diff options
Diffstat (limited to 'tools/perf')
52 files changed, 706 insertions, 848 deletions
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index d240bb2e5b22..1e8e400b4493 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -18,6 +18,10 @@ OPTIONS --debug verbose # sets verbose = 1 --debug verbose=2 # sets verbose = 2 +--buildid-dir:: + Setup buildid cache directory. It has higher priority than + buildid.dir config file option. + DESCRIPTION ----------- Performance counters for Linux are a new kernel-based subsystem diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 344c4d3d0a4a..fbbfdc39271d 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -4,17 +4,37 @@ tools/lib/traceevent tools/lib/api tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h +tools/lib/util/find_next_bit.c tools/include/asm/bug.h +tools/include/asm-generic/bitops/arch_hweight.h +tools/include/asm-generic/bitops/atomic.h +tools/include/asm-generic/bitops/const_hweight.h +tools/include/asm-generic/bitops/__ffs.h +tools/include/asm-generic/bitops/__fls.h +tools/include/asm-generic/bitops/find.h +tools/include/asm-generic/bitops/fls64.h +tools/include/asm-generic/bitops/fls.h +tools/include/asm-generic/bitops/hweight.h +tools/include/asm-generic/bitops.h +tools/include/linux/bitops.h tools/include/linux/compiler.h -tools/include/linux/hash.h tools/include/linux/export.h +tools/include/linux/hash.h +tools/include/linux/log2.h tools/include/linux/types.h +include/asm-generic/bitops/arch_hweight.h +include/asm-generic/bitops/const_hweight.h +include/asm-generic/bitops/fls64.h +include/asm-generic/bitops/__fls.h +include/asm-generic/bitops/fls.h include/linux/const.h include/linux/perf_event.h include/linux/rbtree.h include/linux/list.h include/linux/hash.h include/linux/stringify.h +lib/find_next_bit.c +lib/hweight.c lib/rbtree.c include/linux/swab.h arch/*/include/asm/unistd*.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 478efa9b2364..aa6a50447c32 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -231,8 +231,19 @@ LIB_H += ../../include/uapi/linux/const.h LIB_H += ../include/linux/hash.h LIB_H += ../../include/linux/stringify.h LIB_H += util/include/linux/bitmap.h -LIB_H += util/include/linux/bitops.h +LIB_H += ../include/linux/bitops.h +LIB_H += ../include/asm-generic/bitops/arch_hweight.h +LIB_H += ../include/asm-generic/bitops/atomic.h +LIB_H += ../include/asm-generic/bitops/const_hweight.h +LIB_H += ../include/asm-generic/bitops/find.h +LIB_H += ../include/asm-generic/bitops/fls64.h +LIB_H += ../include/asm-generic/bitops/fls.h +LIB_H += ../include/asm-generic/bitops/__ffs.h +LIB_H += ../include/asm-generic/bitops/__fls.h +LIB_H += ../include/asm-generic/bitops/hweight.h +LIB_H += ../include/asm-generic/bitops.h LIB_H += ../include/linux/compiler.h +LIB_H += ../include/linux/log2.h LIB_H += util/include/linux/const.h LIB_H += util/include/linux/ctype.h LIB_H += util/include/linux/kernel.h @@ -247,7 +258,6 @@ LIB_H += util/include/linux/linkage.h LIB_H += util/include/asm/asm-offsets.h LIB_H += ../include/asm/bug.h LIB_H += util/include/asm/byteorder.h -LIB_H += util/include/asm/hweight.h LIB_H += util/include/asm/swab.h LIB_H += util/include/asm/system.h LIB_H += util/include/asm/uaccess.h @@ -335,6 +345,7 @@ LIB_OBJS += $(OUTPUT)util/event.o LIB_OBJS += $(OUTPUT)util/evlist.o LIB_OBJS += $(OUTPUT)util/evsel.o LIB_OBJS += $(OUTPUT)util/exec_cmd.o +LIB_OBJS += $(OUTPUT)util/find_next_bit.o LIB_OBJS += $(OUTPUT)util/help.o LIB_OBJS += $(OUTPUT)util/kallsyms.o LIB_OBJS += $(OUTPUT)util/levenshtein.o @@ -453,12 +464,13 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o # Benchmark modules BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o -ifeq ($(RAW_ARCH),x86_64) +ifeq ($(ARCH), x86) +ifeq ($(IS_64_BIT), 1) BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o endif +endif BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o -BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o BUILTIN_OBJS += $(OUTPUT)bench/futex-requeue.o @@ -735,6 +747,12 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< +$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $< diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3bb50eac5542..0c370f81e002 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -103,7 +103,7 @@ static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc) return NULL; } - result = dwarf_cfi_addrframe(cfi, pc, &frame); + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); if (result) { pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); return NULL; @@ -128,7 +128,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) return NULL; } - result = dwarf_cfi_addrframe(cfi, pc, &frame); + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); if (result) { pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); return NULL; @@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) * yet used) * -1 in case of errors */ -static int check_return_addr(struct dso *dso, Dwarf_Addr pc) +static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) { int rc = -1; Dwfl *dwfl; @@ -155,6 +155,7 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc) Dwarf_Addr start = pc; Dwarf_Addr end = pc; bool signalp; + const char *exec_file = dso->long_name; dwfl = dso->dwfl; @@ -165,8 +166,10 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc) return -1; } - if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) { - pr_debug("dwfl_report_offline() failed %s\n", + mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1, + map_start, false); + if (!mod) { + pr_debug("dwfl_report_elf() failed %s\n", dwarf_errmsg(-1)); /* * We normally cache the DWARF debug info and never @@ -256,10 +259,10 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) return skip_slot; } - rc = check_return_addr(dso, ip); + rc = check_return_addr(dso, al.map->start, ip); - pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n", - dso->long_name, chain->nr, ip, rc); + pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n", + dso->long_name, al.sym->name, ip, rc); if (rc == 0) { /* diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 2465141b554b..6c14afe8c1b1 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -13,6 +13,7 @@ #include "../util/cloexec.h" #include "bench.h" #include "mem-memcpy-arch.h" +#include "mem-memset-arch.h" #include <stdio.h> #include <stdlib.h> @@ -48,20 +49,24 @@ static const struct option options[] = { }; typedef void *(*memcpy_t)(void *, const void *, size_t); +typedef void *(*memset_t)(void *, int, size_t); struct routine { const char *name; const char *desc; - memcpy_t fn; + union { + memcpy_t memcpy; + memset_t memset; + } fn; }; -struct routine routines[] = { - { "default", - "Default memcpy() provided by glibc", - memcpy }, +struct routine memcpy_routines[] = { + { .name = "default", + .desc = "Default memcpy() provided by glibc", + .fn.memcpy = memcpy }, #ifdef HAVE_ARCH_X86_64_SUPPORT -#define MEMCPY_FN(fn, name, desc) { name, desc, fn }, +#define MEMCPY_FN(_fn, _name, _desc) {.name = _name, .desc = _desc, .fn.memcpy = _fn}, #include "mem-memcpy-x86-64-asm-def.h" #undef MEMCPY_FN @@ -69,7 +74,7 @@ struct routine routines[] = { { NULL, NULL, - NULL } + {NULL} } }; static const char * const bench_mem_memcpy_usage[] = { @@ -110,63 +115,6 @@ static double timeval2double(struct timeval *ts) (double)ts->tv_usec / (double)1000000; } -static void alloc_mem(void **dst, void **src, size_t length) -{ - *dst = zalloc(length); - if (!*dst) - die("memory allocation failed - maybe length is too large?\n"); - - *src = zalloc(length); - if (!*src) - die("memory allocation failed - maybe length is too large?\n"); - /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */ - memset(*src, 0, length); -} - -static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault) -{ - u64 cycle_start = 0ULL, cycle_end = 0ULL; - void *src = NULL, *dst = NULL; - int i; - - alloc_mem(&src, &dst, len); - - if (prefault) - fn(dst, src, len); - - cycle_start = get_cycle(); - for (i = 0; i < iterations; ++i) - fn(dst, src, len); - cycle_end = get_cycle(); - - free(src); - free(dst); - return cycle_end - cycle_start; -} - -static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) -{ - struct timeval tv_start, tv_end, tv_diff; - void *src = NULL, *dst = NULL; - int i; - - alloc_mem(&src, &dst, len); - - if (prefault) - fn(dst, src, len); - - BUG_ON(gettimeofday(&tv_start, NULL)); - for (i = 0; i < iterations; ++i) - fn(dst, src, len); - BUG_ON(gettimeofday(&tv_end, NULL)); - - timersub(&tv_end, &tv_start, &tv_diff); - - free(src); - free(dst); - return (double)((double)len / timeval2double(&tv_diff)); -} - #define pf (no_prefault ? 