diff options
Diffstat (limited to 'tools/perf/util')
103 files changed, 5181 insertions, 935 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 91c5f6e1af59..3840e3a87057 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,5 +1,6 @@ libperf-y += alias.o libperf-y += annotate.o +libperf-y += block-range.o libperf-y += build-id.o libperf-y += config.o libperf-y += ctype.o @@ -85,6 +86,8 @@ libperf-y += term.o libperf-y += help-unknown-cmd.o libperf-y += mem-events.o libperf-y += vsprintf.o +libperf-y += drv_configs.o +libperf-y += time-utils.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -98,6 +101,7 @@ endif libperf-$(CONFIG_DWARF) += probe-finder.o libperf-$(CONFIG_DWARF) += dwarf-aux.o +libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind-local.o @@ -117,9 +121,13 @@ libperf-y += demangle-rust.o ifdef CONFIG_JITDUMP libperf-$(CONFIG_LIBELF) += jitdump.o libperf-$(CONFIG_LIBELF) += genelf.o -libperf-$(CONFIG_LIBELF) += genelf_debug.o +libperf-$(CONFIG_DWARF) += genelf_debug.o endif +libperf-y += perf-hooks.o + +libperf-$(CONFIG_CXX) += c++/ + CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" # avoid compiler warnings in 32-bit mode CFLAGS_genelf_debug.o += -Wno-packed diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 4024d309bb00..06cc04e5806a 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -17,16 +17,120 @@ #include "debug.h" #include "annotate.h" #include "evsel.h" +#include "block-range.h" +#include "arch/common.h" #include <regex.h> #include <pthread.h> #include <linux/bitops.h> +#include <sys/utsname.h> const char *disassembler_style; const char *objdump_path; static regex_t file_lineno; -static struct ins *ins__find(const char *name); -static int disasm_line__parse(char *line, char **namep, char **rawp); +static struct ins_ops *ins__find(struct arch *arch, const char *name); +static void ins__sort(struct arch *arch); +static int disasm_line__parse(char *line, const char **namep, char **rawp); + +struct arch { + const char *name; + struct ins *instructions; + size_t nr_instructions; + size_t nr_instructions_allocated; + struct ins_ops *(*associate_instruction_ops)(struct arch *arch, const char *name); + bool sorted_instructions; + bool initialized; + void *priv; + int (*init)(struct arch *arch); + struct { + char comment_char; + char skip_functions_char; + } objdump; +}; + +static struct ins_ops call_ops; +static struct ins_ops dec_ops; +static struct ins_ops jump_ops; +static struct ins_ops mov_ops; +static struct ins_ops nop_ops; +static struct ins_ops lock_ops; +static struct ins_ops ret_ops; + +static int arch__grow_instructions(struct arch *arch) +{ + struct ins *new_instructions; + size_t new_nr_allocated; + + if (arch->nr_instructions_allocated == 0 && arch->instructions) + goto grow_from_non_allocated_table; + + new_nr_allocated = arch->nr_instructions_allocated + 128; + new_instructions = realloc(arch->instructions, new_nr_allocated * sizeof(struct ins)); + if (new_instructions == NULL) + return -1; + +out_update_instructions: + arch->instructions = new_instructions; + arch->nr_instructions_allocated = new_nr_allocated; + return 0; + +grow_from_non_allocated_table: + new_nr_allocated = arch->nr_instructions + 128; + new_instructions = calloc(new_nr_allocated, sizeof(struct ins)); + if (new_instructions == NULL) + return -1; + + memcpy(new_instructions, arch->instructions, arch->nr_instructions); + goto out_update_instructions; +} + +static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops) +{ + struct ins *ins; + + if (arch->nr_instructions == arch->nr_instructions_allocated && + arch__grow_instructions(arch)) + return -1; + + ins = &arch->instructions[arch->nr_instructions]; + ins->name = strdup(name); + if (!ins->name) + return -1; + + ins->ops = ops; + arch->nr_instructions++; + + ins__sort(arch); + return 0; +} + +#include "arch/arm/annotate/instructions.c" +#include "arch/arm64/annotate/instructions.c" +#include "arch/x86/annotate/instructions.c" +#include "arch/powerpc/annotate/instructions.c" + +static struct arch architectures[] = { + { + .name = "arm", + .init = arm__annotate_init, + }, + { + .name = "arm64", + .init = arm64__annotate_init, + }, + { + .name = "x86", + .instructions = x86__instructions, + .nr_instructions = ARRAY_SIZE(x86__instructions), + .objdump = { + .comment_char = '#', + }, + }, + { + .name = "powerpc", + .init = powerpc__annotate_init, + }, +}; static void ins__delete(struct ins_operands *ops) { @@ -53,7 +157,7 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size, return ins__raw_scnprintf(ins, bf, size, ops); } -static int call__parse(struct ins_operands *ops) +static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map) { char *endptr, *tok, *name; @@ -65,10 +169,9 @@ static int call__parse(struct ins_operands *ops) name++; -#ifdef __arm__ - if (strchr(name, '+')) + if (arch->objdump.skip_functions_char && + strchr(name, arch->objdump.skip_functions_char)) return -1; -#endif tok = strchr(name, '>'); if (tok == NULL) @@ -81,16 +184,16 @@ static int call__parse(struct ins_operands *ops) return ops->target.name == NULL ? -1 : 0; indirect_call: - tok = strchr(endptr, '('); - if (tok != NULL) { - ops->target.addr = 0; + tok = strchr(endptr, '*'); + if (tok == NULL) { + struct symbol *sym = map__find_symbol(map, map->map_ip(map, ops->target.addr)); + if (sym != NULL) + ops->target.name = strdup(sym->name); + else + ops->target.addr = 0; return 0; } - tok = strchr(endptr, '*'); - if (tok == NULL) - return -1; - ops->target.addr = strtoull(tok + 1, NULL, 16); return 0; } @@ -117,16 +220,22 @@ bool ins__is_call(const struct ins *ins) return ins->ops == &call_ops; } -static int jump__parse(struct ins_operands *ops) +static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused) { const char *s = strchr(ops->raw, '+'); + const char *c = strchr(ops->raw, ','); - ops->target.addr = strtoull(ops->raw, NULL, 16); + if (c++ != NULL) + ops->target.addr = strtoull(c, NULL, 16); + else + ops->target.addr = strtoull(ops->raw, NULL, 16); - if (s++ != NULL) + if (s++ != NULL) { ops->target.offset = strtoull(s, NULL, 16); - else - ops->target.offset = UINT64_MAX; + ops->target.offset_avail = true; + } else { + ops->target.offset_avail = false; + } return 0; } @@ -134,6 +243,9 @@ static int jump__parse(struct ins_operands *ops) static int jump__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { + if (!ops->target.addr || ops->target.offset < 0) + return ins__raw_scnprintf(ins, bf, size, ops); + return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset); } @@ -172,28 +284,22 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep) return 0; } -static int lock__parse(struct ins_operands *ops) +static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map *map) { - char *name; - ops->locked.ops = zalloc(sizeof(*ops->locked.ops)); if (ops->locked.ops == NULL) return 0; - if (disasm_line__parse(ops->raw, &name, &ops->locked.ops->raw) < 0) + if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0) goto out_free_ops; - ops->locked.ins = ins__find(name); - free(name); + ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name); - if (ops->locked.ins == NULL) + if (ops->locked.ins.ops == NULL) goto out_free_ops; - if (!ops->locked.ins->ops) - return 0; - - if (ops->locked.ins->ops->parse && - ops->locked.ins->ops->parse(ops->locked.ops) < 0) + if (ops->locked.ins.ops->parse && + ops->locked.ins.ops->parse(arch, ops->locked.ops, map) < 0) goto out_free_ops; return 0; @@ -208,19 +314,19 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size, { int printed; - if (ops->locked.ins == NULL) + if (ops->locked.ins.ops == NULL) return ins__raw_scnprintf(ins, bf, size, ops); printed = scnprintf(bf, size, "%-6.6s ", ins->name); - return printed + ins__scnprintf(ops->locked.ins, bf + printed, + return printed + ins__scnprintf(&ops->locked.ins, bf + printed, size - printed, ops->locked.ops); } static void lock__delete(struct ins_operands *ops) { - struct ins *ins = ops->locked.ins; + struct ins *ins = &ops->locked.ins; - if (ins && ins->ops->free) + if (ins->ops && ins->ops->free) ins->ops->free(ops->locked.ops); else ins__delete(ops->locked.ops); @@ -236,7 +342,7 @@ static struct ins_ops lock_ops = { .scnprintf = lock__scnprintf, }; -static int mov__parse(struct ins_operands *ops) +static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *map __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *comment, prev; @@ -251,11 +357,7 @@ static int mov__parse(struct ins_operands *ops) return -1; target = ++s; -#ifdef __arm__ - comment = strchr(s, ';'); -#else - comment = strchr(s, '#'); -#endif + comment = strchr(s, arch->objdump.comment_char); if (comment != NULL) s = comment - 1; @@ -303,7 +405,7 @@ static struct ins_ops mov_ops = { .scnprintf = mov__scnprintf, }; -static int dec__parse(struct ins_operands *ops) +static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused) { char *target, *comment, *s, prev; @@ -320,7 +422,7 @@ static int dec__parse(struct ins_operands *ops) if (ops->target.raw == NULL) return -1; - comment = strchr(s, '#'); + comment = strchr(s, arch->objdump.comment_char); if (comment == NULL) return 0; @@ -363,99 +465,6 @@ bool ins__is_ret(const struct ins *ins) return ins->ops == &ret_ops; } -static struct ins instructions[] = { - { .name = "add", .ops = &mov_ops, }, - { .name = "addl", .ops = &mov_ops, }, - { .name = "addq", .ops = &mov_ops, }, - { .name = "addw", .ops = &mov_ops, }, - { .name = "and", .ops = &mov_ops, }, -#ifdef __arm__ - { .name = "b", .ops = &jump_ops, }, // might also be a call - { .name = "bcc", .ops = &jump_ops, }, - { .name = "bcs", .ops = &jump_ops, }, - { .name = "beq", .ops = &jump_ops, }, - { .name = "bge", .ops = &jump_ops, }, - { .name = "bgt", .ops = &jump_ops, }, - { .name = "bhi", .ops = &jump_ops, }, - { .name = "bl", .ops = &call_ops, }, - { .name = "bls", .ops = &jump_ops, }, - { .name = "blt", .ops = &jump_ops, }, - { .name = "blx", .ops = &call_ops, }, - { .name = "bne", .ops = &jump_ops, }, -#endif - { .name = "bts", .ops = &mov_ops, }, - { .name = "call", .ops = &call_ops, }, - { .name = "callq", .ops = &call_ops, }, - { .name = "cmp", .ops = &mov_ops, }, - { .name = "cmpb", .ops = &mov_ops, }, - { .name = "cmpl", .ops = &mov_ops, }, - { .name = "cmpq", .ops = &mov_ops, }, - { .name = "cmpw", .ops = &mov_ops, }, - { .name = "cmpxch", .ops = &mov_ops, }, - { .name = "dec", .ops = &dec_ops, }, - { .name = "decl", .ops = &dec_ops, }, - { .name = "imul", .ops = &mov_ops, }, - { .name = "inc", .ops = &dec_ops, }, - { .name = "incl", .ops = &dec_ops, }, - { .name = "ja", .ops = &jump_ops, }, - { .name = "jae", .ops = &jump_ops, }, - { .name = "jb", .ops = &jump_ops, }, - { .name = "jbe", .ops = &jump_ops, }, - { .name = "jc", .ops = &jump_ops, }, - { .name = "jcxz", .ops = &jump_ops, }, - { .name = "je", .ops = &jump_ops, }, - { .name = "jecxz", .ops = &jump_ops, }, - { .name = "jg", .ops = &jump_ops, }, - { .name = "jge", .ops = &jump_ops, }, - { .name = "jl", .ops = &jump_ops, }, - { .name = "jle", .ops = &jump_ops, }, - { .name = "jmp", .ops = &jump_ops, }, - { .name = "jmpq", .ops = &jump_ops, }, - { .name = "jna", .ops = &jump_ops, }, - { .name = "jnae", .ops = &jump_ops, }, - { .name = "jnb", .ops = &jump_ops, }, - { .name = "jnbe", .ops = &jump_ops, }, - { .name = "jnc", .ops = &jump_ops, }, - { .name = "jne", .ops = &jump_ops, }, - { .name = "jng", .ops = &jump_ops, }, - { .name = "jnge", .ops = &jump_ops, }, - { .name = "jnl", .ops = &jump_ops, }, - { .name = "jnle", .ops = &jump_ops, }, - { .name = "jno", .ops = &jump_ops, }, - { .name = "jnp", .ops = &jump_ops, }, - { .name = "jns", .ops = &jump_ops, }, - { .name = "jnz", .ops = &jump_ops, }, - { .name = "jo", .ops = &jump_ops, }, - { .name = "jp", .ops = &jump_ops, }, - { .name = "jpe", .ops = &jump_ops, }, - { .name = "jpo", .ops = &jump_ops, }, - { .name = "jrcxz", .ops = &jump_ops, }, - { .name = "js", .ops = &jump_ops, }, - { .name = "jz", .ops = &jump_ops, }, - { .name = "lea", .ops = &mov_ops, }, - { .name = "lock", .ops = &lock_ops, }, - { .name = "mov", .ops = &mov_ops, }, - { .name = "movb", .ops = &mov_ops, }, - { .name = "movdqa",.ops = &mov_ops, }, - { .name = "movl", .ops = &mov_ops, }, - { .name = "movq", .ops = &mov_ops, }, - { .name = "movslq", .ops = &mov_ops, }, - { .name = "movzbl", .ops = &mov_ops, }, - { .name = "movzwl", .ops = &mov_ops, }, - { .name = "nop", .ops = &nop_ops, }, - { .name = "nopl", .ops = &nop_ops, }, - { .name = "nopw", .ops = &nop_ops, }, - { .name = "or", .ops = &mov_ops, }, - { .name = "orl", .ops = &mov_ops, }, - { .name = "test", .ops = &mov_ops, }, - { .name = "testb", .ops = &mov_ops, }, - { .name = "testl", .ops = &mov_ops, }, - { .name = "xadd", .ops = &mov_ops, }, - { .name = "xbeginl", .ops = &jump_ops, }, - { .name = "xbeginq", .ops = &jump_ops, }, - { .name = "retq", .ops = &ret_ops, }, -}; - static int ins__key_cmp(const void *name, const void *insp) { const struct ins *ins = insp; @@ -471,31 +480,70 @@ static int ins__cmp(const void *a, const void *b) return strcmp(ia->name, ib->name); } -static void ins__sort(void) +static void ins__sort(struct arch *arch) { - const int nmemb = ARRAY_SIZE(instructions); + const int nmemb = arch->nr_instructions; - qsort(instructions, nmemb, sizeof(struct ins), ins__cmp); + qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp); } -static struct ins *ins__find(const char *name) +static struct ins_ops *__ins__find(struct arch *arch, const char *name) { - const int nmemb = ARRAY_SIZE(instructions); - static bool sorted; + struct ins *ins; + const int nmemb = arch->nr_instructions; - if (!sorted) { - ins__sort(); - sorted = true; + if (!arch->sorted_instructions) { + ins__sort(arch); + arch->sorted_instructions = true; } - return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp); + ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp); + return ins ? ins->ops : NULL; } -int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym) +static struct ins_ops *ins__find(struct arch *arch, const char *name) { - struct annotation *notes = symbol__annotation(sym); - pthread_mutex_init(¬es->lock, NULL); - return 0; + struct ins_ops *ops = __ins__find(arch, name); + + if (!ops && arch->associate_instruction_ops) + ops = arch->associate_instruction_ops(arch, name); + + return ops; +} + +static int arch__key_cmp(const void *name, const void *archp) +{ + const struct arch *arch = archp; + + return strcmp(name, arch->name); +} + +static int arch__cmp(const void *a, const void *b) +{ + const struct arch *aa = a; + const struct arch *ab = b; + + return strcmp(aa->name, ab->name); +} + +static void arch__sort(void) +{ + const int nmemb = ARRAY_SIZE(architectures); + + qsort(architectures, nmemb, sizeof(struct arch), arch__cmp); +} + +static struct arch *arch__find(const char *name) +{ + const int nmemb = ARRAY_SIZE(architectures); + static bool sorted; + + if (!sorted) { + arch__sort(); + sorted = true; + } + + return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp); } int symbol__alloc_hist(struct symbol *sym) @@ -599,7 +647,8 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); - if (addr < sym->start || addr >= sym->end) { + if ((addr < sym->start || addr >= sym->end) && + (addr != sym->end || sym->start != sym->end)) { pr_debug("%s(%d): ERANGE! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, __LINE__, sym->name, sym->start, addr, sym->end); return -ERANGE; @@ -715,21 +764,18 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip) return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip); } -static void disasm_line__init_ins(struct disasm_line *dl) +static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map *map) { - dl->ins = ins__find(dl->name); - - if (dl->ins == NULL) - return; + dl->ins.ops = ins__find(arch, dl->ins.name); - if (!dl->ins->ops) + if (!dl->ins.ops) return; - if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0) - dl->ins = NULL; + if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, map) < 0) + dl->ins.ops = NULL; } -static int disasm_line__parse(char *line, char **namep, char **rawp) +static int disasm_line__parse(char *line, const char **namep, char **rawp) { char *name = line, tmp; @@ -762,12 +808,15 @@ static int disasm_line__parse(char *line, char **namep, char **rawp) return 0; out_free_name: - zfree(namep); + free((void *)namep); + *namep = NULL; return -1; } static struct disasm_line *disasm_line__new(s64 offset, char *line, - size_t privsize, int line_nr) + size_t privsize, int line_nr, + struct arch *arch, + struct map *map) { struct disasm_line *dl = zalloc(sizeof(*dl) + privsize); @@ -779,10 +828,10 @@ static struct disasm_line *disasm_line__new(s64 offset, char *line, goto out_delete; if (offset != -1) { - if (disasm_line__parse(dl->line, &dl->name, &dl->ops.raw) < 0) + if (disasm_line__parse(dl->line, &dl->ins.name, &dl->ops.raw) < 0) goto out_free_line; - disasm_line__init_ins(dl); + disasm_line__init_ins(dl, arch, map); } } @@ -798,20 +847,21 @@ out_delete: void disasm_line__free(struct disasm_line *dl) { zfree(&dl->line); - zfree(&dl->name); - if (dl->ins && dl->ins->ops->free) - dl->ins->ops->free(&dl->ops); + if (dl->ins.ops && dl->ins.ops->free) + dl->ins.ops->free(&dl->ops); else ins__delete(&dl->ops); + free((void *)dl->ins.name); + dl->ins.name = NULL; free(dl); } int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw) { - if (raw || !dl->ins) - return scnprintf(bf, size, "%-6.6s %s", dl->name, dl->ops.raw); + if (raw || !dl->ins.ops) + return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw); - return ins__scnprintf(dl->ins, bf, size, &dl->ops); + return ins__scnprintf(&dl->ins, bf, size, &dl->ops); } static void disasm__add(struct list_head *head, struct disasm_line *line) @@ -866,6 +916,89 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, return percent; } +static const char *annotate__address_color(struct block_range *br) +{ + double cov = block_range__coverage(br); + + if (cov >= 0) { + /* mark red for >75% coverage */ + if (cov > 0.75) + return PERF_COLOR_RED; + + /* mark dull for <1% coverage */ + if (cov < 0.01) + return PERF_COLOR_NORMAL; + } + + return PERF_COLOR_MAGENTA; +} + +static const char *annotate__asm_color(struct block_range *br) +{ + double cov = block_range__coverage(br); + + if (cov >= 0) { + /* mark dull for <1% coverage */ + if (cov < 0.01) + return PERF_COLOR_NORMAL; + } + + return PERF_COLOR_BLUE; +} + +static void annotate__branch_printf(struct block_range *br, u64 addr) +{ + bool emit_comment = true; + + if (!br) + return; + +#if 1 + if (br->is_target && br->start == addr) { + struct block_range *branch = br; + double p; + + /* + * Find matching branch to our target. + */ + while (!branch->is_branch) + branch = block_range__next(branch); + + p = 100 *(double)br->entry / branch->coverage; + + if (p > 0.1) { + if (emit_comment) { + emit_comment = false; + printf("\t#"); + } + + /* + * The percentage of coverage joined at this target in relation + * to the next branch. + */ + printf(" +%.2f%%", p); + } + } +#endif + if (br->is_branch && br->end == addr) { + double p = 100*(double)br->taken / br->coverage; + + if (p > 0.1) { + if (emit_comment) { + emit_comment = false; + printf("\t#"); + } + + /* + * The percentage of coverage leaving at this branch, and + * its prediction ratio. + */ + printf(" -%.2f%% (p:%.2f%%)", p, 100*(double)br->pred / br->taken); + } + } +} + + static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start, struct perf_evsel *evsel, u64 len, int min_pcnt, int printed, int max_lines, struct disasm_line *queue) @@ -885,6 +1018,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st s64 offset = dl->offset; const u64 addr = start + offset; struct disasm_line *next; + struct block_range *br; next = disasm__get_next_ip_line(¬es->src->source, dl); @@ -954,8 +1088,12 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st } printf(" : "); - color_fprintf(stdout, PERF_COLOR_MAGENTA, " %" PRIx64 ":", addr); - color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line); + + br = block_range__find(addr); + color_fprintf(stdout, annotate__address_color(br), " %" PRIx64 ":", addr); + color_fprintf(stdout, annotate__asm_color(br), "%s", dl->line); + annotate__branch_printf(br, addr); + printf("\n"); if (ppercents != &percent) free(ppercents); @@ -1004,6 +1142,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st * The ops.raw part will be parsed further according to type of the instruction. */ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, + struct arch *arch, FILE *file, size_t privsize, int *line_nr) { @@ -1066,25 +1205,27 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, parsed_line = tmp2 + 1; } - dl = disasm_line__new(offset, parsed_line, privsize, *line_nr); + dl = disasm_line__new(offset, parsed_line, privsize, *line_nr, arch, map); free(line); (*line_nr)++; if (dl == NULL) return -1; - if (dl->ops.target.offset == UINT64_MAX) + if (!disasm_line__has_offset(dl)) { dl->ops.target.offset = dl->ops.target.addr - map__rip_2objdump(map, sym->start); + dl->ops.target.offset_avail = true; + } /* kcore has no symbols, so add the call target name */ - if (dl->ins && ins__is_call(dl->ins) && !dl->ops.target.name) { + if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.name) { struct addr_map_symbol target = { .map = map, .addr = dl->ops.target.addr, }; - if (!map_groups__find_ams(&target, NULL) && + if (!map_groups__find_ams(&target) && target.sym->start == target.al_addr) dl->ops.target.name = strdup(target.sym->name); } @@ -1108,8 +1249,8 @@ static void delete_last_nop(struct symbol *sym) while (!list_empty(list)) { dl = list_entry(list->prev, struct disasm_line, node); - if (dl->ins && dl->ins->ops) { - if (dl->ins->ops != &nop_ops) + if (dl->ins.ops) { + if (dl->ins.ops != &nop_ops) return; } else { if (!strstr(dl->line, " nop ") && @@ -1162,53 +1303,89 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map * return 0; } -int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize) +static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size) { - struct dso *dso = map->dso; - char *filename = dso__build_id_filename(dso, NULL, 0); - bool free_filename = true; - char command[PATH_MAX * 2]; - FILE *file; - int err = 0; - char symfs_filename[PATH_MAX]; - struct kcore_extract kce; - bool delete_extract = false; - int stdout_fd[2]; - int lineno = 0; - int nline; - pid_t pid; + char linkname[PATH_MAX]; + char *build_id_filename; - if (filename) - symbol__join_symfs(symfs_filename, filename); + if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && + !dso__is_kcore(dso)) + return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX; - if (filename == NULL) { + build_id_filename = dso__build_id_filename(dso, NULL, 0); + if (build_id_filename) { + __symbol__join_symfs(filename, filename_size, build_id_filename); + free(build_id_filename); + } else { if (dso->has_build_id) return ENOMEM; goto fallback; - } else if (dso__is_kcore(dso) || - readlink(symfs_filename, command, sizeof(command)) < 0 || - strstr(command, DSO__NAME_KALLSYMS) || - access(symfs_filename, R_OK)) { - free(filename); + } + + if (dso__is_kcore(dso) || + readlink(filename, linkname, sizeof(linkname)) < 0 || + strstr(linkname, DSO__NAME_KALLSYMS) || + access(filename, R_OK)) { fallback: /* * If we don't have build-ids or the build-id file isn't in the * cache, or is just a kallsyms file, well, lets hope that this * DSO is the same as when 'perf record' ran. */ - filename = (char *)dso->long_name; - symbol__join_symfs(symfs_filename, filename); - free_filename = false; + __symbol__join_symfs(filename, filename_size, dso->long_name); } - if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && - !dso__is_kcore(dso)) { - err = SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX; - goto out_free_filename; + return 0; +} + +static const char *annotate__norm_arch(const char *arch_name) +{ + struct utsname uts; + + if (!arch_name) { /* Assume we are annotating locally. */ + if (uname(&uts) < 0) + return NULL; + arch_name = uts.machine; + } + return normalize_arch((char *)arch_name); +} + +int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize) +{ + struct dso *dso = map->dso; + char command[PATH_MAX * 2]; + struct arch *arch = NULL; + FILE *file; + char symfs_filename[PATH_MAX]; + struct kcore_extract kce; + bool delete_extract = false; + int stdout_fd[2]; + int lineno = 0; + int nline; + pid_t pid; + int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename)); + + if (err) + return err; + + arch_name = annotate__norm_arch(arch_name); + if (!arch_name) + return -1; + + arch = arch__find(arch_name); + if (arch == NULL) + return -ENOTSUP; + + if (arch->init) { + err = arch->init(arch); + if (err) { + pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name); + return err; + } } pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, - filename, sym->name, map->unmap_ip(map, sym->start), + symfs_filename, sym->name, map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end)); pr_debug("annotating [%p] %30s : [%p] %30s\n", @@ -1223,11 +1400,6 @@ fallback: delete_extract = true; strlcpy(symfs_filename, kce.extract_filename, sizeof(symfs_filename)); - if (free_filename) { - free(filename); - free_filename = false; - } - filename = symfs_filename; } } else if (dso__needs_decompress(dso)) { char tmp[PATH_MAX]; @@ -1236,14 +1408,14 @@ fallback: bool ret; if (kmod_path__parse_ext(&m, symfs_filename)) - goto out_free_filename; + goto out; snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX"); fd = mkstemp(tmp); if (fd < 0) { free(m.ext); - goto out_free_filename; + goto out; } ret = decompress_to_file(m.ext, symfs_filename, fd); @@ -1255,7 +1427,7 @@ fallback: close(fd); if (!ret) - goto out_free_filename; + goto out; strcpy(symfs_filename, tmp); } @@ -1271,7 +1443,7 @@ fallback: map__rip_2objdump(map, sym->end), symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", symbol_conf.annotate_src ? "-S" : "", - symfs_filename, filename); + symfs_filename, symfs_filename); pr_debug("Executing: %s\n", command); @@ -1310,7 +1482,7 @@ fallback: nline = 0; while (!feof(file)) { - if (symbol__parse_objdump_line(sym, map, file, privsize, + if (symbol__parse_objdump_line(sym, map, arch, file, privsize, &lineno) < 0) break; nline++; @@ -1333,11 +1505,10 @@ out_remove_tmp: if (dso__needs_decompress(dso)) unlink(symfs_filename); -out_free_filename: + if (delete_extract) kcore_extract__delete(&kce); - if (free_filename) - free(filename); +out: return err; out_close_stdout: @@ -1680,7 +1851,7 @@ static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp) if (dl->offset == -1) return fprintf(fp, "%s\n", dl->line); - printed = fprintf(fp, "%#" PRIx64 " %s", dl->offset, dl->name); + printed = fprintf(fp, "%#" PRIx64 " %s", dl->offset, dl->ins.name); if (dl->ops.raw[0] != '\0') { printed += fprintf(fp, "%.*s %s\n", 6 - (int)printed, " ", @@ -1709,7 +1880,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, struct rb_root source_line = RB_ROOT; u64 len; - if (symbol__disassemble(sym, map, 0) < 0) + if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0) < 0) return -1; len = symbol__size(sym); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index f67ccb027561..09776b5af991 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -11,7 +11,12 @@ #include <linux/rbtree.h> #include <pthread.h> -struct ins; +struct ins_ops; + +struct ins { + const char *name; + struct ins_ops *ops; +}; struct ins_operands { char *raw; @@ -19,7 +24,8 @@ struct ins_operands { char *raw; char *name; u64 addr; - u64 offset; + s64 offset; + bool offset_avail; } target; union { struct { @@ -28,24 +34,21 @@ struct ins_operands { u64 addr; } source; struct { - struct ins *ins; + struct ins ins; struct ins_operands *ops; } locked; }; }; +struct arch; + struct ins_ops { void (*free)(struct ins_operands *ops); - int (*parse)(struct ins_operands *ops); + int (*parse)(struct arch *arch, struct ins_operands *ops, struct map *map); int (*scnprintf)(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); }; -struct ins { - const char *name; - struct ins_ops *ops; -}; - bool ins__is_jump(const struct ins *ins); bool ins__is_call(const struct ins *ins); bool ins__is_ret(const struct ins *ins); @@ -57,8 +60,7 @@ struct disasm_line { struct list_head node; s64 offset; char *line; - char *name; - struct ins *ins; + struct ins ins; int line_nr; float ipc; u64 cycles; @@ -67,7 +69,7 @@ struct disasm_line { static inline bool disasm_line__has_offset(const struct disasm_line *dl) { - return dl->ops.target.offset != UINT64_MAX; + return dl->ops.target.offset_avail; } void disasm_line__free(struct disasm_line *dl); @@ -130,6 +132,7 @@ struct annotated_source { struct annotation { pthread_mutex_t lock; + u64 max_coverage; struct annotated_source *src; }; @@ -155,7 +158,7 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); -int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize); +int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize); enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, @@ -177,7 +180,6 @@ enum symbol_disassemble_errno { int symbol__strerror_disassemble(struct symbol *sym, struct map *map, int errnum, char *buf, size_t buflen); -int symbol__annotate_init(struct map *map, struct symbol *sym); int symbol__annotate_printf(struct symbol *sym, struct map *map, struct perf_evsel *evsel, bool full_paths, int min_pcnt, int max_lines, int context); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index c9169011e55e..c5a6e0b12452 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -16,6 +16,10 @@ #include <sys/types.h> #include <sys/mman.h> #include <stdbool.h> +#include <ctype.h> +#include <string.h> +#include <limits.h> +#include <errno.h> #include <linux/kernel.h> #include <linux/perf_event.h> @@ -35,9 +39,14 @@ #include "../perf.h" #include "util.h" #include "evlist.h" +#include "dso.h" +#include "map.h" +#include "pmu.h" +#include "evsel.h" #include "cpumap.h" #include "thread_map.h" #include "asm/bug.h" +#include "symbol/kallsyms.h" #include "auxtrace.h" #include <linux/hash.h> @@ -892,6 +901,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, return intel_pt_process_auxtrace_info(event, session); case PERF_AUXTRACE_INTEL_BTS: return intel_bts_process_auxtrace_info(event, session); + case PERF_AUXTRACE_CS_ETM: case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; @@ -1398,3 +1408,731 @@ void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key) return NULL; } + +static void addr_filter__free_str(struct addr_filter *filt) +{ + free(filt->str); + filt->action = NULL; + filt->sym_from = NULL; + filt->sym_to = NULL; + filt->filename = NULL; + filt->str = NULL; +} + +static struct addr_filter *addr_filter__new(void) +{ + struct addr_filter *filt = zalloc(sizeof(*filt)); + + if (filt) + INIT_LIST_HEAD(&filt->list); + + return filt; +} + +static void addr_filter__free(struct addr_filter *filt) +{ + if (filt) + addr_filter__free_str(filt); + free(filt); +} + +static void addr_filters__add(struct addr_filters *filts, + struct addr_filter *filt) +{ + list_add_tail(&filt->list, &filts->head); + filts->cnt += 1; +} + +static void addr_filters__del(struct addr_filters *filts, + struct addr_filter *filt) +{ + list_del_init(&filt->list); + filts->cnt -= 1; +} + +void addr_filters__init(struct addr_filters *filts) +{ + INIT_LIST_HEAD(&filts->head); + filts->cnt = 0; +} + +void addr_filters__exit(struct addr_filters *filts) +{ + struct addr_filter *filt, *n; + + list_for_each_entry_safe(filt, n, &filts->head, list) { + addr_filters__del(filts, filt); + addr_filter__free(filt); + } +} + +static int parse_num_or_str(char **inp, u64 *num, const char **str, + const char *str_delim) +{ + *inp += strspn(*inp, " "); + + if (isdigit(**inp)) { + char *endptr; + + if (!num) + return -EINVAL; + errno = 0; + *num = strtoull(*inp, &endptr, 0); + if (errno) + return -errno; + if (endptr == *inp) + return -EINVAL; + *inp = endptr; + } else { + size_t n; + + if (!str) + return -EINVAL; + *inp += strspn(*inp, " "); + *str = *inp; + n = strcspn(*inp, str_delim); + if (!n) + return -EINVAL; + *inp += n; + if (**inp) { + **inp = '\0'; + *inp += 1; + } + } + return 0; +} + +static int parse_action(struct addr_filter *filt) +{ + if (!strcmp(filt->action, "filter")) { + filt->start = true; + filt->range = true; + } else if (!strcmp(filt->action, "start")) { + filt->start = true; + } else if (!strcmp(filt->action, "stop")) { + filt->start = false; + } else if (!strcmp(filt->action, "tracestop")) { + filt->start = false; + filt->range = true; + filt->action += 5; /* Change 'tracestop' to 'stop' */ + } else { + return -EINVAL; + } + return 0; +} + +static int parse_sym_idx(char **inp, int *idx) +{ + *idx = -1; + + *inp += strspn(*inp, " "); + + if (**inp != '#') + return 0; + + *inp += 1; + + if (**inp == 'g' || **inp == 'G') { + *inp += 1; + *idx = 0; + } else { + unsigned long num; + char *endptr; + + errno = 0; + num = strtoul(*inp, &endptr, 0); + if (errno) + return -errno; + if (endptr == *inp || num > INT_MAX) + return -EINVAL; + *inp = endptr; + *idx = num; + } + + return 0; +} + +static int parse_addr_size(char **inp, u64 *num, const char **str, int *idx) +{ + int err = parse_num_or_str(inp, num, str, " "); + + if (!err && *str) + err = parse_sym_idx(inp, idx); + + return err; +} + +static int parse_one_filter(struct addr_filter *filt, const char **filter_inp) +{ + char *fstr; + int err; + + filt->str = fstr = strdup(*filter_inp); + if (!fstr) + return -ENOMEM; + + err = parse_num_or_str(&fstr, NULL, &filt->action, " "); + if (err) + goto out_err; + + err = parse_action(filt); + if (err) + goto out_err; + + err = parse_addr_size(&fstr, &filt->addr, &filt->sym_from, + &filt->sym_from_idx); + if (err) + goto out_err; + + fstr += strspn(fstr, " "); + + if (*fstr == '/') { + fstr += 1; + err = parse_addr_size(&fstr, &filt->size, &filt->sym_to, + &filt->sym_to_idx); + if (err) + goto out_err; + filt->range = true; + } + + fstr += strspn(fstr, " "); + + if (*fstr == '@') { + fstr += 1; + err = parse_num_or_str(&fstr, NULL, &filt->filename, " ,"); + if (err) + goto out_err; + } + + fstr += strspn(fstr, " ,"); + + *filter_inp += fstr - filt->str; + + return 0; + +out_err: + addr_filter__free_str(filt); + + return err; +} + +int addr_filters__parse_bare_filter(struct addr_filters *filts, + const char *filter) +{ + struct addr_filter *filt; + const char *fstr = filter; + int err; + + while (*fstr) { + filt = addr_filter__new(); + err = parse_one_filter(filt, &fstr); + if (err) { + addr_filter__free(filt); + addr_filters__exit(filts); + return err; + } + addr_filters__add(filts, filt); + } + + return 0; +} + +struct sym_args { + const char *name; + u64 start; + u64 size; + int idx; + int cnt; + bool started; + bool global; + bool selected; + bool duplicate; + bool near; +}; + +static bool kern_sym_match(struct sym_args *args, const char *name, char type) +{ + /* A function with the same name, and global or the n'th found or any */ + return symbol_type__is_a(type, MAP__FUNCTION) && + !strcmp(name, args->name) && + ((args->global && isupper(type)) || + (args->selected && ++(args->cnt) == args->idx) || + (!args->global && !args->selected)); +} + +static int find_kern_sym_cb(void *arg, const char *name, char type, u64 start) +{ + struct sym_args *args = arg; + + if (args->started) { + if (!args->size) + args->size = start - args->start; + if (args->selected) { + if (args->size) + return 1; + } else if (kern_sym_match(args, name, type)) { + args->duplicate = true; + return 1; + } + } else if (kern_sym_match(args, name, type)) { + args->started = true; + args->start = start; + } + + return 0; +} + +static int print_kern_sym_cb(void *arg, const char *name, char type, u64 start) +{ + struct sym_args *args = arg; + + if (kern_sym_match(args, name, type)) { + pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n", + ++args->cnt, start, type, name); + args->near = true; + } else if (args->near) { + args->near = false; + pr_err("\t\twhich is near\t\t%s\n", name); + } + + return 0; +} + +static int sym_not_found_error(const char *sym_name, int idx) +{ + if (idx > 0) { + pr_err("N'th occurrence (N=%d) of symbol '%s' not found.