diff options
Diffstat (limited to 'tools/perf/util')
319 files changed, 28958 insertions, 10372 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 5ec97e8d6b6d..70cc91d00804 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,19 +1,22 @@ include $(srctree)/tools/scripts/Makefile.include include $(srctree)/tools/scripts/utilities.mak +perf-util-y += annotate-arch/ perf-util-y += arm64-frame-pointer-unwind-support.o +perf-util-y += addr2line.o perf-util-y += addr_location.o perf-util-y += annotate.o +perf-util-y += blake2s.o perf-util-y += block-info.o perf-util-y += block-range.o perf-util-y += build-id.o perf-util-y += cacheline.o +perf-util-$(CONFIG_LIBCAPSTONE) += capstone.o perf-util-y += config.o perf-util-y += copyfile.o perf-util-y += ctype.o perf-util-y += db-export.o perf-util-y += disasm.o -perf-util-y += disasm_bpf.o perf-util-y += env.o perf-util-y += event.o perf-util-y += evlist.o @@ -23,8 +26,9 @@ perf-util-y += evsel_fprintf.o perf-util-y += perf_event_attr_fprintf.o perf-util-y += evswitch.o perf-util-y += find_bit.o -perf-util-y += get_current_dir_name.o perf-util-y += levenshtein.o +perf-util-$(CONFIG_LIBBFD) += libbfd.o +perf-util-y += llvm.o perf-util-y += mmap.o perf-util-y += memswap.o perf-util-y += parse-events.o @@ -67,6 +71,7 @@ perf-util-y += maps.o perf-util-y += pstack.o perf-util-y += session.o perf-util-y += tool.o +perf-util-y += sample.o perf-util-y += sample-raw.o perf-util-y += s390-sample-raw.o perf-util-y += amd-sample-raw.o @@ -83,8 +88,10 @@ perf-util-y += pmu.o perf-util-y += pmus.o perf-util-y += pmu-flex.o perf-util-y += pmu-bison.o +perf-util-y += drm_pmu.o perf-util-y += hwmon_pmu.o perf-util-y += tool_pmu.o +perf-util-y += tp_pmu.o perf-util-y += svghelper.o perf-util-y += trace-event-info.o perf-util-y += trace-event-scripting.o @@ -121,26 +128,27 @@ perf-util-y += spark.o perf-util-y += topdown.o perf-util-y += iostat.o perf-util-y += stream.o -perf-util-y += kvm-stat.o +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o +perf-util-y += kvm-stat-arch/ perf-util-y += lock-contention.o -perf-util-$(CONFIG_AUXTRACE) += auxtrace.o +perf-util-y += auxtrace.o perf-util-y += intel-pt-decoder/ -perf-util-$(CONFIG_AUXTRACE) += intel-pt.o -perf-util-$(CONFIG_AUXTRACE) += intel-bts.o -perf-util-$(CONFIG_AUXTRACE) += arm-spe.o -perf-util-$(CONFIG_AUXTRACE) += arm-spe-decoder/ -perf-util-$(CONFIG_AUXTRACE) += hisi-ptt.o -perf-util-$(CONFIG_AUXTRACE) += hisi-ptt-decoder/ -perf-util-$(CONFIG_AUXTRACE) += s390-cpumsf.o +perf-util-y += intel-pt.o +perf-util-y += intel-bts.o +perf-util-y += arm-spe.o +perf-util-y += arm-spe-decoder/ +perf-util-y += hisi-ptt.o +perf-util-y += hisi-ptt-decoder/ +perf-util-y += s390-cpumsf.o +perf-util-y += powerpc-vpadtl.o ifdef CONFIG_LIBOPENCSD -perf-util-$(CONFIG_AUXTRACE) += cs-etm.o -perf-util-$(CONFIG_AUXTRACE) += cs-etm-decoder/ +perf-util-y += cs-etm.o +perf-util-y += cs-etm-decoder/ endif -perf-util-$(CONFIG_AUXTRACE) += cs-etm-base.o +perf-util-y += cs-etm-base.o perf-util-y += parse-branch-options.o -perf-util-y += dump-insn.o perf-util-y += parse-regs-options.o perf-util-y += parse-sublevel-options.o perf-util-y += term.o @@ -160,9 +168,8 @@ perf-util-y += clockid.o perf-util-y += list_sort.o perf-util-y += mutex.o perf-util-y += sharded_mutex.o -perf-util-$(CONFIG_X86_64) += intel-tpebs.o +perf-util-y += intel-tpebs.o -perf-util-$(CONFIG_LIBBPF) += bpf_map.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o @@ -172,6 +179,11 @@ perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o perf-util-$(CONFIG_PERF_BPF_SKEL) += btf.o +ifeq ($(CONFIG_TRACE),y) + perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-trace-summary.o + perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_trace_augment.o +endif + ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o endif @@ -207,13 +219,12 @@ endif perf-util-$(CONFIG_LIBDW) += probe-finder.o perf-util-$(CONFIG_LIBDW) += dwarf-aux.o perf-util-$(CONFIG_LIBDW) += dwarf-regs.o -perf-util-$(CONFIG_LIBDW) += dwarf-regs-csky.o -perf-util-$(CONFIG_LIBDW) += dwarf-regs-powerpc.o -perf-util-$(CONFIG_LIBDW) += dwarf-regs-x86.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-arch/ perf-util-$(CONFIG_LIBDW) += debuginfo.o perf-util-$(CONFIG_LIBDW) += annotate-data.o +perf-util-$(CONFIG_LIBDW) += libdw.o +perf-util-$(CONFIG_LIBDW) += unwind-libdw.o -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind-local.o perf-util-$(CONFIG_LIBUNWIND) += unwind-libunwind.o perf-util-$(CONFIG_LIBUNWIND_X86) += libunwind/x86_32.o @@ -236,9 +247,12 @@ perf-util-y += cap.o perf-util-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o perf-util-y += demangle-ocaml.o perf-util-y += demangle-java.o -perf-util-y += demangle-rust.o +perf-util-y += demangle-rust-v0.o perf-util-$(CONFIG_LIBLLVM) += llvm-c-helpers.o +CFLAGS_demangle-rust-v0.o += -Wno-shadow -Wno-declaration-after-statement \ + -Wno-switch-default -Wno-switch-enum -Wno-missing-field-initializers + ifdef CONFIG_JITDUMP perf-util-$(CONFIG_LIBELF) += jitdump.o perf-util-$(CONFIG_LIBELF) += genelf.o @@ -403,16 +417,27 @@ $(OUTPUT)util/list_sort.o: ../lib/list_sort.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -ifdef SHELLCHECK - SHELL_TESTS := generate-cmdlist.sh - TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) +PY_TESTS := setup.py +ifdef MYPY + MYPY_TEST_LOGS := $(PY_TESTS:%=%.mypy_log) +else + MYPY_TEST_LOGS := +endif + +$(OUTPUT)%.mypy_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false) + +perf-util-y += $(MYPY_TEST_LOGS) + +ifdef PYLINT + PYLINT_TEST_LOGS := $(PY_TESTS:%=%.pylint_log) else - SHELL_TESTS := - TEST_LOGS := + PYLINT_TEST_LOGS := endif -$(OUTPUT)%.shellcheck_log: % +$(OUTPUT)%.pylint_log: % $(call rule_mkdir) - $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) + $(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false) -perf-util-y += $(TEST_LOGS) +perf-util-y += $(PYLINT_TEST_LOGS) diff --git a/tools/perf/util/addr2line.c b/tools/perf/util/addr2line.c new file mode 100644 index 000000000000..4b0d349ed334 --- /dev/null +++ b/tools/perf/util/addr2line.c @@ -0,0 +1,436 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "addr2line.h" +#include "debug.h" +#include "dso.h" +#include "string2.h" +#include "srcline.h" +#include "symbol.h" +#include "symbol_conf.h" + +#include <api/io.h> +#include <linux/zalloc.h> +#include <subcmd/run-command.h> + +#include <inttypes.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> + +#define MAX_INLINE_NEST 1024 + +static int filename_split(char *filename, unsigned int *line_nr) +{ + char *sep; + + sep = strchr(filename, '\n'); + if (sep) + *sep = '\0'; + + if (!strcmp(filename, "??:0")) + return 0; + + sep = strchr(filename, ':'); + if (sep) { + *sep++ = '\0'; + *line_nr = strtoul(sep, NULL, 0); + return 1; + } + pr_debug("addr2line missing ':' in filename split\n"); + return 0; +} + +static void addr2line_subprocess_cleanup(struct child_process *a2l) +{ + if (a2l->pid != -1) { + kill(a2l->pid, SIGKILL); + finish_command(a2l); /* ignore result, we don't care */ + a2l->pid = -1; + close(a2l->in); + close(a2l->out); + } + + free(a2l); +} + +static struct child_process *addr2line_subprocess_init(const char *addr2line_path, + const char *binary_path) +{ + const char *argv[] = { + addr2line_path ?: "addr2line", + "-e", binary_path, + "-a", "-i", "-f", NULL + }; + struct child_process *a2l = zalloc(sizeof(*a2l)); + int start_command_status = 0; + + if (a2l == NULL) { + pr_err("Failed to allocate memory for addr2line"); + return NULL; + } + + a2l->pid = -1; + a2l->in = -1; + a2l->out = -1; + a2l->no_stderr = 1; + + a2l->argv = argv; + start_command_status = start_command(a2l); + a2l->argv = NULL; /* it's not used after start_command; avoid dangling pointers */ + + if (start_command_status != 0) { + pr_warning("could not start addr2line (%s) for %s: start_command return code %d\n", + addr2line_path, binary_path, start_command_status); + addr2line_subprocess_cleanup(a2l); + return NULL; + } + + return a2l; +} + +enum cmd_a2l_style { + BROKEN, + GNU_BINUTILS, + LLVM, +}; + +static enum cmd_a2l_style cmd_addr2line_configure(struct child_process *a2l, const char *dso_name) +{ + static bool cached; + static enum cmd_a2l_style style; + + if (!cached) { + char buf[128]; + struct io io; + int ch; + int lines; + + if (write(a2l->in, ",\n", 2) != 2) + return BROKEN; + + io__init(&io, a2l->out, buf, sizeof(buf)); + ch = io__get_char(&io); + if (ch == ',') { + style = LLVM; + cached = true; + lines = 1; + pr_debug3("Detected LLVM addr2line style\n"); + } else if (ch == '0') { + style = GNU_BINUTILS; + cached = true; + lines = 3; + pr_debug3("Detected binutils addr2line style\n"); + } else { + if (!symbol_conf.addr2line_disable_warn) { + char *output = NULL; + size_t output_len; + + io__getline(&io, &output, &output_len); + pr_warning("%s %s: addr2line configuration failed\n", + __func__, dso_name); + pr_warning("\t%c%s", ch, output); + } + pr_debug("Unknown/broken addr2line style\n"); + return BROKEN; + } + while (lines) { + ch = io__get_char(&io); + if (ch <= 0) + break; + if (ch == '\n') + lines--; + } + /* Ignore SIGPIPE in the event addr2line exits. */ + signal(SIGPIPE, SIG_IGN); + } + return style; +} + +static int read_addr2line_record(struct io *io, + enum cmd_a2l_style style, + const char *dso_name, + u64 addr, + bool first, + char **function, + char **filename, + unsigned int *line_nr) +{ + /* + * Returns: + * -1 ==> error + * 0 ==> sentinel (or other ill-formed) record read + * 1 ==> a genuine record read + */ + char *line = NULL; + size_t line_len = 0; + unsigned int dummy_line_nr = 0; + int ret = -1; + + if (function != NULL) + zfree(function); + + if (filename != NULL) + zfree(filename); + + if (line_nr != NULL) + *line_nr = 0; + + /* + * Read the first line. Without an error this will be: + * - for the first line an address like 0x1234, + * - the binutils sentinel 0x0000000000000000, + * - the llvm-addr2line the sentinel ',' character, + * - the function name line for an inlined function. + */ + if (io__getline(io, &line, &line_len) < 0 || !line_len) + goto error; + + pr_debug3("%s %s: addr2line read address for sentinel: %s", __func__, dso_name, line); + if (style == LLVM && line_len == 2 && line[0] == ',') { + /* Found the llvm-addr2line sentinel character. */ + zfree(&line); + return 0; + } else if (style == GNU_BINUTILS && (!first || addr != 0)) { + int zero_count = 0, non_zero_count = 0; + /* + * Check for binutils sentinel ignoring it for the case the + * requested address is 0. + */ + + /* A given address should always start 0x. */ + if (line_len >= 2 || line[0] != '0' || line[1] != 'x') { + for (size_t i = 2; i < line_len; i++) { + if (line[i] == '0') + zero_count++; + else if (line[i] != '\n') + non_zero_count++; + } + if (!non_zero_count) { + int ch; + + if (first && !zero_count) { + /* Line was erroneous just '0x'. */ + goto error; + } + /* + * Line was 0x0..0, the sentinel for binutils. Remove + * the function and filename lines. + */ + zfree(&line); + do { + ch = io__get_char(io); + } while (ch > 0 && ch != '\n'); + do { + ch = io__get_char(io); + } while (ch > 0 && ch != '\n'); + return 0; + } + } + } + /* Read the second function name line (if inline data then this is the first line). */ + if (first && (io__getline(io, &line, &line_len) < 0 || !line_len)) + goto error; + + pr_debug3("%s %s: addr2line read line: %s", __func__, dso_name, line); + if (function != NULL) + *function = strdup(strim(line)); + + zfree(&line); + line_len = 0; + + /* Read the third filename and line number line. */ + if (io__getline(io, &line, &line_len) < 0 || !line_len) + goto error; + + pr_debug3("%s %s: addr2line filename:number : %s", __func__, dso_name, line); + if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0 && + style == GNU_BINUTILS) { + ret = 0; + goto error; + } + + if (filename != NULL) + *filename = strdup(line); + + zfree(&line); + line_len = 0; + + return 1; + +error: + free(line); + if (function != NULL) + zfree(function); + if (filename != NULL) + zfree(filename); + return ret; +} + +static int inline_list__append_record(struct dso *dso, + struct inline_node *node, + struct symbol *sym, + const char *function, + const char *filename, + unsigned int line_nr) +{ + struct symbol *inline_sym = new_inline_sym(dso, sym, function); + + return inline_list__append(inline_sym, srcline_from_fileline(filename, line_nr), node); +} + +int cmd__addr2line(const char *dso_name, u64 addr, + char **file, unsigned int *line_nr, + struct dso *dso, + bool unwind_inlines, + struct inline_node *node, + struct symbol *sym __maybe_unused) +{ + struct child_process *a2l = dso__a2l(dso); + char *record_function = NULL; + char *record_filename = NULL; + unsigned int record_line_nr = 0; + int record_status = -1; + int ret = 0; + size_t inline_count = 0; + int len; + char buf[128]; + ssize_t written; + struct io io = { .eof = false }; + enum cmd_a2l_style cmd_a2l_style; + + if (!a2l) { + if (!filename__has_section(dso_name, ".debug_line")) + goto out; + + dso__set_a2l(dso, + addr2line_subprocess_init(symbol_conf.addr2line_path, dso_name)); + a2l = dso__a2l(dso); + } + + if (a2l == NULL) { + if (!symbol_conf.addr2line_disable_warn) + pr_warning("%s %s: addr2line_subprocess_init failed\n", __func__, dso_name); + goto out; + } + cmd_a2l_style = cmd_addr2line_configure(a2l, dso_name); + if (cmd_a2l_style == BROKEN) + goto out; + + /* + * Send our request and then *deliberately* send something that can't be + * interpreted as a valid address to ask addr2line about (namely, + * ","). This causes addr2line to first write out the answer to our + * request, in an unbounded/unknown number of records, and then to write + * out the lines "0x0...0", "??" and "??:0", for GNU binutils, or "," + * for llvm-addr2line, so that we can detect when it has finished giving + * us anything useful. + */ + len = snprintf(buf, sizeof(buf), "%016"PRIx64"\n,\n", addr); + written = len > 0 ? write(a2l->in, buf, len) : -1; + if (written != len) { + if (!symbol_conf.addr2line_disable_warn) + pr_warning("%s %s: could not send request\n", __func__, dso_name); + goto out; + } + io__init(&io, a2l->out, buf, sizeof(buf)); + io.timeout_ms = symbol_conf.addr2line_timeout_ms; + switch (read_addr2line_record(&io, cmd_a2l_style, dso_name, addr, /*first=*/true, + &record_function, &record_filename, &record_line_nr)) { + case -1: + if (!symbol_conf.addr2line_disable_warn) + pr_warning("%s %s: could not read first record\n", __func__, dso_name); + goto out; + case 0: + /* + * The first record was invalid, so return failure, but first + * read another record, since we sent a sentinel ',' for the + * sake of detected the last inlined function. Treat this as the + * first of a record as the ',' generates a new start with GNU + * binutils, also force a non-zero address as we're no longer + * reading that record. + */ + switch (read_addr2line_record(&io, cmd_a2l_style, dso_name, + /*addr=*/1, /*first=*/true, + NULL, NULL, NULL)) { + case -1: + if (!symbol_conf.addr2line_disable_warn) + pr_warning("%s %s: could not read sentinel record\n", + __func__, dso_name); + break; + case 0: + /* The sentinel as expected. */ + break; + default: + if (!symbol_conf.addr2line_disable_warn) + pr_warning("%s %s: unexpected record instead of sentinel", + __func__, dso_name); + break; + } + goto out; + default: + /* First record as expected. */ + break; + } + + if (file) { + *file = strdup(record_filename); + ret = 1; + } + if (line_nr) + *line_nr = record_line_nr; + + if (unwind_inlines) { + if (node && inline_list__append_record(dso, node, sym, + record_function, + record_filename, + record_line_nr)) { + ret = 0; + goto out; + } + } + + /* + * We have to read the records even if we don't care about the inline + * info. This isn't the first record and force the address to non-zero + * as we're reading records beyond the first. + */ + while ((record_status = read_addr2line_record(&io, + cmd_a2l_style, + dso_name, + /*addr=*/1, + /*first=*/false, + &record_function, + &record_filename, + &record_line_nr)) == 1) { + if (unwind_inlines && node && inline_count++ < MAX_INLINE_NEST) { + if (inline_list__append_record(dso, node, sym, + record_function, + record_filename, + record_line_nr)) { + ret = 0; + goto out; + } + ret = 1; /* found at least one inline frame */ + } + } + +out: + free(record_function); + free(record_filename); + if (io.eof) { + dso__set_a2l(dso, NULL); + addr2line_subprocess_cleanup(a2l); + } + return ret; +} + +void dso__free_a2l(struct dso *dso) +{ + struct child_process *a2l = dso__a2l(dso); + + if (!a2l) + return; + + addr2line_subprocess_cleanup(a2l); + + dso__set_a2l(dso, NULL); +} diff --git a/tools/perf/util/addr2line.h b/tools/perf/util/addr2line.h new file mode 100644 index 000000000000..75989a92f16b --- /dev/null +++ b/tools/perf/util/addr2line.