0 : 1) #define print_bps(x) do { \ @@ -180,16 +128,25 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) printf(" %14lf GB/Sec", x / K / K / K); \ } while (0) -int bench_mem_memcpy(int argc, const char **argv, - const char *prefix __maybe_unused) +struct bench_mem_info { + const struct routine *routines; + u64 (*do_cycle)(const struct routine *r, size_t len, bool prefault); + double (*do_gettimeofday)(const struct routine *r, size_t len, bool prefault); + const char *const *usage; +}; + +static int bench_mem_common(int argc, const char **argv, + const char *prefix __maybe_unused, + struct bench_mem_info *info) { int i; size_t len; + double totallen; double result_bps[2]; u64 result_cycle[2]; argc = parse_options(argc, argv, options, - bench_mem_memcpy_usage, 0); + info->usage, 0); if (no_prefault && only_prefault) { fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); @@ -200,6 +157,7 @@ int bench_mem_memcpy(int argc, const char **argv, init_cycle(); len = (size_t)perf_atoll((char *)length_str); + totallen = (double)len * iterations; result_cycle[0] = result_cycle[1] = 0ULL; result_bps[0] = result_bps[1] = 0.0; @@ -213,16 +171,16 @@ int bench_mem_memcpy(int argc, const char **argv, if (only_prefault && no_prefault) only_prefault = no_prefault = false; - for (i = 0; routines[i].name; i++) { - if (!strcmp(routines[i].name, routine)) + for (i = 0; info->routines[i].name; i++) { + if (!strcmp(info->routines[i].name, routine)) break; } - if (!routines[i].name) { + if (!info->routines[i].name) { printf("Unknown routine:%s\n", routine); printf("Available routines...\n"); - for (i = 0; routines[i].name; i++) { + for (i = 0; info->routines[i].name; i++) { printf("\t%s ... %s\n", - routines[i].name, routines[i].desc); + info->routines[i].name, info->routines[i].desc); } return 1; } @@ -234,25 +192,25 @@ int bench_mem_memcpy(int argc, const char **argv, /* show both of results */ if (use_cycle) { result_cycle[0] = - do_memcpy_cycle(routines[i].fn, len, false); + info->do_cycle(&info->routines[i], len, false); result_cycle[1] = - do_memcpy_cycle(routines[i].fn, len, true); + info->do_cycle(&info->routines[i], len, true); } else { result_bps[0] = - do_memcpy_gettimeofday(routines[i].fn, + info->do_gettimeofday(&info->routines[i], len, false); result_bps[1] = - do_memcpy_gettimeofday(routines[i].fn, + info->do_gettimeofday(&info->routines[i], len, true); } } else { if (use_cycle) { result_cycle[pf] = - do_memcpy_cycle(routines[i].fn, + info->do_cycle(&info->routines[i], len, only_prefault); } else { result_bps[pf] = - do_memcpy_gettimeofday(routines[i].fn, + info->do_gettimeofday(&info->routines[i], len, only_prefault); } } @@ -263,10 +221,10 @@ int bench_mem_memcpy(int argc, const char **argv, if (use_cycle) { printf(" %14lf Cycle/Byte\n", (double)result_cycle[0] - / (double)len); + / totallen); printf(" %14lf Cycle/Byte (with prefault)\n", (double)result_cycle[1] - / (double)len); + / totallen); } else { print_bps(result_bps[0]); printf("\n"); @@ -277,7 +235,7 @@ int bench_mem_memcpy(int argc, const char **argv, if (use_cycle) { printf(" %14lf Cycle/Byte", (double)result_cycle[pf] - / (double)len); + / totallen); } else print_bps(result_bps[pf]); @@ -288,8 +246,8 @@ int bench_mem_memcpy(int argc, const char **argv, if (!only_prefault && !no_prefault) { if (use_cycle) { printf("%lf %lf\n", - (double)result_cycle[0] / (double)len, - (double)result_cycle[1] / (double)len); + (double)result_cycle[0] / totallen, + (double)result_cycle[1] / totallen); } else { printf("%lf %lf\n", result_bps[0], result_bps[1]); @@ -297,7 +255,7 @@ int bench_mem_memcpy(int argc, const char **argv, } else { if (use_cycle) { printf("%lf\n", (double)result_cycle[pf] - / (double)len); + / totallen); } else printf("%lf\n", result_bps[pf]); } @@ -310,3 +268,163 @@ int bench_mem_memcpy(int argc, const char **argv, return 0; } + +static void memcpy_alloc_mem(void **dst, void **src, size_t length) +{ + *dst = zalloc(length); + if (!*dst) + die("memory allocation failed - maybe length is too large?\n"); + + *src = zalloc(length); + if (!*src) + die("memory allocation failed - maybe length is too large?\n"); + /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */ + memset(*src, 0, length); +} + +static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault) +{ + u64 cycle_start = 0ULL, cycle_end = 0ULL; + void *src = NULL, *dst = NULL; + memcpy_t fn = r->fn.memcpy; + int i; + + memcpy_alloc_mem(&src, &dst, len); + + if (prefault) + fn(dst, src, len); + + cycle_start = get_cycle(); + for (i = 0; i < iterations; ++i) + fn(dst, src, len); + cycle_end = get_cycle(); + + free(src); + free(dst); + return cycle_end - cycle_start; +} + +static double do_memcpy_gettimeofday(const struct routine *r, size_t len, + bool prefault) +{ + struct timeval tv_start, tv_end, tv_diff; + memcpy_t fn = r->fn.memcpy; + void *src = NULL, *dst = NULL; + int i; + + memcpy_alloc_mem(&src, &dst, len); + + if (prefault) + fn(dst, src, len); + + BUG_ON(gettimeofday(&tv_start, NULL)); + for (i = 0; i < iterations; ++i) + fn(dst, src, len); + BUG_ON(gettimeofday(&tv_end, NULL)); + + timersub(&tv_end, &tv_start, &tv_diff); + + free(src); + free(dst); + return (double)(((double)len * iterations) / timeval2double(&tv_diff)); +} + +int bench_mem_memcpy(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + struct bench_mem_info info = { + .routines = memcpy_routines, + .do_cycle = do_memcpy_cycle, + .do_gettimeofday = do_memcpy_gettimeofday, + .usage = bench_mem_memcpy_usage, + }; + + return bench_mem_common(argc, argv, prefix, &info); +} + +static void memset_alloc_mem(void **dst, size_t length) +{ + *dst = zalloc(length); + if (!*dst) + die("memory allocation failed - maybe length is too large?\n"); +} + +static u64 do_memset_cycle(const struct routine *r, size_t len, bool prefault) +{ + u64 cycle_start = 0ULL, cycle_end = 0ULL; + memset_t fn = r->fn.memset; + void *dst = NULL; + int i; + + memset_alloc_mem(&dst, len); + + if (prefault) + fn(dst, -1, len); + + cycle_start = get_cycle(); + for (i = 0; i < iterations; ++i) + fn(dst, i, len); + cycle_end = get_cycle(); + + free(dst); + return cycle_end - cycle_start; +} + +static double do_memset_gettimeofday(const struct routine *r, size_t len, + bool prefault) +{ + struct timeval tv_start, tv_end, tv_diff; + memset_t fn = r->fn.memset; + void *dst = NULL; + int i; + + memset_alloc_mem(&dst, len); + + if (prefault) + fn(dst, -1, len); + + BUG_ON(gettimeofday(&tv_start, NULL)); + for (i = 0; i < iterations; ++i) + fn(dst, i, len); + BUG_ON(gettimeofday(&tv_end, NULL)); + + timersub(&tv_end, &tv_start, &tv_diff); + + free(dst); + return (double)(((double)len * iterations) / timeval2double(&tv_diff)); +} + +static const char * const bench_mem_memset_usage[] = { + "perf bench mem memset <options>", + NULL +}; + +static const struct routine memset_routines[] = { + { .name ="default", + .desc = "Default memset() provided by glibc", + .fn.memset = memset }, +#ifdef HAVE_ARCH_X86_64_SUPPORT + +#define MEMSET_FN(_fn, _name, _desc) { .name = _name, .desc = _desc, .fn.memset = _fn }, +#include "mem-memset-x86-64-asm-def.h" +#undef MEMSET_FN + +#endif + + { .name = NULL, + .desc = NULL, + .fn.memset = NULL } +}; + +int bench_mem_memset(int argc, const char **argv, + const char *prefix __maybe_unused) +{ + struct bench_mem_info info = { + .routines = memset_routines, + .do_cycle = do_memset_cycle, + .do_gettimeofday = do_memset_gettimeofday, + .usage = bench_mem_memset_usage, + }; + + return bench_mem_common(argc, argv, prefix, &info); +} diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c deleted file mode 100644 index 75fc3e65fb2a..000000000000 --- a/tools/perf/bench/mem-memset.c +++ /dev/null @@ -1,304 +0,0 @@ -/* - * mem-memset.c - * - * memset: Simple memory set in various ways - * - * Trivial clone of mem-memcpy.c. - */ - -#include "../perf.h" -#include "../util/util.h" -#include "../util/parse-options.h" -#include "../util/header.h" -#include "../util/cloexec.h" -#include "bench.h" -#include "mem-memset-arch.h" - -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/time.h> -#include <errno.h> - -#define K 1024 - -static const char *length_str = "1MB"; -static const char *routine = "default"; -static int iterations = 1; -static bool use_cycle; -static int cycle_fd; -static bool only_prefault; -static bool no_prefault; - -static const struct option options[] = { - OPT_STRING('l', "length", &length_str, "1MB", - "Specify length of memory to set. " - "Available units: B, KB, MB, GB and TB (upper and lower)"), - OPT_STRING('r', "routine", &routine, "default", - "Specify routine to set"), - OPT_INTEGER('i', "iterations", &iterations, - "repeat memset() invocation this number of times"), - OPT_BOOLEAN('c', "cycle", &use_cycle, - "Use cycles event instead of gettimeofday() for measuring"), - OPT_BOOLEAN('o', "only-prefault", &only_prefault, - "Show only the result with page faults before memset()"), - OPT_BOOLEAN('n', "no-prefault", &no_prefault, - "Show only the result without page faults before memset()"), - OPT_END() -}; - -typedef void *(*memset_t)(void *, int, size_t); - -struct routine { - const char *name; - const char *desc; - memset_t fn; -}; - -static const struct routine routines[] = { - { "default", - "Default memset() provided by glibc", - memset }, -#ifdef HAVE_ARCH_X86_64_SUPPORT - -#define MEMSET_FN(fn, name, desc) { name, desc, fn }, -#include "mem-memset-x86-64-asm-def.h" -#undef MEMSET_FN - -#endif - - { NULL, - NULL, - NULL } -}; - -static const char * const bench_mem_memset_usage[] = { - "perf bench mem memset <options>", - NULL -}; - -static struct perf_event_attr cycle_attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES -}; - -static void init_cycle(void) -{ - cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, - perf_event_open_cloexec_flag()); - - if (cycle_fd < 0 && errno == ENOSYS) - die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - else - BUG_ON(cycle_fd < 0); -} - -static u64 get_cycle(void) -{ - int ret; - u64 clk; - - ret = read(cycle_fd, &clk, sizeof(u64)); - BUG_ON(ret != sizeof(u64)); - - return clk; -} - -static double timeval2double(struct timeval *ts) -{ - return (double)ts->tv_sec + - (double)ts->tv_usec / (double)1000000; -} - -static void alloc_mem(void **dst, size_t length) -{ - *dst = zalloc(length); - if (!