diff options
90 files changed, 2225 insertions, 602 deletions
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index f897cb5fb12d..e3292a3a0c46 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -148,6 +148,8 @@ VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ /boot/vmlinux-$(shell uname -r) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) +bootstrap: $(BPFTOOL_BOOTSTRAP) + ifneq ($(VMLINUX_BTF)$(VMLINUX_H),) ifeq ($(feature-clang-bpf-co-re),1) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 97cbfb31b762..74e255d58d8d 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -99,7 +99,9 @@ FEATURE_TESTS_EXTRA := \ clang \ libbpf \ libpfm4 \ - libdebuginfod + libdebuginfod \ + clang-bpf-co-re + FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC) diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c index 1547bc2c0950..52c790b0317b 100644 --- a/tools/build/feature/test-libopencsd.c +++ b/tools/build/feature/test-libopencsd.c @@ -4,9 +4,9 @@ /* * Check OpenCSD library version is sufficient to provide required features */ -#define OCSD_MIN_VER ((0 << 16) | (14 << 8) | (0)) +#define OCSD_MIN_VER ((1 << 16) | (0 << 8) | (0)) #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER) -#error "OpenCSD >= 0.14.0 is required" +#error "OpenCSD >= 1.0.0 is required" #endif int main(void) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b15e3447cd9f..cb6f84103560 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -386,7 +386,8 @@ struct perf_event_attr { aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - __reserved_1 : 30; + build_id : 1, /* use build id in mmap2 events */ + __reserved_1 : 29; union { __u32 wakeup_events; /* wakeup every n events */ @@ -659,6 +660,22 @@ struct perf_event_mmap_page { __u64 aux_size; }; +/* + * The current state of perf_event_header::misc bits usage: + * ('|' used bit, '-' unused bit) + * + * 012 CDEF + * |||---------|||| + * + * Where: + * 0-2 CPUMODE_MASK + * + * C PROC_MAP_PARSE_TIMEOUT + * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT + * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT + * F (reserved) + */ + #define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) @@ -690,6 +707,7 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events + * PERF_RECORD_MISC_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event * * * PERF_RECORD_MISC_EXACT_IP: @@ -699,9 +717,13 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT: * Indicates that thread was preempted in TASK_RUNNING state. + * + * PERF_RECORD_MISC_MMAP_BUILD_ID: + * Indicates that mmap2 event carries build id data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) +#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) /* * Reserve the last bit to indicate some extended misc field */ @@ -915,10 +937,20 @@ enum perf_event_type { * u64 addr; * u64 len; * u64 pgoff; - * u32 maj; - * u32 min; - * u64 ino; - * u64 ino_generation; + * union { + * struct { + * u32 maj; + * u32 min; + * u64 ino; + * u64 ino_generation; + * }; + * struct { + * u8 build_id_size; + * u8 __reserved_1; + * u16 __reserved_2; + * u8 build_id[20]; + * }; + * }; * u32 prot, flags; * char filename[]; * struct sample_id sample_id; diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 988c539bedb6..d82054225fcc 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -23,10 +23,20 @@ struct perf_record_mmap2 { __u64 start; __u64 len; __u64 pgoff; - __u32 maj; - __u32 min; - __u64 ino; - __u64 ino_generation; + union { + struct { + __u32 maj; + __u32 min; + __u64 ino; + __u64 ino_generation; + }; + struct { + __u8 build_id_size; + __u8 __reserved_1; + __u16 __reserved_2; + __u8 build_id[20]; + }; + }; __u32 prot; __u32 flags; char filename[PATH_MAX]; diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index f6de0952ff3c..bb167e32a1d7 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -74,6 +74,12 @@ OPTIONS used when creating a uprobe for a process that resides in a different mount namespace from the perf(1) utility. +--debuginfod=URLs:: + Specify debuginfod URL to be used when retrieving perf.data binaries, + it follows the same syntax as the DEBUGINFOD_URLS variable, like: + + buildid-cache.debuginfod=http://192.168.122.174:8002 + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1] diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 5c379adf8304..c3ce48f1b379 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -238,6 +238,13 @@ buildid.*:: cache location, or to disable it altogether. If you want to disable it, set buildid.dir to /dev/null. The default is $HOME/.debug +buildid-cache.*:: + buildid-cache.debuginfod=URLs + Specify debuginfod URLs to be used when retrieving perf.data binaries, + it follows the same syntax as the DEBUGINFOD_URLS variable, like: + + buildid-cache.debuginfod=http://192.168.122.174:8002 + annotate.*:: These are in control of addresses, jump function, source code in lines of assembly code from a specific program. @@ -552,11 +559,12 @@ kmem.*:: record.*:: record.build-id:: - This option can be 'cache', 'no-cache' or 'skip'. + This option can be 'cache', 'no-cache', 'skip' or 'mmap'. 'cache' is to post-process data and save/update the binaries into the build-id cache (in ~/.debug). This is the default. But if this option is 'no-cache', it will not update the build-id cache. 'skip' skips post-processing and does not update the cache. + 'mmap' skips post-processing and reads build-ids from MMAP events. record.call-graph:: This is identical to 'call-graph.record-mode', except it is diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 199ea0f0a6c0..66177511c5c4 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -63,6 +63,9 @@ OPTIONS --phys-data:: Record/Report sample physical addresses +--data-page-size:: + Record/Report sample data address page size + RECORD OPTIONS -------------- -e:: diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 34cf651ee237..f3161c9673e9 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -296,6 +296,9 @@ OPTIONS --data-page-size:: Record the sampled data address data page size. +--code-page-size:: + Record the sampled code address (ip) page size + -T:: --timestamp:: Record the sample timestamps. Use it with 'perf report -D' to see the @@ -485,6 +488,9 @@ Specify vmlinux path which has debuginfo. --buildid-all:: Record build-id of all DSOs regardless whether it's actually hit or not. +--buildid-mmap:: +Record build ids in mmap2 events, disables build id cache (implies --no-buildid). + --aio[=n]:: Use <n> control blocks in asynchronous (Posix AIO) trace writing mode (default: 1, max: 4). Asynchronous mode is supported only when linking Perf tool with libc library @@ -640,9 +646,18 @@ ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows. Listen on ctl-fd descriptor for command to control measurement. Available commands: - 'enable' : enable events - 'disable' : disable events - 'snapshot': AUX area tracing snapshot). + 'enable' : enable events + 'disable' : disable events + 'enable name' : enable event 'name' + 'disable name' : disable event 'name' + 'snapshot' : AUX area tracing snapshot). + 'stop' : stop perf record + 'ping' : ping + + 'evlist [-v|-g|-F] : display all events + -F Show just the sample frequency used for each event. + -v Show all fields. + -g Show event group information. Measurements can be started with events disabled using --delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor to synchronize with the diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 8f7f4e9605d8..e44045842c5c 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -108,6 +108,7 @@ OPTIONS - period: Raw number of event count of sample - time: Separate the samples by time stamp with the resolution specified by --time-quantum (default 100ms). Specify with overhead and before it. + - code_page_size: the code page size of sampled code address (ip) By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol) diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 44d37210fc8f..6347cfb97ed3 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -118,7 +118,7 @@ OPTIONS comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr, - metric, misc, srccode, ipc, data_page_size. + metric, misc, srccode, ipc, data_page_size, code_page_size. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -425,6 +425,9 @@ include::itrace.txt[] For example, to select the symbol noploop or the address 0x4007a0: perf script --symbols=noploop,0x4007a0 +--dsos=:: + Only consider symbols in these DSOs. + --call-trace:: Show call stream for intel_pt traces. The CPUs are interleaved, but can be filtered with -C. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 5d4a673d7621..98a4dfd3b2dc 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -75,6 +75,24 @@ report:: --tid=<tid>:: stat events on existing thread id (comma separated list) +-b:: +--bpf-prog:: + stat events on existing bpf program id (comma separated list), + requiring root rights. bpftool-prog could be used to find program + id all bpf programs in the system. For example: + + # bpftool prog | head -n 1 + 17247: tracepoint name sys_enter tag 192d548b9d754067 gpl + + # perf stat -e cycles,instructions --bpf-prog 17247 --timeout 1000 + + Performance counter stats for 'BPF program(s) 17247': + + 85,967 cycles + 28,982 instructions # 0.34 insn per cycle + + 1.102235068 seconds time elapsed + ifdef::HAVE_LIBPFM[] --pfm-events events:: Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index ce8516e4de34..d8e59d31399a 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -621,6 +621,15 @@ ifndef NO_LIBBPF endif endif +ifdef BUILD_BPF_SKEL + $(call feature_check,clang-bpf-co-re) + ifeq ($(feature-clang-bpf-co-re), 0) + dummy := $(error Error: clang too old. Please install recent clang) + endif + $(call detected,CONFIG_PERF_BPF_SKEL) + CFLAGS += -DHAVE_BPF_SKEL +endif + dwarf-post-unwind := 1 dwarf-post-unwind-text := BUG diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 62f3deb1d3a8..8c4e039c3b81 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -126,6 +126,8 @@ include ../scripts/utilities.mak # # Define NO_LIBDEBUGINFOD if you do not want support debuginfod # +# Define BUILD_BPF_SKEL to enable BPF skeletons +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -175,6 +177,12 @@ endef LD += $(EXTRA_LDFLAGS) +HOSTCC ?= gcc +HOSTLD ?= ld +HOSTAR ?= ar +CLANG ?= clang +LLVM_STRIP ?= llvm-strip + PKG_CONFIG = $(CROSS_COMPILE)pkg-config LLVM_CONFIG ?= llvm-config @@ -731,7 +739,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(x86_arch_prctl_code_array) \ $(rename_flags_array) \ $(arch_errno_name_array) \ - $(sync_file_range_arrays) + $(sync_file_range_arrays) \ + bpf-skel $(OUTPUT)%.o: %.c prepare FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ @@ -1004,7 +1013,43 @@ config-clean: python-clean: $(python-clean) -clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean config-clean fixdep-clean python-clean +SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel) +SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp) +SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h + +ifdef BUILD_BPF_SKEL +BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool +LIBBPF_SRC := $(abspath ../lib/bpf) +BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(BPF_PATH) -I$(LIBBPF_SRC)/.. + +$(SKEL_TMP_OUT): + $(Q)$(MKDIR) -p $@ + +$(BPFTOOL): | $(SKEL_TMP_OUT) + CFLAGS= $(MAKE) -C ../bpf/bpftool \ + OUTPUT=$(SKEL_TMP_OUT)/ bootstrap + +$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf $(BPF_INCLUDE) \ + -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ + +$(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) + $(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@ + +bpf-skel: $(SKELETONS) + +.PRECIOUS: $(SKEL_TMP_OUT)/%.bpf.o + +else # BUILD_BPF_SKEL + +bpf-skel: + +endif # BUILD_BPF_SKEL + +bpf-skel-clean: + $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) + +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean config-clean fixdep-clean python-clean bpf-skel-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 54efa12fdbea..2518cde18b34 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -1,4 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <regex.h> +#include <string.h> +#include <linux/kernel.h> +#include <linux/zalloc.h> + +#include "../../../util/debug.h" +#include "../../../util/event.h" #include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { @@ -37,3 +45,89 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(pc, PERF_REG_ARM64_PC), SMPL_REG_END }; + +/* %xNUM */ +#define SDT_OP_REGEX1 "^(x[1-2]?[0-9]|3[0-1])$" + +/* [sp], [sp, NUM] */ +#define SDT_OP_REGEX2 "^\\[sp(, )?([0-9]+)?\\]$" + +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + + initialized = 1; + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error.\n"); + return ret; +} + +/* + * SDT marker arguments on Arm64 uses %xREG or [sp, NUM], currently + * support these two formats. + */ +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[5]; + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) { + /* Extract xNUM */ + new_len = 2; /* % NULL */ + new_len += (int)(rm[1].rm_eo - rm[1].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%%%.*s", + (int)(rm[1].rm_eo - rm[1].rm_so), old_op + rm[1].rm_so); + } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) { + /* [sp], [sp, NUM] or [sp,NUM] */ + new_len = 7; /* + ( % s p ) NULL */ + + /* If the arugment is [sp], need to fill offset '0' */ + if (rm[2].rm_so == -1) + new_len += 1; + else + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + if (rm[2].rm_so == -1) + scnprintf(*new_op, new_len, "+0(%%sp)"); + else + scnprintf(*new_op, new_len, "+%.*s(%%sp)", + (int)(rm[2].rm_eo - rm[2].rm_so), + old_op + rm[2].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index e86e210bf514..b7945e5a543b 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,4 +1,5 @@ perf-y += header.o +perf-y += machine.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c new file mode 100644 index 000000000000..c30e5cc88c16 --- /dev/null +++ b/tools/perf/arch/powerpc/util/machine.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <string.h> +#include <internal/lib.h> // page_size +#include "debug.h" +#include "symbol.h" + +/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000 + * whereas the modules are located at very high memory addresses, + * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment + * and beginning of first module's text segment is very high. + * Therefore do not fill this gap and do not assign it to the kernel dso map. + */ + +void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) +{ + if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) + /* Limit the range of last kernel symbol */ + p->end += page_size; + else + p->end = c->start; + pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end); +} diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 347c39b960eb..ce1ec92fecdc 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -6,6 +6,7 @@ perf-y += perf_regs.o perf-y += topdown.o perf-y += machine.o perf-y += event.o +perf-y += evlist.o perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c new file mode 100644 index 000000000000..8c6732cc7794 --- /dev/null +++ b/tools/perf/arch/x86/util/evlist.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include "util/pmu.h" +#include "util/evlist.h" +#include "util/parse-events.h" + +#define TOPDOWN_L1_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}" + +int arch_evlist__add_default_attrs(struct evlist *evlist) +{ + if (!pmu_have_event("cpu", "slots")) + return 0; + + return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL); +} diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index a25411926e48..ecd0d3cb6f5c 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -27,6 +27,7 @@ #include "util/time-utils.h" #include "util/util.h" #include "util/probe-file.h" +#include "util/config.h" #include <linux/string.h> #include <linux/err.h> @@ -348,12 +349,21 @@ static int build_id_cache__show_all(void) return 0; } +static int perf_buildid_cache_config(const char *var, const char *value, void *cb) +{ + const char **debuginfod = cb; + + if (!strcmp(var, "buildid-cache.debuginfod")) + *debuginfod = strdup(value); + + return 0; +} + int cmd_buildid_cache(int argc, const char **argv) { struct strlist *list; struct str_node *pos; - int ret = 0; - int ns_id = -1; + int ret, ns_id = -1; bool force = false; bool list_files = false; bool opts_flag = false; @@ -363,7 +373,8 @@ int cmd_buildid_cache(int argc, const char **argv) *purge_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, - *kcore_filename = NULL; + *kcore_filename = NULL, + *debuginfod = NULL; char sbuf[STRERR_BUFSIZE]; struct perf_data data = { @@ -388,6 +399,8 @@ int cmd_buildid_cache(int argc, const char **argv) OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), OPT_STRING('u', "update", &update_name_list_str, "file list", "file(s) to update"), + OPT_STRING(0, "debuginfod", &debuginfod, "debuginfod url", + "set debuginfod url"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"), OPT_END() @@ -397,6 +410,10 @@ int cmd_buildid_cache(int argc, const char **argv) NULL }; + ret = perf_config(perf_buildid_cache_config, &debuginfod); + if (ret) + return ret; + argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); @@ -408,6 +425,11 @@ int cmd_buildid_cache(int argc, const char **argv) if (argc || !(list_files || opts_flag)) usage_with_options(buildid_cache_usage, buildid_cache_options); + if (debuginfod) { + pr_debug("DEBUGINFOD_URLS=%s\n", debuginfod); + setenv("DEBUGINFOD_URLS", debuginfod, 1); + } + /* -l is exclusive. It can not be used with other options. */ if (list_files && opts_flag) { usage_with_options_msg(buildid_cache_usage, diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index e3ef75583514..87f5b1a4a7fa 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -77,6 +77,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits) perf_header__has_feat(&session->header, HEADER_AUXTRACE)) with_hits = false; + if (!perf_header__has_feat(&session->header, HEADER_BUILD_ID)) + with_hits = true; + /* * in pipe-mode, the only way to get the buildids is to parse * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index c5babeaa3b38..d247f9878948 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -97,8 +97,8 @@ struct perf_c2c { bool symbol_full; bool stitch_lbr; - /* HITM shared clines stats */ - struct c2c_stats hitm_stats; + /* Shared cache line stats */ + struct c2c_stats shared_clines_stats; int shared_clines; int display; @@ -876,7 +876,7 @@ static struct c2c_stats *total_stats(struct hist_entry *he) return &hists->stats; } -static double percent(int st, int tot) +static double percent(u32 st, u32 tot) { return tot ? 