\n", + idx, sym_name); + } else if (!idx) { + pr_err("Global symbol '%s' not found.\n", sym_name); + } else { + pr_err("Symbol '%s' not found.\n", sym_name); + } + pr_err("Note that symbols must be functions.\n"); + + return -EINVAL; +} + +static int find_kern_sym(const char *sym_name, u64 *start, u64 *size, int idx) +{ + struct sym_args args = { + .name = sym_name, + .idx = idx, + .global = !idx, + .selected = idx > 0, + }; + int err; + + *start = 0; + *size = 0; + + err = kallsyms__parse("/proc/kallsyms", &args, find_kern_sym_cb); + if (err < 0) { + pr_err("Failed to parse /proc/kallsyms\n"); + return err; + } + + if (args.duplicate) { + pr_err("Multiple kernel symbols with name '%s'\n", sym_name); + args.cnt = 0; + kallsyms__parse("/proc/kallsyms", &args, print_kern_sym_cb); + pr_err("Disambiguate symbol name by inserting #n after the name e.g. %s #2\n", + sym_name); + pr_err("Or select a global symbol by inserting #0 or #g or #G\n"); + return -EINVAL; + } + + if (!args.started) { + pr_err("Kernel symbol lookup: "); + return sym_not_found_error(sym_name, idx); + } + + *start = args.start; + *size = args.size; + + return 0; +} + +static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, + char type, u64 start) +{ + struct sym_args *args = arg; + + if (!symbol_type__is_a(type, MAP__FUNCTION)) + return 0; + + if (!args->started) { + args->started = true; + args->start = start; + } + /* Don't know exactly where the kernel ends, so we add a page */ + args->size = round_up(start, page_size) + page_size - args->start; + + return 0; +} + +static int addr_filter__entire_kernel(struct addr_filter *filt) +{ + struct sym_args args = { .started = false }; + int err; + + err = kallsyms__parse("/proc/kallsyms", &args, find_entire_kern_cb); + if (err < 0 || !args.started) { + pr_err("Failed to parse /proc/kallsyms\n"); + return err; + } + + filt->addr = args.start; + filt->size = args.size; + + return 0; +} + +static int check_end_after_start(struct addr_filter *filt, u64 start, u64 size) +{ + if (start + size >= filt->addr) + return 0; + + if (filt->sym_from) { + pr_err("Symbol '%s' (0x%"PRIx64") comes before '%s' (0x%"PRIx64")\n", + filt->sym_to, start, filt->sym_from, filt->addr); + } else { + pr_err("Symbol '%s' (0x%"PRIx64") comes before address 0x%"PRIx64")\n", + filt->sym_to, start, filt->addr); + } + + return -EINVAL; +} + +static int addr_filter__resolve_kernel_syms(struct addr_filter *filt) +{ + bool no_size = false; + u64 start, size; + int err; + + if (symbol_conf.kptr_restrict) { + pr_err("Kernel addresses are restricted. Unable to resolve kernel symbols.\n"); + return -EINVAL; + } + + if (filt->sym_from && !strcmp(filt->sym_from, "*")) + return addr_filter__entire_kernel(filt); + + if (filt->sym_from) { + err = find_kern_sym(filt->sym_from, &start, &size, + filt->sym_from_idx); + if (err) + return err; + filt->addr = start; + if (filt->range && !filt->size && !filt->sym_to) { + filt->size = size; + no_size = !!size; + } + } + + if (filt->sym_to) { + err = find_kern_sym(filt->sym_to, &start, &size, + filt->sym_to_idx); + if (err) + return err; + + err = check_end_after_start(filt, start, size); + if (err) + return err; + filt->size = start + size - filt->addr; + no_size = !!size; + } + + /* The very last symbol in kallsyms does not imply a particular size */ + if (no_size) { + pr_err("Cannot determine size of symbol '%s'\n", + filt->sym_to ? filt->sym_to : filt->sym_from); + return -EINVAL; + } + + return 0; +} + +static struct dso *load_dso(const char *name) +{ + struct map *map; + struct dso *dso; + + map = dso__new_map(name); + if (!map) + return NULL; + + map__load(map); + + dso = dso__get(map->dso); + + map__put(map); + + return dso; +} + +static bool dso_sym_match(struct symbol *sym, const char *name, int *cnt, + int idx) +{ + /* Same name, and global or the n'th found or any */ + return !arch__compare_symbol_names(name, sym->name) && + ((!idx && sym->binding == STB_GLOBAL) || + (idx > 0 && ++*cnt == idx) || + idx < 0); +} + +static void print_duplicate_syms(struct dso *dso, const char *sym_name) +{ + struct symbol *sym; + bool near = false; + int cnt = 0; + + pr_err("Multiple symbols with name '%s'\n", sym_name); + + sym = dso__first_symbol(dso, MAP__FUNCTION); + while (sym) { + if (dso_sym_match(sym, sym_name, &cnt, -1)) { + pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n", + ++cnt, sym->start, + sym->binding == STB_GLOBAL ? 'g' : + sym->binding == STB_LOCAL ? 'l' : 'w', + sym->name); + near = true; + } else if (near) { + near = false; + pr_err("\t\twhich is near\t\t%s\n", sym->name); + } + sym = dso__next_symbol(sym); + } + + pr_err("Disambiguate symbol name by inserting #n after the name e.g. %s #2\n", + sym_name); + pr_err("Or select a global symbol by inserting #0 or #g or #G\n"); +} + +static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, + u64 *size, int idx) +{ + struct symbol *sym; + int cnt = 0; + + *start = 0; + *size = 0; + + sym = dso__first_symbol(dso, MAP__FUNCTION); + while (sym) { + if (*start) { + if (!*size) + *size = sym->start - *start; + if (idx > 0) { + if (*size) + return 1; + } else if (dso_sym_match(sym, sym_name, &cnt, idx)) { + print_duplicate_syms(dso, sym_name); + return -EINVAL; + } + } else if (dso_sym_match(sym, sym_name, &cnt, idx)) { + *start = sym->start; + *size = sym->end - sym->start; + } + sym = dso__next_symbol(sym); + } + + if (!*start) + return sym_not_found_error(sym_name, idx); + + return 0; +} + +static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso) +{ + struct symbol *first_sym = dso__first_symbol(dso, MAP__FUNCTION); + struct symbol *last_sym = dso__last_symbol(dso, MAP__FUNCTION); + + if (!first_sym || !last_sym) { + pr_err("Failed to determine filter for %s\nNo symbols found.\n", + filt->filename); + return -EINVAL; + } + + filt->addr = first_sym->start; + filt->size = last_sym->end - first_sym->start; + + return 0; +} + +static int addr_filter__resolve_syms(struct addr_filter *filt) +{ + u64 start, size; + struct dso *dso; + int err = 0; + + if (!filt->sym_from && !filt->sym_to) + return 0; + + if (!filt->filename) + return addr_filter__resolve_kernel_syms(filt); + + dso = load_dso(filt->filename); + if (!dso) { + pr_err("Failed to load symbols from: %s\n", filt->filename); + return -EINVAL; + } + + if (filt->sym_from && !strcmp(filt->sym_from, "*")) { + err = addr_filter__entire_dso(filt, dso); + goto put_dso; + } + + if (filt->sym_from) { + err = find_dso_sym(dso, filt->sym_from, &start, &size, + filt->sym_from_idx); + if (err) + goto put_dso; + filt->addr = start; + if (filt->range && !filt->size && !filt->sym_to) + filt->size = size; + } + + if (filt->sym_to) { + err = find_dso_sym(dso, filt->sym_to, &start, &size, + filt->sym_to_idx); + if (err) + goto put_dso; + + err = check_end_after_start(filt, start, size); + if (err) + return err; + + filt->size = start + size - filt->addr; + } + +put_dso: + dso__put(dso); + + return err; +} + +static char *addr_filter__to_str(struct addr_filter *filt) +{ + char filename_buf[PATH_MAX]; + const char *at = ""; + const char *fn = ""; + char *filter; + int err; + + if (filt->filename) { + at = "@"; + fn = realpath(filt->filename, filename_buf); + if (!fn) + return NULL; + } + + if (filt->range) { + err = asprintf(&filter, "%s 0x%"PRIx64"/0x%"PRIx64"%s%s", + filt->action, filt->addr, filt->size, at, fn); + } else { + err = asprintf(&filter, "%s 0x%"PRIx64"%s%s", + filt->action, filt->addr, at, fn); + } + + return err < 0 ? NULL : filter; +} + +static int parse_addr_filter(struct perf_evsel *evsel, const char *filter, + int max_nr) +{ + struct addr_filters filts; + struct addr_filter *filt; + int err; + + addr_filters__init(&filts); + + err = addr_filters__parse_bare_filter(&filts, filter); + if (err) + goto out_exit; + + if (filts.cnt > max_nr) { + pr_err("Error: number of address filters (%d) exceeds maximum (%d)\n", + filts.cnt, max_nr); + err = -EINVAL; + goto out_exit; + } + + list_for_each_entry(filt, &filts.head, list) { + char *new_filter; + + err = addr_filter__resolve_syms(filt); + if (err) + goto out_exit; + + new_filter = addr_filter__to_str(filt); + if (!new_filter) { + err = -ENOMEM; + goto out_exit; + } + + if (perf_evsel__append_addr_filter(evsel, new_filter)) { + err = -ENOMEM; + goto out_exit; + } + } + +out_exit: + addr_filters__exit(&filts); + + if (err) { + pr_err("Failed to parse address filter: '%s'\n", filter); + pr_err("Filter format is: filter|start|stop|tracestop <start symbol or address> [/ <end symbol or size>] [@<file name>]\n"); + pr_err("Where multiple filters are separated by space or comma.\n"); + } + + return err; +} + +static struct perf_pmu *perf_evsel__find_pmu(struct perf_evsel *evsel) +{ + struct perf_pmu *pmu = NULL; + + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + if (pmu->type == evsel->attr.type) + break; + } + + return pmu; +} + +static int perf_evsel__nr_addr_filter(struct perf_evsel *evsel) +{ + struct perf_pmu *pmu = perf_evsel__find_pmu(evsel); + int nr_addr_filters = 0; + + if (!pmu) + return 0; + + perf_pmu__scan_file(pmu, "nr_addr_filters", "%d", &nr_addr_filters); + + return nr_addr_filters; +} + +int auxtrace_parse_filters(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + char *filter; + int err, max_nr; + + evlist__for_each_entry(evlist, evsel) { + filter = evsel->filter; + max_nr = perf_evsel__nr_addr_filter(evsel); + if (!filter || !max_nr) + continue; + evsel->filter = NULL; + err = parse_addr_filter(evsel, filter, max_nr); + free(filter); + if (err) + return err; + pr_debug("Address filter: %s\n", evsel->filter); + } + + return 0; +} diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index ac5f0d7167e6..26fb1ee5746a 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -41,6 +41,7 @@ enum auxtrace_type { PERF_AUXTRACE_UNKNOWN, PERF_AUXTRACE_INTEL_PT, PERF_AUXTRACE_INTEL_BTS, + PERF_AUXTRACE_CS_ETM, }; enum itrace_period_type { @@ -317,6 +318,48 @@ struct auxtrace_record { unsigned int alignment; }; +/** + * struct addr_filter - address filter. + * @list: list node + * @range: true if it is a range filter + * @start: true if action is 'filter' or 'start' + * @action: 'filter', 'start' or 'stop' ('tracestop' is accepted but converted + * to 'stop') + * @sym_from: symbol name for the filter address + * @sym_to: symbol name that determines the filter size + * @sym_from_idx: selects n'th from symbols with the same name (0 means global + * and less than 0 means symbol must be unique) + * @sym_to_idx: same as @sym_from_idx but for @sym_to + * @addr: filter address + * @size: filter region size (for range filters) + * @filename: DSO file name or NULL for the kernel + * @str: allocated string that contains the other string members + */ +struct addr_filter { + struct list_head list; + bool range; + bool start; + const char *action; + const char *sym_from; + const char *sym_to; + int sym_from_idx; + int sym_to_idx; + u64 addr; + u64 size; + const char *filename; + char *str; +}; + +/** + * struct addr_filters - list of address filters. + * @head: list of address filters + * @cnt: number of address filters + */ +struct addr_filters { + struct list_head head; + int cnt; +}; + #ifdef HAVE_AUXTRACE_SUPPORT /* @@ -481,6 +524,12 @@ void perf_session__auxtrace_error_inc(struct perf_session *session, union perf_event *event); void events_stats__auxtrace_error_warn(const struct events_stats *stats); +void addr_filters__init(struct addr_filters *filts); +void addr_filters__exit(struct addr_filters *filts); +int addr_filters__parse_bare_filter(struct addr_filters *filts, + const char *filter); +int auxtrace_parse_filters(struct perf_evlist *evlist); + static inline int auxtrace__process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -639,6 +688,12 @@ void auxtrace_index__free(struct list_head *head __maybe_unused) { } +static inline +int auxtrace_parse_filters(struct perf_evlist *evlist __maybe_unused) +{ + return 0; +} + int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, struct auxtrace_mmap_params *mp, void *userpg, int fd); diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c new file mode 100644 index 000000000000..7b3e1d75d803 --- /dev/null +++ b/tools/perf/util/block-range.c @@ -0,0 +1,328 @@ +#include "block-range.h" +#include "annotate.h" + +struct { + struct rb_root root; + u64 blocks; +} block_ranges; + +static void block_range__debug(void) +{ + /* + * XXX still paranoid for now; see if we can make this depend on + * DEBUG=1 builds. + */ +#if 1 + struct rb_node *rb; + u64 old = 0; /* NULL isn't executable */ + + for (rb = rb_first(&block_ranges.root); rb; rb = rb_next(rb)) { + struct block_range *entry = rb_entry(rb, struct block_range, node); + + assert(old < entry->start); + assert(entry->start <= entry->end); /* single instruction block; jump to a jump */ + + old = entry->end; + } +#endif +} + +struct block_range *block_range__find(u64 addr) +{ + struct rb_node **p = &block_ranges.root.rb_node; + struct rb_node *parent = NULL; + struct block_range *entry; + + while (*p != NULL) { + parent = *p; + entry = rb_entry(parent, struct block_range, node); + + if (addr < entry->start) + p = &parent->rb_left; + else if (addr > entry->end) + p = &parent->rb_right; + else + return entry; + } + + return NULL; +} + +static inline void rb_link_left_of_node(struct rb_node *left, struct rb_node *node) +{ + struct rb_node **p = &node->rb_left; + while (*p) { + node = *p; + p = &node->rb_right; + } + rb_link_node(left, node, p); +} + +static inline void rb_link_right_of_node(struct rb_node *right, struct rb_node *node) +{ + struct rb_node **p = &node->rb_right; + while (*p) { + node = *p; + p = &node->rb_left; + } + rb_link_node(right, node, p); +} + +/** + * block_range__create + * @start: branch target starting this basic block + * @end: branch ending this basic block + * + * Create all the required block ranges to precisely span the given range. + */ +struct block_range_iter block_range__create(u64 start, u64 end) +{ + struct rb_node **p = &block_ranges.root.rb_node; + struct rb_node *n, *parent = NULL; + struct block_range *next, *entry = NULL; + struct block_range_iter iter = { NULL, NULL }; + + while (*p != NULL) { + parent = *p; + entry = rb_entry(parent, struct block_range, node); + + if (start < entry->start) + p = &parent->rb_left; + else if (start > entry->end) + p = &parent->rb_right; + else + break; + } + + /* + * Didn't find anything.. there's a hole at @start, however @end might + * be inside/behind the next range. + */ + if (!*p) { + if (!entry) /* tree empty */ + goto do_whole; + + /* + * If the last node is before, advance one to find the next. + */ + n = parent; + if (entry->end < start) { + n = rb_next(n); + if (!n) + goto do_whole; + } + next = rb_entry(n, struct block_range, node); + + if (next->start <= end) { /* add head: [start...][n->start...] */ + struct block_range *head = malloc(sizeof(struct block_range)); + if (!head) + return iter; + + *head = (struct block_range){ + .start = start, + .end = next->start - 1, + .is_target = 1, + .is_branch = 0, + }; + + rb_link_left_of_node(&head->node, &next->node); + rb_insert_color(&head->node, &block_ranges.root); + block_range__debug(); + + iter.start = head; + goto do_tail; + } + +do_whole: + /* + * The whole [start..end] range is non-overlapping. + */ + entry = malloc(sizeof(struct block_range)); + if (!entry) + return iter; + + *entry = (struct block_range){ + .start = start, + .end = end, + .is_target = 1, + .is_branch = 1, + }; + + rb_link_node(&entry->node, parent, p); + rb_insert_color(&entry->node, &block_ranges.root); + block_range__debug(); + + iter.start = entry; + iter.end = entry; + goto done; + } + + /* + * We found a range that overlapped with ours, split if needed. + */ + if (entry->start < start) { /* split: [e->start...][start...] */ + struct block_range *head = malloc(sizeof(struct block_range)); + if (!head) + return iter; + + *head = (struct block_range){ + .start = entry->start, + .end = start - 1, + .is_target = entry->is_target, + .is_branch = 0, + + .coverage = entry->coverage, + .entry = entry->entry, + }; + + entry->start = start; + entry->is_target = 1; + entry->entry = 0; + + rb_link_left_of_node(&head->node, &entry->node); + rb_insert_color(&head->node, &block_ranges.root); + block_range__debug(); + + } else if (entry->start == start) + entry->is_target = 1; + + iter.start = entry; + +do_tail: + /* + * At this point we've got: @iter.start = [@start...] but @end can still be + * inside or beyond it. + */ + entry = iter.start; + for (;;) { + /* + * If @end is inside @entry, split. + */ + if (end < entry->end) { /* split: [...end][...e->end] */ + struct block_range *tail = malloc(sizeof(struct block_range)); + if (!tail) + return iter; + + *tail = (struct block_range){ + .start = end + 1, + .end = entry->end, + .is_target = 0, + .is_branch = entry->is_branch, + + .coverage = entry->coverage, + .taken = entry->taken, + .pred = entry->pred, + }; + + entry->end = end; + entry->is_branch = 1; + entry->taken = 0; + entry->pred = 0; + + rb_link_right_of_node(&tail->node, &entry->node); + rb_insert_color(&tail->node, &block_ranges.root); + block_range__debug(); + + iter.end = entry; + goto done; + } + + /* + * If @end matches @entry, done + */ + if (end == entry->end) { + entry->is_branch = 1; + iter.end = entry; + goto done; + } + + next = block_range__next(entry); + if (!next) + goto add_tail; + + /* + * If @end is in beyond @entry but not inside @next, add tail. + */ + if (end < next->start) { /* add tail: [...e->end][...end] */ + struct block_range *tail; +add_tail: + tail = malloc(sizeof(struct block_range)); + if (!tail) + return iter; + + *tail = (struct block_range){ + .start = entry->end + 1, + .end = end, + .is_target = 0, + .is_branch = 1, + }; + + rb_link_right_of_node(&tail->node, &entry->node); + rb_insert_color(&tail->node, &block_ranges.root); + block_range__debug(); + + iter.end = tail; + goto done; + } + + /* + * If there is a hole between @entry and @next, fill it. + */ + if (entry->end + 1 != next->start) { + struct block_range *hole = malloc(sizeof(struct block_range)); + if (!hole) + return iter; + + *hole = (struct block_range){ + .start = entry->end + 1, + .end = next->start - 1, + .is_target = 0, + .is_branch = 0, + }; + + rb_link_left_of_node(&hole->node, &next->node); + rb_insert_color(&hole->node, &block_ranges.root); + block_range__debug(); + } + + entry = next; + } + +done: + assert(iter.start->start == start && iter.start->is_target); + assert(iter.end->end == end && iter.end->is_branch); + + block_ranges.blocks++; + + return iter; +} + + +/* + * Compute coverage as: + * + * br->coverage / br->sym->max_coverage + * + * This ensures each symbol has a 100% spot, to reflect that each symbol has a + * most covered section. + * + * Returns [0-1] for coverage and -1 if we had no data what so ever or the + * symbol does not exist. + */ +double block_range__coverage(struct block_range *br) +{ + struct symbol *sym; + + if (!br) { + if (block_ranges.blocks) + return 0; + + return -1; + } + + sym = br->sym; + if (!sym) + return -1; + + return (double)br->coverage / symbol__annotation(sym)->max_coverage; +} diff --git a/tools/perf/util/block-range.h b/tools/perf/util/block-range.h new file mode 100644 index 000000000000..a8c841381131 --- /dev/null +++ b/tools/perf/util/block-range.h @@ -0,0 +1,71 @@ +#ifndef __PERF_BLOCK_RANGE_H +#define __PERF_BLOCK_RANGE_H + +#include "symbol.h" + +/* + * struct block_range - non-overlapping parts of basic blocks + * @node: treenode + * @start: inclusive start of range + * @end: inclusive end of range + * @is_target: @start is a jump target + * @is_branch: @end is a branch instruction + * @coverage: number of blocks that cover this range + * @taken: number of times the branch is taken (requires @is_branch) + * @pred: number of times the taken branch was predicted + */ +struct block_range { + struct rb_node node; + + struct symbol *sym; + + u64 start; + u64 end; + + int is_target, is_branch; + + u64 coverage; + u64 entry; + u64 taken; + u64 pred; +}; + +static inline struct block_range *block_range__next(struct block_range *br) +{ + struct rb_node *n = rb_next(&br->node); + if (!n) + return NULL; + return rb_entry(n, struct block_range, node); +} + +struct block_range_iter { + struct block_range *start; + struct block_range *end; +}; + +static inline struct block_range *block_range_iter(struct block_range_iter *iter) +{ + return iter->start; +} + +static inline bool block_range_iter__next(struct block_range_iter *iter) +{ + if (iter->start == iter->end) + return false; + + iter->start = block_range__next(iter->start); + return true; +} + +static inline bool block_range_iter__valid(struct block_range_iter *iter) +{ + if (!iter->start || !iter->end) + return false; + return true; +} + +extern struct block_range *block_range__find(u64 addr); +extern struct block_range_iter block_range__create(u64 start, u64 end); +extern double block_range__coverage(struct block_range *br); + +#endif /* __PERF_BLOCK_RANGE_H */ diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 1f12e4e40006..36c861103291 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -14,11 +14,11 @@ #include "debug.h" #include "bpf-loader.h" #include "bpf-prologue.h" -#include "llvm-utils.h" #include "probe-event.h" #include "probe-finder.h" // for MAX_PROBES #include "parse-events.h" #include "llvm-utils.h" +#include "c++/clang-c.h" #define DEFINE_PRINT_FN(name, level) \ static int libbpf_##name(const char *fmt, ...) \ @@ -86,10 +86,21 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) void *obj_buf; size_t obj_buf_sz; - err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz); - if (err) - return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE); + perf_clang__init(); + err = perf_clang__compile_bpf(filename, &obj_buf, &obj_buf_sz); + perf_clang__cleanup(); + if (err) { + pr_warning("bpf: builtin compilation failed: %d, try external compiler\n", err); + err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz); + if (err) + return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE); + } else + pr_debug("bpf: successfull builtin compilation\n"); obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename); + + if (!IS_ERR(obj) && llvm_param.dump_obj) + llvm__dump_obj(filename, obj_buf, obj_buf_sz); + free(obj_buf); } else obj = bpf_object__open(filename); @@ -241,7 +252,7 @@ parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev) int err = 0; if (!text) { - pr_debug("No enough memory: dup config_str failed\n"); + pr_debug("Not enough memory: dup config_str failed\n"); return ERR_PTR(-ENOMEM); } @@ -531,7 +542,7 @@ static int map_prologue(struct perf_probe_event *pev, int *mapping, ptevs = malloc(array_sz); if (!ptevs) { - pr_debug("No ehough memory: alloc ptevs failed\n"); + pr_debug("Not enough memory: alloc ptevs failed\n"); return -ENOMEM; } @@ -604,13 +615,13 @@ static int hook_load_preprocessor(struct bpf_program *prog) priv->need_prologue = true; priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS); if (!priv->insns_buf) { - pr_debug("No enough memory: alloc insns_buf failed\n"); + pr_debug("Not enough memory: alloc insns_buf failed\n"); return -ENOMEM; } priv->type_mapping = malloc(sizeof(int) * pev->ntevs); if (!priv->type_mapping) { - pr_debug("No enough memory: alloc type_mapping failed\n"); + pr_debug("Not enough memory: alloc type_mapping failed\n"); return -ENOMEM; } memset(priv->type_mapping, -1, @@ -864,7 +875,7 @@ bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term) op->k.array.ranges = memdup(term->array.ranges, memsz); if (!op->k.array.ranges) { - pr_debug("No enough memory to alloc indices for map\n"); + pr_debug("Not enough memory to alloc indices for map\n"); return -ENOMEM; } op->key_type = BPF_MAP_KEY_RANGES; @@ -929,7 +940,7 @@ bpf_map_priv__clone(struct bpf_map_priv *priv) newpriv = zalloc(sizeof(*newpriv)); if (!newpriv) { - pr_debug("No enough memory to alloc map private\n"); + pr_debug("Not enough memory to alloc map private\n"); return NULL; } INIT_LIST_HEAD(&newpriv->ops_list); @@ -960,7 +971,7 @@ bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op) if (!priv) { priv = zalloc(sizeof(*priv)); if (!priv) { - pr_debug("No enough memory to alloc map private\n"); + pr_debug("Not enough memory to alloc map private\n"); return -ENOMEM; } INIT_LIST_HEAD(&priv->ops_list); diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 5651f3c12f93..e528c40739cc 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -620,7 +620,7 @@ static int build_id_cache__add_sdt_cache(const char *sbuild_id, ret = probe_cache__scan_sdt(cache, realname); if (ret >= 0) { - pr_debug("Found %d SDTs in %s\n", ret, realname); + pr_debug4("Found %d SDTs in %s\n", ret, realname); if (probe_cache__commit(cache) < 0) ret = -1; } @@ -691,7 +691,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, /* Update SDT cache : error is just warned */ if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) - pr_debug("Failed to update/scan SDT cache for %s\n", realname); + pr_debug4("Failed to update/scan SDT cache for %s\n", realname); out_free: if (!is_kallsyms) diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build new file mode 100644 index 000000000000..988fef1b11d7 --- /dev/null +++ b/tools/perf/util/c++/Build @@ -0,0 +1,2 @@ +libperf-$(CONFIG_CLANGLLVM) += clang.o +libperf-$(CONFIG_CLANGLLVM) += clang-test.o diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h new file mode 100644 index 000000000000..0eadd792ab1f --- /dev/null +++ b/tools/perf/util/c++/clang-c.h @@ -0,0 +1,43 @@ +#ifndef PERF_UTIL_CLANG_C_H +#define PERF_UTIL_CLANG_C_H + +#include <stddef.h> /* for size_t */ +#include <util-cxx.h> /* for __maybe_unused */ + +#ifdef __cplusplus +extern "C" { +#endif + +#ifdef HAVE_LIBCLANGLLVM_SUPPORT +extern void perf_clang__init(void); +extern void perf_clang__cleanup(void); + +extern int test__clang_to_IR(void); +extern int test__clang_to_obj(void); + +extern int perf_clang__compile_bpf(const char *filename, + void **p_obj_buf, + size_t *p_obj_buf_sz); +#else + + +static inline void perf_clang__init(void) { } +static inline void perf_clang__cleanup(void) { } + +static inline int test__clang_to_IR(void) { return -1; } +static inline int test__clang_to_obj(void) { return -1;} + +static inline int +perf_clang__compile_bpf(const char *filename __maybe_unused, + void **p_obj_buf __maybe_unused, + size_t *p_obj_buf_sz __maybe_unused) +{ + return -ENOTSUP; +} + +#endif + +#ifdef __cplusplus +} +#endif +#endif diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp new file mode 100644 index 000000000000..9b11e8c82798 --- /dev/null +++ b/tools/perf/util/c++/clang-test.cpp @@ -0,0 +1,62 @@ +#include "clang.h" +#include "clang-c.h" +#include "llvm/IR/Function.h" +#include "llvm/IR/LLVMContext.h" + +#include <util-cxx.h> +#include <tests/llvm.h> +#include <string> + +class perf_clang_scope { +public: + explicit perf_clang_scope() {perf_clang__init();} + ~perf_clang_scope() {perf_clang__cleanup();} +}; + +static std::unique_ptr<llvm::Module> +__test__clang_to_IR(void) +{ + unsigned int kernel_version; + + if (fetch_kernel_version(&kernel_version, NULL, 0)) + return std::unique_ptr<llvm::Module>(nullptr); + + std::string cflag_kver("-DLINUX_VERSION_CODE=" + + std::to_string(kernel_version)); + + std::unique_ptr<llvm::Module> M = + perf::getModuleFromSource({cflag_kver.c_str()}, + "perf-test.c", + test_llvm__bpf_base_prog); + return M; +} + +extern "C" { +int test__clang_to_IR(void) +{ + perf_clang_scope _scope; + + auto M = __test__clang_to_IR(); + if (!M) + return -1; + for (llvm::Function& F : *M) + if (F.getName() == "bpf_func__SyS_epoll_wait") + return 0; + return -1; +} + +int test__clang_to_obj(void) +{ + perf_clang_scope _scope; + + auto M = __test__clang_to_IR(); + if (!M) + return -1; + + auto Buffer = perf::getBPFObjectFromModule(&*M); + if (!Buffer) + return -1; + return 0; +} + +} diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp new file mode 100644 index 000000000000..1e974152cac2 --- /dev/null +++ b/tools/perf/util/c++/clang.cpp @@ -0,0 +1,195 @@ +/* + * llvm C frontend for perf. Support dynamically compile C file + * + * Inspired by clang example code: + * http://llvm.org/svn/llvm-project/cfe/trunk/examples/clang-interpreter/main.cpp + * + * Copyright (C) 2016 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2016 Huawei Inc. + */ + +#include "clang/CodeGen/CodeGenAction.h" +#include "clang/Frontend/CompilerInvocation.h" +#include "clang/Frontend/CompilerInstance.h" +#include "clang/Frontend/TextDiagnosticPrinter.h" +#include "clang/Tooling/Tooling.h" +#include "llvm/IR/LegacyPassManager.h" +#include "llvm/IR/Module.h" +#include "llvm/Option/Option.h" +#include "llvm/Support/FileSystem.h" +#include "llvm/Support/ManagedStatic.h" +#include "llvm/Support/TargetRegistry.h" +#include "llvm/Support/TargetSelect.h" +#include "llvm/Target/TargetMachine.h" +#include "llvm/Target/TargetOptions.h" +#include <memory> + +#include "clang.h" +#include "clang-c.h" + +namespace perf { + +static std::unique_ptr<llvm::LLVMContext> LLVMCtx; + +using namespace clang; + +static CompilerInvocation * +createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, + DiagnosticsEngine& Diags) +{ + llvm::opt::ArgStringList CCArgs { + "-cc1", + "-triple", "bpf-pc-linux", + "-fsyntax-only", + "-ferror-limit", "19", + "-fmessage-length", "127", + "-O2", + "-nostdsysteminc", + "-nobuiltininc", + "-vectorize-loops", + "-vectorize-slp", + "-Wno-unused-value", + "-Wno-pointer-sign", + "-x", "c"}; + + CCArgs.append(CFlags.begin(), CFlags.end()); + CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs); + + FrontendOptions& Opts = CI->getFrontendOpts(); + Opts.Inputs.clear(); + Opts.Inputs.emplace_back(Path, IK_C); + return CI; +} + +static std::unique_ptr<llvm::Module> +getModuleFromSource(llvm::opt::ArgStringList CFlags, + StringRef Path, IntrusiveRefCntPtr<vfs::FileSystem> VFS) +{ + CompilerInstance Clang; + Clang.createDiagnostics(); + + Clang.setVirtualFileSystem(&*VFS); + + IntrusiveRefCntPtr<CompilerInvocation> CI = + createCompilerInvocation(std::move(CFlags), Path, + Clang.getDiagnostics()); + Clang.setInvocation(&*CI); + + std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx)); + if (!Clang.ExecuteAction(*Act)) + return std::unique_ptr<llvm::Module>(nullptr); + + return Act->takeModule(); +} + +std::unique_ptr<llvm::Module> +getModuleFromSource(llvm::opt::ArgStringList CFlags, + StringRef Name, StringRef Content) +{ + using namespace vfs; + + llvm::IntrusiveRefCntPtr<OverlayFileSystem> OverlayFS( + new OverlayFileSystem(getRealFileSystem())); + llvm::IntrusiveRefCntPtr<InMemoryFileSystem> MemFS( + new InMemoryFileSystem(true)); + + /* + * pushOverlay helps setting working dir for MemFS. Must call + * before addFile. + */ + OverlayFS->pushOverlay(MemFS); + MemFS->addFile(Twine(Name), 0, llvm::MemoryBuffer::getMemBuffer(Content)); + + return getModuleFromSource(std::move(CFlags), Name, OverlayFS); +} + +std::unique_ptr<llvm::Module> +getModuleFromSource(llvm::opt::ArgStringList CFlags, StringRef Path) +{ + IntrusiveRefCntPtr<vfs::FileSystem> VFS(vfs::getRealFileSystem()); + return getModuleFromSource(std::move(CFlags), Path, VFS); +} + +std::unique_ptr<llvm::SmallVectorImpl<char>> +getBPFObjectFromModule(llvm::Module *Module) +{ + using namespace llvm; + + std::string TargetTriple("bpf-pc-linux"); + std::string Error; + const Target* Target = TargetRegistry::lookupTarget(TargetTriple, Error); + if (!Target) { + llvm::errs() << Error; + return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr); + } + + llvm::TargetOptions Opt; + TargetMachine *TargetMachine = + Target->createTargetMachine(TargetTriple, + "generic", "", + Opt, Reloc::Static); + + Module->setDataLayout(TargetMachine->createDataLayout()); + Module->setTargetTriple(TargetTriple); + + std::unique_ptr<SmallVectorImpl<char>> Buffer(new SmallVector<char, 0>()); + raw_svector_ostream ostream(*Buffer); + + legacy::PassManager PM; + if (TargetMachine->addPassesToEmitFile(PM, ostream, + TargetMachine::CGFT_ObjectFile)) { + llvm::errs() << "TargetMachine can't emit a file of this type\n"; + return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);; + } + PM.run(*Module); + + return std::move(Buffer); +} + +} + +extern "C" { +void perf_clang__init(void) +{ + perf::LLVMCtx.reset(new llvm::LLVMContext()); + LLVMInitializeBPFTargetInfo(); + LLVMInitializeBPFTarget(); + LLVMInitializeBPFTargetMC(); + LLVMInitializeBPFAsmPrinter(); +} + +void perf_clang__cleanup(void) +{ + perf::LLVMCtx.reset(nullptr); + llvm::llvm_shutdown(); +} + +int perf_clang__compile_bpf(const