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_ADDR2LINE_H +#define __PERF_ADDR2LINE_H + +#include <linux/types.h> + +struct dso; +struct inline_node; +struct symbol; + +int cmd__addr2line(const char *dso_name, u64 addr, + char **file, unsigned int *line_nr, + struct dso *dso, + bool unwind_inlines, + struct inline_node *node, + struct symbol *sym); + +#endif /* __PERF_ADDR2LINE_H */ diff --git a/tools/perf/util/addr_location.c b/tools/perf/util/addr_location.c index 51825ef8c0ab..57e8217a00f9 100644 --- a/tools/perf/util/addr_location.c +++ b/tools/perf/util/addr_location.c @@ -7,7 +7,6 @@ void addr_location__init(struct addr_location *al) { al->thread = NULL; - al->maps = NULL; al->map = NULL; al->sym = NULL; al->srcline = NULL; @@ -17,28 +16,26 @@ void addr_location__init(struct addr_location *al) al->cpumode = 0; al->cpu = 0; al->socket = 0; + al->parallelism = 1; } /* * The preprocess_sample method will return with reference counts for the * in it, when done using (and perhaps getting ref counts if needing to * keep a pointer to one of those entries) it must be paired with - * addr_location__put(), so that the refcounts can be decremented. + * addr_location__exit(), so that the refcounts can be decremented. */ void addr_location__exit(struct addr_location *al) { map__zput(al->map); thread__zput(al->thread); - maps__zput(al->maps); } void addr_location__copy(struct addr_location *dst, struct addr_location *src) { thread__put(dst->thread); - maps__put(dst->maps); map__put(dst->map); *dst = *src; dst->thread = thread__get(src->thread); - dst->maps = maps__get(src->maps); dst->map = map__get(src->map); } diff --git a/tools/perf/util/addr_location.h b/tools/perf/util/addr_location.h index d8ac0428dff2..fdc4d3f3a68b 100644 --- a/tools/perf/util/addr_location.h +++ b/tools/perf/util/addr_location.h @@ -11,16 +11,19 @@ struct symbol; struct addr_location { struct thread *thread; - struct maps *maps; struct map *map; struct symbol *sym; const char *srcline; u64 addr; char level; - u8 filtered; u8 cpumode; + u16 filtered; s32 cpu; s32 socket; + /* Same as machine.parallelism but within [1, nr_cpus]. */ + int parallelism; + /* See he_stat.latency. */ + u64 latency; }; void addr_location__init(struct addr_location *al); diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c index 38dc4524b7e8..6c64b5f69a4e 100644 --- a/tools/perf/util/affinity.c +++ b/tools/perf/util/affinity.c @@ -5,6 +5,7 @@ #include <stdlib.h> #include <linux/bitmap.h> #include <linux/zalloc.h> +#include <perf/cpumap.h> #include "perf.h" #include "cpumap.h" #include "affinity.h" @@ -83,3 +84,20 @@ void affinity__cleanup(struct affinity *a) if (a != NULL) __affinity__cleanup(a); } + +void cpu_map__set_affinity(const struct perf_cpu_map *cpumap) +{ + int cpu_set_size = get_cpu_set_size(); + unsigned long *cpuset = bitmap_zalloc(cpu_set_size * 8); + struct perf_cpu cpu; + unsigned int idx; + + if (!cpuset) + return; + + perf_cpu_map__for_each_cpu_skip_any(cpu, idx, cpumap) + __set_bit(cpu.cpu, cpuset); + + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)cpuset); + zfree(&cpuset); +} diff --git a/tools/perf/util/affinity.h b/tools/perf/util/affinity.h index 0ad6a18ef20c..7341194b2298 100644 --- a/tools/perf/util/affinity.h +++ b/tools/perf/util/affinity.h @@ -4,6 +4,7 @@ #include <stdbool.h> +struct perf_cpu_map; struct affinity { unsigned long *orig_cpus; unsigned long *sched_cpus; @@ -13,5 +14,6 @@ struct affinity { void affinity__cleanup(struct affinity *a); void affinity__set(struct affinity *a, int cpu); int affinity__setup(struct affinity *a); +void cpu_map__set_affinity(const struct perf_cpu_map *cpumap); #endif // PERF_AFFINITY_H diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c index 9d0ce88e90e4..b084dee76b1a 100644 --- a/tools/perf/util/amd-sample-raw.c +++ b/tools/perf/util/amd-sample-raw.c @@ -9,7 +9,7 @@ #include <inttypes.h> #include <linux/string.h> -#include "../../arch/x86/include/asm/amd-ibs.h" +#include "../../arch/x86/include/asm/amd/ibs.h" #include "debug.h" #include "session.h" @@ -19,6 +19,8 @@ static u32 cpu_family, cpu_model, ibs_fetch_type, ibs_op_type; static bool zen4_ibs_extensions; +static bool ldlat_cap; +static bool dtlb_pgsize_cap; static void pr_ibs_fetch_ctl(union ibs_fetch_ctl reg) { @@ -78,14 +80,20 @@ static void pr_ic_ibs_extd_ctl(union ic_ibs_extd_ctl reg) static void pr_ibs_op_ctl(union ibs_op_ctl reg) { char l3_miss_only[sizeof(" L3MissOnly _")] = ""; + char ldlat[sizeof(" LdLatThrsh __ LdLatEn _")] = ""; if (zen4_ibs_extensions) snprintf(l3_miss_only, sizeof(l3_miss_only), " L3MissOnly %d", reg.l3_miss_only); - printf("ibs_op_ctl:\t%016llx MaxCnt %9d%s En %d Val %d CntCtl %d=%s CurCnt %9d\n", + if (ldlat_cap) { + snprintf(ldlat, sizeof(ldlat), " LdLatThrsh %2d LdLatEn %d", + reg.ldlat_thrsh, reg.ldlat_en); + } + + printf("ibs_op_ctl:\t%016llx MaxCnt %9d%s En %d Val %d CntCtl %d=%s CurCnt %9d%s\n", reg.val, ((reg.opmaxcnt_ext << 16) | reg.opmaxcnt) << 4, l3_miss_only, reg.op_en, reg.op_val, reg.cnt_ctl, - reg.cnt_ctl ? "uOps" : "cycles", reg.opcurcnt); + reg.cnt_ctl ? "uOps" : "cycles", reg.opcurcnt, ldlat); } static void pr_ibs_op_data(union ibs_op_data reg) @@ -154,9 +162,20 @@ static void pr_ibs_op_data2(union ibs_op_data2 reg) static void pr_ibs_op_data3(union ibs_op_data3 reg) { - char l2_miss_str[sizeof(" L2Miss _")] = ""; - char op_mem_width_str[sizeof(" OpMemWidth _____ bytes")] = ""; + static const char * const dc_page_sizes[] = { + " 4K", + " 2M", + " 1G", + " ??", + }; char op_dc_miss_open_mem_reqs_str[sizeof(" OpDcMissOpenMemReqs __")] = ""; + char dc_l1_l2tlb_miss_str[sizeof(" DcL1TlbMiss _ DcL2TlbMiss _")] = ""; + char dc_l1tlb_hit_str[sizeof(" DcL1TlbHit2M _ DcL1TlbHit1G _")] = ""; + char op_mem_width_str[sizeof(" OpMemWidth _____ bytes")] = ""; + char dc_l2tlb_hit_2m_str[sizeof(" DcL2TlbHit2M _")] = ""; + char dc_l2tlb_hit_1g_str[sizeof(" DcL2TlbHit1G _")] = ""; + char dc_page_size_str[sizeof(" DcPageSize ____")] = ""; + char l2_miss_str[sizeof(" L2Miss _")] = ""; /* * Erratum #1293 @@ -172,16 +191,40 @@ static void pr_ibs_op_data3(union ibs_op_data3 reg) snprintf(op_mem_width_str, sizeof(op_mem_width_str), " OpMemWidth %2d bytes", 1 << (reg.op_mem_width - 1)); - printf("ibs_op_data3:\t%016llx LdOp %d StOp %d DcL1TlbMiss %d DcL2TlbMiss %d " - "DcL1TlbHit2M %d DcL1TlbHit1G %d DcL2TlbHit2M %d DcMiss %d DcMisAcc %d " - "DcWcMemAcc %d DcUcMemAcc %d DcLockedOp %d DcMissNoMabAlloc %d DcLinAddrValid %d " - "DcPhyAddrValid %d DcL2TlbHit1G %d%s SwPf %d%s%s DcMissLat %5d TlbRefillLat %5d\n", - reg.val, reg.ld_op, reg.st_op, reg.dc_l1tlb_miss, reg.dc_l2tlb_miss, - reg.dc_l1tlb_hit_2m, reg.dc_l1tlb_hit_1g, reg.dc_l2tlb_hit_2m, reg.dc_miss, - reg.dc_mis_acc, reg.dc_wc_mem_acc, reg.dc_uc_mem_acc, reg.dc_locked_op, - reg.dc_miss_no_mab_alloc, reg.dc_lin_addr_valid, reg.dc_phy_addr_valid, - reg.dc_l2_tlb_hit_1g, l2_miss_str, reg.sw_pf, op_mem_width_str, - op_dc_miss_open_mem_reqs_str, reg.dc_miss_lat, reg.tlb_refill_lat); + if (dtlb_pgsize_cap) { + if (reg.dc_phy_addr_valid) { + int idx = (reg.dc_l1tlb_hit_1g << 1) | reg.dc_l1tlb_hit_2m; + + snprintf(dc_l1_l2tlb_miss_str, sizeof(dc_l1_l2tlb_miss_str), + " DcL1TlbMiss %d DcL2TlbMiss %d", + reg.dc_l1tlb_miss, reg.dc_l2tlb_miss); + snprintf(dc_page_size_str, sizeof(dc_page_size_str), + " DcPageSize %4s", dc_page_sizes[idx]); + } + } else { + snprintf(dc_l1_l2tlb_miss_str, sizeof(dc_l1_l2tlb_miss_str), + " DcL1TlbMiss %d DcL2TlbMiss %d", + reg.dc_l1tlb_miss, reg.dc_l2tlb_miss); + snprintf(dc_l1tlb_hit_str, sizeof(dc_l1tlb_hit_str), + " DcL1TlbHit2M %d DcL1TlbHit1G %d", + reg.dc_l1tlb_hit_2m, reg.dc_l1tlb_hit_1g); + snprintf(dc_l2tlb_hit_2m_str, sizeof(dc_l2tlb_hit_2m_str), + " DcL2TlbHit2M %d", reg.dc_l2tlb_hit_2m); + snprintf(dc_l2tlb_hit_1g_str, sizeof(dc_l2tlb_hit_1g_str), + " DcL2TlbHit1G %d", reg.dc_l2_tlb_hit_1g); + } + + printf("ibs_op_data3:\t%016llx LdOp %d StOp %d%s%s%s DcMiss %d DcMisAcc %d " + "DcWcMemAcc %d DcUcMemAcc %d DcLockedOp %d DcMissNoMabAlloc %d " + "DcLinAddrValid %d DcPhyAddrValid %d%s%s SwPf %d%s%s " + "DcMissLat %5d TlbRefillLat %5d\n", + reg.val, reg.ld_op, reg.st_op, dc_l1_l2tlb_miss_str, + dtlb_pgsize_cap ? dc_page_size_str : dc_l1tlb_hit_str, + dc_l2tlb_hit_2m_str, reg.dc_miss, reg.dc_mis_acc, reg.dc_wc_mem_acc, + reg.dc_uc_mem_acc, reg.dc_locked_op, reg.dc_miss_no_mab_alloc, + reg.dc_lin_addr_valid, reg.dc_phy_addr_valid, dc_l2tlb_hit_1g_str, + l2_miss_str, reg.sw_pf, op_mem_width_str, op_dc_miss_open_mem_reqs_str, + reg.dc_miss_lat, reg.tlb_refill_lat); } /* @@ -311,7 +354,7 @@ static void parse_cpuid(struct perf_env *env) */ bool evlist__has_amd_ibs(struct evlist *evlist) { - struct perf_env *env = evlist->env; + struct perf_env *env = perf_session__env(evlist->session); int ret, nr_pmu_mappings = perf_env__nr_pmu_mappings(env); const char *pmu_mapping = perf_env__pmu_mappings(env); char name[sizeof("ibs_fetch")]; @@ -331,6 +374,12 @@ bool evlist__has_amd_ibs(struct evlist *evlist) if (perf_env__find_pmu_cap(env, "ibs_op", "zen4_ibs_extensions")) zen4_ibs_extensions = 1; + if (perf_env__find_pmu_cap(env, "ibs_op", "ldlat")) + ldlat_cap = 1; + + if (perf_env__find_pmu_cap(env, "ibs_op", "dtlb_pgsize")) + dtlb_pgsize_cap = 1; + if (ibs_fetch_type || ibs_op_type) { if (!cpu_family) parse_cpuid(env); diff --git a/tools/perf/util/annotate-arch/Build b/tools/perf/util/annotate-arch/Build new file mode 100644 index 000000000000..23316743fdc5 --- /dev/null +++ b/tools/perf/util/annotate-arch/Build @@ -0,0 +1,11 @@ +perf-util-y += annotate-arc.o +perf-util-y += annotate-arm.o +perf-util-y += annotate-arm64.o +perf-util-y += annotate-csky.o +perf-util-y += annotate-loongarch.o +perf-util-y += annotate-mips.o +perf-util-y += annotate-x86.o +perf-util-y += annotate-powerpc.o +perf-util-y += annotate-riscv64.o +perf-util-y += annotate-s390.o +perf-util-y += annotate-sparc.o diff --git a/tools/perf/util/annotate-arch/annotate-arc.c b/tools/perf/util/annotate-arch/annotate-arc.c new file mode 100644 index 000000000000..170103e383a4 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-arc.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include "../disasm.h" + +const struct arch *arch__new_arc(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "arc"; + arch->id = *id; + arch->objdump.comment_char = ';'; + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-arm.c b/tools/perf/util/annotate-arch/annotate-arm.c new file mode 100644 index 000000000000..afb413c80156 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-arm.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdlib.h> +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include <errno.h> +#include <regex.h> +#include "../annotate.h" +#include "../disasm.h" + +struct arch_arm { + struct arch arch; + regex_t call_insn; + regex_t jump_insn; +}; + +static const struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const char *name) +{ + struct arch_arm *arm = container_of(arch, struct arch_arm, arch); + const struct ins_ops *ops; + regmatch_t match[2]; + + if (!regexec(&arm->call_insn, name, 2, match, 0)) + ops = &call_ops; + else if (!regexec(&arm->jump_insn, name, 2, match, 0)) + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +const struct arch *arch__new_arm(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + int err; + struct arch_arm *arm = zalloc(sizeof(*arm)); + struct arch *arch; + + if (!arm) + return NULL; + + arch = &arm->arch; + arch->name = "arm"; + arch->id = *id; + arch->objdump.comment_char = ';'; + arch->objdump.skip_functions_char = '+'; + arch->associate_instruction_ops = arm__associate_instruction_ops; + +#define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)" + err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", REG_EXTENDED); + if (err) + goto out_free_arm; + + err = regcomp(&arm->jump_insn, "^bx?" ARM_CONDS "?$", REG_EXTENDED); + if (err) + goto out_free_call; +#undef ARM_CONDS + + return arch; + +out_free_call: + regfree(&arm->call_insn); +out_free_arm: + free(arm); + errno = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP; + return NULL; +} diff --git a/tools/perf/util/annotate-arch/annotate-arm64.c b/tools/perf/util/annotate-arch/annotate-arm64.c new file mode 100644 index 000000000000..33080fdca125 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-arm64.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <linux/zalloc.h> +#include <regex.h> +#include "../annotate.h" +#include "../disasm.h" + +struct arch_arm64 { + struct arch arch; + regex_t call_insn; + regex_t jump_insn; +}; + +static int arm64_mov__parse(const struct arch *arch __maybe_unused, + struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) +{ + char *s = strchr(ops->raw, ','), *target, *endptr; + + if (s == NULL) + return -1; + + *s = '\0'; + ops->source.raw = strdup(ops->raw); + *s = ','; + + if (ops->source.raw == NULL) + return -1; + + target = ++s; + ops->target.raw = strdup(target); + if (ops->target.raw == NULL) + goto out_free_source; + + ops->target.addr = strtoull(target, &endptr, 16); + if (endptr == target) + goto out_free_target; + + s = strchr(endptr, '<'); + if (s == NULL) + goto out_free_target; + endptr = strchr(s + 1, '>'); + if (endptr == NULL) + goto out_free_target; + + *endptr = '\0'; + *s = ' '; + ops->target.name = strdup(s); + *s = '<'; + *endptr = '>'; + if (ops->target.name == NULL) + goto out_free_target; + + return 0; + +out_free_target: + zfree(&ops->target.raw); +out_free_source: + zfree(&ops->source.raw); + return -1; +} + +static const struct ins_ops arm64_mov_ops = { + .parse = arm64_mov__parse, + .scnprintf = mov__scnprintf, +}; + +static const struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name) +{ + struct arch_arm64 *arm = container_of(arch, struct arch_arm64, arch); + const struct ins_ops *ops; + regmatch_t match[2]; + + if (!regexec(&arm->jump_insn, name, 2, match, 0)) + ops = &jump_ops; + else if (!regexec(&arm->call_insn, name, 2, match, 0)) + ops = &call_ops; + else if (!strcmp(name, "ret")) + ops = &ret_ops; + else + ops = &arm64_mov_ops; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +const struct arch *arch__new_arm64(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + int err; + struct arch_arm64 *arm = zalloc(sizeof(*arm)); + struct arch *arch; + + if (!arm) + return NULL; + + arch = &arm->arch; + arch->name = "arm64"; + arch->id = *id; + arch->objdump.comment_char = '/'; + arch->objdump.skip_functions_char = '+'; + arch->associate_instruction_ops = arm64__associate_instruction_ops; + + /* bl, blr */ + err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED); + if (err) + goto out_free_arm; + + /* b, b.cond, br, cbz/cbnz, tbz/tbnz */ + err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|hs|le|lo|ls|lt|mi|ne|pl|vc|vs)?n?z?$", + REG_EXTENDED); + if (err) + goto out_free_call; + + return arch; + +out_free_call: + regfree(&arm->call_insn); +out_free_arm: + free(arm); + errno = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP; + return NULL; +} diff --git a/tools/perf/util/annotate-arch/annotate-csky.c b/tools/perf/util/annotate-arch/annotate-csky.c new file mode 100644 index 000000000000..d2b18e4ea2c9 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-csky.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. +#include <string.h> +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include "../disasm.h" + +static const struct ins_ops *csky__associate_ins_ops(struct arch *arch, + const char *name) +{ + const struct ins_ops *ops = NULL; + + /* catch all kind of jumps */ + if (!strcmp(name, "bt") || + !strcmp(name, "bf") || + !strcmp(name, "bez") || + !strcmp(name, "bnez") || + !strcmp(name, "bnezad") || + !strcmp(name, "bhsz") || + !strcmp(name, "bhz") || + !strcmp(name, "blsz") || + !strcmp(name, "blz") || + !strcmp(name, "br") || + !strcmp(name, "jmpi") || + !strcmp(name, "jmp")) + ops = &jump_ops; + + /* catch function call */ + if (!strcmp(name, "bsr") || + !strcmp(name, "jsri") || + !strcmp(name, "jsr")) + ops = &call_ops; + + /* catch function return */ + if (!strcmp(name, "rts")) + ops = &ret_ops; + + if (ops) + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +const struct arch *arch__new_csky(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "csky"; + arch->id = *id; + arch->objdump.comment_char = '/'; + arch->associate_instruction_ops = csky__associate_ins_ops; + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-loongarch.c b/tools/perf/util/annotate-arch/annotate-loongarch.c new file mode 100644 index 000000000000..c2addca77320 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-loongarch.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Perf annotate functions. + * + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ +#include <stdlib.h> +#include <string.h> +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include "../disasm.h" +#include "../map.h" +#include "../maps.h" +#include "../symbol.h" +#include "../thread.h" + +static int loongarch_call__parse(const struct arch *arch, struct ins_operands *ops, + struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) +{ + char *c, *endptr, *tok, *name; + struct map *map = ms->map; + struct addr_map_symbol target; + + c = strchr(ops->raw, '#'); + if (c++ == NULL) + return -1; + + ops->target.addr = strtoull(c, &endptr, 16); + + name = strchr(endptr, '<'); + name++; + + if (arch->objdump.skip_functions_char && + strchr(name, arch->objdump.skip_functions_char)) + return -1; + + tok = strchr(name, '>'); + if (tok == NULL) + return -1; + + *tok = '\0'; + ops->target.name = strdup(name); + *tok = '>'; + + if (ops->target.name == NULL) + return -1; + + target = (struct addr_map_symbol) { + .ms = { .map = map__get(map), }, + .addr = map__objdump_2mem(map, ops->target.addr), + }; + + if (maps__find_ams(thread__maps(ms->thread), &target) == 0 && + map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) + ops->target.sym = target.ms.sym; + + addr_map_symbol__exit(&target); + return 0; +} + +static const struct ins_ops loongarch_call_ops = { + .parse = loongarch_call__parse, + .scnprintf = call__scnprintf, + .is_call = true, +}; + +static int loongarch_jump__parse(const struct arch *arch, struct ins_operands *ops, + struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) + +{ + struct map *map = ms->map; + struct symbol *sym = ms->sym; + struct addr_map_symbol target = { + .ms = { .map = map__get(map), }, + }; + const char *c = strchr(ops->raw, '#'); + u64 start, end; + + ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char); + ops->jump.raw_func_start = strchr(ops->raw, '<'); + + if (ops->jump.raw_func_start && c > ops->jump.raw_func_start) + c = NULL; + + if (c++ != NULL) + ops->target.addr = strtoull(c, NULL, 16); + else + ops->target.addr = strtoull(ops->raw, NULL, 16); + + target.addr = map__objdump_2mem(map, ops->target.addr); + start = map__unmap_ip(map, sym->start); + end = map__unmap_ip(map, sym->end); + + ops->target.outside = target.addr < start || target.addr >= end; + + if (maps__find_ams(thread__maps(ms->thread), &target) == 0 && + map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) + ops->target.sym = target.ms.sym; + + if (!ops->target.outside) { + ops->target.offset = target.addr - start; + ops->target.offset_avail = true; + } else { + ops->target.offset_avail = false; + } + addr_map_symbol__exit(&target); + return 0; +} + +static const struct ins_ops loongarch_jump_ops = { + .free = jump__delete, + .parse = loongarch_jump__parse, + .scnprintf = jump__scnprintf, + .is_jump = true, +}; + +static +const struct ins_ops *loongarch__associate_ins_ops(struct arch *arch, const char *name) +{ + const struct ins_ops *ops = NULL; + + if (!strcmp(name, "bl")) + ops = &loongarch_call_ops; + else if (!strcmp(name, "jirl")) + ops = &ret_ops; + else if (!strcmp(name, "b") || + !strncmp(name, "beq", 3) || + !strncmp(name, "bne", 3) || + !strncmp(name, "blt", 3) || + !strncmp(name, "bge", 3) || + !strncmp(name, "bltu", 4) || + !strncmp(name, "bgeu", 4)) + ops = &loongarch_jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +const struct arch *arch__new_loongarch(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "loongarch"; + arch->id = *id; + arch->associate_instruction_ops = loongarch__associate_ins_ops; + arch->objdump.comment_char = '#'; + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-mips.c b/tools/perf/util/annotate-arch/annotate-mips.c new file mode 100644 index 000000000000..e8d1c6c7e9f3 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-mips.