100. * (double) st / (double) tot : 0; } @@ -1048,6 +1048,19 @@ empty_cmp(struct perf_hpp_fmt *fmt __maybe_unused, return 0; } +static int display_metrics(struct perf_hpp *hpp, u32 val, u32 sum) +{ + int ret; + + if (sum != 0) + ret = scnprintf(hpp->buf, hpp->size, "%5.1f%% ", + percent(val, sum)); + else + ret = scnprintf(hpp->buf, hpp->size, "%6s ", "n/a"); + + return ret; +} + static int node_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, struct hist_entry *he) @@ -1091,29 +1104,23 @@ node_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp, ret = scnprintf(hpp->buf, hpp->size, "%2d{%2d ", node, num); advance_hpp(hpp, ret); - #define DISPLAY_HITM(__h) \ - if (c2c_he->stats.__h> 0) { \ - ret = scnprintf(hpp->buf, hpp->size, "%5.1f%% ", \ - percent(stats->__h, c2c_he->stats.__h));\ - } else { \ - ret = scnprintf(hpp->buf, hpp->size, "%6s ", "n/a"); \ - } - switch (c2c.display) { case DISPLAY_RMT: - DISPLAY_HITM(rmt_hitm); + ret = display_metrics(hpp, stats->rmt_hitm, + c2c_he->stats.rmt_hitm); break; case DISPLAY_LCL: - DISPLAY_HITM(lcl_hitm); + ret = display_metrics(hpp, stats->lcl_hitm, + c2c_he->stats.lcl_hitm); break; case DISPLAY_TOT: - DISPLAY_HITM(tot_hitm); + ret = display_metrics(hpp, stats->tot_hitm, + c2c_he->stats.tot_hitm); + break; default: break; } - #undef DISPLAY_HITM - advance_hpp(hpp, ret); if (c2c_he->stats.store > 0) { @@ -1851,53 +1858,69 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists, #define DISPLAY_LINE_LIMIT 0.001 +static u8 filter_display(u32 val, u32 sum) +{ + if (sum == 0 || ((double)val / sum) < DISPLAY_LINE_LIMIT) + return HIST_FILTER__C2C; + + return 0; +} + static bool he__display(struct hist_entry *he, struct c2c_stats *stats) { struct c2c_hist_entry *c2c_he; - double ld_dist; if (c2c.show_all) return true; c2c_he = container_of(he, struct c2c_hist_entry, he); -#define FILTER_HITM(__h) \ - if (stats->__h) { \ - ld_dist = ((double)c2c_he->stats.__h / stats->__h); \ - if (ld_dist < DISPLAY_LINE_LIMIT) \ - he->filtered = HIST_FILTER__C2C; \ - } else { \ - he->filtered = HIST_FILTER__C2C; \ - } - switch (c2c.display) { case DISPLAY_LCL: - FILTER_HITM(lcl_hitm); + he->filtered = filter_display(c2c_he->stats.lcl_hitm, + stats->lcl_hitm); break; case DISPLAY_RMT: - FILTER_HITM(rmt_hitm); + he->filtered = filter_display(c2c_he->stats.rmt_hitm, + stats->rmt_hitm); break; case DISPLAY_TOT: - FILTER_HITM(tot_hitm); + he->filtered = filter_display(c2c_he->stats.tot_hitm, + stats->tot_hitm); + break; default: break; } -#undef FILTER_HITM - return he->filtered == 0; } -static inline int valid_hitm_or_store(struct hist_entry *he) +static inline bool is_valid_hist_entry(struct hist_entry *he) { struct c2c_hist_entry *c2c_he; - bool has_hitm; + bool has_record = false; c2c_he = container_of(he, struct c2c_hist_entry, he); - has_hitm = c2c.display == DISPLAY_TOT ? c2c_he->stats.tot_hitm : - c2c.display == DISPLAY_LCL ? c2c_he->stats.lcl_hitm : - c2c_he->stats.rmt_hitm; - return has_hitm || c2c_he->stats.store; + + /* It's a valid entry if contains stores */ + if (c2c_he->stats.store) + return true; + + switch (c2c.display) { + case DISPLAY_LCL: + has_record = !!c2c_he->stats.lcl_hitm; + break; + case DISPLAY_RMT: + has_record = !!c2c_he->stats.rmt_hitm; + break; + case DISPLAY_TOT: + has_record = !!c2c_he->stats.tot_hitm; + break; + default: + break; + } + + return has_record; } static void set_node_width(struct c2c_hist_entry *c2c_he, int len) @@ -1951,7 +1974,7 @@ static int filter_cb(struct hist_entry *he, void *arg __maybe_unused) calc_width(c2c_he); - if (!valid_hitm_or_store(he)) + if (!is_valid_hist_entry(he)) he->filtered = HIST_FILTER__C2C; return 0; @@ -1961,7 +1984,7 @@ static int resort_cl_cb(struct hist_entry *he, void *arg __maybe_unused) { struct c2c_hist_entry *c2c_he; struct c2c_hists *c2c_hists; - bool display = he__display(he, &c2c.hitm_stats); + bool display = he__display(he, &c2c.shared_clines_stats); c2c_he = container_of(he, struct c2c_hist_entry, he); c2c_hists = c2c_he->hists; @@ -2048,14 +2071,14 @@ static int setup_nodes(struct perf_session *session) #define HAS_HITMS(__h) ((__h)->stats.lcl_hitm || (__h)->stats.rmt_hitm) -static int resort_hitm_cb(struct hist_entry *he, void *arg __maybe_unused) +static int resort_shared_cl_cb(struct hist_entry *he, void *arg __maybe_unused) { struct c2c_hist_entry *c2c_he; c2c_he = container_of(he, struct c2c_hist_entry, he); if (HAS_HITMS(c2c_he)) { c2c.shared_clines++; - c2c_add_stats(&c2c.hitm_stats, &c2c_he->stats); + c2c_add_stats(&c2c.shared_clines_stats, &c2c_he->stats); } return 0; @@ -2126,7 +2149,7 @@ static void print_c2c__display_stats(FILE *out) static void print_shared_cacheline_info(FILE *out) { - struct c2c_stats *stats = &c2c.hitm_stats; + struct c2c_stats *stats = &c2c.shared_clines_stats; int hitm_cnt = stats->lcl_hitm + stats->rmt_hitm; fprintf(out, "=================================================\n"); @@ -2176,16 +2199,17 @@ static void print_pareto(FILE *out) struct perf_hpp_list hpp_list; struct rb_node *nd; int ret; + const char *cl_output; + + cl_output = "cl_num," + "cl_rmt_hitm," + "cl_lcl_hitm," + "cl_stores_l1hit," + "cl_stores_l1miss," + "dcacheline"; perf_hpp_list__init(&hpp_list); - ret = hpp_list__parse(&hpp_list, - "cl_num," - "cl_rmt_hitm," - "cl_lcl_hitm," - "cl_stores_l1hit," - "cl_stores_l1miss," - "dcacheline", - NULL); + ret = hpp_list__parse(&hpp_list, cl_output, NULL); if (WARN_ONCE(ret, "failed to setup sort entries\n")) return; @@ -2729,6 +2753,7 @@ static int perf_c2c__report(int argc, const char **argv) OPT_END() }; int err = 0; + const char *output_str, *sort_str = NULL; argc = parse_options(argc, argv, options, report_c2c_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -2805,29 +2830,34 @@ static int perf_c2c__report(int argc, const char **argv) goto out_mem2node; } - c2c_hists__reinit(&c2c.hists, - "cl_idx," - "dcacheline," - "dcacheline_node," - "dcacheline_count," - "percent_hitm," - "tot_hitm,lcl_hitm,rmt_hitm," - "tot_recs," - "tot_loads," - "tot_stores," - "stores_l1hit,stores_l1miss," - "ld_fbhit,ld_l1hit,ld_l2hit," - "ld_lclhit,lcl_hitm," - "ld_rmthit,rmt_hitm," - "dram_lcl,dram_rmt", - c2c.display == DISPLAY_TOT ? "tot_hitm" : - c2c.display == DISPLAY_LCL ? "lcl_hitm" : "rmt_hitm" - ); + output_str = "cl_idx," + "dcacheline," + "dcacheline_node," + "dcacheline_count," + "percent_hitm," + "tot_hitm,lcl_hitm,rmt_hitm," + "tot_recs," + "tot_loads," + "tot_stores," + "stores_l1hit,stores_l1miss," + "ld_fbhit,ld_l1hit,ld_l2hit," + "ld_lclhit,lcl_hitm," + "ld_rmthit,rmt_hitm," + "dram_lcl,dram_rmt"; + + if (c2c.display == DISPLAY_TOT) + sort_str = "tot_hitm"; + else if (c2c.display == DISPLAY_RMT) + sort_str = "rmt_hitm"; + else if (c2c.display == DISPLAY_LCL) + sort_str = "lcl_hitm"; + + c2c_hists__reinit(&c2c.hists, output_str, sort_str); ui_progress__init(&prog, c2c.hists.hists.nr_entries, "Sorting..."); hists__collapse_resort(&c2c.hists.hists, NULL); - hists__output_resort_cb(&c2c.hists.hists, &prog, resort_hitm_cb); + hists__output_resort_cb(&c2c.hists.hists, &prog, resort_shared_cl_cb); hists__iterate_cb(&c2c.hists.hists, resort_cl_cb); ui_progress__finish(); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 43937f4b399a..6fe44d97fde5 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -313,7 +313,7 @@ static int perf_event__jit_repipe_mmap(struct perf_tool *tool, * if jit marker, then inject jit mmaps and generate ELF images */ ret = jit_process(inject->session, &inject->output, machine, - event->mmap.filename, event->mmap.pid, &n); + event->mmap.filename, event->mmap.pid, event->mmap.tid, &n); if (ret < 0) return ret; if (ret) { @@ -413,7 +413,7 @@ static int perf_event__jit_repipe_mmap2(struct perf_tool *tool, * if jit marker, then inject jit mmaps and generate ELF images */ ret = jit_process(inject->session, &inject->output, machine, - event->mmap2.filename, event->mmap2.pid, &n); + event->mmap2.filename, event->mmap2.pid, event->mmap2.tid, &n); if (ret < 0) return ret; if (ret) { diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 823742036ddb..f3aac85aa9d4 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -30,6 +30,7 @@ struct perf_mem { bool dump_raw; bool force; bool phys_addr; + bool data_page_size; int operation; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -124,6 +125,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) if (mem->phys_addr) rec_argv[i++] = "--phys-data"; + if (mem->data_page_size) + rec_argv[i++] = "--data-page-size"; + for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { e = perf_mem_events__ptr(j); if (!e->record) @@ -172,7 +176,8 @@ dump_raw_samples(struct perf_tool *tool, { struct perf_mem *mem = container_of(tool, struct perf_mem, tool); struct addr_location al; - const char *fmt; + const char *fmt, *field_sep; + char str[PAGE_SIZE_NAME_LEN]; if (machine__resolve(machine, &al, sample) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", @@ -186,60 +191,47 @@ dump_raw_samples(struct perf_tool *tool, if (al.map != NULL) al.map->dso->hit = 1; - if (mem->phys_addr) { - if (symbol_conf.field_sep) { - fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64 - "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n"; - } else { - fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64 - "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64 - "%s%s:%s\n"; - symbol_conf.field_sep = " "; - } + field_sep = symbol_conf.field_sep; + if (field_sep) { + fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s"; + } else { + fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64"%s"; + symbol_conf.field_sep = " "; + } + printf(fmt, + sample->pid, + symbol_conf.field_sep, + sample->tid, + symbol_conf.field_sep, + sample->ip, + symbol_conf.field_sep, + sample->addr, + symbol_conf.field_sep); - printf(fmt, - sample->pid, - symbol_conf.field_sep, - sample->tid, - symbol_conf.field_sep, - sample->ip, - symbol_conf.field_sep, - sample->addr, - symbol_conf.field_sep, + if (mem->phys_addr) { + printf("0x%016"PRIx64"%s", sample->phys_addr, - symbol_conf.field_sep, - sample->weight, - symbol_conf.field_sep, - sample->data_src, - symbol_conf.field_sep, - al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", - al.sym ? al.sym->name : "???"); - } else { - if (symbol_conf.field_sep) { - fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64 - "%s0x%"PRIx64"%s%s:%s\n"; - } else { - fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64 - "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n"; - symbol_conf.field_sep = " "; - } + symbol_conf.field_sep); + } - printf(fmt, - sample->pid, - symbol_conf.field_sep, - sample->tid, - symbol_conf.field_sep, - sample->ip, - symbol_conf.field_sep, - sample->addr, - symbol_conf.field_sep, - sample->weight, - symbol_conf.field_sep, - sample->data_src, - symbol_conf.field_sep, - al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", - al.sym ? al.sym->name : "???"); + if (mem->data_page_size) { + printf("%s%s", + get_page_size_name(sample->data_page_size, str), + symbol_conf.field_sep); } + + if (field_sep) + fmt = "%"PRIu64"%s0x%"PRIx64"%s%s:%s\n"; + else + fmt = "%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n"; + + printf(fmt, + sample->weight, + symbol_conf.field_sep, + sample->data_src, + symbol_conf.field_sep, + al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", + al.sym ? al.sym->name : "???"); out_put: addr_location__put(&al); return 0; @@ -287,10 +279,15 @@ static int report_raw_events(struct perf_mem *mem) if (ret < 0) goto out_delete; + printf("# PID, TID, IP, ADDR, "); + if (mem->phys_addr) - printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); - else - printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); + printf("PHYS ADDR, "); + + if (mem->data_page_size) + printf("DATA PAGE SIZE, "); + + printf("LOCAL WEIGHT, DSRC, SYMBOL\n"); ret = perf_session__process_events(session); @@ -300,7 +297,7 @@ out_delete: } static char *get_sort_order(struct perf_mem *mem) { - bool has_extra_options = mem->phys_addr ? true : false; + bool has_extra_options = (mem->phys_addr | mem->data_page_size) ? true : false; char sort[128]; /* @@ -319,6 +316,9 @@ static char *get_sort_order(struct perf_mem *mem) if (mem->phys_addr) strcat(sort, ",phys_daddr"); + if (mem->data_page_size) + strcat(sort, ",data_page_size"); + return strdup(sort); } @@ -464,6 +464,7 @@ int cmd_mem(int argc, const char **argv) " between columns '.' is reserved."), OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"), OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"), + OPT_BOOLEAN(0, "data-page-size", &mem.data_page_size, "Record/Report sample data address page size"), OPT_END() }; const char *const mem_subcommands[] = { "record", "report", NULL }; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fd3911650612..8a0127d4fb52 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -102,6 +102,7 @@ struct record { bool no_buildid_cache; bool no_buildid_cache_set; bool buildid_all; + bool buildid_mmap; bool timestamp_filename; bool timestamp_boundary; struct switch_output switch_output; @@ -1937,18 +1938,19 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (evlist__ctlfd_process(rec->evlist, &cmd) > 0) { switch (cmd) { - case EVLIST_CTL_CMD_ENABLE: - pr_info(EVLIST_ENABLED_MSG); - break; - case EVLIST_CTL_CMD_DISABLE: - pr_info(EVLIST_DISABLED_MSG); - break; case EVLIST_CTL_CMD_SNAPSHOT: hit_auxtrace_snapshot_trigger(rec); evlist__ctlfd_ack(rec->evlist); break; + case EVLIST_CTL_CMD_STOP: + done = 1; + break; case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: + case EVLIST_CTL_CMD_ENABLE: + case EVLIST_CTL_CMD_DISABLE: + case EVLIST_CTL_CMD_EVLIST: + case EVLIST_CTL_CMD_PING: default: break; } @@ -2135,6 +2137,8 @@ static int perf_record_config(const char *var, const char *value, void *cb) rec->no_buildid_cache = true; else if (!strcmp(value, "skip")) rec->no_buildid = true; + else if (!strcmp(value, "mmap")) + rec->buildid_mmap = true; else return -1; return 0; @@ -2474,6 +2478,8 @@ static struct option __record_options[] = { "Record the sample physical addresses"), OPT_BOOLEAN(0, "data-page-size", &record.opts.sample_data_page_size, "Record the sampled data address data page size"), + OPT_BOOLEAN(0, "code-page-size", &record.opts.sample_code_page_size, + "Record the sampled code address (ip) page size"), OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"), OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time, &record.opts.sample_time_set, @@ -2552,6 +2558,8 @@ static struct option __record_options[] = { "file", "vmlinux pathname"), OPT_BOOLEAN(0, "buildid-all", &record.buildid_all, "Record build-id of all DSOs regardless of hits"), + OPT_BOOLEAN(0, "buildid-mmap", &record.buildid_mmap, + "Record build-id in map events"), OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename, "append timestamp to output filename"), OPT_BOOLEAN(0, "timestamp-boundary", &record.timestamp_boundary, @@ -2655,6 +2663,21 @@ int cmd_record(int argc, const char **argv) } + if (rec->buildid_mmap) { + if (!perf_can_record_build_id()) { + pr_err("Failed: no support to record build id in mmap events, update your kernel.\n"); + err = -EINVAL; + goto out_opts; + } + pr_debug("Enabling build id in mmap2 events.\n"); + /* Enable mmap build id synthesizing. */ + symbol_conf.buildid_mmap2 = true; + /* Enable perf_event_attr::build_id bit. */ + rec->opts.build_id = true; + /* Disable build id cache. */ + rec->no_buildid = true; + } + if (rec->opts.kcore) rec->data.is_dir = true; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 42dad4a0f8cf..62bb0f1c35c3 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -117,6 +117,7 @@ enum perf_output_field { PERF_OUTPUT_IPC = 1ULL << 31, PERF_OUTPUT_TOD = 1ULL << 32, PERF_OUTPUT_DATA_PAGE_SIZE = 1ULL << 33, + PERF_OUTPUT_CODE_PAGE_SIZE = 1ULL << 34, }; struct perf_script { @@ -182,6 +183,7 @@ struct output_option { {.str = "ipc", .field = PERF_OUTPUT_IPC}, {.str = "tod", .field = PERF_OUTPUT_TOD}, {.