From 7a1ac110c22eb726684c837544a2d42c33e07be7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 9 Jun 2017 16:54:28 -0300 Subject: [PATCH 1/3] perf evsel: Fix probing of precise_ip level for default cycles event Since commit 18e7a45af91a ("perf/x86: Reject non sampling events with precise_ip") returns -EINVAL for sys_perf_event_open() with an attribute with (attr.precise_ip > 0 && attr.sample_period == 0), just like is done in the routine used to probe the max precise level when no events were passed to 'perf record' or 'perf top', i.e.: perf_evsel__new_cycles() perf_event_attr__set_max_precise_ip() The x86 code, in x86_pmu_hw_config(), which is called all the way from sys_perf_event_open() did, starting with the aforementioned commit: /* There's no sense in having PEBS for non sampling events: */ if (!is_sampling_event(event)) return -EINVAL; Which makes it fail for cycles:ppp, cycles:pp and cycles:p, always using just the non precise cycles variant. To make sure that this is the case, I tested it, before this patch, with: # perf probe -L x86_pmu_hw_config 0 int x86_pmu_hw_config(struct perf_event *event) 1 { 2 if (event->attr.precise_ip) { 17 if (event->attr.precise_ip > precise) 18 return -EOPNOTSUPP; /* There's no sense in having PEBS for non sampling events: */ 21 if (!is_sampling_event(event)) 22 return -EINVAL; } # perf probe x86_pmu_hw_config:22 Added new events: probe:x86_pmu_hw_config (on x86_pmu_hw_config:22) probe:x86_pmu_hw_config_1 (on x86_pmu_hw_config:22) You can now use it in all perf tools, such as: perf record -e probe:x86_pmu_hw_config_1 -aR sleep 1 # perf trace -e perf_event_open,probe:x86_pmu_hwconfig*/max-stack=16/ perf record usleep 1 0.000 ( 0.015 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.015 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.000 ( 0.021 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 0.023 ( 0.002 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.025 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.023 ( 0.004 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 0.028 ( 0.002 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.030 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.028 ( 0.004 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 41.018 ( 0.012 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8b5dd0, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.065 ( 0.011 ms): perf/4150 perf_event_open(attr_uptr: 0x3c7db78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.080 ( 0.006 ms): perf/4150 perf_event_open(attr_uptr: 0x3c7db78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.103 ( 0.010 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), group_fd: -1, flags: FD_CLOEXEC) = 4 41.115 ( 0.006 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 5 41.122 ( 0.004 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 6 41.128 ( 0.008 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 8 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data (2 samples) ] # I.e. that return -EINVAL in x86_pmu_hw_config() is hit three times. So fix it by just setting attr.sample_period Now, after this patch: # perf trace --max-stack=2 -e perf_event_open,probe:x86_pmu_hw_config* perf record usleep 1 [ perf record: Woken up 1 times to write data ] 0.000 ( 0.017 ms): perf/8469 perf_event_open(attr_uptr: 0x7ffe36c27d10, pid: -1, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_event_open_cloexec_flag (/home/acme/bin/perf) 0.050 ( 0.031 ms): perf/8469 perf_event_open(attr_uptr: 0x24ebb78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evlist__config (/home/acme/bin/perf) 0.092 ( 0.040 ms): perf/8469 perf_event_open(attr_uptr: 0x24ebb78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evlist__config (/home/acme/bin/perf) 0.143 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, cpu: -1, group_fd: -1 ) = 4 syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) 0.161 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.171 ( 0.005 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 5 