*dst) - die("memory allocation failed - maybe length is too large?\n"); -} - -static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault) -{ - u64 cycle_start = 0ULL, cycle_end = 0ULL; - void *dst = NULL; - int i; - - alloc_mem(&dst, len); - - if (prefault) - fn(dst, -1, len); - - cycle_start = get_cycle(); - for (i = 0; i < iterations; ++i) - fn(dst, i, len); - cycle_end = get_cycle(); - - free(dst); - return cycle_end - cycle_start; -} - -static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) -{ - struct timeval tv_start, tv_end, tv_diff; - void *dst = NULL; - int i; - - alloc_mem(&dst, len); - - if (prefault) - fn(dst, -1, len); - - BUG_ON(gettimeofday(&tv_start, NULL)); - for (i = 0; i < iterations; ++i) - fn(dst, i, len); - BUG_ON(gettimeofday(&tv_end, NULL)); - - timersub(&tv_end, &tv_start, &tv_diff); - - free(dst); - return (double)((double)len / timeval2double(&tv_diff)); -} - -#define pf (no_prefault ? 0 : 1) - -#define print_bps(x) do { \ - if (x < K) \ - printf(" %14lf B/Sec", x); \ - else if (x < K * K) \ - printf(" %14lfd KB/Sec", x / K); \ - else if (x < K * K * K) \ - printf(" %14lf MB/Sec", x / K / K); \ - else \ - printf(" %14lf GB/Sec", x / K / K / K); \ - } while (0) - -int bench_mem_memset(int argc, const char **argv, - const char *prefix __maybe_unused) -{ - int i; - size_t len; - double result_bps[2]; - u64 result_cycle[2]; - - argc = parse_options(argc, argv, options, - bench_mem_memset_usage, 0); - - if (no_prefault && only_prefault) { - fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n"); - return 1; - } - - if (use_cycle) - init_cycle(); - - len = (size_t)perf_atoll((char *)length_str); - - result_cycle[0] = result_cycle[1] = 0ULL; - result_bps[0] = result_bps[1] = 0.0; - - if ((s64)len <= 0) { - fprintf(stderr, "Invalid length:%s\n", length_str); - return 1; - } - - /* same to without specifying either of prefault and no-prefault */ - if (only_prefault && no_prefault) - only_prefault = no_prefault = false; - - for (i = 0; routines[i].name; i++) { - if (!strcmp(routines[i].name, routine)) - break; - } - if (!routines[i].name) { - printf("Unknown routine:%s\n", routine); - printf("Available routines...\n"); - for (i = 0; routines[i].name; i++) { - printf("\t%s ... %s\n", - routines[i].name, routines[i].desc); - } - return 1; - } - - if (bench_format == BENCH_FORMAT_DEFAULT) - printf("# Copying %s Bytes ...\n\n", length_str); - - if (!only_prefault && !no_prefault) { - /* show both of results */ - if (use_cycle) { - result_cycle[0] = - do_memset_cycle(routines[i].fn, len, false); - result_cycle[1] = - do_memset_cycle(routines[i].fn, len, true); - } else { - result_bps[0] = - do_memset_gettimeofday(routines[i].fn, - len, false); - result_bps[1] = - do_memset_gettimeofday(routines[i].fn, - len, true); - } - } else { - if (use_cycle) { - result_cycle[pf] = - do_memset_cycle(routines[i].fn, - len, only_prefault); - } else { - result_bps[pf] = - do_memset_gettimeofday(routines[i].fn, - len, only_prefault); - } - } - - switch (bench_format) { - case BENCH_FORMAT_DEFAULT: - if (!only_prefault && !no_prefault) { - if (use_cycle) { - printf(" %14lf Cycle/Byte\n", - (double)result_cycle[0] - / (double)len); - printf(" %14lf Cycle/Byte (with prefault)\n ", - (double)result_cycle[1] - / (double)len); - } else { - print_bps(result_bps[0]); - printf("\n"); - print_bps(result_bps[1]); - printf(" (with prefault)\n"); - } - } else { - if (use_cycle) { - printf(" %14lf Cycle/Byte", - (double)result_cycle[pf] - / (double)len); - } else - print_bps(result_bps[pf]); - - printf("%s\n", only_prefault ? " (with prefault)" : ""); - } - break; - case BENCH_FORMAT_SIMPLE: - if (!only_prefault && !no_prefault) { - if (use_cycle) { - printf("%lf %lf\n", - (double)result_cycle[0] / (double)len, - (double)result_cycle[1] / (double)len); - } else { - printf("%lf %lf\n", - result_bps[0], result_bps[1]); - } - } else { - if (use_cycle) { - printf("%lf\n", (double)result_cycle[pf] - / (double)len); - } else - printf("%lf\n", result_bps[pf]); - } - break; - default: - /* reaching this means there's some disaster: */ - die("unknown format: %d\n", bench_format); - break; - } - - return 0; -} diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 07a8d7646a15..005cc283790c 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -19,12 +19,12 @@ #include <stdlib.h> #include <signal.h> #include <sys/wait.h> -#include <linux/unistd.h> #include <string.h> #include <errno.h> #include <assert.h> #include <sys/time.h> #include <sys/types.h> +#include <sys/syscall.h> #include <pthread.h> diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index e7417fe97a97..747f86103599 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann) if (nr_samples > 0) { total_nr_samples += nr_samples; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (symbol_conf.event_group && !perf_evsel__is_group_leader(pos)) diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 70385756da63..77d5cae54c6a 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -285,12 +285,11 @@ int cmd_buildid_cache(int argc, const char **argv, struct str_node *pos; int ret = 0; bool force = false; - char debugdir[PATH_MAX]; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, - *kcore_filename; + *kcore_filename = NULL; char sbuf[STRERR_BUFSIZE]; struct perf_data_file file = { @@ -335,13 +334,11 @@ int cmd_buildid_cache(int argc, const char **argv, setup_pager(); - snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); - if (add_name_list_str) { list = strlist__new(true, add_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__add_file(pos->s, debugdir)) { + if (build_id_cache__add_file(pos->s, buildid_dir)) { if (errno == EEXIST) { pr_debug("%s already in the cache\n", pos->s); @@ -359,7 +356,7 @@ int cmd_buildid_cache(int argc, const char **argv, list = strlist__new(true, remove_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__remove_file(pos->s, debugdir)) { + if (build_id_cache__remove_file(pos->s, buildid_dir)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -380,7 +377,7 @@ int cmd_buildid_cache(int argc, const char **argv, list = strlist__new(true, update_name_list_str); if (list) { strlist__for_each(pos, list) - if (build_id_cache__update_file(pos->s, debugdir)) { + if (build_id_cache__update_file(pos->s, buildid_dir)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -395,7 +392,7 @@ int cmd_buildid_cache(int argc, const char **argv, } if (kcore_filename && - build_id_cache__add_kcore(kcore_filename, debugdir, force)) + build_id_cache__add_kcore(kcore_filename, buildid_dir, force)) pr_warning("Couldn't add %s\n", kcore_filename); out: diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 1ce425d101a9..1fd96c13f199 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -545,6 +545,42 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, return __hist_entry__cmp_compute(p_left, p_right, c); } +static int64_t +hist_entry__cmp_nop(struct hist_entry *left __maybe_unused, + struct hist_entry *right __maybe_unused) +{ + return 0; +} + +static int64_t +hist_entry__cmp_baseline(struct hist_entry *left, struct hist_entry *right) +{ + if (sort_compute) + return 0; + + if (left->stat.period == right->stat.period) + return 0; + return left->stat.period > right->stat.period ? 