USER, + PERF_RECORD_MISC_KERNEL, + PERF_RECORD_MISC_GUEST_USER, + PERF_RECORD_MISC_GUEST_KERNEL + }; + + for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { + thread__find_addr_location(thread, machine, cpumodes[i], type, + addr, al); + if (al->map) + break; + } } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 5b856bf942e1..3c0c2724f82c 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -13,7 +13,7 @@ struct thread { struct rb_node rb_node; struct list_head node; }; - struct map_groups mg; + struct map_groups *mg; pid_t pid_; /* Not all tools update this */ pid_t tid; pid_t ppid; @@ -30,6 +30,7 @@ struct machine; struct comm; struct thread *thread__new(pid_t pid, pid_t tid); +int thread__init_map_groups(struct thread *thread, struct machine *machine); void thread__delete(struct thread *thread); static inline void thread__exited(struct thread *thread) { @@ -44,12 +45,6 @@ void thread__insert_map(struct thread *thread, struct map *map); int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); -static inline struct map *thread__find_map(struct thread *thread, - enum map_type type, u64 addr) -{ - return thread ? map_groups__find(&thread->mg, type, addr) : NULL; -} - void thread__find_addr_map(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); @@ -58,6 +53,11 @@ void thread__find_addr_location(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); +void thread__find_cpumode_addr_location(struct thread *thread, + struct machine *machine, + enum map_type type, u64 addr, + struct addr_location *al); + static inline void *thread__priv(struct thread *thread) { return thread->priv; diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index dab14d0ad3d0..f92c37abb0a8 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -2,7 +2,7 @@ #define __PERF_TOP_H 1 #include "tool.h" -#include "types.h" +#include <linux/types.h> #include <stddef.h> #include <stdbool.h> #include <termios.h> diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index e0d6d07f6848..c36636fd825b 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -126,6 +126,7 @@ 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_destroy(&s); } void parse_proc_kallsyms(struct pevent *pevent, diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h deleted file mode 100644 index c51fa6b70a28..000000000000 --- a/tools/perf/util/types.h +++ /dev/null @@ -1,24 +0,0 @@ -#ifndef __PERF_TYPES_H -#define __PERF_TYPES_H - -#include <stdint.h> - -/* - * We define u64 as uint64_t for every architecture - * so that we can print it with "%"PRIx64 without getting warnings. - */ -typedef uint64_t u64; -typedef int64_t s64; -typedef unsigned int u32; -typedef signed int s32; -typedef unsigned short u16; -typedef signed short s16; -typedef unsigned char u8; -typedef signed char s8; - -union u64_swap { - u64 val64; - u32 val32[2]; -}; - -#endif /* __PERF_TYPES_H */ diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c new file mode 100644 index 000000000000..5ec80a575b50 --- /dev/null +++ b/tools/perf/util/unwind-libdw.c @@ -0,0 +1,210 @@ +#include <linux/compiler.h> +#include <elfutils/libdw.h> +#include <elfutils/libdwfl.h> +#include <inttypes.h> +#include <errno.h> +#include "unwind.h" +#include "unwind-libdw.h" +#include "machine.h" +#include "thread.h" +#include <linux/types.h> +#include "event.h" +#include "perf_regs.h" + +static char *debuginfo_path; + +static const Dwfl_Callbacks offline_callbacks = { + .find_debuginfo = dwfl_standard_find_debuginfo, + .debuginfo_path = &debuginfo_path, + .section_address = dwfl_offline_section_address, +}; + +static int __report_module(struct addr_location *al, u64 ip, + struct unwind_info *ui) +{ + Dwfl_Module *mod; + struct dso *dso = NULL; + + thread__find_addr_location(ui->thread, ui->machine, + PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, al); + + if (al->map) + dso = al->map->dso; + + if (!dso) + return 0; + + mod = dwfl_addrmodule(ui->dwfl, ip); + if (!mod) + mod = dwfl_report_elf(ui->dwfl, dso->short_name, + dso->long_name, -1, al->map->start, + false); + + return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1; +} + +static int report_module(u64 ip, struct unwind_info *ui) +{ + struct addr_location al; + + return __report_module(&al, ip, ui); +} + +static int entry(u64 ip, struct unwind_info *ui) + +{ + struct unwind_entry e; + struct addr_location al; + + if (__report_module(&al, ip, ui)) + return -1; + + e.ip = ip; + e.map = al.map; + e.sym = al.sym; + + pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", + al.sym ? al.sym->name : "''", + ip, + al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + + return ui->cb(&e, ui->arg); +} + +static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp) +{ + /* We want only single thread to be processed. */ + if (*thread_argp != NULL) + return 0; + + *thread_argp = arg; + return dwfl_pid(dwfl); +} + +static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, + Dwarf_Word *data) +{ + struct addr_location al; + ssize_t size; + + thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER, + MAP__FUNCTION, addr, &al); + if (!al.map) { + pr_debug("unwind: no map for %lx\n", (unsigned long)addr); + return -1; + } + + if (!al.map->dso) + return -1; + + size = dso__data_read_addr(al.map->dso, al.map, ui->machine, + addr, (u8 *) data, sizeof(*data)); + + return !