diff options
Diffstat (limited to 'tools')
53 files changed, 745 insertions, 263 deletions
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c index 099e7cd022e4..7c4347962353 100644 --- a/tools/lib/lk/debugfs.c +++ b/tools/lib/lk/debugfs.c @@ -5,7 +5,6 @@ #include <stdbool.h> #include <sys/vfs.h> #include <sys/mount.h> -#include <linux/magic.h> #include <linux/kernel.h> #include "debugfs.h" diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e297b74471b8..ca0d3d9f4bac 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -90,8 +90,20 @@ OPTIONS Number of mmap data pages. Must be a power of two. -g:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Do call-graph (stack chain/backtrace) recording. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -g. + + Allows specifying "fp" (frame pointer) or "dwarf" + (DWARF's CFI - Call Frame Information) as the method to collect + the information used to show the call graphs. + + In some systems, where binaries are build with gcc + --fomit-frame-pointer, using the "fp" method will produce bogus + call graphs, using "dwarf", if available (perf tools linked to + the libunwind library) should be used instead. -q:: --quiet:: diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 58d6598a9686..6a118e71d003 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -140,20 +140,12 @@ Default is to monitor all CPUS. --asm-raw:: Show raw instruction encoding of assembly instructions. --G [type,min,order]:: +-G:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Display call chains using type, min percent threshold and order. - type can be either: - - flat: single column, linear exposure of call chains. - - graph: use a graph tree, displaying absolute overhead rates. - - fractal: like graph, but displays relative rates. Each branch of - the tree is considered as a new profiled object. - - order can be either: - - callee: callee based call graph. - - caller: inverted caller based call graph. - - Default: fractal,0.5,callee. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -G. --ignore-callees=<regex>:: Ignore callees of the function(s) matching the given regex. diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 3a0ff7fb71b6..64c043b7a438 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -770,6 +770,7 @@ check: $(OUTPUT)common-cmds.h install-bin: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifndef NO_LIBPERL $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile index 15130b50dfe3..fe9b61e322a5 100644 --- a/tools/perf/arch/arm/Makefile +++ b/tools/perf/arch/arm/Makefile @@ -2,3 +2,6 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif +ifndef NO_LIBUNWIND +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o +endif diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h new file mode 100644 index 000000000000..2a1cfde66b69 --- /dev/null +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -0,0 +1,54 @@ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include "../../util/types.h" +#include <asm/perf_regs.h> + +#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM_MAX) - 1) +#define PERF_REG_IP PERF_REG_ARM_PC +#define PERF_REG_SP PERF_REG_ARM_SP + +static inline const char *perf_reg_name(int id) +{ + switch (id) { + case PERF_REG_ARM_R0: + return "r0"; + case PERF_REG_ARM_R1: + return "r1"; + case PERF_REG_ARM_R2: + return "r2"; + case PERF_REG_ARM_R3: + return "r3"; + case PERF_REG_ARM_R4: + return "r4"; + case PERF_REG_ARM_R5: + return "r5"; + case PERF_REG_ARM_R6: + return "r6"; + case PERF_REG_ARM_R7: + return "r7"; + case PERF_REG_ARM_R8: + return "r8"; + case PERF_REG_ARM_R9: + return "r9"; + case PERF_REG_ARM_R10: + return "r10"; + case PERF_REG_ARM_FP: + return "fp"; + case PERF_REG_ARM_IP: + return "ip"; + case PERF_REG_ARM_SP: + return "sp"; + case PERF_REG_ARM_LR: + return "lr"; + case PERF_REG_ARM_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm/util/unwind.c b/tools/perf/arch/arm/util/unwind.c new file mode 100644 index 000000000000..da3dc950550c --- /dev/null +++ b/tools/perf/arch/arm/util/unwind.c @@ -0,0 +1,48 @@ + +#include <errno.h> +#include <libunwind.h> +#include "perf_regs.h" +#include "../../util/unwind.h" + +int unwind__arch_reg_id(int regnum) +{ + switch (regnum) { + case UNW_ARM_R0: + return PERF_REG_ARM_R0; + case UNW_ARM_R1: + return PERF_REG_ARM_R1; + case UNW_ARM_R2: + return PERF_REG_ARM_R2; + case UNW_ARM_R3: + return PERF_REG_ARM_R3; + case UNW_ARM_R4: + return PERF_REG_ARM_R4; + case UNW_ARM_R5: + return PERF_REG_ARM_R5; + case UNW_ARM_R6: + return PERF_REG_ARM_R6; + case UNW_ARM_R7: + return PERF_REG_ARM_R7; + case UNW_ARM_R8: + return PERF_REG_ARM_R8; + case UNW_ARM_R9: + return PERF_REG_ARM_R9; + case UNW_ARM_R10: + return PERF_REG_ARM_R10; + case UNW_ARM_R11: + return PERF_REG_ARM_FP; + case UNW_ARM_R12: + return PERF_REG_ARM_IP; + case UNW_ARM_R13: + return PERF_REG_ARM_SP; + case UNW_ARM_R14: + return PERF_REG_ARM_LR; + case UNW_ARM_R15: + return PERF_REG_ARM_PC; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return -EINVAL; +} diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 9570c2b0f83c..b2519e49424f 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -32,7 +32,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) { - bool cap_usr_time_zero; + bool cap_user_time_zero; u32 seq; int i = 0; @@ -42,7 +42,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, tc->time_mult = pc->time_mult; tc->time_shift = pc->time_shift; tc->time_zero = pc->time_zero; - cap_usr_time_zero = pc->cap_usr_time_zero; + cap_user_time_zero = pc->cap_user_time_zero; rmb(); if (pc->lock == seq && !(seq & 1)) break; @@ -52,7 +52,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, } } - if (!cap_usr_time_zero) + if (!cap_user_time_zero) return -EOPNOTSUPP; return 0; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 423875c999b2..afe377b2884f 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -321,8 +321,6 @@ found: return perf_event__repipe(tool, event_sw, &sample_sw, machine); } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index c2dff9cb1f2c..9b5f077fee5b 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -101,7 +101,7 @@ static int setup_cpunode_map(void) dir1 = opendir(PATH_SYS_NODE); if (!dir1) - return -1; + return 0; while ((dent1 = readdir(dir1)) != NULL) { if (dent1->d_type != DT_DIR || diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 935d52216c89..fbc2888d6495 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -888,11 +888,18 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) { err = perf_evlist__parse_sample(kvm->evlist, event, &sample); if (err) { + perf_evlist__mmap_consume(kvm->evlist, idx); pr_err("Failed to parse sample\n"); return -1; } err = perf_session_queue_event(kvm->session, event, &sample, 0); + /* + * FIXME: Here we can't consume the event, as perf_session_queue_event will + * point to it, and it'll get possibly overwritten by the kernel. + */ + perf_evlist__mmap_consume(kvm->evlist, idx); + if (err) { pr_err("Failed to enqueue sample: %d\n", err); return -1; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a41ac41546c9..d04651484640 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -712,21 +712,12 @@ static int get_stack_size(char *str, unsigned long *_size) } #endif /* LIBUNWIND_SUPPORT */ -int record_parse_callchain_opt(const struct option *opt, - const char *arg, int unset) +int record_parse_callchain(const char *arg, struct perf_record_opts *opts) { - struct perf_record_opts *opts = opt->value; char *tok, *name, *saveptr = NULL; char *buf; int ret = -1; - /* --no-call-graph */ - if (unset) - return 0; - - /* We specified default option if none is provided. */ - BUG_ON(!arg); - /* We need buffer that we know we can write to. */ buf = malloc(strlen(arg) + 1); if (!buf) @@ -764,13 +755,9 @@ int record_parse_callchain_opt(const struct option *opt, ret = get_stack_size(tok, &size); opts->stack_dump_size = size; } - - if (!ret) - pr_debug("callchain: stack dump size %d\n", - opts->stack_dump_size); #endif /* LIBUNWIND_SUPPORT */ } else { - pr_err("callchain: Unknown -g option " + pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); break; } @@ -778,13 +765,52 @@ int record_parse_callchain_opt(const struct option *opt, } while (0); free(buf); + return ret; +} + +static void callchain_debug(struct perf_record_opts *opts) +{ + pr_debug("callchain: type %d\n", opts->call_graph); + if (opts->call_graph == CALLCHAIN_DWARF) + pr_debug("callchain: stack dump size %d\n", + opts->stack_dump_size); +} + +int record_parse_callchain_opt(const struct option *opt, + const char *arg, + int unset) +{ + struct perf_record_opts *opts = opt->value; + int ret; + + /* --no-call-graph */ + if (unset) { + opts->call_graph = CALLCHAIN_NONE; + pr_debug("callchain: disabled\n"); + return 0; + } + + ret = record_parse_callchain(arg, opts); if (!ret) - pr_debug("callchain: type %d\n", opts->call_graph); + callchain_debug(opts); return ret; } +int record_callchain_opt(const struct option *opt, + const char *arg __maybe_unused, + int unset __maybe_unused) +{ + struct perf_record_opts *opts = opt->value; + + if (opts->call_graph == CALLCHAIN_NONE) + opts->call_graph = CALLCHAIN_FP; + + callchain_debug(opts); + return 0; +} + static const char * const record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -813,12 +839,12 @@ static struct perf_record record = { }, }; -#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " +#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " #ifdef LIBUNWIND_SUPPORT -const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf"; #else -const char record_callchain_help[] = CALLCHAIN_HELP "[fp]"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp"; #endif /* @@ -858,9 +884,12 @@ const struct option record_options[] = { "number of mmap data pages"), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts, - "mode[,dump_size]", record_callchain_help, - &record_parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('g', NULL, &record.opts, + NULL, "enables call-graph recording" , + &record_callchain_opt), + OPT_CALLBACK(0, "call-graph", &record.opts, + "mode[,dump_size]", record_callchain_help, + &record_parse_callchain_opt), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"), diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8e50d8d77419..72eae7498c09 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -401,8 +401,6 @@ static int perf_report__setup_sample_type(struct perf_report *rep) return 0; } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; @@ -568,6 +566,9 @@ static int __cmd_report(struct perf_report *rep) } } + if (session_done()) + return 0; + if (nr_samples == 0) { ui__error("The %s file has no samples!\n", session->filename); return 0; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 7f31a3ded1b6..9c333ff3dfeb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -553,8 +553,6 @@ static struct perf_tool perf_script = { .ordering_requires_timestamps = true, }; -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f686d5ff594e..5098f144b92d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -457,6 +457,7 @@ static int __run_perf_stat(int argc, const char **argv) perror("failed to prepare workload"); return -1; } + child_pid = evsel_list->workload.pid; } if (group) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 212214162bb2..5a11f13e56f9 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -810,7 +810,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) ret = perf_evlist__parse_sample(top->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); - continue; + goto next_event; } evsel = perf_evlist__id2evsel(session->evlist, sample.id); @@ -825,13 +825,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) case PERF_RECORD_MISC_USER: ++top->us_samples; if (top->hide_user_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_KERNEL: ++top->kernel_samples; if (top->hide_kernel_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_GUEST_KERNEL: @@ -847,7 +847,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) */ /* Fall thru */ default: - continue; + goto next_event; } @@ -859,6 +859,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) machine__process_event(machine, event); } else ++session->stats.nr_unknown_events; +next_event: + perf_evlist__mmap_consume(top->evlist, idx); } } @@ -1016,16 +1018,16 @@ out_delete: } static int -parse_callchain_opt(const struct option *opt, const char *arg, int unset) +callchain_opt(const struct option *opt, const char *arg, int unset) { - /* - * --no-call-graph - */ - if (unset) - return 0; - symbol_conf.use_callchain = true; + return record_callchain_opt(opt, arg, unset); +} +static int +parse_callchain_opt(const struct option *opt, const char *arg, int unset) +{ + symbol_conf.use_callchain = true; return record_parse_callchain_opt(opt, arg, unset); } @@ -1106,9 +1108,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), - OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, - "mode[,dump_size]", record_callchain_help, - &parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts, + NULL, "enables call-graph recording", + &callchain_opt), + OPT_CALLBACK(0, "call-graph", &top.record_opts, + "mode[,dump_size]", record_callchain_help, + &parse_callchain_opt), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", "ignore callees of these functions in call graphs", report_parse_ignore_callees_opt), diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f5aa6375e3e9..99c8d9ad6729 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -16,6 +16,23 @@ #include <sys/mman.h> #include <linux/futex.h> +/* For older distros: */ +#ifndef MAP_STACK +# define MAP_STACK 0x20000 +#endif + +#ifndef MADV_HWPOISON +# define MADV_HWPOISON 100 +#endif + +#ifndef MADV_MERGEABLE +# define MADV_MERGEABLE 12 +#endif + +#ifndef MADV_UNMERGEABLE +# define MADV_UNMERGEABLE 13 +#endif + static size_t syscall_arg__scnprintf_hex(char *bf, size_t size, unsigned long arg, u8 arg_idx __maybe_unused, @@ -970,7 +987,7 @@ again: err = perf_evlist__parse_sample(evlist, event, &sample); if (err) { fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err); - continue; + goto next_event; } if (trace->base_time == 0) @@ -984,18 +1001,20 @@ again: evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); - continue; + goto next_event; } if (sample.raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", perf_evsel__name(evsel), sample.tid, sample.cpu, sample.raw_size); - continue; + goto next_event; } handler = evsel->handler.func; handler(trace, evsel, &sample); +next_event: + perf_evlist__mmap_consume(evlist, i); if (done) goto out_unmap_evlist; @@ -1038,6 +1057,7 @@ static int trace__replay(struct trace *trace) trace->tool.sample = trace__process_sample; trace->tool.mmap = perf_event__process_mmap; + trace->tool.mmap2 = perf_event__process_mmap2; trace->tool.comm = perf_event__process_comm; trace->tool.exit = perf_event__process_exit; trace->tool.fork = perf_event__process_fork; diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 214e17e97e5c..75b93d7f7860 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -29,6 +29,10 @@ ifeq ($(ARCH),x86_64) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 endif +ifeq ($(ARCH),arm) + NO_PERF_REGS := 0 + LIBUNWIND_LIBS = -lunwind -lunwind-arm +endif ifeq ($(NO_PERF_REGS),0) CFLAGS += -DHAVE_PERF_REGS @@ -87,7 +91,7 @@ CFLAGS += -Wall CFLAGS += -Wextra CFLAGS += -std=gnu99 -EXTLIBS = -lelf -lpthread -lrt -lm +EXTLIBS = -lelf -lpthread -lrt -lm -ldl ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y) CFLAGS += -fstack-protector-all @@ -180,6 +184,9 @@ FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) CFLAGS += -DLIBELF_MMAP endif +ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y) + CFLAGS += -DHAVE_ELF_GETPHDRNUM +endif # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile @@ -205,8 +212,7 @@ ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) endif # try-cc endif # NO_LIBELF -# There's only x86 (both 32 and 64) support for CFI unwind so far -ifneq ($(ARCH),x86) +ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 endif @@ -220,9 +226,13 @@ endif FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS) ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y) - msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99); + msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1); NO_LIBUNWIND := 1 endif # Libunwind support +ifneq ($(call try-cc,$(SOURCE_LIBUNWIND_DEBUG_FRAME),$(FLAGS_UNWIND),libunwind debug_frame),y) + msg := $(warning No debug_frame support found in libunwind); +CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME +endif # debug_frame support in libunwind endif # NO_LIBUNWIND ifndef NO_LIBUNWIND diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index 708fb8e9822a..028fe997d5eb 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -61,6 +61,15 @@ int main(void) } endef +define SOURCE_ELF_GETPHDRNUM +#include <libelf.h> +int main(void) +{ + size_t dst; + return elf_getphdrnum(0, &dst); +} +endef + ifndef NO_SLANG define SOURCE_SLANG #include <slang.h> @@ -176,7 +185,6 @@ extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, unw_proc_info_t *pi, int need_unwind_info, void *arg); - #define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) int main(void) @@ -188,6 +196,26 @@ int main(void) return 0; } endef + +define SOURCE_LIBUNWIND_DEBUG_FRAME +#include <libunwind.h> +#include <stdlib.h> + +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + +int main(void) +{ + dwarf_find_debug_frame(0, NULL, 0, 0, NULL, 0, 0); + return 0; +} +endef + endif ifndef NO_BACKTRACE @@ -210,6 +238,7 @@ define SOURCE_LIBAUDIT int main(void) { + printf(\"error message: %s\", audit_errno_to_name(0)); return audit_open(); } endef diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 6fb781d5586c..e3fedfa2906e 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -290,6 +290,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist, for (i = 0; i < evlist->nr_mmaps; i++) { while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { ret = process_event(machine, evlist, event, state); + perf_evlist__mmap_consume(evlist, i); if (ret < 0) return ret; } diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index d444ea2c47d9..376c35608534 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -36,6 +36,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm) (pid_t)event->comm.tid == getpid() && strcmp(event->comm.comm, comm) == 0) found += 1; + perf_evlist__mmap_consume(evlist, i); } } return found; diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index c4185b9aeb80..a7232c204eb9 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -122,6 +122,7 @@ int test__basic_mmap(void) goto out_munmap; } nr_events[evsel->idx]++; + perf_evlist__mmap_consume(evlist, 0); } err = 0; diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c index fc5b9fca8b47..524b221b829b 100644 --- a/tools/perf/tests/open-syscall-tp-fields.c +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -77,8 +77,10 @@ int test__syscall_open_tp_fields(void) ++nr_events; - if (type != PERF_RECORD_SAMPLE) + if (type != PERF_RECORD_SAMPLE) { + perf_evlist__mmap_consume(evlist, i); continue; + } err = perf_evsel__parse_sample(evsel, event, &sample); if (err) { diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index b8a7056519ac..7923b06ffc91 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -263,6 +263,8 @@ int test__PERF_RECORD(void) type); ++errs; } + + perf_evlist__mmap_consume(evlist, i); } } diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 0ab61b1f408e..4ca1b938f6a6 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -122,7 +122,7 @@ int test__perf_time_to_tsc(void) if (event->header.type != PERF_RECORD_COMM || (pid_t)event->comm.pid != getpid() || (pid_t)event->comm.tid != getpid()) - continue; + goto next_event; if (strcmp(event->comm.comm, comm1) == 0) { CHECK__(perf_evsel__parse_sample(evsel, event, @@ -134,6 +134,8 @@ int test__perf_time_to_tsc(void) &sample)); comm2_time = sample.time; } +next_event: + perf_evlist__mmap_consume(evlist, i); } } diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 2e41e2d32ccc..6e2b44ec0749 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) - continue; + goto next_event; err = perf_evlist__parse_sample(evlist, event, &sample); if (err < 0) { @@ -88,6 +88,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) total_periods += sample.period; nr_samples++; +next_event: + perf_evlist__mmap_consume(evlist, 0); } if ((u64) nr_samples == total_periods) { diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 28fe5894b061..a3e64876e940 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -96,10 +96,10 @@ int test__task_exit(void) retry: while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { - if (event->header.type != PERF_RECORD_EXIT) - continue; + if (event->header.type == PERF_RECORD_EXIT) + nr_exit++; - nr_exit++; + perf_evlist__mmap_consume(evlist, 0); } if (!exited || !nr_exit) { diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 194e2f42ff5d..6c152686e837 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -315,8 +315,7 @@ static inline void advance_hpp(struct perf_hpp *hpp, int inc) } static int hist_entry__period_snprintf(struct perf_hpp *hpp, - struct hist_entry *he, - bool color) + struct hist_entry *he) { const char *sep = symbol_conf.field_sep; struct perf_hpp_fmt *fmt; @@ -338,7 +337,7 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp, } else first = false; - if (color && fmt->color) + if (perf_hpp__use_color() && fmt->color) ret = fmt->color(fmt, hpp, he); else ret = fmt->entry(fmt, hpp, he); @@ -358,12 +357,11 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, .buf = bf, .size = size, }; - bool color = !symbol_conf.field_sep; if (size == 0 || size > bfsz) size = hpp.size = bfsz; - ret = hist_entry__period_snprintf(&hpp, he, color); + ret = hist_entry__period_snprintf(&hpp, he); hist_entry__sort_snprintf(he, bf + ret, size - ret, hists); ret = fprintf(fp, "%s\n", bf); @@ -482,6 +480,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, print_entries: linesz = hists__sort_list_width(hists) + 3 + 1; + linesz += perf_hpp__color_overhead(); line = malloc(linesz); if (line == NULL) { ret = -1; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index bfc5a27597d6..7eae5488ecea 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, end = map__rip_2objdump(map, sym->end); offset = line_ip - start; - if (offset < 0 || (u64)line_ip > end) + if ((u64)line_ip < start || (u64)line_ip > end) offset = -1; else parsed_line = tmp2 + 1; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 2b585bc308cf..9e99060408ae 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -147,6 +147,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) struct option; +int record_parse_callchain(const char *arg, struct perf_record_opts *opts); int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +int record_callchain_opt(const struct option *opt, const char *arg, int unset); + extern const char record_callchain_help[]; #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 3e5f5430a28a..7defd77105d0 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die) } /** + * die_is_func_def - Ensure that this DIE is a subprogram and definition + * @dw_die: a DIE + * + * Ensure that this DIE is a subprogram and NOT a declaration. This + * returns true if @dw_die is a function definition. + **/ +bool die_is_func_def(Dwarf_Die *dw_die) +{ + Dwarf_Attribute attr; + + return (dwarf_tag(dw_die) == DW_TAG_subprogram && + dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); +} + +/** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure * @offs: The offset of the member in the data structure @@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) { struct __addr_die_search_param *ad = data; + /* + * Since a declaration entry doesn't has given pc, this always returns + * function definition entry. + */ if (dwarf_tag(fn_die) == DW_TAG_subprogram && dwarf_haspc(fn_die, ad->addr)) { memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die)); @@ -407,7 +426,7 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) * @die_mem: a buffer for result DIE * * Search a non-inlined function DIE which includes @addr. Stores the - * DIE to @die_mem and returns it if found. Returns NULl if failed. + * DIE to @die_mem and returns it if found. Returns NULL if failed. */ Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, Dwarf_Die *die_mem) @@ -435,15 +454,32 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data) } /** + * die_find_top_inlinefunc - Search the top inlined function at given address + * @sp_die: a subprogram DIE which including @addr + * @addr: target address + * @die_mem: a buffer for result DIE + * + * Search an inlined function DIE which includes @addr. Stores the + * DIE to @die_mem and returns it if found. Returns NULL if failed. + * Even if several inlined functions are expanded recursively, this + * doesn't trace it down, and returns the topmost one. + */ +Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) +{ + return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem); +} + +/** * die_find_inlinefunc - Search an inlined function at given address - * @cu_die: a CU DIE which including @addr + * @sp_die: a subprogram DIE which including @addr * @addr: target address * @die_mem: a buffer for result DIE * * Search an inlined function DIE which includes @addr. Stores the - * DIE to @die_mem and returns it if found. Returns NULl if failed. + * DIE to @die_mem and returns it if found. Returns NULL if failed. * If several inlined functions are expanded recursively, this trace - * it and returns deepest one. + * it down and returns deepest one. */ Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, Dwarf_Die *die_mem) diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 6ce1717784b7..b4fe90c6cb2d 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, int (*callback)(Dwarf_Die *, void *), void *data); +/* Ensure that this DIE is a subprogram and definition (not declaration) */ +extern bool die_is_func_def(Dwarf_Die *dw_die); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); @@ -76,7 +79,11 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die, extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, Dwarf_Die *die_mem); -/* Search an inlined function including given address */ +/* Search the top inlined function including given address */ +extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem); + +/* Search the deepest inlined function including given address */ extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, Dwarf_Die *die_mem); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 9b393e7dca6f..49096ea58a15 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -187,7 +187,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, return -1; } - event->header.type = PERF_RECORD_MMAP2; + event->header.type = PERF_RECORD_MMAP; /* * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c */ @@ -198,7 +198,6 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, char prot[5]; char execname[PATH_MAX]; char anonstr[] = "//anon"; - unsigned int ino; size_t size; ssize_t n; @@ -209,15 +208,12 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", - &event->mmap2.start, &event->mmap2.len, prot, - &event->mmap2.pgoff, &event->mmap2.maj, - &event->mmap2.min, - &ino, execname); - - event->mmap2.ino = (u64)ino; + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", + &event->mmap.start, &event->mmap.len, prot, + &event->mmap.pgoff, + execname); - if (n != 8) + if (n != 5) continue; if (prot[2] != 'x') @@ -227,15 +223,15 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, anonstr); size = strlen(execname) + 1; - memcpy(event->mmap2.filename, execname, size); + memcpy(event->mmap.filename, execname, size); size = PERF_ALIGN(size, sizeof(u64)); - event->mmap2.len -= event->mmap.start; - event->mmap2.header.size = (sizeof(event->mmap2) - - (sizeof(event->mmap2.filename) - size)); - memset(event->mmap2.filename + size, 0, machine->id_hdr_size); - event->mmap2.header.size += machine->id_hdr_size; - event->mmap2.pid = tgid; - event->mmap2.tid = pid; + event->mmap.len -= event->mmap.start; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; + event->mmap.pid = tgid; + event->mmap.tid = pid; if (process(tool, event, &synth_sample, machine) != 0) { rc = -1; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f9f77bee0b1b..e584cd30b0f2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -545,12 +545,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) md->prev = old; - if (!evlist->overwrite) - perf_mmap__write_tail(md, old); - return event; } +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) +{ + if (!evlist->overwrite) { + struct perf_mmap *md = &evlist->mmap[idx]; + unsigned int old = md->prev; + + perf_mmap__write_tail(md, old); + } +} + static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) { if (evlist->mmap[idx].base != NULL) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 880d7139d2fb..206d09339306 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -89,6 +89,8 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); + int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 0ce9febf1ba0..9f1ef9bee2d0 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -678,7 +678,6 @@ void perf_evsel__config(struct perf_evsel *evsel, attr->sample_type |= PERF_SAMPLE_WEIGHT; attr->mmap = track; - attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; /* diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 26441d0e571b..c3e5a3b817ab 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -199,9 +199,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id, return write_padded(fd, name, name_len + 1, len); } -static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, - u16 misc, int fd) +static int __dsos__write_buildid_table(struct list_head *head, + struct machine *machine, + pid_t pid, u16 misc, int fd) { + char nm[PATH_MAX]; struct dso *pos; dsos__for_each_with_build_id(pos, head) { @@ -215,6 +217,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, if (is_vdso_map(pos->short_name)) { name = (char *) VDSO__MAP_NAME; name_len = sizeof(VDSO__MAP_NAME) + 1; + } else if (dso__is_kcore(pos)) { + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + name_len = strlen(nm) + 1; } else { name = pos->long_name; name_len = pos->long_name_len + 1; @@ -240,10 +246,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd) umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid, - kmisc, fd); + err = __dsos__write_buildid_table(&machine->kernel_dsos, machine, + machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, + err = __dsos__write_buildid_table(&machine->user_dsos, machine, machine->pid, umisc, fd); return err; } @@ -375,23 +381,31 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; bool is_vdso = is_vdso_map(dso->short_name); + char *name = dso->long_name; + char nm[PATH_MAX]; - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), - dso->long_name, debugdir, - is_kallsyms, is_vdso); + if (dso__is_kcore(dso)) { + is_kallsyms = true; + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + } + return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, + debugdir, is_kallsyms, is_vdso); } -static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) +static int __dsos__cache_build_ids(struct list_head *head, + struct machine *machine, const char *debugdir) { struct dso *pos; int err = 0; dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, debugdir)) + if (dso__cache_build_id(pos, machine, debugdir)) err = -1; return err; @@ -399,8 +413,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine, + debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir); return ret; } @@ -2753,6 +2768,18 @@ int perf_session__read_header(struct perf_session *session) if (perf_file_header__read(&f_header, header, fd) < 0) return -EINVAL; + /* + * Sanity check that perf.data was written cleanly; data size is + * initialized to 0 and updated only if the on_exit function is run. + * If data size is still 0 then the file contains only partial + * information. Just warn user and process it as much as it can. + */ + if (f_header.data.size == 0) { + pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n" + "Was the 'perf record' command properly terminated?\n", + session->filename); + } + nr_attrs = f_header.attrs.size / f_header.attr_size; lseek(fd, f_header.attrs.offset, SEEK_SET); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 46a0d35a05e1..9ff6cf3e9a99 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -611,6 +611,8 @@ void hists__collapse_resort(struct hists *hists) next = rb_first(root); while (next) { + if (session_done()) + break; n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 1329b6b6ffe6..ce8dc61ce2c3 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -5,6 +5,7 @@ #include <pthread.h> #include "callchain.h" #include "header.h" +#include "color.h" extern struct callchain_param callchain_param; @@ -175,6 +176,18 @@ void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); +static inline size_t perf_hpp__use_color(void) +{ + return !symbol_conf.field_sep; +} + +static inline size_t perf_hpp__color_overhead(void) +{ + return perf_hpp__use_color() ? + (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX + : 0; +} + struct perf_evlist; struct hist_browser_timer { diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 933d14f287ca..6188d2876a71 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -792,7 +792,7 @@ static int machine__create_modules(struct machine *machine) modules = path; } - if (symbol__restricted_filename(path, "/proc/modules")) + if (symbol__restricted_filename(modules, "/proc/modules")) return -1; file = fopen(modules, "r"); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index be0329394d56..f0692737ebf1 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -118,7 +118,6 @@ static const Dwfl_Callbacks offline_callbacks = { static int debuginfo__init_offline_dwarf(struct debuginfo *self, const char *path) { - Dwfl_Module *mod; int fd; fd = open(path, O_RDONLY); @@ -129,11 +128,11 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *self, if (!self->dwfl) goto error; - mod = dwfl_report_offline(self->dwfl, "", "", fd); - if (!mod) + self->mod = dwfl_report_offline(self->dwfl, "", "", fd); + if (!self->mod) goto error; - self->dbg = dwfl_module_getdwarf(mod, &self->bias); + self->dbg = dwfl_module_getdwarf(self->mod, &self->bias); if (!self->dbg) goto error; @@ -676,37 +675,42 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) } /* Convert subprogram DIE to trace point */ -static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr, - bool retprobe, struct probe_trace_point *tp) +static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, + Dwarf_Addr paddr, bool retprobe, + struct probe_trace_point *tp) { Dwarf_Addr eaddr, highaddr; - const char *name; - - /* Copy the name of probe point */ - name = dwarf_diename(sp_die); - if (name) { - if (dwarf_entrypc(sp_die, &eaddr) != 0) { - pr_warning("Failed to get entry address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (dwarf_highpc(sp_die, &highaddr) != 0) { - pr_warning("Failed to get end address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (paddr > highaddr) { - pr_warning("Offset specified is greater than size of %s\n", - dwarf_diename(sp_die)); - return -EINVAL; - } - tp->symbol = strdup(name); - if (tp->symbol == NULL) - return -ENOMEM; - tp->offset = (unsigned long)(paddr - eaddr); - } else - /* This function has no name. */ - tp->offset = (unsigned long)paddr; + GElf_Sym sym; + const char *symbol; + + /* Verify the address is correct */ + if (dwarf_entrypc(sp_die, &eaddr) != 0) { + pr_warning("Failed to get entry address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (dwarf_highpc(sp_die, &highaddr) != 0) { + pr_warning("Failed to get end address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (paddr > highaddr) { + pr_warning("Offset specified is greater than size of %s\n", + dwarf_diename(sp_die)); + return -EINVAL; + } + + /* Get an appropriate symbol from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + if (!symbol) { + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; + } + tp->offset = (unsigned long)(paddr - sym.st_value); + tp->symbol = strdup(symbol); + if (!tp->symbol) + return -ENOMEM; /* Return probe must be on the head of a subprogram */ if (retprobe) { @@ -734,7 +738,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) } /* If not a real subprogram, find a real one */ - if (dwarf_tag(sc_die) != DW_TAG_subprogram) { + if (!die_is_func_def(sc_die)) { if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) { pr_warning("Failed to find probe point in any " "functions.\n"); @@ -980,12 +984,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) struct dwarf_callback_param *param = data; struct probe_finder *pf = param->data; struct perf_probe_point *pp = &pf->pev->point; - Dwarf_Attribute attr; /* Check tag and diename */ - if (dwarf_tag(sp_die) != DW_TAG_subprogram || - !die_compare_name(sp_die, pp->function) || - dwarf_attr(sp_die, DW_AT_declaration, &attr)) + if (!die_is_func_def(sp_die) || + !die_compare_name(sp_die, pp->function)) return DWARF_CB_OK; /* Check declared file */ @@ -1151,7 +1153,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) tev = &tf->tevs[tf->ntevs++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr, pf->pev->point.retprobe, &tev->point); if (ret < 0) return ret; @@ -1183,7 +1185,7 @@ int debuginfo__find_trace_events(struct debuginfo *self, { struct trace_event_finder tf = { .pf = {.pev = pev, .callback = add_probe_trace_event}, - .max_tevs = max_tevs}; + .mod = self->mod, .max_tevs = max_tevs}; int ret; /* Allocate result tevs array */ @@ -1252,7 +1254,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) vl = &af->vls[af->nvls++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr, pf->pev->point.retprobe, &vl->point); if (ret < 0) return ret; @@ -1291,6 +1293,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *self, { struct available_var_finder af = { .pf = {.pev = pev, .callback = add_available_vars}, + .mod = self->mod, .max_vls = max_vls, .externs = externs}; int ret; @@ -1324,8 +1327,8 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, struct perf_probe_point *ppt) { Dwarf_Die cudie, spdie, indie; - Dwarf_Addr _addr, baseaddr; - const char *fname = NULL, *func = NULL, *tmp; + Dwarf_Addr _addr = 0, baseaddr = 0; + const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; /* Adjust address with bias */ @@ -1346,27 +1349,36 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, /* Find a corresponding function (name, baseline and baseaddr) */ if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) { /* Get function entry information */ - tmp = dwarf_diename(&spdie); - if (!tmp || + func = basefunc = dwarf_diename(&spdie); + if (!func || dwarf_entrypc(&spdie, &baseaddr) != 0 || - dwarf_decl_line(&spdie, &baseline) != 0) + dwarf_decl_line(&spdie, &baseline) != 0) { + lineno = 0; goto post; - func = tmp; + } - if (addr == (unsigned long)baseaddr) + fname = dwarf_decl_file(&spdie); + if (addr == (unsigned long)baseaddr) { /* Function entry - Relative line number is 0 */ lineno = baseline; - else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr, - &indie)) { + goto post; + } + + /* Track down the inline functions step by step */ + while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, + &indie)) { + /* There is an inline function */ if (dwarf_entrypc(&indie, &_addr) == 0 && - _addr == addr) + _addr == addr) { /* * addr is at an inline function entry. * In this case, lineno should be the call-site - * line number. + * line number. (overwrite lineinfo) */ lineno = die_get_call_lineno(&indie); - else { + fname = die_get_call_file(&indie); + break; + } else { /* * addr is in an inline function body. * Since lineno points one of the lines @@ -1374,19 +1386,27 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, * be the entry line of the inline function. */ tmp = dwarf_diename(&indie); - if (tmp && - dwarf_decl_line(&spdie, &baseline) == 0) - func = tmp; + if (!tmp || + dwarf_decl_line(&indie, &baseline) != 0) + break; + func = tmp; + spdie = indie; } } + /* Verify the lineno and baseline are in a same file */ + tmp = dwarf_decl_file(&spdie); + if (!tmp || strcmp(tmp, fname) != 0) + lineno = 0; } post: /* Make a relative line number or an offset */ if (lineno) ppt->line = lineno - baseline; - else if (func) + else if (basefunc) { ppt->offset = addr - (unsigned long)baseaddr; + func = basefunc; + } /* Duplicate strings */ if (func) { @@ -1474,7 +1494,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data) return 0; } -/* Search function from function name */ +/* Search function definition from function name */ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) { struct dwarf_callback_param *param = data; @@ -1485,7 +1505,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (dwarf_tag(sp_die) == DW_TAG_subprogram && + if (die_is_func_def(sp_die) && die_compare_name(sp_die, lr->function)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 17e94d0c36f9..3b7d63018960 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -23,6 +23,7 @@ static inline int is_c_varname(const char *name) /* debug information structure */ struct debuginfo { Dwarf *dbg; + Dwfl_Module *mod; Dwfl *dwfl; Dwarf_Addr bias; }; @@ -77,6 +78,7 @@ struct probe_finder { struct trace_event_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct probe_trace_event *tevs; /* Found trace events */ int ntevs; /* Number of trace events */ int max_tevs; /* Max number of trace events */ @@ -84,6 +86,7 @@ struct trace_event_finder { struct available_var_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct variable_list *vls; /* Found variable lists */ int nvls; /* Number of variable lists */ int max_vls; /* Max no. of variable lists */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 71b5412bbbb9..2ac4bc92bb1f 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -822,6 +822,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; + perf_evlist__mmap_consume(evlist, cpu); + if (pyevent == NULL) return PyErr_NoMemory(); diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index a85e4ae5f3ac..c0c9795c4f02 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %" PRIu64, evsel->attr.config); + die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); pid = raw_field_value(event, "common_pid", data); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cc75a3cef388..95d91a0b23af 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -56,6 +56,17 @@ static void handler_call_die(const char *handler_name) Py_FatalError("problem in Python trace event handler"); } +/* + * Insert val into into the dictionary and decrement the reference counter. + * This is necessary for dictionaries since PyDict_SetItemString() does not + * steal a reference, as opposed to PyTuple_SetItem(). + */ +static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val) +{ + PyDict_SetItemString(dict, key, val); + Py_DECREF(val); +} + static void define_value(enum print_arg_type field_type, const char *ev_name, const char *field_name, @@ -279,11 +290,11 @@ static void python_process_tracepoint(union perf_event *perf_event PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); } else { - PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu)); - PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s)); - PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns)); - PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid)); - PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); + pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); + pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); + pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); + pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -313,7 +324,7 @@ static void python_process_tracepoint(union perf_event *perf_event if (handler) PyTuple_SetItem(t, n++, obj); else - PyDict_SetItemString(dict, field->name, obj); + pydict_set_item_string_decref(dict, field->name, obj); } if (!handler) @@ -370,21 +381,21 @@ static void python_process_general_event(union perf_event *perf_event if (!handler || !PyCallable_Check(handler)) goto exit; - PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( (const char *)sample, sizeof(*sample))); - PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); - PyDict_SetItemString(dict, "comm", + pydict_set_item_string_decref(dict, "comm", PyString_FromString(thread->comm)); if (al->map) { - PyDict_SetItemString(dict, "dso", + pydict_set_item_string_decref(dict, "dso", PyString_FromString(al->map->dso->name)); } if (al->sym) { - PyDict_SetItemString(dict, "symbol", + pydict_set_item_string_decref(dict, "symbol", PyString_FromString(al->sym->name)); } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 51f5edf2a6d0..568b750c01f6 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -256,6 +256,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->sample = process_event_sample_stub; if (tool->mmap == NULL) tool->mmap = process_event_stub; + if (tool->mmap2 == NULL) + tool->mmap2 = process_event_stub; if (tool->comm == NULL) tool->comm = process_event_stub; if (tool->fork == NULL) @@ -531,6 +533,9 @@ static int flush_sample_queue(struct perf_session *s, return 0; list_for_each_entry_safe(iter, tmp, head, list) { + if (session_done()) + return 0; + if (iter->timestamp > limit) break; @@ -1160,7 +1165,6 @@ static void perf_session__warn_about_errors(const struct perf_session *session, } } -#define session_done() (*(volatile int *)(&session_done)) volatile int session_done; static int __perf_session__process_pipe_events(struct perf_session *self, @@ -1308,7 +1312,7 @@ int __perf_session__process_events(struct perf_session *session, file_offset = page_offset; head = data_offset - page_offset; - if (data_offset + data_size < file_size) + if (data_size && (data_offset + data_size < file_size)) file_size = data_offset + data_size; progress_next = file_size / 16; @@ -1372,10 +1376,13 @@ more: "Processing events..."); } + err = 0; + if (session_done()) + goto out_err; + if (file_pos < file_size) goto more; - err = 0; /* do the final flush for ordered samples */ session->ordered_samples.next_flush = ULLONG_MAX; err = flush_sample_queue(session, tool); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 3aa75fb2225f..04bf7373a7e5 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -124,4 +124,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, #define perf_session__set_tracepoints_handlers(session, array) \ __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) + +extern volatile int session_done; + +#define session_done() (*(volatile int *)(&session_done)) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a7b9ab557380..a9c829be5216 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -8,6 +8,22 @@ #include "symbol.h" #include "debug.h" +#ifndef HAVE_ELF_GETPHDRNUM +static int elf_getphdrnum(Elf *elf, size_t *dst) +{ + GElf_Ehdr gehdr; + GElf_Ehdr *ehdr; + + ehdr = gelf_getehdr(elf, &gehdr); + if (!ehdr) + return -1; + + *dst = ehdr->e_phnum; + + return 0; +} +#endif + #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index fe7a27d67d2b..e9e1c03f927d 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -186,7 +186,7 @@ void parse_proc_kallsyms(struct pevent *pevent, char *next = NULL; char *addr_str; char *mod; - char *fmt; + char *fmt = NULL; line = strtok_r(file, "\n", &next); while (line) { diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c index 2f891f7e70bf..5390d0b8862a 100644 --- a/tools/perf/util/unwind.c +++ b/tools/perf/util/unwind.c @@ -39,6 +39,15 @@ UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, #define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, + unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + #define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */ #define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */ @@ -245,8 +254,9 @@ static int unwind_spec_ehframe(struct dso *dso, struct machine *machine, return 0; } -static int read_unwind_spec(struct dso *dso, struct machine *machine, - u64 *table_data, u64 *segbase, u64 *fde_count) +static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, + u64 *table_data, u64 *segbase, + u64 *fde_count) { int ret = -EINVAL, fd; u64 offset; @@ -255,6 +265,7 @@ static int read_unwind_spec(struct dso *dso, struct machine *machine, if (fd < 0) return -EINVAL; + /* Check the .eh_frame section for unwinding info */ offset = elf_section_offset(fd, ".eh_frame_hdr"); close(fd); @@ -263,10 +274,29 @@ static int read_unwind_spec(struct dso *dso, struct machine *machine, table_data, segbase, fde_count); - /* TODO .debug_frame check if eh_frame_hdr fails */ return ret; } +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int read_unwind_spec_debug_frame(struct dso *dso, + struct machine *machine, u64 *offset) +{ + int fd = dso__data_fd(dso, machine); + + if (fd < 0) + return -EINVAL; + + /* Check the .debug_frame section for unwinding info */ + *offset = elf_section_offset(fd, ".debug_frame"); + close(fd); + + if (*offset) + return 0; + + return -EINVAL; +} +#endif + static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; @@ -291,20 +321,33 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, pr_debug("unwind: find_proc_info dso %s\n", map->dso->name); - if (read_unwind_spec(map->dso, ui->machine, - &table_data, &segbase, &fde_count)) - return -EINVAL; + /* Check the .eh_frame section for unwinding info */ + if (!read_unwind_spec_eh_frame(map->dso, ui->machine, + &table_data, &segbase, &fde_count)) { + memset(&di, 0, sizeof(di)); + di.format = UNW_INFO_FORMAT_REMOTE_TABLE; + di.start_ip = map->start; + di.end_ip = map->end; + di.u.rti.segbase = map->start + segbase; + di.u.rti.table_data = map->start + table_data; + di.u.rti.table_len = fde_count * sizeof(struct table_entry) + / sizeof(unw_word_t); + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } + +#ifndef NO_LIBUNWIND_DEBUG_FRAME + /* Check the .debug_frame section for unwinding info */ + if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { + memset(&di, 0, sizeof(di)); + dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name, + map->start, map->end); + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } +#endif - memset(&di, 0, sizeof(di)); - di.format = UNW_INFO_FORMAT_REMOTE_TABLE; - di.start_ip = map->start; - di.end_ip = map->end; - di.u.rti.segbase = map->start + segbase; - di.u.rti.table_data = map->start + table_data; - di.u.rti.table_len = fde_count * sizeof(struct table_entry) - / sizeof(unw_word_t); - return dwarf_search_unwind_table(as, ip, &di, pi, - need_unwind_info, arg); + return -EINVAL; } static int access_fpreg(unw_addr_space_t __maybe_unused as, diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index fe702076ca46..2bb8bf506681 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2,7 +2,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel turbo-capable processors. * - * Copyright (c) 2012 Intel Corporation. + * Copyright (c) 2013 Intel Corporation. * Len Brown <len.brown@intel.com> * * This program is free software; you can redistribute it and/or modify it @@ -47,6 +47,8 @@ unsigned int skip_c1; unsigned int do_nhm_cstates; unsigned int do_snb_cstates; unsigned int do_c8_c9_c10; +unsigned int do_slm_cstates; +unsigned int use_c1_residency_msr; unsigned int has_aperf; unsigned int has_epb; unsigned int units = 1000000000; /* Ghz etc */ @@ -81,6 +83,8 @@ double rapl_joule_counter_range; #define RAPL_DRAM (1 << 3) #define RAPL_PKG_PERF_STATUS (1 << 4) #define RAPL_DRAM_PERF_STATUS (1 << 5) +#define RAPL_PKG_POWER_INFO (1 << 6) +#define RAPL_CORE_POLICY (1 << 7) #define TJMAX_DEFAULT 100 #define MAX(a, b) ((a) > (b) ? (a) : (b)) @@ -96,7 +100,7 @@ struct thread_data { unsigned long long tsc; unsigned long long aperf; unsigned long long mperf; - unsigned long long c1; /* derived */ + unsigned long long c1; unsigned long long extra_msr64; unsigned long long extra_delta64; unsigned long long extra_msr32; @@ -266,7 +270,7 @@ void print_header(void) outp += sprintf(outp, " MSR 0x%03X", extra_msr_offset64); if (do_nhm_cstates) outp += sprintf(outp, " %%c1"); - if (do_nhm_cstates) + if (do_nhm_cstates && !do_slm_cstates) outp += sprintf(outp, " %%c3"); if (do_nhm_cstates) outp += sprintf(outp, " %%c6"); @@ -280,9 +284,9 @@ void print_header(void) if (do_snb_cstates) outp += sprintf(outp, " %%pc2"); - if (do_nhm_cstates) + if (do_nhm_cstates && !do_slm_cstates) outp += sprintf(outp, " %%pc3"); - if (do_nhm_cstates) + if (do_nhm_cstates && !do_slm_cstates) outp += sprintf(outp, " %%pc6"); if (do_snb_cstates) outp += sprintf(outp, " %%pc7"); @@ -480,7 +484,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (do_nhm_cstates) + if (do_nhm_cstates && !do_slm_cstates) outp += sprintf(outp, " %6.2f", 100.0 * c->c3/t->tsc); if (do_nhm_cstates) outp += sprintf(outp, " %6.2f", 100.0 * c->c6/t->tsc); @@ -499,9 +503,9 @@ int format_counters(struct thread_data *t, struct core_data *c, if (do_snb_cstates) outp += sprintf(outp, " %6.2f", 100.0 * p->pc2/t->tsc); - if (do_nhm_cstates) + if (do_nhm_cstates && !do_slm_cstates) outp += sprintf(outp, " %6.2f", 100.0 * p->pc3/t->tsc); - if (do_nhm_cstates) + if (do_nhm_cstates && !do_slm_cstates) outp += sprintf(outp, " %6.2f", 100.0 * p->pc6/t->tsc); if (do_snb_cstates) outp += sprintf(outp, " %6.2f", 100.0 * p->pc7/t->tsc); @@ -648,17 +652,24 @@ delta_thread(struct thread_data *new, struct thread_data *old, } - /* - * As counter collection is not atomic, - * it is possible for mperf's non-halted cycles + idle states - * to exceed TSC's all cycles: show c1 = 0% in that case. - */ - if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc) - old->c1 = 0; - else { - /* normal case, derive c1 */ - old->c1 = old->tsc - old->mperf - core_delta->c3 + if (use_c1_residency_msr) { + /* + * Some models have a dedicated C1 residency MSR, + * which should