1 : -1; +} + +static int64_t +hist_entry__cmp_delta(struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute(right, left, COMPUTE_DELTA); +} + +static int64_t +hist_entry__cmp_ratio(struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute(right, left, COMPUTE_RATIO); +} + +static int64_t +hist_entry__cmp_wdiff(struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF); +} + static void insert_hist_entry_by_compute(struct rb_root *root, struct hist_entry *he, int c) @@ -605,7 +641,7 @@ static void hists__process(struct hists *hists) hists__precompute(hists); hists__compute_resort(hists); } else { - hists__output_resort(hists); + hists__output_resort(hists, NULL); } hists__fprintf(hists, true, 0, 0, 0, stdout); @@ -1038,27 +1074,35 @@ static void data__hpp_register(struct data__file *d, int idx) fmt->header = hpp__header; fmt->width = hpp__width; fmt->entry = hpp__entry_global; + fmt->cmp = hist_entry__cmp_nop; + fmt->collapse = hist_entry__cmp_nop; /* TODO more colors */ switch (idx) { case PERF_HPP_DIFF__BASELINE: fmt->color = hpp__color_baseline; + fmt->sort = hist_entry__cmp_baseline; break; case PERF_HPP_DIFF__DELTA: fmt->color = hpp__color_delta; + fmt->sort = hist_entry__cmp_delta; break; case PERF_HPP_DIFF__RATIO: fmt->color = hpp__color_ratio; + fmt->sort = hist_entry__cmp_ratio; break; case PERF_HPP_DIFF__WEIGHTED_DIFF: fmt->color = hpp__color_wdiff; + fmt->sort = hist_entry__cmp_wdiff; break; default: + fmt->sort = hist_entry__cmp_nop; break; } init_header(d, dfmt); perf_hpp__column_register(fmt); + perf_hpp__register_sort_field(fmt); } static void ui_init(void) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 3c0f3d4fb021..0894a817f67e 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1293,7 +1293,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, OPT_UINTEGER('d', "display", &kvm->display_time, "time in seconds between display updates"), OPT_STRING(0, "event", &kvm->report_event, "report event", - "event for reporting: vmexit, mmio, ioport"), + "event for reporting: " + "vmexit, mmio (x86 only), ioport (x86 only)"), OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu, "vcpu id to report"), OPT_STRING('k', "key", &kvm->sort_key, "sort-key", diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 011195e38f21..198f3c3aff95 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -19,7 +19,9 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) { int i; - const struct option list_options[] = { + bool raw_dump = false; + struct option list_options[] = { + OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"), OPT_END() }; const char * const list_usage[] = { @@ -27,11 +29,18 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; + set_option_flag(list_options, 0, "raw-dump", PARSE_OPT_HIDDEN); + argc = parse_options(argc, argv, list_options, list_usage, PARSE_OPT_STOP_AT_NON_OPTION); setup_pager(); + if (raw_dump) { + print_events(NULL, true); + return 0; + } + if (argc == 0) { print_events(NULL, false); return 0; @@ -53,8 +62,6 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) print_hwcache_events(NULL, false); else if (strcmp(argv[i], "pmu") == 0) print_pmu_events(NULL, false); - else if (strcmp(argv[i], "--raw-dump") == 0) - print_events(NULL, true); else { char *sep = strchr(argv[i], ':'), *s; int sep_idx; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 39367609c707..072ae8ad67fc 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -457,6 +457,19 @@ static void report__collapse_hists(struct report *rep) ui_progress__finish(); } +static void report__output_resort(struct report *rep) +{ + struct ui_progress prog; + struct perf_evsel *pos; + + ui_progress__init(&prog, rep->nr_entries, "Sorting events for output..."); + + evlist__for_each(rep->session->evlist, pos) + hists__output_resort(evsel__hists(pos), &prog); + + ui_progress__finish(); +} + static int __cmd_report(struct report *rep) { int ret; @@ -505,13 +518,20 @@ static int __cmd_report(struct report *rep) if (session_done()) return 0; + /* + * recalculate number of entries after collapsing since it + * might be changed during the collapse phase. + */ + rep->nr_entries = 0; + evlist__for_each(session->evlist, pos) + rep->nr_entries += evsel__hists(pos)->nr_entries; + if (rep->nr_entries == 0) { ui__error("The %s file has no samples!\n", file->path); return 0; } - evlist__for_each(session->evlist, pos) - hists__output_resort(evsel__hists(pos)); + report__output_resort(rep); return report__browse_hists(rep); } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 0aa7747ff139..616f0fcb4701 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -66,7 +66,6 @@ #include <sys/utsname.h> #include <sys/mman.h> -#include <linux/unistd.h> #include <linux/types.h> static volatile int done; @@ -285,7 +284,7 @@ static void perf_top__print_sym_table(struct perf_top *top) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); @@ -554,7 +553,7 @@ static void perf_top__sort_new_samples(void *arg) } hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); } static void *display_thread_tui(void *arg) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 83a4835c8118..badfabc6a01f 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2045,7 +2045,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv) unsigned long before; const bool forks = argc > 0; bool draining = false; - char sbuf[STRERR_BUFSIZE]; trace->live = true; @@ -2106,11 +2105,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_error_open; err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false); - if (err < 0) { - fprintf(trace->output, "Couldn't mmap the events: %s\n", - strerror_r(errno, sbuf, sizeof(sbuf))); - goto out_delete_evlist; - } + if (err < 0) + goto out_error_mmap; perf_evlist__enable(evlist); @@ -2210,6 +2206,10 @@ out_error_tp: perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf)); goto out_error; +out_error_mmap: + perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf)); + goto out_error; + out_error_open: perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); @@ -2485,7 +2485,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, .no_buffering = true, - .mmap_pages = 1024, + .mmap_pages = UINT_MAX, }, .output = stdout, .show_comm = true, diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 5d4b039fe1ed..648e31ff4021 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -20,7 +20,7 @@ NO_PERF_REGS := 1 # Additional ARCH settings for x86 ifeq ($(ARCH),x86) - ifeq (${IS_X86_64}, 1) + ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch index 851cd0172a76..ff95a68741d1 100644 --- a/tools/perf/config/Makefile.arch +++ b/tools/perf/config/Makefile.arch @@ -1,7 +1,7 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ +RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ @@ -9,23 +9,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/tile.*/tile/ ) # Additional ARCH settings for x86 -ifeq ($(ARCH),i386) - override ARCH := x86 +ifeq ($(RAW_ARCH),i386) + ARCH ?= x86 endif -ifeq ($(ARCH),x86_64) - override ARCH := x86 - IS_X86_64 := 0 - ifeq (, $(findstring m32,$(CFLAGS))) - IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1) - RAW_ARCH := x86_64 +ifeq ($(RAW_ARCH),x86_64) + ARCH ?= x86 + + ifneq (, $(findstring m32,$(CFLAGS))) + RAW_ARCH := x86_32 endif endif -ifeq (${IS_X86_64}, 1) +ARCH ?= $(RAW_ARCH) + +LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) +ifeq ($(LP64), 1) IS_64_BIT := 1 -else ifeq ($(ARCH),x86) - IS_64_BIT := 0 else - IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) + IS_64_BIT := 0 endif diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index a3b13d7dc1d4..6ef68165c9db 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -6,7 +6,6 @@ #include <sys/syscall.h> #include <linux/types.h> #include <linux/perf_event.h> -#include <asm/unistd.h> #if defined(__i386__) #define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 452a8474d29d..3700a7faca6c 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -200,6 +200,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) *envchanged = 1; (*argv)++; (*argc)--; + } else if (!strcmp(cmd, "--buildid-dir")) { + if (*argc < 2) { + fprintf(stderr, "No directory given for --buildid-dir.