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include "../disasm.h" + +static +const struct ins_ops *mips__associate_ins_ops(struct arch *arch, const char *name) +{ + const struct ins_ops *ops = NULL; + + if (!strncmp(name, "bal", 3) || + !strncmp(name, "bgezal", 6) || + !strncmp(name, "bltzal", 6) || + !strncmp(name, "bgtzal", 6) || + !strncmp(name, "blezal", 6) || + !strncmp(name, "beqzal", 6) || + !strncmp(name, "bnezal", 6) || + !strncmp(name, "bgtzl", 5) || + !strncmp(name, "bltzl", 5) || + !strncmp(name, "bgezl", 5) || + !strncmp(name, "blezl", 5) || + !strncmp(name, "jialc", 5) || + !strncmp(name, "beql", 4) || + !strncmp(name, "bnel", 4) || + !strncmp(name, "jal", 3)) + ops = &call_ops; + else if (!strncmp(name, "jr", 2)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +const struct arch *arch__new_mips(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "mips"; + arch->id = *id; + arch->objdump.comment_char = '#'; + arch->associate_instruction_ops = mips__associate_ins_ops; + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-powerpc.c b/tools/perf/util/annotate-arch/annotate-powerpc.c new file mode 100644 index 000000000000..218207b52581 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-powerpc.c @@ -0,0 +1,410 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <linux/compiler.h> +#include <linux/kernel.h> +#include "../annotate-data.h" +#include "../debug.h" +#include "../disasm.h" + +#define PPC_OP(op) (((op) >> 26) & 0x3F) +#define PPC_21_30(R) (((R) >> 1) & 0x3ff) +#define PPC_22_30(R) (((R) >> 1) & 0x1ff) + +#define MINUS_EXT_XO_FORM 234 +#define SUB_EXT_XO_FORM 232 +#define ADD_ZERO_EXT_XO_FORM 202 +#define SUB_ZERO_EXT_XO_FORM 200 + +static int arithmetic__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) +{ + return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, + ops->raw); +} + +/* + * Sets the fields: multi_regs and "mem_ref". + * "mem_ref" is set for ops->source which is later used to + * fill the objdump->memory_ref-char field. This ops is currently + * used by powerpc and since binary instruction code is used to + * extract opcode, regs and offset, no other parsing is needed here. + * + * Dont set multi regs for 4 cases since it has only one operand + * for source: + * - Add to Minus One Extended XO-form ( Ex: addme, addmeo ) + * - Subtract From Minus One Extended XO-form ( Ex: subfme ) + * - Add to Zero Extended XO-form ( Ex: addze, addzeo ) + * - Subtract From Zero Extended XO-form ( Ex: subfze ) + */ +static int arithmetic__parse(const struct arch *arch __maybe_unused, struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, struct disasm_line *dl) +{ + int opcode = PPC_OP(dl->raw.raw_insn); + + ops->source.mem_ref = false; + if (opcode == 31) { + if ((opcode != MINUS_EXT_XO_FORM) && (opcode != SUB_EXT_XO_FORM) && + (opcode != ADD_ZERO_EXT_XO_FORM) && (opcode != SUB_ZERO_EXT_XO_FORM)) + ops->source.multi_regs = true; + } + + ops->target.mem_ref = false; + ops->target.multi_regs = false; + + return 0; +} + +static const struct ins_ops arithmetic_ops = { + .parse = arithmetic__parse, + .scnprintf = arithmetic__scnprintf, +}; + +static int load_store__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) +{ + return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, + ops->raw); +} + +/* + * Sets the fields: multi_regs and "mem_ref". + * "mem_ref" is set for ops->source which is later used to + * fill the objdump->memory_ref-char field. This ops is currently + * used by powerpc and since binary instruction code is used to + * extract opcode, regs and offset, no other parsing is needed here + */ +static int load_store__parse(const struct arch *arch __maybe_unused, struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, struct disasm_line *dl __maybe_unused) +{ + ops->source.mem_ref = true; + ops->source.multi_regs = false; + /* opcode 31 is of X form */ + if (PPC_OP(dl->raw.raw_insn) == 31) + ops->source.multi_regs = true; + + ops->target.mem_ref = false; + ops->target.multi_regs = false; + + return 0; +} + +static const struct ins_ops load_store_ops = { + .parse = load_store__parse, + .scnprintf = load_store__scnprintf, +}; + +static const struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, const char *name) +{ + int i; + const struct ins_ops *ops; + + /* + * - Interested only if instruction starts with 'b'. + * - Few start with 'b', but aren't branch instructions. + */ + if (name[0] != 'b' || + !strncmp(name, "bcd", 3) || + !strncmp(name, "brinc", 5) || + !strncmp(name, "bper", 4)) + return NULL; + + ops = &jump_ops; + + i = strlen(name) - 1; + if (i < 0) + return NULL; + + /* ignore optional hints at the end of the instructions */ + if (name[i] == '+' || name[i] == '-') + i--; + + if (name[i] == 'l' || (name[i] == 'a' && name[i-1] == 'l')) { + /* + * if the instruction ends up with 'l' or 'la', then + * those are considered 'calls' since they update LR. + * ... except for 'bnl' which is branch if not less than + * and the absolute form of the same. + */ + if (strcmp(name, "bnl") && strcmp(name, "bnl+") && + strcmp(name, "bnl-") && strcmp(name, "bnla") && + strcmp(name, "bnla+") && strcmp(name, "bnla-")) + ops = &call_ops; + } + if (name[i] == 'r' && name[i-1] == 'l') + /* + * instructions ending with 'lr' are considered to be + * return instructions + */ + ops = &ret_ops; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +struct insn_offset { + const char *name; + int value; +}; + +/* + * There are memory instructions with opcode 31 which are + * of X Form, Example: + * ldx RT,RA,RB + * ______________________________________ + * | 31 | RT | RA | RB | 21 |/| + * -------------------------------------- + * 0 6 11 16 21 30 31 + * + * But all instructions with opcode 31 are not memory. + * Example: add RT,RA,RB + * + * Use bits 21 to 30 to check memory insns with 31 as opcode. + * In ins_array below, for ldx instruction: + * name => OP_31_XOP_LDX + * value => 21 + */ + +static struct insn_offset ins_array[] = { + { .name = "OP_31_XOP_LXSIWZX", .value = 12, }, + { .name = "OP_31_XOP_LWARX", .value = 20, }, + { .name = "OP_31_XOP_LDX", .value = 21, }, + { .name = "OP_31_XOP_LWZX", .value = 23, }, + { .name = "OP_31_XOP_LDUX", .value = 53, }, + { .name = "OP_31_XOP_LWZUX", .value = 55, }, + { .name = "OP_31_XOP_LXSIWAX", .value = 76, }, + { .name = "OP_31_XOP_LDARX", .value = 84, }, + { .name = "OP_31_XOP_LBZX", .value = 87, }, + { .name = "OP_31_XOP_LVX", .value = 103, }, + { .name = "OP_31_XOP_LBZUX", .value = 119, }, + { .name = "OP_31_XOP_STXSIWX", .value = 140, }, + { .name = "OP_31_XOP_STDX", .value = 149, }, + { .name = "OP_31_XOP_STWX", .value = 151, }, + { .name = "OP_31_XOP_STDUX", .value = 181, }, + { .name = "OP_31_XOP_STWUX", .value = 183, }, + { .name = "OP_31_XOP_STBX", .value = 215, }, + { .name = "OP_31_XOP_STVX", .value = 231, }, + { .name = "OP_31_XOP_STBUX", .value = 247, }, + { .name = "OP_31_XOP_LHZX", .value = 279, }, + { .name = "OP_31_XOP_LHZUX", .value = 311, }, + { .name = "OP_31_XOP_LXVDSX", .value = 332, }, + { .name = "OP_31_XOP_LWAX", .value = 341, }, + { .name = "OP_31_XOP_LHAX", .value = 343, }, + { .name = "OP_31_XOP_LWAUX", .value = 373, }, + { .name = "OP_31_XOP_LHAUX", .value = 375, }, + { .name = "OP_31_XOP_STHX", .value = 407, }, + { .name = "OP_31_XOP_STHUX", .value = 439, }, + { .name = "OP_31_XOP_LXSSPX", .value = 524, }, + { .name = "OP_31_XOP_LDBRX", .value = 532, }, + { .name = "OP_31_XOP_LSWX", .value = 533, }, + { .name = "OP_31_XOP_LWBRX", .value = 534, }, + { .name = "OP_31_XOP_LFSUX", .value = 567, }, + { .name = "OP_31_XOP_LXSDX", .value = 588, }, + { .name = "OP_31_XOP_LSWI", .value = 597, }, + { .name = "OP_31_XOP_LFDX", .value = 599, }, + { .name = "OP_31_XOP_LFDUX", .value = 631, }, + { .name = "OP_31_XOP_STXSSPX", .value = 652, }, + { .name = "OP_31_XOP_STDBRX", .value = 660, }, + { .name = "OP_31_XOP_STXWX", .value = 661, }, + { .name = "OP_31_XOP_STWBRX", .value = 662, }, + { .name = "OP_31_XOP_STFSX", .value = 663, }, + { .name = "OP_31_XOP_STFSUX", .value = 695, }, + { .name = "OP_31_XOP_STXSDX", .value = 716, }, + { .name = "OP_31_XOP_STSWI", .value = 725, }, + { .name = "OP_31_XOP_STFDX", .value = 727, }, + { .name = "OP_31_XOP_STFDUX", .value = 759, }, + { .name = "OP_31_XOP_LXVW4X", .value = 780, }, + { .name = "OP_31_XOP_LHBRX", .value = 790, }, + { .name = "OP_31_XOP_LXVD2X", .value = 844, }, + { .name = "OP_31_XOP_LFIWAX", .value = 855, }, + { .name = "OP_31_XOP_LFIWZX", .value = 887, }, + { .name = "OP_31_XOP_STXVW4X", .value = 908, }, + { .name = "OP_31_XOP_STHBRX", .value = 918, }, + { .name = "OP_31_XOP_STXVD2X", .value = 972, }, + { .name = "OP_31_XOP_STFIWX", .value = 983, }, +}; + +/* + * Arithmetic instructions which are having opcode as 31. + * These instructions are tracked to save the register state + * changes. Example: + * + * lwz r10,264(r3) + * add r31, r3, r3 + * lwz r9, 0(r31) + * + * Here instruction tracking needs to identify the "add" + * instruction and save data type of r3 to r31. If a sample + * is hit at next "lwz r9, 0(r31)", by this instruction tracking, + * data type of r31 can be resolved. + */ +static struct insn_offset arithmetic_ins_op_31[] = { + { .name = "SUB_CARRY_XO_FORM", .value = 8, }, + { .name = "MUL_HDW_XO_FORM1", .value = 9, }, + { .name = "ADD_CARRY_XO_FORM", .value = 10, }, + { .name = "MUL_HW_XO_FORM1", .value = 11, }, + { .name = "SUB_XO_FORM", .value = 40, }, + { .name = "MUL_HDW_XO_FORM", .value = 73, }, + { .name = "MUL_HW_XO_FORM", .value = 75, }, + { .name = "SUB_EXT_XO_FORM", .value = 136, }, + { .name = "ADD_EXT_XO_FORM", .value = 138, }, + { .name = "SUB_ZERO_EXT_XO_FORM", .value = 200, }, + { .name = "ADD_ZERO_EXT_XO_FORM", .value = 202, }, + { .name = "SUB_EXT_XO_FORM2", .value = 232, }, + { .name = "MUL_DW_XO_FORM", .value = 233, }, + { .name = "ADD_EXT_XO_FORM2", .value = 234, }, + { .name = "MUL_W_XO_FORM", .value = 235, }, + { .name = "ADD_XO_FORM", .value = 266, }, + { .name = "DIV_DW_XO_FORM1", .value = 457, }, + { .name = "DIV_W_XO_FORM1", .value = 459, }, + { .name = "DIV_DW_XO_FORM", .value = 489, }, + { .name = "DIV_W_XO_FORM", .value = 491, }, +}; + +static struct insn_offset arithmetic_two_ops[] = { + { .name = "mulli", .value = 7, }, + { .name = "subfic", .value = 8, }, + { .name = "addic", .value = 12, }, + { .name = "addic.", .value = 13, }, + { .name = "addi", .value = 14, }, + { .name = "addis", .value = 15, }, +}; + +static int cmp_offset(const void *a, const void *b) +{ + const struct insn_offset *val1 = a; + const struct insn_offset *val2 = b; + + return (val1->value - val2->value); +} + +const struct ins_ops *check_ppc_insn(struct disasm_line *dl) +{ + int raw_insn = dl->raw.raw_insn; + int opcode = PPC_OP(raw_insn); + int mem_insn_31 = PPC_21_30(raw_insn); + struct insn_offset *ret; + struct insn_offset mem_insns_31_opcode = { + "OP_31_INSN", + mem_insn_31 + }; + char name_insn[32]; + + /* + * Instructions with opcode 32 to 63 are memory + * instructions in powerpc + */ + if ((opcode & 0x20)) { + /* + * Set name in case of raw instruction to + * opcode to be used in insn-stat + */ + if (!strlen(dl->ins.name)) { + sprintf(name_insn, "%d", opcode); + dl->ins.name = strdup(name_insn); + } + return &load_store_ops; + } else if (opcode == 31) { + /* Check for memory instructions with opcode 31 */ + ret = bsearch(&mem_insns_31_opcode, ins_array, ARRAY_SIZE(ins_array), sizeof(ins_array[0]), cmp_offset); + if (ret) { + if (!strlen(dl->ins.name)) + dl->ins.name = strdup(ret->name); + return &load_store_ops; + } else { + mem_insns_31_opcode.value = PPC_22_30(raw_insn); + ret = bsearch(&mem_insns_31_opcode, arithmetic_ins_op_31, ARRAY_SIZE(arithmetic_ins_op_31), + sizeof(arithmetic_ins_op_31[0]), cmp_offset); + if (ret != NULL) + return &arithmetic_ops; + /* Bits 21 to 30 has value 444 for "mr" insn ie, OR X form */ + if (PPC_21_30(raw_insn) == 444) + return &arithmetic_ops; + } + } else { + mem_insns_31_opcode.value = opcode; + ret = bsearch(&mem_insns_31_opcode, arithmetic_two_ops, ARRAY_SIZE(arithmetic_two_ops), + sizeof(arithmetic_two_ops[0]), cmp_offset); + if (ret != NULL) + return &arithmetic_ops; + } + + return NULL; +} + +/* + * Instruction tracking function to track register state moves. + * Example sequence: + * ld r10,264(r3) + * mr r31,r3 + * <<after some sequence> + * ld r9,312(r31) + * + * Previous instruction sequence shows that register state of r3 + * is moved to r31. update_insn_state_powerpc tracks these state + * changes + */ +#ifdef HAVE_LIBDW_SUPPORT +static void update_insn_state_powerpc(struct type_state *state, + struct data_loc_info *dloc, Dwarf_Die * cu_die __maybe_unused, + struct disasm_line *dl) +{ + struct annotated_insn_loc loc; + struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE]; + struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET]; + struct type_state_reg *tsr; + u32 insn_offset = dl->al.offset; + + if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0) + return; + + /* + * Value 444 for bits 21:30 is for "mr" + * instruction. "mr" is extended OR. So set the + * source and destination reg correctly + */ + if (PPC_21_30(dl->raw.raw_insn) == 444) { + int src_reg = src->reg1; + + src->reg1 = dst->reg1; + dst->reg1 = src_reg; + } + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) { + tsr->ok = false; + return; + } + + tsr->type = state->regs[src->reg1].type; + tsr->kind = state->regs[src->reg1].kind; + tsr->ok = true; + + pr_debug_dtp("mov [%x] reg%d -> reg%d", + insn_offset, src->reg1, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); +} +#endif /* HAVE_LIBDW_SUPPORT */ + +const struct arch *arch__new_powerpc(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "powerpc"; + arch->id = *id; + arch->objdump.comment_char = '#'; + annotate_opts.show_asm_raw = true; + arch->associate_instruction_ops = powerpc__associate_instruction_ops; +#ifdef HAVE_LIBDW_SUPPORT + arch->update_insn_state = update_insn_state_powerpc; +#endif + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-riscv64.c b/tools/perf/util/annotate-arch/annotate-riscv64.c new file mode 100644 index 000000000000..29a988fca8c9 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-riscv64.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include "../disasm.h" + +static +const struct ins_ops *riscv64__associate_ins_ops(struct arch *arch, const char *name) +{ + const struct ins_ops *ops = NULL; + + if (!strncmp(name, "jal", 3) || + !strncmp(name, "jr", 2) || + !strncmp(name, "call", 4)) + ops = &call_ops; + else if (!strncmp(name, "ret", 3)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +const struct arch *arch__new_riscv64(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "riscv"; + arch->id = *id; + arch->objdump.comment_char = '#'; + arch->associate_instruction_ops = riscv64__associate_ins_ops; + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-s390.c b/tools/perf/util/annotate-arch/annotate-s390.c new file mode 100644 index 000000000000..af9cabd0a586 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-s390.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <linux/compiler.h> +#include "../debug.h" +#include "../disasm.h" +#include "../map.h" +#include "../maps.h" +#include "../symbol.h" +#include "../thread.h" +#include "../annotate.h" +#include "../annotate-data.h" + +static int s390_call__parse(const struct arch *arch, struct ins_operands *ops, + struct map_symbol *ms, + struct disasm_line *dl __maybe_unused) +{ + char *endptr, *tok, *name; + struct map *map = ms->map; + struct addr_map_symbol target; + + tok = strchr(ops->raw, ','); + if (!tok) + return -1; + + ops->target.addr = strtoull(tok + 1, &endptr, 16); + + name = strchr(endptr, '<'); + if (name == NULL) + return -1; + + name++; + + if (arch->objdump.skip_functions_char && + strchr(name, arch->objdump.skip_functions_char)) + return -1; + + tok = strchr(name, '>'); + if (tok == NULL) + return -1; + + *tok = '\0'; + ops->target.name = strdup(name); + *tok = '>'; + + if (ops->target.name == NULL) + return -1; + + target = (struct addr_map_symbol) { + .ms = { .map = map__get(map), }, + .addr = map__objdump_2mem(map, ops->target.addr), + }; + + if (maps__find_ams(thread__maps(ms->thread), &target) == 0 && + map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) + ops->target.sym = target.ms.sym; + + addr_map_symbol__exit(&target); + return 0; +} + +static const struct ins_ops s390_call_ops = { + .parse = s390_call__parse, + .scnprintf = call__scnprintf, + .is_call = true, +}; + +static int s390_mov__parse(const struct arch *arch __maybe_unused, + struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) +{ + char *s = strchr(ops->raw, ','), *target, *endptr; + + if (s == NULL) + return -1; + + *s = '\0'; + ops->source.raw = strdup(ops->raw); + *s = ','; + + if (ops->source.raw == NULL) + return -1; + + target = ++s; + ops->target.raw = strdup(target); + if (ops->target.raw == NULL) + goto out_free_source; + + ops->target.addr = strtoull(target, &endptr, 16); + if (endptr == target) + goto out_free_target; + + s = strchr(endptr, '<'); + if (s == NULL) + goto out_free_target; + endptr = strchr(s + 1, '>'); + if (endptr == NULL) + goto out_free_target; + + *endptr = '\0'; + ops->target.name = strdup(s + 1); + *endptr = '>'; + if (ops->target.name == NULL) + goto out_free_target; + + return 0; + +out_free_target: + zfree(&ops->target.raw); +out_free_source: + zfree(&ops->source.raw); + return -1; +} + + +static const struct ins_ops s390_mov_ops = { + .parse = s390_mov__parse, + .scnprintf = mov__scnprintf, +}; + +static const struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name) +{ + const struct ins_ops *ops = NULL; + + /* catch all kind of jumps */ + if (strchr(name, 'j') || + !strncmp(name, "bct", 3) || + !strncmp(name, "br", 2)) + ops = &jump_ops; + /* override call/returns */ + if (!strcmp(name, "bras") || + !strcmp(name, "brasl") || + !strcmp(name, "basr")) + ops = &s390_call_ops; + if (!strcmp(name, "br")) + ops = &ret_ops; + /* override load/store relative to PC */ + if (!strcmp(name, "lrl") || + !strcmp(name, "lgrl") || + !strcmp(name, "lgfrl") || + !strcmp(name, "llgfrl") || + !strcmp(name, "strl") || + !strcmp(name, "stgrl")) + ops = &s390_mov_ops; + + if (ops) + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +static int s390__cpuid_parse(struct arch *arch, const char *cpuid) +{ + unsigned int family; + char model[16], model_c[16], cpumf_v[16], cpumf_a[16]; + int ret; + + /* + * cpuid string format: + * "IBM,family,model-capacity,model[,cpum_cf-version,cpum_cf-authorization]" + */ + ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%s", &family, model_c, + model, cpumf_v, cpumf_a); + if (ret >= 2) { + arch->family = family; + arch->model = 0; + return 0; + } + + return -1; +} + +const struct arch *arch__new_s390(const struct e_machine_and_e_flags *id, const char *cpuid) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "s390"; + arch->id = *id; + arch->associate_instruction_ops = s390__associate_ins_ops; + if (cpuid) { + if (s390__cpuid_parse(arch, cpuid)) { + errno = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING; + return NULL; + } + } + arch->objdump.comment_char = '#'; + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-sparc.c b/tools/perf/util/annotate-arch/annotate-sparc.c new file mode 100644 index 000000000000..2f07bc7a56dd --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-sparc.