be more accurate than the derivation below. + */ + } else { + /* + * As counter collection is not atomic, + * it is possible for mperf's non-halted cycles + idle states + * to exceed TSC's all cycles: show c1 = 0% in that case. + */ + if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc) + old->c1 = 0; + else { + /* normal case, derive c1 */ + old->c1 = old->tsc - old->mperf - core_delta->c3 - core_delta->c6 - core_delta->c7; + } } if (old->mperf == 0) { @@ -872,13 +883,21 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, extra_msr_offset64, &t->extra_msr64)) return -5; + if (use_c1_residency_msr) { + if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1)) + return -6; + } + /* collect core counters only for 1st thread in core */ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) return 0; - if (do_nhm_cstates) { + if (do_nhm_cstates && !do_slm_cstates) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; + } + + if (do_nhm_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; } @@ -898,7 +917,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - if (do_nhm_cstates) { + if (do_nhm_cstates && !do_slm_cstates) { if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3)) return -9; if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6)) @@ -1046,25 +1065,28 @@ print_nhm_turbo_ratio_limits: switch(msr & 0x7) { case 0: - fprintf(stderr, "pc0"); + fprintf(stderr, do_slm_cstates ? "no pkg states" : "pc0"); break; case 1: - fprintf(stderr, do_snb_cstates ? "pc2" : "pc0"); + fprintf(stderr, do_slm_cstates ? "no pkg states" : do_snb_cstates ? "pc2" : "pc0"); break; case 2: - fprintf(stderr, do_snb_cstates ? "pc6-noret" : "pc3"); + fprintf(stderr, do_slm_cstates ? "invalid" : do_snb_cstates ? "pc6-noret" : "pc3"); break; case 3: - fprintf(stderr, "pc6"); + fprintf(stderr, do_slm_cstates ? "invalid" : "pc6"); break; case 4: - fprintf(stderr, "pc7"); + fprintf(stderr, do_slm_cstates ? "pc4" : "pc7"); break; case 5: - fprintf(stderr, do_snb_cstates ? "pc7s" : "invalid"); + fprintf(stderr, do_slm_cstates ? "invalid" : do_snb_cstates ? "pc7s" : "invalid"); + break; + case 6: + fprintf(stderr, do_slm_cstates ? "pc6" : "invalid"); break; case 7: - fprintf(stderr, "unlimited"); + fprintf(stderr, do_slm_cstates ? "pc7" : "unlimited"); break; default: fprintf(stderr, "invalid"); @@ -1460,6 +1482,7 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) case 0x3F: /* HSW */ case 0x45: /* HSW */ case 0x46: /* HSW */ + case 0x4D: /* AVN */ return 1; case 0x2E: /* Nehalem-EX Xeon - Beckton */ case 0x2F: /* Westmere-EX Xeon - Eagleton */ @@ -1555,11 +1578,14 @@ void rapl_probe(unsigned int family, unsigned int model) case 0x3F: /* HSW */ case 0x45: /* HSW */ case 0x46: /* HSW */ - do_rapl = RAPL_PKG | RAPL_CORES | RAPL_GFX; + do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO; break; case 0x2D: case 0x3E: - do_rapl = RAPL_PKG | RAPL_CORES | RAPL_DRAM | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS; + do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO; + break; + case 0x4D: /* AVN */ + do_rapl = RAPL_PKG | RAPL_CORES ; break; default: return; @@ -1573,17 +1599,18 @@ void rapl_probe(unsigned int family, unsigned int model) rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F)); rapl_time_units = 1.0 / (1 << (msr >> 16 & 0xF)); - /* get TDP to determine energy counter range */ - if (get_msr(0, MSR_PKG_POWER_INFO, &msr)) - return; + if (do_rapl & RAPL_PKG_POWER_INFO) { + /* get TDP to determine energy counter range */ + if (get_msr(0, MSR_PKG_POWER_INFO, &msr)) + return; - tdp = ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; + tdp = ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; - rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; - - if (verbose) - fprintf(stderr, "RAPL: %.0f sec. Joule Counter Range\n", rapl_joule_counter_range); + rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; + if (verbose) + fprintf(stderr, "RAPL: %.0f sec. Joule Counter Range\n", rapl_joule_counter_range); + } return; } @@ -1702,7 +1729,8 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) "(%f Watts, %f Joules, %f sec.)\n", cpu, msr, local_rapl_power_units, local_rapl_energy_units, local_rapl_time_units); } - if (do_rapl & RAPL_PKG) { + if (do_rapl & RAPL_PKG_POWER_INFO) { + if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr)) return -5; @@ -1714,6 +1742,9 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) ((msr >> 32) & RAPL_POWER_GRANULARITY) * rapl_power_units, ((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units); + } + if (do_rapl & RAPL_PKG) { + if (get_msr(cpu, MSR_PKG_POWER_LIMIT, &msr)) return -9; @@ -1749,12 +1780,16 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) print_power_limit_msr(cpu, msr, "DRAM Limit"); } - if (do_rapl & RAPL_CORES) { + if (do_rapl & RAPL_CORE_POLICY) { if (verbose) { if (get_msr(cpu, MSR_PP0_POLICY, &msr)) return -7; fprintf(stderr, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF); + } + } + if (do_rapl & RAPL_CORES) { + if (verbose) { if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr)) return -9; @@ -1813,10 +1848,47 @@ int has_c8_c9_c10(unsigned int family, unsigned int model) } +int is_slm(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + switch (model) { + case 0x4D: /* AVN */ + return 1; + } + return 0; +} + +#define SLM_BCLK_FREQS 5 +double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0}; + +double slm_bclk(void) +{ + unsigned long long msr = 3; + unsigned int i; + double freq; + + if (get_msr(0, MSR_FSB_FREQ, &msr)) + fprintf(stderr, "SLM BCLK: unknown\n"); + + i = msr & 0xf; + if (i >= SLM_BCLK_FREQS) { + fprintf(stderr, "SLM BCLK[%d] invalid\n", i); + msr = 3; + } + freq = slm_freq_table[i]; + + fprintf(stderr, "SLM BCLK: %.1f Mhz\n", freq); + + return freq; +} + double discover_bclk(unsigned int family, unsigned int model) { if (is_snb(family, model)) return 100.00; + else if (is_slm(family, model)) + return slm_bclk(); else return 133.33; } @@ -1873,7 +1945,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk fprintf(stderr, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", cpu, msr, target_c_local); - if (target_c_local < 85 || target_c_local > 120) + if (target_c_local < 85 || target_c_local > 127) goto guess; tcc_activation_temp = target_c_local; @@ -1970,6 +2042,7 @@ void check_cpuid() do_smi = do_nhm_cstates; do_snb_cstates = is_snb(family, model); do_c8_c9_c10 = has_c8_c9_c10(family, model); + do_slm_cstates = is_slm(family, model); bclk = discover_bclk(family, model); do_nehalem_turbo_ratio_limit = has_nehalem_turbo_ratio_limit(family, model); @@ -2331,7 +2404,7 @@ int main(int argc, char **argv) cmdline(argc, argv); if (verbose) - fprintf(stderr, "turbostat v3.4 April 17, 2013" + fprintf(stderr, "turbostat v3.5 April 26, 2013" " - Len Brown <lenb@kernel.org>\n"); turbostat_init(); diff --git a/tools/testing/ktest/examples/crosstests.conf b/tools/testing/ktest/examples/crosstests.conf index 46736604c26c..a1203148dfa1 100644 --- a/tools/testing/ktest/examples/crosstests.conf +++ b/tools/testing/ktest/examples/crosstests.conf @@ -133,12 +133,6 @@ CROSS = frv-linux ARCH = frv GCC_VER = 4.5.1 -# h8300 - failed make defconfig?? -TEST_START IF ${RUN} == h8300 || ${DO_FAILED} -CROSS = h8300-elf -ARCH = h8300 -GCC_VER = 4.5.1 - # m68k fails with error? TEST_START IF ${RUN} == m68k || ${DO_DEFAULT} CROSS = m68k-linux diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 4fa655d68a81..41bd85559d4b 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -151,7 +151,7 @@ static int check_timer_create(int which) fflush(stdout); done = 0; - timer_create(which, NULL, &id); + err = timer_create(which, NULL, &id); if (err < 0) { perror("Can't create timer\n"); return -1; |