char *filename, + void **p_obj_buf, + size_t *p_obj_buf_sz) +{ + using namespace perf; + + if (!p_obj_buf || !p_obj_buf_sz) + return -EINVAL; + + llvm::opt::ArgStringList CFlags; + auto M = getModuleFromSource(std::move(CFlags), filename); + if (!M) + return -EINVAL; + auto O = getBPFObjectFromModule(&*M); + if (!O) + return -EINVAL; + + size_t size = O->size_in_bytes(); + void *buffer; + + buffer = malloc(size); + if (!buffer) + return -ENOMEM; + memcpy(buffer, O->data(), size); + *p_obj_buf = buffer; + *p_obj_buf_sz = size; + return 0; +} +} diff --git a/tools/perf/util/c++/clang.h b/tools/perf/util/c++/clang.h new file mode 100644 index 000000000000..dd8b0427550d --- /dev/null +++ b/tools/perf/util/c++/clang.h @@ -0,0 +1,26 @@ +#ifndef PERF_UTIL_CLANG_H +#define PERF_UTIL_CLANG_H + +#include "llvm/ADT/StringRef.h" +#include "llvm/IR/LLVMContext.h" +#include "llvm/IR/Module.h" +#include "llvm/Option/Option.h" +#include <memory> + +namespace perf { + +using namespace llvm; + +std::unique_ptr<Module> +getModuleFromSource(opt::ArgStringList CFlags, + StringRef Name, StringRef Content); + +std::unique_ptr<Module> +getModuleFromSource(opt::ArgStringList CFlags, + StringRef Path); + +std::unique_ptr<llvm::SmallVectorImpl<char>> +getBPFObjectFromModule(llvm::Module *Module); + +} +#endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 07fd30bc2f81..42922512c1c6 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -193,7 +193,6 @@ int perf_callchain_config(const char *var, const char *value) if (!strcmp(var, "record-mode")) return parse_callchain_record_opt(value, &callchain_param); -#ifdef HAVE_DWARF_UNWIND_SUPPORT if (!strcmp(var, "dump-size")) { unsigned long size = 0; int ret; @@ -203,7 +202,6 @@ int perf_callchain_config(const char *var, const char *value) return ret; } -#endif if (!strcmp(var, "print-type")) return parse_callchain_mode(value); if (!strcmp(var, "order")) @@ -440,6 +438,21 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) call->ip = cursor_node->ip; call->ms.sym = cursor_node->sym; call->ms.map = cursor_node->map; + + if (cursor_node->branch) { + call->branch_count = 1; + + if (cursor_node->branch_flags.predicted) + call->predicted_count = 1; + + if (cursor_node->branch_flags.abort) + call->abort_count = 1; + + call->cycles_count = cursor_node->branch_flags.cycles; + call->iter_count = cursor_node->nr_loop_iter; + call->samples_count = cursor_node->samples; + } + list_add_tail(&call->list, &node->val); callchain_cursor_advance(cursor); @@ -499,8 +512,23 @@ static enum match_result match_chain(struct callchain_cursor_node *node, right = node->ip; } - if (left == right) + if (left == right) { + if (node->branch) { + cnode->branch_count++; + + if (node->branch_flags.predicted) + cnode->predicted_count++; + + if (node->branch_flags.abort) + cnode->abort_count++; + + cnode->cycles_count += node->branch_flags.cycles; + cnode->iter_count += node->nr_loop_iter; + cnode->samples_count += node->samples; + } + return MATCH_EQ; + } return left > right ? MATCH_GT : MATCH_LT; } @@ -730,7 +758,8 @@ merge_chain_branch(struct callchain_cursor *cursor, list_for_each_entry_safe(list, next_list, &src->val, list) { callchain_cursor_append(cursor, list->ip, - list->ms.map, list->ms.sym); + list->ms.map, list->ms.sym, + false, NULL, 0, 0); list_del(&list->list); free(list); } @@ -767,7 +796,9 @@ int callchain_merge(struct callchain_cursor *cursor, } int callchain_cursor_append(struct callchain_cursor *cursor, - u64 ip, struct map *map, struct symbol *sym) + u64 ip, struct map *map, struct symbol *sym, + bool branch, struct branch_flags *flags, + int nr_loop_iter, int samples) { struct callchain_cursor_node *node = *cursor->last; @@ -782,6 +813,13 @@ int callchain_cursor_append(struct callchain_cursor *cursor, node->ip = ip; node->map = map; node->sym = sym; + node->branch = branch; + node->nr_loop_iter = nr_loop_iter; + node->samples = samples; + + if (flags) + memcpy(&node->branch_flags, flags, + sizeof(struct branch_flags)); cursor->nr++; @@ -939,6 +977,163 @@ int callchain_node__fprintf_value(struct callchain_node *node, return 0; } +static void callchain_counts_value(struct callchain_node *node, + u64 *branch_count, u64 *predicted_count, + u64 *abort_count, u64 *cycles_count) +{ + struct callchain_list *clist; + + list_for_each_entry(clist, &node->val, list) { + if (branch_count) + *branch_count += clist->branch_count; + + if (predicted_count) + *predicted_count += clist->predicted_count; + + if (abort_count) + *abort_count += clist->abort_count; + + if (cycles_count) + *cycles_count += clist->cycles_count; + } +} + +static int callchain_node_branch_counts_cumul(struct callchain_node *node, + u64 *branch_count, + u64 *predicted_count, + u64 *abort_count, + u64 *cycles_count) +{ + struct callchain_node *child; + struct rb_node *n; + + n = rb_first(&node->rb_root_in); + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + n = rb_next(n); + + callchain_node_branch_counts_cumul(child, branch_count, + predicted_count, + abort_count, + cycles_count); + + callchain_counts_value(child, branch_count, + predicted_count, abort_count, + cycles_count); + } + + return 0; +} + +int callchain_branch_counts(struct callchain_root *root, + u64 *branch_count, u64 *predicted_count, + u64 *abort_count, u64 *cycles_count) +{ + if (branch_count) + *branch_count = 0; + + if (predicted_count) + *predicted_count = 0; + + if (abort_count) + *abort_count = 0; + + if (cycles_count) + *cycles_count = 0; + + return callchain_node_branch_counts_cumul(&root->node, + branch_count, + predicted_count, + abort_count, + cycles_count); +} + +static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, u64 cycles_count, + u64 iter_count, u64 samples_count) +{ + double predicted_percent = 0.0; + const char *null_str = ""; + char iter_str[32]; + char *str; + u64 cycles = 0; + + if (branch_count == 0) { + if (fp) + return fprintf(fp, " (calltrace)"); + + return scnprintf(bf, bfsize, " (calltrace)"); + } + + if (iter_count && samples_count) { + scnprintf(iter_str, sizeof(iter_str), + ", iterations:%" PRId64 "", + iter_count / samples_count); + str = iter_str; + } else + str = (char *)null_str; + + predicted_percent = predicted_count * 100.0 / branch_count; + cycles = cycles_count / branch_count; + + if ((predicted_percent >= 100.0) && (abort_count == 0)) { + if (fp) + return fprintf(fp, " (cycles:%" PRId64 "%s)", + cycles, str); + + return scnprintf(bf, bfsize, " (cycles:%" PRId64 "%s)", + cycles, str); + } + + if ((predicted_percent < 100.0) && (abort_count == 0)) { + if (fp) + return fprintf(fp, + " (predicted:%.1f%%, cycles:%" PRId64 "%s)", + predicted_percent, cycles, str); + + return scnprintf(bf, bfsize, + " (predicted:%.1f%%, cycles:%" PRId64 "%s)", + predicted_percent, cycles, str); + } + + if (fp) + return fprintf(fp, + " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)", + predicted_percent, abort_count, cycles, str); + + return scnprintf(bf, bfsize, + " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)", + predicted_percent, abort_count, cycles, str); +} + +int callchain_list_counts__printf_value(struct callchain_node *node, + struct callchain_list *clist, + FILE *fp, char *bf, int bfsize) +{ + u64 branch_count, predicted_count; + u64 abort_count, cycles_count; + u64 iter_count = 0, samples_count = 0; + + branch_count = clist->branch_count; + predicted_count = clist->predicted_count; + abort_count = clist->abort_count; + cycles_count = clist->cycles_count; + + if (node) { + struct callchain_list *call; + + list_for_each_entry(call, &node->val, list) { + iter_count += call->iter_count; + samples_count += call->samples_count; + } + } + + return callchain_counts_printf(fp, bf, bfsize, branch_count, + predicted_count, abort_count, + cycles_count, iter_count, samples_count); +} + static void free_callchain_node(struct callchain_node *node) { struct callchain_list *list, *tmp; @@ -1039,3 +1234,30 @@ out: } return -ENOMEM; } + +int callchain_cursor__copy(struct callchain_cursor *dst, + struct callchain_cursor *src) +{ + int rc = 0; + + callchain_cursor_reset(dst); + callchain_cursor_commit(src); + + while (true) { + struct callchain_cursor_node *node; + + node = callchain_cursor_current(src); + if (node == NULL) + break; + + rc = callchain_cursor_append(dst, node->ip, node->map, node->sym, + node->branch, &node->branch_flags, + node->nr_loop_iter, node->samples); + if (rc) + break; + + callchain_cursor_advance(src); + } + + return rc; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 13e75549c440..35c8e379530f 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -11,11 +11,7 @@ #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n" -#ifdef HAVE_DWARF_UNWIND_SUPPORT # define RECORD_MODE_HELP HELP_PAD "record_mode:\tcall graph recording mode (fp|dwarf|lbr)\n" -#else -# define RECORD_MODE_HELP HELP_PAD "record_mode:\tcall graph recording mode (fp|lbr)\n" -#endif #define RECORD_SIZE_HELP \ HELP_PAD "record_size:\tif record_mode is 'dwarf', max size of stack recording (<bytes>)\n" \ @@ -115,6 +111,12 @@ struct callchain_list { bool unfolded; bool has_children; }; + u64 branch_count; + u64 predicted_count; + u64 abort_count; + u64 cycles_count; + u64 iter_count; + u64 samples_count; char *srcline; struct list_head list; }; @@ -129,6 +131,10 @@ struct callchain_cursor_node { u64 ip; struct map *map; struct symbol *sym; + bool branch; + struct branch_flags branch_flags; + int nr_loop_iter; + int samples; struct callchain_cursor_node *next; }; @@ -183,7 +189,9 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor) } int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, - struct map *map, struct symbol *sym); + struct map *map, struct symbol *sym, + bool branch, struct branch_flags *flags, + int nr_loop_iter, int samples); /* Close a cursor writing session. Initialize for the reader */ static inline void callchain_cursor_commit(struct callchain_cursor *cursor) @@ -208,6 +216,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) cursor->pos++; } +int callchain_cursor__copy(struct callchain_cursor *dst, + struct callchain_cursor *src); + struct option; struct hist_entry; @@ -261,8 +272,16 @@ char *callchain_node__scnprintf_value(struct callchain_node *node, int callchain_node__fprintf_value(struct callchain_node *node, FILE *fp, u64 total); +int callchain_list_counts__printf_value(struct callchain_node *node, + struct callchain_list *clist, + FILE *fp, char *bf, int bfsize); + void free_callchain(struct callchain_root *root); void decay_callchain(struct callchain_root *root); int callchain_node__make_parent_list(struct callchain_node *node); +int callchain_branch_counts(struct callchain_root *root, + u64 *branch_count, u64 *predicted_count, + u64 *abort_count, u64 *cycles_count); + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 18dae745034f..3d906dbbef74 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -594,6 +594,19 @@ static int collect_config(const char *var, const char *value, goto out_free; } + /* perf_config_set can contain both user and system config items. + * So we should know where each value is from. + * The classification would be needed when a particular config file + * is overwrited by setting feature i.e. set_config(). + */ + if (strcmp(config_file_name, perf_etc_perfconfig()) == 0) { + section->from_system_config = true; + item->from_system_config = true; + } else { + section->from_system_config = false; + item->from_system_config = false; + } + ret = set_value(item, value); return ret; @@ -602,6 +615,13 @@ out_free: return -1; } +int perf_config_set__collect(struct perf_config_set *set, const char *file_name, + const char *var, const char *value) +{ + config_file_name = file_name; + return collect_config(var, value, set); +} + static int perf_config_set__init(struct perf_config_set *set) { int ret = -1; diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 6f813d46045e..1a59a6b43f8b 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -7,12 +7,14 @@ struct perf_config_item { char *name; char *value; + bool from_system_config; struct list_head node; }; struct perf_config_section { char *name; struct list_head items; + bool from_system_config; struct list_head node; }; @@ -33,6 +35,8 @@ const char *perf_etc_perfconfig(void); struct perf_config_set *perf_config_set__new(void); void perf_config_set__delete(struct perf_config_set *set); +int perf_config_set__collect(struct perf_config_set *set, const char *file_name, + const char *var, const char *value); void perf_config__init(void); void perf_config__exit(void); void perf_config__refresh(void); diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h new file mode 100644 index 000000000000..3cc6bc3263fe --- /dev/null +++ b/tools/perf/util/cs-etm.h @@ -0,0 +1,74 @@ +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef INCLUDE__UTIL_PERF_CS_ETM_H__ +#define INCLUDE__UTIL_PERF_CS_ETM_H__ + +/* Versionning header in case things need tro change in the future. That way + * decoding of old snapshot is still possible. + */ +enum { + /* Starting with 0x0 */ + CS_HEADER_VERSION_0, + /* PMU->type (32 bit), total # of CPUs (32 bit) */ + CS_PMU_TYPE_CPUS, + CS_ETM_SNAPSHOT, + CS_HEADER_VERSION_0_MAX, +}; + +/* Beginning of header common to both ETMv3 and V4 */ +enum { + CS_ETM_MAGIC, + CS_ETM_CPU, +}; + +/* ETMv3/PTM metadata */ +enum { + /* Dynamic, configurable parameters */ + CS_ETM_ETMCR = CS_ETM_CPU + 1, + CS_ETM_ETMTRACEIDR, + /* RO, taken from sysFS */ + CS_ETM_ETMCCER, + CS_ETM_ETMIDR, + CS_ETM_PRIV_MAX, +}; + +/* ETMv4 metadata */ +enum { + /* Dynamic, configurable parameters */ + CS_ETMV4_TRCCONFIGR = CS_ETM_CPU + 1, + CS_ETMV4_TRCTRACEIDR, + /* RO, taken from sysFS */ + CS_ETMV4_TRCIDR0, + CS_ETMV4_TRCIDR1, + CS_ETMV4_TRCIDR2, + CS_ETMV4_TRCIDR8, + CS_ETMV4_TRCAUTHSTATUS, + CS_ETMV4_PRIV_MAX, +}; + +#define KiB(x) ((x) * 1024) +#define MiB(x) ((x) * 1024 * 1024) + +#define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_0_MAX * sizeof(u64)) + +static const u64 __perf_cs_etmv3_magic = 0x3030303030303030ULL; +static const u64 __perf_cs_etmv4_magic = 0x4040404040404040ULL; +#define CS_ETMV3_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64)) +#define CS_ETMV4_PRIV_SIZE (CS_ETMV4_PRIV_MAX * sizeof(u64)) + +#endif diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 4f979bb27b6c..7123f4de32cc 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -437,7 +437,7 @@ add_bpf_output_values(struct bt_ctf_event_class *event_class, int ret; if (nr_elements * sizeof(u32) != raw_size) - pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n", + pr_warning("Incorrect raw_size (%u) in bpf output event, skip %zu bytes\n", raw_size, nr_elements * sizeof(u32) - raw_size); len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len"); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 8c4212abd19b..c1838b643108 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -6,6 +6,7 @@ #include <stdarg.h> #include <stdio.h> #include <api/debug.h> +#include <linux/time64.h> #include "cache.h" #include "color.h" @@ -14,9 +15,6 @@ #include "util.h" #include "target.h" -#define NSECS_PER_SEC 1000000000ULL -#define NSECS_PER_USEC 1000ULL - int verbose; bool dump_trace = false, quiet = false; int debug_ordered_events; @@ -54,9 +52,9 @@ static int veprintf_time(u64 t, const char *fmt, va_list args) int ret = 0; u64 secs, usecs, nsecs = t; - secs = nsecs / NSECS_PER_SEC; - nsecs -= secs * NSECS_PER_SEC; - usecs = nsecs / NSECS_PER_USEC; + secs = nsecs / NSEC_PER_SEC; + nsecs -= secs * NSEC_PER_SEC; + usecs = nsecs / NSEC_PER_USEC; ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ", secs, usecs); diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c new file mode 100644 index 000000000000..1647f285c629 --- /dev/null +++ b/tools/perf/util/drv_configs.c @@ -0,0 +1,77 @@ +/* + * drv_configs.h: Interface to apply PMU specific configuration + * Copyright (c) 2016-2018, Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include "drv_configs.h" +#include "evlist.h" +#include "evsel.h" +#include "pmu.h" + +static int +perf_evsel__apply_drv_configs(struct perf_evsel *evsel, + struct perf_evsel_config_term **err_term) +{ + bool found = false; + int err = 0; + struct perf_evsel_config_term *term; + struct perf_pmu *pmu = NULL; + + while ((pmu = perf_pmu__scan(pmu)) != NULL) + if (pmu->type == evsel->attr.type) { + found = true; + break; + } + + list_for_each_entry(term, &evsel->config_terms, list) { + if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG) + continue; + + /* + * We have a configuration term, report an error if we + * can't find the PMU or if the PMU driver doesn't support + * cmd line driver configuration. + */ + if (!found || !pmu->set_drv_config) { + err = -EINVAL; + *err_term = term; + break; + } + + err = pmu->set_drv_config(term); + if (err) { + *err_term = term; + break; + } + } + + return err; +} + +int perf_evlist__apply_drv_configs(struct perf_evlist *evlist, + struct perf_evsel **err_evsel, + struct perf_evsel_config_term **err_term) +{ + struct perf_evsel *evsel; + int err = 0; + + evlist__for_each_entry(evlist, evsel) { + err = perf_evsel__apply_drv_configs(evsel, err_term); + if (err) { + *err_evsel = evsel; + break; + } + } + + return err; +} diff --git a/tools/perf/util/drv_configs.h b/tools/perf/util/drv_configs.h new file mode 100644 index 000000000000..32bc9babc2e0 --- /dev/null +++ b/tools/perf/util/drv_configs.h @@ -0,0 +1,26 @@ +/* + * drv_configs.h: Interface to apply PMU specific configuration + * Copyright (c) 2016-2018, Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#ifndef __PERF_DRV_CONFIGS_H +#define __PERF_DRV_CONFIGS_H + +#include "drv_configs.h" +#include "evlist.h" +#include "evsel.h" + +int perf_evlist__apply_drv_configs(struct perf_evlist *evlist, + struct perf_evsel **err_evsel, + struct perf_evsel_config_term **term); +#endif diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 774f6ec884d5..d2c6cdd9d42b 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -363,6 +363,9 @@ static int __open_dso(struct dso *dso, struct machine *machine) return -EINVAL; } + if (!is_regular_file(name)) + return -EINVAL; + fd = do_open(name); free(name); return fd; diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index a347b19c961a..41e068e94349 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -130,6 +130,22 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, } /** + * die_get_linkage_name - Get the linkage name of the object + * @dw_die: A DIE of the object + * + * Get the linkage name attiribute of given @dw_die. + * For C++ binary, the linkage name will be the mangled symbol. + */ +const char *die_get_linkage_name(Dwarf_Die *dw_die) +{ + Dwarf_Attribute attr; + + if (dwarf_attr_integrate(dw_die, DW_AT_linkage_name, &attr) == NULL) + return NULL; + return dwarf_formstring(&attr); +} + +/** * die_compare_name - Compare diename and tname * @dw_die: a DIE * @tname: a string of target name @@ -145,18 +161,26 @@ bool die_compare_name(Dwarf_Die *dw_die, const char *tname) } /** - * die_match_name - Match diename and glob + * die_match_name - Match diename/linkage name and glob * @dw_die: a DIE * @glob: a string of target glob pattern * * Glob matching the name of @dw_die and @glob. Return false if matching fail. + * This also match linkage name. */ bool die_match_name(Dwarf_Die *dw_die, const char *glob) { const char *name; name = dwarf_diename(dw_die); - return name ? strglobmatch(name, glob) : false; + if (name && strglobmatch(name, glob)) + return true; + /* fall back to check linkage name */ + name = die_get_linkage_name(dw_die); + if (name && strglobmatch(name, glob)) + return true; + + return false; } /** @@ -1085,3 +1109,182 @@ int die_get_var_range(Dwarf_Die *sp_die __maybe_unused, return -ENOTSUP; } #endif + +/* + * die_has_loclist - Check if DW_AT_location of @vr_die is a location list + * @vr_die: a variable DIE + */ +static bool die_has_loclist(Dwarf_Die *vr_die) +{ + Dwarf_Attribute loc; + int tag = dwarf_tag(vr_die); + + if (tag != DW_TAG_formal_parameter && + tag != DW_TAG_variable) + return false; + + return (dwarf_attr_integrate(vr_die, DW_AT_location, &loc) && + dwarf_whatform(&loc) == DW_FORM_sec_offset); +} + +/* + * die_is_optimized_target - Check if target program is compiled with + * optimization + * @cu_die: a CU DIE + * + * For any object in given CU whose DW_AT_location is a location list, + * target program is compiled with optimization. This is applicable to + * clang as well. + */ +bool die_is_optimized_target(Dwarf_Die *cu_die) +{ + Dwarf_Die tmp_die; + + if (die_has_loclist(cu_die)) + return true; + + if (!dwarf_child(cu_die, &tmp_die) && + die_is_optimized_target(&tmp_die)) + return true; + + if (!dwarf_siblingof(cu_die, &tmp_die) && + die_is_optimized_target(&tmp_die)) + return true; + + return false; +} + +/* + * die_search_idx - Search index of given line address + * @lines: Line records of single CU + * @nr_lines: Number of @lines + * @addr: address we are looking for + * @idx: index to be set by this function (return value) + * + * Search for @addr by looping over every lines of CU. If address + * matches, set index of that line in @idx. Note that single source + * line can have multiple line records. i.e. single source line can + * have multiple index. + */ +static bool die_search_idx(Dwarf_Lines *lines, unsigned long nr_lines, + Dwarf_Addr addr, unsigned long *idx) +{ + unsigned long i; + Dwarf_Addr tmp; + + for (i = 0; i < nr_lines; i++) { + if (dwarf_lineaddr(dwarf_onesrcline(lines, i), &tmp)) + return false; + + if (tmp == addr) { + *idx = i; + return true; + } + } + return false; +} + +/* + * die_get_postprologue_addr - Search next address after function prologue + * @entrypc_idx: entrypc index + * @lines: Line records of single CU + * @nr_lines: Number of @lines + * @hignpc: high PC address of function + * @postprologue_addr: Next address after function prologue (return value) + * + * Look for prologue-end marker. If there is no explicit marker, return + * address of next line record or next source line. + */ +static bool die_get_postprologue_addr(unsigned long entrypc_idx, + Dwarf_Lines *lines, + unsigned long nr_lines, + Dwarf_Addr highpc, + Dwarf_Addr *postprologue_addr) +{ + unsigned long i; + int entrypc_lno, lno; + Dwarf_Line *line; + Dwarf_Addr addr; + bool p_end; + + /* entrypc_lno is actual source line number */ + line = dwarf_onesrcline(lines, entrypc_idx); + if (dwarf_lineno(line, &entrypc_lno)) + return false; + + for (i = entrypc_idx; i < nr_lines; i++) { + line = dwarf_onesrcline(lines, i); + + if (dwarf_lineaddr(line, &addr) || + dwarf_lineno(line, &lno) || + dwarf_lineprologueend(line, &p_end)) + return false; + + /* highpc is exclusive. [entrypc,highpc) */ + if (addr >= highpc) + break; + + /* clang supports prologue-end marker */ + if (p_end) + break; + + /* Actual next line in source */ + if (lno != entrypc_lno) + break; + + /* + * Single source line can have multiple line records. + * For Example, + * void foo() { printf("hello\n"); } + * contains two line records. One points to declaration and + * other points to printf() line. Variable 'lno' won't get + * incremented in this case but 'i' will. + */ + if (i != entrypc_idx) + break; + } + + dwarf_lineaddr(line, postprologue_addr); + if (*postprologue_addr >= highpc) + dwarf_lineaddr(dwarf_onesrcline(lines, i - 1), + postprologue_addr); + + return true; +} + +/* + * die_skip_prologue - Use next address after prologue as probe location + * @sp_die: a subprogram DIE + * @cu_die: a CU DIE + * @entrypc: entrypc of the function + * + * Function prologue prepares stack and registers before executing function + * logic. When target program is compiled without optimization, function + * parameter information is only valid after prologue. When we probe entrypc + * of the function, and try to record function parameter, it contains + * garbage value. + */ +void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die, + Dwarf_Addr *entrypc) +{ + size_t nr_lines = 0; + unsigned long entrypc_idx = 0; + Dwarf_Lines *lines = NULL; + Dwarf_Addr postprologue_addr; + Dwarf_Addr highpc; + + if (dwarf_highpc(sp_die, &highpc)) + return; + + if (dwarf_getsrclines(cu_die, &lines, &nr_lines)) + return; + + if (!die_search_idx(lines, nr_lines, *entrypc, &entrypc_idx)) + return; + + if (!die_get_postprologue_addr(entrypc_idx, lines, nr_lines, + highpc, &postprologue_addr)) + return; + + *entrypc = postprologue_addr; +} diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index dc0ce1adb075..8ac53bf1ec4e 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -38,6 +38,9 @@ int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, int (*callback)(Dwarf_Die *, void *), void *data); +/* Get DW_AT_linkage_name (should be NULL for C binary) */ +const char *die_get_linkage_name(Dwarf_Die *dw_die); + /* Ensure that this DIE is a subprogram and definition (not declaration) */ bool die_is_func_def(Dwarf_Die *dw_die); @@ -125,4 +128,12 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf); /* Get the name and type of given variable DIE, stored as "type\tname" */ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf); int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf); + +/* Check if target program is compiled with optimization */ +bool die_is_optimized_target(Dwarf_Die *cu_die); + +/* Use next address after prologue as probe location */ +void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die, + Dwarf_Addr *entrypc); + #endif diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c new file mode 100644 index 000000000000..62bc4a86a970 --- /dev/null +++ b/tools/perf/util/dwarf-regs.c @@ -0,0 +1,59 @@ +/* + * dwarf-regs.c : Mapping of DWARF debug register numbers into register names. + * + * Written by: Masami Hiramatsu <mhiramat@kernel.org> + */ + +#include <util.h> +#include <debug.h> +#include <dwarf-regs.h> +#include <elf.h> + +#ifndef EM_AARCH64 +#define EM_AARCH64 183 /* ARM 64 bit */ +#endif + +/* Define const char * {arch}_register_tbl[] */ +#define DEFINE_DWARF_REGSTR_TABLE +#include "../arch/x86/include/dwarf-regs-table.h" +#include "../arch/arm/include/dwarf-regs-table.h" +#include "../arch/arm64/include/dwarf-regs-table.h" +#include "../arch/sh/include/dwarf-regs-table.h" +#include "../arch/powerpc/include/dwarf-regs-table.h" +#include "../arch/s390/include/dwarf-regs-table.h" +#include "../arch/sparc/include/dwarf-regs-table.h" +#include "../arch/xtensa/include/dwarf-regs-table.h" + +#define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL) + +/* Return architecture dependent register string (for kprobe-tracer) */ +const char *get_dwarf_regstr(unsigned int n, unsigned int machine) +{ + switch (machine) { + case EM_NONE: /* Generic arch - use host arch */ + return get_arch_regstr(n); + case EM_386: + return __get_dwarf_regstr(x86_32_regstr_tbl, n); + case EM_X86_64: + return __get_dwarf_regstr(x86_64_regstr_tbl, n); + case EM_ARM: + return __get_dwarf_regstr(arm_regstr_tbl, n); + case EM_AARCH64: + return __get_dwarf_regstr(aarch64_regstr_tbl, n); + case EM_SH: + return __get_dwarf_regstr(sh_regstr_tbl, n); + case EM_S390: + return __get_dwarf_regstr(s390_regstr_tbl, n); + case EM_PPC: + case EM_PPC64: + return __get_dwarf_regstr(powerpc_regstr_tbl, n); + case EM_SPARC: + case EM_SPARCV9: + return __get_dwarf_regstr(sparc_regstr_tbl, n); + case EM_XTENSA: + return __get_dwarf_regstr(xtensa_regstr_tbl, n); + default: + pr_err("ELF MACHINE %x is not supported.\n", machine); + } + return NULL; +} diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index e20438b784be..8ab0d7da956b 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,5 +1,6 @@ #include <linux/types.h> -#include <sys/mman.h> +#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ +#include <api/fs/fs.h> #include "event.h" #include "debug.h" #include "hist.h" @@ -248,6 +249,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, bool truncation = false; unsigned long long timeout = proc_map_timeout * 1000000ULL; int rc = 0; + const char *hugetlbfs_mnt = hugetlbfs__mountpoint(); + int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0; if (machine__is_default_guest(machine)) return 0; @@ -343,6 +346,12 @@ out: if (!strcmp(execname, "")) strcpy(execname, anonstr); + if (hugetlbfs_mnt_len && + !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) { + strcpy(execname, anonstr); + event->mmap2.flags |= MAP_HUGETLB; + } + size = strlen(execname) + 1; memcpy(event->mmap2.filename, execname, size); size = PERF_ALIGN(size, sizeof(u64)); @@ -1286,7 +1295,7 @@ try_again: * must be done prior to using kernel maps. */ if (load_map) - map__load(al->map, machine->symbol_filter); + map__load(al->map); al->addr = al->map->map_ip(al->map, al->addr); } } @@ -1297,8 +1306,7 @@ void thread__find_addr_location(struct thread *thread, { thread__find_addr_map(thread, cpumode, type, addr, al); if (al->map != NULL) - al->sym = map__find_symbol(al->map, al->addr, - thread->mg->machine->symbol_filter); + al->sym = map__find_symbol(al->map, al->addr); else al->sym = NULL; } @@ -1359,8 +1367,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al, al->filtered |= (1 << HIST_FILTER__DSO); } - al->sym = map__find_symbol(al->map, al->addr, - machine->symbol_filter); + al->sym = map__find_symbol(al->map, al->addr); } if (symbol_conf.sym_list && @@ -1416,5 +1423,5 @@ void thread__resolve(struct thread *thread, struct addr_location *al, al->sym = NULL; if (al->map) - al->sym = map__find_symbol(al->map, al->addr, NULL); + al->sym = map__find_symbol(al->map, al->addr); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 8d363d5e65a2..c735c53a26f8 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -177,6 +177,8 @@ enum { PERF_IP_FLAG_TRACE_BEGIN |\ PERF_IP_FLAG_TRACE_END) +#define MAX_INSN 16 + struct perf_sample { u64 ip; u32 pid, tid; @@ -193,6 +195,7 @@ struct perf_sample { u32 flags; u16 insn_len; u8 cpumode; + char insn[MAX_INSN]; void *raw_data; struct ip_callchain *callchain; struct branch_stack *branch_stack; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 097b3ed77fdd..d92e02006fb8 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -384,15 +384,14 @@ void perf_evlist__toggle_enable(struct perf_evlist *evlist) static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu) { - int thread, err; + int thread; int nr_threads = perf_evlist__nr_threads(evlist, evsel); if (!evsel->fd) return -EINVAL; for (thread = 0; thread < nr_threads; thread++) { - err = ioctl(FD(evsel, cpu, thread), - PERF_EVENT_IOC_ENABLE, 0); + int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); if (err) return err; } @@ -403,14 +402,14 @@ static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, struct perf_evsel *evsel, int thread) { - int cpu, err; + int cpu; int nr_cpus = cpu_map__nr(evlist->cpus); if (!evsel->fd) return -EINVAL; for (cpu = 0; cpu < nr_cpus; cpu++) { - err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); + int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); if (err) return err; } @@ -1032,16 +1031,18 @@ perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused, } static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, - struct mmap_params *mp, int cpu, + struct mmap_params *mp, int cpu_idx, int thread, int *_output, int *_output_backward) { struct perf_evsel *evsel; int revent; + int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx); evlist__for_each_entry(evlist, evsel) { struct perf_mmap *maps = evlist->mmap; int *output = _output; int fd; + int cpu; if (evsel->attr.write_backward) { output = _output_backward; @@ -1060,6 +1061,10 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, if (evsel->system_wide && thread) continue; + cpu = cpu_map__idx(evsel->cpus, evlist_cpu); + if (cpu == -1) + continue; + fd = FD(evsel, cpu, thread); if (*output == -1) { @@ -1600,10 +1605,9 @@ void perf_evlist__close(struct perf_evlist *evlist) struct perf_evsel *evsel; int ncpus = cpu_map__nr(evlist->cpus); int nthreads = thread_map__nr(evlist->threads); - int n; evlist__for_each_entry_reverse(evlist, evsel) { - n = evsel->cpus ? evsel->cpus->nr : ncpus; + int n = evsel->cpus ? evsel->cpus->nr : ncpus; perf_evsel__close(evsel, n, nthreads); } } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 21fd573106ed..04e536ae4d88 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -28,6 +28,7 @@ #include "debug.h" #include "trace-event.h" #include "stat.h" +#include "util/parse-branch-options.h" static struct { bool sample_id_all; @@ -708,6 +709,14 @@ static void apply_config_terms(struct perf_evsel *evsel, case PERF_EVSEL__CONFIG_TERM_CALLGRAPH: callgraph_buf = term->val.callgraph; break; + case PERF_EVSEL__CONFIG_TERM_BRANCH: + if (term->val.branch && strcmp(term->val.branch, "no")) { + perf_evsel__set_sample_bit(evsel, BRANCH_STACK); + parse_branch_str(term->val.branch, + &attr->branch_sample_type); + } else + perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); + break; case PERF_EVSEL__CONFIG_TERM_STACK_USER: dump_size = term->val.stack_user; break; @@ -981,18 +990,19 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * it overloads any global configuration. */ apply_config_terms(evsel, opts); + + evsel->ignore_missing_thread = opts->ignore_missing_thread; } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { - int cpu, thread; - if (evsel->system_wide) nthreads = 1; evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); if (evsel->fd) { + int cpu, thread; for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { FD(evsel, cpu, thread) = -1; @@ -1045,15 +1055,15 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter) return -1; } -int perf_evsel__append_filter(struct perf_evsel *evsel, - const char *op, const char *filter) +static int perf_evsel__append_filter(struct perf_evsel *evsel, + const char *fmt, const char *filter) { char *new_filter; if (evsel->filter == NULL) return perf_evsel__set_filter(evsel, filter); - if (asprintf(&new_filter,"(%s) %s (%s)", evsel->filter, op, filter) > 0) { + if (asprintf(&new_filter, fmt, evsel->filter, filter) > 0) { free(evsel->filter); evsel->filter = new_filter; return 0; @@ -1062,6 +1072,16 @@ int perf_evsel__append_filter(struct perf_evsel *evsel, return -1; } +int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter) +{ + return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter); +} + +int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter) +{ + return perf_evsel__append_filter(evsel, "%s,%s", filter); +} + int