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE}, + {.str = "code_page_size", .field = PERF_OUTPUT_CODE_PAGE_SIZE}, }; enum { @@ -256,7 +258,7 @@ static struct { PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR | - PERF_OUTPUT_DATA_PAGE_SIZE, + PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -523,6 +525,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) evsel__check_stype(evsel, PERF_SAMPLE_DATA_PAGE_SIZE, "DATA_PAGE_SIZE", PERF_OUTPUT_DATA_PAGE_SIZE)) return -EINVAL; + if (PRINT_FIELD(CODE_PAGE_SIZE) && + evsel__check_stype(evsel, PERF_SAMPLE_CODE_PAGE_SIZE, "CODE_PAGE_SIZE", PERF_OUTPUT_CODE_PAGE_SIZE)) + return -EINVAL; + return 0; } @@ -2036,6 +2042,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(DATA_PAGE_SIZE)) fprintf(fp, " %s", get_page_size_name(sample->data_page_size, str)); + if (PRINT_FIELD(CODE_PAGE_SIZE)) + fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str)); + perf_sample__fprintf_ipc(sample, attr, fp); fprintf(fp, "\n"); @@ -3535,10 +3544,12 @@ int cmd_script(int argc, const char **argv) "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,bpf-output,brstackinsn,brstackoff," "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod," - "data_page_size", + "data_page_size,code_page_size", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), + OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", + "only consider symbols in these DSOs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 8cc24967bc27..b009dde5c601 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -67,6 +67,7 @@ #include "util/top.h" #include "util/affinity.h" #include "util/pfm.h" +#include "util/bpf_counter.h" #include "asm/bug.h" #include <linux/time64.h> @@ -409,12 +410,32 @@ static int read_affinity_counters(struct timespec *rs) return 0; } +static int read_bpf_map_counters(void) +{ + struct evsel *counter; + int err; + + evlist__for_each_entry(evsel_list, counter) { + err = bpf_counter__read(counter); + if (err) + return err; + } + return 0; +} + static void read_counters(struct timespec *rs) { struct evsel *counter; + int err; - if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0)) - return; + if (!stat_config.stop_read_counter) { + if (target__has_bpf(&target)) + err = read_bpf_map_counters(); + else + err = read_affinity_counters(rs); + if (err < 0) + return; + } evlist__for_each_entry(evsel_list, counter) { if (counter->err) @@ -496,11 +517,22 @@ static bool handle_interval(unsigned int interval, int *times) return false; } -static void enable_counters(void) +static int enable_counters(void) { + struct evsel *evsel; + int err; + + if (target__has_bpf(&target)) { + evlist__for_each_entry(evsel_list, evsel) { + err = bpf_counter__enable(evsel); + if (err) + return err; + } + } + if (stat_config.initial_delay < 0) { pr_info(EVLIST_DISABLED_MSG); - return; + return 0; } if (stat_config.initial_delay > 0) { @@ -518,6 +550,7 @@ static void enable_counters(void) if (stat_config.initial_delay > 0) pr_info(EVLIST_ENABLED_MSG); } + return 0; } static void disable_counters(void) @@ -578,18 +611,19 @@ static void process_evlist(struct evlist *evlist, unsigned int interval) if (evlist__ctlfd_process(evlist, &cmd) > 0) { switch (cmd) { case EVLIST_CTL_CMD_ENABLE: - pr_info(EVLIST_ENABLED_MSG); if (interval) process_interval(); break; case EVLIST_CTL_CMD_DISABLE: if (interval) process_interval(); - pr_info(EVLIST_DISABLED_MSG); break; case EVLIST_CTL_CMD_SNAPSHOT: case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: + case EVLIST_CTL_CMD_EVLIST: + case EVLIST_CTL_CMD_STOP: + case EVLIST_CTL_CMD_PING: default: break; } @@ -720,7 +754,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) const bool forks = (argc > 0); bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false; struct affinity affinity; - int i, cpu; + int i, cpu, err; bool second_pass = false; if (forks) { @@ -737,6 +771,13 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (affinity__setup(&affinity) < 0) return -1; + if (target__has_bpf(&target)) { + evlist__for_each_entry(evsel_list, counter) { + if (bpf_counter__load(counter, &target)) + return -1; + } + } + evlist__for_each_cpu (evsel_list, i, cpu) { affinity__set(&affinity, cpu); @@ -850,7 +891,7 @@ try_again_reset: } if (STAT_RECORD) { - int err, fd = perf_data__fd(&perf_stat.data); + int fd = perf_data__fd(&perf_stat.data); if (is_pipe) { err = perf_header__write_pipe(perf_data__fd(&perf_stat.data)); @@ -876,7 +917,9 @@ try_again_reset: if (forks) { evlist__start_workload(evsel_list); - enable_counters(); + err = enable_counters(); + if (err) + return -1; if (interval || timeout || evlist__ctlfd_initialized(evsel_list)) status = dispatch_events(forks, timeout, interval, ×); @@ -895,7 +938,9 @@ try_again_reset: if (WIFSIGNALED(status)) psignal(WTERMSIG(status), argv[0]); } else { - enable_counters(); + err = enable_counters(); + if (err) + return -1; status = dispatch_events(forks, timeout, interval, ×); } @@ -1085,6 +1130,10 @@ static struct option stat_options[] = { "stat events on existing process id"), OPT_STRING('t', "tid", &target.tid, "tid", "stat events on existing thread id"), +#ifdef HAVE_BPF_SKEL + OPT_STRING('b', "bpf-prog", &target.bpf_str, "bpf-prog-id", + "stat events on existing bpf program id"), +#endif OPT_BOOLEAN('a', "all-cpus", &target.system_wide, "system-wide collection from all CPUs"), OPT_BOOLEAN('g', "group", &group, @@ -1779,6 +1828,9 @@ setup_metrics: } if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0) return -1; + + if (arch_evlist__add_default_attrs(evsel_list) < 0) + return -1; } /* Detailed events get appended to the event list: */ @@ -2064,11 +2116,12 @@ int cmd_stat(int argc, const char **argv) "perf stat [<options>] [<command>]", NULL }; - int status = -EINVAL, run_idx; + int status = -EINVAL, run_idx, err; const char *mode; FILE *output = stderr; unsigned int interval, timeout; const char * const stat_subcommands[] = { "record", "report" }; + char errbuf[BUFSIZ]; setlocale(LC_ALL, ""); @@ -2179,6 +2232,12 @@ int cmd_stat(int argc, const char **argv) } else if (big_num_opt == 0) /* User passed --no-big-num */ stat_config.big_num = false; + err = target__validate(&target); + if (err) { + target__strerror(&target, err, errbuf, BUFSIZ); + pr_warning("%s\n", errbuf); + } + setup_system_wide(argc); /* @@ -2252,8 +2311,6 @@ int cmd_stat(int argc, const char **argv) } } - target__validate(&target); - if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide)) target.per_thread = true; @@ -2384,9 +2441,10 @@ int cmd_stat(int argc, const char **argv) * tools remain -acme */ int fd = perf_data__fd(&perf_stat.data); - int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat, - process_synthesized_event, - &perf_stat.session->machines.host); + + err = perf_event__synthesize_kernel_mmap((void *)&perf_stat, + process_synthesized_event, + &perf_stat.session->machines.host); if (err) { pr_warning("Couldn't synthesize the kernel mmap record, harmless, " "older tools may produce warnings about this file\n."); diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json index 2d15b11e5383..5c69c1e82ef8 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json @@ -9,15 +9,11 @@ "ArchStdEvent": "BR_INDIRECT_SPEC" }, { - "PublicDescription": "Mispredicted or not predicted branch speculatively executed", - "EventCode": "0x10", - "EventName": "BR_MIS_PRED", + "ArchStdEvent": "BR_MIS_PRED", "BriefDescription": "Branch mispredicted" }, { - "PublicDescription": "Predictable branch speculatively executed", - "EventCode": "0x12", - "EventName": "BR_PRED", + "ArchStdEvent": "BR_PRED", "BriefDescription": "Predictable branch" } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json index 5c1a9a922ca4..9bea1ba1c4d2 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json @@ -18,9 +18,6 @@ "ArchStdEvent": "BUS_ACCESS_PERIPH" }, { - "PublicDescription": "Bus access", - "EventCode": "0x19", - "EventName": "BUS_ACCESS", - "BriefDescription": "Bus access" + "ArchStdEvent": "BUS_ACCESS", } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json index 40010a8724b3..1e25f2ae4ae0 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json @@ -39,70 +39,40 @@ "ArchStdEvent": "L2D_CACHE_INVAL" }, { - "PublicDescription": "Level 1 instruction cache refill", - "EventCode": "0x01", - "EventName": "L1I_CACHE_REFILL", - "BriefDescription": "L1I cache refill" + "ArchStdEvent": "L1I_CACHE_REFILL", }, { - "PublicDescription": "Level 1 instruction TLB refill", - "EventCode": "0x02", - "EventName": "L1I_TLB_REFILL", - "BriefDescription": "L1I TLB refill" + "ArchStdEvent": "L1I_TLB_REFILL", }, { - "PublicDescription": "Level 1 data cache refill", - "EventCode": "0x03", - "EventName": "L1D_CACHE_REFILL", - "BriefDescription": "L1D cache refill" + "ArchStdEvent": "L1D_CACHE_REFILL", }, { - "PublicDescription": "Level 1 data cache access", - "EventCode": "0x04", - "EventName": "L1D_CACHE_ACCESS", - "BriefDescription": "L1D cache access" + "ArchStdEvent": "L1D_CACHE", }, { - "PublicDescription": "Level 1 data TLB refill", - "EventCode": "0x05", - "EventName": "L1D_TLB_REFILL", - "BriefDescription": "L1D TLB refill" + "ArchStdEvent": "L1D_TLB_REFILL", }, { - "PublicDescription": "Level 1 instruction cache access", - "EventCode": "0x14", - "EventName": "L1I_CACHE_ACCESS", - "BriefDescription": "L1I cache access" + "ArchStdEvent": "L1I_CACHE", }, { - "PublicDescription": "Level 2 data cache access", - "EventCode": "0x16", - "EventName": "L2D_CACHE_ACCESS", - "BriefDescription": "L2D cache access" + "ArchStdEvent": "L2D_CACHE", }, { - "PublicDescription": "Level 2 data refill", - "EventCode": "0x17", - "EventName": "L2D_CACHE_REFILL", - "BriefDescription": "L2D cache refill" + "ArchStdEvent": "L2D_CACHE_REFILL", }, { - "PublicDescription": "Level 2 data cache, Write-Back", - "EventCode": "0x18", - "EventName": "L2D_CACHE_WB", - "BriefDescription": "L2D cache Write-Back" + "ArchStdEvent": "L2D_CACHE_WB", }, { - "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB", - "EventCode": "0x25", - "EventName": "L1D_TLB_ACCESS", + "PublicDescription": "This event counts any load or store operation which accesses the data L1 TLB", + "ArchStdEvent": "L1D_TLB", "BriefDescription": "L1D TLB access" }, { - "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB", - "EventCode": "0x26", - "EventName": "L1I_TLB_ACCESS", - "BriefDescription": "L1I TLB access" + "PublicDescription": "This event counts any instruction fetch which accesses the instruction L1 TLB", + "ArchStdEvent": "L1I_TLB", }, { "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count", @@ -114,7 +84,7 @@ "PublicDescription": "Level 2 access to instruciton TLB that caused a page table walk. This event counts on any instruciton access which causes L2I_TLB_REFILL to count", "EventCode": "0x35", "EventName": "L2I_TLB_ACCESS", - "BriefDescription": "L2D TLB access" + "BriefDescription": "L2I TLB access" }, { "PublicDescription": "Branch target buffer misprediction", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json index 51d1dc1519b2..9076ca2daf9e 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json @@ -1,9 +1,7 @@ [ { "PublicDescription": "The number of core clock cycles", - "EventCode": "0x11", - "EventName": "CPU_CYCLES", - "BriefDescription": "Clock cycles" + "ArchStdEvent": "CPU_CYCLES", }, { "PublicDescription": "FSU clocking gated off cycle", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json index 66e51bc64b22..9761433ad329 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json @@ -36,15 +36,9 @@ "ArchStdEvent": "EXC_TRAP_FIQ" }, { - "PublicDescription": "Exception taken", - "EventCode": "0x09", - "EventName": "EXC_TAKEN", - "BriefDescription": "Exception taken" + "ArchStdEvent": "EXC_TAKEN", }, { - "PublicDescription": "Instruction architecturally executed, condition check pass, exception return", - "EventCode": "0x0a", - "EventName": "EXC_RETURN", - "BriefDescription": "Exception return" + "ArchStdEvent": "EXC_RETURN", } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json index 0d3e46776642..482aa3f19e58 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json @@ -40,45 +40,29 @@ }, { "PublicDescription": "Instruction architecturally executed, software increment", - "EventCode": "0x00", - "EventName": "SW_INCR", + "ArchStdEvent": "SW_INCR", "BriefDescription": "Software increment" }, { - "PublicDescription": "Instruction architecturally executed", - "EventCode": "0x08", - "EventName": "INST_RETIRED", - "BriefDescription": "Instruction retired" + "ArchStdEvent": "INST_RETIRED", }, { - "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR", - "EventCode": "0x0b", - "EventName": "CID_WRITE_RETIRED", + "ArchStdEvent": "CID_WRITE_RETIRED", "BriefDescription": "Write to CONTEXTIDR" }, { - "PublicDescription": "Operation speculatively executed", - "EventCode": "0x1b", - "EventName": "INST_SPEC", - "BriefDescription": "Speculatively executed" + "ArchStdEvent": "INST_SPEC", }, { - "PublicDescription": "Instruction architecturally executed (condition check pass), write to TTBR", - "EventCode": "0x1c", - "EventName": "TTBR_WRITE_RETIRED", - "BriefDescription": "Instruction executed, TTBR write" + "ArchStdEvent": "TTBR_WRITE_RETIRED", }, { - "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches", - "EventCode": "0x21", - "EventName": "BR_RETIRED", - "BriefDescription": "Branch retired" + "PublicDescription": "This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches", + "ArchStdEvent": "BR_RETIRED", }, { - "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush", - "EventCode": "0x22", - "EventName": "BR_MISPRED_RETIRED", - "BriefDescription": "Mispredicted branch retired" + "PublicDescription": "This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush", + "ArchStdEvent": "BR_MIS_PRED_RETIRED", }, { "PublicDescription": "Operation speculatively executed, NOP", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json index c2fe674df960..2e7555696caf 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json @@ -15,15 +15,10 @@ "ArchStdEvent": "UNALIGNED_LDST_SPEC" }, { - "PublicDescription": "Data memory access", - "EventCode": "0x13", - "EventName": "MEM_ACCESS", - "BriefDescription": "Memory access" + "ArchStdEvent": "MEM_ACCESS", }, { - "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", - "EventCode": "0x1a", - "EventName": "MEM_ERROR", - "BriefDescription": "Memory error" + "PublicDescription": "This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", + "ArchStdEvent": "MEMORY_ERROR", } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json index b5e5d055c70d..ec0dc92288ab 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json @@ -1,14 +1,10 @@ [ { - "PublicDescription": "Mispredicted or not predicted branch speculatively executed. This event counts any predictable branch instruction which is mispredicted either due to dynamic misprediction or because the MMU is off and the branches are statically predicted not taken.", - "EventCode": "0x10", - "EventName": "BR_MIS_PRED", - "BriefDescription": "Mispredicted or not predicted branch speculatively executed." + "PublicDescription": "This event counts any predictable branch instruction which is mispredicted either due to dynamic misprediction or because the MMU is off and the branches are statically predicted not taken", + "ArchStdEvent": "BR_MIS_PRED", }, { - "PublicDescription": "Predictable branch speculatively executed. This event counts all predictable branches.", - "EventCode": "0x12", - "EventName": "BR_PRED", - "BriefDescription": "Predictable branch speculatively executed." + "PublicDescription": "This event counts all predictable branches.", + "ArchStdEvent": "BR_PRED", } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json index fce7309ae624..6263929efce2 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json @@ -1,24 +1,21 @@ [ { - "EventCode": "0x11", - "EventName": "CPU_CYCLES", + "PublicDescription": "The number of core clock cycles" + "ArchStdEvent": "CPU_CYCLES", "BriefDescription": "The number of core clock cycles." }, { - "PublicDescription": "Bus access. This event counts for every beat of data transferred over the data channels between the core and the SCU. If both read and write data beats are transferred on a given cycle, this event is counted twice on that cycle. This event counts the sum of BUS_ACCESS_RD and BUS_ACCESS_WR.", - "EventCode": "0x19", - "EventName": "BUS_ACCESS", - "BriefDescription": "Bus access." + "PublicDescription": "This event counts for every beat of data transferred over the data channels between the core and the SCU. If both read and write data beats are transferred on a given cycle, this event is counted twice on that cycle. This event counts the sum of BUS_ACCESS_RD and BUS_ACCESS_WR.", + "ArchStdEvent": "BUS_ACCESS", }, { - "EventCode": "0x1D", - "EventName": "BUS_CYCLES", - "BriefDescription": "Bus cycles. This event duplicates CPU_CYCLES." + "PublicDescription": "This event duplicates CPU_CYCLES." + "ArchStdEvent": "BUS_CYCLES", }, { - "ArchStdEvent": "BUS_ACCESS_RD" + "ArchStdEvent": "BUS_ACCESS_RD", }, { - "ArchStdEvent": "BUS_ACCESS_WR" + "ArchStdEvent": "BUS_ACCESS_WR", } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json index 24594081c199..cd67bb9df139 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json @@ -1,133 +1,95 @@ [ { - "PublicDescription": "L1 instruction cache refill. This event counts any instruction fetch which misses in the cache.", - "EventCode": "0x01", - "EventName": "L1I_CACHE_REFILL", - "BriefDescription": "L1 instruction cache refill" + "PublicDescription": "This event counts any instruction fetch which misses in the cache.", + "ArchStdEvent": "L1I_CACHE_REFILL", }, { - "PublicDescription": "L1 instruction TLB refill. This event counts any refill of the instruction L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", - "EventCode": "0x02", - "EventName": "L1I_TLB_REFILL", - "BriefDescription": "L1 instruction TLB refill" + "PublicDescription": "This event counts any refill of the instruction L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", + "ArchStdEvent": "L1I_TLB_REFILL", }, { - "PublicDescription": "L1 data cache refill. This event counts any load or store operation or page table walk access which causes data to be read from outside the L1, including accesses which do not allocate into L1.", - "EventCode": "0x03", - "EventName": "L1D_CACHE_REFILL", - "BriefDescription": "L1 data cache refill" + "PublicDescription": "This event counts any load or store operation or page table walk access which causes data to be read from outside the L1, including accesses which do not allocate into L1.", + "ArchStdEvent": "L1D_CACHE_REFILL", }, { - "PublicDescription": "L1 data cache access. This event counts any load or store operation or page table walk access which looks up in the L1 data cache. In particular, any access which could count the L1D_CACHE_REFILL event causes this event to count.", - "EventCode": "0x04", - "EventName": "L1D_CACHE", - "BriefDescription": "L1 data cache access" + "PublicDescription": "This event counts any load or store operation or page table walk access which looks up in the L1 data cache. In particular, any access which could count the L1D_CACHE_REFILL event causes this event to count.", + "ArchStdEvent": "L1D_CACHE", }, { - "PublicDescription": "L1 data TLB refill. This event counts any refill of the data L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", - "EventCode": "0x05", - "EventName": "L1D_TLB_REFILL", - "BriefDescription": "L1 data TLB refill" + "PublicDescription": "This event counts any refill of the data L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", + "ArchStdEvent": "L1D_TLB_REFILL", }, - { + {, "PublicDescription": "Level 1 instruction cache access or Level 0 Macro-op cache access. This event counts any instruction fetch which accesses the L1 instruction cache or L0 Macro-op cache.", - "EventCode": "0x14", - "EventName": "L1I_CACHE", - "BriefDescription": "L1 instruction cache access" + "ArchStdEvent": "L1I_CACHE", }, { - "PublicDescription": "L1 data cache Write-Back. This event counts any write-back of data from the L1 data cache to L2 or L3. This counts both victim line evictions and snoops, including cache maintenance operations.", - "EventCode": "0x15", - "EventName": "L1D_CACHE_WB", - "BriefDescription": "L1 data cache Write-Back" + "PublicDescription": "This event counts any write-back of data from the L1 data cache to L2 or L3. This counts both victim line evictions and snoops, including cache maintenance operations.", + "ArchStdEvent": "L1D_CACHE_WB", }, { - "PublicDescription": "L2 data cache access. This event counts any transaction from L1 which looks up in the L2 cache, and any write-back from the L1 to the L2. Snoops from outside the core and cache maintenance operations are not counted.", - "EventCode": "0x16", - "EventName": "L2D_CACHE", - "BriefDescription": "L2 data cache access" + "PublicDescription": "This event counts any transaction from L1 which looks up in the L2 cache, and any write-back from the L1 to the L2. Snoops from outside the core and cache maintenance operations are not counted.", + "ArchStdEvent": "L2D_CACHE", }, { "PublicDescription": "L2 data