(size == sizeof(*data)); +} + +static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result, + void *arg) +{ + struct unwind_info *ui = arg; + struct stack_dump *stack = &ui->sample->user_stack; + u64 start, end; + int offset; + int ret; + + ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); + if (ret) + return false; + + end = start + stack->size; + + /* Check overflow. */ + if (addr + sizeof(Dwarf_Word) < addr) + return false; + + if (addr < start || addr + sizeof(Dwarf_Word) > end) { + ret = access_dso_mem(ui, addr, result); + if (ret) { + pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range" + " 0x%" PRIx64 "-0x%" PRIx64 "\n", + addr, start, end); + return false; + } + return true; + } + + offset = addr - start; + *result = *(Dwarf_Word *)&stack->data[offset]; + pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n", + addr, (unsigned long)*result, offset); + return true; +} + +static const Dwfl_Thread_Callbacks callbacks = { + .next_thread = next_thread, + .memory_read = memory_read, + .set_initial_registers = libdw__arch_set_initial_registers, +}; + +static int +frame_callback(Dwfl_Frame *state, void *arg) +{ + struct unwind_info *ui = arg; + Dwarf_Addr pc; + + if (!dwfl_frame_pc(state, &pc, NULL)) { + pr_err("%s", dwfl_errmsg(-1)); + return DWARF_CB_ABORT; + } + + return entry(pc, ui) || !(--ui->max_stack) ? + DWARF_CB_ABORT : DWARF_CB_OK; +} + +int unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct machine *machine, struct thread *thread, + struct perf_sample *data, + int max_stack) +{ + struct unwind_info ui = { + .sample = data, + .thread = thread, + .machine = machine, + .cb = cb, + .arg = arg, + .max_stack = max_stack, + }; + Dwarf_Word ip; + int err = -EINVAL; + + if (!data->user_regs.regs) + return -EINVAL; + + ui.dwfl = dwfl_begin(&offline_callbacks); + if (!ui.dwfl) + goto out; + + err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); + if (err) + goto out; + + err = report_module(ip, &ui); + if (err) + goto out; + + if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui)) + goto out; + + err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui); + + if (err && !ui.max_stack) + err = 0; + + out: + if (err) + pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1)); + + dwfl_end(ui.dwfl); + return 0; +} diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h new file mode 100644 index 000000000000..417a1426f3ad --- /dev/null +++ b/tools/perf/util/unwind-libdw.h @@ -0,0 +1,21 @@ +#ifndef __PERF_UNWIND_LIBDW_H +#define __PERF_UNWIND_LIBDW_H + +#include <elfutils/libdwfl.h> +#include "event.h" +#include "thread.h" +#include "unwind.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg); + +struct unwind_info { + Dwfl *dwfl; + struct perf_sample *sample; + struct machine *machine; + struct thread *thread; + unwind_entry_cb_t cb; + void *arg; + int max_stack; +}; + +#endif /* __PERF_UNWIND_LIBDW_H */ diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind-libunwind.c index 742f23bf35ff..bd5768d74f01 100644 --- a/tools/perf/util/unwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -86,7 +86,6 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; - u64 sample_uregs; }; #define dw_read(ptr, type, end) ({ \ @@ -391,30 +390,13 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, return !(size == sizeof(*data)); } -static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id, - u64 sample_regs) -{ - int i, idx = 0; - - if (!