perf_evsel__enable(struct perf_evsel *evsel) { int nthreads = thread_map__nr(evsel->threads); @@ -1401,6 +1421,33 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, return fprintf(fp, " %-32s %s\n", name, val); } +static bool ignore_missing_thread(struct perf_evsel *evsel, + struct thread_map *threads, + int thread, int err) +{ + if (!evsel->ignore_missing_thread) + return false; + + /* The system wide setup does not work with threads. */ + if (evsel->system_wide) + return false; + + /* The -ESRCH is perf event syscall errno for pid's not found. */ + if (err != -ESRCH) + return false; + + /* If there's only one thread, let it fail. */ + if (threads->nr == 1) + return false; + + if (thread_map__remove(threads, thread)) + return false; + + pr_warning("WARNING: Ignored open failure for pid %d\n", + thread_map__pid(threads, thread)); + return true; +} + static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { @@ -1456,29 +1503,47 @@ retry_sample_id: for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < nthreads; thread++) { - int group_fd; + int fd, group_fd; if (!evsel->cgrp && !evsel->system_wide) pid = thread_map__pid(threads, thread); group_fd = get_group_fd(evsel, cpu, thread); retry_open: - pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx\n", + pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, cpus->map[cpu], group_fd, flags); - FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, - pid, - cpus->map[cpu], - group_fd, flags); - if (FD(evsel, cpu, thread) < 0) { + fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], + group_fd, flags); + + FD(evsel, cpu, thread) = fd; + + if (fd < 0) { err = -errno; - pr_debug2("sys_perf_event_open failed, error %d\n", + + if (ignore_missing_thread(evsel, threads, thread, err)) { + /* + * We just removed 1 thread, so take a step + * back on thread index and lower the upper + * nthreads limit. + */ + nthreads--; + thread--; + + /* ... and pretend like nothing have happened. */ + err = 0; + continue; + } + + pr_debug2("\nsys_perf_event_open failed, error %d\n", err); goto try_fallback; } + pr_debug2(" = %d\n", fd); + if (evsel->bpf_fd >= 0) { - int evt_fd = FD(evsel, cpu, thread); + int evt_fd = fd; int bpf_fd = evsel->bpf_fd; err = ioctl(evt_fd, @@ -1728,7 +1793,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; data->period = evsel->attr.sample_period; - data->weight = 0; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; if (event->header.type != PERF_RECORD_SAMPLE) { @@ -1935,7 +1999,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } - data->weight = 0; if (type & PERF_SAMPLE_WEIGHT) { OVERFLOW_CHECK_u64(array); data->weight = *array; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 4d44129e050b..06ef6f29efa1 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -46,6 +46,8 @@ enum { PERF_EVSEL__CONFIG_TERM_INHERIT, PERF_EVSEL__CONFIG_TERM_MAX_STACK, PERF_EVSEL__CONFIG_TERM_OVERWRITE, + PERF_EVSEL__CONFIG_TERM_DRV_CFG, + PERF_EVSEL__CONFIG_TERM_BRANCH, PERF_EVSEL__CONFIG_TERM_MAX, }; @@ -57,10 +59,12 @@ struct perf_evsel_config_term { u64 freq; bool time; char *callgraph; + char *drv_cfg; u64 stack_user; int max_stack; bool inherit; bool overwrite; + char *branch; } val; }; @@ -116,6 +120,7 @@ struct perf_evsel { bool tracking; bool per_pkg; bool precise_max; + bool ignore_missing_thread; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -233,8 +238,9 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel, bool use_sample_identifier); int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter); -int perf_evsel__append_filter(struct perf_evsel *evsel, - const char *op, const char *filter); +int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter); +int perf_evsel__append_addr_filter(struct perf_evsel *evsel, + const char *filter); int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, const char *filter); int perf_evsel__enable(struct perf_evsel *evsel); @@ -386,6 +392,8 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, #define EVSEL__PRINT_ONELINE (1<<4) #define EVSEL__PRINT_SRCLINE (1<<5) #define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) +#define EVSEL__PRINT_CALLCHAIN_ARROW (1<<7) +#define EVSEL__PRINT_SKIP_IGNORED (1<<8) struct callchain_cursor; diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 3674e77ad640..6b2925542c0a 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -108,7 +108,10 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, int print_oneline = print_opts & EVSEL__PRINT_ONELINE; int print_srcline = print_opts & EVSEL__PRINT_SRCLINE; int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; + int print_arrow = print_opts & EVSEL__PRINT_CALLCHAIN_ARROW; + int print_skip_ignored = print_opts & EVSEL__PRINT_SKIP_IGNORED; char s = print_oneline ? ' ' : '\t'; + bool first = true; if (sample->callchain) { struct addr_location node_al; @@ -122,11 +125,14 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (!node) break; - if (node->sym && node->sym->ignore) + if (node->sym && node->sym->ignore && print_skip_ignored) goto next; printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); + if (print_arrow && !first) + printed += fprintf(fp, " <-"); + if (print_ip) printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); @@ -140,7 +146,8 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_symoffset) { printed += __symbol__fprintf_symname_offs(node->sym, &node_al, - print_unknown_as_addr, fp); + print_unknown_as_addr, + true, fp); } else { printed += __symbol__fprintf_symname(node->sym, &node_al, print_unknown_as_addr, fp); @@ -158,6 +165,16 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (!print_oneline) printed += fprintf(fp, "\n"); + + if (symbol_conf.bt_stop_list && + node->sym && + node->sym->name && + strlist__has_entry(symbol_conf.bt_stop_list, + node->sym->name)) { + break; + } + + first = false; next: callchain_cursor_advance(cursor); } @@ -181,7 +198,7 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, if (cursor != NULL) { printed += sample__fprintf_callchain(sample, left_alignment, print_opts, cursor, fp); - } else if (!(al->sym && al->sym->ignore)) { + } else { printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); if (print_ip) @@ -191,7 +208,8 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, printed += fprintf(fp, " "); if (print_symoffset) { printed += __symbol__fprintf_symname_offs(al->sym, al, - print_unknown_as_addr, fp); + print_unknown_as_addr, + true, fp); } else { printed += __symbol__fprintf_symname(al->sym, al, print_unknown_as_addr, fp); diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index c1ef805c6a8f..c540d47583e7 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -19,12 +19,18 @@ #include <limits.h> #include <fcntl.h> #include <err.h> +#ifdef HAVE_DWARF_SUPPORT #include <dwarf.h> +#endif #include "perf.h" #include "genelf.h" #include "../util/jitdump.h" +#ifndef NT_GNU_BUILD_ID +#define NT_GNU_BUILD_ID 3 +#endif + #define JVMTI #define BUILD_ID_URANDOM /* different uuid for each run */ @@ -67,6 +73,8 @@ static char shd_string_table[] = { '.', 'd', 'e', 'b', 'u', 'g', '_', 'l', 'i', 'n', 'e', 0, /* 52 */ '.', 'd', 'e', 'b', 'u', 'g', '_', 'i', 'n', 'f', 'o', 0, /* 64 */ '.', 'd', 'e', 'b', 'u', 'g', '_', 'a', 'b', 'b', 'r', 'e', 'v', 0, /* 76 */ + '.', 'e', 'h', '_', 'f', 'r', 'a', 'm', 'e', '_', 'h', 'd', 'r', 0, /* 90 */ + '.', 'e', 'h', '_', 'f', 'r', 'a', 'm', 'e', 0, /* 104 */ }; static struct buildid_note { @@ -147,6 +155,86 @@ gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *cod } #endif +static int +jit_add_eh_frame_info(Elf *e, void* unwinding, uint64_t unwinding_header_size, + uint64_t unwinding_size, uint64_t base_offset) +{ + Elf_Data *d; + Elf_Scn *scn; + Elf_Shdr *shdr; + uint64_t unwinding_table_size = unwinding_size - unwinding_header_size; + + /* + * setup eh_frame section + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + return -1; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + return -1; + } + + d->d_align = 8; + d->d_off = 0LL; + d->d_buf = unwinding; + d->d_type = ELF_T_BYTE; + d->d_size = unwinding_table_size; + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + return -1; + } + + shdr->sh_name = 104; + shdr->sh_type = SHT_PROGBITS; + shdr->sh_addr = base_offset; + shdr->sh_flags = SHF_ALLOC; + shdr->sh_entsize = 0; + + /* + * setup eh_frame_hdr section + */ + scn = elf_newscn(e); + if (!scn) { + warnx("cannot create section"); + return -1; + } + + d = elf_newdata(scn); + if (!d) { + warnx("cannot get new data"); + return -1; + } + + d->d_align = 4; + d->d_off = 0LL; + d->d_buf = unwinding + unwinding_table_size; + d->d_type = ELF_T_BYTE; + d->d_size = unwinding_header_size; + d->d_version = EV_CURRENT; + + shdr = elf_getshdr(scn); + if (!shdr) { + warnx("cannot get section header"); + return -1; + } + + shdr->sh_name = 90; + shdr->sh_type = SHT_PROGBITS; + shdr->sh_addr = base_offset + unwinding_table_size; + shdr->sh_flags = SHF_ALLOC; + shdr->sh_entsize = 0; + + return 0; +} + /* * fd: file descriptor open for writing for the output file * load_addr: code load address (could be zero, just used for buildid) @@ -157,13 +245,15 @@ gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *cod int jit_write_elf(int fd, uint64_t load_addr, const char *sym, const void *code, int csize, - void *debug, int nr_debug_entries) + void *debug __maybe_unused, int nr_debug_entries __maybe_unused, + void *unwinding, uint64_t unwinding_header_size, uint64_t unwinding_size) { Elf *e; Elf_Data *d; Elf_Scn *scn; Elf_Ehdr *ehdr; Elf_Shdr *shdr; + uint64_t eh_frame_base_offset; char *strsym = NULL; int symlen; int retval = -1; @@ -194,7 +284,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, ehdr->e_type = ET_DYN; ehdr->e_entry = GEN_ELF_TEXT_OFFSET; ehdr->e_version = EV_CURRENT; - ehdr->e_shstrndx= 2; /* shdr index for section name */ + ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */ /* * setup text section @@ -231,6 +321,18 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, shdr->sh_entsize = 0; /* + * Setup .eh_frame_hdr and .eh_frame + */ + if (unwinding) { + eh_frame_base_offset = ALIGN_8(GEN_ELF_TEXT_OFFSET + csize); + retval = jit_add_eh_frame_info(e, unwinding, + unwinding_header_size, unwinding_size, + eh_frame_base_offset); + if (retval) + goto error; + } + + /* * setup section headers string table */ scn = elf_newscn(e); @@ -298,7 +400,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, shdr->sh_type = SHT_SYMTAB; shdr->sh_flags = 0; shdr->sh_entsize = sizeof(Elf_Sym); - shdr->sh_link = 4; /* index of .strtab section */ + shdr->sh_link = unwinding ? 6 : 4; /* index of .strtab section */ /* * setup symbols string table @@ -386,11 +488,14 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, shdr->sh_size = sizeof(bnote); shdr->sh_entsize = 0; +#ifdef HAVE_DWARF_SUPPORT if (debug && nr_debug_entries) { retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries); if (retval) goto error; - } else { + } else +#endif + { if (elf_update(e, ELF_C_WRITE) < 0) { warnx("elf_update 4 failed"); goto error; diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index 2fbeb59c4bdd..2424bd9862a3 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -3,9 +3,12 @@ /* genelf.c */ int jit_write_elf(int fd, uint64_t code_addr, const char *sym, - const void *code, int csize, void *debug, int nr_debug_entries); + const void *code, int csize, void *debug, int nr_debug_entries, + void *unwinding, uint64_t unwinding_header_size, uint64_t unwinding_size); +#ifdef HAVE_DWARF_SUPPORT /* genelf_debug.c */ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries); +#endif #if defined(__arm__) #define GEN_ELF_ARCH EM_ARM diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 8f0db4007282..d89c9c7ef4e5 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -828,8 +828,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, * default get_cpuid(): nothing gets recorded * actual implementation must be in arch/$(ARCH)/util/header.c */ -int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused, - size_t sz __maybe_unused) +int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) { return -1; } @@ -1896,7 +1895,6 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse if (ph->needs_swap) nr = bswap_32(nr); - ph->env.nr_numa_nodes = nr; nodes = zalloc(sizeof(*nodes) * nr); if (!nodes) return -ENOMEM; @@ -1933,6 +1931,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse free(str); } + ph->env.nr_numa_nodes = nr; ph->env.numa_nodes = nodes; return 0; @@ -2251,11 +2250,28 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) struct header_print_data hd; struct perf_header *header = &session->header; int fd = perf_data_file__fd(session->file); + struct stat st; + int ret, bit; + hd.fp = fp; hd.full = full; + ret = fstat(fd, &st); + if (ret == -1) + return -1; + + fprintf(fp, "# captured on: %s", ctime(&st.st_ctime)); + perf_header__process_sections(header, fd, &hd, perf_file_section__fprintf_info); + + fprintf(fp, "# missing features: "); + for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) { + if (bit) + fprintf(fp, "%s ", feat_ops[bit].name); + } + + fprintf(fp, "\n"); return 0; } @@ -2274,7 +2290,7 @@ static int do_write_feat(int fd, struct perf_header *h, int type, err = feat_ops[type].write(fd, h, evlist); if (err < 0) { - pr_debug("failed to write feature %d\n", type); + pr_debug("failed to write feature %s\n", feat_ops[type].name); /* undo anything written */ lseek(fd, (*p)->offset, SEEK_SET); diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d306ca118449..d30109b421ee 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -151,4 +151,5 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned); */ int get_cpuid(char *buffer, size_t sz); +char *get_cpuid_str(void); #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index de15dbcdcecf..6770a9645609 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -177,8 +177,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); - if (h->srcline) - hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline)); + if (h->srcline) { + len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header)); + hists__new_col_len(hists, HISTC_SRCLINE, len); + } if (h->srcfile) hists__new_col_len(hists, HISTC_SRCFILE, strlen(h->srcfile)); @@ -417,6 +419,8 @@ static int hist_entry__init(struct hist_entry *he, } INIT_LIST_HEAD(&he->pairs.node); thread__get(he->thread); + he->hroot_in = RB_ROOT; + he->hroot_out = RB_ROOT; if (!symbol_conf.report_hierarchy) he->leaf = true; @@ -1191,6 +1195,7 @@ static void hist_entry__check_and_remove_filter(struct hist_entry *he, case HIST_FILTER__GUEST: case HIST_FILTER__HOST: case HIST_FILTER__SOCKET: + case HIST_FILTER__C2C: default: return; } @@ -1596,18 +1601,18 @@ static void hists__hierarchy_output_resort(struct hists *hists, if (prog) ui_progress__update(prog, 1); + hists->nr_entries++; + if (!he->filtered) { + hists->nr_non_filtered_entries++; + hists__calc_col_len(hists, he); + } + if (!he->leaf) { hists__hierarchy_output_resort(hists, prog, &he->hroot_in, &he->hroot_out, min_callchain_hits, use_callchain); - hists->nr_entries++; - if (!he->filtered) { - hists->nr_non_filtered_entries++; - hists__calc_col_len(hists, he); - } - continue; } @@ -2149,6 +2154,50 @@ out: return he; } +static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists, + struct rb_root *root, + struct hist_entry *pair) +{ + struct rb_node **p; + struct rb_node *parent = NULL; + struct hist_entry *he; + struct perf_hpp_fmt *fmt; + + p = &root->rb_node; + while (*p != NULL) { + int64_t cmp = 0; + + parent = *p; + he = rb_entry(parent, struct hist_entry, rb_node_in); + + perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { + cmp = fmt->collapse(fmt, he, pair); + if (cmp) + break; + } + if (!cmp) + goto out; + + if (cmp < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + + he = hist_entry__new(pair, true); + if (he) { + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, root); + + he->dummy = true; + he->hists = hists; + memset(&he->stat, 0, sizeof(he->stat)); + hists__inc_stats(hists, he); + } +out: + return he; +} + static struct hist_entry *hists__find_entry(struct hists *hists, struct hist_entry *he) { @@ -2174,6 +2223,51 @@ static struct hist_entry *hists__find_entry(struct hists *hists, return NULL; } +static struct hist_entry *hists__find_hierarchy_entry(struct rb_root *root, + struct hist_entry *he) +{ + struct rb_node *n = root->rb_node; + + while (n) { + struct hist_entry *iter; + struct perf_hpp_fmt *fmt; + int64_t cmp = 0; + + iter = rb_entry(n, struct hist_entry, rb_node_in); + perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { + cmp = fmt->collapse(fmt, iter, he); + if (cmp) + break; + } + + if (cmp < 0) + n = n->rb_left; + else if (cmp > 0) + n = n->rb_right; + else + return iter; + } + + return NULL; +} + +static void hists__match_hierarchy(struct rb_root *leader_root, + struct rb_root *other_root) +{ + struct rb_node *nd; + struct hist_entry *pos, *pair; + + for (nd = rb_first(leader_root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); + pair = hists__find_hierarchy_entry(other_root, pos); + + if (pair) { + hist_entry__add_pair(pair, pos); + hists__match_hierarchy(&pos->hroot_in, &pair->hroot_in); + } + } +} + /* * Look for pairs to link to the leader buckets (hist_entries): */ @@ -2183,6 +2277,12 @@ void hists__match(struct hists *leader, struct hists *other) struct rb_node *nd; struct hist_entry *pos, *pair; + if (symbol_conf.report_hierarchy) { + /* hierarchy report always collapses entries */ + return hists__match_hierarchy(&leader->entries_collapsed, + &other->entries_collapsed); + } + if (hists__has(leader, need_collapse)) root = &leader->entries_collapsed; else @@ -2197,6 +2297,50 @@ void hists__match(struct hists *leader, struct hists *other) } } +static int hists__link_hierarchy(struct hists *leader_hists, + struct hist_entry *parent, + struct rb_root *leader_root, + struct rb_root *other_root) +{ + struct rb_node *nd; + struct hist_entry *pos, *leader; + + for (nd = rb_first(other_root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); + + if (hist_entry__has_pairs(pos)) { + bool found = false; + + list_for_each_entry(leader, &pos->pairs.head, pairs.node) { + if (leader->hists == leader_hists) { + found = true; + break; + } + } + if (!found) + return -1; + } else { + leader = add_dummy_hierarchy_entry(leader_hists, + leader_root, pos); + if (leader == NULL) + return -1; + + /* do not point parent in the pos */ + leader->parent_he = parent; + + hist_entry__add_pair(pos, leader); + } + + if (!pos->leaf) { + if (hists__link_hierarchy(leader_hists, leader, + &leader->hroot_in, + &pos->hroot_in) < 0) + return -1; + } + } + return 0; +} + /* * Look for entries in the other hists that are not present in the leader, if * we find them, just add a dummy entry on the leader hists, with period=0, @@ -2208,6 +2352,13 @@ int hists__link(struct hists *leader, struct hists *other) struct rb_node *nd; struct hist_entry *pos, *pair; + if (symbol_conf.report_hierarchy) { + /* hierarchy report always collapses entries */ + return hists__link_hierarchy(leader, NULL, + &leader->entries_collapsed, + &other->entries_collapsed); + } + if (hists__has(other, need_collapse)) root = &other->entries_collapsed; else diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 0a1edf1ab450..d4b6514eeef5 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -22,6 +22,7 @@ enum hist_filter { HIST_FILTER__GUEST, HIST_FILTER__HOST, HIST_FILTER__SOCKET, + HIST_FILTER__C2C, }; enum hist_column { @@ -230,7 +231,7 @@ struct perf_hpp { struct perf_hpp_fmt { const char *name; int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct hists *hists); + struct hists *hists, int line, int *span); int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hists *hists); int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, @@ -259,6 +260,7 @@ struct perf_hpp_list { struct list_head fields; struct list_head sorts; + int nr_header_lines; int need_collapse; int parent; int sym; @@ -367,6 +369,7 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format, void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists); void perf_hpp__set_user_width(const char *width_list_str); +void hists__reset_column_width(struct hists *hists); typedef u64 (*hpp_field_fn)(struct hist_entry *he); typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front); @@ -483,5 +486,10 @@ static inline struct rb_node *rb_hierarchy_next(struct rb_node *node) #define HIERARCHY_INDENT 3 bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit); +int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...); +int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...); +int __hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp, + struct perf_hpp_list *hpp_list); +int hists__fprintf_headers(struct hists *hists, FILE *fp); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h index 07c644ed64c4..43bfd8da7919 100644 --- a/tools/perf/util/include/dwarf-regs.h +++ b/tools/perf/util/include/dwarf-regs.h @@ -3,6 +3,12 @@ #ifdef HAVE_DWARF_SUPPORT const char *get_arch_regstr(unsigned int n); +/* + * get_dwarf_regstr - Returns ftrace register string from DWARF regnum + * n: DWARF register number + * machine: ELF machine signature (EM_*) + */ +const char *get_dwarf_regstr(unsigned int n, unsigned int machine); #endif #ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 749e6f2e37ca..6c2eb5da4afc 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -295,6 +295,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, sample.cpu = btsq->cpu; sample.flags = btsq->sample_flags; sample.insn_len = btsq->intel_pt_insn.length; + memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ); if (bts->synth_opts.inject) { event.sample.header.size = bts->branches_event_size; @@ -319,15 +320,12 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip) struct machine *machine = btsq->bts->machine; struct thread *thread; struct addr_location al; - unsigned char buf[1024]; - size_t bufsz; + unsigned char buf[INTEL_PT_INSN_BUF_SZ]; ssize_t len; int x86_64; uint8_t cpumode; int err = -1; - bufsz = intel_pt_insn_max_size(); - if (machine__kernel_ip(machine, ip)) cpumode = PERF_RECORD_MISC_KERNEL; else @@ -341,12 +339,13 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip) if (!al.map || !al.map->dso) goto out_put; - len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, bufsz); + len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, + INTEL_PT_INSN_BUF_SZ); if (len <= 0) goto out_put; /* Load maps to ensure dso->is_64_bit has been updated */ - map__load(al.map, machine->symbol_filter); + map__load(al.map); x86_64 = al.map->dso->is_64_bit; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 8ff6c6a61291..e4e7dc781d21 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -80,6 +80,7 @@ struct intel_pt_decoder { int (*walk_insn)(struct intel_pt_insn *intel_pt_insn, uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip, uint64_t max_insn_cnt, void *data); + bool (*pgd_ip)(uint64_t ip, void *data); void *data; struct intel_pt_state state; const unsigned char *buf; @@ -89,6 +90,7 @@ struct intel_pt_decoder { bool pge; bool have_tma; bool have_cyc; + bool fixup_last_mtc; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -186,6 +188,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->get_trace = params->get_trace; decoder->walk_insn = params->walk_insn; + decoder->pgd_ip = params->pgd_ip; decoder->data = params->data; decoder->return_compression = params->return_compression; @@ -584,10 +587,31 @@ struct intel_pt_calc_cyc_to_tsc_info { uint64_t tsc_timestamp; uint64_t timestamp; bool have_tma; + bool fixup_last_mtc; bool from_mtc; double cbr_cyc_to_tsc; }; +/* + * MTC provides a 8-bit slice of CTC but the TMA packet only provides the lower + * 16 bits of CTC. If mtc_shift > 8 then some of the MTC bits are not in the CTC + * provided by the TMA packet. Fix-up the last_mtc calculated from the TMA + * packet by copying the missing bits from the current MTC assuming the least + * difference between the two, and that the current MTC comes after last_mtc. + */ +static void intel_pt_fixup_last_mtc(uint32_t mtc, int mtc_shift, + uint32_t *last_mtc) +{ + uint32_t first_missing_bit = 1U << (16 - mtc_shift); + uint32_t mask = ~(first_missing_bit - 1); + + *last_mtc |= mtc & mask; + if (*last_mtc >= mtc) { + *last_mtc -= first_missing_bit; + *last_mtc &= 0xff; + } +} + static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) { struct intel_pt_decoder *decoder = pkt_info->decoder; @@ -617,6 +641,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) return 0; mtc = pkt_info->packet.payload; + if (decoder->mtc_shift > 8 && data->fixup_last_mtc) { + data->fixup_last_mtc = false; + intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift, + &data->last_mtc); + } if (mtc > data->last_mtc) mtc_delta = mtc - data->last_mtc; else @@ -685,6 +714,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) data->ctc_delta = 0; data->have_tma = true; + data->fixup_last_mtc = true; return 0; @@ -751,6 +781,7 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder, .tsc_timestamp = decoder->tsc_timestamp, .timestamp = decoder->timestamp, .have_tma = decoder->have_tma, + .fixup_last_mtc = decoder->fixup_last_mtc, .from_mtc = from_mtc, .cbr_cyc_to_tsc = 0, }; @@ -949,6 +980,8 @@ out: out_no_progress: decoder->state.insn_op = intel_pt_insn->op; decoder->state.insn_len = intel_pt_insn->length; + memcpy(decoder->state.insn, intel_pt_insn->buf, + INTEL_PT_INSN_BUF_SZ); if (decoder->tx_flags & INTEL_PT_IN_TX) decoder->state.flags |= INTEL_PT_IN_TX; @@ -1008,6 +1041,19 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder) int err; err = intel_pt_walk_insn(decoder, &intel_pt_insn, 0); + if (err == INTEL_PT_RETURN && + decoder->pgd_ip && + decoder->pkt_state == INTEL_PT_STATE_TIP_PGD && + (decoder->state.type & INTEL_PT_BRANCH) && + decoder->pgd_ip(decoder->state.to_ip, decoder->data)) { + /* Unconditional branch leaving filter region */ + decoder->no_progress = 0; + decoder->pge = false; + decoder->continuous_period = false; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->state.to_ip = 0; + return 0; + } if (err == INTEL_PT_RETURN) return 0; if (err) @@ -1036,6 +1082,21 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder) } if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) { + uint64_t to_ip = decoder->ip + intel_pt_insn.length + + intel_pt_insn.rel; + + if (decoder->pgd_ip && + decoder->pkt_state == INTEL_PT_STATE_TIP_PGD && + decoder->pgd_ip(to_ip, decoder->data)) { + /* Conditional branch leaving filter region */ + decoder->pge = false; + decoder->continuous_period = false; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->ip = to_ip; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return 0; + } intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch", decoder->ip); decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; @@ -1241,6 +1302,7 @@ static void intel_pt_calc_tma(struct intel_pt_decoder *decoder) } decoder->ctc_delta = 0; decoder->have_tma = true; + decoder->fixup_last_mtc = true; intel_pt_log("CTC timestamp " x64_fmt " last MTC %#x CTC rem %#x\n", decoder->ctc_timestamp, decoder->last_mtc, ctc_rem); } @@ -1255,6 +1317,12 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) mtc = decoder->packet.payload; + if (decoder->mtc_shift > 8 && decoder->fixup_last_mtc) { + decoder->fixup_last_mtc = false; + intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift, + &decoder->last_mtc); + } + if (mtc > decoder->last_mtc) mtc_delta = mtc - decoder->last_mtc; else @@ -1323,6 +1391,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder) timestamp, decoder->timestamp); else decoder->timestamp = timestamp; + + decoder->timestamp_insn_cnt = 0; } /* Walk PSB+ packets when already in sync. */ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index 02c38fec1c37..e90619a43c0c 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -66,6 +66,7 @@ struct intel_pt_state { uint32_t flags; enum intel_pt_insn_op insn_op; int insn_len; + char insn[INTEL_PT_INSN_BUF_SZ]; }; struct intel_pt_insn; @@ -83,6 +84,7 @@ struct intel_pt_params { int (*walk_insn)(struct intel_pt_insn *intel_pt_insn, uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip, uint64_t max_insn_cnt, void *data); + bool (*pgd_ip)(uint64_t ip, void *data); void *data; bool return_compression; uint64_t period; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index d23138c06665..7913363bde5c 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -27,6 +27,10 @@ #include "intel-pt-insn-decoder.h" +#if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN +#error Instruction buffer size too small +#endif + /* Based on branch_type() from perf_event_intel_lbr.c */ static void intel_pt_insn_decoder(struct insn *insn, struct intel_pt_insn *intel_pt_insn) @@ -166,10 +170,10 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64, if (!insn_complete(&insn) || insn.length > len) return -1; intel_pt_insn_decoder(&insn, intel_pt_insn); - if (insn.length < INTEL_PT_INSN_DBG_BUF_SZ) + if (insn.length < INTEL_PT_INSN_BUF_SZ) memcpy(intel_pt_insn->buf, buf, insn.length); else - memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_DBG_BUF_SZ); + memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_BUF_SZ); return 0; } @@ -211,11 +215,6 @@ int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf, return 0; } -size_t intel_pt_insn_max_size(void) -{ - return MAX_INSN_SIZE; -} - int intel_pt_insn_type(enum intel_pt_insn_op op) { switch (op) { diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h index b0adbf37323e..37ec5627ae9b 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h @@ -20,7 +20,7 @@ #include <stdint.h> #define INTEL_PT_INSN_DESC_MAX 32 -#define INTEL_PT_INSN_DBG_BUF_SZ 16 +#define INTEL_PT_INSN_BUF_SZ 16 enum intel_pt_insn_op { INTEL_PT_OP_OTHER, @@ -47,7 +47,7 @@ struct intel_pt_insn { enum intel_pt_insn_branch branch; int length; int32_t rel; - unsigned char buf[INTEL_PT_INSN_DBG_BUF_SZ]; + unsigned char buf[INTEL_PT_INSN_BUF_SZ]; }; int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64, @@ -58,8 +58,6 @@ const char *intel_pt_insn_name(enum intel_pt_insn_op op); int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf, size_t buf_len); -size_t intel_pt_insn_max_size(void); - int intel_pt_insn_type(enum intel_pt_insn_op op); #endif diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index 319bef33a64b..e02bc7b166a0 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -119,8 +119,8 @@ void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip) if (intel_pt_log_open()) return; - if (len > INTEL_PT_INSN_DBG_BUF_SZ) - len = INTEL_PT_INSN_DBG_BUF_SZ; + if (len > INTEL_PT_INSN_BUF_SZ) + len = INTEL_PT_INSN_BUF_SZ; intel_pt_print_data(intel_pt_insn->buf, len, ip, 8); if (intel_pt_insn_desc(intel_pt_insn, desc, INTEL_PT_INSN_DESC_MAX) > 0) fprintf(f, "%s\n", desc); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 551ff6f640be..85d5eeb66c75 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -103,6 +103,9 @@ struct intel_pt { unsigned max_non_turbo_ratio; unsigned long num_events; + + char *filter; + struct addr_filters filts; }; enum switch_state { @@ -140,6 +143,7 @@ struct intel_pt_queue { u32 flags; u16 insn_len; u64 last_insn_cnt; + char insn[INTEL_PT_INSN_BUF_SZ]; }; static void intel_pt_dump(struct intel_pt *pt __maybe_unused, @@ -241,7 +245,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) } queue = &ptq->pt->queues.queue_array[ptq->queue_nr]; - +next: buffer = auxtrace_buffer__next(queue, buffer); if (!buffer) { if (old_buffer) @@ -264,9 +268,6 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer)) return -ENOMEM; - if (old_buffer) - auxtrace_buffer__drop_data(old_buffer); - if (buffer->use_data) { b->len = buffer->use_size; b->buf = buffer->use_data; @@ -276,6 +277,16 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) } b->ref_timestamp = buffer->reference; + /* + * If in snapshot mode and the buffer has no usable data, get next + * buffer and again check overlap against old_buffer. + */ + if (ptq->pt->snapshot_mode && !b->len) + goto next; + + if (old_buffer) + auxtrace_buffer__drop_data(old_buffer); + if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode && !buffer->consecutive)) { b->consecutive = false; @@ -305,6 +316,7 @@ struct intel_pt_cache_entry { enum intel_pt_insn_branch branch; int length; int32_t rel; + char insn[INTEL_PT_INSN_BUF_SZ]; }; static int intel_pt_config_div(const char *var, const char *value, void *data) @@ -390,6 +402,7 @@ static int intel_pt_cache_add(struct dso *dso, struct machine *machine, e->branch = intel_pt_insn->branch; e->length = intel_pt_insn->length; e->rel = intel_pt_insn->rel; + memcpy(e->insn, intel_pt_insn->buf, INTEL_PT_INSN_BUF_SZ); err = auxtrace_cache__add(c, offset, &e->entry); if (err) @@ -418,8 +431,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, struct machine *machine = ptq->pt->machine; struct thread *thread; struct addr_location al; - unsigned char buf[1024]; - size_t bufsz; + unsigned char buf[INTEL_PT_INSN_BUF_SZ]; ssize_t len; int x86_64; u8 cpumode; @@ -427,11 +439,11 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, u64 insn_cnt = 0; bool one_map = true; + intel_pt_insn->length = 0; + if (to_ip && *ip == to_ip) goto out_no_cache; - bufsz = intel_pt_insn_max_size(); - if (*ip >= ptq->pt->kernel_start) cpumode = PERF_RECORD_MISC_KERNEL; else @@ -468,6 +480,8 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, intel_pt_insn->branch = e->branch; intel_pt_insn->length = e->length; intel_pt_insn->rel = e->rel; + memcpy(intel_pt_insn->buf, e->insn, + INTEL_PT_INSN_BUF_SZ); intel_pt_log_insn_no_data(intel_pt_insn, *ip); return 0; } @@ -477,13 +491,14 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, start_ip = *ip; /* Load maps to ensure dso->is_64_bit has been updated */ - map__load(al.map, machine->symbol_filter); + map__load(al.map); x86_64 = al.map->dso->is_64_bit; while (1) { len = dso__data_read_offset(al.map->dso, machine, - offset, buf, bufsz); + offset, buf, + INTEL_PT_INSN_BUF_SZ); if (len <= 0) return -EINVAL; @@ -541,6 +556,76 @@ out_no_cache: return 0; } +static bool intel_pt_match_pgd_ip(struct intel_pt *pt, uint64_t ip, + uint64_t offset, const char *filename) +{ + struct addr_filter *filt; + bool have_filter = false; + bool hit_tracestop = false; + bool hit_filter = false; + + list_for_each_entry(filt, &pt->filts.head, list) { + if (filt->start) + have_filter = true; + + if ((filename && !filt->filename) || + (!filename && filt->filename) || + (filename && strcmp(filename, filt->filename))) + continue; + + if (!