diff options
Diffstat (limited to 'tools/perf')
36 files changed, 518 insertions, 202 deletions
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 9932dcb502e9..5cf88cfb6bdc 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -755,27 +755,36 @@ else endif endif -ifeq ($(feature-libbfd), 1) - EXTLIBS += -lbfd -lopcodes -else - # we are on a system that requires -liberty and (maybe) -lz - # to link against -lbfd; test each case individually here - - # call all detections now so we get correct - # status in VF output - $(call feature_check,libbfd-liberty) - $(call feature_check,libbfd-liberty-z) - ifeq ($(feature-libbfd-liberty), 1) - EXTLIBS += -lbfd -lopcodes -liberty - FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl +ifndef NO_LIBBFD + ifeq ($(feature-libbfd), 1) + EXTLIBS += -lbfd -lopcodes else - ifeq ($(feature-libbfd-liberty-z), 1) - EXTLIBS += -lbfd -lopcodes -liberty -lz - FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl + # we are on a system that requires -liberty and (maybe) -lz + # to link against -lbfd; test each case individually here + + # call all detections now so we get correct + # status in VF output + $(call feature_check,libbfd-liberty) + $(call feature_check,libbfd-liberty-z) + + ifeq ($(feature-libbfd-liberty), 1) + EXTLIBS += -lbfd -lopcodes -liberty + FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl + else + ifeq ($(feature-libbfd-liberty-z), 1) + EXTLIBS += -lbfd -lopcodes -liberty -lz + FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl + endif endif + $(call feature_check,disassembler-four-args) + endif + + ifeq ($(feature-libbfd-buildid), 1) + CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT + else + msg := $(warning Old version of libbfd/binutils things like PE executable profiling will not be available); endif - $(call feature_check,disassembler-four-args) endif ifdef NO_DEMANGLE diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 4aa6de1aa67d..d9329ae84e17 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -10,25 +10,13 @@ extern struct timeval bench__start, bench__end, bench__runtime; * The madvise transparent hugepage constants were added in glibc * 2.13. For compatibility with older versions of glibc, define these * tokens if they are not already defined. - * - * PA-RISC uses different madvise values from other architectures and - * needs to be special-cased. */ -#ifdef __hppa__ -# ifndef MADV_HUGEPAGE -# define MADV_HUGEPAGE 67 -# endif -# ifndef MADV_NOHUGEPAGE -# define MADV_NOHUGEPAGE 68 -# endif -#else # ifndef MADV_HUGEPAGE # define MADV_HUGEPAGE 14 # endif # ifndef MADV_NOHUGEPAGE # define MADV_NOHUGEPAGE 15 # endif -#endif int bench_numa(int argc, const char **argv); int bench_sched_messaging(int argc, const char **argv); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 454e275cd5df..9c03f67398cb 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -80,6 +80,7 @@ struct record { struct auxtrace_record *itr; struct evlist *evlist; struct perf_session *session; + struct evlist *sb_evlist; int realtime_prio; bool no_buildid; bool no_buildid_set; @@ -1109,8 +1110,8 @@ static int record__switch_output(struct record *rec, bool at_exit) { struct perf_data *data = &rec->data; + char *new_filename = NULL; int fd, err; - char *new_filename; /* Same Size: "2015122520103046"*/ char timestamp[] = "InvalidTimestamp"; @@ -1343,7 +1344,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) struct perf_data *data = &rec->data; struct perf_session *session; bool disabled = false, draining = false; - struct evlist *sb_evlist = NULL; int fd; float ratio = 0; @@ -1446,18 +1446,29 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } + err = -1; if (!rec->no_buildid && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) { pr_err("Couldn't generate buildids. " "Use --no-buildid to profile anyway.\n"); - err = -1; goto out_child; } - if (!opts->no_bpf_event) - bpf_event__add_sb_event(&sb_evlist, &session->header.env); + if (!opts->no_bpf_event) { + rec->sb_evlist = evlist__new(); + + if (rec->sb_evlist == NULL) { + pr_err("Couldn't create side band evlist.\n."); + goto out_child; + } + + if (evlist__add_bpf_sb_event(rec->sb_evlist, &session->header.env)) { + pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n."); + goto out_child; + } + } - if (perf_evlist__start_sb_thread(sb_evlist, &rec->opts.target)) { + if (perf_evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); opts->no_bpf_event = true; } @@ -1731,7 +1742,7 @@ out_delete_session: perf_session__delete(session); if (!opts->no_bpf_event) - perf_evlist__stop_sb_thread(sb_evlist); + perf_evlist__stop_sb_thread(rec->sb_evlist); return status; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 5cacc4f84c8d..0826893098ce 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -666,7 +666,7 @@ static void create_tasks(struct perf_sched *sched) err = pthread_attr_init(&attr); BUG_ON(err); err = pthread_attr_setstacksize(&attr, - (size_t) max(16 * 1024, PTHREAD_STACK_MIN)); + (size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN)); BUG_ON(err); err = pthread_mutex_lock(&sched->start_work_mutex); BUG_ON(err); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a30d62186f5e..b8fab267e855 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1542,7 +1542,6 @@ int cmd_top(int argc, const char **argv) OPTS_EVSWITCH(&top.evswitch), OPT_END() }; - struct evlist *sb_evlist = NULL; const char * const top_usage[] = { "perf top [<options>]", NULL @@ -1679,13 +1678,27 @@ int cmd_top(int argc, const char **argv) top.session = perf_session__new(NULL, false, NULL); if (IS_ERR(top.session)) { status = PTR_ERR(top.session); + top.session = NULL; goto out_delete_evlist; } - if (!top.record_opts.no_bpf_event) - bpf_event__add_sb_event(&sb_evlist, &perf_env); +#ifdef HAVE_LIBBPF_SUPPORT + if (!top.record_opts.no_bpf_event) { + top.sb_evlist = evlist__new(); - if (perf_evlist__start_sb_thread(sb_evlist, target)) { + if (top.sb_evlist == NULL) { + pr_err("Couldn't create side band evlist.\n."); + goto out_delete_evlist; + } + + if (evlist__add_bpf_sb_event(top.sb_evlist, &perf_env)) { + pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n."); + goto out_delete_evlist; + } + } +#endif + + if (perf_evlist__start_sb_thread(top.sb_evlist, target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); opts->no_bpf_event = true; } @@ -1693,7 +1706,7 @@ int cmd_top(int argc, const char **argv) status = __cmd_top(&top); if (!opts->no_bpf_event) - perf_evlist__stop_sb_thread(sb_evlist); + perf_evlist__stop_sb_thread(top.sb_evlist); out_delete_evlist: evlist__delete(top.evlist); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index a5201de1a191..6052eb057821 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -86,6 +86,34 @@ # define F_LINUX_SPECIFIC_BASE 1024 #endif +#define RAW_SYSCALL_ARGS_NUM 6 + +/* + * strtoul: Go from a string to a value, i.e. for msr: MSR_FS_BASE to 0xc0000100 + */ +struct syscall_arg_fmt { + size_t (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg); + bool (*strtoul)(char *bf, size_t size, struct syscall_arg *arg, u64 *val); + unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val); + void *parm; + const char *name; + bool show_zero; +}; + +struct syscall_fmt { + const char *name; + const char *alias; + struct { + const char *sys_enter, + *sys_exit; + } bpf_prog_name; + struct syscall_arg_fmt arg[RAW_SYSCALL_ARGS_NUM]; + u8 nr_args; + bool errpid; + bool timeout; + bool hexret; +}; + struct trace { struct perf_tool tool; struct syscalltbl *sctbl; @@ -694,27 +722,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size, #include "trace/beauty/socket_type.c" #include "trace/beauty/waitid_options.c" -struct syscall_arg_fmt { - size_t (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg); - unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val); - void *parm; - const char *name; - bool show_zero; -}; - -static struct syscall_fmt { - const char *name; - const char *alias; - struct { - const char *sys_enter, - *sys_exit; - } bpf_prog_name; - struct syscall_arg_fmt arg[6]; - u8 nr_args; - bool errpid; - bool timeout; - bool hexret; -} syscall_fmts[] = { +static struct syscall_fmt syscall_fmts[] = { { .name = "access", .arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, }, { .name = "arch_prctl", @@ -1012,7 +1020,7 @@ struct syscall { */ struct bpf_map_syscall_entry { bool enabled; - u16 string_args_len[6]; + u16 string_args_len[RAW_SYSCALL_ARGS_NUM]; }; /* @@ -1437,7 +1445,7 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args) { int idx; - if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0) + if (nr_args == RAW_SYSCALL_ARGS_NUM && sc->fmt && sc->fmt->nr_args != 0) nr_args = sc->fmt->nr_args; sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt)); @@ -1453,15 +1461,37 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args) return 0; } -static int syscall__set_arg_fmts(struct syscall *sc) +static struct syscall_arg_fmt syscall_arg_fmts__by_name[] = { +}; + +static int syscall_arg_fmt__cmp(const void *name, const void *fmtp) +{ + const struct syscall_arg_fmt *fmt = fmtp; + return strcmp(name, fmt->name); +} + +static struct syscall_arg_fmt * +__syscall_arg_fmt__find_by_name(struct syscall_arg_fmt *fmts, const int nmemb, const char *name) { - struct tep_format_field *field, *last_field = NULL; - int idx = 0, len; + return bsearch(name, fmts, nmemb, sizeof(struct syscall_arg_fmt), syscall_arg_fmt__cmp); +} + +static struct syscall_arg_fmt *syscall_arg_fmt__find_by_name(const char *name) +{ + const int nmemb = ARRAY_SIZE(syscall_arg_fmts__by_name); + return __syscall_arg_fmt__find_by_name(syscall_arg_fmts__by_name, nmemb, name); +} - for (field = sc->args; field; field = field->next, ++idx) { +static struct tep_format_field * +syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field *field) +{ + struct tep_format_field *last_field = NULL; + int len; + + for (; field; field = field->next, ++arg) { last_field = field; - if (sc->fmt && sc->fmt->arg[idx].scnprintf) + if (arg->scnprintf) continue; len = strlen(field->name); @@ -1469,13 +1499,13 @@ static int syscall__set_arg_fmts(struct syscall *sc) if (strcmp(field->type, "const char *") == 0 && ((len >= 4 && strcmp(field->name + len - 4, "name") == 0) || strstr(field->name, "path") != NULL)) - sc->arg_fmt[idx].scnprintf = SCA_FILENAME; + arg->scnprintf = SCA_FILENAME; else if ((field->flags & TEP_FIELD_IS_POINTER) || strstr(field->name, "addr")) - sc->arg_fmt[idx].scnprintf = SCA_PTR; + arg->scnprintf = SCA_PTR; else if (strcmp(field->type, "pid_t") == 0) - sc->arg_fmt[idx].scnprintf = SCA_PID; + arg->scnprintf = SCA_PID; else if (strcmp(field->type, "umode_t") == 0) - sc->arg_fmt[idx].scnprintf = SCA_MODE_T; + arg->scnprintf = SCA_MODE_T; else if ((strcmp(field->type, "int") == 0 || strcmp(field->type, "unsigned int") == 0 || strcmp(field->type, "long") == 0) && @@ -1487,10 +1517,24 @@ static int syscall__set_arg_fmts(struct syscall *sc) * 23 unsigned int * 7 unsigned long */ - sc->arg_fmt[idx].scnprintf = SCA_FD; + arg->scnprintf = SCA_FD; + } else { + struct syscall_arg_fmt *fmt = syscall_arg_fmt__find_by_name(field->name); + + if (fmt) { + arg->scnprintf = fmt->scnprintf; + arg->strtoul = fmt->strtoul; + } } } + return last_field; +} + +static int syscall__set_arg_fmts(struct syscall *sc) +{ + struct tep_format_field *last_field = syscall_arg_fmt__init_array(sc->arg_fmt, sc->args); + if (last_field) sc->args_size = last_field->offset + last_field->size; @@ -1511,11 +1555,11 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc = trace->syscalls.table + id; if (sc->nonexistent) - return 0; + return -EEXIST; if (name == NULL) { sc->nonexistent = true; - return 0; + return -EEXIST; } sc->name = name; @@ -1529,11 +1573,18 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc->tp_format = trace_event__tp_format("syscalls", tp_name); } - if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields)) - return -ENOMEM; - - if (IS_ERR(sc->tp_format)) + /* + * Fails to read trace point format via sysfs node, so the trace point + * doesn't exist. Set the 'nonexistent' flag as true. + */ + if (IS_ERR(sc->tp_format)) { + sc->nonexistent = true; return PTR_ERR(sc->tp_format); + } + + if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? + RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields)) + return -ENOMEM; sc->args = sc->tp_format->format.fields; /* @@ -1736,6 +1787,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, if (arg.mask & bit) continue; + arg.fmt = &sc->arg_fmt[arg.idx]; val = syscall_arg__val(&arg, arg.idx); /* * Some syscall args need some mask, most don't and @@ -1825,11 +1877,8 @@ static struct syscall *trace__syscall_info(struct trace *trace, (err = trace__read_syscall_info(trace, id)) != 0) goto out_cant_read; - if (trace->syscalls.table[id].name == NULL) { - if (trace->syscalls.table[id].nonexistent) - return NULL; + if (trace->syscalls.table && trace->syscalls.table[id].nonexistent) goto out_cant_read; - } return &trace->syscalls.table[id]; diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index fdf75d45efff..978249d7868c 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -165,7 +165,12 @@ __perf_main () local cur1=${COMP_WORDS[COMP_CWORD]} local raw_evts=$($cmd list --raw-dump) - local arr s tmp result + local arr s tmp result cpu_evts + + # aarch64 doesn't have /sys/bus/event_source/devices/cpu/events + if [[ `uname -m` != aarch64 ]]; then + cpu_evts=$(ls /sys/bus/event_source/devices/cpu/events) + fi if [[ "$cur1" == */* && ${cur1#*/} =~ ^[A-Z] ]]; then OLD_IFS="$IFS" @@ -183,9 +188,9 @@ __perf_main () fi done - evts=${result}" "$(ls /sys/bus/event_source/devices/cpu/events) + evts=${result}" "${cpu_evts} else - evts=${raw_evts}" "$(ls /sys/bus/event_source/devices/cpu/events) + evts=${raw_evts}" "${cpu_evts} fi if [[ "$cur1" == , ]]; then diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 215ba30b8534..a055dee6a46a 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -6,10 +6,13 @@ pmu-events-y += pmu-events.o JDIR = pmu-events/arch/$(SRCARCH) JSON = $(shell [ -d $(JDIR) ] && \ find $(JDIR) -name '*.json' -o -name 'mapfile.csv') +JDIR_TEST = pmu-events/arch/test +JSON_TEST = $(shell [ -d $(JDIR_TEST) ] && \ + find $(JDIR_TEST) -name '*.json') # # Locate/process JSON files in pmu-events/arch/ # directory and create tables in pmu-events.c. # -$(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JEVENTS) +$(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JSON_TEST) $(JEVENTS) $(Q)$(call echo-cmd,gen)$(JEVENTS) $(SRCARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V) diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json index 62b864269623..ce75652e9051 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json @@ -1417,7 +1417,7 @@ {, "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", - "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. " + "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only." }, {, "EventCode": "0x201E8", @@ -2017,7 +2017,7 @@ {, "EventCode": "0xC0BC", "EventName": "PM_LSU_FLUSH_OTHER", - "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the “bad dval” back and flush all younger ops)" + "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the 'bad dval' back and flush all younger ops)" }, {, "EventCode": "0x5094", diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json index b4772f54a271..e2f2ed0a3549 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json @@ -442,7 +442,7 @@ {, "EventCode": "0x4D052", "EventName": "PM_2FLOP_CMPL", - "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg " + "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg" }, {, "EventCode": "0x1F142", diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh new file mode 100644 index 000000000000..319f36ebb9a4 --- /dev/null +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# test perf probe of function from different CU +# SPDX-License-Identifier: GPL-2.0 + +set -e + +# skip if there's no gcc +if ! [ -x "$(command -v gcc)" ]; then + echo "failed: no gcc compiler" + exit 2 +fi + +temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX) + +cleanup() +{ + trap - EXIT TERM INT + if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then + echo "--- Cleaning up ---" + perf probe -x ${temp_dir}/testfile -d foo || true + rm -f "${temp_dir}/"* + rmdir "${temp_dir}" + fi +} + +trap_cleanup() +{ + cleanup + exit 1 +} + +trap trap_cleanup EXIT TERM INT + +cat > ${temp_dir}/testfile-foo.h << EOF +struct t +{ + int *p; + int c; +}; + +extern int foo (int i, struct t *t); +EOF + +cat > ${temp_dir}/testfile-foo.c << EOF +#include "testfile-foo.h" + +int +foo (int i, struct t *t) +{ + int j, res = 0; + for (j = 0; j < i && j < t->c; j++) + res += t->p[j]; + + return res; +} +EOF + +cat > ${temp_dir}/testfile-main.c << EOF +#include "testfile-foo.h" + +static struct t g; + +int +main (int argc, char **argv) +{ + int i; + int j[argc]; + g.c = argc; + g.p = j; + for (i = 0; i < argc; i++) + j[i] = (int) argv[i][0]; + return foo (3, &g); +} +EOF + +gcc -g -Og -flto -c ${temp_dir}/testfile-foo.c -o ${temp_dir}/testfile-foo.o +gcc -g -Og -c ${temp_dir}/testfile-main.c -o ${temp_dir}/testfile-main.o +gcc -g -Og -o ${temp_dir}/testfile ${temp_dir}/testfile-foo.o ${temp_dir}/testfile-main.o + +perf probe -x ${temp_dir}/testfile --funcs foo +perf probe -x ${temp_dir}/testfile foo + +cleanup diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 7e06605f7c76..4cc4f6b3d4a1 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -78,6 +78,8 @@ struct augmented_arg { u64 value[]; }; +struct syscall_arg_fmt; + /** * @val: value of syscall argument being formatted * @args: All the args, use syscall_args__val(arg, nth) to access one @@ -94,6 +96,7 @@ struct augmented_arg { struct syscall_arg { unsigned long val; unsigned char *args; + struct syscall_arg_fmt *fmt; struct { struct augmented_arg *args; int size; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 514cef3a17b4..3461fa8cf440 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1718,7 +1718,7 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser) hists_browser__scnprintf_hierarchy_headers(browser, headers, sizeof(headers)); - ui_browser__gotorc(&browser->b, 0, 0); + ui_browser__gotorc_title(&browser->b, 0, 0); ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1); } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0c5e4ce390ef..e4f8e8903a0f 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1741,8 +1741,11 @@ static int symbol__disassemble_bpf(struct symbol *sym, perf_exe(tpath, sizeof(tpath)); bfdf = bfd_openr(tpath, NULL); - assert(bfdf); - assert(bfd_check_format(bfdf, bfd_object)); + if (bfdf == NULL) + abort(); + + if (!bfd_check_format(bfdf, bfd_object)) + abort(); s = open_memstream(&buf, &buf_size); if (!s) { @@ -1790,7 +1793,8 @@ static int symbol__disassemble_bpf(struct symbol *sym, #else disassemble = disassembler(bfdf); #endif - assert(disassemble); + if (disassemble == NULL) + abort(); fflush(s); do { diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index ae5b97427192..3d5cd16ca4de 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1710,11 +1710,19 @@ struct sym_args { bool near; }; +static bool kern_sym_name_match(const char *kname, const char *name) +{ + size_t n = strlen(name); + + return !strcmp(kname, name) || + (!strncmp(kname, name, n) && kname[n] == '\t'); +} + static bool kern_sym_match(struct sym_args *args, const char *name, char type) { /* A function with the same name, and global or the n'th found or any */ return kallsyms__is_function(type) && - !strcmp(name, args->name) && + kern_sym_name_match(name, args->name) && ((args->global && isupper(type)) || (args->selected && ++(args->cnt) == args->idx) || (!args->global && !args->selected)); @@ -1817,6 +1825,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, char type, u64 start) { struct sym_args *args = arg; + u64 size; if (!kallsyms__is_function(type)) return 0; @@ -1826,7 +1835,9 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, args->start = start; } /* Don't know exactly where the kernel ends, so we add a page */ - args->size = round_up(start, page_size) + page_size - args->start; + size = round_up(start, page_size) + page_size - args->start; + if (size > args->size) + args->size = size; return 0; } @@ -1987,7 +1998,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, *size = sym->start - *start; if (idx > 0) { if (*size) - return 1; + return 0; } else if (dso_sym_match(sym, sym_name, &cnt, idx)) { print_duplicate_syms(dso, sym_name); return -EINVAL; diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 782c0c8a9a83..ae30e20af246 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -422,8 +422,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data) return 0; } -int bpf_event__add_sb_event(struct evlist **evlist, - struct perf_env *env) +int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env) { struct perf_event_attr attr = { .type = PERF_TYPE_SOFTWARE, @@ -443,9 +442,9 @@ int bpf_event__add_sb_event(struct evlist **evlist, return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env); } -void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, - struct perf_env *env, - FILE *fp) +void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, + struct perf_env *env, + FILE *fp) { __u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens); __u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms); @@ -461,7 +460,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, if (info->btf_id) { struct btf_node *node; - node = perf_env__find_btf(env, info->btf_id); + node = __perf_env__find_btf(env, info->btf_id); if (node) btf = btf__new((__u8 *)(node->data), node->data_size); diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 81fdc88e6c1a..50f7412464df 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -33,11 +33,10 @@ struct btf_node { #ifdef HAVE_LIBBPF_SUPPORT int machine__process_bpf(struct machine *machine, union perf_event *event, struct perf_sample *sample); -int bpf_event__add_sb_event(struct evlist **evlist, - struct perf_env *env); -void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, - struct perf_env *env, - FILE *fp); +int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env); +void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, + struct perf_env *env, + FILE *fp); #else static inline int machine__process_bpf(struct machine *machine __maybe_unused, union perf_event *event __maybe_unused, @@ -46,15 +45,15 @@ static inline int machine__process_bpf(struct machine *machine __maybe_unused, return 0; } -static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused, - struct perf_env *env __maybe_unused) +static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused, + struct perf_env *env __maybe_unused) { return 0; } -static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused, - struct perf_env *env __maybe_unused, - FILE *fp __maybe_unused) +static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused, + struct perf_env *env __maybe_unused, + FILE *fp __maybe_unused) { } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 3c874f52f1a2..4da900bdb2f1 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -120,6 +120,7 @@ int perf_data__open_dir(struct perf_data *data) file->size = st.st_size; } + closedir(dir); if (!files) return -EINVAL; @@ -128,6 +129,7 @@ int perf_data__open_dir(struct perf_data *data) return 0; out_err: + closedir(dir); close_dir(files, nr); return ret; } diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index ab34ef2c661f..1d51aa88f4cb 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -254,26 +254,13 @@ static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name, { Dwarf_Attribute attr; - if (dwarf_attr(tp_die, attr_name, &attr) == NULL || + if (dwarf_attr_integrate(tp_die, attr_name, &attr) == NULL || dwarf_formudata(&attr, result) != 0) return -ENOENT; return 0; } -/* Get attribute and translate it as a sdata */ -static int die_get_attr_sdata(Dwarf_Die *tp_die, unsigned int attr_name, - Dwarf_Sword *result) -{ - Dwarf_Attribute attr; - - if (dwarf_attr(tp_die, attr_name, &attr) == NULL || - dwarf_formsdata(&attr, result) != 0) - return -ENOENT; - - return 0; -} - /** * die_is_signed_type - Check whether a type DIE is signed or not * @tp_die: a DIE of a type @@ -397,9 +384,9 @@ int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs) /* Get the call file index number in CU DIE */ static int die_get_call_fileno(Dwarf_Die *in_die) { - Dwarf_Sword idx; + Dwarf_Word idx; - if (die_get_attr_sdata(in_die, DW_AT_call_file, &idx) == 0) + if (die_get_attr_udata(in_die, DW_AT_call_file, &idx) == 0) return (int)idx; else return -ENOENT; @@ -408,9 +395,9 @@ static int die_get_call_fileno(Dwarf_Die *in_die) /* Get the declared file index number in CU DIE */ static int die_get_decl_fileno(Dwarf_Die *pdie) { - Dwarf_Sword idx; + Dwarf_Word idx; - if (die_get_attr_sdata(pdie, DW_AT_decl_file, &idx) == 0) + if (die_get_attr_udata(pdie, DW_AT_decl_file, &idx) == 0) return (int)idx; else return -ENOENT; @@ -1020,7 +1007,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf) ret = die_get_typename(vr_die, buf); if (ret < 0) { pr_debug("Failed to get type, make it unknown.\n"); - ret = strbuf_add(buf, " (unknown_type)", 14); + ret = strbuf_add(buf, "(unknown_type)", 14); } return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die)); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index ef64e197bc8d..953db9dd25eb 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -16,12 +16,18 @@ struct perf_env perf_env; void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { + down_write(&env->bpf_progs.lock); + __perf_env__insert_bpf_prog_info(env, info_node); + up_write(&env->bpf_progs.lock); +} + +void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) +{ __u32 prog_id = info_node->info_linear->info.id; struct bpf_prog_info_node *node; struct rb_node *parent = NULL; struct rb_node **p; - down_write(&env->bpf_progs.lock); p = &env->bpf_progs.infos.rb_node; while (*p != NULL) { @@ -33,15 +39,13 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env, p = &(*p)->rb_right; } else { pr_debug("duplicated bpf prog info %u\n", prog_id); - goto out; + return; } } rb_link_node(&info_node->rb_node, parent, p); rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos); env->bpf_progs.infos_cnt++; -out: - up_write(&env->bpf_progs.lock); } struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, @@ -71,13 +75,21 @@ out: bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) { + bool ret; + + down_write(&env->bpf_progs.lock); + ret = __perf_env__insert_btf(env, btf_node); + up_write(&env->bpf_progs.lock); + return ret; +} + +bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) +{ struct rb_node *parent = NULL; __u32 btf_id = btf_node->id; struct btf_node *node; struct rb_node **p; - bool ret = true; - down_write(&env->bpf_progs.lock); p = &env->bpf_progs.btfs.rb_node; while (*p != NULL) { @@ -89,25 +101,31 @@ bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) p = &(*p)->rb_right; } else { pr_debug("duplicated btf %u\n", btf_id); - ret = false; - goto out; + return false; } } rb_link_node(&btf_node->rb_node, parent, p); rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs); env->bpf_progs.btfs_cnt++; -out: - up_write(&env->bpf_progs.lock); - return ret; + return true; } struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) { + struct btf_node *res; + + down_read(&env->bpf_progs.lock); + res = __perf_env__find_btf(env, btf_id); + up_read(&env->bpf_progs.lock); + return res; +} + +struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id) +{ struct btf_node *node = NULL; struct rb_node *n; - down_read(&env->bpf_progs.lock); n = env->bpf_progs.btfs.rb_node; while (n) { @@ -117,13 +135,9 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) else if (btf_id > node->id) n = n->rb_right; else - goto out; + return node; } - node = NULL; - -out: - up_read(&env->bpf_progs.lock); - return node; + return NULL; } /* purge data in bpf_progs.infos tree */ @@ -183,6 +197,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->sibling_threads); zfree(&env->pmu_mappings); zfree(&env->cpu); + zfree(&env->numa_map); for (i = 0; i < env->nr_numa_nodes; i++) perf_cpu_map__put(env->numa_nodes[i].map); @@ -342,3 +357,42 @@ const char *perf_env__arch(struct perf_env *env) return normalize_arch(arch_name); } + + +int perf_env__numa_node(struct perf_env *env, int cpu) +{ + if (!env->nr_numa_map) { + struct numa_node *nn; + int i, nr = 0; + + for (i = 0; i < env->nr_numa_nodes; i++) { + nn = &env->numa_nodes[i]; + nr = max(nr, perf_cpu_map__max(nn->map)); + } + + nr++; + + /* + * We initialize the numa_map array to prepare + * it for missing cpus, which return node -1 + */ + env->numa_map = malloc(nr * sizeof(int)); + if (!env->numa_map) + return -1; + + for (i = 0; i < nr; i++) + env->numa_map[i] = -1; + + env->nr_numa_map = nr; + + for (i = 0; i < env->nr_numa_nodes; i++) { + int tmp, j; + + nn = &env->numa_nodes[i]; + perf_cpu_map__for_each_cpu(j, tmp, nn->map) + env->numa_map[j] = i; + } + } + + return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1; +} diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 37028215d4a5..b0778483fa04 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -87,6 +87,10 @@ struct perf_env { struct rb_root btfs; u32 btfs_cnt; } bpf_progs; + + /* For fast cpu to numa node lookup via perf_env__numa_node */ + int *numa_map; + int nr_numa_map; }; enum perf_compress_type { @@ -113,10 +117,16 @@ const char *perf_env__raw_arch(struct perf_env *env); int perf_env__nr_cpus_avail(struct perf_env *env); void perf_env__init(struct perf_env *env); +void __perf_env__insert_bpf_prog_info(struct perf_env *env, + struct bpf_prog_info_node *info_node); void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); +bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); +struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id); + +int perf_env__numa_node(struct perf_env *env, int cpu); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 505b890ac85c..b110deb88425 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1672,39 +1672,26 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, return leader; } -int perf_evlist__add_sb_event(struct evlist **evlist, +int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, perf_evsel__sb_cb_t cb, void *data) { struct evsel *evsel; - bool new_evlist = (*evlist) == NULL; - - if (*evlist == NULL) - *evlist = evlist__new(); - if (*evlist == NULL) - return -1; if (!attr->sample_id_all) { pr_warning("enabling sample_id_all for all side band events\n"); attr->sample_id_all = 1; } - evsel = perf_evsel__new_idx(attr, (*evlist)->core.nr_entries); + evsel = perf_evsel__new_idx(attr, evlist->core.nr_entries); if (!evsel) - goto out_err; + return -1; evsel->side_band.cb = cb; evsel->side_band.data = data; - evlist__add(*evlist, evsel); + evlist__add(evlist, evsel); return 0; - -out_err: - if (new_evlist) { - evlist__delete(*evlist); - *evlist = NULL; - } - return -1; } static void *perf_evlist__poll_thread(void *arg) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 7cfe75522ba5..6f920ca91a69 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -107,7 +107,7 @@ int __perf_evlist__add_default_attrs(struct evlist *evlist, int perf_evlist__add_dummy(struct evlist *evlist); -int perf_evlist__add_sb_event(struct evlist **evlist, +int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, perf_evsel__sb_cb_t cb, void *data); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 9dd9e3f4ef59..cd1eddf0ab37 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1955,7 +1955,6 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->period = evsel->core.attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; data->misc = event->header.misc; - data->id = -1ULL; data->data_src = PERF_MEM_DATA_SRC_NONE; if (event->header.type != PERF_RECORD_SAMPLE) { diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index f9f18b8b1df9..04509144ff84 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -35,7 +35,11 @@ #define BUILD_ID_URANDOM /* different uuid for each run */ -#ifdef HAVE_LIBCRYPTO +// FIXME, remove this and fix the deprecation warnings before its removed and +// We'll break for good here... +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + +#ifdef HAVE_LIBCRYPTO_SUPPORT #define BUILD_ID_MD5 #undef BUILD_ID_SHA /* does not seem to work well when linked with Java */ @@ -252,6 +256,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, Elf_Data *d; Elf_Scn *scn; Elf_Ehdr *ehdr; + Elf_Phdr *phdr; Elf_Shdr *shdr; uint64_t eh_frame_base_offset; char *strsym = NULL; @@ -287,6 +292,19 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */ /* + * setup program header + */ + phdr = elf_newphdr(e, 1); + phdr[0].p_type = PT_LOAD; + phdr[0].p_offset = GEN_ELF_TEXT_OFFSET; + phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET; + phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET; + phdr[0].p_filesz = csize; + phdr[0].p_memsz = csize; + phdr[0].p_flags = PF_X | PF_R; + phdr[0].p_align = 8; + + /* * setup text section */ scn = elf_newscn(e); diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index d4137559be05..ac638945b4cb 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -50,8 +50,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #if GEN_ELF_CLASS == ELFCLASS64 #define elf_newehdr elf64_newehdr +#define elf_newphdr elf64_newphdr #define elf_getshdr elf64_getshdr #define Elf_Ehdr Elf64_Ehdr +#define Elf_Phdr Elf64_Phdr #define Elf_Shdr Elf64_Shdr #define Elf_Sym Elf64_Sym #define ELF_ST_TYPE(a) ELF64_ST_TYPE(a) @@ -59,8 +61,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #define ELF_ST_VIS(a) ELF64_ST_VISIBILITY(a) #else #define elf_newehdr elf32_newehdr +#define elf_newphdr elf32_newphdr #define elf_getshdr elf32_getshdr #define Elf_Ehdr Elf32_Ehdr +#define Elf_Phdr Elf32_Phdr #define Elf_Shdr Elf32_Shdr #define Elf_Sym Elf32_Sym #define ELF_ST_TYPE(a) ELF32_ST_TYPE(a) diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c index b205d929245f..e68935e9ac8c 100644 --- a/tools/perf/util/get_current_dir_name.c +++ b/tools/perf/util/get_current_dir_name.c @@ -3,8 +3,9 @@ // #ifndef HAVE_GET_CURRENT_DIR_NAME #include "get_current_dir_name.h" +#include <limits.h> +#include <string.h> #include <unistd.h> -#include <stdlib.h> /* Android's 'bionic' library, for one, doesn't have this */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d3412f2c0d18..a68feeb3eb00 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1546,8 +1546,8 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); - bpf_event__print_bpf_prog_info(&node->info_linear->info, - env, fp); + __bpf_event__print_bpf_prog_info(&node->info_linear->info, + env, fp); } up_read(&env->bpf_progs.lock); @@ -2724,7 +2724,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) /* after reading from file, translate offset to address */ bpf_program__bpil_offs_to_addr(info_linear); info_node->info_linear = info_linear; - perf_env__insert_bpf_prog_info(env, info_node); + __perf_env__insert_bpf_prog_info(env, info_node); } up_write(&env->bpf_progs.lock); @@ -2777,7 +2777,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) if (__do_read(ff, node->data, data_size)) goto out; - perf_env__insert_btf(env, node); + __perf_env__insert_btf(env, node); node = NULL; } @@ -3720,7 +3720,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, union perf_event *event, struct evlist **pevlist) { - u32 i, ids, n_ids; + u32 i, n_ids; + u64 *ids; struct evsel *evsel; struct evlist *evlist = *pevlist; @@ -3736,9 +3737,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, evlist__add(evlist, evsel); - ids = event->header.size; - ids -= (void *)&event->attr.id - (void *)event; - n_ids = ids / sizeof(u64); + n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size; + n_ids = n_ids / sizeof(u64); /* * We don't have the cpu and thread maps on the header, so * for allocating the perf_sample_id table we fake 1 cpu and @@ -3747,8 +3747,9 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, if (perf_evsel__alloc_id(&evsel->core, 1, n_ids)) return -ENOMEM; + ids = (void *)&event->attr.attr + event->attr.attr.size; for (i = 0; i < n_ids; i++) { - perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]); + perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]); } return 0; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index eab7e8ef6789..52474e44fb28 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1592,6 +1592,8 @@ static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) decoder->cbr = cbr; decoder->cbr_cyc_to_tsc = decoder->max_non_turbo_ratio_fp / cbr; + decoder->cyc_ref_timestamp = decoder->timestamp; + decoder->cycle_cnt = 0; intel_pt_mtc_cyc_cnt_cbr(decoder); } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 9b7cc5f909b0..b40832419a27 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3038,6 +3038,7 @@ static const char * const intel_pt_info_fmts[] = { [INTEL_PT_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n", [INTEL_PT_PER_CPU_MMAPS] = " Per-cpu maps %"PRId64"\n", [INTEL_PT_MTC_BIT] = " MTC bit %#"PRIx64"\n", + [INTEL_PT_MTC_FREQ_BITS] = " MTC freq bits %#"PRIx64"\n", [INTEL_PT_TSC_CTC_N] = " TSC:CTC numerator %"PRIu64"\n", [INTEL_PT_TSC_CTC_D] = " TSC:CTC denominator %"PRIu64"\n", [INTEL_PT_CYC_BIT] = " CYC bit %#"PRIx64"\n", @@ -3052,8 +3053,12 @@ static void intel_pt_print_info(__u64 *arr, int start, int finish) if (!dump_trace) return; - for (i = start; i <= finish; i++) - fprintf(stdout, intel_pt_info_fmts[i], arr[i]); + for (i = start; i <= finish; i++) { + const char *fmt = intel_pt_info_fmts[i]; + + if (fmt) + fprintf(stdout, fmt, arr[i]); + } } static void intel_pt_print_info_str(const char *name, const char *str) diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index e7c7e3232fc5..b275a1b297c3 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -523,14 +523,37 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, pr_debug("llvm compiling command template: %s\n", template); + /* + * Below, substitute control characters for values that can cause the + * echo to misbehave, then substitute the values back. + */ err = -ENOMEM; - if (asprintf(&command_echo, "echo -n \"%s\"", template) < 0) + if (asprintf(&command_echo, "echo -n \a%s\a", template) < 0) goto errout; +#define SWAP_CHAR(a, b) do { if (*p == a) *p = b; } while (0) + for (char *p = command_echo; *p; p++) { + SWAP_CHAR('<', '\001'); + SWAP_CHAR('>', '\002'); + SWAP_CHAR('"', '\003'); + SWAP_CHAR('\'', '\004'); + SWAP_CHAR('|', '\005'); + SWAP_CHAR('&', '\006'); + SWAP_CHAR('\a', '"'); + } err = read_from_pipe(command_echo, (void **) &command_out, NULL); if (err) goto errout; + for (char *p = command_out; *p; p++) { + SWAP_CHAR('\001', '<'); + SWAP_CHAR('\002', '>'); + SWAP_CHAR('\003', '"'); + SWAP_CHAR('\004', '\''); + SWAP_CHAR('\005', '|'); + SWAP_CHAR('\006', '&'); + } +#undef SWAP_CHAR pr_debug("llvm compiling command : %s\n", command_out); err = read_from_pipe(template, &obj_buf, &obj_buf_sz); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 4027906fd3e3..baf73ca66a2b 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -830,8 +830,7 @@ static int hist_entry__dso_to_filter(struct hist_entry *he, int type, static int64_t sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) { - struct addr_map_symbol *from_l = &left->branch_info->from; - struct addr_map_symbol *from_r = &right->branch_info->from; + struct addr_map_symbol *from_l, *from_r; if (!left->branch_info || !right->branch_info) return cmp_null(left->branch_info, right->branch_info); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 93147cc40162..70612ec583f3 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -193,7 +193,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx) fputc('\n', os->fh); if (os->prefix) - fprintf(os->fh, "%s%s", os->prefix, config->csv_sep); + fprintf(os->fh, "%s", os->prefix); aggr_printout(config, os->evsel, os->id, os->nr); for (i = 0; i < os->nfields; i++) fputs(config->csv_sep, os->fh); @@ -263,7 +263,7 @@ static void print_metric_only(struct perf_stat_config *config, if (color) mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; - color_snprintf(str, sizeof(str), color ?: "", fmt, val); + color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val); fprintf(out, "%*s ", mlen, str); } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 2ec0a32da579..73f890664be5 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -230,6 +230,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, return NULL; } +static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr) +{ + size_t i, phdrnum; + u64 sz; + + if (elf_getphdrnum(elf, &phdrnum)) + return -1; + + for (i = 0; i < phdrnum; i++) { + if (gelf_getphdr(elf, i, phdr) == NULL) + return -1; + + if (phdr->p_type != PT_LOAD) + continue; + + sz = max(phdr->p_memsz, phdr->p_filesz); + if (!sz) + continue; + + if (vaddr >= phdr->p_vaddr && (vaddr < phdr->p_vaddr + sz)) + return 0; + } + + /* Not found any valid program header */ + return -1; +} + static bool want_demangle(bool is_kernel_sym) { return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; @@ -519,7 +546,7 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) size_t sz = min(size, descsz); memcpy(bf, ptr, sz); memset(bf + sz, 0, size - sz); - err = descsz; + err = sz; break; } } @@ -1091,6 +1118,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, sym.st_value); used_opd = true; } + /* * When loading symbols in a data mapping, ABS symbols (which * has a value of SHN_ABS in its st_shndx) failed at @@ -1127,11 +1155,33 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, goto out_elf_end; } else if ((used_opd && runtime_ss->adjust_symbols) || (!used_opd && syms_ss->adjust_symbols)) { - pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " - "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__, - (u64)sym.st_value, (u64)shdr.sh_addr, - (u64)shdr.sh_offset); - sym.st_value -= shdr.sh_addr - shdr.sh_offset; + GElf_Phdr phdr; + + if (elf_read_program_header(runtime_ss->elf, + (u64)sym.st_value, &phdr)) { + pr_debug4("%s: failed to find program header for " + "symbol: %s st_value: %#" PRIx64 "\n", + __func__, elf_name, (u64)sym.st_value); + pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " + "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", + __func__, (u64)sym.st_value, (u64)shdr.sh_addr, + (u64)shdr.sh_offset); + /* + * Fail to find program header, let's rollback + * to use shdr.sh_addr and shdr.sh_offset to + * calibrate symbol's file address, though this + * is not necessary for normal C ELF file, we + * still need to handle java JIT symbols in this + * case. + */ + sym.st_value -= shdr.sh_addr - shdr.sh_offset; + } else { + pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " + "p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n", + __func__, (u64)sym.st_value, (u64)phdr.p_vaddr, + (u64)phdr.p_offset); + sym.st_value -= phdr.p_vaddr - phdr.p_offset; + } } demangled = demangle_sym(dso, kmodule, elf_name); @@ -1862,8 +1912,8 @@ static int kcore_copy__compare_file(const char *from_dir, const char *to_dir, * unusual. One significant peculiarity is that the mapping (start -> pgoff) * is not the same for the kernel map and the modules map. That happens because * the data is copied adjacently whereas the original kcore has gaps. Finally, - * kallsyms and modules files are compared with their copies to check that - * modules have not been loaded or unloaded while the copies were taking place. + * kallsyms file is compared with its copy to check that modules have not been + * loaded or unloaded while the copies were taking place. * * Return: %0 on success, %-1 on failure. */ @@ -1926,9 +1976,6 @@ int kcore_copy(const char *from_dir, const char *to_dir) goto out_extract_close; } - if (kcore_copy__compare_file(from_dir, to_dir, "modules")) - goto out_extract_close; - if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms")) goto out_extract_close; diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index c9bfe4696943..cee7fc3b5bb0 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -279,13 +279,13 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str) threads->nr = ntasks; } out: + strlist__delete(slist); if (threads) refcount_set(&threads->refcnt, 1); return threads; out_free_threads: zfree(&threads); - strlist__delete(slist); goto out; } diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index f117d4f4821e..7bea36a61645 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -18,7 +18,7 @@ struct perf_session; struct perf_top { struct perf_tool tool; - struct evlist *evlist; + struct evlist *evlist, *sb_evlist; struct record_opts record_opts; struct annotation_options annotation_opts; struct evswitch evswitch; |