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include "../../util/disasm.h" + +static int is_branch_cond(const char *cond) +{ + if (cond[0] == '\0') + return 1; + + if (cond[0] == 'a' && cond[1] == '\0') + return 1; + + if (cond[0] == 'c' && + (cond[1] == 'c' || cond[1] == 's') && + cond[2] == '\0') + return 1; + + if (cond[0] == 'e' && + (cond[1] == '\0' || + (cond[1] == 'q' && cond[2] == '\0'))) + return 1; + + if (cond[0] == 'g' && + (cond[1] == '\0' || + (cond[1] == 't' && cond[2] == '\0') || + (cond[1] == 'e' && cond[2] == '\0') || + (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0'))) + return 1; + + if (cond[0] == 'l' && + (cond[1] == '\0' || + (cond[1] == 't' && cond[2] == '\0') || + (cond[1] == 'u' && cond[2] == '\0') || + (cond[1] == 'e' && cond[2] == '\0') || + (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0'))) + return 1; + + if (cond[0] == 'n' && + (cond[1] == '\0' || + (cond[1] == 'e' && cond[2] == '\0') || + (cond[1] == 'z' && cond[2] == '\0') || + (cond[1] == 'e' && cond[2] == 'g' && cond[3] == '\0'))) + return 1; + + if (cond[0] == 'b' && + cond[1] == 'p' && + cond[2] == 'o' && + cond[3] == 's' && + cond[4] == '\0') + return 1; + + if (cond[0] == 'v' && + (cond[1] == 'c' || cond[1] == 's') && + cond[2] == '\0') + return 1; + + if (cond[0] == 'b' && + cond[1] == 'z' && + cond[2] == '\0') + return 1; + + return 0; +} + +static int is_branch_reg_cond(const char *cond) +{ + if ((cond[0] == 'n' || cond[0] == 'l') && + cond[1] == 'z' && + cond[2] == '\0') + return 1; + + if (cond[0] == 'z' && + cond[1] == '\0') + return 1; + + if ((cond[0] == 'g' || cond[0] == 'l') && + cond[1] == 'e' && + cond[2] == 'z' && + cond[3] == '\0') + return 1; + + if (cond[0] == 'g' && + cond[1] == 'z' && + cond[2] == '\0') + return 1; + + return 0; +} + +static int is_branch_float_cond(const char *cond) +{ + if (cond[0] == '\0') + return 1; + + if ((cond[0] == 'a' || cond[0] == 'e' || + cond[0] == 'z' || cond[0] == 'g' || + cond[0] == 'l' || cond[0] == 'n' || + cond[0] == 'o' || cond[0] == 'u') && + cond[1] == '\0') + return 1; + + if (((cond[0] == 'g' && cond[1] == 'e') || + (cond[0] == 'l' && (cond[1] == 'e' || + cond[1] == 'g')) || + (cond[0] == 'n' && (cond[1] == 'e' || + cond[1] == 'z')) || + (cond[0] == 'u' && (cond[1] == 'e' || + cond[1] == 'g' || + cond[1] == 'l'))) && + cond[2] == '\0') + return 1; + + if (cond[0] == 'u' && + (cond[1] == 'g' || cond[1] == 'l') && + cond[2] == 'e' && + cond[3] == '\0') + return 1; + + return 0; +} + +static const struct ins_ops *sparc__associate_instruction_ops(struct arch *arch, const char *name) +{ + const struct ins_ops *ops = NULL; + + if (!strcmp(name, "call") || + !strcmp(name, "jmp") || + !strcmp(name, "jmpl")) { + ops = &call_ops; + } else if (!strcmp(name, "ret") || + !strcmp(name, "retl") || + !strcmp(name, "return")) { + ops = &ret_ops; + } else if (!strcmp(name, "mov")) { + ops = &mov_ops; + } else { + if (name[0] == 'c' && + (name[1] == 'w' || name[1] == 'x')) + name += 2; + + if (name[0] == 'b') { + const char *cond = name + 1; + + if (cond[0] == 'r') { + if (is_branch_reg_cond(cond + 1)) + ops = &jump_ops; + } else if (is_branch_cond(cond)) { + ops = &jump_ops; + } + } else if (name[0] == 'f' && name[1] == 'b') { + if (is_branch_float_cond(name + 2)) + ops = &jump_ops; + } + } + + if (ops) + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +const struct arch *arch__new_sparc(const struct e_machine_and_e_flags *id, + const char *cpuid __maybe_unused) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "sparc"; + arch->id = *id; + arch->associate_instruction_ops = sparc__associate_instruction_ops; + arch->objdump.comment_char = '#'; + return arch; +} diff --git a/tools/perf/util/annotate-arch/annotate-x86.c b/tools/perf/util/annotate-arch/annotate-x86.c new file mode 100644 index 000000000000..7e6136536393 --- /dev/null +++ b/tools/perf/util/annotate-arch/annotate-x86.c @@ -0,0 +1,852 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <linux/compiler.h> +#include <linux/zalloc.h> +#include <assert.h> +#include <inttypes.h> +#include "../annotate-data.h" +#include "../debug.h" +#include "../disasm.h" +#include "../dso.h" +#include "../map.h" +#include "../string2.h" // strstarts +#include "../symbol.h" + +/* + * x86 instruction nmemonic table to parse disasm lines for annotate. + * This table is searched twice - one for exact match and another for + * match without a size suffix (b, w, l, q) in case of AT&T syntax. + * + * So this table should not have entries with the suffix unless it's + * a complete different instruction than ones without the suffix. + */ +static const struct ins x86__instructions[] = { + { .name = "adc", .ops = &mov_ops, }, + { .name = "add", .ops = &mov_ops, }, + { .name = "addsd", .ops = &mov_ops, }, + { .name = "and", .ops = &mov_ops, }, + { .name = "andpd", .ops = &mov_ops, }, + { .name = "andps", .ops = &mov_ops, }, + { .name = "bsr", .ops = &mov_ops, }, + { .name = "bt", .ops = &mov_ops, }, + { .name = "btr", .ops = &mov_ops, }, + { .name = "bts", .ops = &mov_ops, }, + { .name = "call", .ops = &call_ops, }, + { .name = "cmovae", .ops = &mov_ops, }, + { .name = "cmovbe", .ops = &mov_ops, }, + { .name = "cmove", .ops = &mov_ops, }, + { .name = "cmp", .ops = &mov_ops, }, + { .name = "cmpxch", .ops = &mov_ops, }, + { .name = "cmpxchg", .ops = &mov_ops, }, + { .name = "cs", .ops = &mov_ops, }, + { .name = "dec", .ops = &dec_ops, }, + { .name = "divsd", .ops = &mov_ops, }, + { .name = "divss", .ops = &mov_ops, }, + { .name = "gs", .ops = &mov_ops, }, + { .name = "imul", .ops = &mov_ops, }, + { .name = "inc", .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 = "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 = "movapd", .ops = &mov_ops, }, + { .name = "movaps", .ops = &mov_ops, }, + { .name = "movdqa", .ops = &mov_ops, }, + { .name = "movdqu", .ops = &mov_ops, }, + { .name = "movsb", .ops = &mov_ops, }, + { .name = "movsd", .ops = &mov_ops, }, + { .name = "movsl", .ops = &mov_ops, }, + { .name = "movss", .ops = &mov_ops, }, + { .name = "movsw", .ops = &mov_ops, }, + { .name = "movupd", .ops = &mov_ops, }, + { .name = "movups", .ops = &mov_ops, }, + { .name = "movzb", .ops = &mov_ops, }, + { .name = "movzl", .ops = &mov_ops, }, + { .name = "movzw", .ops = &mov_ops, }, + { .name = "mulsd", .ops = &mov_ops, }, + { .name = "mulss", .ops = &mov_ops, }, + { .name = "nop", .ops = &nop_ops, }, + { .name = "or", .ops = &mov_ops, }, + { .name = "orps", .ops = &mov_ops, }, + { .name = "paddq", .ops = &mov_ops, }, + { .name = "pand", .ops = &mov_ops, }, + { .name = "pcmpeqb", .ops = &mov_ops, }, + { .name = "por", .ops = &mov_ops, }, + { .name = "rcl", .ops = &mov_ops, }, + { .name = "ret", .ops = &ret_ops, }, + { .name = "sbb", .ops = &mov_ops, }, + { .name = "sete", .ops = &mov_ops, }, + { .name = "sub", .ops = &mov_ops, }, + { .name = "subsd", .ops = &mov_ops, }, + { .name = "test", .ops = &mov_ops, }, + { .name = "tzcnt", .ops = &mov_ops, }, + { .name = "ucomisd", .ops = &mov_ops, }, + { .name = "ucomiss", .ops = &mov_ops, }, + { .name = "vaddsd", .ops = &mov_ops, }, + { .name = "vandpd", .ops = &mov_ops, }, + { .name = "vmovdqa", .ops = &mov_ops, }, + { .name = "vmovq", .ops = &mov_ops, }, + { .name = "vmovsd", .ops = &mov_ops, }, + { .name = "vmulsd", .ops = &mov_ops, }, + { .name = "vorpd", .ops = &mov_ops, }, + { .name = "vsubsd", .ops = &mov_ops, }, + { .name = "vucomisd", .ops = &mov_ops, }, + { .name = "xadd", .ops = &mov_ops, }, + { .name = "xbegin", .ops = &jump_ops, }, + { .name = "xchg", .ops = &mov_ops, }, + { .name = "xor", .ops = &mov_ops, }, + { .name = "xorpd", .ops = &mov_ops, }, + { .name = "xorps", .ops = &mov_ops, }, +}; + +static bool amd__ins_is_fused(const struct arch *arch, const char *ins1, + const char *ins2) +{ + if (strstr(ins2, "jmp")) + return false; + + /* Family >= 15h supports cmp/test + branch fusion */ + if (arch->family >= 0x15 && (strstarts(ins1, "test") || + (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) { + return true; + } + + /* Family >= 19h supports some ALU + branch fusion */ + if (arch->family >= 0x19 && (strstarts(ins1, "add") || + strstarts(ins1, "sub") || strstarts(ins1, "and") || + strstarts(ins1, "inc") || strstarts(ins1, "dec") || + strstarts(ins1, "or") || strstarts(ins1, "xor"))) { + return true; + } + + return false; +} + +static bool intel__ins_is_fused(const struct arch *arch, const char *ins1, + const char *ins2) +{ + if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp")) + return false; + + if (arch->model == 0x1e) { + /* Nehalem */ + if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) || + strstr(ins1, "test")) { + return true; + } + } else { + /* Newer platform */ + if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) || + strstr(ins1, "test") || + strstr(ins1, "add") || + strstr(ins1, "sub") || + strstr(ins1, "and") || + strstr(ins1, "inc") || + strstr(ins1, "dec")) { + return true; + } + } + + return false; +} + +static int x86__cpuid_parse(struct arch *arch, const char *cpuid) +{ + unsigned int family, model, stepping; + int ret; + + /* + * cpuid = "GenuineIntel,family,model,stepping" + */ + ret = sscanf(cpuid, "%*[^,],%u,%u,%u", &family, &model, &stepping); + if (ret == 3) { + arch->family = family; + arch->model = model; + arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ? + amd__ins_is_fused : + intel__ins_is_fused; + return 0; + } + + return -1; +} + +#ifdef HAVE_LIBDW_SUPPORT +static void invalidate_reg_state(struct type_state_reg *reg) +{ + reg->kind = TSR_KIND_INVALID; + reg->ok = false; + reg->lifetime_active = false; + reg->lifetime_end = 0; + reg->copied_from = -1; +} + +static void update_insn_state_x86(struct type_state *state, + struct data_loc_info *dloc, Dwarf_Die *cu_die, + struct disasm_line *dl) +{ + struct annotated_insn_loc loc; + struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE]; + struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET]; + struct type_state_reg *tsr; + Dwarf_Die type_die; + u32 insn_offset = dl->al.offset; + int fbreg = dloc->fbreg; + int fboff = 0; + + if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0) + return; + + if (ins__is_call(&dl->ins)) { + struct symbol *func = dl->ops.target.sym; + const char *call_name; + u64 call_addr; + + /* Try to resolve the call target name */ + if (func) + call_name = func->name; + else + call_name = dl->ops.target.name; + + /* __fentry__ will preserve all registers */ + if (call_name && !strcmp(call_name, "__fentry__")) + return; + + if (call_name) + pr_debug_dtp("call [%x] %s\n", insn_offset, call_name); + else + pr_debug_dtp("call [%x] <unknown>\n", insn_offset); + + /* Invalidate caller-saved registers after call */ + call_addr = map__rip_2objdump(dloc->ms->map, + dloc->ms->sym->start + dl->al.offset); + for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) { + struct type_state_reg *reg = &state->regs[i]; + + if (!reg->caller_saved) + continue; + /* Keep register valid within DWARF location lifetime */ + if (reg->lifetime_active && call_addr < reg->lifetime_end) + continue; + invalidate_reg_state(reg); + } + + /* Update register with the return type (if any) */ + if (call_name && die_find_func_rettype(cu_die, call_name, &type_die)) { + tsr = &state->regs[state->ret_reg]; + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("call [%x] return -> reg%d", + insn_offset, state->ret_reg); + pr_debug_type_name(&type_die, tsr->kind); + } + return; + } + + if (!strncmp(dl->ins.name, "add", 3)) { + u64 imm_value = -1ULL; + int offset; + const char *var_name = NULL; + struct map_symbol *ms = dloc->ms; + u64 ip = ms->sym->start + dl->al.offset; + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + tsr->copied_from = -1; + tsr->lifetime_active = false; + tsr->lifetime_end = 0; + + if (src->imm) + imm_value = src->offset; + else if (has_reg_type(state, src->reg1) && + state->regs[src->reg1].kind == TSR_KIND_CONST) + imm_value = state->regs[src->reg1].imm_value; + else if (src->reg1 == DWARF_REG_PC) { + u64 var_addr = annotate_calc_pcrel(dloc->ms, ip, + src->offset, dl); + + if (get_global_var_info(dloc, var_addr, + &var_name, &offset) && + !strcmp(var_name, "this_cpu_off") && + tsr->kind == TSR_KIND_CONST) { + tsr->kind = TSR_KIND_PERCPU_BASE; + tsr->offset = 0; + tsr->ok = true; + imm_value = tsr->imm_value; + } + } + else + return; + + /* Ignore add to non-pointer or non-const types */ + if (tsr->kind == TSR_KIND_POINTER || + (dwarf_tag(&tsr->type) == DW_TAG_pointer_type && + src->reg1 != DWARF_REG_PC && tsr->kind == TSR_KIND_TYPE && !dst->mem_ref)) { + tsr->offset += imm_value; + pr_debug_dtp("add [%x] offset %#"PRIx64" to reg%d", + insn_offset, imm_value, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + + if (tsr->kind == TSR_KIND_CONST) + tsr->imm_value += imm_value; + + if (tsr->kind != TSR_KIND_PERCPU_BASE) + return; + + if (get_global_var_type(cu_die, dloc, ip, imm_value, &offset, + &type_die) && offset == 0) { + /* + * This is not a pointer type, but it should be treated + * as a pointer. + */ + tsr->type = type_die; + tsr->kind = TSR_KIND_PERCPU_POINTER; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("add [%x] percpu %#"PRIx64" -> reg%d", + insn_offset, imm_value, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + return; + } + + if (!strncmp(dl->ins.name, "sub", 3)) { + u64 imm_value = -1ULL; + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + tsr->copied_from = -1; + tsr->lifetime_active = false; + tsr->lifetime_end = 0; + + if (src->imm) + imm_value = src->offset; + else if (has_reg_type(state, src->reg1) && + state->regs[src->reg1].kind == TSR_KIND_CONST) + imm_value = state->regs[src->reg1].imm_value; + + if (tsr->kind == TSR_KIND_POINTER || + (dwarf_tag(&tsr->type) == DW_TAG_pointer_type && + src->reg1 != DWARF_REG_PC && tsr->kind == TSR_KIND_TYPE && !dst->mem_ref)) { + tsr->offset -= imm_value; + pr_debug_dtp("sub [%x] offset %#"PRIx64" to reg%d", + insn_offset, imm_value, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + + if (tsr->kind == TSR_KIND_CONST) + tsr->imm_value -= imm_value; + + return; + } + + if (!strncmp(dl->ins.name, "lea", 3)) { + int sreg = src->reg1; + struct type_state_reg src_tsr; + + if (!has_reg_type(state, sreg) || + !has_reg_type(state, dst->reg1) || + !src->mem_ref) + return; + + src_tsr = state->regs[sreg]; + tsr = &state->regs[dst->reg1]; + + invalidate_reg_state(tsr); + + /* Case 1: Based on stack pointer or frame pointer */ + if (sreg == fbreg || sreg == state->stack_reg) { + struct type_state_stack *stack; + int offset = src->offset - fboff; + + stack = find_stack_state(state, offset); + if (!stack) + return; + + tsr->type = stack->type; + tsr->kind = TSR_KIND_POINTER; + tsr->offset = offset - stack->offset; + tsr->ok = true; + + if (sreg == fbreg) { + pr_debug_dtp("lea [%x] address of -%#x(stack) -> reg%d", + insn_offset, -src->offset, dst->reg1); + } else { + pr_debug_dtp("lea [%x] address of %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + } + + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Case 2: Based on a register holding a typed pointer */ + else if (src_tsr.ok && (src_tsr.kind == TSR_KIND_POINTER || + (dwarf_tag(&src_tsr.type) == DW_TAG_pointer_type && + src_tsr.kind == TSR_KIND_TYPE))) { + + if (src_tsr.kind == TSR_KIND_TYPE && + __die_get_real_type(&state->regs[sreg].type, &type_die) == NULL) + return; + + if (src_tsr.kind == TSR_KIND_POINTER) + type_die = state->regs[sreg].type; + + /* Check if the target type has a member at the new offset */ + if (die_get_member_type(&type_die, + src->offset + src_tsr.offset, &type_die) == NULL) + return; + + tsr->type = src_tsr.type; + tsr->kind = src_tsr.kind; + tsr->offset = src->offset + src_tsr.offset; + tsr->ok = true; + + pr_debug_dtp("lea [%x] address of %s%#x(reg%d) -> reg%d", + insn_offset, src->offset < 0 ? "-" : "", + abs(src->offset), sreg, dst->reg1); + + pr_debug_type_name(&tsr->type, tsr->kind); + } + return; + } + + /* Invalidate register states for other ops which may change pointers */ + if (has_reg_type(state, dst->reg1) && !dst->mem_ref && + dwarf_tag(&state->regs[dst->reg1].type) == DW_TAG_pointer_type) { + if (!strncmp(dl->ins.name, "imul", 4) || !strncmp(dl->ins.name, "mul", 3) || + !strncmp(dl->ins.name, "idiv", 4) || !strncmp(dl->ins.name, "div", 3) || + !strncmp(dl->ins.name, "shl", 3) || !strncmp(dl->ins.name, "shr", 3) || + !strncmp(dl->ins.name, "sar", 3) || !strncmp(dl->ins.name, "and", 3) || + !strncmp(dl->ins.name, "or", 2) || !strncmp(dl->ins.name, "neg", 3) || + !strncmp(dl->ins.name, "inc", 3) || !strncmp(dl->ins.name, "dec", 3)) { + pr_debug_dtp("%s [%x] invalidate reg%d\n", + dl->ins.name, insn_offset, dst->reg1); + invalidate_reg_state(&state->regs[dst->reg1]); + return; + } + + if (!strncmp(dl->ins.name, "xor", 3) && dst->reg1 == src->reg1) { + /* xor reg, reg clears the register */ + pr_debug_dtp("xor [%x] clear reg%d\n", + insn_offset, dst->reg1); + + state->regs[dst->reg1].kind = TSR_KIND_CONST; + state->regs[dst->reg1].imm_value = 0; + state->regs[dst->reg1].ok = true; + state->regs[dst->reg1].lifetime_active = false; + state->regs[dst->reg1].lifetime_end = 0; + state->regs[dst->reg1].copied_from = -1; + return; + } + } + + if (strncmp(dl->ins.name, "mov", 3)) + return; + + if (dloc->fb_cfa) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 pc = map__rip_2objdump(dloc->ms->map, ip); + + if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0) + fbreg = -1; + } + + /* Case 1. register to register or segment:offset to register transfers */ + if (!src->mem_ref && !dst->mem_ref) { + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + tsr->copied_from = -1; + + if (dso__kernel(map__dso(dloc->ms->map)) && + src->segment == INSN_SEG_X86_GS && src->imm) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 var_addr; + int offset; + + /* + * In kernel, %gs points to a per-cpu region for the + * current CPU. Access with a constant offset should + * be treated as a global variable access. + */ + var_addr = src->offset; + + if (var_addr == 40) { + tsr->kind = TSR_KIND_CANARY; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("mov [%x] stack canary -> reg%d\n", + insn_offset, dst->reg1); + return; + } + + if (!get_global_var_type(cu_die, dloc, ip, var_addr, + &offset, &type_die) || + !die_get_member_type(&type_die, offset, &type_die)) { + invalidate_reg_state(tsr); + return; + } + + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("mov [%x] this-cpu addr=%#"PRIx64" -> reg%d", + insn_offset, var_addr, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + return; + } + + if (src->imm) { + tsr->kind = TSR_KIND_CONST; + tsr->imm_value = src->offset; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("mov [%x] imm=%#x -> reg%d\n", + insn_offset, tsr->imm_value, dst->reg1); + return; + } + + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) { + invalidate_reg_state(tsr); + return; + } + + tsr->type = state->regs[src->reg1].type; + tsr->kind = state->regs[src->reg1].kind; + tsr->imm_value = state->regs[src->reg1].imm_value; + tsr->offset = state->regs[src->reg1].offset; + tsr->lifetime_active = state->regs[src->reg1].lifetime_active; + tsr->lifetime_end = state->regs[src->reg1].lifetime_end; + tsr->ok = true; + + /* To copy back the variable type later (hopefully) */ + if (tsr->kind == TSR_KIND_TYPE || tsr->kind == TSR_KIND_POINTER) + tsr->copied_from = src->reg1; + + pr_debug_dtp("mov [%x] reg%d -> reg%d", + insn_offset, src->reg1, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Case 2. memory to register transers */ + if (src->mem_ref && !dst->mem_ref) { + int sreg = src->reg1; + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + tsr->copied_from = -1; + +retry: + /* Check stack variables with offset */ + if (sreg == fbreg || sreg == state->stack_reg) { + struct type_state_stack *stack; + int offset = src->offset - fboff; + + stack = find_stack_state(state, offset); + if (stack == NULL) { + invalidate_reg_state(tsr); + return; + } else if (!stack->compound) { + tsr->type = stack->type; + tsr->kind = stack->kind; + tsr->offset = stack->ptr_offset; + tsr->ok = true; + } else if (die_get_member_type(&stack->type, + offset - stack->offset, + &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = 0; + tsr->ok = true; + } else { + invalidate_reg_state(tsr); + return; + } + + if (sreg == fbreg) { + pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d", + insn_offset, -offset, dst->reg1); + } else { + pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d", + insn_offset, offset, sreg, dst->reg1); + } + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* And then dereference the pointer if it has one */ + else if (has_reg_type(state, sreg) && state->regs[sreg].ok && + state->regs[sreg].kind == TSR_KIND_TYPE && + die_deref_ptr_type(&state->regs[sreg].type, + src->offset + state->regs[sreg].offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Handle dereference of TSR_KIND_POINTER registers */ + else if (has_reg_type(state, sreg) && state->regs[sreg].ok && + state->regs[sreg].kind == TSR_KIND_POINTER && + die_get_member_type(&state->regs[sreg].type, + src->offset + state->regs[sreg].offset, &type_die)) { + tsr->type = state->regs[sreg].type; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = src->offset + state->regs[sreg].offset; + tsr->ok = true; + + pr_debug_dtp("mov [%x] addr %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Or check if it's a global variable */ + else if (sreg == DWARF_REG_PC) { + struct map_symbol *ms = dloc->ms; + u64 ip = ms->sym->start + dl->al.offset; + u64 addr; + int offset; + + addr = annotate_calc_pcrel(ms, ip, src->offset, dl); + + if (!get_global_var_type(cu_die, dloc, ip, addr, &offset, + &type_die) || + !die_get_member_type(&type_die, offset, &type_die)) { + invalidate_reg_state(tsr); + return; + } + + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d", + insn_offset, addr, dst->reg1); + pr_debug_type_name(&type_die, tsr->kind); + } + /* And check percpu access with base register */ + else if (has_reg_type(state, sreg) && + state->regs[sreg].kind == TSR_KIND_PERCPU_BASE) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 var_addr = src->offset; + int offset; + + if (src->multi_regs) { + int reg2 = (sreg == src->reg1) ? src->reg2 : src->reg1; + + if (has_reg_type(state, reg2) && state->regs[reg2].ok && + state->regs[reg2].kind == TSR_KIND_CONST) + var_addr += state->regs[reg2].imm_value; + } + + /* + * In kernel, %gs points to a per-cpu region for the + * current CPU. Access with a constant offset should + * be treated as a global variable access. + */ + if (get_global_var_type(cu_die, dloc, ip, var_addr, + &offset, &type_die) && + die_get_member_type(&type_die, offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = 0; + tsr->ok = true; + + if (src->multi_regs) { + pr_debug_dtp("mov [%x] percpu %#x(reg%d,reg%d) -> reg%d", + insn_offset, src->offset, src->reg1, + src->reg2, dst->reg1); + } else { + pr_debug_dtp("mov [%x] percpu %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + } + pr_debug_type_name(&tsr->type, tsr->kind); + } else { + invalidate_reg_state(tsr); + } + } + /* And then dereference the calculated pointer if it has one */ + else if (has_reg_type(state, sreg) && state->regs[sreg].ok && + state->regs[sreg].kind == TSR_KIND_PERCPU_POINTER && + die_get_member_type(&state->regs[sreg].type, + src->offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("mov [%x] pointer %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Or try another register if any */ + else if (src->multi_regs && sreg == src->reg1 && + src->reg1 != src->reg2) { + sreg = src->reg2; + goto retry; + } + else { + int offset; + const char *var_name = NULL; + + /* it might be per-cpu variable (in kernel) access */ + if (src->offset < 0) { + if (get_global_var_info(dloc, (s64)src->offset, + &var_name, &offset) && + !strcmp(var_name, "__per_cpu_offset")) { + tsr->kind = TSR_KIND_PERCPU_BASE; + tsr->offset = 0; + tsr->ok = true; + + pr_debug_dtp("mov [%x] percpu base reg%d\n", + insn_offset, dst->reg1); + return; + } + } + + invalidate_reg_state(tsr); + } + } + /* Case 3. register to memory transfers */ + if (!src->mem_ref && dst->mem_ref) { + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) + return; + + /* Check stack variables with offset */ + if (dst->reg1 == fbreg || dst->reg1 == state->stack_reg) { + struct type_state_stack *stack; + int offset = dst->offset - fboff; + + tsr = &state->regs[src->reg1]; + + stack = find_stack_state(state, offset); + if (stack) { + /* + * The source register is likely to hold a type + * of member if it's a compound type. Do not + * update the stack variable type since we can + * get the member type later by using the + * die_get_member_type(). + */ + if (!stack->compound) + set_stack_state(stack, offset, tsr->kind, + &tsr->type, tsr->offset); + } else { + findnew_stack_state(state, offset, tsr->kind, + &tsr->type, tsr->offset); + } + + if (dst->reg1 == fbreg) { + pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)", + insn_offset, src->reg1, -offset); + } else { + pr_debug_dtp("mov [%x] reg%d -> %#x(reg%d)", + insn_offset, src->reg1, offset, dst->reg1); + } + if (tsr->offset != 0) { + pr_debug_dtp(" reg%d offset %#x ->", + src->reg1, tsr->offset); + } + + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* + * Ignore other transfers since it'd set a value in a struct + * and won't change the type. + */ + } + /* Case 4. memory to memory transfers (not handled for now) */ +} +#endif + +const struct arch *arch__new_x86(const struct e_machine_and_e_flags *id, const char *cpuid) +{ + struct arch *arch = zalloc(sizeof(*arch)); + + if (!arch) + return NULL; + + arch->name = "x86"; + arch->id = *id; + if (cpuid) { + if (x86__cpuid_parse(arch, cpuid)) { + errno = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING; + return NULL; + } + } + arch->instructions = x86__instructions; + arch->nr_instructions = ARRAY_SIZE(x86__instructions); +#ifndef NDEBUG + { + static bool sorted_check; + + if (!sorted_check) { + for (size_t i = 0; i < arch->nr_instructions - 1; i++) { + assert(strcmp(arch->instructions[i].name, + arch->instructions[i + 1].name) <= 0); + } + sorted_check = true; + } + } +#endif + arch->sorted_instructions = true; + arch->objdump.comment_char = '#'; + arch->objdump.register_char = '%'; + arch->objdump.memory_ref_char = '('; + arch->objdump.imm_char = '$'; + arch->insn_suffix = "bwlq"; +#ifdef HAVE_LIBDW_SUPPORT + arch->update_insn_state = update_insn_state_x86; +#endif + return arch; +} diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c index 976abedca09e..1eff0a27237d 100644 --- a/tools/perf/util/annotate-data.c +++ b/tools/perf/util/annotate-data.c @@ -4,7 +4,7 @@ * * Written by Namhyung Kim <namhyung@kernel.org> */ - +#include <errno.h> #include <stdio.h> #include <stdlib.h> #include <inttypes.h> @@ -58,6 +58,10 @@ void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind) case TSR_KIND_CONST: pr_info(" constant\n"); return; + case TSR_KIND_PERCPU_POINTER: + pr_info(" percpu pointer"); + /* it also prints the type info */ + break; case TSR_KIND_POINTER: pr_info(" pointer"); /* it also prints the type info */ @@ -156,12 +160,12 @@ bool has_reg_type(struct type_state *state, int reg) return (unsigned)reg < ARRAY_SIZE(state->regs); } -static void init_type_state(struct type_state *state, struct arch *arch) +static void init_type_state(struct type_state *state, const struct arch *arch) { memset(state, 0, sizeof(*state)); INIT_LIST_HEAD(&state->stack_vars); - if (arch__is(arch, "x86")) { + if (arch__is_x86(arch)) { state->regs[0].caller_saved = true; state->regs[1].caller_saved = true; state->regs[2].caller_saved = true; @@ -314,6 +318,40 @@ static void delete_members(struct annotated_member *member) } } +static int fill_member_name(char *buf, size_t sz, struct annotated_member *m, + int offset, bool first) +{ + struct annotated_member *child; + + if (list_empty(&m->children)) + return 0; + + list_for_each_entry(child, &m->children, node) { + int len; + + if (offset < child->offset || offset >= child->offset + child->size) + continue; + + /* It can have anonymous struct/union members */ + if (child->var_name) { + len = scnprintf(buf, sz, "%s%s", + first ? "" : ".", child->var_name); + first = false; + } else { + len = 0; + } + + return fill_member_name(buf + len, sz - len, child, offset, first) + len; + } + return 0; +} + +int annotated_data_type__get_member_name(struct annotated_data_type *adt, + char *buf, size_t sz, int member_offset) +{ + return fill_member_name(buf, sz, &adt->self, member_offset, /*first=*/true); +} + static struct annotated_data_type *dso__findnew_data_type(struct dso *dso, Dwarf_Die *type_die) { @@ -417,13 +455,6 @@ static const char *match_result_str(enum type_match_result tmr) } } -static bool is_pointer_type(Dwarf_Die *type_die) -{ - int tag = dwarf_tag(type_die); - - return tag == DW_TAG_pointer_type || tag == DW_TAG_array_type; -} - static bool is_compound_type(Dwarf_Die *type_die) { int tag = dwarf_tag(type_die); @@ -436,19 +467,24 @@ static bool is_better_type(Dwarf_Die *type_a, Dwarf_Die *type_b) { Dwarf_Word size_a, size_b; Dwarf_Die die_a, die_b; + Dwarf_Die ptr_a, ptr_b; + Dwarf_Die *ptr_type_a, *ptr_type_b; + + ptr_type_a = die_get_pointer_type(type_a, &ptr_a); + ptr_type_b = die_get_pointer_type(type_b, &ptr_b); /* pointer type is preferred */ - if (is_pointer_type(type_a) != is_pointer_type(type_b)) - return is_pointer_type(type_b); + if ((ptr_type_a != NULL) != (ptr_type_b != NULL)) + return ptr_type_b != NULL; - if (is_pointer_type(type_b)) { + if (ptr_type_b) { /* * We want to compare the target type, but 'void *' can fail to * get the target type. */ - if (die_get_real_type(type_a, &die_a) == NULL) + if (die_get_real_type(ptr_type_a, &die_a) == NULL) return true; - if (die_get_real_type(type_b, &die_b) == NULL) + if (die_get_real_type(ptr_type_b, &die_b) == NULL) return false; type_a = &die_a; @@ -488,7 +524,7 @@ static enum type_match_result check_variable(struct data_loc_info *dloc, needs_pointer = false; else if (reg == dloc->fbreg || is_fbreg) needs_pointer = false; - else if (arch__is(dloc->arch, "x86") && reg == X86_REG_SP) + else if (arch__is_x86(dloc->arch) && reg == X86_REG_SP) needs_pointer = false; /* Get the type of the variable */ @@ -501,7 +537,7 @@ static enum type_match_result check_variable(struct data_loc_info *dloc, * and local variables are accessed directly without a pointer. */ if (needs_pointer) { - if (!is_pointer_type(type_die) || + if (die_get_pointer_type(type_die, type_die) == NULL || __die_get_real_type(type_die, type_die) == NULL) return PERF_TMR_NO_POINTER; } @@ -539,25 +575,35 @@ struct type_state_stack *find_stack_state(struct type_state *state, } void set_stack_state(struct type_state_stack *stack, int offset, u8 kind, - Dwarf_Die *type_die) + Dwarf_Die *type_die, int ptr_offset) { int tag; Dwarf_Word size; - if (dwarf_aggregate_size(type_die, &size) < 0) + if (kind == TSR_KIND_POINTER) { + /* TODO: arch-dependent pointer size */ + size = sizeof(void *); + } + else if (dwarf_aggregate_size(type_die, &size) < 0) size = 0; - tag = dwarf_tag(type_die); - stack->type = *type_die; stack->size = size; stack->offset = offset; + stack->ptr_offset = ptr_offset; stack->kind = kind; + if (kind == TSR_KIND_POINTER) { + stack->compound = false; + return; + } + + tag = dwarf_tag(type_die); + switch (tag) { case DW_TAG_structure_type: case DW_TAG_union_type: - stack->compound = (kind != TSR_KIND_POINTER); + stack->compound = (kind != TSR_KIND_PERCPU_POINTER); break; default: stack->compound = false; @@ -567,18 +613,19 @@ void set_stack_state(struct type_state_stack *stack, int offset, u8 kind, struct type_state_stack *findnew_stack_state(struct type_state *state, int offset, u8 kind, - Dwarf_Die *type_die) + Dwarf_Die *type_die, + int ptr_offset) { struct type_state_stack *stack = find_stack_state(state, offset); if (stack) { - set_stack_state(stack, offset, kind, type_die); + set_stack_state(stack, offset, kind, type_die, ptr_offset); return stack; } stack = malloc(sizeof(*stack)); if (stack) { - set_stack_state(stack, offset, kind, type_die); + set_stack_state(stack, offset, kind, type_die, ptr_offset); list_add(&stack->list, &state->stack_vars); } return stack; @@ -727,12 +774,7 @@ static void global_var__collect(struct data_loc_info *dloc) if (!dwarf_offdie(dwarf, pos->die_off, &type_die)) continue; - if (!get_global_var_info(dloc, pos->addr, &var_name, - &var_offset)) - continue; - - if (var_offset != 0) - continue; + get_global_var_info(dloc, pos->addr, &var_name, &var_offset); global_var__add(dloc, pos->addr, var_name, &type_die); } @@ -767,9 +809,8 @@ bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc, } /* Try to get the variable by address first */ - if (die_find_variable_by_addr(cu_die, var_addr, &var_die, &offset) && - check_variable(dloc, &var_die, type_die, DWARF_REG_PC, offset, - /*is_fbreg=*/false) == PERF_TMR_OK) { + if (die_find_variable_by_addr(cu_die, var_addr, &var_die, type_die, + &offset)) { var_name = dwarf_diename(&var_die); *var_offset = offset; goto ok; @@ -799,6 +840,18 @@ static bool die_is_same(Dwarf_Die *die_a, Dwarf_Die *die_b) return (die_a->cu == die_b->cu) && (die_a->addr == die_b->addr); } +static void tsr_set_lifetime(struct type_state_reg *tsr, + const struct die_var_type *var) +{ + if (var && var->has_range && var->end > var->addr) { + tsr->lifetime_active = true; + tsr->lifetime_end = var->end; + } else { + tsr->lifetime_active = false; + tsr->lifetime_end = 0; + } +} + /** * update_var_state - Update type state using given variables * @state: type state table @@ -824,16 +877,31 @@ static void update_var_state(struct type_state *state, struct data_loc_info *dlo } for (var = var_types; var != NULL; var = var->next) { - if (var->addr != addr) - continue; + /* Check if addr falls within the variable's valid range */ + if (var->has_range) { + if (addr < var->addr || (var->end && addr >= var->end)) + continue; + } else { + if (addr != var->addr) + continue; + } /* Get the type DIE using the offset */ if (!dwarf_offdie(dloc->di->dbg, var->die_off, &mem_die)) continue; - if (var->reg == DWARF_REG_FB || var->reg == fbreg) { + if (var->reg == DWARF_REG_FB || var->reg == fbreg || var->reg == state->stack_reg) { + Dwarf_Die ptr_die; + Dwarf_Die *ptr_type; int offset = var->offset; struct type_state_stack *stack; + ptr_type = die_get_pointer_type(&mem_die, &ptr_die); + + /* If the reg location holds the pointer value, dereference the type */ + if (!var->is_reg_var_addr && ptr_type && + __die_get_real_type(ptr_type, &mem_die) == NULL) + continue; + if (var->reg != DWARF_REG_FB) offset -= fb_offset; @@ -843,29 +911,57 @@ static void update_var_state(struct type_state *state, struct data_loc_info *dlo continue; findnew_stack_state(state, offset, TSR_KIND_TYPE, - &mem_die); + &mem_die, /*ptr_offset=*/0); - pr_debug_dtp("var [%"PRIx64"] -%#x(stack)", - insn_offset, -offset); + if (var->reg == state->stack_reg) { + pr_debug_dtp("var [%"PRIx64"] %#x(reg%d)", + insn_offset, offset, state->stack_reg); + } else { + pr_debug_dtp("var [%"PRIx64"] -%#x(stack)", + insn_offset, -offset); + } pr_debug_type_name(&mem_die, TSR_KIND_TYPE); - } else if (has_reg_type(state, var->reg) && var->offset == 0) { + } else if (has_reg_type(state, var->reg)) { struct type_state_reg *reg; Dwarf_Die orig_type; reg = &state->regs[var->reg]; if (reg->ok && reg->kind == TSR_KIND_TYPE && - !is_better_type(®->type, &mem_die)) + (!is_better_type(®->type, &mem_die) || var->is_reg_var_addr)) continue; - orig_type = reg->type; + /* Handle address registers with TSR_KIND_POINTER */ + if (var->is_reg_var_addr) { + if (reg->ok && reg->kind == TSR_KIND_POINTER && + !is_better_type(®->type, &mem_die)) + continue; + + reg->offset = -var->offset; + reg->type = mem_die; + reg->kind = TSR_KIND_POINTER; + reg->ok = true; + tsr_set_lifetime(reg, var); + + pr_debug_dtp("var [%"PRIx64"] reg%d addr offset %x", + insn_offset, var->reg, var->offset); + pr_debug_type_name(&mem_die, TSR_KIND_POINTER); + continue; + } + orig_type = reg->type; + /* + * var->offset + reg value is the beginning of the struct + * reg->offset is the offset the reg points + */ + reg->offset = -var->offset; reg->type = mem_die; reg->kind = TSR_KIND_TYPE; reg->ok = true; + tsr_set_lifetime(reg, var); - pr_debug_dtp("var [%"PRIx64"] reg%d", - insn_offset, var->reg); + pr_debug_dtp("var [%"PRIx64"] reg%d offset %x", + insn_offset, var->reg, var->offset); pr_debug_type_name(&mem_die, TSR_KIND_TYPE); /* @@ -991,7 +1087,7 @@ static void delete_var_types(struct die_var_type *var_types) /* should match to is_stack_canary() in util/annotate.c */ static void setup_stack_canary(struct data_loc_info *dloc) { - if (arch__is(dloc->arch, "x86")) { + if (arch__is_x86(dloc->arch)) { dloc->op->segment = INSN_SEG_X86_GS; dloc->op->imm = true; dloc->op->offset = 40; @@ -1030,7 +1126,9 @@ again: goto check_non_register; if (state->regs[reg].kind == TSR_KIND_TYPE) { + Dwarf_Die ptr_die; Dwarf_Die sized_type; + Dwarf_Die *ptr_type; struct strbuf sb; strbuf_init(&sb, 32); @@ -1042,7 +1140,8 @@ again: * Normal registers should hold a pointer (or array) to * dereference a memory location. */ - if (!is_pointer_type(&state->regs[reg].type)) { + ptr_type = die_get_pointer_type(&state->regs[reg].type, &ptr_die); + if (!ptr_type) { if (dloc->op->offset < 0 && reg != state->stack_reg) goto check_kernel; @@ -1050,10 +1149,10 @@ again: } /* Remove the pointer and get the target type */ - if (__die_get_real_type(&state->regs[reg].type, type_die) == NULL) + if (__die_get_real_type(ptr_type, type_die) == NULL) return PERF_TMR_NO_POINTER; - dloc->type_offset = dloc->op->offset; + dloc->type_offset = dloc->op->offset + state->regs[reg].offset; if (dwarf_tag(type_die) == DW_TAG_typedef) die_get_real_type(type_die, &sized_type); @@ -1069,6 +1168,30 @@ again: } if (state->regs[reg].kind == TSR_KIND_POINTER) { + struct strbuf sb; + + strbuf_init(&sb, 32); + die_get_typename_from_type(&state->regs[reg].type, &sb); + pr_debug_dtp("(ptr->%s)", sb.buf); + strbuf_release(&sb); + + /* + * Register holds a pointer (address) to the target variable. + * The type is the type of the variable it points to. + */ + *type_die = state->regs[reg].type; + + dloc->type_offset = dloc->op->offset + state->regs[reg].offset; + + /* Get the size of the actual type */ + if (dwarf_aggregate_size(type_die, &size) < 0 || + (unsigned)dloc->type_offset >= size) + return PERF_TMR_BAD_OFFSET; + + return PERF_TMR_OK; + } + + if (state->regs[reg].kind == TSR_KIND_PERCPU_POINTER) { pr_debug_dtp("percpu ptr"); /* @@ -1126,11 +1249,16 @@ again: return PERF_TMR_BAIL_OUT; } + if (state->regs[reg].kind == TSR_KIND_CONST && + dso__kernel(map__dso(dloc->ms->map))) { + if (dloc->op->offset < 0 && reg != state->stack_reg && reg != dloc->fbreg) + goto check_kernel; + } check_non_register: - if (reg == dloc->fbreg) { + if (reg == dloc->fbreg || reg == state->stack_reg) { struct type_state_stack *stack; - pr_debug_dtp("fbreg"); + pr_debug_dtp("%s", reg == dloc->fbreg ? "fbreg" : "stack"); stack = find_stack_state(state, dloc->type_offset); if (stack == NULL) { @@ -1207,7 +1335,7 @@ check_kernel: /* Direct this-cpu access like "%gs:0x34740" */ if (dloc->op->segment == INSN_SEG_X86_GS && dloc->op->imm && - arch__is(dloc->arch, "x86")) { + arch__is_x86(dloc->arch)) { pr_debug_dtp("this-cpu var"); addr = dloc->op->offset; @@ -1293,7 +1421,7 @@ out: static int arch_supports_insn_tracking(struct data_loc_info *dloc) { - if ((arch__is(dloc->arch, "x86")) || (arch__is(dloc->arch, "powerpc"))) + if ((arch__is_x86(dloc->arch)) || (arch__is_powerpc(dloc->arch))) return 1; return 0; } @@ -1497,12 +1625,13 @@ retry: if (reg == DWARF_REG_PC) { if (!die_find_variable_by_addr(&scopes[i], dloc->var_addr, - &var_die, &type_offset)) + &var_die, &mem_die, + &type_offset)) continue; } else { /* Look up variables/parameters in this scope */ if (!die_find_variable_by_reg(&scopes[i], pc, reg, - &type_offset, is_fbreg, &var_die)) + &mem_die, &type_offset, is_fbreg, &var_die)) continue; } @@ -1510,26 +1639,22 @@ retry: dwarf_diename(&var_die), (long)dwarf_dieoffset(&var_die), i+1, nr_scopes, (long)dwarf_dieoffset(&scopes[i])); - /* Found a variable, see if it's correct */ - result = check_variable(dloc, &var_die, &mem_die, reg, type_offset, is_fbreg); - if (result == PERF_TMR_OK) { - if (reg == DWARF_REG_PC) { - pr_debug_dtp("addr=%#"PRIx64" type_offset=%#x\n", - dloc->var_addr, type_offset); - } else if (reg == DWARF_REG_FB || is_fbreg) { - pr_debug_dtp("stack_offset=%#x type_offset=%#x\n", - fb_offset, type_offset); - } else { - pr_debug_dtp("type_offset=%#x\n", type_offset); - } - - if (!found || is_better_type(type_die, &mem_die)) { - *type_die = mem_die; - dloc->type_offset = type_offset; - found = true; - } + if (reg == DWARF_REG_PC) { + pr_debug_dtp("addr=%#"PRIx64" type_offset=%#x\n", + dloc->var_addr, type_offset); + } else if (reg == DWARF_REG_FB || is_fbreg) { + pr_debug_dtp("stack_offset=%#x type_offset=%#x\n", + fb_offset, type_offset); } else { - pr_debug_dtp("failed: %s\n", match_result_str(result)); + pr_debug_dtp("type_offset=%#x\n", type_offset); + } + + if (!found || dloc->type_offset < type_offset || + (dloc->type_offset == type_offset && + !is_better_type(&mem_die, type_die))) { + *type_die = mem_die; + dloc->type_offset = type_offset; + found = true; } pr_debug_location(&var_die, pc, reg); diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h index 98c80b2268dd..c26130744260 100644 --- a/tools/perf/util/annotate-data.h +++ b/tools/perf/util/annotate-data.h @@ -34,6 +34,7 @@ enum type_state_kind { TSR_KIND_TYPE, TSR_KIND_PERCPU_BASE, TSR_KIND_CONST, + TSR_KIND_PERCPU_POINTER, TSR_KIND_POINTER, TSR_KIND_CANARY, }; @@ -116,7 +117,7 @@ extern struct annotated_data_type canary_type; */ struct data_loc_info { /* These are input field, should be filled by caller */ - struct arch *arch; + const struct arch *arch; struct thread *thread; struct map_symbol *ms; u64 ip; @@ -173,8 +174,17 @@ extern struct annotated_data_stat ann_data_stat; struct type_state_reg { Dwarf_Die type; u32 imm_value; + /* + * The offset within the struct that the register points to. + * A value of 0 means the register points to the beginning. + * type_offset = op->offset + reg->offset + */ + s32 offset; bool ok; bool caller_saved; + /* DWARF location range tracking for register lifetime */ + bool lifetime_active; + u64 lifetime_end; u8 kind; u8 copied_from; }; @@ -184,17 +194,22 @@ struct type_state_stack { struct list_head list; Dwarf_Die type; int offset; + /* pointer offset, saves tsr->offset on the stack state */ + int ptr_offset; int size; bool compound; u8 kind; }; -/* FIXME: This should be arch-dependent */ -#ifdef __powerpc__ +/* + * Maximum number of registers tracked in type_state. + * + * This limit must cover all supported architectures, since perf + * may analyze perf.data files generated on systems with a different + * register set. Use 32 as a safe upper bound instead of relying on + * build-arch specific values. + */ #define TYPE_STATE_MAX_REGS 32 -#else -#define TYPE_STATE_MAX_REGS 16 -#endif /* * State table to maintain type info in each register and stack location. @@ -227,14 +242,20 @@ void annotated_data_type__tree_delete(struct rb_root *root); /* Release all global variable information in the tree */ void global_var_type__tree_delete(struct rb_root *root); +/* Print data type annotation (including members) on stdout */ int hist_entry__annotate_data_tty(struct hist_entry *he, struct evsel *evsel); +/* Get name of member field at the given offset in the data type */ +int annotated_data_type__get_member_name(struct annotated_data_type *adt, + char *buf, size_t sz, int member_offset); + bool has_reg_type(struct type_state *state, int reg); struct type_state_stack *findnew_stack_state(struct type_state *state, int offset, u8 kind, - Dwarf_Die *type_die); + Dwarf_Die *type_die, + int ptr_offset); void set_stack_state(struct type_state_stack *stack, int offset, u8 kind, - Dwarf_Die *type_die); + Dwarf_Die *type_die, int ptr_offset); struct type_state_stack *find_stack_state(struct type_state *state, int offset); bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc, @@ -276,6 +297,14 @@ static inline int hist_entry__annotate_data_tty(struct hist_entry *he __maybe_un return -1; } +static inline int annotated_data_type__get_member_name(struct annotated_data_type *adt __maybe_unused, + char *buf __maybe_unused, + size_t sz __maybe_unused, + int member_offset __maybe_unused) +{ + return -1; +} + #endif /* HAVE_LIBDW_SUPPORT */ #ifdef HAVE_SLANG_SUPPORT diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 31bb326b07a6..e745f3034a0e 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -8,7 +8,6 @@ #include <errno.h> #include <inttypes.h> -#include <libgen.h> #include <stdlib.h> #include "util.h" // hex_width() #include "ui/ui.h" @@ -44,6 +43,7 @@ #include "strbuf.h" #include <regex.h> #include <linux/bitops.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/zalloc.h> @@ -87,6 +87,8 @@ struct annotated_data_type canary_type = { }, }; +#define NO_TYPE ((struct annotated_data_type *)-1UL) + /* symbol histogram: key = offset << 16 | evsel->core.idx */ static size_t sym_hist_hash(long key, void *ctx __maybe_unused) { @@ -135,8 +137,10 @@ static int annotated_source__alloc_histograms(struct annotated_source *src, return -1; src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL); - if (src->samples == NULL) + if (IS_ERR(src->samples)) { zfree(&src->histograms); + src->samples = NULL; + } return src->histograms ? 0 : -1; } @@ -758,15 +762,33 @@ static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_wi return 0; } +static struct annotated_data_type * +__hist_entry__get_data_type(struct hist_entry *he, const struct arch *arch, + struct debuginfo *dbg, struct disasm_line *dl, + int *type_offset); + +static bool needs_type_info(struct annotated_data_type *data_type) +{ + if (data_type == NULL || data_type == NO_TYPE) + return false; + + if (verbose) + return true; + + return (data_type != &stackop_type) && (data_type != &canary_type); +} + static int -annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start, - struct evsel *evsel, u64 len, int min_pcnt, int printed, - int max_lines, struct annotation_line *queue, int addr_fmt_width, - int percent_type) +annotation_line__print(struct annotation_line *al, struct annotation_print_data *apd, + struct annotation_options *opts, int printed, + struct annotation_line *queue) { + struct symbol *sym = apd->he->ms.sym; struct disasm_line *dl = container_of(al, struct disasm_line, al); struct annotation *notes = symbol__annotation(sym); static const char *prev_line; + int max_lines = opts->max_lines; + int percent_type = opts->percent_type; if (al->offset != -1) { double max_percent = 0.0; @@ -786,19 +808,23 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start if (al->data_nr > nr_percent) nr_percent = al->data_nr; - if (max_percent < min_pcnt) + if (max_percent < opts->min_pcnt) return -1; if (max_lines && printed >= max_lines) return 1; if (queue != NULL) { + struct annotation_options queue_opts = { + .max_lines = 1, + .percent_type = percent_type, + }; + list_for_each_entry_from(queue, ¬es->src->source, node) { if (queue == al) break; - annotation_line__print(queue, sym, start, evsel, len, - 0, 0, 1, NULL, addr_fmt_width, - percent_type); + annotation_line__print(queue, apd, &queue_opts, + /*printed=*/0, /*queue=*/NULL); } } @@ -823,7 +849,31 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start printf(" : "); - disasm_line__print(dl, start, addr_fmt_width); + disasm_line__print(dl, notes->src->start, apd->addr_fmt_width); + + if (opts->code_with_type && apd->dbg) { + struct annotated_data_type *data_type; + int offset = 0; + + data_type = __hist_entry__get_data_type(apd->he, apd->arch, + apd->dbg, dl, &offset); + if (needs_type_info(data_type)) { + char buf[4096]; + + printf("\t\t# data-type: %s", + data_type->self.type_name); + + if (data_type != &stackop_type && + data_type != &canary_type) + printf(" +%#x", offset); + + if (annotated_data_type__get_member_name(data_type, + buf, + sizeof(buf), + offset)) + printf(" (%s)", buf); + } + } /* * Also color the filename and line if needed, with @@ -849,7 +899,8 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start if (!*al->line) printf(" %*s:\n", width, " "); else - printf(" %*s: %-*d %s\n", width, " ", addr_fmt_width, al->line_nr, al->line); + printf(" %*s: %-*d %s\n", width, " ", apd->addr_fmt_width, + al->line_nr, al->line); } return 0; @@ -931,49 +982,44 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel) annotation__calc_percent(notes, evsel, symbol__size(sym)); } -static int evsel__get_arch(struct evsel *evsel, struct arch **parch) +int thread__get_arch(struct thread *thread, const struct arch **parch) { - struct perf_env *env = evsel__env(evsel); - const char *arch_name = perf_env__arch(env); - struct arch *arch; - int err; + const struct arch *arch; + struct machine *machine; + uint32_t e_flags; + uint16_t e_machine; - if (!arch_name) { + if (!thread) { *parch = NULL; - return errno; + return -1; } - *parch = arch = arch__find(arch_name); + machine = maps__machine(thread__maps(thread)); + e_machine = thread__e_machine(thread, machine, &e_flags); + arch = arch__find(e_machine, e_flags, machine->env ? machine->env->cpuid : NULL); if (arch == NULL) { - pr_err("%s: unsupported arch %s\n", __func__, arch_name); - return ENOTSUP; + pr_err("%s: unsupported arch %d\n", __func__, e_machine); + return errno; } + if (parch) + *parch = arch; - if (arch->init) { - err = arch->init(arch, env ? env->cpuid : NULL); - if (err) { - pr_err("%s: failed to initialize %s arch priv area\n", - __func__, arch->name); - return err; - } - } return 0; } int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, - struct arch **parch) + const struct arch **parch) { struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); struct annotate_args args = { - .evsel = evsel, .options = &annotate_opts, }; - struct arch *arch = NULL; + const struct arch *arch = NULL; int err, nr; - err = evsel__get_arch(evsel, &arch); - if (err < 0) + err = thread__get_arch(ms->thread, &arch); + if (err) return err; if (parch) @@ -983,7 +1029,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, return 0; args.arch = arch; - args.ms = *ms; + args.ms = ms; if (notes->src == NULL) { notes->src = annotated_source__new(); @@ -1167,8 +1213,9 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) return 0; } -int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) +int hist_entry__annotate_printf(struct hist_entry *he, struct evsel *evsel) { + struct map_symbol *ms = &he->ms; struct map *map = ms->map; struct symbol *sym = ms->sym; struct dso *dso = map__dso(map); @@ -1179,11 +1226,13 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) struct sym_hist *h = annotation__histogram(notes, evsel); struct annotation_line *pos, *queue = NULL; struct annotation_options *opts = &annotate_opts; - u64 start = map__rip_2objdump(map, sym->start); - int printed = 2, queue_len = 0, addr_fmt_width; + struct annotation_print_data apd = { + .he = he, + .evsel = evsel, + }; + int printed = 2, queue_len = 0; int more = 0; bool context = opts->context; - u64 len; int width = annotation__pcnt_width(notes); int graph_dotted_len; char buf[512]; @@ -1195,9 +1244,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) if (opts->full_path) d_filename = filename; else - d_filename = basename(filename); - - len = symbol__size(sym); + d_filename = perf_basename(filename); if (evsel__is_group_event(evsel)) { evsel__group_desc(evsel, buf, sizeof(buf)); @@ -1217,7 +1264,10 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) if (verbose > 0) symbol__annotate_hits(sym, evsel); - addr_fmt_width = annotated_source__addr_fmt_width(¬es->src->source, start); + apd.addr_fmt_width = annotated_source__addr_fmt_width(¬es->src->source, + notes->src->start); + thread__get_arch(ms->thread, &apd.arch); + apd.dbg = dso__debuginfo(dso); list_for_each_entry(pos, ¬es->src->source, node) { int err; @@ -1227,9 +1277,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) queue_len = 0; } - err = annotation_line__print(pos, sym, start, evsel, len, - opts->min_pcnt, printed, opts->max_lines, - queue, addr_fmt_width, opts->percent_type); + err = annotation_line__print(pos, &apd, opts, printed, queue); switch (err) { case 0: @@ -1260,6 +1308,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) } } + debuginfo__delete(apd.dbg); free(filename); return more; @@ -1306,7 +1355,8 @@ static void FILE__write_graph(void *fp, int graph) fputs(s, fp); } -static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp) +static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, + struct annotation_print_data *apd) { struct annotation *notes = symbol__annotation(sym); struct annotation_write_ops wops = { @@ -1320,24 +1370,37 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp) }; struct annotation_line *al; + if (annotate_opts.code_with_type) { + thread__get_arch(apd->he->ms.thread, &apd->arch); + apd->dbg = dso__debuginfo(map__dso(apd->he->ms.map)); + } + list_for_each_entry(al, ¬es->src->source, node) { if (annotation_line__filter(al)) continue; - annotation_line__write(al, notes, &wops); + annotation_line__write(al, notes, &wops, apd); fputc('\n', fp); wops.first_line = false; } + if (annotate_opts.code_with_type) + debuginfo__delete(apd->dbg); + return 0; } -int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel) +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, + struct hist_entry *he) { const char *ev_name = evsel__name(evsel); char buf[1024]; char *filename; int err = -1; FILE *fp; + struct annotation_print_data apd = { + .he = he, + .evsel = evsel, + }; if (asprintf(&filename, "%s.annotation", ms->sym->name) < 0) return -1; @@ -1353,7 +1416,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel) fprintf(fp, "%s() %s\nEvent: %s\n\n", ms->sym->name, dso__long_name(map__dso(ms->map)), ev_name); - symbol__annotate_fprintf2(ms->sym, fp); + symbol__annotate_fprintf2(ms->sym, fp, &apd); fclose(fp); err = 0; @@ -1400,6 +1463,7 @@ void annotated_source__purge(struct annotated_source *as) list_del_init(&al->node); disasm_line__free(disasm_line(al)); } + as->tried_source = false; } static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp) @@ -1597,12 +1661,17 @@ static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root) annotation__calc_lines(notes, ms, root); } -int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel) +int hist_entry__tty_annotate2(struct hist_entry *he, struct evsel *evsel) { + struct map_symbol *ms = &he->ms; struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; struct hists *hists = evsel__hists(evsel); + struct annotation_print_data apd = { + .he = he, + .evsel = evsel, + }; char buf[1024]; int err; @@ -1625,15 +1694,16 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel) hists__scnprintf_title(hists, buf, sizeof(buf)); fprintf(stdout, "%s, [percent: %s]\n%s() %s\n", buf, percent_type_str(annotate_opts.percent_type), sym->name, dso__long_name(dso)); - symbol__annotate_fprintf2(sym, stdout); + symbol__annotate_fprintf2(sym, stdout, &apd); annotated_source__purge(symbol__annotation(sym)->src); return 0; } -int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel) +int hist_entry__tty_annotate(struct hist_entry *he, struct evsel *evsel) { + struct map_symbol *ms = &he->ms; struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; @@ -1657,7 +1727,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel) print_summary(&source_line, dso__long_name(dso)); } - symbol__annotate_printf(ms, evsel); + hist_entry__annotate_printf(he, evsel); annotated_source__purge(symbol__annotation(sym)->src); @@ -1689,7 +1759,7 @@ static double annotation_line__max_percent(struct annotation_line *al, return percent_max; } -static void disasm_line__write(struct disasm_line *dl, struct annotation *notes, +static int disasm_line__write(struct disasm_line *dl, struct annotation *notes, void *obj, char *bf, size_t size, void (*obj__printf)(void *obj, const char *fmt, ...), void (*obj__write_graph)(void *obj, int graph)) @@ -1717,8 +1787,8 @@ call_like: obj__printf(obj, " "); } - disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, - notes->src->widths.max_ins_name); + return disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, + notes->src->widths.max_ins_name) + 2; } static void ipc_coverage_string(char *bf, int size, struct annotation *notes) @@ -1881,24 +1951,82 @@ err: return -ENOMEM; } -static void __annotation_line__write(struct annotation_line *al, struct annotation *notes, - bool first_line, bool current_entry, bool change_color, int width, - void *obj, unsigned int percent_type, - int (*obj__set_color)(void *obj, int color), - void (*obj__set_percent_color)(void *obj, double percent, bool current), - int (*obj__set_jumps_percent_color)(void *obj, int nr, bool current), - void (*obj__printf)(void *obj, const char *fmt, ...), - void (*obj__write_graph)(void *obj, int graph)) +struct type_hash_entry { + struct annotated_data_type *type; + int offset; +}; +static int disasm_line__snprint_type_info(struct disasm_line *dl, + char *buf, int len, + struct annotation_print_data *apd) { - double percent_max = annotation_line__max_percent(al, percent_type); - int pcnt_width = annotation__pcnt_width(notes), - cycles_width = annotation__cycles_width(notes); + struct annotated_data_type *data_type = NULL; + struct type_hash_entry *entry = NULL; + char member[256]; + int offset = 0; + int printed; + + scnprintf(buf, len, " "); + + if (!annotate_opts.code_with_type || apd->dbg == NULL) + return 1; + + if (apd->type_hash) { + hashmap__find(apd->type_hash, dl->al.offset, &entry); + if (entry != NULL) { + data_type = entry->type; + offset = entry->offset; + } + } + + if (data_type == NULL) + data_type = __hist_entry__get_data_type(apd->he, apd->arch, apd->dbg, dl, &offset); + + if (apd->type_hash && entry == NULL) { + entry = malloc(sizeof(*entry)); + if (entry != NULL) { + entry->type = data_type; + entry->offset = offset; + hashmap__add(apd->type_hash, dl->al.offset, entry); + } + } + + if (!needs_type_info(data_type)) + return 1; + + printed = scnprintf(buf, len, "\t\t# data-type: %s", data_type->self.type_name); + + if (data_type != &stackop_type && data_type != &canary_type && len > printed) + printed += scnprintf(buf + printed, len - printed, " +%#x", offset); + + if (annotated_data_type__get_member_name(data_type, member, sizeof(member), offset) && + len > printed) { + printed += scnprintf(buf + printed, len - printed, " (%s)", member); + } + return printed; +} + +void annotation_line__write(struct annotation_line *al, struct annotation *notes, + const struct annotation_write_ops *wops, + struct annotation_print_data *apd) +{ + bool current_entry = wops->current_entry; + bool change_color = wops->change_color; + double percent_max = annotation_line__max_percent(al, annotate_opts.percent_type); + int width = wops->width; + int pcnt_width = annotation__pcnt_width(notes); + int cycles_width = annotation__cycles_width(notes); bool show_title = false; char bf[256]; int printed; - - if (first_line && (al->offset == -1 || percent_max == 0.0)) { + void *obj = wops->obj; + int (*obj__set_color)(void *obj, int color) = wops->set_color; + void (*obj__set_percent_color)(void *obj, double percent, bool current) = wops->set_percent_color; + int (*obj__set_jumps_percent_color)(void *obj, int nr, bool current) = wops->set_jumps_percent_color; + void (*obj__printf)(void *obj, const char *fmt, ...) = wops->printf; + void (*obj__write_graph)(void *obj, int graph) = wops->write_graph; + + if (wops->first_line && (al->offset == -1 || percent_max == 0.0)) { if (notes->branch && al->cycles) { if (al->cycles->ipc == 0.0 && al->cycles->avg == 0) show_title = true; @@ -1912,7 +2040,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati for (i = 0; i < al->data_nr; i++) { double percent; - percent = annotation_data__percent(&al->data[i], percent_type); + percent = annotation_data__percent(&al->data[i], + annotate_opts.percent_type); obj__set_percent_color(obj, percent, current_entry); if (symbol_conf.show_total_period) { @@ -1935,6 +2064,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati symbol_conf.show_nr_samples ? "Samples" : "Percent"); } } + width -= pcnt_width; if (notes->branch) { if (al->cycles && al->cycles->ipc) @@ -1998,11 +2128,13 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati obj__printf(obj, "%*s", ANNOTATION__AVG_IPC_WIDTH, bf); } } + width -= cycles_width; obj__printf(obj, " "); + width -= 1; if (!