(offset >= filt->addr && offset < filt->addr + filt->size)) + continue; + + intel_pt_log("TIP.PGD ip %#"PRIx64" offset %#"PRIx64" in %s hit filter: %s offset %#"PRIx64" size %#"PRIx64"\n", + ip, offset, filename ? filename : "[kernel]", + filt->start ? "filter" : "stop", + filt->addr, filt->size); + + if (filt->start) + hit_filter = true; + else + hit_tracestop = true; + } + + if (!hit_tracestop && !hit_filter) + intel_pt_log("TIP.PGD ip %#"PRIx64" offset %#"PRIx64" in %s is not in a filter region\n", + ip, offset, filename ? filename : "[kernel]"); + + return hit_tracestop || (have_filter && !hit_filter); +} + +static int __intel_pt_pgd_ip(uint64_t ip, void *data) +{ + struct intel_pt_queue *ptq = data; + struct thread *thread; + struct addr_location al; + u8 cpumode; + u64 offset; + + if (ip >= ptq->pt->kernel_start) + return intel_pt_match_pgd_ip(ptq->pt, ip, ip, NULL); + + cpumode = PERF_RECORD_MISC_USER; + + thread = ptq->thread; + if (!thread) + return -EINVAL; + + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al); + if (!al.map || !al.map->dso) + return -EINVAL; + + offset = al.map->map_ip(al.map, ip); + + return intel_pt_match_pgd_ip(ptq->pt, ip, offset, + al.map->dso->long_name); +} + +static bool intel_pt_pgd_ip(uint64_t ip, void *data) +{ + return __intel_pt_pgd_ip(ip, data) > 0; +} + static bool intel_pt_get_config(struct intel_pt *pt, struct perf_event_attr *attr, u64 *config) { @@ -717,6 +802,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n; params.tsc_ctc_ratio_d = pt->tsc_ctc_ratio_d; + if (pt->filts.cnt > 0) + params.pgd_ip = intel_pt_pgd_ip; + if (pt->synth_opts.instructions) { if (pt->synth_opts.period) { switch (pt->synth_opts.period_type) { @@ -817,6 +905,7 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq) if (ptq->state->flags & INTEL_PT_IN_TX) ptq->flags |= PERF_IP_FLAG_IN_TX; ptq->insn_len = ptq->state->insn_len; + memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ); } } @@ -997,6 +1086,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) sample.cpu = ptq->cpu; sample.flags = ptq->flags; sample.insn_len = ptq->insn_len; + memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); /* * perf report cannot handle events without a branch stack when using @@ -1058,6 +1148,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) sample.cpu = ptq->cpu; sample.flags = ptq->flags; sample.insn_len = ptq->insn_len; + memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); ptq->last_insn_cnt = ptq->state->tot_insn_cnt; @@ -1120,6 +1211,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) sample.cpu = ptq->cpu; sample.flags = ptq->flags; sample.insn_len = ptq->insn_len; + memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); if (pt->synth_opts.callchain) { thread_stack__sample(ptq->thread, ptq->chain, @@ -1294,7 +1386,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) if (!map) return 0; - if (map__load(map, machine->symbol_filter)) + if (map__load(map)) return 0; start = dso__first_symbol(map->dso, MAP__FUNCTION); @@ -1767,6 +1859,8 @@ static void intel_pt_free(struct perf_session *session) intel_pt_free_events(session); session->auxtrace = NULL; thread__put(pt->unknown_thread); + addr_filters__exit(&pt->filts); + zfree(&pt->filter); free(pt); } @@ -2016,6 +2110,8 @@ static const char * const intel_pt_info_fmts[] = { [INTEL_PT_TSC_CTC_N] = " TSC:CTC numerator %"PRIu64"\n", [INTEL_PT_TSC_CTC_D] = " TSC:CTC denominator %"PRIu64"\n", [INTEL_PT_CYC_BIT] = " CYC bit %#"PRIx64"\n", + [INTEL_PT_MAX_NONTURBO_RATIO] = " Max non-turbo ratio %"PRIu64"\n", + [INTEL_PT_FILTER_STR_LEN] = " Filter string len. %"PRIu64"\n", }; static void intel_pt_print_info(u64 *arr, int start, int finish) @@ -2029,12 +2125,28 @@ static void intel_pt_print_info(u64 *arr, int start, int finish) fprintf(stdout, intel_pt_info_fmts[i], arr[i]); } +static void intel_pt_print_info_str(const char *name, const char *str) +{ + if (!dump_trace) + return; + + fprintf(stdout, " %-20s%s\n", name, str ? str : ""); +} + +static bool intel_pt_has(struct auxtrace_info_event *auxtrace_info, int pos) +{ + return auxtrace_info->header.size >= + sizeof(struct auxtrace_info_event) + (sizeof(u64) * (pos + 1)); +} + int intel_pt_process_auxtrace_info(union perf_event *event, struct perf_session *session) { struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS; struct intel_pt *pt; + void *info_end; + u64 *info; int err; if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) + @@ -2045,6 +2157,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (!pt) return -ENOMEM; + addr_filters__init(&pt->filts); + perf_config(intel_pt_perf_config, pt); err = auxtrace_queues__init(&pt->queues); @@ -2069,8 +2183,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, intel_pt_print_info(&auxtrace_info->priv[0], INTEL_PT_PMU_TYPE, INTEL_PT_PER_CPU_MMAPS); - if (auxtrace_info->header.size >= sizeof(struct auxtrace_info_event) + - (sizeof(u64) * INTEL_PT_CYC_BIT)) { + if (intel_pt_has(auxtrace_info, INTEL_PT_CYC_BIT)) { pt->mtc_bit = auxtrace_info->priv[INTEL_PT_MTC_BIT]; pt->mtc_freq_bits = auxtrace_info->priv[INTEL_PT_MTC_FREQ_BITS]; pt->tsc_ctc_ratio_n = auxtrace_info->priv[INTEL_PT_TSC_CTC_N]; @@ -2080,6 +2193,54 @@ int intel_pt_process_auxtrace_info(union perf_event *event, INTEL_PT_CYC_BIT); } + if (intel_pt_has(auxtrace_info, INTEL_PT_MAX_NONTURBO_RATIO)) { + pt->max_non_turbo_ratio = + auxtrace_info->priv[INTEL_PT_MAX_NONTURBO_RATIO]; + intel_pt_print_info(&auxtrace_info->priv[0], + INTEL_PT_MAX_NONTURBO_RATIO, + INTEL_PT_MAX_NONTURBO_RATIO); + } + + info = &auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] + 1; + info_end = (void *)info + auxtrace_info->header.size; + + if (intel_pt_has(auxtrace_info, INTEL_PT_FILTER_STR_LEN)) { + size_t len; + + len = auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN]; + intel_pt_print_info(&auxtrace_info->priv[0], + INTEL_PT_FILTER_STR_LEN, + INTEL_PT_FILTER_STR_LEN); + if (len) { + const char *filter = (const char *)info; + + len = roundup(len + 1, 8); + info += len >> 3; + if ((void *)info > info_end) { + pr_err("%s: bad filter string length\n", __func__); + err = -EINVAL; + goto err_free_queues; + } + pt->filter = memdup(filter, len); + if (!pt->filter) { + err = -ENOMEM; + goto err_free_queues; + } + if (session->header.needs_swap) + mem_bswap_64(pt->filter, len); + if (pt->filter[len - 1]) { + pr_err("%s: filter string not null terminated\n", __func__); + err = -EINVAL; + goto err_free_queues; + } + err = addr_filters__parse_bare_filter(&pt->filts, + filter); + if (err) + goto err_free_queues; + } + intel_pt_print_info_str("Filter string", pt->filter); + } + pt->timeless_decoding = intel_pt_timeless_decoding(pt); pt->have_tsc = intel_pt_have_tsc(pt); pt->sampling_mode = false; @@ -2121,11 +2282,13 @@ int intel_pt_process_auxtrace_info(union perf_event *event, pt->switch_evsel = intel_pt_find_sched_switch(session->evlist); if (!pt->switch_evsel) { pr_err("%s: missing sched_switch event\n", __func__); + err = -EINVAL; goto err_delete_thread; } } else if (pt->have_sched_switch == 2 && !intel_pt_find_switch(session->evlist)) { pr_err("%s: missing context_switch attribute flag\n", __func__); + err = -EINVAL; goto err_delete_thread; } @@ -2149,7 +2312,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (pt->tc.time_mult) { u64 tsc_freq = intel_pt_ns_to_ticks(pt, 1000000000); - pt->max_non_turbo_ratio = (tsc_freq + 50000000) / 100000000; + if (!pt->max_non_turbo_ratio) + pt->max_non_turbo_ratio = + (tsc_freq + 50000000) / 100000000; intel_pt_log("TSC frequency %"PRIu64"\n", tsc_freq); intel_pt_log("Maximum non-turbo ratio %u\n", pt->max_non_turbo_ratio); @@ -2193,6 +2358,8 @@ err_free_queues: auxtrace_queues__free(&pt->queues); session->auxtrace = NULL; err_free: + addr_filters__exit(&pt->filts); + zfree(&pt->filter); free(pt); return err; } diff --git a/tools/perf/util/intel-pt.h b/tools/perf/util/intel-pt.h index 0065949df693..e13b14e5a37b 100644 --- a/tools/perf/util/intel-pt.h +++ b/tools/perf/util/intel-pt.h @@ -34,11 +34,11 @@ enum { INTEL_PT_TSC_CTC_N, INTEL_PT_TSC_CTC_D, INTEL_PT_CYC_BIT, + INTEL_PT_MAX_NONTURBO_RATIO, + INTEL_PT_FILTER_STR_LEN, INTEL_PT_AUXTRACE_PRIV_MAX, }; -#define INTEL_PT_AUXTRACE_PRIV_SIZE (INTEL_PT_AUXTRACE_PRIV_MAX * sizeof(u64)) - struct auxtrace_record; struct perf_tool; union perf_event; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 95f0884aae02..c9a941ef0f6d 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -37,6 +37,10 @@ struct jit_buf_desc { bool needs_bswap; /* handles cross-endianess */ bool use_arch_timestamp; void *debug_data; + void *unwinding_data; + uint64_t unwinding_size; + uint64_t unwinding_mapped_size; + uint64_t eh_frame_hdr_size; size_t nr_debug_entries; uint32_t code_load_count; u64 bytes_written; @@ -68,7 +72,10 @@ jit_emit_elf(char *filename, const void *code, int csize, void *debug, - int nr_debug_entries) + int nr_debug_entries, + void *unwinding, + uint32_t unwinding_header_size, + uint32_t unwinding_size) { int ret, fd; @@ -81,7 +88,8 @@ jit_emit_elf(char *filename, return -1; } - ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries); + ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries, + unwinding, unwinding_header_size, unwinding_size); close(fd); @@ -172,6 +180,12 @@ jit_open(struct jit_buf_desc *jd, const char *name) header.elf_mach, jd->use_arch_timestamp); + if (header.version > JITHEADER_VERSION) { + pr_err("wrong jitdump version %u, expected " STR(JITHEADER_VERSION), + header.version); + goto error; + } + if (header.flags & JITDUMP_FLAGS_RESERVED) { pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n", (unsigned long long)header.flags & JITDUMP_FLAGS_RESERVED); @@ -263,8 +277,7 @@ jit_get_next_entry(struct jit_buf_desc *jd) return NULL; if (id >= JIT_CODE_MAX) { - pr_warning("next_entry: unknown prefix %d, skipping\n", id); - return NULL; + pr_warning("next_entry: unknown record type %d, skipping\n", id); } if (bs > jd->bufsize) { void *n; @@ -296,6 +309,13 @@ jit_get_next_entry(struct jit_buf_desc *jd) } } break; + case JIT_CODE_UNWINDING_INFO: + if (jd->needs_bswap) { + jr->unwinding.unwinding_size = bswap_64(jr->unwinding.unwinding_size); + jr->unwinding.eh_frame_hdr_size = bswap_64(jr->unwinding.eh_frame_hdr_size); + jr->unwinding.mapped_size = bswap_64(jr->unwinding.mapped_size); + } + break; case JIT_CODE_CLOSE: break; case JIT_CODE_LOAD: @@ -322,7 +342,8 @@ jit_get_next_entry(struct jit_buf_desc *jd) break; case JIT_CODE_MAX: default: - return NULL; + /* skip unknown record (we have read them) */ + break; } return jr; } @@ -370,7 +391,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) u16 idr_size; const char *sym; uint32_t count; - int ret, csize; + int ret, csize, usize; pid_t pid, tid; struct { u32 pid, tid; @@ -380,6 +401,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) pid = jr->load.pid; tid = jr->load.tid; csize = jr->load.code_size; + usize = jd->unwinding_mapped_size; addr = jr->load.code_addr; sym = (void *)((unsigned long)jr + sizeof(jr->load)); code = (unsigned long)jr + jr->load.p.total_size - csize; @@ -400,7 +422,8 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) size = PERF_ALIGN(size, sizeof(u64)); uaddr = (uintptr_t)code; - ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries); + ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries, + jd->unwinding_data, jd->eh_frame_hdr_size, jd->unwinding_size); if (jd->debug_data && jd->nr_debug_entries) { free(jd->debug_data); @@ -408,6 +431,14 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) jd->nr_debug_entries = 0; } + if (jd->unwinding_data && jd->eh_frame_hdr_size) { + free(jd->unwinding_data); + jd->unwinding_data = NULL; + jd->eh_frame_hdr_size = 0; + jd->unwinding_mapped_size = 0; + jd->unwinding_size = 0; + } + if (ret) { free(event); return -1; @@ -422,7 +453,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET; event->mmap2.start = addr; - event->mmap2.len = csize; + event->mmap2.len = usize ? ALIGN_8(csize) + usize : csize; event->mmap2.pid = pid; event->mmap2.tid = tid; event->mmap2.ino = st.st_ino; @@ -473,6 +504,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) char *filename; size_t size; struct stat st; + int usize; u16 idr_size; int ret; pid_t pid, tid; @@ -483,6 +515,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) pid = jr->move.pid; tid = jr->move.tid; + usize = jd->unwinding_mapped_size; idr_size = jd->machine->id_hdr_size; /* @@ -511,7 +544,8 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) (sizeof(event->mmap2.filename) - size) + idr_size); event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET; event->mmap2.start = jr->move.new_code_addr; - event->mmap2.len = jr->move.code_size; + event->mmap2.len = usize ? ALIGN_8(jr->move.code_size) + usize + : jr->move.code_size; event->mmap2.pid = pid; event->mmap2.tid = tid; event->mmap2.ino = st.st_ino; @@ -578,10 +612,35 @@ static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr) } static int +jit_repipe_unwinding_info(struct jit_buf_desc *jd, union jr_entry *jr) +{ + void *unwinding_data; + uint32_t unwinding_data_size; + + if (!(jd && jr)) + return -1; + + unwinding_data_size = jr->prefix.total_size - sizeof(jr->unwinding); + unwinding_data = malloc(unwinding_data_size); + if (!unwinding_data) + return -1; + + memcpy(unwinding_data, &jr->unwinding.unwinding_data, + unwinding_data_size); + + jd->eh_frame_hdr_size = jr->unwinding.eh_frame_hdr_size; + jd->unwinding_size = jr->unwinding.unwinding_size; + jd->unwinding_mapped_size = jr->unwinding.mapped_size; + jd->unwinding_data = unwinding_data; + + return 0; +} + +static int jit_process_dump(struct jit_buf_desc *jd) { union jr_entry *jr; - int ret; + int ret = 0; while ((jr = jit_get_next_entry(jd))) { switch(jr->prefix.id) { @@ -594,6 +653,9 @@ jit_process_dump(struct jit_buf_desc *jd) case JIT_CODE_DEBUG_INFO: ret = jit_repipe_debug_info(jd, jr); break; + case JIT_CODE_UNWINDING_INFO: + ret = jit_repipe_unwinding_info(jd, jr); + break; default: ret = 0; continue; diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h index bcacd20d0c1c..c6b9b67f43bf 100644 --- a/tools/perf/util/jitdump.h +++ b/tools/perf/util/jitdump.h @@ -19,6 +19,7 @@ #define JITHEADER_MAGIC_SW 0x4454694A #define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7) +#define ALIGN_8(x) (((x) + 7) & (~7)) #define JITHEADER_VERSION 1 @@ -48,6 +49,7 @@ enum jit_record_type { JIT_CODE_MOVE = 1, JIT_CODE_DEBUG_INFO = 2, JIT_CODE_CLOSE = 3, + JIT_CODE_UNWINDING_INFO = 4, JIT_CODE_MAX, }; @@ -101,12 +103,22 @@ struct jr_code_debug_info { struct debug_entry entries[0]; }; +struct jr_code_unwinding_info { + struct jr_prefix p; + + uint64_t unwinding_size; + uint64_t eh_frame_hdr_size; + uint64_t mapped_size; + const char unwinding_data[0]; +}; + union jr_entry { struct jr_code_debug_info info; struct jr_code_close close; struct jr_code_load load; struct jr_code_move move; struct jr_prefix prefix; + struct jr_code_unwinding_info unwinding; }; static inline struct debug_entry * diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index bf7216b8731d..b23ff44cf214 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -7,6 +7,7 @@ #include <limits.h> #include <stdio.h> #include <stdlib.h> +#include <linux/err.h> #include "debug.h" #include "llvm-utils.h" #include "config.h" @@ -282,9 +283,10 @@ static const char *kinc_fetch_script = "rm -rf $TMPDIR\n" "exit $RET\n"; -static inline void -get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) +void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) { + static char *saved_kbuild_dir; + static char *saved_kbuild_include_opts; int err; if (!kbuild_dir || !kbuild_include_opts) @@ -293,10 +295,28 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) *kbuild_dir = NULL; *kbuild_include_opts = NULL; + if (saved_kbuild_dir && saved_kbuild_include_opts && + !IS_ERR(saved_kbuild_dir) && !IS_ERR(saved_kbuild_include_opts)) { + *kbuild_dir = strdup(saved_kbuild_dir); + *kbuild_include_opts = strdup(saved_kbuild_include_opts); + + if (*kbuild_dir && *kbuild_include_opts) + return; + + zfree(kbuild_dir); + zfree(kbuild_include_opts); + /* + * Don't fall through: it may breaks saved_kbuild_dir and + * saved_kbuild_include_opts if detect them again when + * memory is low. + */ + return; + } + if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0]) { pr_debug("[llvm.kbuild-dir] is set to \"\" deliberately.\n"); pr_debug("Skip kbuild options detection.\n"); - return; + goto errout; } err = detect_kbuild_dir(kbuild_dir); @@ -306,7 +326,7 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) "Hint:\tSet correct kbuild directory using 'kbuild-dir' option in [llvm]\n" " \tsection of ~/.perfconfig or set it to \"\" to suppress kbuild\n" " \tdetection.\n\n"); - return; + goto errout; } pr_debug("Kernel build dir is set to %s\n", *kbuild_dir); @@ -325,21 +345,50 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) free(*kbuild_dir); *kbuild_dir = NULL; - return; + goto errout; } pr_debug("include option is set to %s\n", *kbuild_include_opts); + + saved_kbuild_dir = strdup(*kbuild_dir); + saved_kbuild_include_opts = strdup(*kbuild_include_opts); + + if (!saved_kbuild_dir || !saved_kbuild_include_opts) { + zfree(&saved_kbuild_dir); + zfree(&saved_kbuild_include_opts); + } + return; +errout: + saved_kbuild_dir = ERR_PTR(-EINVAL); + saved_kbuild_include_opts = ERR_PTR(-EINVAL); } -static void -dump_obj(const char *path, void *obj_buf, size_t size) +int llvm__get_nr_cpus(void) +{ + static int nr_cpus_avail = 0; + char serr[STRERR_BUFSIZE]; + + if (nr_cpus_avail > 0) + return nr_cpus_avail; + + nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF); + if (nr_cpus_avail <= 0) { + pr_err( +"WARNING:\tunable to get available CPUs in this system: %s\n" +" \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr))); + nr_cpus_avail = 128; + } + return nr_cpus_avail; +} + +void llvm__dump_obj(const char *path, void *obj_buf, size_t size) { char *obj_path = strdup(path); FILE *fp; char *p; if (!obj_path) { - pr_warning("WARNING: No enough memory, skip object dumping\n"); + pr_warning("WARNING: Not enough memory, skip object dumping\n"); return; } @@ -406,15 +455,9 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, * This is an optional work. Even it fail we can continue our * work. Needn't to check error return. */ - get_kbuild_opts(&kbuild_dir, &kbuild_include_opts); + llvm__get_kbuild_opts(&kbuild_dir, &kbuild_include_opts); - nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF); - if (nr_cpus_avail <= 0) { - pr_err( -"WARNING:\tunable to get available CPUs in this system: %s\n" -" \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr))); - nr_cpus_avail = 128; - } + nr_cpus_avail = llvm__get_nr_cpus(); snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d", nr_cpus_avail); @@ -453,9 +496,6 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, free(kbuild_dir); free(kbuild_include_opts); - if (llvm_param.dump_obj) - dump_obj(path, obj_buf, obj_buf_sz); - if (!p_obj_buf) free(obj_buf); else diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h index 9f501cef06a1..c87a2a92a88f 100644 --- a/tools/perf/util/llvm-utils.h +++ b/tools/perf/util/llvm-utils.h @@ -50,4 +50,10 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, size_t *p_obj_buf_sz); /* This function is for test__llvm() use only */ int llvm__search_clang(void); + +/* Following functions are reused by builtin clang support */ +void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts); +int llvm__get_nr_cpus(void); + +void llvm__dump_obj(const char *path, void *obj_buf, size_t size); #endif diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 95a1acb61245..9ddea5cecd94 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -29,6 +29,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) lzma_action action = LZMA_RUN; lzma_stream strm = LZMA_STREAM_INIT; lzma_ret ret; + int err = -1; u8 buf_in[BUFSIZE]; u8 buf_out[BUFSIZE]; @@ -45,7 +46,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (ret != LZMA_OK) { pr_err("lzma: lzma_stream_decoder failed %s (%d)\n", lzma_strerror(ret), ret); - return -1; + goto err_fclose; } strm.next_in = NULL; @@ -60,7 +61,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (ferror(infile)) { pr_err("lzma: read error: %s\n", strerror(errno)); - return -1; + goto err_fclose; } if (feof(infile)) @@ -74,7 +75,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (writen(output_fd, buf_out, write_size) != write_size) { pr_err("lzma: write error: %s\n", strerror(errno)); - return -1; + goto err_fclose; } strm.next_out = buf_out; @@ -83,13 +84,15 @@ int lzma_decompress_to_file(const char *input, int output_fd) if (ret != LZMA_OK) { if (ret == LZMA_STREAM_END) - return 0; + break; pr_err("lzma: failed %s\n", lzma_strerror(ret)); - return -1; + goto err_fclose; } } + err = 0; +err_fclose: fclose(infile); - return 0; + return err; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index cb6388dbdd98..9b33bef54581 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -41,7 +41,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->pid = pid; - machine->symbol_filter = NULL; machine->id_hdr_size = 0; machine->kptr_restrict_warned = false; machine->comm_exec = false; @@ -148,7 +147,6 @@ void machines__init(struct machines *machines) { machine__init(&machines->host, "", HOST_KERNEL_ID); machines->guests = RB_ROOT; - machines->symbol_filter = NULL; } void machines__exit(struct machines *machines) @@ -172,8 +170,6 @@ struct machine *machines__add(struct machines *machines, pid_t pid, return NULL; } - machine->symbol_filter = machines->symbol_filter; - while (*p != NULL) { parent = *p; pos = rb_entry(parent, struct machine, rb_node); @@ -189,21 +185,6 @@ struct machine *machines__add(struct machines *machines, pid_t pid, return machine; } -void machines__set_symbol_filter(struct machines *machines, - symbol_filter_t symbol_filter) -{ - struct rb_node *nd; - - machines->symbol_filter = symbol_filter; - machines->host.symbol_filter = symbol_filter; - - for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { - struct machine *machine = rb_entry(nd, struct machine, rb_node); - - machine->symbol_filter = symbol_filter; - } -} - void machines__set_comm_exec(struct machines *machines, bool comm_exec) { struct rb_node *nd; @@ -916,10 +897,10 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid) } int __machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, bool no_kcore, symbol_filter_t filter) + enum map_type type, bool no_kcore) { struct map *map = machine__kernel_map(machine); - int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore, filter); + int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore); if (ret > 0) { dso__set_loaded(map->dso, type); @@ -935,16 +916,15 @@ int __machine__load_kallsyms(struct machine *machine, const char *filename, } int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, symbol_filter_t filter) + enum map_type type) { - return __machine__load_kallsyms(machine, filename, type, false, filter); + return __machine__load_kallsyms(machine, filename, type, false); } -int machine__load_vmlinux_path(struct machine *machine, enum map_type type, - symbol_filter_t filter) +int machine__load_vmlinux_path(struct machine *machine, enum map_type type) { struct map *map = machine__kernel_map(machine); - int ret = dso__load_vmlinux_path(map->dso, map, filter); + int ret = dso__load_vmlinux_path(map->dso, map); if (ret > 0) dso__set_loaded(map->dso, type); @@ -1313,7 +1293,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, /* * preload dso of guest kernel and modules */ - dso__load(kernel, machine__kernel_map(machine), NULL); + dso__load(kernel, machine__kernel_map(machine)); } } return 0; @@ -1636,7 +1616,11 @@ static int add_callchain_ip(struct thread *thread, struct symbol **parent, struct addr_location *root_al, u8 *cpumode, - u64 ip) + u64 ip, + bool branch, + struct branch_flags *flags, + int nr_loop_iter, + int samples) { struct addr_location al; @@ -1688,7 +1672,8 @@ static int add_callchain_ip(struct thread *thread, if (symbol_conf.hide_unresolved && al.sym == NULL) return 0; - return callchain_cursor_append(cursor, al.addr, al.map, al.sym); + return callchain_cursor_append(cursor, al.addr, al.map, al.sym, + branch, flags, nr_loop_iter, samples); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, @@ -1765,9 +1750,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread, int max_stack) { struct ip_callchain *chain = sample->callchain; - int chain_nr = min(max_stack, (int)chain->nr); + int chain_nr = min(max_stack, (int)chain->nr), i; u8 cpumode = PERF_RECORD_MISC_USER; - int i, j, err; u64 ip; for (i = 0; i < chain_nr; i++) { @@ -1778,7 +1762,9 @@ static int resolve_lbr_callchain_sample(struct thread *thread, /* LBR only affects the user callchain */ if (i != chain_nr) { struct branch_stack *lbr_stack = sample->branch_stack; - int lbr_nr = lbr_stack->nr; + int lbr_nr = lbr_stack->nr, j, k; + bool branch; + struct branch_flags *flags; /* * LBR callstack can only get user call chain. * The mix_chain_nr is kernel call chain @@ -1792,23 +1778,42 @@ static int resolve_lbr_callchain_sample(struct thread *thread, int mix_chain_nr = i + 1 + lbr_nr + 1; for (j = 0; j < mix_chain_nr; j++) { + int err; + branch = false; + flags = NULL; + if (callchain_param.order == ORDER_CALLEE) { if (j < i + 1) ip = chain->ips[j]; - else if (j > i + 1) - ip = lbr_stack->entries[j - i - 2].from; - else + else if (j > i + 1) { + k = j - i - 2; + ip = lbr_stack->entries[k].from; + branch = true; + flags = &lbr_stack->entries[k].flags; + } else { ip = lbr_stack->entries[0].to; + branch = true; + flags = &lbr_stack->entries[0].flags; + } } else { - if (j < lbr_nr) - ip = lbr_stack->entries[lbr_nr - j - 1].from; + if (j < lbr_nr) { + k = lbr_nr - j - 1; + ip = lbr_stack->entries[k].from; + branch = true; + flags = &lbr_stack->entries[k].flags; + } else if (j > lbr_nr) ip = chain->ips[i + 1 - (j - lbr_nr)]; - else + else { ip = lbr_stack->entries[0].to; + branch = true; + flags = &lbr_stack->entries[0].flags; + } } - err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, + root_al, &cpumode, ip, + branch, flags, 0, 0); if (err) return (err < 0) ? err : 0; } @@ -1833,6 +1838,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, int i, j, err, nr_entries; int skip_idx = -1; int first_call = 0; + int nr_loop_iter; if (perf_evsel__has_branch_callstack(evsel)) { err = resolve_lbr_callchain_sample(thread, cursor, sample, parent, @@ -1888,14 +1894,37 @@ static int thread__resolve_callchain_sample(struct thread *thread, be[i] = branch->entries[branch->nr - i - 1]; } + nr_loop_iter = nr; nr = remove_loops(be, nr); + /* + * Get the number of iterations. + * It's only approximation, but good enough in practice. + */ + if (nr_loop_iter > nr) + nr_loop_iter = nr_loop_iter - nr + 1; + else + nr_loop_iter = 0; + for (i = 0; i < nr; i++) { - err = add_callchain_ip(thread, cursor, parent, root_al, - NULL, be[i].to); + if (i == nr - 1) + err = add_callchain_ip(thread, cursor, parent, + root_al, + NULL, be[i].to, + true, &be[i].flags, + nr_loop_iter, 1); + else + err = add_callchain_ip(thread, cursor, parent, + root_al, + NULL, be[i].to, + true, &be[i].flags, + 0, 0); + if (!err) err = add_callchain_ip(thread, cursor, parent, root_al, - NULL, be[i].from); + NULL, be[i].from, + true, &be[i].flags, + 0, 0); if (err == -EINVAL) break; if (err) @@ -1923,7 +1952,9 @@ check_calls: if (ip < PERF_CONTEXT_MAX) ++nr_entries; - err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, + root_al, &cpumode, ip, + false, NULL, 0, 0); if (err) return (err < 0) ? err : 0; @@ -1939,7 +1970,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) if (symbol_conf.hide_unresolved && entry->sym == NULL) return 0; return callchain_cursor_append(cursor, entry->ip, - entry->map, entry->sym); + entry->map, entry->sym, + false, NULL, 0, 0); } static int thread__resolve_callchain_unwind(struct thread *thread, @@ -2115,7 +2147,7 @@ int machine__get_kernel_start(struct machine *machine) */ machine->kernel_start = 1ULL << 63; if (map) { - err = map__load(map, machine->symbol_filter); + err = map__load(map); if (map->start) machine->kernel_start = map->start; } @@ -2131,7 +2163,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch { struct machine *machine = vmachine; struct map *map; - struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map, NULL); + struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map); if (sym == NULL) return NULL; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 20739f746bc4..354de6e56109 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -41,7 +41,6 @@ struct machine { struct map_groups kmaps; struct map *vmlinux_maps[MAP__NR_TYPES]; u64 kernel_start; - symbol_filter_t symbol_filter; pid_t *current_tid; union { /* Tool specific area */ void *priv; @@ -110,7 +109,6 @@ typedef void (*machine__process_t)(struct machine *machine, void *data); struct machines { struct machine host; struct rb_root guests; - symbol_filter_t symbol_filter; }; void machines__init(struct machines *machines); @@ -128,8 +126,6 @@ struct machine *machines__findnew(struct machines *machines, pid_t pid); void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size); char *machine__mmap_name(struct machine *machine, char *bf, size_t size); -void machines__set_symbol_filter(struct machines *machines, - symbol_filter_t symbol_filter); void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); @@ -178,40 +174,33 @@ size_t machine__fprintf(struct machine *machine, FILE *fp); static inline struct symbol *machine__find_kernel_symbol(struct machine *machine, enum map_type type, u64 addr, - struct map **mapp, - symbol_filter_t filter) + struct map **mapp) { - return map_groups__find_symbol(&machine->kmaps, type, addr, - mapp, filter); + return map_groups__find_symbol(&machine->kmaps, type, addr, mapp); } static inline struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, enum map_type type, const char *name, - struct map **mapp, - symbol_filter_t filter) + struct map **mapp) { - return map_groups__find_symbol_by_name(&machine->kmaps, type, name, - mapp, filter); + return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp); } static inline struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, - struct map **mapp, - symbol_filter_t filter) + struct map **mapp) { return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr, - mapp, filter); + mapp); } static inline struct symbol *machine__find_kernel_function_by_name(struct machine *machine, const char *name, - struct map **mapp, - symbol_filter_t filter) + struct map **mapp) { - return map_groups__find_function_by_name(&machine->kmaps, name, mapp, - filter); + return map_groups__find_function_by_name(&machine->kmaps, name, mapp); } struct map *machine__findnew_module_map(struct machine *machine, u64 start, @@ -219,11 +208,10 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, int arch__fix_module_text_start(u64 *start, const char *name); int __machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, bool no_kcore, symbol_filter_t filter); + enum map_type type, bool no_kcore); int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, symbol_filter_t filter); -int machine__load_vmlinux_path(struct machine *machine, enum map_type type, - symbol_filter_t filter); + enum map_type type); +int machine__load_vmlinux_path(struct machine *machine, enum map_type type); size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 728129ac653a..4f9a71c63026 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -6,6 +6,7 @@ #include <string.h> #include <stdio.h> #include <unistd.h> +#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include "map.h" #include "thread.h" #include "strlist.h" @@ -24,9 +25,10 @@ const char *map_type__name[MAP__NR_TYPES] = { [MAP__VARIABLE] = "Variables", }; -static inline int is_anon_memory(const char *filename) +static inline int is_anon_memory(const char *filename, u32 flags) { - return !strcmp(filename, "//anon") || + return flags & MAP_HUGETLB || + !strcmp(filename, "//anon") || !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) || !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1); } @@ -155,7 +157,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, int anon, no_dso, vdso, android; android = is_android_lib(filename); - anon = is_anon_memory(filename); + anon = is_anon_memory(filename, flags); vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); @@ -279,7 +281,7 @@ void map__fixup_end(struct map *map) #define DSO__DELETED "(deleted)" -int map__load(struct map *map, symbol_filter_t filter) +int map__load(struct map *map) { const char *name = map->dso->long_name; int nr; @@ -287,7 +289,7 @@ int map__load(struct map *map, symbol_filter_t filter) if (dso__loaded(map->dso, map->type)) return 0; - nr = dso__load(map->dso, map, filter); + nr = dso__load(map->dso, map); if (nr < 0) { if (map->dso->has_build_id) { char sbuild_id[SBUILD_ID_SIZE]; @@ -312,9 +314,6 @@ int map__load(struct map *map, symbol_filter_t filter) pr_warning("%.*s was updated (is prelink enabled?). " "Restart the long running apps that use it!\n", (int)real_len, name); - } else if (filter) { - pr_warning("no symbols passed the given filter.\n"); - return -2; /* Empty but maybe by the filter */ } else { pr_warning("no symbols found in %s, maybe install " "a debug package?