cache refill. This event counts any cacheable transaction from L1 which causes data to be read from outside the core. L2 refills caused by stashes into L2 should not be counted", - "EventCode": "0x17", - "EventName": "L2D_CACHE_REFILL", - "BriefDescription": "L2 data cache refill" + "ArchStdEvent": "L2D_CACHE_REFILL", }, { - "PublicDescription": "L2 data cache write-back. This event counts any write-back of data from the L2 cache to outside the core. This includes snoops to the L2 which return data, regardless of whether they cause an invalidation. Invalidations from the L2 which do not write data outside of the core and snoops which return data from the L1 are not counted", - "EventCode": "0x18", - "EventName": "L2D_CACHE_WB", - "BriefDescription": "L2 data cache write-back" + "PublicDescription": "This event counts any write-back of data from the L2 cache to outside the core. This includes snoops to the L2 which return data, regardless of whether they cause an invalidation. Invalidations from the L2 which do not write data outside of the core and snoops which return data from the L1 are not counted", + "ArchStdEvent": "L2D_CACHE_WB", }, { - "PublicDescription": "L2 data cache allocation without refill. This event counts any full cache line write into the L2 cache which does not cause a linefill, including write-backs from L1 to L2 and full-line writes which do not allocate into L1.", - "EventCode": "0x20", - "EventName": "L2D_CACHE_ALLOCATE", - "BriefDescription": "L2 data cache allocation without refill" + "PublicDescription": "This event counts any full cache line write into the L2 cache which does not cause a linefill, including write-backs from L1 to L2 and full-line writes which do not allocate into L1.", + "ArchStdEvent": "L2D_CACHE_ALLOCATE", }, { - "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB. If both a load and a store are executed on a cycle, this event counts twice. This event counts regardless of whether the MMU is enabled.", - "EventCode": "0x25", - "EventName": "L1D_TLB", + "PublicDescription": "This event counts any load or store operation which accesses the data L1 TLB. If both a load and a store are executed on a cycle, this event counts twice. This event counts regardless of whether the MMU is enabled.", + "ArchStdEvent": "L1D_TLB", "BriefDescription": "Level 1 data TLB access." }, { - "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB.This event counts regardless of whether the MMU is enabled.", - "EventCode": "0x26", - "EventName": "L1I_TLB", + "PublicDescription": "This event counts any instruction fetch which accesses the instruction L1 TLB.This event counts regardless of whether the MMU is enabled.", + "ArchStdEvent": "L1I_TLB", "BriefDescription": "Level 1 instruction TLB access" }, { "PublicDescription": "This event counts any full cache line write into the L3 cache which does not cause a linefill, including write-backs from L2 to L3 and full-line writes which do not allocate into L2", - "EventCode": "0x29", - "EventName": "L3D_CACHE_ALLOCATE", + "ArchStdEvent": "L3D_CACHE_ALLOCATE", "BriefDescription": "Allocation without refill" }, { - "PublicDescription": "Attributable Level 3 unified cache refill. This event counts for any cacheable read transaction returning datafrom the SCU for which the data source was outside the cluster. Transactions such as ReadUnique are counted here as 'read' transactions, even though they can be generated by store instructions.", - "EventCode": "0x2A", - "EventName": "L3D_CACHE_REFILL", + "PublicDescription": "This event counts for any cacheable read transaction returning datafrom the SCU for which the data source was outside the cluster. Transactions such as ReadUnique are counted here as 'read' transactions, even though they can be generated by store instructions.", + "ArchStdEvent": "L3D_CACHE_REFILL", "BriefDescription": "Attributable Level 3 unified cache refill." }, { - "PublicDescription": "Attributable Level 3 unified cache access. This event counts for any cacheable read transaction returning datafrom the SCU, or for any cacheable write to the SCU.", - "EventCode": "0x2B", - "EventName": "L3D_CACHE", + "PublicDescription": "This event counts for any cacheable read transaction returning datafrom the SCU, or for any cacheable write to the SCU.", + "ArchStdEvent": "L3D_CACHE", "BriefDescription": "Attributable Level 3 unified cache access." }, { - "PublicDescription": "Attributable L2 data or unified TLB refill. This event counts on anyrefill of the L2 TLB, caused by either an instruction or data access.This event does not count if the MMU is disabled.", - "EventCode": "0x2D", - "EventName": "L2D_TLB_REFILL", + "PublicDescription": "This event counts on anyrefill of the L2 TLB, caused by either an instruction or data access.This event does not count if the MMU is disabled.", + "ArchStdEvent": "L2D_TLB_REFILL", "BriefDescription": "Attributable L2 data or unified TLB refill" }, { - "PublicDescription": "Attributable L2 data or unified TLB access. This event counts on any access to the L2 TLB (caused by a refill of any of the L1 TLBs). This event does not count if the MMU is disabled.", - "EventCode": "0x2F", - "EventName": "L2D_TLB", - "BriefDescription": "Attributable L2 data or unified TLB access" + "PublicDescription": "This event counts on any access to the L2 TLB (caused by a refill of any of the L1 TLBs). This event does not count if the MMU is disabled.", + "ArchStdEvent": "L2D_TLB", }, { - "PublicDescription": "Access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count.", - "EventCode": "0x34", - "EventName": "DTLB_WALK", - "BriefDescription": "Access to data TLB that caused a page table walk." + "PublicDescription": "This event counts on any data access which causes L2D_TLB_REFILL to count.", + "ArchStdEvent": "DTLB_WALK", }, { - "PublicDescription": "Access to instruction TLB that caused a page table walk. This event counts on any instruction access which causes L2D_TLB_REFILL to count.", - "EventCode": "0x35", - "EventName": "ITLB_WALK", - "BriefDescription": "Access to instruction TLB that caused a page table walk." + "PublicDescription": "This event counts on any instruction access which causes L2D_TLB_REFILL to count.", + "ArchStdEvent": "ITLB_WALK", }, { - "EventCode": "0x36", - "EventName": "LL_CACHE_RD", - "BriefDescription": "Last level cache access, read" + "ArchStdEvent": "LL_CACHE_RD", }, { - "EventCode": "0x37", - "EventName": "LL_CACHE_MISS_RD", - "BriefDescription": "Last level cache miss, read" + "ArchStdEvent": "LL_CACHE_MISS_RD", }, { "ArchStdEvent": "L1D_CACHE_INVAL" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json index 98d29c862320..ea4631db41b5 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json @@ -1,14 +1,10 @@ [ { - "EventCode": "0x09", - "EventName": "EXC_TAKEN", - "BriefDescription": "Exception taken." + "ArchStdEvent": "EXC_TAKEN", }, { - "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", - "EventCode": "0x1A", - "EventName": "MEMORY_ERROR", - "BriefDescription": "Local memory error." + "PublicDescription": "This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", + "ArchStdEvent": "MEMORY_ERROR", }, { "ArchStdEvent": "EXC_DABORT" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json index c153ac706d8d..8e59566cba8b 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json @@ -1,49 +1,32 @@ [ { - "PublicDescription": "Software increment. Instruction architecturally executed (condition code check pass).", - "EventCode": "0x00", - "EventName": "SW_INCR", - "BriefDescription": "Software increment." + "ArchStdEvent": "SW_INCR", }, { - "PublicDescription": "Instruction architecturally executed. This event counts all retired instructions, including those that fail their condition check.", - "EventCode": "0x08", - "EventName": "INST_RETIRED", - "BriefDescription": "Instruction architecturally executed." + "PublicDescription": "This event counts all retired instructions, including those that fail their condition check.", + "ArchStdEvent": "INST_RETIRED", }, { - "EventCode": "0x0A", - "EventName": "EXC_RETURN", - "BriefDescription": "Instruction architecturally executed, condition code check pass, exception return." + "ArchStdEvent": "EXC_RETURN", }, { - "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR. This event only counts writes to CONTEXTIDR in AArch32 state, and via the CONTEXTIDR_EL1 mnemonic in AArch64 state.", - "EventCode": "0x0B", - "EventName": "CID_WRITE_RETIRED", - "BriefDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR." + "PublicDescription": "This event only counts writes to CONTEXTIDR in AArch32 state, and via the CONTEXTIDR_EL1 mnemonic in AArch64 state.", + "ArchStdEvent": "CID_WRITE_RETIRED", }, { - "EventCode": "0x1B", - "EventName": "INST_SPEC", - "BriefDescription": "Operation speculatively executed" + "ArchStdEvent": "INST_SPEC", }, { - "PublicDescription": "Instruction architecturally executed, condition code check pass, write to TTBR. This event only counts writes to TTBR0/TTBR1 in AArch32 state and TTBR0_EL1/TTBR1_EL1 in AArch64 state.", - "EventCode": "0x1C", - "EventName": "TTBR_WRITE_RETIRED", - "BriefDescription": "Instruction architecturally executed, condition code check pass, write to TTBR" + "PublicDescription": "This event only counts writes to TTBR0/TTBR1 in AArch32 state and TTBR0_EL1/TTBR1_EL1 in AArch64 state.", + "ArchStdEvent": "TTBR_WRITE_RETIRED", }, - { - "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches.", - "EventCode": "0x21", - "EventName": "BR_RETIRED", - "BriefDescription": "Instruction architecturally executed, branch." + {, + "PublicDescription": "This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches.", + "ArchStdEvent": "BR_RETIRED", }, { - "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush.", - "EventCode": "0x22", - "EventName": "BR_MIS_PRED_RETIRED", - "BriefDescription": "Instruction architecturally executed, mispredicted branch." + "PublicDescription": "This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush.", + "ArchStdEvent": "BR_MIS_PRED_RETIRED", }, { "ArchStdEvent": "ASE_SPEC" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json index b86643253f19..f06f399051c1 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json @@ -1,9 +1,7 @@ [ { - "PublicDescription": "Data memory access. This event counts memory accesses due to load or store instructions. This event counts the sum of MEM_ACCESS_RD and MEM_ACCESS_WR.", - "EventCode": "0x13", - "EventName": "MEM_ACCESS", - "BriefDescription": "Data memory access" + "PublicDescription": "This event counts memory accesses due to load or store instructions. This event counts the sum of MEM_ACCESS_RD and MEM_ACCESS_WR.", + "ArchStdEvent": "MEM_ACCESS", }, { "ArchStdEvent": "MEM_ACCESS_RD" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json index 8bde029a62d5..c2ccbf6fbfa0 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json @@ -1,7 +1,5 @@ [ { - "EventCode": "0x31", - "EventName": "REMOTE_ACCESS", - "BriefDescription": "Access to another socket in a multi-socket system" + "ArchStdEvent": "REMOTE_ACCESS", } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json index 010a647f9d02..d79f0aeaf7f1 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json @@ -1,14 +1,10 @@ [ { - "PublicDescription": "No operation issued because of the frontend. The counter counts on any cycle when there are no fetched instructions available to dispatch.", - "EventCode": "0x23", - "EventName": "STALL_FRONTEND", - "BriefDescription": "No operation issued because of the frontend." + "PublicDescription": "The counter counts on any cycle when there are no fetched instructions available to dispatch.", + "ArchStdEvent": "STALL_FRONTEND", }, { - "PublicDescription": "No operation issued because of the backend. The counter counts on any cycle fetched instructions are not dispatched due to resource constraints.", - "EventCode": "0x24", - "EventName": "STALL_BACKEND", - "BriefDescription": "No operation issued because of the backend." + "PublicDescription": "The counter counts on any cycle fetched instructions are not dispatched due to resource constraints.", + "ArchStdEvent": "STALL_BACKEND", } ] diff --git a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json new file mode 100644 index 000000000000..75376c7cc072 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json @@ -0,0 +1,248 @@ +[ + { + "PublicDescription": "Instruction architecturally executed, Condition code check pass, software increment", + "EventCode": "0x00", + "EventName": "SW_INCR", + "BriefDescription": "Instruction architecturally executed, Condition code check pass, software increment" + }, + { + "PublicDescription": "Level 1 instruction cache refill", + "EventCode": "0x01", + "EventName": "L1I_CACHE_REFILL", + "BriefDescription": "Level 1 instruction cache refill" + }, + { + "PublicDescription": "Attributable Level 1 instruction TLB refill", + "EventCode": "0x02", + "EventName": "L1I_TLB_REFILL", + "BriefDescription": "Attributable Level 1 instruction TLB refill" + }, + { + "PublicDescription": "Level 1 data cache refill", + "EventCode": "0x03", + "EventName": "L1D_CACHE_REFILL", + "BriefDescription": "Level 1 data cache refill" + }, + { + "PublicDescription": "Level 1 data cache access", + "EventCode": "0x04", + "EventName": "L1D_CACHE", + "BriefDescription": "Level 1 data cache access" + }, + { + "PublicDescription": "Attributable Level 1 data TLB refill", + "EventCode": "0x05", + "EventName": "L1D_TLB_REFILL", + "BriefDescription": "Attributable Level 1 data TLB refill" + }, + { + "PublicDescription": "Instruction architecturally executed", + "EventCode": "0x08", + "EventName": "INST_RETIRED", + "BriefDescription": "Instruction architecturally executed" + }, + { + "PublicDescription": "Exception taken", + "EventCode": "0x09", + "EventName": "EXC_TAKEN", + "BriefDescription": "Exception taken" + }, + { + "PublicDescription": "Instruction architecturally executed, condition check pass, exception return", + "EventCode": "0x0a", + "EventName": "EXC_RETURN", + "BriefDescription": "Instruction architecturally executed, condition check pass, exception return" + }, + { + "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR", + "EventCode": "0x0b", + "EventName": "CID_WRITE_RETIRED", + "BriefDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR" + }, + { + "PublicDescription": "Mispredicted or not predicted branch speculatively executed", + "EventCode": "0x10", + "EventName": "BR_MIS_PRED", + "BriefDescription": "Mispredicted or not predicted branch speculatively executed" + }, + { + "PublicDescription": "Cycle", + "EventCode": "0x11", + "EventName": "CPU_CYCLES", + "BriefDescription": "Cycle" + }, + { + "PublicDescription": "Predictable branch speculatively executed", + "EventCode": "0x12", + "EventName": "BR_PRED", + "BriefDescription": "Predictable branch speculatively executed" + }, + { + "PublicDescription": "Data memory access", + "EventCode": "0x13", + "EventName": "MEM_ACCESS", + "BriefDescription": "Data memory access" + }, + { + "PublicDescription": "Attributable Level 1 instruction cache access", + "EventCode": "0x14", + "EventName": "L1I_CACHE", + "BriefDescription": "Attributable Level 1 instruction cache access" + }, + { + "PublicDescription": "Attributable Level 1 data cache write-back", + "EventCode": "0x15", + "EventName": "L1D_CACHE_WB", + "BriefDescription": "Attributable Level 1 data cache write-back" + }, + { + "PublicDescription": "Level 2 data cache access", + "EventCode": "0x16", + "EventName": "L2D_CACHE", + "BriefDescription": "Level 2 data cache access" + }, + { + "PublicDescription": "Level 2 data refill", + "EventCode": "0x17", + "EventName": "L2D_CACHE_REFILL", + "BriefDescription": "Level 2 data refill" + }, + { + "PublicDescription": "Attributable Level 2 data cache write-back", + "EventCode": "0x18", + "EventName": "L2D_CACHE_WB", + "BriefDescription": "Attributable Level 2 data cache write-back" + }, + { + "PublicDescription": "Attributable Bus access", + "EventCode": "0x19", + "EventName": "BUS_ACCESS", + "BriefDescription": "Attributable Bus access" + }, + { + "PublicDescription": "Local memory error", + "EventCode": "0x1a", + "EventName": "MEMORY_ERROR", + "BriefDescription": "Local memory error" + }, + { + "PublicDescription": "Operation speculatively executed", + "EventCode": "0x1b", + "EventName": "INST_SPEC", + "BriefDescription": "Operation speculatively executed" + }, + { + "PublicDescription": "Instruction architecturally executed, Condition code check pass, write to TTBR", + "EventCode": "0x1c", + "EventName": "TTBR_WRITE_RETIRED", + "BriefDescription": "Instruction architecturally executed, Condition code check pass, write to TTBR" + }, + { + "PublicDescription": "Bus cycle", + "EventCode": "0x1D", + "EventName": "BUS_CYCLES", + "BriefDescription": "Bus cycle" + }, + { + "PublicDescription": "Attributable Level 2 data cache allocation without refill", + "EventCode": "0x20", + "EventName": "L2D_CACHE_ALLOCATE", + "BriefDescription": "Attributable Level 2 data cache allocation without refill" + }, + { + "PublicDescription": "Instruction architecturally executed, branch", + "EventCode": "0x21", + "EventName": "BR_RETIRED", + "BriefDescription": "Instruction architecturally executed, branch" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted branch", + "EventCode": "0x22", + "EventName": "BR_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted branch" + }, + { + "PublicDescription": "No operation issued because of the frontend", + "EventCode": "0x23", + "EventName": "STALL_FRONTEND", + "BriefDescription": "No operation issued because of the frontend" + }, + { + "PublicDescription": "No operation issued due to the backend", + "EventCode": "0x24", + "EventName": "STALL_BACKEND", + "BriefDescription": "No operation issued due to the backend" + }, + { + "PublicDescription": "Attributable Level 1 data or unified TLB access", + "EventCode": "0x25", + "EventName": "L1D_TLB", + "BriefDescription": "Attributable Level 1 data or unified TLB access" + }, + { + "PublicDescription": "Attributable Level 1 instruction TLB access", + "EventCode": "0x26", + "EventName": "L1I_TLB", + "BriefDescription": "Attributable Level 1 instruction TLB access" + }, + { + "PublicDescription": "Attributable Level 3 data cache allocation without refill", + "EventCode": "0x29", + "EventName": "L3D_CACHE_ALLOCATE", + "BriefDescription": "Attributable Level 3 data cache allocation without refill" + }, + { + "PublicDescription": "Attributable Level 3 data cache refill", + "EventCode": "0x2A", + "EventName": "L3D_CACHE_REFILL", + "BriefDescription": "Attributable