(sample_regs & (1 << id))) - return -EINVAL; - - for (i = 0; i < id; i++) { - if (sample_regs & (1 << i)) - idx++; - } - - *valp = regs->regs[idx]; - return 0; -} - static int access_mem(unw_addr_space_t __maybe_unused as, unw_word_t addr, unw_word_t *valp, int __write, void *arg) { struct unwind_info *ui = arg; struct stack_dump *stack = &ui->sample->user_stack; - unw_word_t start, end; + u64 start, end; int offset; int ret; @@ -424,8 +406,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as, return 0; } - ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP, - ui->sample_uregs); + ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); if (ret) return ret; @@ -438,8 +419,9 @@ static int access_mem(unw_addr_space_t __maybe_unused as, if (addr < start || addr + sizeof(unw_word_t) >= end) { ret = access_dso_mem(ui, addr, valp); if (ret) { - pr_debug("unwind: access_mem %p not inside range %p-%p\n", - (void *)addr, (void *)start, (void *)end); + pr_debug("unwind: access_mem %p not inside range" + " 0x%" PRIx64 "-0x%" PRIx64 "\n", + (void *) addr, start, end); *valp = 0; return ret; } @@ -448,8 +430,8 @@ static int access_mem(unw_addr_space_t __maybe_unused as, offset = addr - start; *valp = *(unw_word_t *)&stack->data[offset]; - pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n", - (void *)addr, (unsigned long)*valp, offset); + pr_debug("unwind: access_mem addr %p val %lx, offset %d\n", + (void *) addr, (unsigned long)*valp, offset); return 0; } @@ -459,6 +441,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as, { struct unwind_info *ui = arg; int id, ret; + u64 val; /* Don't support write, I suspect we don't need it. */ if (__write) { @@ -471,16 +454,17 @@ static int access_reg(unw_addr_space_t __maybe_unused as, return 0; } - id = unwind__arch_reg_id(regnum); + id = libunwind__arch_reg_id(regnum); if (id < 0) return -EINVAL; - ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs); + ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { pr_err("unwind: can't read reg %d\n", regnum); return ret; } + *valp = (unw_word_t) val; pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp); return 0; } @@ -563,7 +547,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, unw_word_t ip; unw_get_reg(&c, UNW_REG_IP, &ip); - ret = entry(ip, ui->thread, ui->machine, cb, arg); + ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0; } unw_destroy_addr_space(addr_space); @@ -572,13 +556,11 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct machine *machine, struct thread *thread, - u64 sample_uregs, struct perf_sample *data, - int max_stack) + struct perf_sample *data, int max_stack) { - unw_word_t ip; + u64 ip; struct unwind_info ui = { .sample = data, - .sample_uregs = sample_uregs, .thread = thread, .machine = machine, }; @@ -587,7 +569,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (!data->user_regs.regs) return -EINVAL; - ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs); + ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); if (ret) return ret; @@ -595,5 +577,5 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (ret) return -ENOMEM; - return get_entries(&ui, cb, arg, max_stack); + return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index d5966f49e22c..f03061260b4e 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -1,7 +1,7 @@ #ifndef __UNWIND_H #define __UNWIND_H -#include "types.h" +#include <linux/types.h> #include "event.h" #include "symbol.h" @@ -13,24 +13,25 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); -#ifdef HAVE_LIBUNWIND_SUPPORT +#ifdef HAVE_DWARF_UNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct machine *machine, struct thread *thread, - u64 sample_uregs, struct perf_sample *data, int max_stack); -int unwind__arch_reg_id(int regnum); +/* libunwind specific */ +#ifdef HAVE_LIBUNWIND_SUPPORT +int libunwind__arch_reg_id(int regnum); +#endif #else static inline int unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct machine *machine __maybe_unused, struct thread *thread __maybe_unused, - u64 sample_uregs __maybe_unused, struct perf_sample *data __maybe_unused, int max_stack __maybe_unused) { return 0; } -#endif /* HAVE_LIBUNWIND_SUPPORT */ +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 42ad667bb317..7fff6be07f07 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,6 +1,6 @@ #include "../perf.h" #include "util.h" -#include "fs.h" +#include <api/fs/fs.h> #include <sys/mman.h> #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> @@ -166,6 +166,8 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n) ssize_t ret = is_read ? read(fd, buf, left) : write(fd, buf, left); + if (ret < 0 && errno == EINTR) + continue; if (ret <= 0) return ret; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 6995d66f225c..b03da44e94e4 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -69,7 +69,7 @@ #include <sys/ioctl.h> #include <inttypes.h> #include <linux/magic.h> -#include "types.h" +#include <linux/types.h> #include <sys/ttydefaults.h> #include <api/fs/debugfs.h> #include <termios.h> diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h index 2fa967e1a88a..b21a80c6cf8d 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -1,7 +1,7 @@ #ifndef __PERF_VALUES_H #define __PERF_VALUES_H -#include "types.h" +#include <linux/types.h> struct perf_read_values { int threads; |