\n", name); @@ -331,19 +330,17 @@ int __weak arch__compare_symbol_names(const char *namea, const char *nameb) return strcmp(namea, nameb); } -struct symbol *map__find_symbol(struct map *map, u64 addr, - symbol_filter_t filter) +struct symbol *map__find_symbol(struct map *map, u64 addr) { - if (map__load(map, filter) < 0) + if (map__load(map) < 0) return NULL; return dso__find_symbol(map->dso, map->type, addr); } -struct symbol *map__find_symbol_by_name(struct map *map, const char *name, - symbol_filter_t filter) +struct symbol *map__find_symbol_by_name(struct map *map, const char *name) { - if (map__load(map, filter) < 0) + if (map__load(map) < 0) return NULL; if (!dso__sorted_by_name(map->dso, map->type)) @@ -556,23 +553,22 @@ void map_groups__put(struct map_groups *mg) struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, - struct map **mapp, - symbol_filter_t filter) + struct map **mapp) { struct map *map = map_groups__find(mg, type, addr); /* Ensure map is loaded before using map->map_ip */ - if (map != NULL && map__load(map, filter) >= 0) { + if (map != NULL && map__load(map) >= 0) { if (mapp != NULL) *mapp = map; - return map__find_symbol(map, map->map_ip(map, addr), filter); + return map__find_symbol(map, map->map_ip(map, addr)); } return NULL; } struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, - struct map **mapp, symbol_filter_t filter) + struct map **mapp) { struct symbol *sym; struct rb_node *nd; @@ -582,7 +578,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node); - sym = map__find_symbol_by_name(pos, name, filter); + sym = map__find_symbol_by_name(pos, name); if (sym == NULL) continue; @@ -600,15 +596,14 @@ out: struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, enum map_type type, const char *name, - struct map **mapp, - symbol_filter_t filter) + struct map **mapp) { - struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp, filter); + struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp); return sym; } -int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) +int map_groups__find_ams(struct addr_map_symbol *ams) { if (ams->addr < ams->map->start || ams->addr >= ams->map->end) { if (ams->map->groups == NULL) @@ -620,7 +615,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) } ams->al_addr = ams->map->map_ip(ams->map, ams->addr); - ams->sym = map__find_symbol(ams->map, ams->al_addr, filter); + ams->sym = map__find_symbol(ams->map, ams->al_addr); return ams->sym ? 0 : -1; } @@ -687,9 +682,16 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp continue; if (verbose >= 2) { - fputs("overlapping maps:\n", fp); - map__fprintf(map, fp); - map__fprintf(pos, fp); + + if (use_browser) { + pr_warning("overlapping maps in %s " + "(disable tui for more info)\n", + map->dso->name); + } else { + fputs("overlapping maps:\n", fp); + map__fprintf(map, fp); + map__fprintf(pos, fp); + } } rb_erase_init(&pos->rb_node, root); @@ -707,7 +709,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp before->end = map->start; __map_groups__insert(pos->groups, before); - if (verbose >= 2) + if (verbose >= 2 && !use_browser) map__fprintf(before, fp); map__put(before); } @@ -722,7 +724,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp after->start = map->end; __map_groups__insert(pos->groups, after); - if (verbose >= 2) + if (verbose >= 2 && !use_browser) map__fprintf(after, fp); map__put(after); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index d83396ceecba..abdacf800c98 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -127,17 +127,14 @@ struct thread; * @map: the 'struct map *' in which symbols itereated * @sym_name: the symbol name * @pos: the 'struct symbol *' to use as a loop cursor - * @filter: to use when loading the DSO */ -#define __map__for_each_symbol_by_name(map, sym_name, pos, filter) \ - for (pos = map__find_symbol_by_name(map, sym_name, filter); \ +#define __map__for_each_symbol_by_name(map, sym_name, pos) \ + for (pos = map__find_symbol_by_name(map, sym_name); \ pos && arch__compare_symbol_names(pos->name, sym_name) == 0; \ pos = symbol__next_by_name(pos)) #define map__for_each_symbol_by_name(map, sym_name, pos) \ - __map__for_each_symbol_by_name(map, sym_name, (pos), NULL) - -typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); + __map__for_each_symbol_by_name(map, sym_name, (pos)) int arch__compare_symbol_names(const char *namea, const char *nameb); void map__init(struct map *map, enum map_type type, @@ -173,11 +170,9 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp); int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp); -int map__load(struct map *map, symbol_filter_t filter); -struct symbol *map__find_symbol(struct map *map, - u64 addr, symbol_filter_t filter); -struct symbol *map__find_symbol_by_name(struct map *map, const char *name, - symbol_filter_t filter); +int map__load(struct map *map); +struct symbol *map__find_symbol(struct map *map, u64 addr); +struct symbol *map__find_symbol_by_name(struct map *map, const char *name); void map__fixup_start(struct map *map); void map__fixup_end(struct map *map); @@ -191,7 +186,7 @@ struct map *maps__find(struct maps *maps, u64 addr); struct map *maps__first(struct maps *maps); struct map *map__next(struct map *map); struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, - struct map **mapp, symbol_filter_t filter); + struct map **mapp); void map_groups__init(struct map_groups *mg, struct machine *machine); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct thread *thread, @@ -231,25 +226,22 @@ static inline struct map *map_groups__next(struct map *map) struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, - struct map **mapp, - symbol_filter_t filter); + struct map **mapp); struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, enum map_type type, const char *name, - struct map **mapp, - symbol_filter_t filter); + struct map **mapp); struct addr_map_symbol; -int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter); +int map_groups__find_ams(struct addr_map_symbol *ams); static inline struct symbol *map_groups__find_function_by_name(struct map_groups *mg, - const char *name, struct map **mapp, - symbol_filter_t filter) + const char *name, struct map **mapp) { - return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter); + return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp); } int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index bbc368e7d1e4..1d4ab53c60ca 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -9,6 +9,7 @@ #include "mem-events.h" #include "debug.h" #include "symbol.h" +#include "sort.h" unsigned int perf_mem_events__loads_ldlat = 30; @@ -268,3 +269,138 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_in return i; } + +int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) +{ + union perf_mem_data_src *data_src = &mi->data_src; + u64 daddr = mi->daddr.addr; + u64 op = data_src->mem_op; + u64 lvl = data_src->mem_lvl; + u64 snoop = data_src->mem_snoop; + u64 lock = data_src->mem_lock; + int err = 0; + +#define HITM_INC(__f) \ +do { \ + stats->__f++; \ + stats->tot_hitm++; \ +} while (0) + +#define P(a, b) PERF_MEM_##a##_##b + + stats->nr_entries++; + + if (lock & P(LOCK, LOCKED)) stats->locks++; + + if (op & P(OP, LOAD)) { + /* load */ + stats->load++; + + if (!daddr) { + stats->ld_noadrs++; + return -1; + } + + if (lvl & P(LVL, HIT)) { + if (lvl & P(LVL, UNC)) stats->ld_uncache++; + if (lvl & P(LVL, IO)) stats->ld_io++; + if (lvl & P(LVL, LFB)) stats->ld_fbhit++; + if (lvl & P(LVL, L1 )) stats->ld_l1hit++; + if (lvl & P(LVL, L2 )) stats->ld_l2hit++; + if (lvl & P(LVL, L3 )) { + if (snoop & P(SNOOP, HITM)) + HITM_INC(lcl_hitm); + else + stats->ld_llchit++; + } + + if (lvl & P(LVL, LOC_RAM)) { + stats->lcl_dram++; + if (snoop & P(SNOOP, HIT)) + stats->ld_shared++; + else + stats->ld_excl++; + } + + if ((lvl & P(LVL, REM_RAM1)) || + (lvl & P(LVL, REM_RAM2))) { + stats->rmt_dram++; + if (snoop & P(SNOOP, HIT)) + stats->ld_shared++; + else + stats->ld_excl++; + } + } + + if ((lvl & P(LVL, REM_CCE1)) || + (lvl & P(LVL, REM_CCE2))) { + if (snoop & P(SNOOP, HIT)) + stats->rmt_hit++; + else if (snoop & P(SNOOP, HITM)) + HITM_INC(rmt_hitm); + } + + if ((lvl & P(LVL, MISS))) + stats->ld_miss++; + + } else if (op & P(OP, STORE)) { + /* store */ + stats->store++; + + if (!daddr) { + stats->st_noadrs++; + return -1; + } + + if (lvl & P(LVL, HIT)) { + if (lvl & P(LVL, UNC)) stats->st_uncache++; + if (lvl & P(LVL, L1 )) stats->st_l1hit++; + } + if (lvl & P(LVL, MISS)) + if (lvl & P(LVL, L1)) stats->st_l1miss++; + } else { + /* unparsable data_src? */ + stats->noparse++; + return -1; + } + + if (!mi->daddr.map || !mi->iaddr.map) { + stats->nomap++; + return -1; + } + +#undef P +#undef HITM_INC + return err; +} + +void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add) +{ + stats->nr_entries += add->nr_entries; + + stats->locks += add->locks; + stats->store += add->store; + stats->st_uncache += add->st_uncache; + stats->st_noadrs += add->st_noadrs; + stats->st_l1hit += add->st_l1hit; + stats->st_l1miss += add->st_l1miss; + stats->load += add->load; + stats->ld_excl += add->ld_excl; + stats->ld_shared += add->ld_shared; + stats->ld_uncache += add->ld_uncache; + stats->ld_io += add->ld_io; + stats->ld_miss += add->ld_miss; + stats->ld_noadrs += add->ld_noadrs; + stats->ld_fbhit += add->ld_fbhit; + stats->ld_l1hit += add->ld_l1hit; + stats->ld_l2hit += add->ld_l2hit; + stats->ld_llchit += add->ld_llchit; + stats->lcl_hitm += add->lcl_hitm; + stats->rmt_hitm += add->rmt_hitm; + stats->tot_hitm += add->tot_hitm; + stats->rmt_hit += add->rmt_hit; + stats->lcl_dram += add->lcl_dram; + stats->rmt_dram += add->rmt_dram; + stats->nomap += add->nomap; + stats->noparse += add->noparse; +} diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 7f69bf9d789d..40f72ee4f42a 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -2,6 +2,10 @@ #define __PERF_MEM_EVENTS_H #include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <linux/types.h> +#include "stat.h" struct perf_mem_event { bool record; @@ -33,4 +37,38 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info); int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info); +struct c2c_stats { + u32 nr_entries; + + u32 locks; /* count of 'lock' transactions */ + u32 store; /* count of all stores in trace */ + u32 st_uncache; /* stores to uncacheable address */ + u32 st_noadrs; /* cacheable store with no address */ + u32 st_l1hit; /* count of stores that hit L1D */ + u32 st_l1miss; /* count of stores that miss L1D */ + u32 load; /* count of all loads in trace */ + u32 ld_excl; /* exclusive loads, rmt/lcl DRAM - snp none/miss */ + u32 ld_shared; /* shared loads, rmt/lcl DRAM - snp hit */ + u32 ld_uncache; /* loads to uncacheable address */ + u32 ld_io; /* loads to io address */ + u32 ld_miss; /* loads miss */ + u32 ld_noadrs; /* cacheable load with no address */ + u32 ld_fbhit; /* count of loads hitting Fill Buffer */ + u32 ld_l1hit; /* count of loads that hit L1D */ + u32 ld_l2hit; /* count of loads that hit L2D */ + u32 ld_llchit; /* count of loads that hit LLC */ + u32 lcl_hitm; /* count of loads with local HITM */ + u32 rmt_hitm; /* count of loads with remote HITM */ + u32 tot_hitm; /* count of loads with local and remote HITM */ + u32 rmt_hit; /* count of loads with remote hit clean; */ + u32 lcl_dram; /* count of loads miss to local DRAM */ + u32 rmt_dram; /* count of loads miss to remote DRAM */ + u32 nomap; /* count of load/stores with no phys adrs */ + u32 noparse; /* count of unparsable data sources */ +}; + +struct hist_entry; +int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi); +void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add); + #endif /* __PERF_MEM_EVENTS_H */ diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index afc088dd7d20..38fd11504015 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -31,59 +31,51 @@ static const struct branch_mode branch_modes[] = { BRANCH_END }; -int -parse_branch_stack(const struct option *opt, const char *str, int unset) +int parse_branch_str(const char *str, __u64 *mode) { #define ONLY_PLM \ (PERF_SAMPLE_BRANCH_USER |\ PERF_SAMPLE_BRANCH_KERNEL |\ PERF_SAMPLE_BRANCH_HV) - uint64_t *mode = (uint64_t *)opt->value; + int ret = 0; + char *p, *s; + char *os = NULL; const struct branch_mode *br; - char *s, *os = NULL, *p; - int ret = -1; - if (unset) + if (str == NULL) { + *mode = PERF_SAMPLE_BRANCH_ANY; return 0; + } - /* - * cannot set it twice, -b + --branch-filter for instance - */ - if (*mode) + /* because str is read-only */ + s = os = strdup(str); + if (!s) return -1; - /* str may be NULL in case no arg is passed to -b */ - if (str) { - /* because str is read-only */ - s = os = strdup(str); - if (!s) - return -1; - - for (;;) { - p = strchr(s, ','); - if (p) - *p = '\0'; - - for (br = branch_modes; br->name; br++) { - if (!strcasecmp(s, br->name)) - break; - } - if (!br->name) { - ui__warning("unknown branch filter %s," - " check man page\n", s); - goto error; - } - - *mode |= br->mode; - - if (!p) - break; + for (;;) { + p = strchr(s, ','); + if (p) + *p = '\0'; - s = p + 1; + for (br = branch_modes; br->name; br++) { + if (!strcasecmp(s, br->name)) + break; + } + if (!br->name) { + ret = -1; + pr_warning("unknown branch filter %s," + " check man page\n", s); + goto error; } + + *mode |= br->mode; + + if (!p) + break; + + s = p + 1; } - ret = 0; /* default to any branch */ if ((*mode & ~ONLY_PLM) == 0) { @@ -93,3 +85,20 @@ error: free(os); return ret; } + +int +parse_branch_stack(const struct option *opt, const char *str, int unset) +{ + __u64 *mode = (__u64 *)opt->value; + + if (unset) + return 0; + + /* + * cannot set it twice, -b + --branch-filter for instance + */ + if (*mode) + return -1; + + return parse_branch_str(str, mode); +} diff --git a/tools/perf/util/parse-branch-options.h b/tools/perf/util/parse-branch-options.h index b9d9470c2e82..6086fd90eb23 100644 --- a/tools/perf/util/parse-branch-options.h +++ b/tools/perf/util/parse-branch-options.h @@ -1,5 +1,6 @@ #ifndef _PERF_PARSE_BRANCH_OPTIONS_H #define _PERF_PARSE_BRANCH_OPTIONS_H 1 -struct option; +#include <stdint.h> int parse_branch_stack(const struct option *opt, const char *str, int unset); +int parse_branch_str(const char *str, __u64 *mode); #endif /* _PERF_PARSE_BRANCH_OPTIONS_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 6c913c3914fb..3c876b8ba4de 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -22,6 +22,7 @@ #include "cpumap.h" #include "probe-file.h" #include "asm/bug.h" +#include "util/parse-branch-options.h" #define MAX_NAME_LEN 100 @@ -904,6 +905,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_MAX_STACK] = "max-stack", [PARSE_EVENTS__TERM_TYPE_OVERWRITE] = "overwrite", [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite", + [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", }; static bool config_term_shrinked; @@ -923,6 +925,7 @@ config_term_avail(int term_type, struct parse_events_error *err) case PARSE_EVENTS__TERM_TYPE_CONFIG1: case PARSE_EVENTS__TERM_TYPE_CONFIG2: case PARSE_EVENTS__TERM_TYPE_NAME: + case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: return true; default: if (!err) @@ -971,10 +974,13 @@ do { \ CHECK_TYPE_VAL(NUM); break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: - /* - * TODO uncomment when the field is available - * attr->branch_sample_type = term->val.num; - */ + CHECK_TYPE_VAL(STR); + if (strcmp(term->val.str, "no") && + parse_branch_str(term->val.str, &attr->branch_sample_type)) { + err->str = strdup("invalid branch sample type"); + err->idx = term->err_val; + return -EINVAL; + } break; case PARSE_EVENTS__TERM_TYPE_TIME: CHECK_TYPE_VAL(NUM); @@ -1034,7 +1040,8 @@ static int config_term_pmu(struct perf_event_attr *attr, struct parse_events_term *term, struct parse_events_error *err) { - if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) + if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER || + term->type_term == PARSE_EVENTS__TERM_TYPE_DRV_CFG) /* * Always succeed for sysfs terms, as we dont know * at this point what type they need to have. @@ -1116,6 +1123,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: ADD_CONFIG_TERM(CALLGRAPH, callgraph, term->val.str); break; + case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: + ADD_CONFIG_TERM(BRANCH, branch, term->val.str); + break; case PARSE_EVENTS__TERM_TYPE_STACKSIZE: ADD_CONFIG_TERM(STACK_USER, stack_user, term->val.num); break; @@ -1134,6 +1144,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1); break; + case PARSE_EVENTS__TERM_TYPE_DRV_CFG: + ADD_CONFIG_TERM(DRV_CFG, drv_cfg, term->val.str); + break; default: break; } @@ -1453,7 +1466,7 @@ comp_pmu(const void *p1, const void *p2) struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1; struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2; - return strcmp(pmu1->symbol, pmu2->symbol); + return strcasecmp(pmu1->symbol, pmu2->symbol); } static void perf_pmu__parse_cleanup(void) @@ -1755,20 +1768,49 @@ foreach_evsel_in_last_glob(struct perf_evlist *evlist, static int set_filter(struct perf_evsel *evsel, const void *arg) { const char *str = arg; + bool found = false; + int nr_addr_filters = 0; + struct perf_pmu *pmu = NULL; - if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) { - fprintf(stderr, - "--filter option should follow a -e tracepoint option\n"); - return -1; + if (evsel == NULL) + goto err; + + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { + if (perf_evsel__append_tp_filter(evsel, str) < 0) { + fprintf(stderr, + "not enough memory to hold filter string\n"); + return -1; + } + + return 0; } - if (perf_evsel__append_filter(evsel, "&&", str) < 0) { + while ((pmu = perf_pmu__scan(pmu)) != NULL) + if (pmu->type == evsel->attr.type) { + found = true; + break; + } + + if (found) + perf_pmu__scan_file(pmu, "nr_addr_filters", + "%d", &nr_addr_filters); + + if (!nr_addr_filters) + goto err; + + if (perf_evsel__append_addr_filter(evsel, str) < 0) { fprintf(stderr, "not enough memory to hold filter string\n"); return -1; } return 0; + +err: + fprintf(stderr, + "--filter option should follow a -e tracepoint or HW tracer option\n"); + + return -1; } int parse_filter(const struct option *opt, const char *str, @@ -1793,7 +1835,7 @@ static int add_exclude_perf_filter(struct perf_evsel *evsel, snprintf(new_filter, sizeof(new_filter), "common_pid != %d", getpid()); - if (perf_evsel__append_filter(evsel, "&&", new_filter) < 0) { + if (perf_evsel__append_tp_filter(evsel, new_filter) < 0) { fprintf(stderr, "not enough memory to hold filter string\n"); return -1; @@ -2229,7 +2271,8 @@ out_enomem: /* * Print the help text for the event symbols: */ -void print_events(const char *event_glob, bool name_only) +void print_events(const char *event_glob, bool name_only, bool quiet_flag, + bool long_desc) { print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); @@ -2239,7 +2282,7 @@ void print_events(const char *event_glob, bool name_only) print_hwcache_events(event_glob, name_only); - print_pmu_events(event_glob, name_only); + print_pmu_events(event_glob, name_only, quiet_flag, long_desc); if (event_glob != NULL) return; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index d1edbf8cc66a..da246a3ddb69 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -71,6 +71,7 @@ enum { PARSE_EVENTS__TERM_TYPE_MAX_STACK, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE, PARSE_EVENTS__TERM_TYPE_OVERWRITE, + PARSE_EVENTS__TERM_TYPE_DRV_CFG, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -171,7 +172,8 @@ void parse_events_update_lists(struct list_head *list_event, void parse_events_evlist_error(struct parse_events_evlist *data, int idx, const char *str); -void print_events(const char *event_glob, bool name_only); +void print_events(const char *event_glob, bool name_only, bool quiet, + bool long_desc); struct event_symbol { const char *symbol; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 7a2519435da0..660fca05bc93 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -53,6 +53,26 @@ static int str(yyscan_t scanner, int token) return token; } +/* + * This function is called when the parser gets two kind of input: + * + * @cfg1 or @cfg2=config + * + * The leading '@' is stripped off before 'cfg1' and 'cfg2=config' are given to + * bison. In the latter case it is necessary to keep the string intact so that + * the PMU kernel driver can determine what configurable is associated to + * 'config'. + */ +static int drv_str(yyscan_t scanner, int token) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + /* Strip off the '@' */ + yylval->str = strdup(text + 1); + return token; +} + #define REWIND(__alloc) \ do { \ YYSTYPE *__yylval = parse_events_get_lval(yyscanner); \ @@ -116,14 +136,15 @@ do { \ group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ -bpf_object .*\.(o|bpf) -bpf_source .*\.c +bpf_object [^,{}]+\.(o|bpf) +bpf_source [^,{}]+\.c num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?.]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* +drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ modifier_event [ukhpPGHSDI]+ modifier_bp [rwx]{1,3} @@ -209,6 +230,7 @@ no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } {name_minus} { return str(yyscanner, PE_NAME); } \[all\] { return PE_ARRAY_ALL; } "[" { BEGIN(array); return '['; } +@{drv_cfg_term} { return drv_str(yyscanner, PE_DRV_CFG_TERM); } } <mem>{ diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 5be4a5f216d6..879115f93edc 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -49,6 +49,7 @@ static void inc_group_count(struct list_head *list, %token PE_ERROR %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT %token PE_ARRAY_ALL PE_ARRAY_RANGE +%token PE_DRV_CFG_TERM %type <num> PE_VALUE %type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW @@ -63,6 +64,7 @@ static void inc_group_count(struct list_head *list, %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT +%type <str> PE_DRV_CFG_TERM %type <num> value_sym %type <head> event_config %type <head> opt_event_config @@ -599,6 +601,15 @@ PE_NAME array '=' PE_VALUE term->array = $2; $$ = term; } +| +PE_DRV_CFG_TERM +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, + $1, $1, &@1, NULL)); + $$ = term; +} array: '[' array_terms ']' diff --git a/tools/perf/util/perf-hooks-list.h b/tools/perf/util/perf-hooks-list.h new file mode 100644 index 000000000000..2867c07ee84e --- /dev/null +++ b/tools/perf/util/perf-hooks-list.h @@ -0,0 +1,3 @@ +PERF_HOOK(record_start) +PERF_HOOK(record_end) +PERF_HOOK(test) diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c new file mode 100644 index 000000000000..cb368306b12b --- /dev/null +++ b/tools/perf/util/perf-hooks.c @@ -0,0 +1,88 @@ +/* + * perf_hooks.c + * + * Copyright (C) 2016 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2016 Huawei Inc. + */ + +#include <errno.h> +#include <stdlib.h> +#include <setjmp.h> +#include <linux/err.h> +#include "util/util.h" +#include "util/debug.h" +#include "util/perf-hooks.h" + +static sigjmp_buf jmpbuf; +static const struct perf_hook_desc *current_perf_hook; + +void perf_hooks__invoke(const struct perf_hook_desc *desc) +{ + if (!(desc && desc->p_hook_func && *desc->p_hook_func)) + return; + + if (sigsetjmp(jmpbuf, 1)) { + pr_warning("Fatal error (SEGFAULT) in perf hook '%s'\n", + desc->hook_name); + *(current_perf_hook->p_hook_func) = NULL; + } else { + current_perf_hook = desc; + (**desc->p_hook_func)(desc->hook_ctx); + } + current_perf_hook = NULL; +} + +void perf_hooks__recover(void) +{ + if (current_perf_hook) + siglongjmp(jmpbuf, 1); +} + +#define PERF_HOOK(name) \ +perf_hook_func_t __perf_hook_func_##name = NULL; \ +struct perf_hook_desc __perf_hook_desc_##name = \ + {.hook_name = #name, \ + .p_hook_func = &__perf_hook_func_##name, \ + .hook_ctx = NULL}; +#include "perf-hooks-list.h" +#undef PERF_HOOK + +#define PERF_HOOK(name) \ + &__perf_hook_desc_##name, + +static struct perf_hook_desc *perf_hooks[] = { +#include "perf-hooks-list.h" +}; +#undef PERF_HOOK + +int perf_hooks__set_hook(const char *hook_name, + perf_hook_func_t hook_func, + void *hook_ctx) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(perf_hooks); i++) { + if (strcmp(hook_name, perf_hooks[i]->hook_name) != 0) + continue; + + if (*(perf_hooks[i]->p_hook_func)) + pr_warning("Overwrite existing hook: %s\n", hook_name); + *(perf_hooks[i]->p_hook_func) = hook_func; + perf_hooks[i]->hook_ctx = hook_ctx; + return 0; + } + return -ENOENT; +} + +perf_hook_func_t perf_hooks__get_hook(const char *hook_name) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(perf_hooks); i++) { + if (strcmp(hook_name, perf_hooks[i]->hook_name) != 0) + continue; + + return *(perf_hooks[i]->p_hook_func); + } + return ERR_PTR(-ENOENT); +} diff --git a/tools/perf/util/perf-hooks.h b/tools/perf/util/perf-hooks.h new file mode 100644 index 000000000000..838d5797bc1e --- /dev/null +++ b/tools/perf/util/perf-hooks.h @@ -0,0 +1,39 @@ +#ifndef PERF_UTIL_PERF_HOOKS_H +#define PERF_UTIL_PERF_HOOKS_H + +#ifdef __cplusplus +extern "C" { +#endif + +typedef void (*perf_hook_func_t)(void *ctx); +struct perf_hook_desc { + const char * const hook_name; + perf_hook_func_t * const p_hook_func; + void *hook_ctx; +}; + +extern void perf_hooks__invoke(const struct perf_hook_desc *); +extern void perf_hooks__recover(void); + +#define PERF_HOOK(name) \ +extern struct perf_hook_desc __perf_hook_desc_##name; \ +static inline void perf_hooks__invoke_##name(void) \ +{ \ + perf_hooks__invoke(&__perf_hook_desc_##name); \ +} + +#include "perf-hooks-list.h" +#undef PERF_HOOK + +extern int +perf_hooks__set_hook(const char *hook_name, + perf_hook_func_t hook_func, + void *hook_ctx); + +extern perf_hook_func_t +perf_hooks__get_hook(const char *hook_name); + +#ifdef __cplusplus +} +#endif +#endif diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index ddb0261b2577..dc6ccaa4e927 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -12,6 +12,9 @@ #include "pmu.h" #include "parse-events.h" #include "cpumap.h" +#include "header.h" +#include "pmu-events/pmu-events.h" +#include "cache.h" struct perf_pmu_format { char *name; @@ -220,7 +223,8 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc __maybe_unused, char *val) + char *desc, char *val, char *long_desc, + char *topic) { struct perf_pmu_alias *alias; int ret; @@ -253,6 +257,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, perf_pmu__parse_snapshot(alias, dir, name); } + alias->desc = desc ? strdup(desc) : NULL; + alias->long_desc = long_desc ? strdup(long_desc) : + desc ? strdup(desc) : NULL; + alias->topic = topic ? strdup(topic) : NULL; + list_add_tail(&alias->list, list); return 0; @@ -269,7 +278,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI buf[ret] = 0; - return __perf_pmu__new_alias(list, dir, name, NULL, buf); + return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -445,14 +454,23 @@ static struct cpu_map *pmu_cpumask(const char *name) FILE *file; struct cpu_map *cpus; const char *sysfs = sysfs__mountpoint(); + const char *templates[] = { + "%s/bus/event_source/devices/%s/cpumask", + "%s/bus/event_source/devices/%s/cpus", + NULL + }; + const char **template; if (!sysfs) return NULL; - snprintf(path, PATH_MAX, - "%s/bus/event_source/devices/%s/cpumask", sysfs, name); + for (template = templates; *template; template++) { + snprintf(path, PATH_MAX, *template, sysfs, name); + if (stat(path, &st) == 0) + break; + } - if (stat(path, &st) < 0) + if (!*template) return NULL; file = fopen(path, "r"); @@ -464,6 +482,72 @@ static struct cpu_map *pmu_cpumask(const char *name) return cpus; } +/* + * Return the CPU id as a raw string. + * + * Each architecture should provide a more precise id string that + * can be use to match the architecture's "mapfile". + */ +char * __weak get_cpuid_str(void) +{ + return NULL; +} + +/* + * From the pmu_events_map, find the table of PMU events that corresponds + * to the current running CPU. Then, add all PMU events from that table + * as aliases. + */ +static void pmu_add_cpu_aliases(struct list_head *head) +{ + int i; + struct pmu_events_map *map; + struct pmu_event *pe; + char *cpuid; + static bool printed; + + cpuid = getenv("PERF_CPUID"); + if (cpuid) + cpuid = strdup(cpuid); + if (!cpuid) + cpuid = get_cpuid_str(); + if (!cpuid) + return; + + if (!printed) { + pr_debug("Using CPUID %s\n", cpuid); + printed = true; + } + + i = 0; + while (1) { + map = &pmu_events_map[i++]; + if (!map->table) + goto out; + + if (!strcmp(map->cpuid, cpuid)) + break; + } + + /* + * Found a matching PMU events table. Create aliases + */ + i = 0; + while (1) { + pe = &map->table[i++]; + if (!pe->name) + break; + + /* need type casts to override 'const' */ + __perf_pmu__new_alias(head, NULL, (char *)pe->name, + (char *)pe->desc, (char *)pe->event, + (char *)pe->long_desc, (char *)pe->topic); + } + +out: + free(cpuid); +} + struct perf_event_attr * __weak perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { @@ -488,6 +572,9 @@ static struct perf_pmu *pmu_lookup(const char *name) if (pmu_aliases(name, &aliases)) return NULL; + if (!strcmp(name, "cpu")) + pmu_add_cpu_aliases(&aliases); + if (pmu_type(name, &type)) return NULL; @@ -974,21 +1061,63 @@ static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu, return buf; } -static int cmp_string(const void *a, const void *b) +struct sevent { + char *name; + char *desc; + char *topic; +}; + +static int cmp_sevent(const void *a, const void *b) { - const char * const *as = a; - const char * const *bs = b; - return strcmp(*as, *bs); + const struct sevent *as = a; + const struct sevent *bs = b; + + /* Put extra events last */ + if (!!as->desc != !!bs->desc) + return !!as->desc - !!bs->desc; + if (as->topic && bs->topic) { + int n = strcmp(as->topic, bs->topic); + + if (n) + return n; + } + return strcmp(as->name, bs->name); } -void print_pmu_events(const char *event_glob, bool name_only) +static void wordwrap(char *s, int start, int max, int corr) +{ + int column = start; + int n; + + while (*s) { + int wlen = strcspn(s, " \t"); + + if (column + wlen >= max && column > start) { + printf("\n%*s", start, ""); + column = start + corr; + } + n = printf("%s%.*s", column > start ? " " : "", wlen, s); + if (n <= 0) + break; + s += wlen; + column += n; + while (isspace(*s)) + s++; + } +} + +void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, + bool long_desc) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; char buf[1024]; int printed = 0; int len, j; - char **aliases; + struct sevent *aliases; + int numdesc = 0; + int columns = pager_get_columns(); + char *topic = NULL; pmu = NULL; len = 0; @@ -998,28 +1127,40 @@ void print_pmu_events(const char *event_glob, bool name_only) if (pmu->selectable) len++; } - aliases = zalloc(sizeof(char *) * len); + aliases = zalloc(sizeof(struct sevent) * len); if (!aliases) goto out_enomem; pmu = NULL; j = 0; while ((pmu = perf_pmu__scan(pmu)) != NULL) { list_for_each_entry(alias, &pmu->aliases, list) { - char *name = format_alias(buf, sizeof(buf), pmu, alias); + char *name = alias->desc ? alias->name : + format_alias(buf, sizeof(buf), pmu, alias); bool is_cpu = !strcmp(pmu->name, "cpu"); if (event_glob != NULL && - !(strglobmatch(name, event_glob) || - (!is_cpu && strglobmatch(alias->name, - event_glob)))) + !(strglobmatch_nocase(name, event_glob) || + (!is_cpu && strglobmatch_nocase(alias->name, + event_glob)) || + (alias->topic && + strglobmatch_nocase(alias->topic, event_glob)))) continue; - if (is_cpu && !name_only) + if (is_cpu && !name_only && !alias->desc) name = format_alias_or(buf, sizeof(buf), pmu, alias); - aliases[j] = strdup(name); - if (aliases[j] == NULL) + aliases[j].name = name; + if (is_cpu && !name_only && !alias->desc) + aliases[j].name = format_alias_or(buf, + sizeof(buf), + pmu, alias); + aliases[j].name = strdup(aliases[j].name); + if (!aliases[j].name) goto out_enomem; + + aliases[j].desc = long_desc ? alias->long_desc : + alias->desc; + aliases[j].topic = alias->topic; j++; } if (pmu->selectable && @@ -1027,25 +1168,39 @@ void print_pmu_events(const char *event_glob, bool name_only) char *s; if (asprintf(&s, "%s//", pmu->name) < 0) goto out_enomem; - aliases[j] = s; + aliases[j].name = s; j++; } } len = j; - qsort(aliases, len, sizeof(char *), cmp_string); + qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { if (name_only) { - printf("%s ", aliases[j]); + printf("%s ", aliases[j].name); continue; } - printf(" %-50s [Kernel PMU event]\n", aliases[j]); + if (aliases[j].desc && !quiet_flag) { + if (numdesc++ == 0) + printf("\n"); + if (aliases[j].topic && (!topic || + strcmp(topic, aliases[j].topic))) { + printf("%s%s:\n", topic ? "\n" : "", + aliases[j].topic); + topic = aliases[j].topic; + } + printf(" %-50s\n", aliases[j].name); + printf("%*s", 8, "["); + wordwrap(aliases[j].desc, 8, columns, 0); + printf("]\n"); + } else + printf(" %-50s [Kernel PMU event]\n", aliases[j].name); printed++; } if (printed && pager_in_use()) printf("\n"); out_free: for (j = 0; j < len; j++) - zfree(&aliases[j]); + zfree(&aliases[j].name); zfree(&aliases); return; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 5d7e84466bee..25712034c815 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -4,6 +4,7 @@ #include <linux/bitmap.h> #include <linux/perf_event.h> #include <stdbool.h> +#include "evsel.h" #include "parse-events.h" enum { @@ -25,6 +26,7 @@ struct perf_pmu { struct list_head format; /* HEAD struct perf_pmu_format -> list */ struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */ struct list_head list; /* ELEM */ + int (*set_drv_config) (struct perf_evsel_config_term *term); }; struct perf_pmu_info { @@ -38,6 +40,9 @@ struct perf_pmu_info { struct perf_pmu_alias { char *name; + char *desc; + char *long_desc; + char *topic; struct list_head terms; /* HEAD struct parse_events_term -> list */ struct list_head list; /* ELEM */ char unit[UNIT_MAX_LEN+1]; @@ -69,7 +74,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); -void print_pmu_events(const char *event_glob, bool name_only); +void print_pmu_events(const char *event_glob, bool name_only, bool quiet, + bool long_desc); bool pmu_have_event(const char *pname, const char *name); int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 28733962cd80..d281ae2b54e8 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -110,13 +110,12 @@ void exit_probe_symbol_maps(void) static struct symbol *__find_kernel_function_by_name(const char *name, struct map **mapp) { - return machine__find_kernel_function_by_name(host_machine, name, mapp, - NULL); + return machine__find_kernel_function_by_name(host_machine, name, mapp); } static struct symbol *__find_kernel_function(u64 addr, struct map **mapp) { - return machine__find_kernel_function(host_machine, addr, mapp, NULL); + return machine__find_kernel_function(host_machine, addr, mapp); } static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) @@ -125,7 +124,7 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) struct kmap *kmap; struct map *map = machine__kernel_map(host_machine); - if (map__load(map, NULL) < 0) + if (map__load(map) < 0) return NULL; kmap = map__kmap(map); @@ -214,9 +213,13 @@ static int convert_exec_to_group(const char *exec, char **result) goto out; } - ptr2 = strpbrk(ptr1, "-._"); - if (ptr2) - *ptr2 = '\0'; + for (ptr2 = ptr1; *ptr2 != '\0'; ptr2++) { + if (!isalnum(*ptr2) && *ptr2 != '_') { + *ptr2 = '\0'; + break; + } + } + ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1); if (ret < 0) goto out; @@ -351,9 +354,9 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) vmlinux_name = symbol_conf.vmlinux_name; dso->load_errno = 0; if (vmlinux_name) - ret = dso__load_vmlinux(dso, map, vmlinux_name, false, NULL); + ret = dso__load_vmlinux(dso, map, vmlinux_name, false); else - ret = dso__load_vmlinux_path(dso, map, NULL); + ret = dso__load_vmlinux_path(dso, map); found: *pdso = dso; return ret; @@ -674,6 +677,10 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, char *tmp; int i, skipped = 0; + /* Skip post process if the target is an offline kernel */ + if (symbol_conf.ignore_vmlinux_buildid) + return 0; + reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -1614,19 +1621,27 @@ out: return ret; } +/* Returns true if *any* ARG is either C variable, $params or $vars. */ +bool perf_probe_with_var(struct perf_probe_event *pev) +{ + int i = 0; + + for (i = 0; i < pev->nargs; i++) + if (is_c_varname(pev->args[i].var) || + !strcmp(pev->args[i].var, PROBE_ARG_PARAMS) || + !strcmp(pev->args[i].var, PROBE_ARG_VARS)) + return true; + return false; +} + /* Return true if this perf_probe_event requires debuginfo */ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev) { - int i; - if (pev->point.file || pev->point.line || pev->point.lazy_line) return true; - for (i = 0; i < pev->nargs; i++) - if (is_c_varname(pev->args[i].var) || - !strcmp(pev->args[i].var, "$params") || - !strcmp(pev->args[i].var, "$vars")) - return true; + if (perf_probe_with_var(pev)) + return true; return false; } @@ -1987,7 +2002,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp, map = dso__new_map(tp->module); if (!map) goto out; - sym = map__find_symbol(map, addr, NULL); + sym = map__find_symbol(map, addr); } else { if (tp->symbol && !addr) { if (kernel_get_symbol_address_by_name(tp->symbol, @@ -2692,7 +2707,7 @@ static int find_probe_functions(struct map *map, char *name, struct symbol *sym; struct rb_node *tmp; - if (map__load(map, NULL) < 0) + if (map__load(map) < 0) return 0; map__for_each_symbol(map, sym, tmp) { @@ -3207,6 +3222,52 @@ int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs) return 0; } +static int show_probe_trace_event(struct probe_trace_event *tev) +{ + char *buf = synthesize_probe_trace_command(tev); + + if (!buf) { + pr_debug("Failed to synthesize probe trace event.