diff options
Diffstat (limited to 'tools/perf')
92 files changed, 2878 insertions, 1322 deletions
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 888d51137fb..1d78a4064da 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 b715cb71592..1513935c399 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. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. + LINE SYNTAX ----------- Line range is described by following syntax. diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index f41572d0dd7..c0c87c87b60 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -6,6 +6,7 @@ tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h tools/include/asm/bug.h tools/include/linux/compiler.h +tools/include/linux/hash.h include/linux/const.h include/linux/perf_event.h include/linux/rbtree.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 7257e7e9e38..50d875d970c 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -7,6 +7,8 @@ include config/utilities.mak # Define V to have a more verbose compile. # +# Define VF to have a more verbose feature check output. +# # Define O to save output files in a separate directory. # # Define ARCH as name of target architecture if you want cross-builds. @@ -55,6 +57,9 @@ include config/utilities.mak # Define NO_LIBAUDIT if you do not want libaudit support # # Define NO_LIBBIONIC if you do not want bionic support +# +# Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support +# for dwarf backtrace post unwind. ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(shell pwd))) @@ -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 @@ -218,9 +223,7 @@ 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 += 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 @@ -244,7 +247,6 @@ LIB_H += util/cache.h LIB_H += util/callchain.h LIB_H += util/build-id.h LIB_H += util/debug.h -LIB_H += util/fs.h LIB_H += util/pmu.h LIB_H += util/event.h LIB_H += util/evsel.h @@ -306,7 +308,6 @@ 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 @@ -408,6 +409,11 @@ 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),x86) +LIB_OBJS += $(OUTPUT)tests/dwarf-unwind.o +endif +endif BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o @@ -420,6 +426,9 @@ 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 +484,13 @@ 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 += $(OUTPUT)tests/keep-tracking.o @@ -533,6 +547,7 @@ ifeq ($(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 @@ -655,6 +670,9 @@ $(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 +725,15 @@ $(patsubst perf-%,%.o,$(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 +910,7 @@ 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 fe9b61e322a..67e9b3d38e8 100644 --- a/tools/perf/arch/arm/Makefile +++ b/tools/perf/arch/arm/Makefile @@ -3,5 +3,5 @@ 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 diff --git a/tools/perf/arch/arm/util/unwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index da3dc950550..729ed69a666 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/x86/Makefile b/tools/perf/arch/x86/Makefile index 8801fe02f20..1641542e363 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 e84ca76aae7..fc819ca34a7 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -5,14 +5,20 @@ #include "../../util/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 00000000000..b602ad93ce6 --- /dev/null +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -0,0 +1,59 @@ +#include <string.h> +#include "perf_regs.h" +#include "thread.h" +#include "map.h" +#include "event.h" +#include "tests/tests.h" + +#define STACK_SIZE 8192 |