*al->line) - obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " "); + obj__printf(obj, "%-*s", width, " "); else if (al->offset == -1) { if (al->line_nr && annotate_opts.show_linenr) printed = scnprintf(bf, sizeof(bf), "%-*d ", @@ -2011,7 +2143,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati printed = scnprintf(bf, sizeof(bf), "%-*s ", notes->src->widths.addr, " "); obj__printf(obj, bf); - obj__printf(obj, "%-*s", width - printed - pcnt_width - cycles_width + 1, al->line); + width -= printed; + obj__printf(obj, "%-*s", width, al->line); } else { u64 addr = al->offset; int color = -1; @@ -2054,26 +2187,22 @@ print_addr: if (change_color) obj__set_color(obj, color); - disasm_line__write(disasm_line(al), notes, obj, bf, sizeof(bf), obj__printf, obj__write_graph); + width -= printed; - obj__printf(obj, "%-*s", width - pcnt_width - cycles_width - 3 - printed, bf); - } + printed = disasm_line__write(disasm_line(al), notes, obj, bf, sizeof(bf), + obj__printf, obj__write_graph); -} + obj__printf(obj, "%s", bf); + width -= printed; + + disasm_line__snprint_type_info(disasm_line(al), bf, sizeof(bf), apd); + obj__printf(obj, "%-*s", width, bf); + } -void annotation_line__write(struct annotation_line *al, struct annotation *notes, - struct annotation_write_ops *wops) -{ - __annotation_line__write(al, notes, wops->first_line, wops->current_entry, - wops->change_color, wops->width, wops->obj, - annotate_opts.percent_type, - wops->set_color, wops->set_percent_color, - wops->set_jumps_percent_color, wops->printf, - wops->write_graph); } int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, - struct arch **parch) + const struct arch **parch) { struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); @@ -2227,6 +2356,8 @@ void annotation_options__init(void) opt->annotate_src = true; opt->offset_level = ANNOTATION__OFFSET_JUMP_TARGETS; opt->percent_type = PERCENT_PERIOD_LOCAL; + opt->hide_src_code = true; + opt->hide_src_code_on_title = true; } void annotation_options__exit(void) @@ -2318,17 +2449,39 @@ int annotate_check_args(void) return 0; } +static int arch__dwarf_regnum(const struct arch *arch, const char *str) +{ + const char *p; + char *regname, *q; + int reg; + + p = strchr(str, arch->objdump.register_char); + if (p == NULL) + return -1; + + regname = strdup(p); + if (regname == NULL) + return -1; + + q = strpbrk(regname, ",) "); + if (q) + *q = '\0'; + + reg = get_dwarf_regnum(regname, arch->id.e_machine, arch->id.e_flags); + free(regname); + return reg; +} + /* * Get register number and access offset from the given instruction. * It assumes AT&T x86 asm format like OFFSET(REG). Maybe it needs * to revisit the format when it handles different architecture. * Fills @reg and @offset when return 0. */ -static int extract_reg_offset(struct arch *arch, const char *str, +static int extract_reg_offset(const struct arch *arch, const char *str, struct annotated_op_loc *op_loc) { char *p; - char *regname; if (arch->objdump.register_char == 0) return -1; @@ -2341,7 +2494,7 @@ static int extract_reg_offset(struct arch *arch, const char *str, * %gs:0x18(%rbx). In that case it should skip the part. */ if (*str == arch->objdump.register_char) { - if (arch__is(arch, "x86")) { + if (arch__is_x86(arch)) { /* FIXME: Handle other segment registers */ if (!strncmp(str, "%gs:", 4)) op_loc->segment = INSN_SEG_X86_GS; @@ -2353,31 +2506,14 @@ static int extract_reg_offset(struct arch *arch, const char *str, } op_loc->offset = strtol(str, &p, 0); - - p = strchr(p, arch->objdump.register_char); - if (p == NULL) + op_loc->reg1 = arch__dwarf_regnum(arch, p); + if (op_loc->reg1 == -1) return -1; - regname = strdup(p); - if (regname == NULL) - return -1; - - op_loc->reg1 = get_dwarf_regnum(regname, arch->e_machine, arch->e_flags); - free(regname); - /* Get the second register */ - if (op_loc->multi_regs) { - p = strchr(p + 1, arch->objdump.register_char); - if (p == NULL) - return -1; + if (op_loc->multi_regs) + op_loc->reg2 = arch__dwarf_regnum(arch, p + 1); - regname = strdup(p); - if (regname == NULL) - return -1; - - op_loc->reg2 = get_dwarf_regnum(regname, arch->e_machine, arch->e_flags); - free(regname); - } return 0; } @@ -2405,7 +2541,7 @@ static int extract_reg_offset(struct arch *arch, const char *str, * # dst_reg1 = rbx, dst_reg2 = rcx, dst_mem = 1 * # dst_multi_regs = 1, dst_offset = 8 */ -int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl, +int annotate_get_insn_location(const struct arch *arch, struct disasm_line *dl, struct annotated_insn_loc *loc) { struct ins_operands *ops; @@ -2438,7 +2574,7 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl, op_loc->reg2 = -1; if (insn_str == NULL) { - if (!arch__is(arch, "powerpc")) + if (!arch__is_powerpc(arch)) continue; } @@ -2447,7 +2583,7 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl, * required fields for op_loc, ie reg1, reg2, offset from the * raw instruction. */ - if (arch__is(arch, "powerpc")) { + if (arch__is_powerpc(arch)) { op_loc->mem_ref = mem_ref; op_loc->multi_regs = multi_regs; get_powerpc_regs(dl->raw.raw_insn, !i, op_loc); @@ -2456,9 +2592,10 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl, op_loc->multi_regs = multi_regs; extract_reg_offset(arch, insn_str, op_loc); } else { - char *s, *p = NULL; + const char *s = insn_str; + char *p = NULL; - if (arch__is(arch, "x86")) { + if (arch__is_x86(arch)) { /* FIXME: Handle other segment registers */ if (!strncmp(insn_str, "%gs:", 4)) { op_loc->segment = INSN_SEG_X86_GS; @@ -2470,18 +2607,14 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl, } } - s = strdup(insn_str); - if (s == NULL) - return -1; - - if (*s == arch->objdump.register_char) - op_loc->reg1 = get_dwarf_regnum(s, arch->e_machine, arch->e_flags); + if (*s == arch->objdump.register_char) { + op_loc->reg1 = arch__dwarf_regnum(arch, s); + } else if (*s == arch->objdump.imm_char) { op_loc->offset = strtol(s + 1, &p, 0); if (p && p != s + 1) op_loc->imm = true; } - free(s); } } @@ -2540,9 +2673,9 @@ static struct annotated_item_stat *annotate_data_stat(struct list_head *head, return istat; } -static bool is_stack_operation(struct arch *arch, struct disasm_line *dl) +static bool is_stack_operation(const struct arch *arch, struct disasm_line *dl) { - if (arch__is(arch, "x86")) { + if (arch__is_x86(arch)) { if (!strncmp(dl->ins.name, "push", 4) || !strncmp(dl->ins.name, "pop", 3) || !strncmp(dl->ins.name, "call", 4) || @@ -2553,10 +2686,10 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl) return false; } -static bool is_stack_canary(struct arch *arch, struct annotated_op_loc *loc) +static bool is_stack_canary(const struct arch *arch, struct annotated_op_loc *loc) { /* On x86_64, %gs:40 is used for stack canary */ - if (arch__is(arch, "x86")) { + if (arch__is_x86(arch)) { if (loc->segment == INSN_SEG_X86_GS && loc->imm && loc->offset == 40) return true; @@ -2565,6 +2698,20 @@ static bool is_stack_canary(struct arch *arch, struct annotated_op_loc *loc) return false; } +/** + * Returns true if the instruction has a memory operand without + * performing a load/store + */ +static bool is_address_gen_insn(const struct arch *arch, struct disasm_line *dl) +{ + if (arch__is_x86(arch)) { + if (!strncmp(dl->ins.name, "lea", 3)) + return true; + } + + return false; +} + static struct disasm_line * annotation__prev_asm_line(struct annotation *notes, struct disasm_line *curr) { @@ -2643,114 +2790,56 @@ void debuginfo_cache__delete(void) di_cache.dbg = NULL; } -/** - * hist_entry__get_data_type - find data type for given hist entry - * @he: hist entry - * - * This function first annotates the instruction at @he->ip and extracts - * register and offset info from it. Then it searches the DWARF debug - * info to get a variable and type information using the address, register, - * and offset. - */ -struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he) +static struct annotated_data_type * +__hist_entry__get_data_type(struct hist_entry *he, const struct arch *arch, + struct debuginfo *dbg, struct disasm_line *dl, + int *type_offset) { struct map_symbol *ms = &he->ms; - struct evsel *evsel = hists_to_evsel(he->hists); - struct arch *arch; - struct disasm_line *dl; struct annotated_insn_loc loc; struct annotated_op_loc *op_loc; struct annotated_data_type *mem_type; struct annotated_item_stat *istat; - u64 ip = he->ip; int i; - ann_data_stat.total++; - - if (ms->map == NULL || ms->sym == NULL) { - ann_data_stat.no_sym++; - return NULL; - } - - if (!symbol_conf.init_annotation) { - ann_data_stat.no_sym++; - return NULL; - } - - /* - * di_cache holds a pair of values, but code below assumes - * di_cache.dso can be compared/updated and di_cache.dbg can be - * read/updated independently from each other. That assumption only - * holds in single threaded code. - */ - assert(perf_singlethreaded); - - if (map__dso(ms->map) != di_cache.dso) { - dso__put(di_cache.dso); - di_cache.dso = dso__get(map__dso(ms->map)); - - debuginfo__delete(di_cache.dbg); - di_cache.dbg = debuginfo__new(dso__long_name(di_cache.dso)); - } - - if (di_cache.dbg == NULL) { - ann_data_stat.no_dbginfo++; - return NULL; - } - - /* Make sure it has the disasm of the function */ - if (symbol__annotate(ms, evsel, &arch) < 0) { - ann_data_stat.no_insn++; - return NULL; - } - - /* - * Get a disasm to extract the location from the insn. - * This is too slow... - */ - dl = find_disasm_line(ms->sym, ip, /*allow_update=*/true); - if (dl == NULL) { - ann_data_stat.no_insn++; - return NULL; - } - -retry: istat = annotate_data_stat(&ann_insn_stat, dl->ins.name); if (istat == NULL) { ann_data_stat.no_insn++; - return NULL; + return NO_TYPE; } if (annotate_get_insn_location(arch, dl, &loc) < 0) { ann_data_stat.no_insn_ops++; istat->bad++; - return NULL; + return NO_TYPE; } if (is_stack_operation(arch, dl)) { istat->good++; - he->mem_type_off = 0; + *type_offset = 0; return &stackop_type; } + if (is_address_gen_insn(arch, dl)) { + istat->bad++; + ann_data_stat.no_mem_ops++; + return NO_TYPE; + } + for_each_insn_op_loc(&loc, i, op_loc) { struct data_loc_info dloc = { .arch = arch, .thread = he->thread, .ms = ms, - /* Recalculate IP for LOCK prefix or insn fusion */ .ip = ms->sym->start + dl->al.offset, .cpumode = he->cpumode, .op = op_loc, - .di = di_cache.dbg, + .di = dbg, }; if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE) continue; - /* Recalculate IP because of LOCK prefix or insn fusion */ - ip = ms->sym->start + dl->al.offset; - /* PC-relative addressing */ if (op_loc->reg1 == DWARF_REG_PC) { dloc.var_addr = annotate_calc_pcrel(ms, dloc.ip, @@ -2758,7 +2847,7 @@ retry: } /* This CPU access in kernel - pretend PC-relative addressing */ - if (dso__kernel(map__dso(ms->map)) && arch__is(arch, "x86") && + if (dso__kernel(map__dso(ms->map)) && arch__is_x86(arch) && op_loc->segment == INSN_SEG_X86_GS && op_loc->imm) { dloc.var_addr = op_loc->offset; op_loc->reg1 = DWARF_REG_PC; @@ -2768,7 +2857,7 @@ retry: if (mem_type == NULL && is_stack_canary(arch, op_loc)) { istat->good++; - he->mem_type_off = 0; + *type_offset = 0; return &canary_type; } @@ -2778,16 +2867,96 @@ retry: istat->bad++; if (symbol_conf.annotate_data_sample) { + struct evsel *evsel = hists_to_evsel(he->hists); + annotated_data_type__update_samples(mem_type, evsel, dloc.type_offset, he->stat.nr_events, he->stat.period); } - he->mem_type_off = dloc.type_offset; - return mem_type; + *type_offset = dloc.type_offset; + return mem_type ?: NO_TYPE; + } + + /* retry with a fused instruction */ + return NULL; +} + +/** + * hist_entry__get_data_type - find data type for given hist entry + * @he: hist entry + * + * This function first annotates the instruction at @he->ip and extracts + * register and offset info from it. Then it searches the DWARF debug + * info to get a variable and type information using the address, register, + * and offset. + */ +struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he) +{ + struct map_symbol *ms = &he->ms; + struct evsel *evsel = hists_to_evsel(he->hists); + const struct arch *arch; + struct disasm_line *dl; + struct annotated_data_type *mem_type; + struct annotated_item_stat *istat; + u64 ip = he->ip; + + ann_data_stat.total++; + + if (ms->map == NULL || ms->sym == NULL) { + ann_data_stat.no_sym++; + return NULL; + } + + if (!symbol_conf.init_annotation) { + ann_data_stat.no_sym++; + return NULL; } /* + * di_cache holds a pair of values, but code below assumes + * di_cache.dso can be compared/updated and di_cache.dbg can be + * read/updated independently from each other. That assumption only + * holds in single threaded code. + */ + assert(perf_singlethreaded); + + if (map__dso(ms->map) != di_cache.dso) { + dso__put(di_cache.dso); + di_cache.dso = dso__get(map__dso(ms->map)); + + debuginfo__delete(di_cache.dbg); + di_cache.dbg = dso__debuginfo(di_cache.dso); + } + + if (di_cache.dbg == NULL) { + ann_data_stat.no_dbginfo++; + return NULL; + } + + /* Make sure it has the disasm of the function */ + if (symbol__annotate(ms, evsel, &arch) < 0) { + ann_data_stat.no_insn++; + return NULL; + } + + /* + * Get a disasm to extract the location from the insn. + * This is too slow... + */ + dl = find_disasm_line(ms->sym, ip, /*allow_update=*/true); + if (dl == NULL) { + ann_data_stat.no_insn++; + return NULL; + } + +retry: + mem_type = __hist_entry__get_data_type(he, arch, di_cache.dbg, dl, + &he->mem_type_off); + if (mem_type) + return mem_type == NO_TYPE ? NULL : mem_type; + + /* * Some instructions can be fused and the actual memory access came * from the previous instruction. */ @@ -2805,7 +2974,9 @@ retry: } ann_data_stat.no_mem_ops++; - istat->bad++; + istat = annotate_data_stat(&ann_insn_stat, dl->ins.name); + if (istat) + istat->bad++; return NULL; } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 98db1b88daf4..696e36dbf013 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -44,6 +44,7 @@ enum perf_disassembler { struct annotation_options { bool hide_src_code, + hide_src_code_on_title, use_offset, jump_arrows, print_lines, @@ -55,9 +56,11 @@ struct annotation_options { show_asm_raw, show_br_cntr, annotate_src, + code_with_type, full_addr; u8 offset_level; u8 disassemblers[MAX_DISASSEMBLERS]; + u8 disassembler_used; int min_pcnt; int max_lines; int context; @@ -196,8 +199,20 @@ struct annotation_write_ops { void (*write_graph)(void *obj, int graph); }; +struct annotation_print_data { + struct hist_entry *he; + struct evsel *evsel; + const struct arch *arch; + struct debuginfo *dbg; + /* save data type info keyed by al->offset */ + struct hashmap *type_hash; + /* It'll be set in hist_entry__annotate_printf() */ + int addr_fmt_width; +}; + void annotation_line__write(struct annotation_line *al, struct annotation *notes, - struct annotation_write_ops *ops); + const struct annotation_write_ops *ops, + struct annotation_print_data *apd); int __annotation__scnprintf_samples_period(struct annotation *notes, char *bf, size_t size, @@ -291,6 +306,7 @@ struct annotated_source { int nr_entries; int nr_asm_entries; int max_jump_sources; + bool tried_source; u64 start; struct { u8 addr; @@ -425,10 +441,10 @@ void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, - struct arch **parch); + const struct arch **parch); int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, - struct arch **parch); + const struct arch **parch); enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, @@ -455,30 +471,18 @@ enum symbol_disassemble_errno { int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen); -int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel); void symbol__annotate_zero_histogram(struct symbol *sym, struct evsel *evsel); void symbol__annotate_decay_histogram(struct symbol *sym, struct evsel *evsel); void annotated_source__purge(struct annotated_source *as); -int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel); +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, + struct hist_entry *he); bool ui__has_annotation(void); -int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel); - -int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel); - -#ifdef HAVE_SLANG_SUPPORT -int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, - struct hist_browser_timer *hbt); -#else -static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused, - struct evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) -{ - return 0; -} -#endif +int hist_entry__annotate_printf(struct hist_entry *he, struct evsel *evsel); +int hist_entry__tty_annotate(struct hist_entry *he, struct evsel *evsel); +int hist_entry__tty_annotate2(struct hist_entry *he, struct evsel *evsel); void annotation_options__init(void); void annotation_options__exit(void); @@ -542,7 +546,7 @@ struct annotated_insn_loc { i++, op_loc++) /* Get detailed location info in the instruction */ -int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl, +int annotate_get_insn_location(const struct arch *arch, struct disasm_line *dl, struct annotated_insn_loc *loc); /* Returns a data type from the sample instruction (if any) */ @@ -581,4 +585,6 @@ void debuginfo_cache__delete(void); int annotation_br_cntr_entry(char **str, int br_cntr_nr, u64 *br_cntr, int num_aggr, struct evsel *evsel); int annotation_br_cntr_abbr_list(char **str, struct evsel *evsel, bool header); + +int thread__get_arch(struct thread *thread, const struct arch **parch); #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/archinsn.h b/tools/perf/util/archinsn.h deleted file mode 100644 index 448cbb6b8d7e..000000000000 --- a/tools/perf/util/archinsn.