\n"); + return -EINVAL; + } + + /* Showing definition always go stdout */ + printf("%s\n", buf); + free(buf); + + return 0; +} + +int show_probe_trace_events(struct perf_probe_event *pevs, int npevs) +{ + struct strlist *namelist = strlist__new(NULL, NULL); + struct probe_trace_event *tev; + struct perf_probe_event *pev; + int i, j, ret = 0; + + if (!namelist) + return -ENOMEM; + + for (j = 0; j < npevs && !ret; j++) { + pev = &pevs[j]; + for (i = 0; i < pev->ntevs && !ret; i++) { + tev = &pev->tevs[i]; + /* Skip if the symbol is out of .text or blacklisted */ + if (!tev->point.symbol && !pev->uprobes) + continue; + + /* Set new name for tev (and update namelist) */ + ret = probe_trace_event__set_name(tev, pev, + namelist, true); + if (!ret) + ret = show_probe_trace_event(tev); + } + } + strlist__delete(namelist); + + return ret; +} + int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs) { int i, ret = 0; @@ -3289,24 +3350,10 @@ out: return ret; } -/* TODO: don't use a global variable for filter ... */ -static struct strfilter *available_func_filter; - -/* - * If a symbol corresponds to a function with global binding and - * matches filter return 0. For all others return 1. - */ -static int filter_available_functions(struct map *map __maybe_unused, - struct symbol *sym) -{ - if (strfilter__compare(available_func_filter, sym->name)) - return 0; - return 1; -} - int show_available_funcs(const char *target, struct strfilter *_filter, bool user) { + struct rb_node *nd; struct map *map; int ret; @@ -3324,9 +3371,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, return -EINVAL; } - /* Load symbols with given filter */ - available_func_filter = _filter; - ret = map__load(map, filter_available_functions); + ret = map__load(map); if (ret) { if (ret == -2) { char *str = strfilter__string(_filter); @@ -3343,7 +3388,14 @@ int show_available_funcs(const char *target, struct strfilter *_filter, /* Show all (filtered) symbols */ setup_pager(); - dso__fprintf_symbols_by_name(map->dso, map->type, stdout); + + for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) { + struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); + + if (strfilter__compare(_filter, pos->sym.name)) + printf("%s\n", pos->sym.name); + } + end: if (user) { map__put(map); diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index f4f45db77c1c..5d4e94061402 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -18,6 +18,8 @@ struct probe_conf { extern struct probe_conf probe_conf; extern bool probe_event_dry_run; +struct symbol; + /* kprobe-tracer and uprobe-tracer tracing point */ struct probe_trace_point { char *realname; /* function real name (if needed) */ @@ -128,6 +130,8 @@ char *synthesize_perf_probe_point(struct perf_probe_point *pp); int perf_probe_event__copy(struct perf_probe_event *dst, struct perf_probe_event *src); +bool perf_probe_with_var(struct perf_probe_event *pev); + /* Check the perf_probe_event needs debuginfo */ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev); @@ -147,6 +151,7 @@ int line_range__init(struct line_range *lr); int add_perf_probe_events(struct perf_probe_event *pevs, int npevs); int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs); int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs); +int show_probe_trace_events(struct perf_probe_event *pevs, int npevs); void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs); int del_perf_probe_events(struct strfilter *filter); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 9c3b9ed5b3c3..436b64731f65 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -73,11 +73,10 @@ static void print_both_open_warning(int kerr, int uerr) static int open_probe_events(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; - const char *tracing_dir = ""; int ret; - ret = e_snprintf(buf, PATH_MAX, "%s/%s%s", - tracing_path, tracing_dir, trace_file); + ret = e_snprintf(buf, PATH_MAX, "%s/%s", + tracing_path, trace_file); if (ret >= 0) { pr_debug("Opening %s write=%d\n", buf, readwrite); if (readwrite && !probe_event_dry_run) @@ -700,7 +699,7 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) INIT_LIST_HEAD(&sdtlist); ret = get_sdt_note_list(&sdtlist, pathname); if (ret < 0) { - pr_debug("Failed to get sdt note: %d\n", ret); + pr_debug4("Failed to get sdt note: %d\n", ret); return ret; } list_for_each_entry(note, &sdtlist, note_list) { @@ -877,3 +876,60 @@ int probe_cache__show_all_caches(struct strfilter *filter) return 0; } + +static struct { + const char *pattern; + bool avail; + bool checked; +} probe_type_table[] = { +#define DEFINE_TYPE(idx, pat, def_avail) \ + [idx] = {.pattern = pat, .avail = (def_avail)} + DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true), + DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true), + DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false), + DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true), + DEFINE_TYPE(PROBE_TYPE_BITFIELD, + "* b<bit-width>@<bit-offset>/<container-size>", true), +}; + +bool probe_type_is_available(enum probe_type type) +{ + FILE *fp; + char *buf = NULL; + size_t len = 0; + bool target_line = false; + bool ret = probe_type_table[type].avail; + + if (type >= PROBE_TYPE_END) + return false; + /* We don't have to check the type which supported by default */ + if (ret || probe_type_table[type].checked) + return ret; + + if (asprintf(&buf, "%s/README", tracing_path) < 0) + return ret; + + fp = fopen(buf, "r"); + if (!fp) + goto end; + + zfree(&buf); + while (getline(&buf, &len, fp) > 0 && !ret) { + if (!target_line) { + target_line = !!strstr(buf, " type: "); + if (!target_line) + continue; + } else if (strstr(buf, "\t ") != buf) + break; + ret = strglobmatch(buf, probe_type_table[type].pattern); + } + /* Cache the result */ + probe_type_table[type].checked = true; + probe_type_table[type].avail = ret; + + fclose(fp); +end: + free(buf); + + return ret; +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 9577b5c0b487..eba44c3e9dca 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -19,6 +19,15 @@ struct probe_cache { struct list_head entries; }; +enum probe_type { + PROBE_TYPE_U = 0, + PROBE_TYPE_S, + PROBE_TYPE_X, + PROBE_TYPE_STRING, + PROBE_TYPE_BITFIELD, + PROBE_TYPE_END, +}; + #define PF_FL_UPROBE 1 #define PF_FL_RW 2 #define for_each_probe_cache_entry(entry, pcache) \ @@ -54,6 +63,7 @@ struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache, struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, const char *group, const char *event); int probe_cache__show_all_caches(struct strfilter *filter); +bool probe_type_is_available(enum probe_type type); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 5c290c682afe..df4debe564da 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -39,6 +39,7 @@ #include "util.h" #include "symbol.h" #include "probe-finder.h" +#include "probe-file.h" /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 @@ -170,6 +171,7 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs) */ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, Dwarf_Op *fb_ops, Dwarf_Die *sp_die, + unsigned int machine, struct probe_trace_arg *tvar) { Dwarf_Attribute attr; @@ -265,7 +267,7 @@ static_var: if (!tvar) return ret2; - regs = get_arch_regstr(regn); + regs = get_dwarf_regstr(regn, machine); if (!regs) { /* This should be a bug in DWARF or this tool */ pr_warning("Mapping for the register number %u " @@ -297,13 +299,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, char sbuf[STRERR_BUFSIZE]; int bsize, boffs, total; int ret; - char sign; + char prefix; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0 && + if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "x") != 0 && strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ - /* and respect signedness cast */ + /* and respect signedness/hexadecimal cast */ tvar->type = strdup(cast); return (tvar->type == NULL) ? -ENOMEM : 0; } @@ -365,11 +367,15 @@ static int convert_variable_type(Dwarf_Die *vr_die, } if (cast && (strcmp(cast, "u") == 0)) - sign = 'u'; + prefix = 'u'; else if (cast && (strcmp(cast, "s") == 0)) - sign = 's'; + prefix = 's'; + else if (cast && (strcmp(cast, "x") == 0) && + probe_type_is_available(PROBE_TYPE_X)) + prefix = 'x'; else - sign = die_is_signed_type(&type) ? 's' : 'u'; + prefix = die_is_signed_type(&type) ? 's' : + probe_type_is_available(PROBE_TYPE_X) ? 'x' : 'u'; ret = dwarf_bytesize(&type); if (ret <= 0) @@ -383,7 +389,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, dwarf_diename(&type), MAX_BASIC_TYPE_BITS); ret = MAX_BASIC_TYPE_BITS; } - ret = snprintf(buf, 16, "%c%d", sign, ret); + ret = snprintf(buf, 16, "%c%d", prefix, ret); formatted: if (ret < 0 || ret >= 16) { @@ -538,7 +544,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) dwarf_diename(vr_die)); ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops, - &pf->sp_die, pf->tvar); + &pf->sp_die, pf->machine, pf->tvar); if (ret == -ENOENT || ret == -EINVAL) { pr_err("Failed to find the location of the '%s' variable at this address.\n" " Perhaps it has been optimized out.\n" @@ -901,6 +907,38 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) return die_walk_lines(sp_die, probe_point_lazy_walker, pf); } +static void skip_prologue(Dwarf_Die *sp_die, struct probe_finder *pf) +{ + struct perf_probe_point *pp = &pf->pev->point; + + /* Not uprobe? */ + if (!pf->pev->uprobes) + return; + + /* Compiled with optimization? */ + if (die_is_optimized_target(&pf->cu_die)) + return; + + /* Don't know entrypc? */ + if (!pf->addr) + return; + + /* Only FUNC and FUNC@SRC are eligible. */ + if (!pp->function || pp->line || pp->retprobe || pp->lazy_line || + pp->offset || pp->abs_address) + return; + + /* Not interested in func parameter? */ + if (!perf_probe_with_var(pf->pev)) + return; + + pr_info("Target program is compiled without optimization. Skipping prologue.\n" + "Probe on address 0x%" PRIx64 " to force probing at the function entry.\n\n", + pf->addr); + + die_skip_prologue(sp_die, &pf->cu_die, &pf->addr); +} + static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) { struct probe_finder *pf = data; @@ -917,6 +955,11 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data) dwarf_diename(in_die)); return -ENOENT; } + if (addr == 0) { + pr_debug("%s has no valid entry address. skipped.\n", + dwarf_diename(in_die)); + return -ENOENT; + } pf->addr = addr; pf->addr += pp->offset; pr_debug("found inline addr: 0x%jx\n", @@ -950,7 +993,8 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - pr_debug("Matched function: %s\n", dwarf_diename(sp_die)); + pr_debug("Matched function: %s [%lx]\n", dwarf_diename(sp_die), + (unsigned long)dwarf_dieoffset(sp_die)); pf->fname = dwarf_decl_file(sp_die); if (pp->line) { /* Function relative line */ dwarf_decl_line(sp_die, &pf->lno); @@ -959,10 +1003,16 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) } else if (die_is_func_instance(sp_die)) { /* Instances always have the entry address */ dwarf_entrypc(sp_die, &pf->addr); + /* But in some case the entry address is 0 */ + if (pf->addr == 0) { + pr_debug("%s has no entry PC. Skipped\n", + dwarf_diename(sp_die)); + param->retval = 0; /* Real function */ - if (pp->lazy_line) + } else if (pp->lazy_line) param->retval = find_probe_point_lazy(sp_die, pf); else { + skip_prologue(sp_die, pf); pf->addr += pp->offset; /* TODO: Check the address in this function */ param->retval = call_probe_finder(sp_die, pf); @@ -972,7 +1022,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) param->retval = die_walk_instances(sp_die, probe_point_inline_cb, (void *)pf); /* This could be a non-existed inline definition */ - if (param->retval == -ENOENT && strisglob(pp->function)) + if (param->retval == -ENOENT) param->retval = 0; } @@ -1101,11 +1151,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg, struct probe_finder *pf) { int ret = 0; - -#if _ELFUTILS_PREREQ(0, 142) Elf *elf; GElf_Ehdr ehdr; - GElf_Shdr shdr; if (pf->cfi_eh || pf->cfi_dbg) return debuginfo__find_probe_location(dbg, pf); @@ -1118,11 +1165,18 @@ static int debuginfo__find_probes(struct debuginfo *dbg, 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_eh = dwarf_getcfi_elf(elf); + pf->machine = ehdr.e_machine; + +#if _ELFUTILS_PREREQ(0, 142) + do { + GElf_Shdr shdr; + + if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) && + shdr.sh_type == SHT_PROGBITS) + pf->cfi_eh = dwarf_getcfi_elf(elf); - pf->cfi_dbg = dwarf_getcfi(dbg->dbg); + pf->cfi_dbg = dwarf_getcfi(dbg->dbg); + } while (0); #endif ret = debuginfo__find_probe_location(dbg, pf); @@ -1150,7 +1204,7 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data) (tag == DW_TAG_variable && vf->vars)) { if (convert_variable_location(die_mem, vf->pf->addr, vf->pf->fb_ops, &pf->sp_die, - NULL) == 0) { + pf->machine, NULL) == 0) { vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem); if (vf->args[vf->nargs].var == NULL) { vf->ret = -ENOMEM; @@ -1313,7 +1367,7 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) tag == DW_TAG_variable) { ret = convert_variable_location(die_mem, af->pf.addr, af->pf.fb_ops, &af->pf.sp_die, - NULL); + af->pf.machine, NULL); if (ret == 0 || ret == -ERANGE) { int ret2; bool externs = !af->child; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 51137fccb9c8..f1d8558f498e 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -80,6 +80,7 @@ struct probe_finder { Dwarf_CFI *cfi_dbg; #endif Dwarf_Op *fb_ops; /* Frame base attribute */ + unsigned int machine; /* Target machine arch */ struct perf_probe_arg *pvar; /* Current target variable */ struct probe_trace_arg *tvar; /* Current result variable */ }; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index b7d4f4aeee61..0546a4304347 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -18,6 +18,7 @@ util/thread_map.c util/util.c util/xyarray.c util/cgroup.c +util/parse-branch-options.c util/rblist.c util/counts.c util/strlist.c diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index 639d1da2f978..293534c1a474 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -54,7 +54,7 @@ int sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen) break; ret = sq_quote_buf(dst, argv[i]); if (maxlen && dst->len > maxlen) - die("Too many or long arguments"); + return -ENOSPC; } return ret; } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 5d1eb1ccd96c..e55a132f69b7 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -25,6 +25,7 @@ #include <ctype.h> #include <errno.h> #include <linux/bitmap.h> +#include <linux/time64.h> #include "../util.h" #include <EXTERN.h> @@ -359,8 +360,8 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (!test_and_set_bit(event->id, events_defined)) define_event_symbols(event, handler, event->print_fmt.args); - s = nsecs / NSECS_PER_SEC; - ns = nsecs - s * NSECS_PER_SEC; + s = nsecs / NSEC_PER_SEC; + ns = nsecs - s * NSEC_PER_SEC; scripting_context->event_data = data; scripting_context->pevent = evsel->tp_format->pevent; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index e0203b979474..089438da1f7f 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -27,6 +27,7 @@ #include <stdbool.h> #include <errno.h> #include <linux/bitmap.h> +#include <linux/time64.h> #include "../../perf.h" #include "../debug.h" @@ -426,8 +427,8 @@ static void python_process_tracepoint(struct perf_sample *sample, if (!dict) Py_FatalError("couldn't create Python dict"); } - s = nsecs / NSECS_PER_SEC; - ns = nsecs - s * NSECS_PER_SEC; + s = nsecs / NSEC_PER_SEC; + ns = nsecs - s * NSEC_PER_SEC; scripting_context->event_data = data; scripting_context->pevent = evsel->tp_format->pevent; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5d61242a6e64..f268201048a0 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2025,20 +2025,10 @@ out_delete_map: void perf_session__fprintf_info(struct perf_session *session, FILE *fp, bool full) { - struct stat st; - int fd, ret; - if (session == NULL || fp == NULL) return; - fd = perf_data_file__fd(session->file); - - ret = fstat(fd, &st); - if (ret == -1) - return; - fprintf(fp, "# ========\n"); - fprintf(fp, "# captured on: %s", ctime(&st.st_ctime)); perf_header__fprintf_info(session, fp, full); fprintf(fp, "# ========\n#\n"); } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 3d3cb8392c86..df622f4e301e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -11,7 +11,7 @@ regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; -const char default_sort_order[] = "comm,dso,symbol"; +const char *default_sort_order = "comm,dso,symbol"; const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles"; const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; const char default_top_sort_order[] = "dso,symbol"; @@ -315,7 +315,7 @@ struct sort_entry sort_sym = { /* --sort srcline */ -static char *hist_entry__get_srcline(struct hist_entry *he) +char *hist_entry__get_srcline(struct hist_entry *he) { struct map *map = he->ms.map; @@ -867,7 +867,7 @@ struct sort_entry sort_cycles = { }; /* --sort daddr_sym */ -static int64_t +int64_t sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right) { uint64_t l = 0, r = 0; @@ -896,7 +896,7 @@ static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf, width); } -static int64_t +int64_t sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right) { uint64_t l = 0, r = 0; @@ -1062,7 +1062,7 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, out); } -static int64_t +int64_t sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) { u64 l, r; @@ -1492,7 +1492,8 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists) } static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct hists *hists) + struct hists *hists, int line __maybe_unused, + int *span __maybe_unused) { struct hpp_sort_entry *hse; size_t len = fmt->user_len; @@ -1797,7 +1798,9 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde, } static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct hists *hists __maybe_unused) + struct hists *hists __maybe_unused, + int line __maybe_unused, + int *span __maybe_unused) { struct hpp_dynamic_entry *hde; size_t len = fmt->user_len; @@ -2305,9 +2308,9 @@ int hpp_dimension__add_output(unsigned col) return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]); } -static int sort_dimension__add(struct perf_hpp_list *list, const char *tok, - struct perf_evlist *evlist, - int level) +int sort_dimension__add(struct perf_hpp_list *list, const char *tok, + struct perf_evlist *evlist, + int level) { unsigned int i; @@ -2682,7 +2685,7 @@ void sort__setup_elide(FILE *output) } } -static int output_field_add(struct perf_hpp_list *list, char *tok) +int output_field_add(struct perf_hpp_list *list, char *tok) { unsigned int i; @@ -2745,7 +2748,7 @@ static int setup_output_list(struct perf_hpp_list *list, char *str) return ret; } -static void reset_dimensions(void) +void reset_dimensions(void) { unsigned int i; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7ca37ea17395..7aff317fc7c4 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -28,7 +28,7 @@ extern const char *sort_order; extern const char *field_order; extern const char default_parent_pattern[]; extern const char *parent_pattern; -extern const char default_sort_order[]; +extern const char *default_sort_order; extern regex_t ignore_callees_regex; extern int have_ignore_callees; extern enum sort_mode sort__mode; @@ -40,6 +40,7 @@ extern struct sort_entry sort_dso_from; extern struct sort_entry sort_dso_to; extern struct sort_entry sort_sym_from; extern struct sort_entry sort_sym_to; +extern struct sort_entry sort_srcline; extern enum sort_type sort__first_dimension; extern const char default_mem_sort_order[]; @@ -268,4 +269,16 @@ int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, i bool is_strict_order(const char *order); int hpp_dimension__add_output(unsigned col); +void reset_dimensions(void); +int sort_dimension__add(struct perf_hpp_list *list, const char *tok, + struct perf_evlist *evlist, + int level); +int output_field_add(struct perf_hpp_list *list, char *tok); +int64_t +sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right); +int64_t +sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right); +int64_t +sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right); +char *hist_entry__get_srcline(struct hist_entry *he); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index b268a6648a5d..318424ea561d 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -66,9 +66,8 @@ static inline ssize_t strbuf_avail(const struct strbuf *sb) { int strbuf_grow(struct strbuf *buf, size_t); static inline int strbuf_setlen(struct strbuf *sb, size_t len) { - int ret; if (!sb->alloc) { - ret = strbuf_grow(sb, 0); + int ret = strbuf_grow(sb, 0); if (ret) return ret; } diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 7f7e072be746..d8dfaf64b32e 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -193,7 +193,8 @@ error: } /* Glob/lazy pattern matching */ -static bool __match_glob(const char *str, const char *pat, bool ignore_space) +static bool __match_glob(const char *str, const char *pat, bool ignore_space, + bool case_ins) { while (*str && *pat && *pat != '*') { if (ignore_space) { @@ -219,8 +220,13 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space) return false; else if (*pat == '\\') /* Escaped char match as normal char */ pat++; - if (*str++ != *pat++) + if (case_ins) { + if (tolower(*str) != tolower(*pat)) + return false; + } else if (*str != *pat) return false; + str++; + pat++; } /* Check wild card */ if (*pat == '*') { @@ -229,7 +235,7 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space) if (!*pat) /* Tail wild card matches all */ return true; while (*str) - if (__match_glob(str++, pat, ignore_space)) + if (__match_glob(str++, pat, ignore_space, case_ins)) return true; } return !*str && !*pat; @@ -249,7 +255,12 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space) */ bool strglobmatch(const char *str, const char *pat) { - return __match_glob(str, pat, false); + return __match_glob(str, pat, false, false); +} + +bool strglobmatch_nocase(const char *str, const char *pat) +{ + return __match_glob(str, pat, false, true); } /** @@ -262,7 +273,7 @@ bool strglobmatch(const char *str, const char *pat) */ bool strlazymatch(const char *str, const char *pat) { - return __match_glob(str, pat, true); + return __match_glob(str, pat, true, false); } /** diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index eec6c1149f44..1cbada2dc6be 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -18,6 +18,7 @@ #include <unistd.h> #include <string.h> #include <linux/bitmap.h> +#include <linux/time64.h> #include "perf.h" #include "svghelper.h" @@ -274,14 +275,14 @@ static char *time_to_string(u64 duration) text[0] = 0; - if (duration < 1000) /* less than 1 usec */ + if (duration < NSEC_PER_USEC) /* less than 1 usec */ return text; - if (duration < 1000 * 1000) { /* less than 1 msec */ - sprintf(text, "%.1f us", duration / 1000.0); + if (duration < NSEC_PER_MSEC) { /* less than 1 msec */ + sprintf(text, "%.1f us", duration / (double)NSEC_PER_USEC); return text; } - sprintf(text, "%.1f ms", duration / 1000.0 / 1000); + sprintf(text, "%.1f ms", duration / (double)NSEC_PER_MSEC); return text; } @@ -297,7 +298,7 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace) style = "waiting"; - if (end-start > 10 * 1000000) /* 10 msec */ + if (end-start > 10 * NSEC_PER_MSEC) /* 10 msec */ style = "WAITING"; text = time_to_string(end-start); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a811c13a74d6..99400b0e8f2a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -206,6 +206,37 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, return NULL; } +static bool want_demangle(bool is_kernel_sym) +{ + return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; +} + +static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) +{ + int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS; + char *demangled = NULL; + + /* + * We need to figure out if the object was created from C++ sources + * DWARF DW_compile_unit has this, but we don't always have access + * to it... + */ + if (!want_demangle(dso->kernel || kmodule)) + return demangled; + + demangled = bfd_demangle(NULL, elf_name, demangle_flags); + if (demangled == NULL) + demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET); + else if (rust_is_mangled(demangled)) + /* + * Input to Rust demangling is the BFD-demangled + * name which it Rust-demangles in place. + */ + rust_demangle_sym(demangled); + + return demangled; +} + #define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \ for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \ idx < nr_entries; \ @@ -223,8 +254,7 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, * And always look at the original dso, not at debuginfo packages, that * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). */ -int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map, - symbol_filter_t filter) +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map) { uint32_t nr_rel_entries, idx; GElf_Sym sym; @@ -301,45 +331,53 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_rel_entries) { + const char *elf_name = NULL; + char *demangled = NULL; symidx = GELF_R_SYM(pos->r_info); plt_offset += shdr_plt.sh_entsize; gelf_getsym(syms, symidx, &sym); + + elf_name = elf_sym__name(&sym, symstrs); + demangled = demangle_sym(dso, 0, elf_name); + if (demangled != NULL) + elf_name = demangled; snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_sym__name(&sym, symstrs)); + "%s@plt", elf_name); + free(demangled); f = symbol__new(plt_offset, shdr_plt.sh_entsize, STB_GLOBAL, sympltname); if (!f) goto out_elf_end; - if (filter && filter(map, f)) - symbol__delete(f); - else { - symbols__insert(&dso->symbols[map->type], f); - ++nr; - } + symbols__insert(&dso->symbols[map->type], f); + ++nr; } } else if (shdr_rel_plt.sh_type == SHT_REL) { GElf_Rel pos_mem, *pos; elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_rel_entries) { + const char *elf_name = NULL; + char *demangled = NULL; symidx = GELF_R_SYM(pos->r_info); plt_offset += shdr_plt.sh_entsize; gelf_getsym(syms, symidx, &sym); + + elf_name = elf_sym__name(&sym, symstrs); + demangled = demangle_sym(dso, 0, elf_name); + if (demangled != NULL) + elf_name = demangled; snprintf(sympltname, sizeof(sympltname), - "%s@plt", elf_sym__name(&sym, symstrs)); + "%s@plt", elf_name); + free(demangled); f = symbol__new(plt_offset, shdr_plt.sh_entsize, STB_GLOBAL, sympltname); if (!f) goto out_elf_end; - if (filter && filter(map, f)) - symbol__delete(f); - else { - symbols__insert(&dso->symbols[map->type], f); - ++nr; - } + symbols__insert(&dso->symbols[map->type], f); + ++nr; } } @@ -685,7 +723,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, } /* Always reject images with a mismatched build-id: */ - if (dso->has_build_id) { + if (dso->has_build_id && !symbol_conf.ignore_vmlinux_buildid) { u8 build_id[BUILD_ID_SIZE]; if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) { @@ -775,17 +813,11 @@ static u64 ref_reloc(struct kmap *kmap) return 0; } -static bool want_demangle(bool is_kernel_sym) -{ - return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; -} - void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } -int dso__load_sym(struct dso *dso, struct map *map, - struct symsrc *syms_ss, struct symsrc *runtime_ss, - symbol_filter_t filter, int kmodule) +int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, + struct symsrc *runtime_ss, int kmodule) { struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL; struct map_groups *kmaps = kmap ? map__kmaps(map) : NULL; @@ -1070,29 +1102,10 @@ int dso__load_sym(struct dso *dso, struct map *map, sym.st_value -= shdr.sh_addr - shdr.sh_offset; } new_symbol: - /* - * We need to figure out if the object was created from C++ sources - * DWARF DW_compile_unit has this, but we don't always have access - * to it... - */ - if (want_demangle(dso->kernel || kmodule)) { - int demangle_flags = DMGL_NO_OPTS; - if (verbose) - demangle_flags = DMGL_PARAMS | DMGL_ANSI; - - demangled = bfd_demangle(NULL, elf_name, demangle_flags); - if (demangled == NULL) - demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET); - else if (rust_is_mangled(demangled)) - /* - * Input to Rust demangling is the BFD-demangled - * name which it Rust-demangles in place. - */ - rust_demangle_sym(demangled); + demangled = demangle_sym(dso, kmodule, elf_name); + if (demangled != NULL) + elf_name = demangled; - if (demangled != NULL) - elf_name = demangled; - } f = symbol__new(sym.st_value, sym.st_size, GELF_ST_BIND(sym.st_info), elf_name); free(demangled); @@ -1101,21 +1114,16 @@ new_symbol: arch__sym_update(f, &sym); - if (filter && filter(curr_map, f)) - symbol__delete(f); - else { - symbols__insert(&curr_dso->symbols[curr_map->type], f); - nr++; - } + __symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel); + nr++; } /* * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - if (!symbol_conf.allow_aliases) - symbols__fixup_duplicate(&dso->symbols[map->type]); symbols__fixup_end(&dso->symbols[map->type]); + symbols__fixup_duplicate(&dso->symbols[map->type]); if (kmap) { /* * We need to fixup this here too because we create new diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 48906333a858..11cdde980545 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -287,8 +287,7 @@ void symsrc__destroy(struct symsrc *ss) int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, struct symsrc *ss __maybe_unused, - struct map *map __maybe_unused, - symbol_filter_t filter __maybe_unused) + struct map *map __maybe_unused) { return 0; } @@ -334,7 +333,6 @@ enum dso_type dso__type_fd(int fd) int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, struct symsrc *ss, struct symsrc *runtime_ss __maybe_unused, - symbol_filter_t filter __maybe_unused, int kmodule __maybe_unused) { unsigned char build_id[BUILD_ID_SIZE]; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 37e8d20ae03e..dc93940de351 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -9,6 +9,7 @@ #include <fcntl.h> #include <unistd.h> #include <inttypes.h> +#include "annotate.h" #include "build-id.h" #include "util.h" #include "debug.h" @@ -23,10 +24,10 @@ #include <symbol/kallsyms.h> #include <sys/utsname.h> -static int dso__load_kernel_sym(struct dso *dso, struct map *map, - symbol_filter_t filter); -static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, - symbol_filter_t filter); +static int dso__load_kernel_sym(struct dso *dso, struct map *map); +static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map); +static bool symbol__is_idle(const char *name); + int vmlinux_path__nr_entries; char **vmlinux_path; @@ -152,6 +153,9 @@ void symbols__fixup_duplicate(struct rb_root *symbols) struct rb_node *nd; struct symbol *curr, *next; + if (symbol_conf.allow_aliases) + return; + nd = rb_first(symbols); while (nd) { @@ -235,8 +239,13 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) if (sym == NULL) return NULL; - if (symbol_conf.priv_size) + if (symbol_conf.priv_size) { + if (symbol_conf.init_annotation) { + struct annotation *notes = (void *)sym; + pthread_mutex_init(¬es->lock, NULL); + } sym = ((void *)sym) + symbol_conf.priv_size; + } sym->start = start; sym->end = len ? start + len : start; @@ -268,13 +277,24 @@ void symbols__delete(struct rb_root *symbols) } } -void symbols__insert(struct rb_root *symbols, struct symbol *sym) +void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel) { struct rb_node **p = &symbols->rb_node; struct rb_node *parent = NULL; const u64 ip = sym->start; struct symbol *s; + if (kernel) { + const char *name = sym->name; + /* + * ppc64 uses function descriptors and appends a '.' to the + * start of every instruction address. Remove it. + */ + if (name[0] == '.') + name++; + sym->idle = symbol__is_idle(name); + } + while (*p != NULL) { parent = *p; s = rb_entry(parent, struct symbol, rb_node); @@ -287,6 +307,11 @@ void symbols__insert(struct rb_root *symbols, struct symbol *sym) rb_insert_color(&sym->rb_node, symbols); } +void symbols__insert(struct rb_root *symbols, struct symbol *sym) +{ + __symbols__insert(symbols, sym, false); +} + static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) { struct rb_node *n; @@ -320,6 +345,16 @@ static struct symbol *symbols__first(struct rb_root *symbols) return NULL; } +static struct symbol *symbols__last(struct rb_root *symbols) +{ + struct rb_node *n = rb_last(symbols); + + if (n) + return rb_entry(n, struct symbol, rb_node); + + return NULL; +} + static struct symbol *symbols__next(struct symbol *sym) { struct rb_node *n = rb_next(&sym->rb_node); @@ -415,7 +450,7 @@ void dso__reset_find_symbol_cache(struct dso *dso) void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym) { - symbols__insert(&dso->symbols[type], sym); + __symbols__insert(&dso->symbols[type], sym, dso->kernel); /* update the symbol cache if necessary */ if (dso->last_find_result[type].addr >= sym->start && @@ -441,6 +476,11 @@ struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) return symbols__first(&dso->symbols[type]); } +struct symbol *dso__last_symbol(struct dso *dso, enum map_type type) +{ + return symbols__last(&dso->symbols[type]); +} + struct symbol *dso__next_symbol(struct symbol *sym) { return symbols__next(sym); @@ -537,7 +577,7 @@ struct process_kallsyms_args { * These are symbols in the kernel image, so make sure that * sym is from a kernel DSO. */ -bool symbol__is_idle(struct symbol *sym) +static bool symbol__is_idle(const char *name) { const char * const idle_symbols[] = { "cpu_idle", @@ -554,14 +594,10 @@ bool symbol__is_idle(struct symbol *sym) "pseries_dedicated_idle_sleep", NULL }; - int i; - if (!sym) - return false; - for (i = 0; idle_symbols[i]; i++) { - if (!strcmp(idle_symbols[i], sym->name)) + if (!strcmp(idle_symbols[i], name)) return true; } @@ -590,7 +626,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * We will pass the symbols to the filter later, in * map__split_kallsyms, when we have split the maps per module */ - symbols__insert(root, sym); + __symbols__insert(root, sym, !strchr(name, '[')); return 0; } @@ -607,8 +643,7 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename, return kallsyms__parse(filename, &args, map__process_kallsym_symbol); } -static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, - symbol_filter_t filter) +static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) { struct map_groups *kmaps = map__kmaps(map); struct map *curr_map; @@ -637,7 +672,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, curr_map = map_groups__find(kmaps, map->type, pos->start); - if (!curr_map || (filter && filter(curr_map, pos))) { + if (!curr_map) { symbol__delete(pos); continue; } @@ -660,8 +695,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, * kernel range is broken in several maps, named [kernel].N, as we don't have * the original ELF section names vmlinux have. */ -static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, - symbol_filter_t filter) +static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) { struct map_groups *kmaps = map__kmaps(map); struct machine *machine; @@ -738,7 +772,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, if (count == 0) { curr_map = map; - goto filter_symbol; + goto add_symbol; } if (dso->kernel == DSO_TYPE_GUEST_KERNEL) @@ -770,18 +804,18 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, pos->start -= delta; pos->end -= delta; } -filter_symbol: - if (filter && filter(curr_map, pos)) { -discard_symbol: rb_erase(&pos->rb_node, root); - symbol__delete(pos); - } else { - if (curr_map != map) { - rb_erase(&pos->rb_node, root); - symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); - ++moved; - } else - ++count; - } +add_symbol: + if (curr_map != map) { + rb_erase(&pos->rb_node, root); + symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); + ++moved; + } else + ++count; + + continue; +discard_symbol: + rb_erase(&pos->rb_node, root); + symbol__delete(pos); } if (curr_map != map && @@ -1221,7 +1255,7 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) } int __dso__load_kallsyms(struct dso *dso, const char *filename, - struct map *map, bool no_kcore, symbol_filter_t filter) + struct map *map, bool no_kcore) { u64 delta = 0; @@ -1234,8 +1268,8 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(map, filename, &delta)) return -1; - symbols__fixup_duplicate(&dso->symbols[map->type]); symbols__fixup_end(&dso->symbols[map->type]); + symbols__fixup_duplicate(&dso->symbols[map->type]); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; @@ -1243,19 +1277,18 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; if (!no_kcore && !dso__load_kcore(dso, map, filename)) - return dso__split_kallsyms_for_kcore(dso, map, filter); + return dso__split_kallsyms_for_kcore(dso, map); else - return dso__split_kallsyms(dso, map, delta, filter); + return dso__split_kallsyms(dso, map, delta); } int dso__load_kallsyms(struct dso *dso, const char *filename, - struct map *map, symbol_filter_t filter) + struct map *map) { - return __dso__load_kallsyms(dso, filename, map, false, filter); + return __dso__load_kallsyms(dso, filename, map, false); } -static int dso__load_perf_map(struct dso *dso, struct map *map, - symbol_filter_t filter) +static int dso__load_perf_map(struct dso *dso, struct map *map) { char *line = NULL; size_t n; @@ -1297,12 +1330,8 @@ static int dso__load_perf_map(struct dso *dso, struct map *map, if (sym == NULL) goto out_delete_line; - if (filter && filter(map, sym)) - symbol__delete(sym); - else { - symbols__insert(&dso->symbols[map->type], sym); - nr_syms++; - } + symbols__insert(&dso->symbols[map->type], sym); + nr_syms++; } free(line); @@ -1358,7 +1387,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, } } -int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) +int dso__load(struct dso *dso, struct map *map) { char *name; int ret = -1; @@ -1381,9 +1410,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (dso->kernel) { if (dso->kernel == DSO_TYPE_KERNEL) - ret = dso__load_kernel_sym(dso, map, filter); + ret = dso__load_kernel_sym(dso, map); else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) - ret = dso__load_guest_kernel_sym(dso, map, filter); + ret = dso__load_guest_kernel_sym(dso, map); goto out; } @@ -1407,7 +1436,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) goto out; } - ret = dso__load_perf_map(dso, map, filter); + ret = dso__load_perf_map(dso, map); dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT : DSO_BINARY_TYPE__NOT_FOUND; goto out; @@ -1430,7 +1459,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (is_regular_file(dso->long_name) && + if (!dso->has_build_id && + is_regular_file(dso->long_name) && filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); @@ -1498,14 +1528,14 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) kmod = true; if (syms_ss) - ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod); + ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod); else ret = -1; if (ret > 0) { int nr_plt; - nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map, filter); + nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map); if (nr_plt > 0) ret += nr_plt; } @@ -1544,8 +1574,7 @@ out_unlock: } int dso__load_vmlinux(struct dso *dso, struct map *map, - const char *vmlinux, bool vmlinux_allocated, - symbol_filter_t filter) + const char *vmlinux, bool vmlinux_allocated) { int err = -1; struct symsrc ss; @@ -1565,7 +1594,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) return -1; - err = dso__load_sym(dso, map, &ss, &ss, filter, 0); + err = dso__load_sym(dso, map, &ss, &ss, 0); symsrc__destroy(&ss); if (err > 0) { @@ -1581,8 +1610,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, return err; } -int dso__load_vmlinux_path(struct dso *dso, struct map *map, - symbol_filter_t filter) +int dso__load_vmlinux_path(struct dso *dso, struct map *map) { int i, err = 0; char *filename = NULL; @@ -1591,7 +1619,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, vmlinux_path__nr_entries + 1); for (i = 0; i < vmlinux_path__nr_entries; ++i) { - err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter); + err = dso__load_vmlinux(dso, map, vmlinux_path[i], false); if (err > 0) goto out; } @@ -1599,7 +1627,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, if (!symbol_conf.ignore_vmlinux_buildid) filename = dso__build_id_filename(dso, NULL, 0); if (filename != NULL) { - err = dso__load_vmlinux(dso, map, filename, true, filter); + err = dso__load_vmlinux(dso, map, filename, true); if (err > 0) goto out; free(filename); @@ -1713,8 +1741,7 @@ proc_kallsyms: return strdup(path); } -static int dso__load_kernel_sym(struct dso *dso, struct map *map, - symbol_filter_t filter) +static int dso__load_kernel_sym(struct dso *dso, struct map *map) { int err; const char *kallsyms_filename = NULL; @@ -1740,12 +1767,11 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map, } if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) { - return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, - false, filter); + return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, false); } if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) { - err = dso__load_vmlinux_path(dso, map, filter); + err = dso__load_vmlinux_path(dso, map); if (err > 0) return err; } @@ -1761,7 +1787,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map, kallsyms_filename = kallsyms_allocated_filename; do_kallsyms: - err = dso__load_kallsyms(dso, kallsyms_filename, map, filter); + err = dso__load_kallsyms(dso, kallsyms_filename, map); if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); free(kallsyms_allocated_filename); @@ -1776,8 +1802,7 @@ do_kallsyms: return err; } -static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, - symbol_filter_t filter) +static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map) { int err; const char *kallsyms_filename = NULL; @@ -1799,7 +1824,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, if (symbol_conf.default_guest_vmlinux_name != NULL) { err = dso__load_vmlinux(dso, map, symbol_conf.default_guest_vmlinux_name, - false, filter); + false); return err; } @@ -1811,7 +1836,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, kallsyms_filename = path; } - err = dso__load_kallsyms(dso, kallsyms_filename, map, filter); + err = dso__load_kallsyms(dso, kallsyms_filename, map); if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); if (err > 0 && !dso__is_kcore(dso)) { @@ -1938,7 +1963,7 @@ static bool symbol__read_kptr_restrict(void) char line[8]; if (fgets(line, sizeof(line), fp) != NULL) - value = (geteuid() != 0) ? + value = ((geteuid() != 0) || (getuid() != 0)) ? (atoi(line) != 0) : (atoi(line) == 2); @@ -1948,6 +1973,23 @@ static bool symbol__read_kptr_restrict(void) return value; } +int symbol__annotation_init(void) +{ + if (symbol_conf.initialized) { + pr_err("Annotation needs to be init before symbol__init()\n"); + return -1; + } + + if (symbol_conf.init_annotation) { + pr_warning("Annotation being initialized multiple times\n"); + return 0; + } + + symbol_conf.priv_size += sizeof(struct annotation); + symbol_conf.init_annotation = true; + return 0; +} + int symbol__init(struct perf_env *env) { const char *symfs; @@ -1991,6 +2033,10 @@ int symbol__init(struct perf_env *env) symbol_conf.sym_list_str, "symbol") < 0) goto out_free_tid_list; + if (setup_list(&symbol_conf.bt_stop_list, + symbol_conf.bt_stop_list_str, "symbol") < 0) + goto out_free_sym_list; + /* * A path to symbols of "/" is identical to "" * reset here for simplicity. @@ -2008,6 +2054,8 @@ int symbol__init(struct perf_env *env) symbol_conf.initialized = true; return 0; +out_free_sym_list: + strlist__delete(symbol_conf.sym_list); out_free_tid_list: intlist__delete(symbol_conf.tid_list); out_free_pid_list: @@ -2023,6 +2071,7 @@ void symbol__exit(void) { if (!symbol_conf.initialized) return; + strlist__delete(symbol_conf.bt_stop_list); strlist__delete(symbol_conf.sym_list); strlist__delete(symbol_conf.dso_list); strlist__delete(symbol_conf.comm_list); @@ -2030,6 +2079,7 @@ void symbol__exit(void) intlist__delete(symbol_conf.pid_list); vmlinux_path__exit(); symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; + symbol_conf.bt_stop_list = NULL; symbol_conf.initialized = false; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 699f7cbcfe72..6c358b7ed336 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -57,7 +57,8 @@ struct symbol { u64 end; u16 namelen; u8 binding; - bool ignore; + u8 idle:1; + u8 ignore:1; u8 arch_sym; char name[0]; }; @@ -88,6 +89,7 @@ struct symbol_conf { unsigned short priv_size; unsigned short nr_events; bool try_vmlinux_path, + init_annotation, force, ignore_vmlinux, ignore_vmlinux_buildid, @@ -99,6 +101,7 @@ struct symbol_conf { show_total_period, use_callchain, cumulate_callchain, + show_branchflag_count, exclude_other, show_cpu_utilization, initialized, @@ -129,14 +132,16 @@ struct symbol_conf { *pid_list_str, *tid_list_str, *sym_list_str, - *col_width_list_str; + *col_width_list_str, + *bt_stop_list_str; struct strlist *dso_list, *comm_list, *sym_list, *dso_from_list, *dso_to_list, *sym_from_list, - *sym_to_list; + *sym_to_list, + *bt_stop_list; struct intlist *pid_list, *tid_list; const char *symfs; @@ -240,16 +245,13 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, bool symsrc__has_symtab(struct symsrc *ss); bool symsrc__possibly_runtime(struct symsrc *ss); -int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter); +int dso__load(struct dso *dso, struct map *map); int dso__load_vmlinux(struct dso *dso, struct map *map, - const char *vmlinux, bool vmlinux_allocated, - symbol_filter_t filter); -int dso__load_vmlinux_path(struct dso *dso, struct map *map, - symbol_filter_t filter); + const char *vmlinux, bool vmlinux_allocated); +int dso__load_vmlinux_path(struct dso *dso, struct map *map); int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, - bool no_kcore, symbol_filter_t filter); -int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, - symbol_filter_t filter); + bool no_kcore); +int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map); void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym); @@ -261,6 +263,7 @@ struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, struct symbol *symbol__next_by_name(struct symbol *sym); struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); +struct symbol *dso__last_symbol(struct dso *dso, enum map_type type); struct symbol *dso__next_symbol(struct symbol *sym); enum dso_type dso__type_fd(int fd); @@ -277,10 +280,13 @@ struct perf_env; int symbol__init(struct perf_env *env); void symbol__exit(void); void symbol__elf_init(void); +int symbol__annotation_init(void); + struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); size_t __symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, - bool unknown_as_addr, FILE *fp); + bool unknown_as_addr, + bool print_offsets, FILE *fp); size_t symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, FILE *fp); size_t __symbol__fprintf_symname(const struct symbol *sym, @@ -291,16 +297,15 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); bool symbol__restricted_filename(const char *filename, const char *restricted_filename); -bool symbol__is_idle(struct symbol *sym); int symbol__config_symfs(const struct option *opt __maybe_unused, const char *dir, int unset __maybe_unused); int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, - struct symsrc *runtime_ss, symbol_filter_t filter, - int kmodule); + struct symsrc *runtime_ss, int kmodule); int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, - struct map *map, symbol_filter_t filter); + struct map *map); +void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root *symbols); void symbols__fixup_end(struct rb_root *symbols); diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index a680bdaa65dc..7c6b33e8e2d2 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -15,14 +15,15 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp) size_t __symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, - bool unknown_as_addr, FILE *fp) + bool unknown_as_addr, + bool print_offsets, FILE *fp) { unsigned long offset; size_t length; if (sym && sym->name) { length = fprintf(fp, "%s", sym->name); - if (al) { + if (al && print_offsets) { if (al->addr < sym->end) offset = al->addr - sym->start; else @@ -40,19 +41,19 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, FILE *fp) { - return __symbol__fprintf_symname_offs(sym, al, false, fp); + return __symbol__fprintf_symname_offs(sym, al, false, true, fp); } size_t __symbol__fprintf_symname(const struct symbol *sym, const struct addr_location *al, bool unknown_as_addr, FILE *fp) { - return __symbol__fprintf_symname_offs(sym, al, unknown_as_addr, fp); + return __symbol__fprintf_symname_offs(sym, al, unknown_as_addr, false, fp); } size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) { - return __symbol__fprintf_symname_offs(sym, NULL, false, fp); + return __symbol__fprintf_symname_offs(sym, NULL, false, false, fp); } size_t dso__fprintf_symbols_by_name(struct dso *dso, diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 8b10a55410a2..f5af87f66663 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -14,13 +14,12 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine) { - struct thread *leader; pid_t pid = thread->pid_; if (pid == thread->tid || pid == -1) { thread->mg = map_groups__new(machine); } else { - leader = __machine__findnew_thread(machine, pid, pid); + struct thread *leader = __machine__findnew_thread(machine, pid, pid); if (leader) { thread->mg = map_groups__get(leader->mg); thread__put(leader); @@ -130,11 +129,10 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, bool exec) { struct comm *new, *curr = thread__comm(thread); - int err; /* Override the default :tid entry */ if (!thread->comm_set) { - err = comm__override(curr, str, timestamp, exec); + int err = comm__override(curr, str, timestamp, exec); if (err) return err; } else { @@ -270,10 +268,9 @@ static int thread__clone_map_groups(struct thread *thread, int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) { - int err; - if (parent->comm_set) { const char *comm = thread__comm_str(parent); + int err; if (!comm) return -ENOMEM; err = thread__set_comm(thread, comm, timestamp); diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 40585f5b7027..f9eab200fd75 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -448,3 +448,25 @@ bool thread_map__has(struct thread_map *threads, pid_t pid) return false; } + +int thread_map__remove(struct thread_map *threads, int idx) +{ + int i; + + if (threads->nr < 1) + return -EINVAL; + + if (idx >= threads->nr) + return -EINVAL; + + /* + * Free the 'idx' item and shift the rest up. + */ + free(threads->map[idx].comm); + + for (i = idx; i < threads->nr - 1; i++) + threads->map[i] = threads->map[i + 1]; + + threads->nr--; + return 0; +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index bd3b971588da..ea0ef08c6303 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -58,4 +58,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread) void thread_map__read_comms(struct thread_map *threads); bool thread_map__has(struct thread_map *threads, pid_t pid); +int thread_map__remove(struct thread_map *threads, int idx); #endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c new file mode 100644 index 000000000000..d1b21c72206d --- /dev/null +++ b/tools/perf/util/time-utils.c @@ -0,0 +1,119 @@ +#include <stdlib.h> +#include <string.h> +#include <sys/time.h> +#include <linux/time64.h> +#include <time.h> +#include <errno.h> +#include <inttypes.h> + +#include "perf.h" +#include "debug.h" +#include "time-utils.h" + +int parse_nsec_time(const char *str, u64 *ptime) +{ + u64 time_sec, time_nsec; + char *end; + + time_sec = strtoul(str, &end, 10); + if (*end != '.' && *end != '\0') + return -1; + + if (*end == '.') { + int i; + char nsec_buf[10]; + + if (strlen(++end) > 9) + return -1; + + strncpy(nsec_buf, end, 9); + nsec_buf[9] = '\0'; + + /* make it nsec precision */ + for (i = strlen(nsec_buf); i < 9; i++) + nsec_buf[i] = '0'; + + time_nsec = strtoul(nsec_buf, &end, 10); + if (*end != '\0') + return -1; + } else + time_nsec = 0; + + *ptime = time_sec * NSEC_PER_SEC + time_nsec; + return 0; +} + +static int parse_timestr_sec_nsec(struct perf_time_interval *ptime, + char *start_str, char *end_str) +{ + if (start_str && (*start_str != '\0') && + (parse_nsec_time(start_str, &ptime->start) != 0)) { + return -1; + } + + if (end_str && (*end_str != '\0') && + (parse_nsec_time(end_str, &ptime->end) != 0)) { + return -1; + } + + return 0; +} + +int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr) +{ + char *start_str, *end_str; + char *d, *str; + int rc = 0; + + if (ostr == NULL || *ostr == '\0') + return 0; + + /* copy original string because we need to modify it */ + str = strdup(ostr); + if (str == NULL) + return -ENOMEM; + + ptime->start = 0; + ptime->end = 0; + + /* str has the format: <start>,<stop> + * variations: <start>, + * ,<stop> + * , + */ + start_str = str; + d = strchr(start_str, ','); + if (d) { + *d = '\0'; + ++d; + } + end_str = d; + + rc = parse_timestr_sec_nsec(ptime, start_str, end_str); + + free(str); + + /* make sure end time is after start time if it was given */ + if (rc == 0 && ptime->end && ptime->end < ptime->start) + return -EINVAL; + + pr_debug("start time %" PRIu64 ", ", ptime->start); + pr_debug("end time %" PRIu64 "\n", ptime->end); + + return rc; +} + +bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp) +{ + /* if time is not set don't drop sample */ + if (timestamp == 0) + return false; + + /* otherwise compare sample time to time window */ + if ((ptime->start && timestamp < ptime->start) || + (ptime->end && timestamp > ptime->end)) { + return true; + } + + return false; +} diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h new file mode 100644 index 000000000000..c1f197c4af6c --- /dev/null +++ b/tools/perf/util/time-utils.h @@ -0,0 +1,14 @@ +#ifndef _TIME_UTILS_H_ +#define _TIME_UTILS_H_ + +struct perf_time_interval { + u64 start, end; +}; + +int parse_nsec_time(const char *str, u64 *ptime); + +int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr); + +bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp); + +#endif diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 9df61059a85d..0ac9077f62a2 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -25,6 +25,7 @@ #include <errno.h> #include "../perf.h" +#include "debug.h" #include "util.h" #include "trace-event.h" @@ -86,16 +87,15 @@ struct scripting_ops python_scripting_unsupported_ops = { static void register_python_scripting(struct scripting_ops *scripting_ops) { - int err; - err = script_spec_register("Python", scripting_ops); - if (err) - die("error registering Python script extension"); - - err = script_spec_register("py", scripting_ops); - if (err) - die("error registering py script extension"); - - scripting_context = malloc(sizeof(struct scripting_context)); + if (scripting_context == NULL) + scripting_context = malloc(sizeof(*scripting_context)); + + if (scripting_context == NULL || + script_spec_register("Python", scripting_ops) || + script_spec_register("py", scripting_ops)) { + pr_err("Error registering Python script extension: disabling it\n"); + zfree(&scripting_context); + } } #ifdef NO_LIBPYTHON @@ -150,16 +150,15 @@ struct scripting_ops perl_scripting_unsupported_ops = { static void register_perl_scripting(struct scripting_ops *scripting_ops) { - int err; - err = script_spec_register("Perl", scripting_ops); - if (err) - die("error registering Perl script extension"); - - err = script_spec_register("pl", scripting_ops); - if (err) - die("error registering pl script extension"); - - scripting_context = malloc(sizeof(struct scripting_context)); + if (scripting_context == NULL) + scripting_context = malloc(sizeof(*scripting_context)); + + if (scripting_context == NULL || + script_spec_register("Perl", scripting_ops) || + script_spec_register("pl", scripting_ops)) { + pr_err("Error registering Perl script extension: disabling it\n"); + zfree(&scripting_context); + } } #ifdef NO_LIBPERL diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 20c2e5743903..6fec84dff3f7 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -357,8 +357,8 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, 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.segbase = map->start + segbase - map->pgoff; + di.u.rti.table_data = map->start + table_data - map->pgoff; di.u.rti.table_len = fde_count * sizeof(struct table_entry) / sizeof(unw_word_t); ret = dwarf_search_unwind_table(as, ip, &di, pi, diff --git a/tools/perf/util/util-cxx.h b/tools/perf/util/util-cxx.h new file mode 100644 index 000000000000..0e0e019c9f34 --- /dev/null +++ b/tools/perf/util/util-cxx.h @@ -0,0 +1,26 @@ +/* + * Support C++ source use utilities defined in util.h + */ + +#ifndef PERF_UTIL_UTIL_CXX_H +#define PERF_UTIL_UTIL_CXX_H + +#ifdef __cplusplus +extern "C" { +#endif + +/* + * Now 'new' is the only C++ keyword found in util.h: + * in tools/include/linux/rbtree.h + * + * Other keywords, like class and delete, should be + * redefined if necessary. + */ +#define new _new +#include "util.h" +#undef new + +#ifdef __cplusplus +} +#endif +#endif diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index cee559d8c9e8..9ddd98827d12 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -15,6 +15,7 @@ #include <byteswap.h> #include <linux/kernel.h> #include <linux/log2.h> +#include <linux/time64.h> #include <unistd.h> #include "callchain.h" #include "strlist.h" @@ -399,37 +400,12 @@ void sighandler_dump_stack(int sig) raise(sig); } -int parse_nsec_time(const char *str, u64 *ptime) +int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) { - u64 time_sec, time_nsec; - char *end; + u64 sec = timestamp / NSEC_PER_SEC; + u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC; - time_sec = strtoul(str, &end, 10); - if (*end != '.' && *end != '\0') - return -1; - - if (*end == '.') { - int i; - char nsec_buf[10]; - - if (strlen(++end) > 9) - return -1; - - strncpy(nsec_buf, end, 9); - nsec_buf[9] = '\0'; - - /* make it nsec precision */ - for (i = strlen(nsec_buf); i < 9; i++) - nsec_buf[i] = '0'; - - time_nsec = strtoul(nsec_buf, &end, 10); - if (*end != '\0') - return -1; - } else - time_nsec = 0; - - *ptime = time_sec * NSEC_PER_SEC + time_nsec; - return 0; + return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec); } unsigned long parse_tag_value(const char *str, struct parse_tag *tags) @@ -628,12 +604,63 @@ bool find_process(const char *name) return ret ? false : true; } +static int +fetch_ubuntu_kernel_version(unsigned int *puint) +{ + ssize_t len; + size_t line_len = 0; + char *ptr, *line = NULL; + int version, patchlevel, sublevel, err; + FILE *vsig = fopen("/proc/version_signature", "r"); + + if (!vsig) { + pr_debug("Open /proc/version_signature failed: %s\n", + strerror(errno)); + return -1; + } + + len = getline(&line, &line_len, vsig); + fclose(vsig); + err = -1; + if (len <= 0) { + pr_debug("Reading from /proc/version_signature failed: %s\n", + strerror(errno)); + goto errout; + } + + ptr = strrchr(line, ' '); + if (!ptr) { + pr_debug("Parsing /proc/version_signature failed: %s\n", line); + goto errout; + } + + err = sscanf(ptr + 1, "%d.%d.%d", + &version, &patchlevel, &sublevel); + if (err != 3) { + pr_debug("Unable to get kernel version from /proc/version_signature '%s'\n", + line); + goto errout; + } + + if (puint) + *puint = (version << 16) + (patchlevel << 8) + sublevel; + err = 0; +errout: + free(line); + return err; +} + int fetch_kernel_version(unsigned int *puint, char *str, size_t str_size) { struct utsname utsname; int version, patchlevel, sublevel, err; + bool int_ver_ready = false; + + if (access("/proc/version_signature", R_OK) == 0) + if (!fetch_ubuntu_kernel_version(puint)) + int_ver_ready = true; if (uname(&utsname)) return -1; @@ -647,12 +674,12 @@ fetch_kernel_version(unsigned int *puint, char *str, &version, &patchlevel, &sublevel); if (err != 3) { - pr_debug("Unablt to get kernel version from uname '%s'\n", + pr_debug("Unable to get kernel version from uname '%s'\n", utsname.release); return -1; } - if (puint) + if (puint && !int_ver_ready) *puint = (version << 16) + (patchlevel << 8) + sublevel; return 0; } diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index e5f55477491d..1d639e38aa82 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -179,12 +179,6 @@ static inline void *zalloc(size_t size) #undef tolower #undef toupper -#ifndef NSEC_PER_MSEC -#define NSEC_PER_MSEC 1000000L -#endif - -int parse_nsec_time(const char *str, u64 *ptime); - extern unsigned char sane_ctype[256]; #define GIT_SPACE 0x01 #define GIT_DIGIT 0x02 @@ -226,6 +220,7 @@ s64 perf_atoll(const char *str); char **argv_split(const char *str, int *argcp); void argv_free(char **argv); bool strglobmatch(const char *str, const char *pat); +bool strglobmatch_nocase(const char *str, const char *pat); bool strlazymatch(const char *str, const char *pat); static inline bool strisglob(const char *str) { @@ -365,4 +360,7 @@ extern int sched_getcpu(void); #endif int is_printable_array(char *p, unsigned int len); + +int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); + #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 0fb3c1fcd3e6..5074be4ed467 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -2,15 +2,18 @@ #include "util.h" #include "values.h" +#include "debug.h" -void perf_read_values_init(struct perf_read_values *values) +int perf_read_values_init(struct perf_read_values *values) { values->threads_max = 16; values->pid = malloc(values->threads_max * sizeof(*values->pid)); values->tid = malloc(values->threads_max * sizeof(*values->tid)); values->value = malloc(values->threads_max * sizeof(*values->value)); - if (!values->pid || !values->tid || !values->value) - die("failed to allocate read_values threads arrays"); + if (!values->pid || !values->tid || !values->value) { + pr_debug("failed to allocate read_values threads arrays"); + goto out_free_pid; + } values->threads = 0; values->counters_max = 16; @@ -18,9 +21,22 @@ void perf_read_values_init(struct perf_read_values *values) * sizeof(*values->counterrawid)); values->countername = malloc(values->counters_max * sizeof(*values->countername)); - if (!values->counterrawid || !values->countername) - die("failed to allocate read_values counters arrays"); + if (!values->counterrawid || !values->countername) { + pr_debug("failed to allocate read_values counters arrays"); + goto out_free_counter; + } values->counters = 0; + + return 0; + +out_free_counter: + zfree(&values->counterrawid); + zfree(&values->countername); +out_free_pid: + zfree(&values->pid); + zfree(&values->tid); + zfree(&values->value); + return -ENOMEM; } void perf_read_values_destroy(struct perf_read_values *values) @@ -41,17 +57,27 @@ void perf_read_values_destroy(struct perf_read_values *values) zfree(&values->countername); } -static void perf_read_values__enlarge_threads(struct perf_read_values *values) +static int perf_read_values__enlarge_threads(struct perf_read_values *values) { - values->threads_max *= 2; - values->pid = realloc(values->pid, - values->threads_max * sizeof(*values->pid)); - values->tid = realloc(values->tid, - values->threads_max * sizeof(*values->tid)); - values->value = realloc(values->value, - values->threads_max * sizeof(*values->value)); - if (!values->pid || !values->tid || !values->value) - die("failed to enlarge read_values threads arrays"); + int nthreads_max = values->threads_max * 2; + void *npid = realloc(values->pid, nthreads_max * sizeof(*values->pid)), + *ntid = realloc(values->tid, nthreads_max * sizeof(*values->tid)), + *nvalue = realloc(values->value, nthreads_max * sizeof(*values->value)); + + if (!npid || !ntid || !nvalue) + goto out_err; + + values->threads_max = nthreads_max; + values->pid = npid; + values->tid = ntid; + values->value = nvalue; + return 0; +out_err: + free(npid); + free(ntid); + free(nvalue); + pr_debug("failed to enlarge read_values threads arrays"); + return -ENOMEM; } static int perf_read_values__findnew_thread(struct perf_read_values *values, @@ -63,15 +89,21 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, if (values->pid[i] == pid && values->tid[i] == tid) return i; - if (values->threads == values->threads_max) - perf_read_values__enlarge_threads(values); + if (values->threads == values->threads_max) { + i = perf_read_values__enlarge_threads(values); + if (i < 0) + return i; + } - i = values->threads++; + i = values->threads + 1; + values->value[i] = malloc(values->counters_max * sizeof(**values->value)); + if (!values->value[i]) { + pr_debug("failed to allocate read_values counters array"); + return -ENOMEM; + } values->pid[i] = pid; values->tid[i] = tid; - values->value[i] = malloc(values->counters_max * sizeof(**values->value)); - if (!values->value[i]) - die("failed to allocate read_values counters array"); + values->threads = i; return i; } @@ -115,16 +147,21 @@ static int perf_read_values__findnew_counter(struct perf_read_values *values, return i; } -void perf_read_values_add_value(struct perf_read_values *values, +int perf_read_values_add_value(struct perf_read_values *values, u32 pid, u32 tid, u64 rawid, const char *name, u64 value) { int tindex, cindex; tindex = perf_read_values__findnew_thread(values, pid, tid); + if (tindex < 0) + return tindex; cindex = perf_read_values__findnew_counter(values, rawid, name); + if (cindex < 0) + return cindex; values->value[tindex][cindex] = value; + return 0; } static void perf_read_values__display_pretty(FILE *fp, diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h index b21a80c6cf8d..808ff9c73bf5 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -14,10 +14,10 @@ struct perf_read_values { u64 **value; }; -void perf_read_values_init(struct perf_read_values *values); +int perf_read_values_init(struct perf_read_values *values); void perf_read_values_destroy(struct perf_read_values *values); -void perf_read_values_add_value(struct perf_read_values *values, +int perf_read_values_add_value(struct perf_read_values *values, u32 pid, u32 tid, u64 rawid, const char *name, u64 value); |