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.180 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 6 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.190 ( 0.005 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 8 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) [ perf record: Captured and wrote 0.017 MB perf.data (7 samples) ] # The probe one called from perf_event_attr__set_max_precise_ip() works the first time, with attr.precise_ip = 3, wit hthe next ones being the per cpu ones for the cycles:ppp event. And here is the text from a report and alternative proposed patch by Thomas-Mich Richter: --- On s390 the counter and sampling facility do not support a precise IP skid level and sometimes returns EOPNOTSUPP when structure member precise_ip in struct perf_event_attr is not set to zero. On s390 commnd 'perf record -- true' fails with error EOPNOTSUPP. This happens only when no events are specified on command line. The functions called are ... --> perf_evlist__add_default --> perf_evsel__new_cycles --> perf_event_attr__set_max_precise_ip The last function determines the value of structure member precise_ip by invoking the perf_event_open() system call and checking the return code. The first successful open is the value for precise_ip. However the value is determined without setting member sample_period and indicates no sampling. On s390 the counter facility and sampling facility are different. The above procedure determines a precise_ip value of 3 using the counter facility. Later it uses the sampling facility with a value of 3 and fails with EOPNOTSUPP. --- v2: Older compilers (e.g. gcc 4.4.7) don't support referencing members of unnamed union members in the container struct initialization, so move from: struct perf_event_attr attr = { ... .sample_period = 1, }; to right after it as: struct perf_event_attr attr = { ... }; attr.sample_period = 1; v3: We need to reset .sample_period to 0 to let the users of perf_evsel__new_cycles() to properly setup attr.sample_period or attr.sample_freq. Reported by Ingo Molnar. Reported-and-Acked-by: Thomas-Mich Richter Acked-by: Hendrik Brueckner Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Fixes: 18e7a45af91a ("perf/x86: Reject non sampling events with precise_ip") Link: http://lkml.kernel.org/n/tip-yv6nnkl7tzqocrm0hl3x7vf1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/task-exit.c | 2 +- tools/perf/util/evsel.c | 12 ++++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 32873ec91a4e..cf00ebad2ef5 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -83,7 +83,7 @@ int test__task_exit(int subtest __maybe_unused) evsel = perf_evlist__first(evlist); evsel->attr.task = 1; - evsel->attr.sample_freq = 0; + evsel->attr.sample_freq = 1; evsel->attr.inherit = 0; evsel->attr.watermark = 0; evsel->attr.wakeup_events = 1; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index e4f7902d5afa..cda44b0e821c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -273,8 +273,20 @@ struct perf_evsel *perf_evsel__new_cycles(void) struct perf_evsel *evsel; event_attr_init(&attr); + /* + * Unnamed union member, not supported as struct member named + * initializer in older compilers such as gcc 4.4.7 + * + * Just for probing the precise_ip: + */ + attr.sample_period = 1; perf_event_attr__set_max_precise_ip(&attr); + /* + * Now let the usual logic to set up the perf_event_attr defaults + * to kick in when we return and before perf_evsel__open() is called. + */ + attr.sample_period = 0; evsel = perf_evsel__new(&attr); if (evsel == NULL) From 7a759cd8e8272ee18922838ee711219c7c796a31 Mon Sep 17 00:00:00 2001 From: Jiada Wang Date: Sun, 9 Apr 2017 20:02:37 -0700 Subject: [PATCH 2/3] perf tools: Fix build with ARCH=x86_64 With commit: 0a943cb10ce78 (tools build: Add HOSTARCH Makefile variable) when building for ARCH=x86_64, ARCH=x86_64 is passed to perf instead of ARCH=x86, so the perf build process searchs header files from tools/arch/x86_64/include, which doesn't exist. The following build failure is seen: In file included from util/event.c:2:0: tools/include/uapi/linux/mman.h:4:27: fatal error: uapi/asm/mman.h: No such file or directory compilation terminated. Fix this issue by using SRCARCH instead of ARCH in perf, just like the main kernel Makefile and tools/objtool's. Signed-off-by: Jiada Wang Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Eugeniu Rosca Cc: Jan Stancek Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rui Teng Cc: Sukadev Bhattiprolu Cc: Wang Nan Fixes: 0a943cb10ce7 ("tools build: Add HOSTARCH Makefile variable") Link: http://lkml.kernel.org/r/1491793357-14977-2-git-send-email-jiada_wang@mentor.