\n"); + usage(perf_usage_string); + } + set_buildid_dir((*argv)[1]); + if (envchanged) + *envchanged = 1; + (*argv)++; + (*argc)--; } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) { perf_debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR)); fprintf(stderr, "dir: %s\n", debugfs_mountpoint); @@ -499,7 +509,7 @@ int main(int argc, const char **argv) } if (!prefixcmp(cmd, "trace")) { #ifdef HAVE_LIBAUDIT_SUPPORT - set_buildid_dir(); + set_buildid_dir(NULL); setup_path(); argv[0] = "trace"; return cmd_trace(argc, argv, NULL); @@ -514,7 +524,7 @@ int main(int argc, const char **argv) argc--; handle_options(&argv, &argc, NULL); commit_pager_choice(); - set_buildid_dir(); + set_buildid_dir(NULL); if (argc > 0) { if (!prefixcmp(argv[0], "--")) diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index f710b92ccff6..d3095dafed36 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0|1 -size=96 +size=104 config=0 sample_period=4000 sample_type=263 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index dc3ada2470c0..872ed7e24c7c 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0 -size=96 +size=104 config=0 sample_period=0 sample_type=0 diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index ab28cca2cb97..0bf06bec68c7 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -11,6 +11,9 @@ #include "thread.h" #include "callchain.h" +/* For bsearch. We try to unwind functions in shared object. */ +#include <stdlib.h> + static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -28,7 +31,7 @@ static int init_live_machine(struct machine *machine) mmap_handler, machine, true); } -#define MAX_STACK 6 +#define MAX_STACK 8 static int unwind_entry(struct unwind_entry *entry, void *arg) { @@ -37,6 +40,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) static const char *funcs[MAX_STACK] = { "test__arch_unwind_sample", "unwind_thread", + "compare", + "bsearch", "krava_3", "krava_2", "krava_1", @@ -88,10 +93,37 @@ static int unwind_thread(struct thread *thread) return err; } +static int global_unwind_retval = -INT_MAX; + +__attribute__ ((noinline)) +static int compare(void *p1, void *p2) +{ + /* Any possible value should be 'thread' */ + struct thread *thread = *(struct thread **)p1; + + if (global_unwind_retval == -INT_MAX) + global_unwind_retval = unwind_thread(thread); + + return p1 - p2; +} + __attribute__ ((noinline)) static int krava_3(struct thread *thread) { - return unwind_thread(thread); + struct thread *array[2] = {thread, thread}; + void *fp = &bsearch; + /* + * make _bsearch a volatile function pointer to + * prevent potential optimization, which may expand + * bsearch and call compare directly from this function, + * instead of libc shared object. + */ + void *(*volatile _bsearch)(void *, void *, size_t, + size_t, int (*)(void *, void *)); + + _bsearch = fp; + _bsearch(array, &thread, 2, sizeof(struct thread **), compare); + return global_unwind_retval; } __attribute__ ((noinline)) diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 614d5c4978ab..8d110dec393e 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -187,7 +187,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec * function since TEST_ASSERT_VAL() returns in case of failure. */ hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("use callchain: %d, cumulate callchain: %d\n", @@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) * 30.00% 10.00% perf perf [.] cmd_record * 20.00% 0.00% bash libc [.] malloc * 10.00% 10.00% bash [kernel] [k] page_fault - * 10.00% 10.00% perf [kernel] [k] schedule - * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open + * 10.00% 10.00% bash bash [.] xmalloc * 10.00% 10.00% perf [kernel] [k] page_fault - * 10.00% 10.00% perf libc [.] free * 10.00% 10.00% perf libc [.] malloc - * 10.00% 10.00% bash bash [.] xmalloc + * 10.00% 10.00% perf [kernel] [k] schedule + * 10.00% 10.00% perf libc [.] free + * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open */ struct result expected[] = { { 7000, 2000, "perf", "perf", "main" }, @@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) { 3000, 1000, "perf", "perf", "cmd_record" }, { 2000, 0, "bash", "libc", "malloc" }, { 1000, 1000, "bash", "[kernel]", "page_fault" }, - { 1000, 1000, "perf", "[kernel]", "schedule" }, - { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, + { 1000, 1000, "bash", "bash", "xmalloc" }, { 1000, 1000, "perf", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "[kernel]", "schedule" }, { 1000, 1000, "perf", "libc", "free" }, { 1000, 1000, "perf", "libc", "malloc" }, - { 1000, 1000, "bash", "bash", "xmalloc" }, + { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, }; symbol_conf.use_callchain = false; @@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) * malloc * main * - * 10.00% 10.00% perf [kernel] [k] schedule + * 10.00% 10.00% bash bash [.] xmalloc * | - * --- schedule - * run_command + * --- xmalloc + * malloc + * xmalloc <--- NOTE: there's a cycle + * malloc + * xmalloc * main * * 10.00% 0.00% perf [kernel] [k] sys_perf_event_open @@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) * run_command * main * + * 10.00% 10.00% perf [kernel] [k] schedule + * | + * --- schedule + * run_command + * main + * * 10.00% 10.00% perf libc [.] free * | * --- free @@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) * run_command * main * - * 10.00% 10.00% bash bash [.] xmalloc - * | - * --- xmalloc - * malloc - * xmalloc <--- NOTE: there's a cycle - * malloc - * xmalloc - * main - * */ struct result expected[] = { { 7000, 2000, "perf", "perf", "main" }, @@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { 3000, 1000, "perf", "perf", "cmd_record" }, { 2000, 0, "bash", "libc", "malloc" }, { 1000, 1000, "bash", "[kernel]", "page_fault" }, - { 1000, 1000, "perf", "[kernel]", "schedule" }, + { 1000, 1000, "bash", "bash", "xmalloc" }, { 1000, 0, "perf", "[kernel]", "sys_perf_event_open" }, { 1000, 1000, "perf", "[kernel]", "page_fault" }, + { 1000, 1000, "perf", "[kernel]", "schedule" }, { 1000, 1000, "perf", "libc", "free" }, { 1000, 1000, "perf", "libc", "malloc" }, - { 1000, 1000, "bash", "bash", "xmalloc" }, }; struct callchain_result expected_callchain[] = { { @@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { "bash", "main" }, }, }, { - 3, { { "[kernel]", "schedule" }, - { "perf", "run_command" }, - { "perf", "main" }, }, + 6, { { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "libc", "malloc" }, + { "bash", "xmalloc" }, + { "bash", "main" }, }, }, { 3, { { "[kernel]", "sys_perf_event_open" }, @@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { "perf", "main" }, }, }, { + 3, { { "[kernel]", "schedule" }, + { "perf", "run_command" }, + { "perf", "main" }, }, + }, + { 4, { { "libc", "free" }, { "perf", "cmd_record" }, { "perf", "run_command" }, @@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) { "perf", "run_command" }, { "perf", "main" }, }, }, - { - 6, { { "bash", "xmalloc" }, - { "libc", "malloc" }, - { "bash", "xmalloc" }, - { "libc", "malloc" }, - { "bash", "xmalloc" }, - { "bash", "main" }, }, - }, }; symbol_conf.use_callchain = true; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 74f257a81265..59e53db7914c 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -138,7 +138,7 @@ int test__hists_filter(void) struct hists *hists = evsel__hists(evsel); hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("Normal histogram\n"); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index a748f2be1222..f5547610da02 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -152,7 +152,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -252,7 +252,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -306,7 +306,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -384,7 +384,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); @@ -487,7 +487,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) goto out; hists__collapse_resort(hists, NULL); - hists__output_resort(hists); + hists__output_resort(hists, NULL); if (verbose > 2) { pr_info("[fields = %s, sort = %s]\n", field_order, sort_order); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 502daff76ceb..788506eef567 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -550,7 +550,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser, bool need_percent; node = rb_first(root); - need_percent = !!rb_next(node); + need_percent = node && rb_next(node); while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); @@ -1252,7 +1252,7 @@ static int hists__browser_title(struct hists *hists, nr_samples = convert_unit(nr_samples, &unit); printed = scnprintf(bf, size, - "Samples: %lu%c of event '%s', Event count (approx.): %lu", + "Samples: %lu%c of event '%s', Event count (approx.): %" PRIu64, nr_samples, unit, ev_name, nr_events); diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 2af18376b077..482adae3cc44 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -162,8 +162,8 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, return ret; nr_members = evsel->nr_members; - fields_a = calloc(sizeof(*fields_a), nr_members); - fields_b = calloc(sizeof(*fields_b), nr_members); + fields_a = calloc(nr_members, sizeof(*fields_a)); + fields_b = calloc(nr_members, sizeof(*fields_b)); if (!fields_a || !fields_b) goto out; @@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, if (ret) return ret; + if (a->thread != b->thread || !symbol_conf.use_callchain) + return 0; + ret = b->callchain->max_depth - a->callchain->max_depth; } return ret; diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 2f612562978c..3c38f25b1695 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -1,5 +1,8 @@ #include <signal.h> #include <stdbool.h> +#ifdef HAVE_BACKTRACE_SUPPORT +#include <execinfo.h> +#endif #include "../../util/cache.h" #include "../../util/debug.h" @@ -88,6 +91,25 @@ int ui__getch(int delay_secs) return SLkp_getkey(); } +#ifdef HAVE_BACKTRACE_SUPPORT +static void ui__signal_backtrace(int sig) +{ + void *stackdump[32]; + size_t size; + + ui__exit(false); + psignal(sig, "perf"); + + printf("-------- backtrace --------\n"); + size = backtrace(stackdump, ARRAY_SIZE(stackdump)); + backtrace_symbols_fd(stackdump, size, STDOUT_FILENO); + + exit(0); +} +#else +# define ui__signal_backtrace ui__signal +#endif + static void ui__signal(int sig) { ui__exit(false); @@ -122,8 +144,8 @@ int ui__init(void) ui_browser__init(); tui_progress__init(); - signal(SIGSEGV, ui__signal); - signal(SIGFPE, ui__signal); + signal(SIGSEGV, ui__signal_backtrace); + signal(SIGFPE, ui__signal_backtrace); signal(SIGINT, ui__signal); signal(SIGQUIT, ui__signal); signal(SIGTERM, ui__signal); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 0784a9420528..cadbdc90a5cb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -116,11 +116,6 @@ struct annotation { struct annotated_source *src; }; -struct sannotation { - struct annotation annotation; - struct symbol symbol; -}; - static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) { return (((void *)¬es->src->histograms) + @@ -129,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i static inline struct annotation *symbol__annotation(struct symbol *sym) { - struct sannotation *a = container_of(sym, struct sannotation, symbol); - return &a->annotation; + return (void *)sym - symbol_conf.priv_size; } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e8d79e5bfaf7..0c72680a977f 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -410,21 +410,18 @@ int perf_session__cache_build_ids(struct perf_session *session) { struct rb_node *nd; int ret; - char debugdir[PATH_MAX]; if (no_buildid_cache) return 0; - snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); - - if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) + if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&session->machines.host, debugdir); + ret = machine__cache_build_ids(&session->machines.host, buildid_dir); for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret |= machine__cache_build_ids(pos, debugdir); + ret |= machine__cache_build_ids(pos, buildid_dir); } return ret ? -1 : 0; } diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 5cf9e1b5989d..d04d770d90f6 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2 extern char *perf_pathdup(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +#ifndef __UCLIBC__ /* Matches the libc/libbsd function attribute so we declare this unconditionally: */ extern size_t strlcpy(char *dest, const char *src, size_t size); +#endif #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index cf524a35cc84..14e7a123d43b 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -77,7 +77,7 @@ int parse_callchain_record_opt(const char *arg) ret = 0; } else pr_err("callchain: No more arguments " - "needed for -g fp\n"); + "needed for --call-graph fp\n"); break; #ifdef HAVE_DWARF_UNWIND_SUPPORT @@ -841,3 +841,33 @@ char *callchain_list__sym_name(struct callchain_list *cl, return bf; } + +static void free_callchain_node(struct callchain_node *node) +{ + struct callchain_list *list, *tmp; + struct callchain_node *child; + struct rb_node *n; + + list_for_each_entry_safe(list, tmp, &node->val, list) { + list_del(&list->list); + free(list); + } + + n = rb_first(&node->rb_root_in); + while (n) { + child = container_of(n, struct callchain_node, rb_node_in); + n = rb_next(n); + rb_erase(&child->rb_node_in, &node->rb_root_in); + + free_callchain_node(child); + free(child); + } +} + +void free_callchain(struct callchain_root *root) +{ + if (!symbol_conf.use_callchain) + return; + + free_callchain_node(&root->node); +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index dbc08cf5f970..c0ec1acc38e4 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -198,4 +198,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused, char *callchain_list__sym_name(struct callchain_list *cl, char *bf, size_t bfsize, bool show_dso); +void free_callchain(struct callchain_root *root); + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 57ff826f150b..e18f653cd7db 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -522,7 +522,7 @@ static int buildid_dir_command_config(const char *var, const char *value, const char *v; /* same dir for all commands */ - if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) { + if (!strcmp(var, "buildid.dir")) { v = perf_config_dirname(var, value); if (!v) return -1; @@ -539,12 +539,14 @@ static void check_buildid_dir_config(void) perf_config(buildid_dir_command_config, &c); } -void set_buildid_dir(void) +void set_buildid_dir(const char *dir) { - buildid_dir[0] = '\0'; + if (dir) + scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir); /* try config file */ - check_buildid_dir_config(); + if (buildid_dir[0] == '\0') + check_buildid_dir_config(); /* default to $HOME/.debug */ if (buildid_dir[0] == '\0') { diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index cfbe2b99b9aa..cbab1fb77b1d 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -8,6 +8,7 @@ */ #include "util.h" #include <api/fs/debugfs.h> +#include <api/fs/fs.h> #include <poll.h> #include "cpumap.h" #include "thread_map.h" @@ -24,6 +25,7 @@ #include <linux/bitops.h> #include <linux/hash.h> +#include <linux/log2.h> static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx); static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx); @@ -892,10 +894,24 @@ out_unmap: static size_t perf_evlist__mmap_size(unsigned long pages) { - /* 512 kiB: default amount of unprivileged mlocked memory */ - if (pages == UINT_MAX) - pages = (512 * 1024) / page_size; - else if (!is_power_of_2(pages)) + if (pages == UINT_MAX) { + int max; + + if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) { + /* + * Pick a once upon a time good value, i.e. things look + * strange since we can't read a sysctl value, but lets not + * die yet... + */ + max = 512; + } else { + max -= (page_size / 1024); + } + + pages = (max * 1024) / page_size; + if (!is_power_of_2(pages)) + pages = rounddown_pow_of_two(pages); + } else if (!is_power_of_2(pages)) return 0; return (pages + 1) * page_size; @@ -932,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min, /* leave number of pages at 0 */ } else if (!is_power_of_2(pages)) { /* round pages up to next power of 2 */ - pages = next_pow2_l(pages); + pages = roundup_pow_of_two(pages); if (!pages) return -EINVAL; pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n", @@ -1483,6 +1499,37 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, return 0; } +int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size) +{ + char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0; + + switch (err) { + case EPERM: + sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user); + printed += scnprintf(buf + printed, size - printed, + "Error:\t%s.\n" + "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n" + "Hint:\tTried using %zd kB.\n", + emsg, pages_max_per_user, pages_attempted); + + if (pages_attempted >= pages_max_per_user) { + printed += scnprintf(buf + printed, size - printed, + "Hint:\tTry 'sudo sh -c \"echo %d > /proc/sys/kernel/perf_event_mlock_kb\"', or\n", + pages_max_per_user + pages_attempted); + } + + printed += scnprintf(buf + printed, size - printed, + "Hint:\tTry using a smaller -m/--mmap-pages value."); + break; + default: + scnprintf(buf, size, "%s", emsg); + break; + } + + return 0; +} + void perf_evlist__to_front(struct perf_evlist *evlist, struct perf_evsel *move_evsel) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 649b0c597283..0ba93f67ab94 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -185,6 +185,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); +int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size); static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) { diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 6e88b9e395df..182395546ddc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -6,6 +6,7 @@ #include "evlist.h" #include "evsel.h" #include "annotate.h" +#include "ui/progress.h" #include <math.h> static bool hists__filter_entry_by_dso(struct hists *hists, @@ -303,7 +304,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, size_t callchain_size = 0; struct hist_entry *he; - if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) + if (symbol_conf.use_callchain) callchain_size = sizeof(struct callchain_root); he = zalloc(sizeof(*he) + callchain_size); @@ -736,7 +737,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, iter->he = he; he_cache[iter->curr++] = he; - callchain_append(he->callchain, &callchain_cursor, sample->period); + hist_entry__append_callchain(he, sample); /* * We need to re-initialize the cursor since callchain_append() @@ -809,7 +810,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, iter->he = he; he_cache[iter->curr++] = he; - callchain_append(he->callchain, &cursor, sample->period); + if (symbol_conf.use_callchain) + callchain_append(he->callchain, &cursor, sample->period); return 0; } @@ -945,6 +947,7 @@ void hist_entry__free(struct hist_entry *he) zfree(&he->mem_info); zfree(&he->stat_acc); free_srcline(he->srcline); + free_callchain(he->callchain); free(he); } @@ -987,6 +990,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, else p = &(*p)->rb_right; } + hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); @@ -1024,7 +1028,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) if (!sort__need_collapse) return; + hists->nr_entries = 0; + root = hists__get_rotate_entries_in(hists); + next = rb_first(root); while (next) { @@ -1119,7 +1126,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, rb_insert_color(&he->rb_node, entries); } -void hists__output_resort(struct hists *hists) +void hists__output_resort(struct hists *hists, struct ui_progress *prog) { struct rb_root *root; struct rb_node *next; @@ -1148,6 +1155,9 @@ void hists__output_resort(struct hists *hists) if (!n->filtered) hists__calc_col_len(hists, n); + + if (prog) + ui_progress__update(prog, 1); } } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d0ef9a19a744..46bd50344f85 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -121,7 +121,7 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); void hist_entry__free(struct hist_entry *); -void hists__output_resort(struct hists *hists); +void hists__output_resort(struct hists *hists, struct ui_progress *prog); void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c deleted file mode 100644 index 5c1d0d099f0d..000000000000 --- a/tools/perf/util/hweight.c +++ /dev/null @@ -1,31 +0,0 @@ -#include <linux/bitops.h> - -/** - * hweightN - returns the hamming weight of a N-bit word - * @x: the word to weigh - * - * The Hamming Weight of a number is the total number of bits set in it. - */ - -unsigned int hweight32(unsigned int w) -{ - unsigned int res = w - ((w >> 1) & 0x55555555); - res = (res & 0x33333333) + ((res >> 2) & 0x33333333); - res = (res + (res >> 4)) & 0x0F0F0F0F; - res = res + (res >> 8); - return (res + (res >> 16)) & 0x000000FF; -} - -unsigned long hweight64(__u64 w) -{ -#if BITS_PER_LONG == 32 - return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w); -#elif BITS_PER_LONG == 64 - __u64 res = w - ((w >> 1) & 0x5555555555555555ul); - res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul); - res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful; - res = res + (res >> 8); - res = res + (res >> 16); - return (res + (res >> 32)) & 0x00000000000000FFul; -#endif -} diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h deleted file mode 100644 index d82b170bb216..000000000000 --- a/tools/perf/util/include/asm/hash.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_GENERIC_HASH_H -#define __ASM_GENERIC_HASH_H - -/* Stub */ - -#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h deleted file mode 100644 index 36cf26d434a5..000000000000 --- a/tools/perf/util/include/asm/hweight.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef PERF_HWEIGHT_H -#define PERF_HWEIGHT_H - -#include <linux/types.h> -unsigned int hweight32(unsigned int w); -unsigned long hweight64(__u64 w); - -#endif /* PERF_HWEIGHT_H */ diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h deleted file mode 100644 index c3294163de17..000000000000 --- a/tools/perf/util/include/linux/bitops.h +++ /dev/null @@ -1,162 +0,0 @@ -#ifndef _PERF_LINUX_BITOPS_H_ -#define _PERF_LINUX_BITOPS_H_ - -#include <linux/kernel.h> -#include <linux/compiler.h> -#include <asm/hweight.h> - -#ifndef __WORDSIZE -#define __WORDSIZE (__SIZEOF_LONG__ * 8) -#endif - -#define BITS_PER_LONG __WORDSIZE -#define BITS_PER_BYTE 8 -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) -#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) -#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) - -#define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -/* same as for_each_set_bit() but use bit as value to start with */ -#define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -static inline void set_bit(int nr, unsigned long *addr) -{ - addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG); -} - -static inline void clear_bit(int nr, unsigned long *addr) -{ - addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG)); -} - -static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) -{ - return ((1UL << (nr % BITS_PER_LONG)) & - (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; -} - -static inline unsigned long hweight_long(unsigned long w) -{ - return sizeof(w) == 4 ? hweight32(w) : hweight64(w); -} - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static __always_inline unsigned long __ffs(unsigned long word) -{ - int num = 0; - -#if BITS_PER_LONG == 64 - if ((word & 0xffffffff) == 0) { - num += 32; - word >>= 32; - } -#endif - if ((word & 0xffff) == 0) { - num += 16; - word >>= 16; - } - if ((word & 0xff) == 0) { - num += 8; - word >>= 8; - } - if ((word & 0xf) == 0) { - num += 4; - word >>= 4; - } - if ((word & 0x3) == 0) { - num += 2; - word >>= 2; - } - if ((word & 0x1) == 0) - num += 1; - return num; -} - -typedef const unsigned long __attribute__((__may_alias__)) long_alias_t; - -/* - * Find the first set bit in a memory region. - */ -static inline unsigned long -find_first_bit(const unsigned long *addr, unsigned long size) -{ - long_alias_t *p = (long_alias_t *) addr; - unsigned long result = 0; - unsigned long tmp; - - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - - tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found: - return result + __ffs(tmp); -} - -/* - * Find the next set bit in a memory region. - */ -static inline unsigned long -find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) -{ - const unsigned long *p = addr + BITOP_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG-1); - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset %= BITS_PER_LONG; - if (offset) { - tmp = *(p++); - tmp &= (~0UL << offset); - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - } - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found_middle; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - tmp = *p; - -found_first: - tmp &= (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __ffs(tmp); -} - -#endif diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 15dd0a9691ce..1bca3a9f2b16 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine, if (th != NULL) { rb_link_node(&th->rb_node, parent, p); rb_insert_color(&th->rb_node, &machine->threads); - machine->last_match = th; /* * We have to initialize map_groups separately @@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine, * leader and that would screwed the rb tree. */ if (thread__init_map_groups(th, machine)) { + rb_erase(&th->rb_node, &machine->threads); thread__delete(th); return NULL; } + + machine->last_match = th; } return th; @@ -1385,19 +1387,46 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, static int add_callchain_ip(struct thread *thread, struct symbol **parent, struct addr_location *root_al, - int cpumode, + bool branch_history, u64 ip) { struct addr_location al; al.filtered = 0; al.sym = NULL; - if (cpumode == -1) + if (branch_history) thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al); - else + else { + u8 cpumode = PERF_RECORD_MISC_USER; + + if (ip >= PERF_CONTEXT_MAX) { + switch (ip) { + case PERF_CONTEXT_HV: + cpumode = PERF_RECORD_MISC_HYPERVISOR; + break; + case PERF_CONTEXT_KERNEL: + cpumode = PERF_RECORD_MISC_KERNEL; + break; + case PERF_CONTEXT_USER: + cpumode = PERF_RECORD_MISC_USER; + break; + default: + pr_debug("invalid callchain context: " + "%"PRId64"\n", (s64) ip); + /* + * It seems the callchain is corrupted. + * Discard all. + */ + callchain_cursor_reset(&callchain_cursor); + return 1; + } + return 0; + } thread__find_addr_location(thread, cpumode, MAP__FUNCTION, ip, &al); + } + if (al.sym != NULL) { if (sort__has_parent && !*parent && symbol__match_regex(al.sym, &parent_regex)) @@ -1480,11 +1509,8 @@ static int thread__resolve_callchain_sample(struct thread *thread, struct addr_location *root_al, int max_stack) { - u8 cpumode = PERF_RECORD_MISC_USER; int chain_nr = min(max_stack, (int)chain->nr); - int i; - int j; - int err; + int i, j, err; int skip_idx = -1; int first_call = 0; @@ -1542,10 +1568,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, for (i = 0; i < nr; i++) { err = add_callchain_ip(thread, parent, root_al, - -1, be[i].to); + true, be[i].to); if (!err) err = add_callchain_ip(thread, parent, root_al, - -1, be[i].from); + true, be[i].from); if (err == -EINVAL) break; if (err) @@ -1574,36 +1600,10 @@ check_calls: #endif ip = chain->ips[j]; - if (ip >= PERF_CONTEXT_MAX) { - switch (ip) { - case PERF_CONTEXT_HV: - cpumode = PERF_RECORD_MISC_HYPERVISOR; - break; - case PERF_CONTEXT_KERNEL: - cpumode = PERF_RECORD_MISC_KERNEL; - break; - case PERF_CONTEXT_USER: - cpumode = PERF_RECORD_MISC_USER; - break; - default: - pr_debug("invalid callchain context: " - "%"PRId64"\n", (s64) ip); - /* - * It seems the callchain is corrupted. - * Discard all. - */ - callchain_cursor_reset(&callchain_cursor); - return 0; - } - continue; - } + err = add_callchain_ip(thread, parent, root_al, false, ip); - err = add_callchain_ip(thread, parent, root_al, - cpumode, ip); - if (err == -EINVAL) - break; if (err) - return err; + return (err < 0) ? err : 0; } return 0; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 28eb1417cb2a..94a717bf007d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, } if (ntevs == 0) { /* No error but failed to find probe point. */ - pr_warning("Probe point '%s' not found.