Level 3 data cache refill" + }, + { + "PublicDescription": "Attributable Level 3 data cache access", + "EventCode": "0x2B", + "EventName": "L3D_CACHE", + "BriefDescription": "Attributable Level 3 data cache access" + }, + { + "PublicDescription": "Attributable Level 2 data TLB refill", + "EventCode": "0x2D", + "EventName": "L2D_TLB_REFILL", + "BriefDescription": "Attributable Level 2 data TLB refill" + }, + { + "PublicDescription": "Attributable Level 2 data or unified TLB access", + "EventCode": "0x2F", + "EventName": "L2D_TLB", + "BriefDescription": "Attributable Level 2 data or unified TLB access" + }, + { + "PublicDescription": "Access to another socket in a multi-socket system", + "EventCode": "0x31", + "EventName": "REMOTE_ACCESS", + "BriefDescription": "Access to another socket in a multi-socket system" + }, + { + "PublicDescription": "Access to data TLB causes a translation table walk", + "EventCode": "0x34", + "EventName": "DTLB_WALK", + "BriefDescription": "Access to data TLB causes a translation table walk" + }, + { + "PublicDescription": "Access to instruction TLB that causes a translation table walk", + "EventCode": "0x35", + "EventName": "ITLB_WALK", + "BriefDescription": "Access to instruction TLB that causes a translation table walk" + }, + { + "PublicDescription": "Attributable Last level cache memory read", + "EventCode": "0x36", + "EventName": "LL_CACHE_RD", + "BriefDescription": "Attributable Last level cache memory read" + }, + { + "PublicDescription": "Last level cache miss, read", + "EventCode": "0x37", + "EventName": "LL_CACHE_MISS_RD", + "BriefDescription": "Last level cache miss, read" + } +] diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index ce7be37f0d88..6dc1db1626ad 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -70,6 +70,10 @@ static struct pmu_event pme_test[] = { .metric_name = "M3", }, { + .metric_expr = "64 * l1d.replacement / 1000000000 / duration_time", + .metric_name = "L1D_Cache_Fill_BW", +}, +{ .name = NULL, } }; @@ -107,6 +111,8 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); perf_stat__update_shadow_stats(evsel, count, 0, st); + if (!strcmp(evsel->name, "duration_time")) + update_stats(&walltime_nsecs_stats, count); } } @@ -321,6 +327,23 @@ static int test_recursion_fail(void) return 0; } +static int test_memory_bandwidth(void) +{ + double ratio; + struct value vals[] = { + { .event = "l1d.replacement", .val = 4000000 }, + { .event = "duration_time", .val = 200000000 }, + { .event = NULL, }, + }; + + TEST_ASSERT_VAL("failed to compute metric", + compute_metric("L1D_Cache_Fill_BW", vals, &ratio) == 0); + TEST_ASSERT_VAL("L1D_Cache_Fill_BW, wrong ratio", + 1.28 == ratio); + + return 0; +} + static int test_metric_group(void) { double ratio1, ratio2; @@ -353,5 +376,6 @@ int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("DCache_L2 failed", test_dcache_l2() == 0); TEST_ASSERT_VAL("recursion fail failed", test_recursion_fail() == 0); TEST_ASSERT_VAL("test metric group", test_metric_group() == 0); + TEST_ASSERT_VAL("Memory bandwidth", test_memory_bandwidth() == 0); return 0; } diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 2393916f6128..e93d0689a27b 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -157,6 +157,9 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_DATA_PAGE_SIZE) COMP(data_page_size); + if (type & PERF_SAMPLE_CODE_PAGE_SIZE) + COMP(code_page_size); + if (type & PERF_SAMPLE_AUX) { COMP(aux_sample.size); if (memcmp(s1->aux_sample.data, s2->aux_sample.data, @@ -238,6 +241,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .phys_addr = 113, .cgroup = 114, .data_page_size = 115, + .code_page_size = 116, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data, diff --git a/tools/perf/util/Build b/tools/perf/util/Build index e2563d0154eb..188521f34347 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -135,6 +135,7 @@ perf-y += clockid.o perf-$(CONFIG_LIBBPF) += bpf-loader.o perf-$(CONFIG_LIBBPF) += bpf_map.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c new file mode 100644 index 000000000000..04f89120b323 --- /dev/null +++ b/tools/perf/util/bpf_counter.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Copyright (c) 2019 Facebook */ + +#include <assert.h> +#include <limits.h> +#include <unistd.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <linux/err.h> +#include <linux/zalloc.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> + +#include "bpf_counter.h" +#include "counts.h" +#include "debug.h" +#include "evsel.h" +#include "target.h" + +#include "bpf_skel/bpf_prog_profiler.skel.h" + +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *)(unsigned long)ptr; +} + +static void set_max_rlimit(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + setrlimit(RLIMIT_MEMLOCK, &rinf); +} + +static struct bpf_counter *bpf_counter_alloc(void) +{ + struct bpf_counter *counter; + + counter = zalloc(sizeof(*counter)); + if (counter) + INIT_LIST_HEAD(&counter->list); + return counter; +} + +static int bpf_program_profiler__destroy(struct evsel *evsel) +{ + struct bpf_counter *counter, *tmp; + + list_for_each_entry_safe(counter, tmp, + &evsel->bpf_counter_list, list) { + list_del_init(&counter->list); + bpf_prog_profiler_bpf__destroy(counter->skel); + free(counter); + } + assert(list_empty(&evsel->bpf_counter_list)); + + return 0; +} + +static char *bpf_target_prog_name(int tgt_fd) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_func_info *func_info; + const struct btf_type *t; + char *name = NULL; + struct btf *btf; + + info_linear = bpf_program__get_prog_info_linear( + tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); + if (IS_ERR_OR_NULL(info_linear)) { + pr_debug("failed to get info_linear for prog FD %d\n", tgt_fd); + return NULL; + } + + if (info_linear->info.btf_id == 0 || + btf__get_from_id(info_linear->info.btf_id, &btf)) { + pr_debug("prog FD %d doesn't have valid btf\n", tgt_fd); + goto out; + } + + func_info = u64_to_ptr(info_linear->info.func_info); + t = btf__type_by_id(btf, func_info[0].type_id); + if (!t) { + pr_debug("btf %d doesn't have type %d\n", + info_linear->info.btf_id, func_info[0].type_id); + goto out; + } + name = strdup(btf__name_by_offset(btf, t->name_off)); +out: + free(info_linear); + return name; +} + +static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id) +{ + struct bpf_prog_profiler_bpf *skel; + struct bpf_counter *counter; + struct bpf_program *prog; + char *prog_name; + int prog_fd; + int err; + + prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (prog_fd < 0) { + pr_err("Failed to open fd for bpf prog %u\n", prog_id); + return -1; + } + counter = bpf_counter_alloc(); + if (!counter) { + close(prog_fd); + return -1; + } + + skel = bpf_prog_profiler_bpf__open(); + if (!skel) { + pr_err("Failed to open bpf skeleton\n"); + goto err_out; + } + + skel->rodata->num_cpu = evsel__nr_cpus(evsel); + + bpf_map__resize(skel->maps.events, evsel__nr_cpus(evsel)); + bpf_map__resize(skel->maps.fentry_readings, 1); + bpf_map__resize(skel->maps.accum_readings, 1); + + prog_name = bpf_target_prog_name(prog_fd); + if (!prog_name) { + pr_err("Failed to get program name for bpf prog %u. Does it have BTF?\n", prog_id); + goto err_out; + } + + bpf_object__for_each_program(prog, skel->obj) { + err = bpf_program__set_attach_target(prog, prog_fd, prog_name); + if (err) { + pr_err("bpf_program__set_attach_target failed.\n" + "Does bpf prog %u have BTF?\n", prog_id); + goto err_out; + } + } + set_max_rlimit(); + err = bpf_prog_profiler_bpf__load(skel); + if (err) { + pr_err("bpf_prog_profiler_bpf__load failed\n"); + goto err_out; + } + + assert(skel != NULL); + counter->skel = skel; + list_add(&counter->list, &evsel->bpf_counter_list); + close(prog_fd); + return 0; +err_out: + bpf_prog_profiler_bpf__destroy(skel); + free(counter); + close(prog_fd); + return -1; +} + +static int bpf_program_profiler__load(struct evsel *evsel, struct target *target) +{ + char *bpf_str, *bpf_str_, *tok, *saveptr = NULL, *p; + u32 prog_id; + int ret; + + bpf_str_ = bpf_str = strdup(target->bpf_str); + if (!bpf_str) + return -1; + + while ((tok = strtok_r(bpf_str, ",", &saveptr)) != NULL) { + prog_id = strtoul(tok, &p, 10); + if (prog_id == 0 || prog_id == UINT_MAX || + (*p != '\0' && *p != ',')) { + pr_err("Failed to parse bpf prog ids %s\n", + target->bpf_str); + return -1; + } + + ret = bpf_program_profiler_load_one(evsel, prog_id); + if (ret) { + bpf_program_profiler__destroy(evsel); + free(bpf_str_); + return -1; + } + bpf_str = NULL; + } + free(bpf_str_); + return 0; +} + +static int bpf_program_profiler__enable(struct evsel *evsel) +{ + struct bpf_counter *counter; + int ret; + + list_for_each_entry(counter, &evsel->bpf_counter_list, list) { + assert(counter->skel != NULL); + ret = bpf_prog_profiler_bpf__attach(counter->skel); + if (ret) { + bpf_program_profiler__destroy(evsel); + return ret; + } + } + return 0; +} + +static int bpf_program_profiler__read(struct evsel *evsel) +{ + // perf_cpu_map uses /sys/devices/system/cpu/online + int num_cpu = evsel__nr_cpus(evsel); + // BPF_MAP_TYPE_PERCPU_ARRAY uses /sys/devices/system/cpu/possible + // Sometimes possible > online, like on a Ryzen 3900X that has 24 + // threads but its possible showed 0-31 -acme + int num_cpu_bpf = libbpf_num_possible_cpus(); + struct bpf_perf_event_value values[num_cpu_bpf]; + struct bpf_counter *counter; + int reading_map_fd; + __u32 key = 0; + int err, cpu; + + if (list_empty(&evsel->bpf_counter_list)) + return -EAGAIN; + + for (cpu = 0; cpu < num_cpu; cpu++) { + perf_counts(evsel->counts, cpu, 0)->val = 0; + perf_counts(evsel->counts, cpu, 0)->ena = 0; + perf_counts(evsel->counts, cpu, 0)->run = 0; + } + list_for_each_entry(counter, &evsel->bpf_counter_list, list) { + struct bpf_prog_profiler_bpf *skel = counter->skel; + + assert(skel != NULL); + reading_map_fd = bpf_map__fd(skel->maps.accum_readings); + + err = bpf_map_lookup_elem(reading_map_fd, &key, values); + if (err) { + pr_err("failed to read value\n"); + return err; + } + + for (cpu = 0; cpu < num_cpu; cpu++) { + perf_counts(evsel->counts, cpu, 0)->val += values[cpu].counter; + perf_counts(evsel->counts, cpu, 0)->ena += values[cpu].enabled; + perf_counts(evsel->counts, cpu, 0)->run += values[cpu].running; + } + } + return 0; +} + +static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, + int fd) +{ + struct bpf_prog_profiler_bpf *skel; + struct bpf_counter *counter; + int ret; + + list_for_each_entry(counter, &evsel->bpf_counter_list, list) { + skel = counter->skel; + assert(skel != NULL); + + ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events), + &cpu, &fd, BPF_ANY); + if (ret) + return ret; + } + return 0; +} + +struct bpf_counter_ops bpf_program_profiler_ops = { + .load = bpf_program_profiler__load, + .enable = bpf_program_profiler__enable, + .read = bpf_program_profiler__read, + .destroy = bpf_program_profiler__destroy, + .install_pe = bpf_program_profiler__install_pe, +}; + +int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd) +{ + if (list_empty(&evsel->bpf_counter_list)) + return 0; + return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd); +} + +int bpf_counter__load(struct evsel *evsel, struct target *target) +{ + if (target__has_bpf(target)) + evsel->bpf_counter_ops = &bpf_program_profiler_ops; + + if (evsel->bpf_counter_ops) + return evsel->bpf_counter_ops->load(evsel, target); + return 0; +} + +int bpf_counter__enable(struct evsel *evsel) +{ + if (list_empty(&evsel->bpf_counter_list)) + return 0; + return evsel->bpf_counter_ops->enable(evsel); +} + +int bpf_counter__read(struct evsel *evsel) +{ + if (list_empty(&evsel->bpf_counter_list)) + return -EAGAIN; + return evsel->bpf_counter_ops->read(evsel); +} + +void bpf_counter__destroy(struct evsel *evsel) +{ + if (list_empty(&evsel->bpf_counter_list)) + return; + evsel->bpf_counter_ops->destroy(evsel); + evsel->bpf_counter_ops = NULL; +} diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h new file mode 100644 index 000000000000..2eca210e5dc1 --- /dev/null +++ b/tools/perf/util/bpf_counter.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_BPF_COUNTER_H +#define __PERF_BPF_COUNTER_H 1 + +#include <linux/list.h> + +struct evsel; +struct target; +struct bpf_counter; + +typedef int (*bpf_counter_evsel_op)(struct evsel *evsel); +typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel, + struct target *target); +typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel, + int cpu, + int fd); + +struct bpf_counter_ops { + bpf_counter_evsel_target_op load; + bpf_counter_evsel_op enable; + bpf_counter_evsel_op read; + bpf_counter_evsel_op destroy; + bpf_counter_evsel_install_pe_op install_pe; +}; + +struct bpf_counter { + void *skel; + struct list_head list; +}; + +#ifdef HAVE_BPF_SKEL + +int bpf_counter__load(struct evsel *evsel, struct target *target); +int bpf_counter__enable(struct evsel *evsel); +int bpf_counter__read(struct evsel *evsel); +void bpf_counter__destroy(struct evsel *evsel); +int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); + +#else /* HAVE_BPF_SKEL */ + +#include<linux/err.h> + +static inline int bpf_counter__load(struct evsel *evsel __maybe_unused, + struct target *target __maybe_unused) +{ + return 0; +} + +static inline int bpf_counter__enable(struct evsel *evsel __maybe_unused) +{ + return 0; +} + +static inline int bpf_counter__read(struct evsel *evsel __maybe_unused) +{ + return -EAGAIN; +} + +static inline void bpf_counter__destroy(struct evsel *evsel __maybe_unused) +{ +} + +static inline int bpf_counter__install_pe(struct evsel *evsel __maybe_unused, + int cpu __maybe_unused, + int fd __maybe_unused) +{ + return 0; +} + +#endif /* HAVE_BPF_SKEL */ + +#endif /* __PERF_BPF_COUNTER_H */ diff --git a/tools/perf/util/bpf_skel/.gitignore b/tools/perf/util/bpf_skel/.gitignore new file mode 100644 index 000000000000..5263e9e6c5d8 --- /dev/null +++ b/tools/perf/util/bpf_skel/.gitignore @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +.tmp +*.skel.h
\ No newline at end of file diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c new file mode 100644 index 000000000000..c7cec92d0236 --- /dev/null +++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2020 Facebook +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* map of perf event fds, num_cpu * num_metric entries */ +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(int)); +} events SEC(".maps"); + +/* readings at fentry */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} fentry_readings SEC(".maps"); + +/* accumulated readings */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} accum_readings SEC(".maps"); + +const volatile __u32 num_cpu = 1; + +SEC("fentry/XXX") +int BPF_PROG(fentry_XXX) +{ + __u32 key = bpf_get_smp_processor_id(); + struct bpf_perf_event_value *ptr; + __u32 zero = 0; + long err; + + /* look up before reading, to reduce error */ + ptr = bpf_map_lookup_elem(&fentry_readings, &zero); + if (!ptr) + return 0; + + err = bpf_perf_event_read_value(&events, key, ptr, sizeof(*ptr)); + if (err) + return 0; + + return 0; +} + +static inline void +fexit_update_maps(struct bpf_perf_event_value *after) +{ + struct bpf_perf_event_value *before, diff, *accum; + __u32 zero = 0; + + before = bpf_map_lookup_elem(&fentry_readings, &zero); + /* only account samples with a valid fentry_reading */ + if (before && before->counter) { + struct bpf_perf_event_value *accum; + + diff.counter = after->counter - before->counter; + diff.enabled = after->enabled - before->enabled; + diff.running = after->running - before->running; + + accum = bpf_map_lookup_elem(&accum_readings, &zero); + if (accum) { + accum->counter += diff.counter; + accum->enabled += diff.enabled; + accum->running += diff.running; + } + } +} + +SEC("fexit/XXX") +int BPF_PROG(fexit_XXX) +{ + struct bpf_perf_event_value reading; + __u32 cpu = bpf_get_smp_processor_id(); + __u32 one = 1, zero = 0; + int err; + + /* read all events before updating the maps, to reduce error */ + err = bpf_perf_event_read_value(&events, cpu, &reading, sizeof(reading)); + if (err) + return 0; + + fexit_update_maps(&reading); + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 6969f82843ee..6984c77068a3 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -489,7 +489,7 @@ int perf_default_config(const char *var, const char *value, return 0; } -int perf_config_from_file(config_fn_t fn, const char *filename, void *data) +static int perf_config_from_file(config_fn_t fn, const char *filename, void *data) { int ret; FILE *f = fopen(filename, "r"); @@ -521,16 +521,66 @@ static int perf_env_bool(const char *k, int def) return v ? perf_config_bool(k, v) : def; } -static int perf_config_system(void) +int perf_config_system(void) { return !perf_env_bool("PERF_CONFIG_NOSYSTEM", 0); } -static int perf_config_global(void) +int perf_config_global(void) { return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0); } +static char *home_perfconfig(void) +{ + const char *home = NULL; + char *config; + struct stat st; + + home = getenv("HOME"); + + /* + * Skip reading user config if: + * - there is no place to read it from (HOME) + * - we are asked not to (PERF_CONFIG_NOGLOBAL=1) + */ + if (!home || !*home || !perf_config_global()) + return NULL; + + config = strdup(mkpath("%s/.perfconfig", home)); + if (config == NULL) { + pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home); + return NULL; + } + + if (stat(config, &st) < 0) + goto out_free; + + if (st.st_uid && (st.st_uid != geteuid())) { + pr_warning("File %s not owned by current user or root, ignoring it.", config); + goto out_free; + } + + if (st.st_size) + return config; + +out_free: + free(config); + return NULL; +} + +const char *perf_home_perfconfig(void) +{ + static const char *config; + static bool failed; + + config = failed ? NULL : home_perfconfig(); + if (!config) + failed = true; + + return config; +} + static struct perf_config_section *find_section(struct list_head *sections, const char *section_name) { @@ -676,9 +726,6 @@ int perf_config_set__collect(struct perf_config_set *set, const char *file_name, static int perf_config_set__init(struct perf_config_set *set) { int ret = -1; - const char *home = NULL; - char *user_config; - struct stat st; /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ if (config_exclusive_filename) @@ -687,41 +734,11 @@ static int perf_config_set__init(struct perf_config_set *set) if (perf_config_from_file(collect_config, perf_etc_perfconfig(), set) < 0) goto out; } - - home = getenv("HOME"); - - /* - * Skip reading user config if: - * - there is no place to read it from (HOME) - * - we are asked not to (PERF_CONFIG_NOGLOBAL=1) - */ - if (!home || !