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 38 ++++++++++++++++++------------------- tools/perf/Makefile.perf | 2 +- tools/perf/arch/Build | 2 +- tools/perf/pmu-events/Build | 4 ++-- tools/perf/tests/Build | 2 +- tools/perf/util/header.c | 2 +- 6 files changed, 25 insertions(+), 25 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 8354d04b392f..1f4fbc9a3292 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -19,18 +19,18 @@ CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) include $(srctree)/tools/scripts/Makefile.arch -$(call detected_var,ARCH) +$(call detected_var,SRCARCH) NO_PERF_REGS := 1 # Additional ARCH settings for ppc -ifeq ($(ARCH),powerpc) +ifeq ($(SRCARCH),powerpc) NO_PERF_REGS := 0 LIBUNWIND_LIBS := -lunwind -lunwind-ppc64 endif # Additional ARCH settings for x86 -ifeq ($(ARCH),x86) +ifeq ($(SRCARCH),x86) $(call detected,CONFIG_X86) ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated @@ -43,12 +43,12 @@ ifeq ($(ARCH),x86) NO_PERF_REGS := 0 endif -ifeq ($(ARCH),arm) +ifeq ($(SRCARCH),arm) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-arm endif -ifeq ($(ARCH),arm64) +ifeq ($(SRCARCH),arm64) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif @@ -61,7 +61,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(ARCH),$(filter $(ARCH),x86 arm)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -115,9 +115,9 @@ endif FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf -FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi +FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi # include ARCH specific config --include $(src-perf)/arch/$(ARCH)/Makefile +-include $(src-perf)/arch/$(SRCARCH)/Makefile ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET CFLAGS += -DHAVE_ARCH_REGS_QUERY_REGISTER_OFFSET @@ -228,12 +228,12 @@ ifeq ($(DEBUG),0) endif INC_FLAGS += -I$(src-perf)/util/include -INC_FLAGS += -I$(src-perf)/arch/$(ARCH)/include +INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include INC_FLAGS += -I$(srctree)/tools/include/uapi INC_FLAGS += -I$(srctree)/tools/include/ -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/ -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/ +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/ +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/ # $(obj-perf) for generated common-cmds.h # $(obj-perf)/util for generated bison/flex headers @@ -355,7 +355,7 @@ ifndef NO_LIBELF ifndef NO_DWARF ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) - msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); + msg := $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled); NO_DWARF := 1 else CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) @@ -380,7 +380,7 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_BPF_PROLOGUE $(call detected,CONFIG_BPF_PROLOGUE) else - msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset()); + msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset()); endif else msg := $(warning DWARF support is off, BPF prologue is disabled); @@ -406,7 +406,7 @@ ifdef PERF_HAVE_JITDUMP endif endif -ifeq ($(ARCH),powerpc) +ifeq ($(SRCARCH),powerpc) ifndef NO_DWARF CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX endif @@ -487,7 +487,7 @@ else endif ifndef NO_LOCAL_LIBUNWIND - ifeq ($(ARCH),$(filter $(ARCH),arm arm64)) + ifeq ($(SRCARCH),$(filter $(SRCARCH),arm arm64)) $(call feature_check,libunwind-debug-frame) ifneq ($(feature-libunwind-debug-frame), 1) msg := $(warning No debug_frame support found in