\n", + pr_warning("Probe point '%s' not found in debuginfo.\n", synthesize_perf_probe_point(&pev->point)); - return -ENOENT; + if (need_dwarf) + return -ENOENT; + return 0; } /* Error path : ntevs < 0 */ pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs); @@ -2050,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev) pr_debug("Writing event: %s\n", buf); if (!probe_event_dry_run) { ret = write(fd, buf, strlen(buf)); - if (ret <= 0) + if (ret <= 0) { + ret = -errno; pr_warning("Failed to write event: %s\n", strerror_r(errno, sbuf, sizeof(sbuf))); + } } free(buf); return ret; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index c7918f83b300..b5247d777f0e 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg, int ret = 0; #if _ELFUTILS_PREREQ(0, 142) + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + /* Get the call frame information from this dwarf */ - pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg)); + elf = dwarf_getelf(dbg->dbg); + if (elf == NULL) + return -EINVAL; + + if (gelf_getehdr(elf, &ehdr) == NULL) + return -EINVAL; + + if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) && + shdr.sh_type == SHT_PROGBITS) { + pf->cfi = dwarf_getcfi_elf(elf); + } else { + pf->cfi = dwarf_getcfi(dbg->dbg); + } #endif off = 0; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 16a475a7d492..6c6a6953fa93 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,7 +10,7 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c -util/hweight.c +../../lib/hweight.c util/thread_map.c util/util.c util/xyarray.c diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index cf69325b985f..8acd0df88b5c 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -137,16 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) static int get_max_rate(unsigned int *rate) { - char path[PATH_MAX]; - const char *procfs = procfs__mountpoint(); - - if (!procfs) - return -1; - - snprintf(path, PATH_MAX, - "%s/sys/kernel/perf_event_max_sample_rate", procfs); - - return filename__read_int(path, (int *) rate); + return sysctl__read_int("kernel/perf_event_max_sample_rate", (int *)rate); } static int record_opts__config_freq(struct record_opts *opts) diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index e73b6a5c9e0f..c93fb0c5bd0b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -20,7 +20,7 @@ struct a2l_data { const char *input; - unsigned long addr; + u64 addr; bool found; const char *filename; @@ -147,7 +147,7 @@ static void addr2line_cleanup(struct a2l_data *a2l) free(a2l); } -static int addr2line(const char *dso_name, unsigned long addr, +static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line, struct dso *dso) { int ret = 0; @@ -193,7 +193,7 @@ void dso__free_a2l(struct dso *dso) #else /* HAVE_LIBBFD_SUPPORT */ -static int addr2line(const char *dso_name, unsigned long addr, +static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line_nr, struct dso *dso __maybe_unused) { @@ -252,7 +252,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused) */ #define A2L_FAIL_LIMIT 123 -char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym, +char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, bool show_sym) { char *file = NULL; @@ -293,10 +293,10 @@ out: dso__free_a2l(dso); } if (sym) { - if (asprintf(&srcline, "%s+%ld", show_sym ? sym->name : "", + if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "", addr - sym->start) < 0) return SRCLINE_UNKNOWN; - } else if (asprintf(&srcline, "%s[%lx]", dso->short_name, addr) < 0) + } else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0) return SRCLINE_UNKNOWN; return srcline; } diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index fa585c63f56a..d7efb03b3f9a 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { void *tmp; + long offset; if (need_swap) { phdr->p_type = bswap_32(phdr->p_type); @@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) continue; buf_size = phdr->p_filesz; + offset = phdr->p_offset; tmp = realloc(buf, buf_size); if (tmp == NULL) goto out_free; buf = tmp; - fseek(fp, phdr->p_offset, SEEK_SET); + fseek(fp, offset, SEEK_SET); if (fread(buf, buf_size, 1, fp) != 1) goto out_free; @@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { void *tmp; + long offset; if (need_swap) { phdr->p_type = bswap_32(phdr->p_type); @@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) continue; buf_size = phdr->p_filesz; + offset = phdr->p_offset; tmp = realloc(buf, buf_size); if (tmp == NULL) goto out_free; buf = tmp; - fseek(fp, phdr->p_offset, SEEK_SET); + fseek(fp, offset, SEEK_SET); if (fread(buf, buf_size, 1, fp) != 1) goto out_free; diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 371219a6daf1..6edf535f65c2 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name) return offset; } +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int elf_is_exec(int fd, const char *name) +{ + Elf *elf; + GElf_Ehdr ehdr; + int retval = 0; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return 0; + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out; + + retval = (ehdr.e_type == ET_EXEC); + +out: + elf_end(elf); + pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval); + return retval; +} +#endif + struct table_entry { u32 start_ip_offset; u32 fde_offset; @@ -322,8 +344,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, #ifndef NO_LIBUNWIND_DEBUG_FRAME /* Check the .debug_frame section for unwinding info */ if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { + int fd = dso__data_fd(map->dso, ui->machine); + int is_exec = elf_is_exec(fd, map->dso->name); + unw_word_t base = is_exec ? 0 : map->start; + memset(&di, 0, sizeof(di)); - if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name, + if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name, map->start, map->end)) return dwarf_search_unwind_table(as, ip, &di, pi, need_unwind_info, arg); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index d5eab3f3323f..b86744f29eef 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -442,23 +442,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags) return (unsigned long) -1; } -int filename__read_int(const char *filename, int *value) -{ - char line[64]; - int fd = open(filename, O_RDONLY), err = -1; - - if (fd < 0) - return -1; - - if (read(fd, line, sizeof(line)) > 0) { - *value = atoi(line); - err = 0; - } - - close(fd); - return err; -} - int filename__read_str(const char *filename, char **buf, size_t *sizep) { size_t size = 0, alloc_size = 0; @@ -523,16 +506,9 @@ const char *get_filename_for_perf_kvm(void) int perf_event_paranoid(void) { - char path[PATH_MAX]; - const char *procfs = procfs__mountpoint(); int value; - if (!procfs) - return INT_MAX; - - scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs); - - if (filename__read_int(path, &value)) + if (sysctl__read_int("kernel/perf_event_paranoid", &value)) return INT_MAX; return value; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 419bee030f83..027a5153495c 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -153,7 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2))) extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); extern int prefixcmp(const char *str, const char *prefix); -extern void set_buildid_dir(void); +extern void set_buildid_dir(const char *dir); static inline const char *skip_prefix(const char *str, const char *prefix) { @@ -269,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr); #define _STR(x) #x #define STR(x) _STR(x) -/* - * Determine whether some value is a power of two, where zero is - * *not* considered a power of two. - */ - -static inline __attribute__((const)) -bool is_power_of_2(unsigned long n) -{ - return (n != 0 && ((n & (n - 1)) == 0)); -} - -static inline unsigned next_pow2(unsigned x) -{ - if (!x) - return 1; - return 1ULL << (32 - __builtin_clz(x - 1)); -} - -static inline unsigned long next_pow2_l(unsigned long x) -{ -#if BITS_PER_LONG == 64 - if (x <= (1UL << 31)) - return next_pow2(x); - return (unsigned long)next_pow2(x >> 32) << 32; -#else - return next_pow2(x); -#endif -} - size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); @@ -339,11 +310,10 @@ static inline int path__join3(char *bf, size_t size, struct dso; struct symbol; -char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym, +char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, bool show_sym); void free_srcline(char *srcline); -int filename__read_int(const char *filename, int *value); int filename__read_str(const char *filename, char **buf, size_t *sizep); int perf_event_paranoid(void); |