*home || !perf_config_global()) - return 0; - - user_config = strdup(mkpath("%s/.perfconfig", home)); - if (user_config == NULL) { - pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home); - goto out; - } - - if (stat(user_config, &st) < 0) { - if (errno == ENOENT) - ret = 0; - goto out_free; - } - - ret = 0; - - if (st.st_uid && (st.st_uid != geteuid())) { - pr_warning("File %s not owned by current user or root, ignoring it.", user_config); - goto out_free; + if (perf_config_global() && perf_home_perfconfig()) { + if (perf_config_from_file(collect_config, perf_home_perfconfig(), set) < 0) + goto out; } - if (st.st_size) - ret = perf_config_from_file(collect_config, user_config, set); - -out_free: - free(user_config); out: return ret; } @@ -738,6 +755,18 @@ struct perf_config_set *perf_config_set__new(void) return set; } +struct perf_config_set *perf_config_set__load_file(const char *file) +{ + struct perf_config_set *set = zalloc(sizeof(*set)); + + if (set) { + INIT_LIST_HEAD(&set->sections); + perf_config_from_file(collect_config, file, set); + } + + return set; +} + static int perf_config__init(void) { if (config_set == NULL) @@ -746,17 +775,15 @@ static int perf_config__init(void) return config_set == NULL; } -int perf_config(config_fn_t fn, void *data) +int perf_config_set(struct perf_config_set *set, + config_fn_t fn, void *data) { int ret = 0; char key[BUFSIZ]; struct perf_config_section *section; struct perf_config_item *item; - if (config_set == NULL && perf_config__init()) - return -1; - - perf_config_set__for_each_entry(config_set, section, item) { + perf_config_set__for_each_entry(set, section, item) { char *value = item->value; if (value) { @@ -778,6 +805,14 @@ out: return ret; } +int perf_config(config_fn_t fn, void *data) +{ + if (config_set == NULL && perf_config__init()) + return -1; + + return perf_config_set(config_set, fn, data); +} + void perf_config__exit(void) { perf_config_set__delete(config_set); diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 8c881e3a3ec3..2fd77aaff4d2 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -27,17 +27,22 @@ extern const char *config_exclusive_filename; typedef int (*config_fn_t)(const char *, const char *, void *); -int perf_config_from_file(config_fn_t fn, const char *filename, void *data); int perf_default_config(const char *, const char *, void *); int perf_config(config_fn_t fn, void *); +int perf_config_set(struct perf_config_set *set, + config_fn_t fn, void *data); int perf_config_int(int *dest, const char *, const char *); int perf_config_u8(u8 *dest, const char *name, const char *value); int perf_config_u64(u64 *dest, const char *, const char *); int perf_config_bool(const char *, const char *); int config_error_nonbool(const char *); const char *perf_etc_perfconfig(void); +const char *perf_home_perfconfig(void); +int perf_config_system(void); +int perf_config_global(void); struct perf_config_set *perf_config_set__new(void); +struct perf_config_set *perf_config_set__load_file(const char *file); void perf_config_set__delete(struct perf_config_set *set); int perf_config_set__collect(struct perf_config_set *set, const char *file_name, const char *var, const char *value); diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index cd007cc9c283..3f4bc4050477 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -419,19 +419,10 @@ cs_etm_decoder__buffer_range(struct cs_etm_queue *etmq, packet->last_instr_subtype = elem->last_i_subtype; packet->last_instr_cond = elem->last_instr_cond; - switch (elem->last_i_type) { - case OCSD_INSTR_BR: - case OCSD_INSTR_BR_INDIRECT: + if (elem->last_i_type == OCSD_INSTR_BR || elem->last_i_type == OCSD_INSTR_BR_INDIRECT) packet->last_instr_taken_branch = elem->last_instr_exec; - break; - case OCSD_INSTR_ISB: - case OCSD_INSTR_DSB_DMB: - case OCSD_INSTR_WFI_WFE: - case OCSD_INSTR_OTHER: - default: + else packet->last_instr_taken_branch = false; - break; - } packet->last_instr_size = elem->last_instr_sz; @@ -572,6 +563,8 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( case OCSD_GEN_TRC_ELEM_EVENT: case OCSD_GEN_TRC_ELEM_SWTRACE: case OCSD_GEN_TRC_ELEM_CUSTOM: + case OCSD_GEN_TRC_ELEM_SYNC_MARKER: + case OCSD_GEN_TRC_ELEM_MEMTRANS: default: break; } diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 50fd6a4be4e0..2c06abf6dcd2 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -10,6 +10,7 @@ #include <api/debug.h> #include <linux/kernel.h> #include <linux/time64.h> +#include <sys/time.h> #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif @@ -31,21 +32,48 @@ int debug_ordered_events; static int redirect_to_stderr; int debug_data_convert; static FILE *debug_file; +bool debug_display_time; void debug_set_file(FILE *file) { debug_file = file; } +void debug_set_display_time(bool set) +{ + debug_display_time = set; +} + +static int fprintf_time(FILE *file) +{ + struct timeval tod; + struct tm ltime; + char date[64]; + + if (!debug_display_time) + return 0; + + if (gettimeofday(&tod, NULL) != 0) + return 0; + + if (localtime_r(&tod.tv_sec, <ime) == NULL) + return 0; + + strftime(date, sizeof(date), "%F %H:%M:%S", <ime); + return fprintf(file, "[%s.%06lu] ", date, (long)tod.tv_usec); +} + int veprintf(int level, int var, const char *fmt, va_list args) { int ret = 0; if (var >= level) { - if (use_browser >= 1 && !redirect_to_stderr) + if (use_browser >= 1 && !redirect_to_stderr) { ui_helpline__vshow(fmt, args); - else - ret = vfprintf(debug_file, fmt, args); + } else { + ret = fprintf_time(debug_file); + ret += vfprintf(debug_file, fmt, args); + } } return ret; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 43f712295645..48f631966067 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -64,6 +64,7 @@ int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); void debug_set_file(FILE *file); +void debug_set_display_time(bool set); void perf_debug_setup(void); int perf_quiet_option(void); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 05616d4138a9..208b6c141d98 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -288,17 +288,36 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) { - return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 - " %02x:%02x %"PRI_lu64" %"PRI_lu64"]: %c%c%c%c %s\n", - event->mmap2.pid, event->mmap2.tid, event->mmap2.start, - event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, - event->mmap2.min, event->mmap2.ino, - event->mmap2.ino_generation, - (event->mmap2.prot & PROT_READ) ? 'r' : '-', - (event->mmap2.prot & PROT_WRITE) ? 'w' : '-', - (event->mmap2.prot & PROT_EXEC) ? 'x' : '-', - (event->mmap2.flags & MAP_SHARED) ? 's' : 'p', - event->mmap2.filename); + if (event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID) { + char sbuild_id[SBUILD_ID_SIZE]; + struct build_id bid; + + build_id__init(&bid, event->mmap2.build_id, + event->mmap2.build_id_size); + build_id__sprintf(&bid, sbuild_id); + + return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 + " <%s>]: %c%c%c%c %s\n", + event->mmap2.pid, event->mmap2.tid, event->mmap2.start, + event->mmap2.len, event->mmap2.pgoff, sbuild_id, + (event->mmap2.prot & PROT_READ) ? 'r' : '-', + (event->mmap2.prot & PROT_WRITE) ? 'w' : '-', + (event->mmap2.prot & PROT_EXEC) ? 'x' : '-', + (event->mmap2.flags & MAP_SHARED) ? 's' : 'p', + event->mmap2.filename); + } else { + return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 + " %02x:%02x %"PRI_lu64" %"PRI_lu64"]: %c%c%c%c %s\n", + event->mmap2.pid, event->mmap2.tid, event->mmap2.start, + event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, + event->mmap2.min, event->mmap2.ino, + event->mmap2.ino_generation, + (event->mmap2.prot & PROT_READ) ? 'r' : '-', + (event->mmap2.prot & PROT_WRITE) ? 'w' : '-', + (event->mmap2.prot & PROT_EXEC) ? 'x' : '-', + (event->mmap2.flags & MAP_SHARED) ? 's' : 'p', + event->mmap2.filename); + } } size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp) @@ -673,6 +692,8 @@ int machine__resolve(struct machine *machine, struct addr_location *al, } al->sym = map__find_symbol(al->map, al->addr); + } else if (symbol_conf.dso_list) { + al->filtered |= (1 << HIST_FILTER__DSO); } if (symbol_conf.sym_list) { diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index ff403ea578e1..2afea7247dd3 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -136,6 +136,7 @@ struct perf_sample { u64 data_src; u64 phys_addr; u64 data_page_size; + u64 code_page_size; u64 cgroup; u32 flags; u16 insn_len; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 05363a7247c4..5983a9f13930 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -24,6 +24,7 @@ #include "bpf-event.h" #include "util/string2.h" #include "util/perf_api_probe.h" +#include "util/evsel_fprintf.h" #include <signal.h> #include <unistd.h> #include <sched.h> @@ -303,6 +304,11 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a return evlist__add_attrs(evlist, attrs, nr_attrs); } +__weak int arch_evlist__add_default_attrs(struct evlist *evlist __maybe_unused) +{ + return 0; +} + struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id) { struct evsel *evsel; @@ -1936,6 +1942,15 @@ static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd, (sizeof(EVLIST_CTL_CMD_SNAPSHOT_TAG)-1))) { *cmd = EVLIST_CTL_CMD_SNAPSHOT; pr_debug("is snapshot\n"); + } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_EVLIST_TAG, + (sizeof(EVLIST_CTL_CMD_EVLIST_TAG)-1))) { + *cmd = EVLIST_CTL_CMD_EVLIST; + } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_STOP_TAG, + (sizeof(EVLIST_CTL_CMD_STOP_TAG)-1))) { + *cmd = EVLIST_CTL_CMD_STOP; + } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_PING_TAG, + (sizeof(EVLIST_CTL_CMD_PING_TAG)-1))) { + *cmd = EVLIST_CTL_CMD_PING; } } @@ -1957,6 +1972,98 @@ int evlist__ctlfd_ack(struct evlist *evlist) return err; } +static int get_cmd_arg(char *cmd_data, size_t cmd_size, char **arg) +{ + char *data = cmd_data + cmd_size; + + /* no argument */ + if (!*data) + return 0; + + /* there's argument */ + if (*data == ' ') { + *arg = data + 1; + return 1; + } + + /* malformed */ + return -1; +} + +static int evlist__ctlfd_enable(struct evlist *evlist, char *cmd_data, bool enable) +{ + struct evsel *evsel; + char *name; + int err; + + err = get_cmd_arg(cmd_data, + enable ? sizeof(EVLIST_CTL_CMD_ENABLE_TAG) - 1 : + sizeof(EVLIST_CTL_CMD_DISABLE_TAG) - 1, + &name); + if (err < 0) { + pr_info("failed: wrong command\n"); + return -1; + } + + if (err) { + evsel = evlist__find_evsel_by_str(evlist, name); + if (evsel) { + if (enable) + evlist__enable_evsel(evlist, name); + else + evlist__disable_evsel(evlist, name); + pr_info("Event %s %s\n", evsel->name, + enable ? "enabled" : "disabled"); + } else { + pr_info("failed: can't find '%s' event\n", name); + } + } else { + if (enable) { + evlist__enable(evlist); + pr_info(EVLIST_ENABLED_MSG); + } else { + evlist__disable(evlist); + pr_info(EVLIST_DISABLED_MSG); + } + } + + return 0; +} + +static int evlist__ctlfd_list(struct evlist *evlist, char *cmd_data) +{ + struct perf_attr_details details = { .verbose = false, }; + struct evsel *evsel; + char *arg; + int err; + + err = get_cmd_arg(cmd_data, + sizeof(EVLIST_CTL_CMD_EVLIST_TAG) - 1, + &arg); + if (err < 0) { + pr_info("failed: wrong command\n"); + return -1; + } + + if (err) { + if (!strcmp(arg, "-v")) { + details.verbose = true; + } else if (!strcmp(arg, "-g")) { + details.event_group = true; + } else if (!strcmp(arg, "-F")) { + details.freq = true; + } else { + pr_info("failed: wrong command\n"); + return -1; + } + } + + evlist__for_each_entry(evlist, evsel) + evsel__fprintf(evsel, &details, stderr); + + return 0; +} + int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd) { int err = 0; @@ -1973,12 +2080,16 @@ int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd) if (err > 0) { switch (*cmd) { case EVLIST_CTL_CMD_ENABLE: - evlist__enable(evlist); - break; case EVLIST_CTL_CMD_DISABLE: - evlist__disable(evlist); + err = evlist__ctlfd_enable(evlist, cmd_data, + *cmd == EVLIST_CTL_CMD_ENABLE); + break; + case EVLIST_CTL_CMD_EVLIST: + err = evlist__ctlfd_list(evlist, cmd_data); break; case EVLIST_CTL_CMD_SNAPSHOT: + case EVLIST_CTL_CMD_STOP: + case EVLIST_CTL_CMD_PING: break; case EVLIST_CTL_CMD_ACK: case EVLIST_CTL_CMD_UNSUPPORTED: diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 1aae75895dea..7243e94da398 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -110,6 +110,8 @@ int __evlist__add_default_attrs(struct evlist *evlist, #define evlist__add_default_attrs(evlist, array) \ __evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) +int arch_evlist__add_default_attrs(struct evlist *evlist); + int evlist__add_dummy(struct evlist *evlist); int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, @@ -330,6 +332,9 @@ struct evsel *evlist__reset_weak_group(struct evlist *evlist, struct evsel *evse #define EVLIST_CTL_CMD_DISABLE_TAG "disable" #define EVLIST_CTL_CMD_ACK_TAG "ack\n" #define EVLIST_CTL_CMD_SNAPSHOT_TAG "snapshot" +#define EVLIST_CTL_CMD_EVLIST_TAG "evlist" +#define EVLIST_CTL_CMD_STOP_TAG "stop" +#define EVLIST_CTL_CMD_PING_TAG "ping" #define EVLIST_CTL_CMD_MAX_LEN 64 @@ -339,6 +344,9 @@ enum evlist_ctl_cmd { EVLIST_CTL_CMD_DISABLE, EVLIST_CTL_CMD_ACK, EVLIST_CTL_CMD_SNAPSHOT, + EVLIST_CTL_CMD_EVLIST, + EVLIST_CTL_CMD_STOP, + EVLIST_CTL_CMD_PING, }; int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c26ea82220bd..8b18ec56e266 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -25,6 +25,7 @@ #include <stdlib.h> #include <perf/evsel.h> #include "asm/bug.h" +#include "bpf_counter.h" #include "callchain.h" #include "cgroup.h" #include "counts.h" @@ -247,6 +248,7 @@ void evsel__init(struct evsel *evsel, evsel->bpf_obj = NULL; evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->config_terms); + INIT_LIST_HEAD(&evsel->bpf_counter_list); perf_evsel__object.init(evsel); evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); @@ -1168,10 +1170,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (opts->sample_weight) evsel__set_sample_bit(evsel, WEIGHT); - attr->task = track; - attr->mmap = track; - attr->mmap2 = track && !perf_missing_features.mmap2; - attr->comm = track; + attr->task = track; + attr->mmap = track; + attr->mmap2 = track && !perf_missing_features.mmap2; + attr->comm = track; + attr->build_id = track && opts->build_id; + /* * ksymbol is tracked separately with text poke because it needs to be * system wide and enabled immediately. @@ -1191,6 +1195,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (opts->sample_data_page_size) evsel__set_sample_bit(evsel, DATA_PAGE_SIZE); + if (opts->sample_code_page_size) + evsel__set_sample_bit(evsel, CODE_PAGE_SIZE); + if (opts->record_switch_events) attr->context_switch = track; @@ -1366,6 +1373,7 @@ void evsel__exit(struct evsel *evsel) { assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); + bpf_counter__destroy(evsel); evsel__free_counts(evsel); perf_evsel__free_fd(&evsel->core); perf_evsel__free_id(&evsel->core); @@ -1781,6 +1789,8 @@ retry_open: FD(evsel, cpu, thread) = fd; + bpf_counter__install_pe(evsel, cpu, fd); + if (unlikely(test_attr__enabled)) { test_attr__open(&evsel->core.attr, pid, cpus->map[cpu], fd, group_fd, flags); @@ -1873,7 +1883,12 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.data_page_size && + if (!perf_missing_features.code_page_size && + (evsel->core.attr.sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)) { + perf_missing_features.code_page_size = true; + pr_debug2_peo("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support, bailing out\n"); + goto out_close; + } else if (!perf_missing_features.data_page_size && (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) { perf_missing_features.data_page_size = true; pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n"); @@ -2369,6 +2384,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + data->code_page_size = 0; + if (type & PERF_SAMPLE_CODE_PAGE_SIZE) { + data->code_page_size = *array; + array++; + } + if (type & PERF_SAMPLE_AUX) { OVERFLOW_CHECK_u64(array); sz = *array++; @@ -2678,6 +2699,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, "We found oprofile daemon running, please stop it and try again."); break; case EINVAL: + if (evsel->core.attr.sample_type & PERF_SAMPLE_CODE_PAGE_SIZE && perf_missing_features.code_page_size) + return scnprintf(msg, size, "Asking for the code page size isn't supported by this kernel."); if (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE && perf_missing_features.data_page_size) return scnprintf(msg, size, "Asking for the data page size isn't supported by this kernel."); if (evsel->core.attr.write_backward && perf_missing_features.write_backward) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index cd1d8dd43199..e25594494cf6 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -17,6 +17,8 @@ struct cgroup; struct perf_counts; struct perf_stat_evsel; union perf_event; +struct bpf_counter_ops; +struct target; typedef int (evsel__sb_cb_t)(union perf_event *event, void *data); @@ -127,6 +129,8 @@ struct evsel { * See also evsel__has_callchain(). */ __u64 synth_sample_type; + struct list_head bpf_counter_list; + struct bpf_counter_ops *bpf_counter_ops; }; struct perf_missing_features { @@ -145,6 +149,7 @@ struct perf_missing_features { bool branch_hw_idx; bool cgroup; bool data_page_size; + bool code_page_size; }; extern struct perf_missing_features perf_missing_features; @@ -424,4 +429,5 @@ static inline bool evsel__is_dummy_event(struct evsel *evsel) struct perf_env *evsel__env(struct evsel *evsel); int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); + #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index fb498a723a00..bfedd7b23521 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -100,6 +100,7 @@ out: return ++printed; } +#ifndef PYTHON_PERF int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, unsigned int print_opts, struct callchain_cursor *cursor, struct strlist *bt_stop_list, FILE *fp) @@ -239,3 +240,4 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, return printed; } +#endif /* PYTHON_PERF */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index a08fb9ea411b..6d50379af90e 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -212,6 +212,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_TIME, 16); else hists__new_col_len(hists, HISTC_TIME, 12); + hists__new_col_len(hists, HISTC_CODE_PAGE_SIZE, 6); if (h->srcline) { len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header)); @@ -718,6 +719,7 @@ __hists__add_entry(struct hists *hists, .cpumode = al->cpumode, .ip = al->addr, .level = al->level, + .code_page_size = sample->code_page_size, .stat = { .nr_events = 1, .period = sample->period, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 14f66330923d..361108533a56 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -53,6 +53,7 @@ enum hist_column { HISTC_DSO_TO, HISTC_LOCAL_WEIGHT, HISTC_GLOBAL_WEIGHT, + HISTC_CODE_PAGE_SIZE, HISTC_MEM_DADDR_SYMBOL, HISTC_MEM_DADDR_DSO, HISTC_MEM_PHYS_DADDR, diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h index 6817ffc2a059..fb810e1b2de7 100644 --- a/tools/perf/util/jit.h +++ b/tools/perf/util/jit.h @@ -5,7 +5,7 @@ #include <data.h> int jit_process(struct perf_session *session, struct perf_data *output, - struct machine *machine, char *filename, pid_t pid, u64 *nbytes); + struct machine *machine, char *filename, pid_t pid, pid_t tid, u64 *nbytes); int jit_inject_record(const char *filename); diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 055bab7a92b3..9760d8e7b386 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -18,6 +18,7 @@ #include "event.h" #include "debug.h" #include "evlist.h" +#include "namespaces.h" #include "symbol.h" #include <elf.h> @@ -35,6 +36,7 @@ struct jit_buf_desc { struct perf_data *output; struct perf_session *session; struct machine *machine; + struct nsinfo *nsi; union jr_entry *entry; void *buf; uint64_t sample_type; @@ -72,7 +74,8 @@ struct jit_tool { #define get_jit_tool(t) (container_of(tool, struct jit_tool, tool)) static int -jit_emit_elf(char *filename, +jit_emit_elf(struct jit_buf_desc *jd, + char *filename, const char *sym, uint64_t code_addr, const void *code, @@ -83,14 +86,18 @@ jit_emit_elf(char *filename, uint32_t unwinding_header_size, uint32_t unwinding_size) { - int ret, fd; + int ret, fd, saved_errno; + struct nscookie nsc; if (verbose > 0) fprintf(stderr, "write ELF image %s\n", filename); + nsinfo__mountns_enter(jd->nsi, &nsc); fd = open(filename, O_CREAT|O_TRUNC|O_WRONLY, 0644); + saved_errno = errno; + nsinfo__mountns_exit(&nsc); if (fd == -1) { - pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(errno)); + pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(saved_errno)); return -1; } @@ -99,8 +106,11 @@ jit_emit_elf(char *filename, close(fd); - if (ret) - unlink(filename); + if (ret) { + nsinfo__mountns_enter(jd->nsi, &nsc); + unlink(filename); + nsinfo__mountns_exit(&nsc); + } return ret; } @@ -134,12 +144,15 @@ static int jit_open(struct jit_buf_desc *jd, const char *name) { struct jitheader header; + struct nscookie nsc; struct jr_prefix *prefix; ssize_t bs, bsz = 0; void *n, *buf = NULL; int ret, retval = -1; + nsinfo__mountns_enter(jd->nsi, &nsc); jd->in = fopen(name, "r"); + nsinfo__mountns_exit(&nsc); if (!jd->in) return -1; @@ -367,6 +380,20 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event) return 0; } +static pid_t jr_entry_pid(struct jit_buf_desc *jd, union jr_entry *jr) +{ + if (jd->nsi && jd->nsi->in_pidns) + return jd->nsi->tgid; + return jr->load.pid; +} + +static pid_t jr_entry_tid(struct jit_buf_desc *jd, union jr_entry *jr) +{ + if (jd->nsi && jd->nsi->in_pidns) + return jd->nsi->pid; + return jr->load.tid; +} + static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp) { struct perf_tsc_conversion tc; @@ -402,14 +429,15 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) const char *sym; uint64_t count; int ret, csize, usize; - pid_t pid, tid; + pid_t nspid, pid, tid; struct { u32 pid, tid; u64 time; } *id; - pid = jr->load.pid; - tid = jr->load.tid; + nspid = jr->load.pid; + pid = jr_entry_pid(jd, jr); + tid = jr_entry_tid(jd, jr); csize = jr->load.code_size; usize = jd->unwinding_mapped_size; addr = jr->load.code_addr; @@ -425,14 +453,14 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) filename = event->mmap2.filename; size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so", jd->dir, - pid, + nspid, count); size++; /* for \0 */ size = PERF_ALIGN(size, sizeof(u64)); uaddr = (uintptr_t)code; - ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries, + ret = jit_emit_elf(jd, filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries, jd->unwinding_data, jd->eh_frame_hdr_size, jd->unwinding_size); if (jd->debug_data && jd->nr_debug_entries) { @@ -451,7 +479,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) free(event); return -1; } - if (stat(filename, &st)) + if (nsinfo__stat(filename, &st, jd->nsi)) memset(&st, 0, sizeof(st)); event->mmap2.header.type = PERF_RECORD_MMAP2; @@ -515,14 +543,15 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) int usize; u16 idr_size; int ret; - pid_t pid, tid; + pid_t nspid, pid, tid; struct { u32 pid, tid; u64 time; } *id; - pid = jr->move.pid; - tid = jr->move.tid; + nspid = jr->load.pid; + pid = jr_entry_pid(jd, jr); + tid = jr_entry_tid(jd, jr); usize = jd->unwinding_mapped_size; idr_size = jd->machine->id_hdr_size; @@ -536,12 +565,12 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) filename = event->mmap2.filename; size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so", jd->dir, - pid, + nspid, jr->move.code_index); size++; /* for \0 */ - if (stat(filename, &st)) + if (nsinfo__stat(filename, &st, jd->nsi)) memset(&st, 0, sizeof(st)); size = PERF_ALIGN(size, sizeof(u64)); @@ -700,7 +729,7 @@ jit_inject(struct jit_buf_desc *jd, char *path) * as captured in the RECORD_MMAP record */ static int -jit_detect(char *mmap_name, pid_t pid) +jit_detect(char *mmap_name, pid_t pid, struct nsinfo *nsi) { char *p; char *end = NULL; @@ -740,7 +769,7 @@ jit_detect(char *mmap_name, pid_t pid) * pid does not match mmap pid * pid==0 in system-wide mode (synthesized) */ - if (pid && pid2 != pid) + if (pid && pid2 != nsi->nstgid) return -1; /* * validate suffix @@ -782,16 +811,30 @@ jit_process(struct perf_session *session, struct machine *machine, char *filename, pid_t pid, + pid_t tid, u64 *nbytes) { + struct thread *thread; + struct nsinfo *nsi; struct evsel *first; struct jit_buf_desc jd; int ret; + thread = machine__findnew_thread(machine, pid, tid); + if (thread == NULL) { + pr_err("problem processing JIT mmap event, skipping it.\n"); + return 0; + } + + nsi = nsinfo__get(thread->nsinfo); + thread__put(thread); + /* * first, detect marker mmap (i.e., the jitdump mmap) */ - if (jit_detect(filename, pid)) { + if (jit_detect(filename, pid, nsi)) { + nsinfo__put(nsi); + // Strip //anon* mmaps if we processed a jitdump for this pid if (jit_has_pid(machine, pid) && (strncmp(filename, "//anon", 6) == 0)) return 1; @@ -804,6 +847,7 @@ jit_process(struct perf_session *session, jd.session = session; jd.output = output; jd.machine = machine; + jd.nsi = nsi; /* * track sample_type to compute id_all layout @@ -821,5 +865,7 @@ jit_process(struct perf_session *session, ret = 1; } + nsinfo__put(jd.nsi); + return ret; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 1e9d3f982b47..ab8a6b3e801d 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1599,7 +1599,8 @@ static int machine__process_extra_kernel_map(struct machine *machine, } static int machine__process_kernel_mmap_event(struct machine *machine, - struct extra_kernel_map *xm) + struct extra_kernel_map *xm, + struct build_id *bid) { struct map *map; enum dso_space_type dso_space; @@ -1624,6 +1625,10 @@ static int machine__process_kernel_mmap_event(struct machine *machine, goto out_problem; map->end = map->start + xm->end - xm->start; + + if (build_id__is_defined(bid)) + dso__set_build_id(map->dso, bid); + } else if (is_kernel_mmap) { const char *symbol_name = (xm->name + strlen(machine->mmap_name)); /* @@ -1681,6 +1686,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine, machine__update_kernel_mmap(machine, xm->start, xm->end); + if (build_id__is_defined(bid)) + dso__set_build_id(kernel, bid); + /* * Avoid using a zero address (kptr_restrict) for the ref reloc * symbol. Effectively having zero here means that at record @@ -1718,11 +1726,17 @@ int machine__process_mmap2_event(struct machine *machine, .ino = event->mmap2.ino, .ino_generation = event->mmap2.ino_generation, }; + struct build_id __bid, *bid = NULL; int ret = 0; if (dump_trace) perf_event__fprintf_mmap2(event, stdout); + if (event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID) { + bid = &__bid; + build_id__init(bid, event->mmap2.build_id, event->mmap2.build_id_size); + } + if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL || sample->cpumode == PERF_RECORD_MISC_KERNEL) { struct extra_kernel_map xm = { @@ -1732,7 +1746,7 @@ int machine__process_mmap2_event(struct machine *machine, }; strlcpy(xm.name, event->mmap2.filename, KMAP_NAME_LEN); - ret = machine__process_kernel_mmap_event(machine, &xm); + ret = machine__process_kernel_mmap_event(machine, &xm, bid); if (ret < 0) goto out_problem; return 0; @@ -1746,7 +1760,7 @@ int machine__process_mmap2_event(struct machine *machine, map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, &dso_id, event->mmap2.prot, - event->mmap2.flags, + event->mmap2.flags, bid, event->mmap2.filename, thread); if (map == NULL) @@ -1789,7 +1803,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event }; strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN); - ret = machine__process_kernel_mmap_event(machine, &xm); + ret = machine__process_kernel_mmap_event(machine, &xm, NULL); if (ret < 0) goto out_problem; return 0; @@ -1805,7 +1819,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, - NULL, prot, 0, event->mmap.filename, thread); + NULL, prot, 0, NULL, event->mmap.filename, thread); if (map == NULL) goto out_problem_map; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index f44ede437dc7..692e56dc832e 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -130,8 +130,8 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, struct dso_id *id, - u32 prot, u32 flags, char *filename, - struct thread *thread) + u32 prot, u32 flags, struct build_id *bid, + char *filename, struct thread *thread) { struct map *map = malloc(sizeof(*map)); struct nsinfo *nsi = NULL; @@ -194,6 +194,10 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, dso__set_loaded(dso); } dso->nsinfo = nsi; + + if (build_id__is_defined(bid)) + dso__set_build_id(dso, bid); + dso__put(dso); } return map; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index b1c0686db1b7..9f32825c98d8 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -104,10 +104,11 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso); struct dso_id; +struct build_id; struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, struct dso_id *id, u32 prot, u32 flags, - char *filename, struct thread *thread); + struct build_id *bid, char *filename, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso); void map__delete(struct map *map); struct map *map__clone(struct map *map); diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 285d6f30d912..608b20c72a5c 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -66,6 +66,7 @@ int nsinfo__init(struct nsinfo *nsi) char spath[PATH_MAX]; char *newns = NULL; char *statln = NULL; + char *nspid; struct stat old_stat; struct stat new_stat; FILE *f = NULL; @@ -112,8 +113,12 @@ int nsinfo__init(struct nsinfo *nsi) } if (strstr(statln, "NStgid:") != NULL) { - nsi->nstgid = (pid_t)strtol(strrchr(statln, '\t'), - NULL, 10); + nspid = strrchr(statln, '\t'); + nsi->nstgid = (pid_t)strtol(nspid, NULL, 10); + /* If innermost tgid is not the first, process is in a different + * PID namespace. + */ + nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid; break; } } @@ -140,6 +145,7 @@ struct nsinfo *nsinfo__new(pid_t pid) nsi->tgid = pid; nsi->nstgid = pid; nsi->need_setns = false; + nsi->in_pidns = false; /* Init may fail if the process exits while we're trying to look * at its proc information. In that case, save the pid but * don't try to enter the namespace. @@ -166,6 +172,7 @@ struct nsinfo *nsinfo__copy(struct nsinfo *nsi) nnsi->tgid = nsi->tgid; nnsi->nstgid = nsi->nstgid; nnsi->need_setns = nsi->need_setns; + nnsi->in_pidns = nsi->in_pidns; if (nsi->mntns_path) { nnsi->mntns_path = strdup(nsi->mntns_path); if (!nnsi->mntns_path) { @@ -280,3 +287,15 @@ char *nsinfo__realpath(const char *path, struct nsinfo *nsi) return rpath; } + +int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi) +{ + int ret; + struct nscookie nsc; + + nsinfo__mountns_enter(nsi, &nsc); + ret = stat(filename, st); + nsinfo__mountns_exit(&nsc); + + return ret; +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 4b33f684eddd..ad9775db7b9c 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -8,6 +8,7 @@ #define __PERF_NAMESPACES_H #include <sys/types.h> +#include <sys/stat.h> #include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/refcount.h> @@ -33,6 +34,7 @@ struct nsinfo { pid_t tgid; pid_t nstgid; bool need_setns; + bool in_pidns; char *mntns_path; refcount_t refcnt; }; @@ -55,6 +57,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc); void nsinfo__mountns_exit(struct nscookie *nc); char *nsinfo__realpath(const char *path, struct nsinfo *nsi); +int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi); static inline void __nsinfo__zput(struct nsinfo **nsip) { diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 3840d02f0f7b..829af17a0867 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -98,6 +98,11 @@ static void perf_probe_text_poke(struct evsel *evsel) evsel->core.attr.text_poke = 1; } +static void perf_probe_build_id(struct evsel *evsel) +{ + evsel->core.attr.build_id = 1; +} + bool perf_can_sample_identifier(void) { return perf_probe_api(perf_probe_sample_identifier); @@ -172,3 +177,8 @@ bool perf_can_aux_sample(void) return true; } + +bool perf_can_record_build_id(void) +{ + return perf_probe_api(perf_probe_build_id); +} diff --git a/tools/perf/util/perf_api_probe.h b/tools/perf/util/perf_api_probe.h index d5506a983a94..f12ca55f509a 100644 --- a/tools/perf/util/perf_api_probe.h +++ b/tools/perf/util/perf_api_probe.h @@ -11,5 +11,6 @@ bool perf_can_record_cpu_wide(void); bool perf_can_record_switch_events(void); bool perf_can_record_text_poke_events(void); bool perf_can_sample_identifier(void); +bool perf_can_record_build_id(void); #endif // __PERF_API_PROBE_H diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index fb0bb6684438..1bd6cfd74257 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -35,7 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX), - bit_name(CGROUP), bit_name(DATA_PAGE_SIZE), + bit_name(CGROUP), bit_name(DATA_PAGE_SIZE), bit_name(CODE_PAGE_SIZE), { .name = NULL, } }; #undef bit_name @@ -134,6 +134,8 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(bpf_event, p_unsigned); PRINT_ATTRf(aux_output, p_unsigned); PRINT_ATTRf(cgroup, p_unsigned); + PRINT_ATTRf(text_poke, p_unsigned); + PRINT_ATTRf(build_id, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); PRINT_ATTRf(bp_type, p_unsigned); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index bbecb449ea94..52273542e6ef 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -794,6 +794,8 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note, char *ret = NULL; int i, args_count, err; unsigned long long ref_ctr_offset; + char *arg; + int arg_idx = 0; if (strbuf_init(&buf, 32) < 0) return NULL; @@ -818,11 +820,43 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note, if (args == NULL) goto error; - for (i = 0; i < args_count; ++i) { - if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) { + for (i = 0; i < args_count; ) { + /* + * FIXUP: Arm64 ELF section '.note.stapsdt' uses string + * format "-4@[sp, NUM]" if a probe is to access data in + * the stack, e.g. below is an example for the SDT + * Arguments: + * + * Arguments: -4@[sp, 12] -4@[sp, 8] -4@[sp, 4] + * + * Since the string introduces an extra space character + * in the middle of square brackets, the argument is + * divided into two items. Fixup for this case, if an + * item contains sub string "[sp,", need to concatenate + * the two items. + */ + if (strstr(args[i], "[sp,") && (i+1) < args_count) { + err = asprintf(&arg, "%s %s", args[i], args[i+1]); + i += 2; + } else { + err = asprintf(&arg, "%s", args[i]); + i += 1; + } + + /* Failed to allocate memory */ + if (err < 0) { argv_free(args); goto error; } + + if (synthesize_sdt_probe_arg(&buf, arg_idx, arg) < 0) { + free(arg); + argv_free(args); + goto error; + } + + free(arg); + arg_idx++; } argv_free(args); diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index a9d9c142eb7c..71b753523fac 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,6 +10,7 @@ util/python.c util/cap.c util/evlist.c util/evsel.c +util/evsel_fprintf.c util/perf_event_attr_fprintf.c util/cpumap.c util/memswap.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index cc5ade85a33f..278abecb5bdf 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -80,6 +80,27 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, } /* + * XXX: All these evsel destructors need some better mechanism, like a linked + * list of destructors registered when the relevant code indeed is used instead + * of having more and more calls in perf_evsel__delete(). -- acme + * + * For now, add some more: + * + * Not to drag the BPF bandwagon... + */ +void bpf_counter__destroy(struct evsel *evsel); +int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); + +void bpf_counter__destroy(struct evsel *evsel __maybe_unused) +{ +} + +int bpf_counter__install_pe(struct evsel *evsel __maybe_unused, int cpu __maybe_unused, int fd __maybe_unused) +{ + return 0; +} + +/* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. */ diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index e70c9dd04567..1c1f24d9b6d0 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -201,10 +201,10 @@ static int record_opts__config_freq(struct record_opts *opts) * Default frequency is over current maximum. */ if (max_rate < opts->freq) { - pr_warning("Lowering default frequency rate to %u.\n" + pr_warning("Lowering default frequency rate from %u to %u.\n" "Please consider tweaking " "/proc/sys/kernel/perf_event_max_sample_rate.\n", - max_rate); + opts->freq, max_rate); opts->freq = max_rate; } diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 694b351dcd27..68f471d9a88b 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -23,6 +23,7 @@ struct record_opts { bool sample_address; bool sample_phys_addr; bool sample_data_page_size; + bool sample_code_page_size; bool sample_weight; bool sample_time; bool sample_time_set; @@ -50,6 +51,7 @@ struct record_opts { bool no_bpf_event; bool kcore; bool text_poke; + bool build_id; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 25adbcce0281..5b1a31cae047 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -593,10 +593,13 @@ static void perf_event__mmap2_swap(union perf_event *event, event->mmap2.start = bswap_64(event->mmap2.start); event->mmap2.len = bswap_64(event->mmap2.len); event->mmap2.pgoff = bswap_64(event->mmap2.pgoff); - event->mmap2.maj = bswap_32(event->mmap2.maj); - event->mmap2.min = bswap_32(event->mmap2.min); - event->mmap2.ino = bswap_64(event->mmap2.ino); - event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation); + + if (!(event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID)) { + event->mmap2.maj = bswap_32(event->mmap2.maj); + event->mmap2.min = bswap_32(event->mmap2.min); + event->mmap2.ino = bswap_64(event->mmap2.ino); + event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation); + } if (sample_id_all) { void *data = &event->mmap2.filename; @@ -1309,6 +1312,9 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE) printf(" .. data page size: %s\n", get_page_size_name(sample->data_page_size, str)); + if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE) + printf(" .. code page size: %s\n", get_page_size_name(sample->code_page_size, str)); + if (sample_type & PERF_SAMPLE_TRANSACTION) printf("... transaction: %" PRIx64 "\n", sample->transaction); diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index c5e3e9a68162..483f05004e68 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -43,7 +43,7 @@ class install_lib(_install_lib): cflags = getenv('CFLAGS', '').split() # switch off several checks (need to be at the end of cflags list) -cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ] +cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls', '-DPYTHON_PERF' ] if not cc_is_clang: cflags += ['-Wno-cast-function-type' ] diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 80907bc32683..c00934c91b58 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1492,6 +1492,31 @@ struct sort_entry sort_mem_data_page_size = { }; static int64_t +sort__code_page_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = left->code_page_size; + uint64_t r = right->code_page_size; + + return (int64_t)(r - l); +} + +static int hist_entry__code_page_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + char str[PAGE_SIZE_NAME_LEN]; + + return repsep_snprintf(bf, size, "%-*s", width, + get_page_size_name(he->code_page_size, str)); +} + +struct sort_entry sort_code_page_size = { + .se_header = "Code Page Size", + .se_cmp = sort__code_page_size_cmp, + .se_snprintf = hist_entry__code_page_size_snprintf, + .se_width_idx = HISTC_CODE_PAGE_SIZE, +}; + +static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { if (!left->branch_info || !right->branch_info) @@ -1735,6 +1760,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null), DIM(SORT_TIME, "time", sort_time), + DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index e50f2b695bc4..cab4172a6ec3 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -106,6 +106,7 @@ struct hist_entry { u64 transaction; s32 socket; s32 cpu; + u64 code_page_size; u8 cpumode; u8 depth; @@ -229,6 +230,7 @@ enum sort_type { SORT_CGROUP_ID, SORT_SYM_IPC_NULL, SORT_TIME, + SORT_CODE_PAGE_SIZE, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 583ae4f09c5d..cce7a76d6473 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -1045,7 +1045,9 @@ static void print_header(struct perf_stat_config *config, if (!config->csv_output) { fprintf(output, "\n"); fprintf(output, " Performance counter stats for "); - if (_target->system_wide) + if (_target->bpf_str) + fprintf(output, "\'BPF program(s) %s", _target->bpf_str); + else if (_target->system_wide) fprintf(output, "\'system wide"); else if (_target->cpu_list) fprintf(output, "\'CPU(s) %s", _target->cpu_list); diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 8ce1479c98f0..0b3957323f66 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -527,7 +527,7 @@ int create_perf_stat_counter(struct evsel *evsel, if (leader->core.nr_members > 1) attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP; - attr->inherit = !config->no_inherit; + attr->inherit = !config->no_inherit && list_empty(&evsel->bpf_counter_list); /* * Some events get initialized with sample_(period/type) set, diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index b916afb95ec5..b18f9c8dbb75 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -42,7 +42,8 @@ struct symbol_conf { report_block, report_individual_block, inline_name, - disable_add2line_warn; + disable_add2line_warn, + buildid_mmap2; const char *vmlinux_name, *kallsyms_name, *source_prefix, diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 2947e3f3c6d9..fcec775636ac 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -69,19 +69,22 @@ int perf_tool__process_synth_event(struct perf_tool *tool, * Assumes that the first 4095 bytes of /proc/pid/stat contains * the comm, tgid and ppid. */ -static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, - pid_t *tgid, pid_t *ppid) +static int perf_event__get_comm_ids(pid_t pid, pid_t tid, char *comm, size_t len, + pid_t *tgid, pid_t *ppid, bool *kernel) { char bf[4096]; int fd; size_t size = 0; ssize_t n; - char *name, *tgids, *ppids; + char *name, *tgids, *ppids, *vmpeak, *threads; *tgid = -1; *ppid = -1; - snprintf(bf, sizeof(bf), "/proc/%d/status", pid); + if (pid) + snprintf(bf, sizeof(bf), "/proc/%d/task/%d/status", pid, tid); + else + snprintf(bf, sizeof(bf), "/proc/%d/status", tid); fd = open(bf, O_RDONLY); if (fd < 0) { @@ -93,14 +96,20 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, close(fd); if (n <= 0) { pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n", - pid); + tid); return -1; } bf[n] = '\0'; name = strstr(bf, "Name:"); - tgids = strstr(bf, "Tgid:"); - ppids = strstr(bf, "PPid:"); + tgids = strstr(name ?: bf, "Tgid:"); + ppids = strstr(tgids ?: bf, "PPid:"); + vmpeak = strstr(ppids ?: bf, "VmPeak:"); + + if (vmpeak) + threads = NULL; + else + threads = strstr(ppids ?: bf, "Threads:"); if (name) { char *nl; @@ -116,29 +125,34 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, memcpy(comm, name, size); comm[size] = '\0'; } else { - pr_debug("Name: string not found for pid %d\n", pid); + pr_debug("Name: string not found for pid %d\n", tid); } if (tgids) { tgids += 5; /* strlen("Tgid:") */ *tgid = atoi(tgids); } else { - pr_debug("Tgid: string not found for pid %d\n", pid); + pr_debug("Tgid: string not found for pid %d\n", tid); } if (ppids) { ppids += 5; /* strlen("PPid:") */ *ppid = atoi(ppids); } else { - pr_debug("PPid: string not found for pid %d\n", pid); + pr_debug("PPid: string not found for pid %d\n", tid); } + if (!vmpeak && threads) + *kernel = true; + else + *kernel = false; + return 0; } -static int perf_event__prepare_comm(union perf_event *event, pid_t pid, +static int perf_event__prepare_comm(union perf_event *event, pid_t pid, pid_t tid, struct machine *machine, - pid_t *tgid, pid_t *ppid) + pid_t *tgid, pid_t *ppid, bool *kernel) { size_t size; @@ -147,9 +161,9 @@ static int perf_event__prepare_comm(union perf_event *event, pid_t pid, memset(&event->comm, 0, sizeof(event->comm)); if (machine__is_host(machine)) { - if (perf_event__get_comm_ids(pid, event->comm.comm, + if (perf_event__get_comm_ids(pid, tid, event->comm.comm, sizeof(event->comm.comm), - tgid, ppid) != 0) { + tgid, ppid, kernel) != 0) { return -1; } } else { @@ -168,7 +182,7 @@ static int perf_event__prepare_comm(union perf_event *event, pid_t pid, event->comm.header.size = (sizeof(event->comm) - (sizeof(event->comm.comm) - size) + machine->id_hdr_size); - event->comm.tid = pid; + event->comm.tid = tid; return 0; } @@ -179,8 +193,10 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, struct machine *machine) { pid_t tgid, ppid; + bool kernel_thread; - if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0) + if (perf_event__prepare_comm(event, 0, pid, machine, &tgid, &ppid, + &kernel_thread) != 0) return -1; if (perf_tool__process_synth_event(tool, event, machine, process) != 0) @@ -347,6 +363,31 @@ static bool read_proc_maps_line(struct io *io, __u64 *start, __u64 *end, } } +static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event, + bool is_kernel) +{ + struct build_id bid; + int rc; + + if (is_kernel) + rc = sysfs__read_build_id("/sys/kernel/notes", &bid); + else + rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1; + + if (rc == 0) { + memcpy(event->build_id, bid.data, sizeof(bid.data)); + event->build_id_size = (u8) bid.size; + event->header.misc |= PERF_RECORD_MISC_MMAP_BUILD_ID; + event->__reserved_1 = 0; + event->__reserved_2 = 0; + } else { + if (event->filename[0] == '/') { + pr_debug2("Failed to read build ID for %s\n", + event->filename); + } + } +} + int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, @@ -453,6 +494,9 @@ out: event->mmap2.pid = tgid; event->mmap2.tid = pid; + if (symbol_conf.buildid_mmap2) + perf_record_mmap2__read_build_id(&event->mmap2, false); + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { rc = -1; break; @@ -596,16 +640,17 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t int rc = 0; struct map *pos; struct maps *maps = machine__kernel_maps(machine); - union perf_event *event = zalloc((sizeof(event->mmap) + - machine->id_hdr_size)); + union perf_event *event; + size_t size = symbol_conf.buildid_mmap2 ? + sizeof(event->mmap2) : sizeof(event->mmap); + + event = zalloc(size + machine->id_hdr_size); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); return -1; } - event->header.type = PERF_RECORD_MMAP; - /* * kernel uses 0 for user space maps, see kernel/perf_event.c * __perf_event_mmap @@ -616,23 +661,39 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; maps__for_each_entry(maps, pos) { - size_t size; - if (!__map__is_kmodule(pos)) continue; - size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); - event->mmap.header.type = PERF_RECORD_MMAP; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.start = pos->start; - event->mmap.len = pos->end - pos->start; - event->mmap.pid = machine->pid; + if (symbol_conf.buildid_mmap2) { + size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + event->mmap2.header.type = PERF_RECORD_MMAP2; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + event->mmap2.header.size += machine->id_hdr_size; + event->mmap2.start = pos->start; + event->mmap2.len = pos->end - pos->start; + event->mmap2.pid = machine->pid; + + memcpy(event->mmap2.filename, pos->dso->long_name, + pos->dso->long_name_len + 1); + + perf_record_mmap2__read_build_id(&event->mmap2, false); + } else { + size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; + event->mmap.start = pos->start; + event->mmap.len = pos->end - pos->start; + event->mmap.pid = machine->pid; + + memcpy(event->mmap.filename, pos->dso->long_name, + pos->dso->long_name_len + 1); + } - memcpy(event->mmap.filename, pos->dso->long_name, - pos->dso->long_name_len + 1); if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { rc = -1; break; @@ -643,6 +704,11 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t return rc; } +static int filter_task(const struct dirent *dirent) +{ + return isdigit(dirent->d_name[0]); +} + static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *mmap_event, union perf_event *fork_event, @@ -651,10 +717,10 @@ static int __event__synthesize_thread(union perf_event *comm_event, struct perf_tool *tool, struct machine *machine, bool mmap_data) { char filename[PATH_MAX]; - DIR *tasks; - struct dirent *dirent; + struct dirent **dirent; pid_t tgid, ppid; int rc = 0; + int i, n; /* special case: only send one comm event using passed in pid */ if (!full) { @@ -686,23 +752,22 @@ static int __event__synthesize_thread(union perf_event *comm_event, 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; - } + n = scandir(filename, &dirent, filter_task, alphasort); + if (n < 0) + return n; - while ((dirent = readdir(tasks)) != NULL) { + for (i = 0; i < n; i++) { char *end; pid_t _pid; + bool kernel_thread; - _pid = strtol(dirent->d_name, &end, 10); + _pid = strtol(dirent[i]->d_name, &end, 10); if (*end) continue; rc = -1; - if (perf_event__prepare_comm(comm_event, _pid, machine, - &tgid, &ppid) != 0) + if (perf_event__prepare_comm(comm_event, pid, _pid, machine, + &tgid, &ppid, &kernel_thread) != 0) break; if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, @@ -720,7 +785,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, break; rc = 0; - if (_pid == pid) { + if (_pid == pid && !kernel_thread) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); @@ -729,7 +794,10 @@ static int __event__synthesize_thread(union perf_event *comm_event, } } - closedir(tasks); + for (i = 0; i < n; i++) + zfree(&dirent[i]); + free(dirent); + return rc; } @@ -914,7 +982,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, return 0; snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); - n = scandir(proc_path, &dirent, 0, alphasort); + n = scandir(proc_path, &dirent, filter_task, alphasort); if (n < 0) return err; @@ -991,11 +1059,12 @@ static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine) { - size_t size; + union perf_event *event; + size_t size = symbol_conf.buildid_mmap2 ? + sizeof(event->mmap2) : sizeof(event->mmap); struct map *map = machine__kernel_map(machine); struct kmap *kmap; int err; - union perf_event *event; if (map == NULL) return -1; @@ -1009,7 +1078,7 @@ static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, * available use this, and after it is use this as a fallback for older * kernels. */ - event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); + event = zalloc(size + machine->id_hdr_size); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); @@ -1026,16 +1095,31 @@ static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; } - size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), - "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; - size = PERF_ALIGN(size, sizeof(u64)); - event->mmap.header.type = PERF_RECORD_MMAP; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); - event->mmap.pgoff = kmap->ref_reloc_sym->addr; - event->mmap.start = map->start; - event->mmap.len = map->end - event->mmap.start; - event->mmap.pid = machine->pid; + if (symbol_conf.buildid_mmap2) { + size = snprintf(event->mmap2.filename, sizeof(event->mmap2.filename), + "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap2.header.type = PERF_RECORD_MMAP2; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size) + machine->id_hdr_size); + event->mmap2.pgoff = kmap->ref_reloc_sym->addr; + event->mmap2.start = map->start; + event->mmap2.len = map->end - event->mmap.start; + event->mmap2.pid = machine->pid; + + perf_record_mmap2__read_build_id(&event->mmap2, true); + } else { + size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), + "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; + size = PERF_ALIGN(size, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); + event->mmap.pgoff = kmap->ref_reloc_sym->addr; + event->mmap.start = map->start; + event->mmap.len = map->end - event->mmap.start; + event->mmap.pid = machine->pid; + } err = perf_tool__process_synth_event(tool, event, machine, process); free(event); @@ -1412,6 +1496,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_DATA_PAGE_SIZE) result += sizeof(u64); + if (type & PERF_SAMPLE_CODE_PAGE_SIZE) + result += sizeof(u64); + if (type & PERF_SAMPLE_AUX) { result += sizeof(u64); result += sample->aux_sample.size; @@ -1596,6 +1683,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } + if (type & PERF_SAMPLE_CODE_PAGE_SIZE) { + *array = sample->code_page_size; + array++; + } + if (type & PERF_SAMPLE_AUX) { sz = sample->aux_sample.size; *array++ = sz; diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index a3db13dea937..0f383418e3df 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -56,6 +56,34 @@ enum target_errno target__validate(struct target *target) ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM; } + /* BPF and CPU are mutually exclusive */ + if (target->bpf_str && target->cpu_list) { + target->cpu_list = NULL; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__BPF_OVERRIDE_CPU; + } + + /* BPF and PID/TID are mutually exclusive */ + if (target->bpf_str && target->tid) { + target->tid = NULL; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__BPF_OVERRIDE_PID; + } + + /* BPF and UID are mutually exclusive */ + if (target->bpf_str && target->uid_str) { + target->uid_str = NULL; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__BPF_OVERRIDE_UID; + } + + /* BPF and THREADS are mutually exclusive */ + if (target->bpf_str && target->per_thread) { + target->per_thread = false; + if (ret == TARGET_ERRNO__SUCCESS) + ret = TARGET_ERRNO__BPF_OVERRIDE_THREAD; + } + /* THREAD and SYSTEM/CPU are mutually exclusive */ if (target->per_thread && (target->system_wide || target->cpu_list)) { target->per_thread = false; @@ -109,6 +137,10 @@ static const char *target__error_str[] = { "PID/TID switch overriding SYSTEM", "UID switch overriding SYSTEM", "SYSTEM/CPU switch overriding PER-THREAD", + "BPF switch overriding CPU", + "BPF switch overriding PID/TID", + "BPF switch overriding UID", + "BPF switch overriding THREAD", "Invalid User: %s", "Problems obtaining information for user %s", }; @@ -134,7 +166,7 @@ int target__strerror(struct target *target, int errnum, switch (errnum) { case TARGET_ERRNO__PID_OVERRIDE_CPU ... - TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD: + TARGET_ERRNO__BPF_OVERRIDE_THREAD: snprintf(buf, buflen, "%s", msg); break; diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h index 6ef01a83b24e..f132c6c2eef8 100644 --- a/tools/perf/util/target.h +++ b/tools/perf/util/target.h @@ -10,6 +10,7 @@ struct target { const char *tid; const char *cpu_list; const char *uid_str; + const char *bpf_str; uid_t uid; bool system_wide; bool uses_mmap; @@ -36,6 +37,10 @@ enum target_errno { TARGET_ERRNO__PID_OVERRIDE_SYSTEM, TARGET_ERRNO__UID_OVERRIDE_SYSTEM, TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD, + TARGET_ERRNO__BPF_OVERRIDE_CPU, + TARGET_ERRNO__BPF_OVERRIDE_PID, + TARGET_ERRNO__BPF_OVERRIDE_UID, + TARGET_ERRNO__BPF_OVERRIDE_THREAD, /* for target__parse_uid() */ TARGET_ERRNO__INVALID_UID, @@ -59,6 +64,11 @@ static inline bool target__has_cpu(struct target *target) return target->system_wide || target->cpu_list; } +static inline bool target__has_bpf(struct target *target) +{ + return target->bpf_str; +} + static inline bool target__none(struct target *target) { return !target__has_task(target) && !target__has_cpu(target); diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 1358e89cdf7d..62119ce69ad9 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -127,6 +127,7 @@ ifneq ($(silent),1) $(MAKE) $(PRINT_DIR) -C $$subdir QUIET_FLEX = @echo ' FLEX '$@; QUIET_BISON = @echo ' BISON '$@; + QUIET_GENSKEL = @echo ' GEN-SKEL '$@; descend = \ +@echo ' DESCEND '$(1); \ |