libunwind); @@ -740,7 +740,7 @@ ifeq (${IS_64_BIT}, 1) NO_PERF_READ_VDSO32 := 1 endif endif - ifneq ($(ARCH), x86) + ifneq ($(SRCARCH), x86) NO_PERF_READ_VDSOX32 := 1 endif ifndef NO_PERF_READ_VDSOX32 @@ -769,7 +769,7 @@ ifdef LIBBABELTRACE endif ifndef NO_AUXTRACE - ifeq ($(ARCH),x86) + ifeq ($(SRCARCH),x86) ifeq ($(feature-get_cpuid), 0) msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc); NO_AUXTRACE := 1 @@ -872,7 +872,7 @@ sysconfdir = $(prefix)/etc ETC_PERFCONFIG = etc/perfconfig endif ifndef lib -ifeq ($(ARCH)$(IS_64_BIT), x861) +ifeq ($(SRCARCH)$(IS_64_BIT), x861) lib = lib64 else lib = lib diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 79fe31f20a17..5008f51a08a2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -226,7 +226,7 @@ endif ifeq ($(config),0) include $(srctree)/tools/scripts/Makefile.arch --include arch/$(ARCH)/Makefile +-include arch/$(SRCARCH)/Makefile endif # The FEATURE_DUMP_EXPORT holds location of the actual diff --git a/tools/perf/arch/Build b/tools/perf/arch/Build index 109eb75cf7de..d9b6af837c7d 100644 --- a/tools/perf/arch/Build +++ b/tools/perf/arch/Build @@ -1,2 +1,2 @@ libperf-y += common.o -libperf-y += $(ARCH)/ +libperf-y += $(SRCARCH)/ diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 9213a1273697..999a4e878162 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -2,7 +2,7 @@ hostprogs := jevents jevents-y += json.o jsmn.o jevents.o pmu-events-y += pmu-events.o -JDIR = pmu-events/arch/$(ARCH) +JDIR = pmu-events/arch/$(SRCARCH) JSON = $(shell [ -d $(JDIR) ] && \ find $(JDIR) -name '*.json' -o -name 'mapfile.csv') # @@ -10,4 +10,4 @@ JSON = $(shell [ -d $(JDIR) ] && \ # directory and create tables in pmu-events.c. # $(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JEVENTS) - $(Q)$(call echo-cmd,gen)$(JEVENTS) $(ARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V) + $(Q)$(call echo-cmd,gen)$(JEVENTS) $(SRCARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index af58ebc243ef..84222bdb8689 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -75,7 +75,7 @@ $(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/B $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ -ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc)) +ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 5cac8d5e009a..b5baff3007bb 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -841,7 +841,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, /* * default get_cpuid(): nothing gets recorded - * actual implementation must be in arch/$(ARCH)/util/header.c + * actual implementation must be in arch/$(SRCARCH)/util/header.c */ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) { From 9126cbbacecb8917bd0418809ef1d26616b2061e Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Fri, 2 Jun 2017 16:37:53 +0200 Subject: [PATCH 3/3] perf unwind: Report module before querying isactivation in dwfl unwind The PC returned by dwfl_frame_pc() may map into a not-yet-reported module. We have to report it before we continue unwinding. But when we query for the isactivation flag in dwfl_frame_pc, libdw will actually do one more unwinding step internally which can then break and lead to missed frames or broken stacks. With libunwind we get e.g.: ~~~~~ heaptrack_gui 2228 135073.400474: 613969 cycles: 108c8e [unknown] (/usr/lib/libQt5Core.so.5.8.0) 1093bc [unknown] (/usr/lib/libQt5Core.so.5.8.0) 109e7b QLocale::QLocale (/usr/lib/libQt5Core.so.5.8.0) 1470ff [unknown] (/usr/lib/libQt5Core.so.5.8.0) 147f67 QSystemLocale::query (/usr/lib/libQt5Core.so.5.8.0) 109fbf QLocalePrivate::updateSystemPrivate (/usr/lib/libQt5Core.so.5.8.0) 10aa27 QLocale::QLocale (/usr/lib/libQt5Core.so.5.8.0) 1e02c3 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 2113bb [unknown] (/usr/lib/libQt5Core.so.5.8.0) 211505 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 1b5df0 QFileInfo::exists (/usr/lib/libQt5Core.so.5.8.0) 92eb2 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 93423 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 93d2a QLibraryInfo::location (/usr/lib/libQt5Core.so.5.8.0) 2170af [unknown] (/usr/lib/libQt5Core.so.5.8.0) 297c53 QCoreApplicationPrivate::init (/usr/lib/libQt5Core.so.5.8.0) f7cde QGuiApplicationPrivate::init (/usr/lib/libQt5Gui.so.5.8.0) 1589e8 QApplicationPrivate::init (/usr/lib/libQt5Widgets.so.5.8.0) 78622 main (/home/milian/projects/compiled/other/bin/heaptrack_gui) 20439 __libc_start_main (/usr/lib/libc-2.25.so) 78299 _start (/home/milian/projects/compiled/other/bin/heaptrack_gui) heaptrack_gui 2228 135073.401156: 569521 cycles: 131633 QString::endsWith (/usr/lib/libQt5Core.so.5.8.0) 1a0701 QDir::cleanPath (/usr/lib/libQt5Core.so.5.8.0) 21b82d [unknown] (/usr/lib/libQt5Core.so.5.8.0) 1b3727 QFileInfo::canonicalFilePath (/usr/lib/libQt5Core.so.5.8.0) 2780c7 QFactoryLoader::update (/usr/lib/libQt5Core.so.5.8.0) 279525 QFactoryLoader::QFactoryLoader (/usr/lib/libQt5Core.so.5.8.0) e5bd0 QPlatformIntegrationFactory::create (/usr/lib/libQt5Gui.so.5.8.0) f5a1c QGuiApplicationPrivate::createPlatformIntegration (/usr/lib/libQt5Gui.so.5.8.0) f650c QGuiApplicationPrivate::createEventDispatcher (/usr/lib/libQt5Gui.so.5.8.0) 298524 QCoreApplicationPrivate::init (/usr/lib/libQt5Core.so.5.8.0) f7cde QGuiApplicationPrivate::init (/usr/lib/libQt5Gui.so.5.8.0) 1589e8 QApplicationPrivate::init (/usr/lib/libQt5Widgets.so.5.8.0) 78622 main (/home/milian/projects/compiled/other/bin/heaptrack_gui) 20439 __libc_start_main (/usr/lib/libc-2.25.so) 78299 _start (/home/milian/projects/compiled/other/bin/heaptrack_gui) ~~~~~ Note the two frames 1589e8 and 78622 in the first sample. These are missing when unwinding with libdw. The second sample's breakage is more obvious: ~~~~~ heaptrack_gui 2228 135073.400474: 613969 cycles: 108c8e [unknown] (/usr/lib/libQt5Core.so.5.8.0) 1093bc [unknown] (/usr/lib/libQt5Core.so.5.8.0) 109e7b QLocale::QLocale (/usr/lib/libQt5Core.so.5.8.0) 1470ff [unknown] (/usr/lib/libQt5Core.so.5.8.0) 147f67 QSystemLocale::query (/usr/lib/libQt5Core.so.5.8.0) 109fbf QLocalePrivate::updateSystemPrivate (/usr/lib/libQt5Core.so.5.8.0) 10aa27 QLocale::QLocale (/usr/lib/libQt5Core.so.5.8.0) 1e02c3 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 2113bb [unknown] (/usr/lib/libQt5Core.so.5.8.0) 211505 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 1b5df0 QFileInfo::exists (/usr/lib/libQt5Core.so.5.8.0) 92eb2 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 93423 [unknown] (/usr/lib/libQt5Core.so.5.8.0) 93d2a QLibraryInfo::location (/usr/lib/libQt5Core.so.5.8.0) 2170af [unknown] (/usr/lib/libQt5Core.so.5.8.0) 297c53 QCoreApplicationPrivate::init (/usr/lib/libQt5Core.so.5.8.0) f7cde QGuiApplicationPrivate::init (/usr/lib/libQt5Gui.so.5.8.0) 20439 __libc_start_main (/usr/lib/libc-2.25.so) 78299 _start (/home/milian/projects/compiled/other/bin/heaptrack_gui) heaptrack_gui 2228 135073.401156: 569521 cycles: 131633 QString::endsWith (/usr/lib/libQt5Core.so.5.8.0) 1a0701 QDir::cleanPath (/usr/lib/libQt5Core.so.5.8.0) 21b82d [unknown] (/usr/lib/libQt5Core.so.5.8.0) 1b3727 QFileInfo::canonicalFilePath (/usr/lib/libQt5Core.so.5.8.0) 2780c7 QFactoryLoader::update (/usr/lib/libQt5Core.so.5.8.0) 279525 QFactoryLoader::QFactoryLoader (/usr/lib/libQt5Core.so.5.8.0) e5bd0 QPlatformIntegrationFactory::create (/usr/lib/libQt5Gui.so.5.8.0) 723dbf [unknown] ([unknown]) ~~~~~ This patch fixes this issue and the libdw unwinder mimicks the libunwind behavior more closely. Signed-off-by: Milian Wolff Acked-by: Jan Kratochvil Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20170602143753.16907-2-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/unwind-libdw.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index da45c4be5fb3..7755a5e0fe5e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -178,6 +178,14 @@ frame_callback(Dwfl_Frame *state, void *arg) Dwarf_Addr pc; bool isactivation; + if (!dwfl_frame_pc(state, &pc, NULL)) { + pr_err("%s", dwfl_errmsg(-1)); + return DWARF_CB_ABORT; + } + + // report the module before we query for isactivation + report_module(pc, ui); + if (!dwfl_frame_pc(state, &pc, &isactivation)) { pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT;