diff options
Diffstat (limited to 'tools/perf')
69 files changed, 605 insertions, 366 deletions
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 2da07e51e119..822414235170 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -76,7 +76,7 @@ REPORT OPTIONS -c:: --coalesce:: - Specify sorintg fields for single cacheline display. + Specify sorting fields for single cacheline display. Following fields are available: tid,pid,iaddr,dso (see COALESCE) @@ -106,7 +106,7 @@ REPORT OPTIONS -d:: --display:: - Siwtch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default. + Switch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default. C2C RECORD ---------- diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index e6c9902c6d82..165c2b1d4317 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -240,9 +240,13 @@ Add a probe on schedule() function 12th line with recording cpu local variable: or ./perf probe --add='schedule:12 cpu' - this will add one or more probes which has the name start with "schedule". +Add one or more probes which has the name start with "schedule". - Add probes on lines in schedule() function which calls update_rq_clock(). + ./perf probe schedule* + or + ./perf probe --add='schedule*' + +Add probes on lines in schedule() function which calls update_rq_clock(). ./perf probe 'schedule;update_rq_clock*' or diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index ea3789d05e5e..b0e9e921d534 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -225,7 +225,7 @@ OPTIONS the libunwind or libdw library) should be used instead. Using the "lbr" method doesn't require any compiler options. It will produce call graphs from the hardware LBR registers. The - main limition is that it is only available on new Intel + main limitation is that it is only available on new Intel platforms, such as Haswell. It can only get user call chain. It doesn't work with branch stack sampling at the same time. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 37a175914157..9fa84617181e 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -182,7 +182,7 @@ OPTIONS --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this function and searched through the callchain, thus it requires callchain - information recorded. The pattern is in the exteneded regex format and + information recorded. The pattern is in the extended regex format and defaults to "\^sys_|^do_page_fault", see '--sort parent'. -x:: @@ -207,8 +207,8 @@ OPTIONS -g:: --call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>:: Display call chains using type, min percent threshold, print limit, - call order, sort key, optional branch and value. Note that ordering of - parameters is not fixed so any parement can be given in an arbitraty order. + call order, sort key, optional branch and value. Note that ordering + is not fixed so any parameter can be given in an arbitrary order. One exception is the print_limit which should be preceded by threshold. print_type can be either: diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index dfbb506d2c34..142606c0ec9c 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -39,7 +39,7 @@ EVENT HANDLERS When perf script is invoked using a trace script, a user-defined 'handler function' is called for each event in the trace. If there's no handler function defined for a given event type, the event is -ignored (or passed to a 'trace_handled' function, see below) and the +ignored (or passed to a 'trace_unhandled' function, see below) and the next event is processed. Most of the event's field values are passed as arguments to the diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 54acba221558..51ec2d20068a 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -149,10 +149,8 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, print "id=%d, args=%s\n" % \ (id, args), -def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): - print_header(event_name, common_cpu, common_secs, common_nsecs, - common_pid, common_comm) +def trace_unhandled(event_name, context, event_fields_dict): + print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]) def print_header(event_name, cpu, secs, nsecs, pid, comm): print "%-20s %5u %05u.%09u %8u %-20s " % \ @@ -321,7 +319,7 @@ So those are the essential steps in writing and running a script. The process can be generalized to any tracepoint or set of tracepoints you're interested in - basically find the tracepoint(s) you're interested in by looking at the list of available events shown by -'perf list' and/or look in /sys/kernel/debug/tracing events for +'perf list' and/or look in /sys/kernel/debug/tracing/events/ for detailed event and field info, record the corresponding trace data using 'perf record', passing it the list of interesting events, generate a skeleton script using 'perf script -g python' and modify the @@ -334,7 +332,7 @@ right place, you can have your script listed alongside the other scripts listed by the 'perf script -l' command e.g.: ---- -root@tropicana:~# perf script -l +# perf script -l List of available trace scripts: wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file @@ -383,8 +381,6 @@ source tree: ---- # ls -al kernel-source/tools/perf/scripts/python - -root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python total 32 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 . drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 .. @@ -399,7 +395,7 @@ otherwise your script won't show up at run-time), 'perf script -l' should show a new entry for your script: ---- -root@tropicana:~# perf script -l +# perf script -l List of available trace scripts: wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file @@ -437,7 +433,7 @@ EVENT HANDLERS When perf script is invoked using a trace script, a user-defined 'handler function' is called for each event in the trace. If there's no handler function defined for a given event type, the event is -ignored (or passed to a 'trace_handled' function, see below) and the +ignored (or passed to a 'trace_unhandled' function, see below) and the next event is processed. Most of the event's field values are passed as arguments to the @@ -532,7 +528,7 @@ can implement a set of optional functions: gives scripts a chance to do setup tasks: ---- -def trace_begin: +def trace_begin(): pass ---- @@ -541,7 +537,7 @@ def trace_begin: as display results: ---- -def trace_end: +def trace_end(): pass ---- @@ -550,8 +546,7 @@ def trace_end: of common arguments are passed into it: ---- -def trace_unhandled(event_name, context, common_cpu, common_secs, - common_nsecs, common_pid, common_comm): +def trace_unhandled(event_name, context, event_fields_dict): pass ---- diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index cb0eda3925e6..3517e204a2b3 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -311,6 +311,10 @@ include::itrace.txt[] Set the maximum number of program blocks to print with brstackasm for each sample. +--inline:: + If a callgraph address belongs to an inlined function, the inline stack + will be printed. Each entry has function name and file/line. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index fa2a9132f0a9..de8b39dda7b8 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -270,7 +270,7 @@ When the event stream contains multiple events each event is identified by an ID. This can be either through the PERF_SAMPLE_ID or the PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is at a fixed offset from the event header, which allows reliable -parsing of the header. Relying on ID may be ambigious. +parsing of the header. Relying on ID may be ambiguous. IDENTIFIER is only supported by newer Linux kernels. Perf record specific events: @@ -288,7 +288,7 @@ struct attr_event { uint64_t id[]; }; - PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ #define MAX_EVENT_NAME 64 diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index 170b0289a7bc..db0ca3063eae 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -23,7 +23,7 @@ For memory address profiling, try: perf mem record / perf mem report For tracepoint events, try: perf report -s trace_fields To record callchains for each sample: perf record -g To record every process run by a user: perf record -u <user> -Skip collecing build-id when recording: perf record -B +Skip collecting build-id when recording: perf record -B To change sampling frequency to 100 Hz: perf record -F 100 See assembly instructions with percentage: perf annotate <symbol> If you prefer Intel style assembly, try: perf annotate -M intel diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 8354d04b392f..1f4fbc9a3292 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -19,18 +19,18 @@ CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) include $(srctree)/tools/scripts/Makefile.arch -$(call detected_var,ARCH) +$(call detected_var,SRCARCH) NO_PERF_REGS := 1 # Additional ARCH settings for ppc -ifeq ($(ARCH),powerpc) +ifeq ($(SRCARCH),powerpc) NO_PERF_REGS := 0 LIBUNWIND_LIBS := -lunwind -lunwind-ppc64 endif # Additional ARCH settings for x86 -ifeq ($(ARCH),x86) +ifeq ($(SRCARCH),x86) $(call detected,CONFIG_X86) ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated @@ -43,12 +43,12 @@ ifeq ($(ARCH),x86) NO_PERF_REGS := 0 endif -ifeq ($(ARCH),arm) +ifeq ($(SRCARCH),arm) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-arm endif -ifeq ($(ARCH),arm64) +ifeq ($(SRCARCH),arm64) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif @@ -61,7 +61,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(ARCH),$(filter $(ARCH),x86 arm)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -115,9 +115,9 @@ endif FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf -FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi +FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi # include ARCH specific config --include $(src-perf)/arch/$(ARCH)/Makefile +-include $(src-perf)/arch/$(SRCARCH)/Makefile ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET CFLAGS += -DHAVE_ARCH_REGS_QUERY_REGISTER_OFFSET @@ -228,12 +228,12 @@ ifeq ($(DEBUG),0) endif INC_FLAGS += -I$(src-perf)/util/include -INC_FLAGS += -I$(src-perf)/arch/$(ARCH)/include +INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include INC_FLAGS += -I$(srctree)/tools/include/uapi INC_FLAGS += -I$(srctree)/tools/include/ -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/ -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/ +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/ +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/ # $(obj-perf) for generated common-cmds.h # $(obj-perf)/util for generated bison/flex headers @@ -355,7 +355,7 @@ ifndef NO_LIBELF ifndef NO_DWARF ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) - msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); + msg := $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled); NO_DWARF := 1 else CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) @@ -380,7 +380,7 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_BPF_PROLOGUE $(call detected,CONFIG_BPF_PROLOGUE) else - msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset()); + msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset()); endif else msg := $(warning DWARF support is off, BPF prologue is disabled); @@ -406,7 +406,7 @@ ifdef PERF_HAVE_JITDUMP endif endif -ifeq ($(ARCH),powerpc) +ifeq ($(SRCARCH),powerpc) ifndef NO_DWARF CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX endif @@ -487,7 +487,7 @@ else endif ifndef NO_LOCAL_LIBUNWIND - ifeq ($(ARCH),$(filter $(ARCH),arm arm64)) + ifeq ($(SRCARCH),$(filter $(SRCARCH),arm arm64)) $(call feature_check,libunwind-debug-frame) ifneq ($(feature-libunwind-debug-frame), 1) msg := $(warning No debug_frame support found in libunwind); @@ -740,7 +740,7 @@ ifeq (${IS_64_BIT}, 1) NO_PERF_READ_VDSO32 := 1 endif endif - ifneq ($(ARCH), x86) + ifneq ($(SRCARCH), x86) NO_PERF_READ_VDSOX32 := 1 endif ifndef NO_PERF_READ_VDSOX32 @@ -769,7 +769,7 @@ ifdef LIBBABELTRACE endif ifndef NO_AUXTRACE - ifeq ($(ARCH),x86) + ifeq ($(SRCARCH),x86) ifeq ($(feature-get_cpuid), 0) msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc); NO_AUXTRACE := 1 @@ -872,7 +872,7 @@ sysconfdir = $(prefix)/etc ETC_PERFCONFIG = etc/perfconfig endif ifndef lib -ifeq ($(ARCH)$(IS_64_BIT), x861) +ifeq ($(SRCARCH)$(IS_64_BIT), x861) lib = lib64 else lib = lib diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 79fe31f20a17..5008f51a08a2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -226,7 +226,7 @@ endif ifeq ($(config),0) include $(srctree)/tools/scripts/Makefile.arch --include arch/$(ARCH)/Makefile +-include arch/$(SRCARCH)/Makefile endif # The FEATURE_DUMP_EXPORT holds location of the actual diff --git a/tools/perf/arch/Build b/tools/perf/arch/Build index 109eb75cf7de..d9b6af837c7d 100644 --- a/tools/perf/arch/Build +++ b/tools/perf/arch/Build @@ -1,2 +1,2 @@ libperf-y += common.o -libperf-y += $(ARCH)/ +libperf-y += $(SRCARCH)/ diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 44eafd6f2d50..8f1908756cb6 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -50,7 +50,7 @@ static int arm64__annotate_init(struct arch *arch) arch->initialized = true; arch->priv = arm; arch->associate_instruction_ops = arm64__associate_instruction_ops; - arch->objdump.comment_char = ';'; + arch->objdump.comment_char = '/'; arch->objdump.skip_functions_char = '+'; return 0; diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 837067f48a4c..6b40e9f01740 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -26,6 +26,7 @@ const char *const arm64_triplets[] = { const char *const powerpc_triplets[] = { "powerpc-unknown-linux-gnu-", + "powerpc-linux-gnu-", "powerpc64-unknown-linux-gnu-", "powerpc64-linux-gnu-", "powerpc64le-linux-gnu-", diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 39dbe512b9fc..bf9a2594572c 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -52,6 +52,18 @@ int arch__compare_symbol_names(const char *namea, const char *nameb) return strcmp(namea, nameb); } + +int arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n) +{ + /* Skip over initial dot */ + if (*namea == '.') + namea++; + if (*nameb == '.') + nameb++; + + return strncmp(namea, nameb, n); +} #endif #if defined(_CALL_ELF) && _CALL_ELF == 2 diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 64b44e81c771..9eba7f1add1f 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -49,19 +49,22 @@ static bool same_kallsyms_reloc(const char *from_dir, char *to_dir) char to[PATH_MAX]; const char *name; u64 addr1 = 0, addr2 = 0; - int i; + int i, err = -1; scnprintf(from, sizeof(from), "%s/kallsyms", from_dir); scnprintf(to, sizeof(to), "%s/kallsyms", to_dir); for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr1 = kallsyms__get_function_start(from, name); - if (addr1) + err = kallsyms__get_function_start(from, name, &addr1); + if (!err) break; } - if (name) - addr2 = kallsyms__get_function_start(to, name); + if (err) + return false; + + if (kallsyms__get_function_start(to, name, &addr2)) + return false; return addr1 == addr2; } diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index e33b4acece90..620a467ee304 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -27,6 +27,7 @@ #include "tool.h" #include "data.h" #include "sort.h" +#include "event.h" #include "evlist.h" #include "evsel.h" #include <asm/bug.h> diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 55f04f85b049..80668fa7556e 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -159,6 +159,7 @@ int cmd_config(int argc, const char **argv) int i, ret = 0; struct perf_config_set *set; char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); + const char *config_filename; argc = parse_options(argc, argv, config_options, config_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -175,6 +176,11 @@ int cmd_config(int argc, const char **argv) else if (use_user_config) config_exclusive_filename = user_config; + if (!config_exclusive_filename) + config_filename = user_config; + else + config_filename = config_exclusive_filename; + /* * At only 'config' sub-command, individually use the config set * because of reinitializing with options config file location. @@ -192,13 +198,9 @@ int cmd_config(int argc, const char **argv) parse_options_usage(config_usage, config_options, "l", 1); } else { ret = show_config(set); - if (ret < 0) { - const char * config_filename = config_exclusive_filename; - if (!config_exclusive_filename) - config_filename = user_config; + if (ret < 0) pr_err("Nothing configured, " "please check your %s \n", config_filename); - } } break; default: @@ -221,13 +223,8 @@ int cmd_config(int argc, const char **argv) if (value == NULL) ret = show_spec_config(set, var); - else { - const char *config_filename = config_exclusive_filename; - - if (!config_exclusive_filename) - config_filename = user_config; + else ret = set_config(set, config_filename, var, value); - } free(arg); } } else diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index d05aec491cff..4761b0d7fcb5 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2494,6 +2494,8 @@ int cmd_script(int argc, const char **argv) "Enable kernel symbol demangling"), OPT_STRING(0, "time", &script.time_str, "str", "Time span of interest (start,stop)"), + OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, + "Show inline function"), OPT_END() }; const char * const script_subcommands[] = { "record", "report", NULL }; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a935b5023732..ad9324d1daf9 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1578,6 +1578,7 @@ static void print_header(int argc, const char **argv) static void print_footer(void) { FILE *output = stat_config.output; + int n; if (!null_run) fprintf(output, "\n"); @@ -1590,7 +1591,9 @@ static void print_footer(void) } fprintf(output, "\n\n"); - if (print_free_counters_hint) + if (print_free_counters_hint && + sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 && + n > 0) fprintf(output, "Some events weren't counted. Try disabling the NMI watchdog:\n" " echo 0 > /proc/sys/kernel/nmi_watchdog\n" diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7ab42b8311a1..10b6362ca0bf 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -27,13 +27,13 @@ #include "util/drv_configs.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/event.h" #include "util/machine.h" #include "util/session.h" #include "util/symbol.h" #include "util/thread.h" #include "util/thread_map.h" #include "util/top.h" -#include "util/util.h" #include <linux/rbtree.h> #include <subcmd/parse-options.h> #include "util/parse-events.h" diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index eaa66fb57347..4b2a5d298197 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -21,6 +21,7 @@ #include "builtin.h" #include "util/color.h" #include "util/debug.h" +#include "util/event.h" #include "util/evlist.h" #include <subcmd/exec-cmd.h> #include "util/machine.h" @@ -680,6 +681,10 @@ static struct syscall_fmt { { .name = "mlockall", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "mmap", .hexret = true, +/* The standard mmap maps to old_mmap on s390x */ +#if defined(__s390x__) + .alias = "old_mmap", +#endif .arg_scnprintf = { [0] = SCA_HEX, /* addr */ [2] = SCA_MMAP_PROT, /* prot */ [3] = SCA_MMAP_FLAGS, /* flags */ }, }, diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 4cc6960f6226..628a5e412cb1 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -17,6 +17,7 @@ #include <subcmd/parse-options.h> #include "util/bpf-loader.h" #include "util/debug.h" +#include "util/event.h" #include <api/fs/fs.h> #include <api/fs/tracing_path.h> #include <errno.h> diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 9213a1273697..999a4e878162 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -2,7 +2,7 @@ hostprogs := jevents jevents-y += json.o jsmn.o jevents.o pmu-events-y += pmu-events.o -JDIR = pmu-events/arch/$(ARCH) +JDIR = pmu-events/arch/$(SRCARCH) JSON = $(shell [ -d $(JDIR) ] && \ find $(JDIR) -name '*.json' -o -name 'mapfile.csv') # @@ -10,4 +10,4 @@ JSON = $(shell [ -d $(JDIR) ] && \ # directory and create tables in pmu-events.c. # $(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JEVENTS) - $(Q)$(call echo-cmd,gen)$(JEVENTS) $(ARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V) + $(Q)$(call echo-cmd,gen)$(JEVENTS) $(SRCARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index af58ebc243ef..84222bdb8689 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -75,7 +75,7 @@ $(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/B $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ -ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc)) +ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index e7664fe3bd33..8ba2c4618fe9 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -288,3 +288,17 @@ int test__bp_signal(int subtest __maybe_unused) return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ? TEST_OK : TEST_FAIL; } + +bool test__bp_signal_is_supported(void) +{ +/* + * The powerpc so far does not have support to even create + * instruction breakpoint using the perf event interface. + * Once it's there we can release this. + */ +#ifdef __powerpc__ + return false; +#else + return true; +#endif +} diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 9e08d297f1a9..3ccfd58a8c3c 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -97,10 +97,12 @@ static struct test generic_tests[] = { { .desc = "Breakpoint overflow signal handler", .func = test__bp_signal, + .is_supported = test__bp_signal_is_supported, }, { .desc = "Breakpoint overflow sampling", .func = test__bp_signal_overflow, + .is_supported = test__bp_signal_is_supported, }, { .desc = "Number of exit events of a simple workload", @@ -401,6 +403,11 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) if (!perf_test__matches(t, curr, argc, argv)) continue; + if (t->is_supported && !t->is_supported()) { + pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc); + continue; + } + pr_info("%2d: %-*s:", i, width, t->desc); if (intlist__find(skiplist, i)) { diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 1f14e7612cbb..94b7c7b02bde 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -229,6 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, unsigned char buf2[BUFSZ]; size_t ret_len; u64 objdump_addr; + const char *objdump_name; + char decomp_name[KMOD_DECOMP_LEN]; int ret; pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); @@ -289,9 +291,25 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, state->done[state->done_cnt++] = al.map->start; } + objdump_name = al.map->dso->long_name; + if (dso__needs_decompress(al.map->dso)) { + if (dso__decompress_kmodule_path(al.map->dso, objdump_name, + decomp_name, + sizeof(decomp_name)) < 0) { + pr_debug("decompression failed\n"); + return -1; + } + + objdump_name = decomp_name; + } + /* Read the object code using objdump */ objdump_addr = map__rip_2objdump(al.map, al.addr); - ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len); + ret = read_via_objdump(objdump_name, objdump_addr, buf2, len); + + if (dso__needs_decompress(al.map->dso)) + unlink(objdump_name); + if (ret > 0) { /* * The kernel maps are inaccurate - assume objdump is right in diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 70918b986568..d549a9f2c41b 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -1,5 +1,6 @@ #include "perf.h" #include "util/debug.h" +#include "util/event.h" #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index f171b2da4899..df9c91f49af1 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -3,6 +3,7 @@ #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" +#include "util/event.h" #include "util/evlist.h" #include "util/machine.h" #include "util/thread.h" diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index cdf0dde5fe97..06e5080182d3 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -1,5 +1,6 @@ #include "perf.h" #include "util/debug.h" +#include "util/event.h" #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 76f41f249944..6cd9e5107f77 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -61,6 +61,7 @@ int test__kmod_path__parse(int subtest __maybe_unused) M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false); +#ifdef HAVE_ZLIB_SUPPORT /* path alloc_name alloc_ext kmod comp name ext */ T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz"); T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz"); @@ -96,6 +97,7 @@ int test__kmod_path__parse(int subtest __maybe_unused) M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true); M("x.ko.gz", PERF_RECORD_MISC_USER, false); +#endif /* path alloc_name alloc_ext kmod comp name ext */ T("[test_module]", true , true , true, false, "[test_module]", NULL); diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index f73b3c5e125d..06eda675ae2c 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -1,7 +1,6 @@ #include <errno.h> #include <stdio.h> #include <sys/epoll.h> -#include <util/util.h> #include <util/evlist.h> #include <linux/filter.h> #include "tests.h" diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 32873ec91a4e..cf00ebad2ef5 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -83,7 +83,7 @@ int test__task_exit(int subtest __maybe_unused) evsel = perf_evlist__first(evlist); evsel->attr.task = 1; - evsel->attr.sample_freq = 0; + evsel->attr.sample_freq = 1; evsel->attr.inherit = 0; evsel->attr.watermark = 0; evsel->attr.wakeup_events = 1; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 631859629403..577363809c9b 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -34,6 +34,7 @@ struct test { int (*get_nr)(void); const char *(*get_desc)(int subtest); } subtest; + bool (*is_supported)(void); }; /* Tests */ @@ -99,6 +100,8 @@ const char *test__clang_subtest_get_desc(int subtest); int test__clang_subtest_get_nr(void); int test__unit_number__scnprint(int subtest); +bool test__bp_signal_is_supported(void); + #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 59addd52d9cd..ddb2c6fbdf91 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -210,6 +210,8 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, return 0; ret = b->callchain->max_depth - a->callchain->max_depth; + if (callchain_param.order == ORDER_CALLER) + ret = -ret; } return ret; } diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 5ea0b40c4fc2..caf1ce6f5152 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -10,7 +10,10 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; void *perf_gtk_handle; int use_browser = -1; +#define PERF_GTK_DSO "libperf-gtk.so" + #ifdef HAVE_GTK2_SUPPORT + static int setup_gtk_browser(void) { int (*perf_ui_init)(void); diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 069583bdc670..79dea95a7f68 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -13,6 +13,7 @@ libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o +libperf-y += memswap.o libperf-y += parse-events.o libperf-y += perf_regs.o libperf-y += path.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 683f8340460c..ddbd56df9187 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -239,10 +239,20 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op const char *s = strchr(ops->raw, '+'); const char *c = strchr(ops->raw, ','); - if (c++ != NULL) + /* + * skip over possible up to 2 operands to get to address, e.g.: + * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0> + */ + if (c++ != NULL) { ops->target.addr = strtoull(c, NULL, 16); - else + if (!ops->target.addr) { + c = strchr(c, ','); + if (c++ != NULL) + ops->target.addr = strtoull(c, NULL, 16); + } + } else { ops->target.addr = strtoull(ops->raw, NULL, 16); + } if (s++ != NULL) { ops->target.offset = strtoull(s, NULL, 16); @@ -257,10 +267,27 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op static int jump__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { + const char *c = strchr(ops->raw, ','); + if (!ops->target.addr || ops->target.offset < 0) return ins__raw_scnprintf(ins, bf, size, ops); - return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset); + if (c != NULL) { + const char *c2 = strchr(c + 1, ','); + + /* check for 3-op insn */ + if (c2 != NULL) + c = c2; + c++; + + /* mirror arch objdump's space-after-comma style */ + if (*c == ' ') + c++; + } + + return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64, + ins->name, c ? c - ops->raw : 0, ops->raw, + ops->target.offset); } static struct ins_ops jump_ops = { @@ -1294,6 +1321,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil char linkname[PATH_MAX]; char *build_id_filename; char *build_id_path = NULL; + char *pos; if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) @@ -1313,7 +1341,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil if (!build_id_path) return -1; - dirname(build_id_path); + /* + * old style build-id cache has name of XX/XXXXXXX.. while + * new style has XX/XXXXXXX../{elf,kallsyms,vdso}. + * extract the build-id part of dirname in the new style only. + */ + pos = strrchr(build_id_path, '/'); + if (pos && strlen(pos) < SBUILD_ID_SIZE - 2) + dirname(build_id_path); if (dso__is_kcore(dso) || readlink(build_id_path, linkname, sizeof(linkname)) < 0 || @@ -1396,31 +1431,10 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na sizeof(symfs_filename)); } } else if (dso__needs_decompress(dso)) { - char tmp[PATH_MAX]; - struct kmod_path m; - int fd; - bool ret; - - if (kmod_path__parse_ext(&m, symfs_filename)) - goto out; - - snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX"); - - fd = mkstemp(tmp); - if (fd < 0) { - free(m.ext); - goto out; - } - - ret = decompress_to_file(m.ext, symfs_filename, fd); - - if (ret) - pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename); - - free(m.ext); - close(fd); + char tmp[KMOD_DECOMP_LEN]; - if (!ret) + if (dso__decompress_kmodule_path(dso, symfs_filename, + tmp, sizeof(tmp)) < 0) goto out; strcpy(symfs_filename, tmp); @@ -1429,7 +1443,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na snprintf(command, sizeof(command), "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand", + " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand", objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 168cc49654e7..e0148b081bdf 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -278,51 +278,6 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) return bf; } -bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size) -{ - char *id_name = NULL, *ch; - struct stat sb; - char sbuild_id[SBUILD_ID_SIZE]; - - if (!dso->has_build_id) - goto err; - - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); - id_name = build_id_cache__linkname(sbuild_id, NULL, 0); - if (!id_name) - goto err; - if (access(id_name, F_OK)) - goto err; - if (lstat(id_name, &sb) == -1) - goto err; - if ((size_t)sb.st_size > size - 1) - goto err; - if (readlink(id_name, bf, size - 1) < 0) - goto err; - - bf[sb.st_size] = '\0'; - - /* - * link should be: - * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92 - */ - ch = strrchr(bf, '/'); - if (!ch) - goto err; - if (ch - 3 < bf) - goto err; - - free(id_name); - return strncmp(".ko", ch - 3, 3) == 0; -err: - pr_err("Invalid build id: %s\n", id_name ? : - dso->long_name ? : - dso->short_name ? : - "[unknown]"); - free(id_name); - return false; -} - #define dsos__for_each_with_build_id(pos, head) \ list_for_each_entry(pos, head, node) \ if (!pos->has_build_id) \ diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index a96081121179..96690a55c62c 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -17,7 +17,6 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, size_t size); char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size); -bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, @@ -44,6 +43,10 @@ bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id); + +extern char buildid_dir[]; + +void set_buildid_dir(const char *dir); void disable_buildid_cache(void); #endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 81fc29ac798f..b4204b43ed58 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -621,14 +621,19 @@ enum match_result { static enum match_result match_chain_srcline(struct callchain_cursor_node *node, struct callchain_list *cnode) { - char *left = get_srcline(cnode->ms.map->dso, + char *left = NULL; + char *right = NULL; + enum match_result ret = MATCH_EQ; + int cmp; + + if (cnode->ms.map) + left = get_srcline(cnode->ms.map->dso, map__rip_2objdump(cnode->ms.map, cnode->ip), cnode->ms.sym, true, false); - char *right = get_srcline(node->map->dso, + if (node->map) + right = get_srcline(node->map->dso, map__rip_2objdump(node->map, node->ip), node->sym, true, false); - enum match_result ret = MATCH_EQ; - int cmp; if (left && right) cmp = strcmp(left, right); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index a96a99d2369f..4e7ab611377a 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -248,6 +248,64 @@ bool dso__needs_decompress(struct dso *dso) dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; } +static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf) +{ + int fd = -1; + struct kmod_path m; + + if (!dso__needs_decompress(dso)) + return -1; + + if (kmod_path__parse_ext(&m, dso->long_name)) + return -1; + + if (!m.comp) + goto out; + + fd = mkstemp(tmpbuf); + if (fd < 0) { + dso->load_errno = errno; + goto out; + } + + if (!decompress_to_file(m.ext, name, fd)) { + dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; + close(fd); + fd = -1; + } + +out: + free(m.ext); + return fd; +} + +int dso__decompress_kmodule_fd(struct dso *dso, const char *name) +{ + char tmpbuf[] = KMOD_DECOMP_NAME; + int fd; + + fd = decompress_kmodule(dso, name, tmpbuf); + unlink(tmpbuf); + return fd; +} + +int dso__decompress_kmodule_path(struct dso *dso, const char *name, + char *pathname, size_t len) +{ + char tmpbuf[] = KMOD_DECOMP_NAME; + int fd; + + fd = decompress_kmodule(dso, name, tmpbuf); + if (fd < 0) { + unlink(tmpbuf); + return -1; + } + + strncpy(pathname, tmpbuf, len); + close(fd); + return 0; +} + /* * Parses kernel module specified in @path and updates * @m argument like: @@ -335,6 +393,21 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, return 0; } +void dso__set_module_info(struct dso *dso, struct kmod_path *m, + struct machine *machine) +{ + if (machine__is_host(machine)) + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; + else + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + + /* _KMODULE_COMP should be next to _KMODULE */ + if (m->kmod && m->comp) + dso->symtab_type++; + + dso__set_short_name(dso, strdup(m->name), true); +} + /* * Global list of open DSOs and the counter. */ @@ -381,7 +454,7 @@ static int do_open(char *name) static int __open_dso(struct dso *dso, struct machine *machine) { - int fd; + int fd = -EINVAL; char *root_dir = (char *)""; char *name = malloc(PATH_MAX); @@ -392,15 +465,30 @@ static int __open_dso(struct dso *dso, struct machine *machine) root_dir = machine->root_dir; if (dso__read_binary_type_filename(dso, dso->binary_type, - root_dir, name, PATH_MAX)) { - free(name); - return -EINVAL; - } + root_dir, name, PATH_MAX)) + goto out; if (!is_regular_file(name)) - return -EINVAL; + goto out; + + if (dso__needs_decompress(dso)) { + char newpath[KMOD_DECOMP_LEN]; + size_t len = sizeof(newpath); + + if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) { + fd = -dso->load_errno; + goto out; + } + + strcpy(name, newpath); + } fd = do_open(name); + + if (dso__needs_decompress(dso)) + unlink(name); + +out: free(name); return fd; } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 12350b171727..bd061ba7b47c 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -244,6 +244,12 @@ bool is_supported_compression(const char *ext); bool is_kernel_module(const char *pathname, int cpumode); bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); +int dso__decompress_kmodule_fd(struct dso *dso, const char *name); +int dso__decompress_kmodule_path(struct dso *dso, const char *name, + char *pathname, size_t len); + +#define KMOD_DECOMP_NAME "/tmp/perf-kmod-XXXXXX" +#define KMOD_DECOMP_LEN sizeof(KMOD_DECOMP_NAME) struct kmod_path { char *name; @@ -259,6 +265,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) +void dso__set_module_info(struct dso *dso, struct kmod_path *m, + struct machine *machine); + /* * The dso__data_* external interface provides following functions: * dso__data_get_fd diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 142835c0ca0a..dc5c3bb69d73 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -8,6 +8,7 @@ #include <unistd.h> #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <api/fs/fs.h> +#include <linux/perf_event.h> #include "event.h" #include "debug.h" #include "hist.h" @@ -767,15 +768,16 @@ static int find_symbol_cb(void *arg, const char *name, char type, return 1; } -u64 kallsyms__get_function_start(const char *kallsyms_filename, - const char *symbol_name) +int kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr) { struct process_symbol_args args = { .name = symbol_name, }; if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0) - return 0; + return -1; - return args.start; + *addr = args.start; + return 0; } int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index db2de6413518..7c3fa1c8cbcd 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -229,7 +229,7 @@ struct build_id_event { enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_USER_TYPE_START = 64, PERF_RECORD_HEADER_ATTR = 64, - PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ PERF_RECORD_HEADER_TRACING_DATA = 66, PERF_RECORD_HEADER_BUILD_ID = 67, PERF_RECORD_FINISHED_ROUND = 68, @@ -675,10 +675,18 @@ size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); -u64 kallsyms__get_function_start(const char *kallsyms_filename, - const char *symbol_name); +int kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr); void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max); void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, u16 type, int max); + +void event_attr_init(struct perf_event_attr *attr); + +int perf_event_paranoid(void); + +extern int sysctl_perf_event_max_stack; +extern int sysctl_perf_event_max_contexts_per_stack; + #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 0e879097adfb..cda44b0e821c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -21,6 +21,7 @@ #include "asm/bug.h" #include "callchain.h" #include "cgroup.h" +#include "event.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -272,8 +273,20 @@ struct perf_evsel *perf_evsel__new_cycles(void) struct perf_evsel *evsel; event_attr_init(&attr); + /* + * Unnamed union member, not supported as struct member named + * initializer in older compilers such as gcc 4.4.7 + * + * Just for probing the precise_ip: + */ + attr.sample_period = 1; perf_event_attr__set_max_precise_ip(&attr); + /* + * Now let the usual logic to set up the perf_event_attr defaults + * to kick in when we return and before perf_evsel__open() is called. + */ + attr.sample_period = 0; evsel = perf_evsel__new(&attr); if (evsel == NULL) diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index e415aee6a245..583f3a602506 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -7,6 +7,7 @@ #include "map.h" #include "strlist.h" #include "symbol.h" +#include "srcline.h" static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) { @@ -168,6 +169,38 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (!print_oneline) printed += fprintf(fp, "\n"); + if (symbol_conf.inline_name && node->map) { + struct inline_node *inode; + + addr = map__rip_2objdump(node->map, node->ip), + inode = dso__parse_addr_inlines(node->map->dso, addr); + + if (inode) { + struct inline_list *ilist; + + list_for_each_entry(ilist, &inode->val, list) { + if (print_arrow) + printed += fprintf(fp, " <-"); + + /* IP is same, just skip it */ + if (print_ip) + printed += fprintf(fp, "%c%16s", + s, ""); + if (print_sym) + printed += fprintf(fp, " %s", + ilist->funcname); + if (print_srcline) + printed += fprintf(fp, "\n %s:%d", + ilist->filename, + ilist->line_nr); + if (!print_oneline) + printed += fprintf(fp, "\n"); + } + + inline_node__delete(inode); + } + } + if (symbol_conf.bt_stop_list && node->sym && strlist__has_entry(symbol_conf.bt_stop_list, diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 948b2c5efb65..b5baff3007bb 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -19,6 +19,7 @@ #include "evlist.h" #include "evsel.h" #include "header.h" +#include "memswap.h" #include "../perf.h" #include "trace-event.h" #include "session.h" @@ -840,7 +841,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, /* * default get_cpuid(): nothing gets recorded - * actual implementation must be in arch/$(ARCH)/util/header.c + * actual implementation must be in arch/$(SRCARCH)/util/header.c */ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) { @@ -1468,8 +1469,16 @@ static int __event_process_build_id(struct build_id_event *bev, dso__set_build_id(dso, &bev->build_id); - if (!is_kernel_module(filename, cpumode)) - dso->kernel = dso_type; + if (dso_type != DSO_TYPE_USER) { + struct kmod_path m = { .name = NULL, }; + + if (!kmod_path__parse_name(&m, filename) && m.kmod) + dso__set_module_info(dso, &m, machine); + else + dso->kernel = dso_type; + + free(m.name); + } build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index bdd4a28c6cee..4c7718f87a08 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -23,6 +23,7 @@ #include "../perf.h" #include "session.h" #include "machine.h" +#include "memswap.h" #include "sort.h" #include "tool.h" #include "event.h" diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 7a47f52ccfcc..d7f31cb0a4cb 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -572,16 +572,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, if (dso == NULL) goto out_unlock; - if (machine__is_host(machine)) - dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; - else - dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; - - /* _KMODULE_COMP should be next to _KMODULE */ - if (m->kmod && m->comp) - dso->symtab_type++; - - dso__set_short_name(dso, strdup(m->name), true); + dso__set_module_info(dso, m, machine); dso__set_long_name(dso, strdup(filename), true); } @@ -796,11 +787,11 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; * Returns the name of the start symbol in *symbol_name. Pass in NULL as * symbol_name if it's not that important. */ -static u64 machine__get_running_kernel_start(struct machine *machine, - const char **symbol_name) +static int machine__get_running_kernel_start(struct machine *machine, + const char **symbol_name, u64 *start) { char filename[PATH_MAX]; - int i; + int i, err = -1; const char *name; u64 addr = 0; @@ -810,21 +801,28 @@ static u64 machine__get_running_kernel_start(struct machine *machine, return 0; for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr = kallsyms__get_function_start(filename, name); - if (addr) + err = kallsyms__get_function_start(filename, name, &addr); + if (!err) break; } + if (err) + return -1; + if (symbol_name) *symbol_name = name; - return addr; + *start = addr; + return 0; } int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { int type; - u64 start = machine__get_running_kernel_start(machine, NULL); + u64 start = 0; + + if (machine__get_running_kernel_start(machine, NULL, &start)) + return -1; /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); @@ -1185,8 +1183,8 @@ static int machine__create_modules(struct machine *machine) int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); - const char *name; - u64 addr; + const char *name = NULL; + u64 addr = 0; int ret; if (kernel == NULL) @@ -1211,8 +1209,7 @@ int machine__create_kernel_maps(struct machine *machine) */ map_groups__fixup_end(&machine->kmaps); - addr = machine__get_running_kernel_start(machine, &name); - if (!addr) { + if (machine__get_running_kernel_start(machine, &name, &addr)) { } else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { machine__destroy_kernel_maps(machine); return -1; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index ebfa5d92358a..2179b2deb730 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -325,11 +325,6 @@ int map__load(struct map *map) return 0; } -int __weak arch__compare_symbol_names(const char *namea, const char *nameb) -{ - return strcmp(namea, nameb); -} - struct symbol *map__find_symbol(struct map *map, u64 addr) { if (map__load(map) < 0) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index c8a5a644c0a9..f9e8ac8a52cd 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -130,13 +130,14 @@ struct thread; */ #define __map__for_each_symbol_by_name(map, sym_name, pos) \ for (pos = map__find_symbol_by_name(map, sym_name); \ - pos && arch__compare_symbol_names(pos->name, sym_name) == 0; \ + pos && \ + !symbol__match_symbol_name(pos->name, sym_name, \ + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); \ pos = symbol__next_by_name(pos)) #define map__for_each_symbol_by_name(map, sym_name, pos) \ __map__for_each_symbol_by_name(map, sym_name, (pos)) -int arch__compare_symbol_names(const char *namea, const char *nameb); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct machine *machine, u64 start, u64 len, diff --git a/tools/perf/util/memswap.c b/tools/perf/util/memswap.c new file mode 100644 index 000000000000..55f7faa8d9ec --- /dev/null +++ b/tools/perf/util/memswap.c @@ -0,0 +1,24 @@ +#include <byteswap.h> +#include "memswap.h" +#include <linux/types.h> + +void mem_bswap_32(void *src, int byte_size) +{ + u32 *m = src; + while (byte_size > 0) { + *m = bswap_32(*m); + byte_size -= sizeof(u32); + ++m; + } +} + +void mem_bswap_64(void *src, int byte_size) +{ + u64 *m = src; + + while (byte_size > 0) { + *m = bswap_64(*m); + byte_size -= sizeof(u64); + ++m; + } +} diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h new file mode 100644 index 000000000000..7d1b1c34bb57 --- /dev/null +++ b/tools/perf/util/memswap.h @@ -0,0 +1,7 @@ +#ifndef PERF_MEMSWAP_H_ +#define PERF_MEMSWAP_H_ + +void mem_bswap_64(void *src, int byte_size); +void mem_bswap_32(void *src, int byte_size); + +#endif /* PERF_MEMSWAP_H_ */ diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 2b12bdb3ce33..7b79c413486b 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -28,7 +28,9 @@ #include <linux/bitmap.h> #include <linux/time64.h> -#include "../util.h" +#include <stdbool.h> +/* perl needs the following define, right after including stdbool.h */ +#define HAS_BOOL #include <EXTERN.h> #include <perl.h> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 9d92af7d0718..40de3cb40d21 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1219,7 +1219,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "# be retrieved using Python functions of the form " "common_*(context).\n"); - fprintf(ofp, "# See the perf-trace-python Documentation for the list " + fprintf(ofp, "# See the perf-script-python Documentation for the list " "of available functions.\n\n"); fprintf(ofp, "import os\n"); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3041c6b98191..7dc1096264c5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -11,6 +11,7 @@ #include "evlist.h" #include "evsel.h" +#include "memswap.h" #include "session.h" #include "tool.h" #include "sort.h" diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index df051a52393c..ebc88a74e67b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -56,7 +56,10 @@ static int inline_list__append(char *filename, char *funcname, int line_nr, } } - list_add_tail(&ilist->list, &node->val); + if (callchain_param.order == ORDER_CALLEE) + list_add_tail(&ilist->list, &node->val); + else + list_add(&ilist->list, &node->val); return 0; } @@ -200,12 +203,14 @@ static void addr2line_cleanup(struct a2l_data *a2l) #define MAX_INLINE_NEST 1024 -static void inline_list__reverse(struct inline_node *node) +static int inline_list__append_dso_a2l(struct dso *dso, + struct inline_node *node) { - struct inline_list *ilist, *n; + struct a2l_data *a2l = dso->a2l; + char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL; + char *filename = a2l->filename ? strdup(a2l->filename) : NULL; - list_for_each_entry_safe_reverse(ilist, n, &node->val, list) - list_move_tail(&ilist->list, &node->val); + return inline_list__append(filename, funcname, a2l->line, node, dso); } static int addr2line(const char *dso_name, u64 addr, @@ -230,36 +235,36 @@ static int addr2line(const char *dso_name, u64 addr, bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l); - if (a2l->found && unwind_inlines) { + if (!a2l->found) + return 0; + + if (unwind_inlines) { int cnt = 0; + if (node && inline_list__append_dso_a2l(dso, node)) + return 0; + while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, &a2l->funcname, &a2l->line) && cnt++ < MAX_INLINE_NEST) { if (node != NULL) { - if (inline_list__append(strdup(a2l->filename), - strdup(a2l->funcname), - a2l->line, node, - dso) != 0) + if (inline_list__append_dso_a2l(dso, node)) return 0; + // found at least one inline frame + ret = 1; } } + } - if ((node != NULL) && - (callchain_param.order != ORDER_CALLEE)) { - inline_list__reverse(node); - } + if (file) { + *file = a2l->filename ? strdup(a2l->filename) : NULL; + ret = *file ? 1 : 0; } - if (a2l->found && a2l->filename) { - *file = strdup(a2l->filename); + if (line) *line = a2l->line; - if (*file) - ret = 1; - } - return ret; } @@ -278,8 +283,6 @@ void dso__free_a2l(struct dso *dso) static struct inline_node *addr2inlines(const char *dso_name, u64 addr, struct dso *dso) { - char *file = NULL; - unsigned int line = 0; struct inline_node *node; node = zalloc(sizeof(*node)); @@ -291,7 +294,7 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr, INIT_LIST_HEAD(&node->val); node->addr = addr; - if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node)) + if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node)) goto out_free_inline_node; if (list_empty(&node->val)) diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index e91b5e86f027..aafe908b82b5 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -3,15 +3,6 @@ #include <linux/kernel.h> #include <errno.h> -int prefixcmp(const char *str, const char *prefix) -{ - for (; ; str++, prefix++) - if (!*prefix) - return 0; - else if (*str != *prefix) - return (unsigned char)*prefix - (unsigned char)*str; -} - /* * Used as the default ->buf value, so that people can always assume * buf is non NULL and ->buf is NUL terminated even for a freshly diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index e7ee47f7377a..502505cf236a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -637,43 +637,6 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata) return 0; } -static int decompress_kmodule(struct dso *dso, const char *name, - enum dso_binary_type type) -{ - int fd = -1; - char tmpbuf[] = "/tmp/perf-kmod-XXXXXX"; - struct kmod_path m; - - if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && - type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP && - type != DSO_BINARY_TYPE__BUILD_ID_CACHE) - return -1; - - if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE) - name = dso->long_name; - - if (kmod_path__parse_ext(&m, name) || !m.comp) - return -1; - - fd = mkstemp(tmpbuf); - if (fd < 0) { - dso->load_errno = errno; - goto out; - } - - if (!decompress_to_file(m.ext, name, fd)) { - dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; - close(fd); - fd = -1; - } - - unlink(tmpbuf); - -out: - free(m.ext); - return fd; -} - bool symsrc__possibly_runtime(struct symsrc *ss) { return ss->dynsym || ss->opdsec; @@ -705,9 +668,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, int fd; if (dso__needs_decompress(dso)) { - fd = decompress_kmodule(dso, name, type); + fd = dso__decompress_kmodule_fd(dso, name); if (fd < 0) return -1; + + type = dso->symtab_type; } else { fd = open(name, O_RDONLY); if (fd < 0) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 2cb7665e9973..e7a98dbd2aed 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -90,6 +90,17 @@ static int prefix_underscores_count(const char *str) return tail - str; } +int __weak arch__compare_symbol_names(const char *namea, const char *nameb) +{ + return strcmp(namea, nameb); +} + +int __weak arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n) +{ + return strncmp(namea, nameb, n); +} + int __weak arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { @@ -399,8 +410,26 @@ static void symbols__sort_by_name(struct rb_root *symbols, } } +int symbol__match_symbol_name(const char *name, const char *str, + enum symbol_tag_include includes) +{ + const char *versioning; + + if (includes == SYMBOL_TAG_INCLUDE__DEFAULT_ONLY && + (versioning = strstr(name, "@@"))) { + int len = strlen(str); + + if (len < versioning - name) + len = versioning - name; + + return arch__compare_symbol_names_n(name, str, len); + } else + return arch__compare_symbol_names(name, str); +} + static struct symbol *symbols__find_by_name(struct rb_root *symbols, - const char *name) + const char *name, + enum symbol_tag_include includes) { struct rb_node *n; struct symbol_name_rb_node *s = NULL; @@ -414,11 +443,11 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, int cmp; s = rb_entry(n, struct symbol_name_rb_node, rb_node); - cmp = arch__compare_symbol_names(name, s->sym.name); + cmp = symbol__match_symbol_name(s->sym.name, name, includes); - if (cmp < 0) + if (cmp > 0) n = n->rb_left; - else if (cmp > 0) + else if (cmp < 0) n = n->rb_right; else break; @@ -427,16 +456,17 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, if (n == NULL) return NULL; - /* return first symbol that has same name (if any) */ - for (n = rb_prev(n); n; n = rb_prev(n)) { - struct symbol_name_rb_node *tmp; + if (includes != SYMBOL_TAG_INCLUDE__DEFAULT_ONLY) + /* return first symbol that has same name (if any) */ + for (n = rb_prev(n); n; n = rb_prev(n)) { + struct symbol_name_rb_node *tmp; - tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); - if (arch__compare_symbol_names(tmp->sym.name, s->sym.name)) - break; + tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); + if (arch__compare_symbol_names(tmp->sym.name, s->sym.name)) + break; - s = tmp; - } + s = tmp; + } return &s->sym; } @@ -466,7 +496,7 @@ void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym) struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr) { - if (dso->last_find_result[type].addr != addr) { + if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) { dso->last_find_result[type].addr = addr; dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr); } @@ -503,7 +533,12 @@ struct symbol *symbol__next_by_name(struct symbol *sym) struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { - return symbols__find_by_name(&dso->symbol_names[type], name); + struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name, + SYMBOL_TAG_INCLUDE__NONE); + if (!s) + s = symbols__find_by_name(&dso->symbol_names[type], name, + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); + return s; } void dso__sort_by_name(struct dso *dso, enum map_type type) @@ -1075,8 +1110,9 @@ static int validate_kcore_addresses(const char *kallsyms_filename, if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) { u64 start; - start = kallsyms__get_function_start(kallsyms_filename, - kmap->ref_reloc_sym->name); + if (kallsyms__get_function_start(kallsyms_filename, + kmap->ref_reloc_sym->name, &start)) + return -ENOENT; if (start != kmap->ref_reloc_sym->addr) return -EINVAL; } @@ -1248,9 +1284,7 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) return 0; - addr = kallsyms__get_function_start(filename, - kmap->ref_reloc_sym->name); - if (!addr) + if (kallsyms__get_function_start(filename, kmap->ref_reloc_sym->name, &addr)) return -1; *delta = addr - kmap->ref_reloc_sym->addr; @@ -1528,10 +1562,6 @@ int dso__load(struct dso *dso, struct map *map) if (!runtime_ss && syms_ss) runtime_ss = syms_ss; - if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE) - if (dso__build_id_is_kmod(dso, name, PATH_MAX)) - kmod = true; - if (syms_ss) ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod); else diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 7acd70fce68e..41ebba9a2eb2 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -348,8 +348,19 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym); #define SYMBOL_A 0 #define SYMBOL_B 1 +int arch__compare_symbol_names(const char *namea, const char *nameb); +int arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n); int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb); +enum symbol_tag_include { + SYMBOL_TAG_INCLUDE__NONE = 0, + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY +}; + +int symbol__match_symbol_name(const char *namea, const char *nameb, + enum symbol_tag_include includes); + /* structure containing an SDT note's info */ struct sdt_note { char *name; /* name of the note*/ diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c index f6a2a3d117d5..4767ec2c5ef6 100644 --- a/tools/perf/util/units.c +++ b/tools/perf/util/units.c @@ -1,8 +1,37 @@ #include "units.h" #include <inttypes.h> +#include <limits.h> +#include <stdlib.h> +#include <string.h> #include <linux/kernel.h> #include <linux/time64.h> +unsigned long parse_tag_value(const char *str, struct parse_tag *tags) +{ + struct parse_tag *i = tags; + + while (i->tag) { + char *s = strchr(str, i->tag); + + if (s) { + unsigned long int value; + char *endptr; + + value = strtoul(str, &endptr, 10); + if (s != endptr) + break; + + if (value > ULONG_MAX / i->mult) + break; + value *= i->mult; + return value; + } + i++; + } + + return (unsigned long) -1; +} + unsigned long convert_unit(unsigned long value, char *unit) { *unit = ' '; diff --git a/tools/perf/util/units.h b/tools/perf/util/units.h index 3ed7774afaa9..f02c87317150 100644 --- a/tools/perf/util/units.h +++ b/tools/perf/util/units.h @@ -4,6 +4,13 @@ #include <stddef.h> #include <linux/types.h> +struct parse_tag { + char tag; + int mult; +}; + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags); + unsigned long convert_unit(unsigned long value, char *unit); int unit_number__scnprintf(char *buf, size_t size, u64 n); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index f90e11a555b2..7755a5e0fe5e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -39,6 +39,14 @@ static int __report_module(struct addr_location *al, u64 ip, return 0; mod = dwfl_addrmodule(ui->dwfl, ip); + if (mod) { + Dwarf_Addr s; + + dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); + if (s != al->map->start) + mod = 0; + } + if (!mod) mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1, al->map->start, @@ -168,12 +176,24 @@ frame_callback(Dwfl_Frame *state, void *arg) { struct unwind_info *ui = arg; Dwarf_Addr pc; + bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } + // report the module before we query for isactivation + report_module(pc, ui); + + if (!dwfl_frame_pc(state, &pc, &isactivation)) { + pr_err("%s", dwfl_errmsg(-1)); + return DWARF_CB_ABORT; + } + + if (!isactivation) + --pc; + return entry(pc, ui) || !(--ui->max_stack) ? DWARF_CB_ABORT : DWARF_CB_OK; } @@ -220,7 +240,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui); - if (err && !ui->max_stack) + if (err && ui->max_stack != max_stack) err = 0; /* diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index f8455bed6e65..672c2ada9357 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -692,6 +692,17 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, while (!ret && (unw_step(&c) > 0) && i < max_stack) { unw_get_reg(&c, UNW_REG_IP, &ips[i]); + + /* + * Decrement the IP for any non-activation frames. + * this is required to properly find the srcline + * for caller frames. + * See also the documentation for dwfl_frame_pc(), + * which this code tries to replicate. + */ + if (unw_is_signal_frame(&c) <= 0) + --ips[i]; + ++i; } diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 6450c75a6f5b..28c9f335006c 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -13,7 +13,6 @@ #include <string.h> #include <errno.h> #include <limits.h> -#include <byteswap.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/time64.h> @@ -335,33 +334,6 @@ int hex2u64(const char *ptr, u64 *long_val) return p - ptr; } -unsigned long parse_tag_value(const char *str, struct parse_tag *tags) -{ - struct parse_tag *i = tags; - - while (i->tag) { - char *s; - - s = strchr(str, i->tag); - if (s) { - unsigned long int value; - char *endptr; - - value = strtoul(str, &endptr, 10); - if (s != endptr) - break; - - if (value > ULONG_MAX / i->mult) - break; - value *= i->mult; - return value; - } - i++; - } - - return (unsigned long) -1; -} - int perf_event_paranoid(void) { int value; @@ -372,27 +344,6 @@ int perf_event_paranoid(void) return value; } -void mem_bswap_32(void *src, int byte_size) -{ - u32 *m = src; - while (byte_size > 0) { - *m = bswap_32(*m); - byte_size -= sizeof(u32); - ++m; - } -} - -void mem_bswap_64(void *src, int byte_size) -{ - u64 *m = src; - - while (byte_size > 0) { - *m = bswap_64(*m); - byte_size -= sizeof(u64); - ++m; - } -} - bool find_process(const char *name) { size_t len = strlen(name); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 3852b6d3270a..5dfb9bb6482d 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -5,7 +5,6 @@ #define _BSD_SOURCE 1 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 -#define HAS_BOOL #include <fcntl.h> #include <stdbool.h> @@ -14,8 +13,6 @@ #include <stdarg.h> #include <linux/types.h> -extern char buildid_dir[]; - #ifdef __GNUC__ #define NORETURN __attribute__((__noreturn__)) #else @@ -25,8 +22,6 @@ extern char buildid_dir[]; #endif #endif -#define PERF_GTK_DSO "libperf-gtk.so" - /* General helper functions */ void usage(const char *err) NORETURN; void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); @@ -35,9 +30,6 @@ void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); void set_warning_routine(void (*routine)(const char *err, va_list params)); -int prefixcmp(const char *str, const char *prefix); -void set_buildid_dir(const char *dir); - static inline void *zalloc(size_t size) { return calloc(1, size); @@ -59,29 +51,11 @@ int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 si ssize_t readn(int fd, void *buf, size_t n); ssize_t writen(int fd, void *buf, size_t n); -struct perf_event_attr; - -void event_attr_init(struct perf_event_attr *attr); - size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); extern unsigned int page_size; extern int cacheline_size; -extern int sysctl_perf_event_max_stack; -extern int sysctl_perf_event_max_contexts_per_stack; - -struct parse_tag { - char tag; - int mult; -}; - -unsigned long parse_tag_value(const char *str, struct parse_tag *tags); - -int perf_event_paranoid(void); - -void mem_bswap_64(void *src, int byte_size); -void mem_bswap_32(void *src, int byte_size); bool find_process(const char *name); |