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef INSN_H -#define INSN_H 1 - -struct perf_sample; -struct machine; -struct thread; - -void arch_fetch_insn(struct perf_sample *sample, - struct thread *thread, - struct machine *machine); - -#endif diff --git a/tools/perf/util/arm-spe-decoder/Build b/tools/perf/util/arm-spe-decoder/Build index 960062b3cb9e..ab500e0efe24 100644 --- a/tools/perf/util/arm-spe-decoder/Build +++ b/tools/perf/util/arm-spe-decoder/Build @@ -1 +1 @@ -perf-util-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o arm-spe-decoder.o +perf-util-y += arm-spe-pkt-decoder.o arm-spe-decoder.o diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index ba807071d3c1..9e02b2bdd117 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -28,7 +28,8 @@ static u64 arm_spe_calc_ip(int index, u64 payload) /* Instruction virtual address or Branch target address */ if (index == SPE_ADDR_PKT_HDR_INDEX_INS || - index == SPE_ADDR_PKT_HDR_INDEX_BRANCH) { + index == SPE_ADDR_PKT_HDR_INDEX_BRANCH || + index == SPE_ADDR_PKT_HDR_INDEX_PREV_BRANCH) { ns = SPE_ADDR_PKT_GET_NS(payload); el = SPE_ADDR_PKT_GET_EL(payload); @@ -181,6 +182,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) decoder->record.virt_addr = ip; else if (idx == SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS) decoder->record.phys_addr = ip; + else if (idx == SPE_ADDR_PKT_HDR_INDEX_PREV_BRANCH) + decoder->record.prev_br_tgt = ip; break; case ARM_SPE_COUNTER: if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT) @@ -197,16 +200,76 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) decoder->record.op |= ARM_SPE_OP_ST; else decoder->record.op |= ARM_SPE_OP_LD; - if (SPE_OP_PKT_IS_LDST_SVE(payload)) - decoder->record.op |= ARM_SPE_OP_SVE_LDST; + + if (SPE_OP_PKT_LDST_SUBCLASS_GP_REG(payload)) { + decoder->record.op |= ARM_SPE_OP_GP_REG; + } else if (SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP(payload)) { + decoder->record.op |= ARM_SPE_OP_SIMD_FP; + } else if (SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG(payload)) { + decoder->record.op |= ARM_SPE_OP_UNSPEC_REG; + } else if (SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG(payload)) { + decoder->record.op |= ARM_SPE_OP_NV_SYSREG; + } else if (SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG(payload)) { + decoder->record.op |= ARM_SPE_OP_MTE_TAG; + } else if (SPE_OP_PKT_LDST_SUBCLASS_EXTENDED(payload)) { + if (payload & SPE_OP_PKT_AR) + decoder->record.op |= ARM_SPE_OP_AR; + if (payload & SPE_OP_PKT_EXCL) + decoder->record.op |= ARM_SPE_OP_EXCL; + if (payload & SPE_OP_PKT_AT) + decoder->record.op |= ARM_SPE_OP_ATOMIC; + } else if (SPE_OP_PKT_LDST_SUBCLASS_SVE_SME_REG(payload)) { + decoder->record.op |= ARM_SPE_OP_SVE; + if (payload & SPE_OP_PKT_SVE_PRED) + decoder->record.op |= ARM_SPE_OP_PRED; + if (payload & SPE_OP_PKT_SVE_SG) + decoder->record.op |= ARM_SPE_OP_SG; + } else if (SPE_OP_PKT_LDST_SUBCLASS_MEMCPY(payload)) { + decoder->record.op |= ARM_SPE_OP_MEMCPY; + } else if (SPE_OP_PKT_LDST_SUBCLASS_MEMSET(payload)) { + decoder->record.op |= ARM_SPE_OP_MEMSET; + } else if (SPE_OP_PKT_LDST_SUBCLASS_GCS(payload)) { + decoder->record.op |= ARM_SPE_OP_GCS; + if (payload & SPE_OP_PKT_GCS_COMM) + decoder->record.op |= ARM_SPE_OP_COMM; + } + break; case SPE_OP_PKT_HDR_CLASS_OTHER: decoder->record.op |= ARM_SPE_OP_OTHER; - if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload)) - decoder->record.op |= ARM_SPE_OP_SVE_OTHER; + if (SPE_OP_PKT_OTHER_SUBCLASS_SVE(payload)) { + decoder->record.op |= ARM_SPE_OP_SVE | ARM_SPE_OP_DP; + if (payload & SPE_OP_PKT_OTHER_FP) + decoder->record.op |= ARM_SPE_OP_FP; + if (payload & SPE_OP_PKT_SVE_PRED) + decoder->record.op |= ARM_SPE_OP_PRED; + } else if (SPE_OP_PKT_OTHER_SUBCLASS_SME(payload)) { + decoder->record.op |= ARM_SPE_OP_SME; + if (payload & SPE_OP_PKT_OTHER_FP) + decoder->record.op |= ARM_SPE_OP_FP; + } else if (SPE_OP_PKT_OTHER_SUBCLASS_OTHER(payload)) { + if (payload & SPE_OP_PKT_OTHER_ASE) + decoder->record.op |= ARM_SPE_OP_ASE; + if (payload & SPE_OP_PKT_OTHER_FP) + decoder->record.op |= ARM_SPE_OP_FP; + if (payload & SPE_OP_PKT_COND) + decoder->record.op |= ARM_SPE_OP_COND; + } break; case SPE_OP_PKT_HDR_CLASS_BR_ERET: decoder->record.op |= ARM_SPE_OP_BRANCH_ERET; + if (payload & SPE_OP_PKT_COND) + decoder->record.op |= ARM_SPE_OP_BR_COND; + if (payload & SPE_OP_PKT_INDIRECT_BRANCH) + decoder->record.op |= ARM_SPE_OP_BR_INDIRECT; + if (payload & SPE_OP_PKT_GCS) + decoder->record.op |= ARM_SPE_OP_BR_GCS; + if (SPE_OP_PKT_CR_BL(payload)) + decoder->record.op |= ARM_SPE_OP_BR_CR_BL; + if (SPE_OP_PKT_CR_RET(payload)) + decoder->record.op |= ARM_SPE_OP_BR_CR_RET; + if (SPE_OP_PKT_CR_NON_BL_RET(payload)) + decoder->record.op |= ARM_SPE_OP_BR_CR_NON_BL_RET; break; default: pr_err("Get packet error!\n"); @@ -214,36 +277,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) } break; case ARM_SPE_EVENTS: - if (payload & BIT(EV_L1D_REFILL)) - decoder->record.type |= ARM_SPE_L1D_MISS; - - if (payload & BIT(EV_L1D_ACCESS)) - decoder->record.type |= ARM_SPE_L1D_ACCESS; - - if (payload & BIT(EV_TLB_WALK)) - decoder->record.type |= ARM_SPE_TLB_MISS; - - if (payload & BIT(EV_TLB_ACCESS)) - decoder->record.type |= ARM_SPE_TLB_ACCESS; - - if (payload & BIT(EV_LLC_MISS)) - decoder->record.type |= ARM_SPE_LLC_MISS; - - if (payload & BIT(EV_LLC_ACCESS)) - decoder->record.type |= ARM_SPE_LLC_ACCESS; - - if (payload & BIT(EV_REMOTE_ACCESS)) - decoder->record.type |= ARM_SPE_REMOTE_ACCESS; - - if (payload & BIT(EV_MISPRED)) - decoder->record.type |= ARM_SPE_BRANCH_MISS; - - if (payload & BIT(EV_PARTIAL_PREDICATE)) - decoder->record.type |= ARM_SPE_SVE_PARTIAL_PRED; - - if (payload & BIT(EV_EMPTY_PREDICATE)) - decoder->record.type |= ARM_SPE_SVE_EMPTY_PRED; - + decoder->record.type = payload; break; case ARM_SPE_DATA_SOURCE: decoder->record.source = payload; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 4bcd627e859f..3310e05122f0 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -13,47 +13,65 @@ #include "arm-spe-pkt-decoder.h" -enum arm_spe_sample_type { - ARM_SPE_L1D_ACCESS = 1 << 0, - ARM_SPE_L1D_MISS = 1 << 1, - ARM_SPE_LLC_ACCESS = 1 << 2, - ARM_SPE_LLC_MISS = 1 << 3, - ARM_SPE_TLB_ACCESS = 1 << 4, - ARM_SPE_TLB_MISS = 1 << 5, - ARM_SPE_BRANCH_MISS = 1 << 6, - ARM_SPE_REMOTE_ACCESS = 1 << 7, - ARM_SPE_SVE_PARTIAL_PRED = 1 << 8, - ARM_SPE_SVE_EMPTY_PRED = 1 << 9, -}; +#define ARM_SPE_L1D_ACCESS BIT(EV_L1D_ACCESS) +#define ARM_SPE_L1D_MISS BIT(EV_L1D_REFILL) +#define ARM_SPE_LLC_ACCESS BIT(EV_LLC_ACCESS) +#define ARM_SPE_LLC_MISS BIT(EV_LLC_MISS) +#define ARM_SPE_TLB_ACCESS BIT(EV_TLB_ACCESS) +#define ARM_SPE_TLB_MISS BIT(EV_TLB_WALK) +#define ARM_SPE_BRANCH_MISS BIT(EV_MISPRED) +#define ARM_SPE_BRANCH_NOT_TAKEN BIT(EV_NOT_TAKEN) +#define ARM_SPE_REMOTE_ACCESS BIT(EV_REMOTE_ACCESS) +#define ARM_SPE_SVE_PARTIAL_PRED BIT(EV_PARTIAL_PREDICATE) +#define ARM_SPE_SVE_EMPTY_PRED BIT(EV_EMPTY_PREDICATE) +#define ARM_SPE_IN_TXN BIT(EV_TRANSACTIONAL) +#define ARM_SPE_L2D_ACCESS BIT(EV_L2D_ACCESS) +#define ARM_SPE_L2D_MISS BIT(EV_L2D_MISS) +#define ARM_SPE_RECENTLY_FETCHED BIT(EV_RECENTLY_FETCHED) +#define ARM_SPE_DATA_SNOOPED BIT(EV_DATA_SNOOPED) +#define ARM_SPE_HITM BIT(EV_CACHE_DATA_MODIFIED) enum arm_spe_op_type { /* First level operation type */ ARM_SPE_OP_OTHER = 1 << 0, ARM_SPE_OP_LDST = 1 << 1, ARM_SPE_OP_BRANCH_ERET = 1 << 2, +}; + +enum arm_spe_2nd_op_ldst { + ARM_SPE_OP_GP_REG = 1 << 8, + ARM_SPE_OP_UNSPEC_REG = 1 << 9, + ARM_SPE_OP_NV_SYSREG = 1 << 10, + ARM_SPE_OP_SIMD_FP = 1 << 11, + ARM_SPE_OP_SVE = 1 << 12, + ARM_SPE_OP_MTE_TAG = 1 << 13, + ARM_SPE_OP_MEMCPY = 1 << 14, + ARM_SPE_OP_MEMSET = 1 << 15, + ARM_SPE_OP_GCS = 1 << 16, + ARM_SPE_OP_SME = 1 << 17, + ARM_SPE_OP_ASE = 1 << 18, + + /* Assisted information for memory / SIMD */ + ARM_SPE_OP_LD = 1 << 20, + ARM_SPE_OP_ST = 1 << 21, + ARM_SPE_OP_ATOMIC = 1 << 22, + ARM_SPE_OP_EXCL = 1 << 23, + ARM_SPE_OP_AR = 1 << 24, + ARM_SPE_OP_DP = 1 << 25, /* Data processing */ + ARM_SPE_OP_PRED = 1 << 26, /* Predicated */ + ARM_SPE_OP_SG = 1 << 27, /* Gather/Scatter */ + ARM_SPE_OP_COMM = 1 << 28, /* Common */ + ARM_SPE_OP_FP = 1 << 29, /* Floating-point */ + ARM_SPE_OP_COND = 1 << 30, /* Conditional */ +}; - /* Second level operation type for OTHER */ - ARM_SPE_OP_SVE_OTHER = 1 << 16, - ARM_SPE_OP_SVE_FP = 1 << 17, - ARM_SPE_OP_SVE_PRED_OTHER = 1 << 18, - - /* Second level operation type for LDST */ - ARM_SPE_OP_LD = 1 << 16, - ARM_SPE_OP_ST = 1 << 17, - ARM_SPE_OP_ATOMIC = 1 << 18, - ARM_SPE_OP_EXCL = 1 << 19, - ARM_SPE_OP_AR = 1 << 20, - ARM_SPE_OP_SIMD_FP = 1 << 21, - ARM_SPE_OP_GP_REG = 1 << 22, - ARM_SPE_OP_UNSPEC_REG = 1 << 23, - ARM_SPE_OP_NV_SYSREG = 1 << 24, - ARM_SPE_OP_SVE_LDST = 1 << 25, - ARM_SPE_OP_SVE_PRED_LDST = 1 << 26, - ARM_SPE_OP_SVE_SG = 1 << 27, - - /* Second level operation type for BRANCH_ERET */ - ARM_SPE_OP_BR_COND = 1 << 16, - ARM_SPE_OP_BR_INDIRECT = 1 << 17, +enum arm_spe_2nd_op_branch { + ARM_SPE_OP_BR_COND = 1 << 8, + ARM_SPE_OP_BR_INDIRECT = 1 << 9, + ARM_SPE_OP_BR_GCS = 1 << 10, + ARM_SPE_OP_BR_CR_BL = 1 << 11, + ARM_SPE_OP_BR_CR_RET = 1 << 12, + ARM_SPE_OP_BR_CR_NON_BL_RET = 1 << 13, }; enum arm_spe_common_data_source { @@ -76,13 +94,31 @@ enum arm_spe_ampereone_data_source { ARM_SPE_AMPEREONE_L2D = 0x9, }; +enum arm_spe_hisi_hip_data_source { + ARM_SPE_HISI_HIP_PEER_CPU = 0, + ARM_SPE_HISI_HIP_PEER_CPU_HITM = 1, + ARM_SPE_HISI_HIP_L3 = 2, + ARM_SPE_HISI_HIP_L3_HITM = 3, + ARM_SPE_HISI_HIP_PEER_CLUSTER = 4, + ARM_SPE_HISI_HIP_PEER_CLUSTER_HITM = 5, + ARM_SPE_HISI_HIP_REMOTE_SOCKET = 6, + ARM_SPE_HISI_HIP_REMOTE_SOCKET_HITM = 7, + ARM_SPE_HISI_HIP_LOCAL_MEM = 8, + ARM_SPE_HISI_HIP_REMOTE_MEM = 9, + ARM_SPE_HISI_HIP_NC_DEV = 13, + ARM_SPE_HISI_HIP_L2 = 16, + ARM_SPE_HISI_HIP_L2_HITM = 17, + ARM_SPE_HISI_HIP_L1 = 18, +}; + struct arm_spe_record { - enum arm_spe_sample_type type; + u64 type; int err; u32 op; u32 latency; u64 from_ip; u64 to_ip; + u64 prev_br_tgt; u64 timestamp; u64 virt_addr; u64 phys_addr; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index 4cef10a83962..5769ba2f4140 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -308,10 +308,26 @@ static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet, arm_spe_pkt_out_string(&err, &buf, &buf_len, " REMOTE-ACCESS"); if (payload & BIT(EV_ALIGNMENT)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " ALIGNMENT"); + if (payload & BIT(EV_TRANSACTIONAL)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " TXN"); if (payload & BIT(EV_PARTIAL_PREDICATE)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-PARTIAL-PRED"); if (payload & BIT(EV_EMPTY_PREDICATE)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-EMPTY-PRED"); + if (payload & BIT(EV_L2D_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " L2D-ACCESS"); + if (payload & BIT(EV_L2D_MISS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " L2D-MISS"); + if (payload & BIT(EV_CACHE_DATA_MODIFIED)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " HITM"); + if (payload & BIT(EV_RECENTLY_FETCHED)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " LFB"); + if (payload & BIT(EV_DATA_SNOOPED)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SNOOPED"); + if (payload & BIT(EV_STREAMING_SVE_MODE)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " STREAMING-SVE"); + if (payload & BIT(EV_SMCU)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SMCU"); return err; } @@ -324,7 +340,7 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, switch (packet->index) { case SPE_OP_PKT_HDR_CLASS_OTHER: - if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload)) { + if (SPE_OP_PKT_OTHER_SUBCLASS_SVE(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, "SVE-OTHER"); /* SVE effective vector length */ @@ -335,8 +351,21 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, arm_spe_pkt_out_string(&err, &buf, &buf_len, " FP"); if (payload & SPE_OP_PKT_SVE_PRED) arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED"); - } else { + } else if (SPE_OP_PKT_OTHER_SUBCLASS_SME(payload)) { + arm_spe_pkt_out_string(&err, &buf, &buf_len, "SME-OTHER"); + + /* SME effective vector length or tile size */ + arm_spe_pkt_out_string(&err, &buf, &buf_len, " ETS %d", + SPE_OP_PKG_SME_ETS(payload)); + + if (payload & SPE_OP_PKT_OTHER_FP) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " FP"); + } else if (SPE_OP_PKT_OTHER_SUBCLASS_OTHER(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, "OTHER"); + if (payload & SPE_OP_PKT_OTHER_ASE) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " ASE"); + if (payload & SPE_OP_PKT_OTHER_FP) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " FP"); arm_spe_pkt_out_string(&err, &buf, &buf_len, " %s", payload & SPE_OP_PKT_COND ? "COND-SELECT" : "INSN-OTHER"); @@ -346,42 +375,30 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, arm_spe_pkt_out_string(&err, &buf, &buf_len, payload & 0x1 ? "ST" : "LD"); - if (SPE_OP_PKT_IS_LDST_ATOMIC(payload)) { + if (SPE_OP_PKT_LDST_SUBCLASS_EXTENDED(payload)) { if (payload & SPE_OP_PKT_AT) arm_spe_pkt_out_string(&err, &buf, &buf_len, " AT"); if (payload & SPE_OP_PKT_EXCL) arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCL"); if (payload & SPE_OP_PKT_AR) arm_spe_pkt_out_string(&err, &buf, &buf_len, " AR"); - } - - switch (SPE_OP_PKT_LDST_SUBCLASS_GET(payload)) { - case SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP: + } else if (SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, " SIMD-FP"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_GP_REG: + } else if (SPE_OP_PKT_LDST_SUBCLASS_GP_REG(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, " GP-REG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG: + } else if (SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, " UNSPEC-REG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG: + } else if (SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, " NV-SYSREG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG: + } else if (SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, " MTE-TAG"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_MEMCPY: + } else if (SPE_OP_PKT_LDST_SUBCLASS_MEMCPY(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMCPY"); - break; - case SPE_OP_PKT_LDST_SUBCLASS_MEMSET: + } else if (SPE_OP_PKT_LDST_SUBCLASS_MEMSET(payload)) { arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMSET"); - break; - default: - break; - } + } else if (SPE_OP_PKT_LDST_SUBCLASS_SVE_SME_REG(payload)) { + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-SME-REG"); - if (SPE_OP_PKT_IS_LDST_SVE(payload)) { /* SVE effective vector length */ arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d", SPE_OP_PKG_SVE_EVL(payload)); @@ -390,6 +407,10 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED"); if (payload & SPE_OP_PKT_SVE_SG) arm_spe_pkt_out_string(&err, &buf, &buf_len, " SG"); + } else if (SPE_OP_PKT_LDST_SUBCLASS_GCS(payload)) { + arm_spe_pkt_out_string(&err, &buf, &buf_len, " GCS"); + if (payload & SPE_OP_PKT_GCS_COMM) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " COMM"); } break; case SPE_OP_PKT_HDR_CLASS_BR_ERET: @@ -397,10 +418,16 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, if (payload & SPE_OP_PKT_COND) arm_spe_pkt_out_string(&err, &buf, &buf_len, " COND"); - - if (SPE_OP_PKT_IS_INDIRECT_BRANCH(payload)) + if (payload & SPE_OP_PKT_INDIRECT_BRANCH) arm_spe_pkt_out_string(&err, &buf, &buf_len, " IND"); - + if (payload & SPE_OP_PKT_GCS) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " GCS"); + if (SPE_OP_PKT_CR_BL(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " CR-BL"); + if (SPE_OP_PKT_CR_RET(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " CR-RET"); + if (SPE_OP_PKT_CR_NON_BL_RET(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " CR-NON-BL-RET"); break; default: /* Unknown index */ diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h index 464a912b221c..adf4cde320aa 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h @@ -7,6 +7,7 @@ #ifndef INCLUDE__ARM_SPE_PKT_DECODER_H__ #define INCLUDE__ARM_SPE_PKT_DECODER_H__ +#include <linux/bitfield.h> #include <stddef.h> #include <stdint.h> @@ -104,8 +105,16 @@ enum arm_spe_events { EV_LLC_MISS = 9, EV_REMOTE_ACCESS = 10, EV_ALIGNMENT = 11, + EV_TRANSACTIONAL = 16, EV_PARTIAL_PREDICATE = 17, EV_EMPTY_PREDICATE = 18, + EV_L2D_ACCESS = 19, + EV_L2D_MISS = 20, + EV_CACHE_DATA_MODIFIED = 21, + EV_RECENTLY_FETCHED = 22, + EV_DATA_SNOOPED = 23, + EV_STREAMING_SVE_MODE = 24, + EV_SMCU = 25, }; /* Operation packet header */ @@ -114,27 +123,39 @@ enum arm_spe_events { #define SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC 0x1 #define SPE_OP_PKT_HDR_CLASS_BR_ERET 0x2 -#define SPE_OP_PKT_IS_OTHER_SVE_OP(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8) +#define SPE_OP_PKT_OTHER_SUBCLASS_OTHER(v) (((v) & GENMASK_ULL(7, 3)) == 0x0) +#define SPE_OP_PKT_OTHER_SUBCLASS_SVE(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8) +#define SPE_OP_PKT_OTHER_SUBCLASS_SME(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x88) -#define SPE_OP_PKT_COND BIT(0) +#define SPE_OP_PKT_OTHER_ASE BIT(2) +#define SPE_OP_PKT_OTHER_FP BIT(1) + +/* + * SME effective vector length or tile size (ETS) is stored in byte 0 + * bits [6:4,2]; the length is rounded up to a power of two and use 128 + * as one step, so ETS calculation is: + * + * 128 * (2 ^ bits [6:4,2]) = 32 << (bits [6:4,2]) + */ +#define SPE_OP_PKG_SME_ETS(v) (128 << (FIELD_GET(GENMASK_ULL(6, 4), (v)) << 1 | \ + (FIELD_GET(BIT(2), (v))))) -#define SPE_OP_PKT_LDST_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1)) -#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG 0x0 -#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP 0x4 -#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG 0x10 -#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG 0x30 -#define SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG 0x14 -#define SPE_OP_PKT_LDST_SUBCLASS_MEMCPY 0x20 -#define SPE_OP_PKT_LDST_SUBCLASS_MEMSET 0x25 +#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG(v) (((v) & GENMASK_ULL(7, 1)) == 0x0) +#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP(v) (((v) & GENMASK_ULL(7, 1)) == 0x4) +#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG(v) (((v) & GENMASK_ULL(7, 1)) == 0x10) +#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG(v) (((v) & GENMASK_ULL(7, 1)) == 0x30) +#define SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG(v) (((v) & GENMASK_ULL(7, 1)) == 0x14) +#define SPE_OP_PKT_LDST_SUBCLASS_MEMCPY(v) (((v) & GENMASK_ULL(7, 1)) == 0x20) +#define SPE_OP_PKT_LDST_SUBCLASS_MEMSET(v) (((v) & GENMASK_ULL(7, 0)) == 0x25) -#define SPE_OP_PKT_IS_LDST_ATOMIC(v) (((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2) +#define SPE_OP_PKT_LDST_SUBCLASS_EXTENDED(v) (((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2) #define SPE_OP_PKT_AR BIT(4) #define SPE_OP_PKT_EXCL BIT(3) #define SPE_OP_PKT_AT BIT(2) #define SPE_OP_PKT_ST BIT(0) -#define SPE_OP_PKT_IS_LDST_SVE(v) (((v) & (BIT(3) | BIT(1))) == 0x8) +#define SPE_OP_PKT_LDST_SUBCLASS_SVE_SME_REG(v) (((v) & (BIT(3) | BIT(1))) == 0x8) #define SPE_OP_PKT_SVE_SG BIT(7) /* @@ -148,7 +169,17 @@ enum arm_spe_events { #define SPE_OP_PKT_SVE_PRED BIT(2) #define SPE_OP_PKT_SVE_FP BIT(1) -#define SPE_OP_PKT_IS_INDIRECT_BRANCH(v) (((v) & GENMASK_ULL(7, 1)) == 0x2) +#define SPE_OP_PKT_LDST_SUBCLASS_GCS(v) (((v) & (GENMASK_ULL(7, 3) | BIT(1))) == 0x40) + +#define SPE_OP_PKT_GCS_COMM BIT(2) + +#define SPE_OP_PKT_CR_MASK GENMASK_ULL(4, 3) +#define SPE_OP_PKT_CR_BL(v) (FIELD_GET(SPE_OP_PKT_CR_MASK, (v)) == 1) +#define SPE_OP_PKT_CR_RET(v) (FIELD_GET(SPE_OP_PKT_CR_MASK, (v)) == 2) +#define SPE_OP_PKT_CR_NON_BL_RET(v) (FIELD_GET(SPE_OP_PKT_CR_MASK, (v)) == 3) +#define SPE_OP_PKT_GCS BIT(2) +#define SPE_OP_PKT_INDIRECT_BRANCH BIT(1) +#define SPE_OP_PKT_COND BIT(0) const char *arm_spe_pkt_name(enum arm_spe_pkt_type); diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 12761c39788f..e5835042acdf 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -37,6 +37,25 @@ #include "../../arch/arm64/include/asm/cputype.h" #define MAX_TIMESTAMP (~0ULL) +#define is_ldst_op(op) (!!((op) & ARM_SPE_OP_LDST)) + +#define is_simd_op(op) (!!((op) & (ARM_SPE_OP_SIMD_FP | ARM_SPE_OP_SVE | \ + ARM_SPE_OP_SME | ARM_SPE_OP_ASE))) + +#define is_mem_op(op) (is_ldst_op(op) || is_simd_op(op)) + +#define ARM_SPE_CACHE_EVENT(lvl) \ + (ARM_SPE_##lvl##_ACCESS | ARM_SPE_##lvl##_MISS) + +#define arm_spe_is_cache_level(type, lvl) \ + ((type) & ARM_SPE_CACHE_EVENT(lvl)) + +#define arm_spe_is_cache_hit(type, lvl) \ + (((type) & ARM_SPE_CACHE_EVENT(lvl)) == ARM_SPE_##lvl##_ACCESS) + +#define arm_spe_is_cache_miss(type, lvl) \ + ((type) & ARM_SPE_##lvl##_MISS) + struct arm_spe { struct auxtrace auxtrace; struct auxtrace_queues queues; @@ -60,7 +79,6 @@ struct arm_spe { u8 sample_remote_access; u8 sample_memory; u8 sample_instructions; - u64 instructions_sample_period; u64 l1d_miss_id; u64 l1d_access_id; @@ -99,8 +117,9 @@ struct arm_spe_queue { u64 time; u64 timestamp; struct thread *thread; - u64 period_instructions; + u64 sample_count; u32 flags; + struct branch_stack *last_branch; }; struct data_source_handle { @@ -225,12 +244,22 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe, speq->pid = -1; speq->tid = -1; speq->cpu = -1; - speq->period_instructions = 0; /* params set */ params.get_trace = arm_spe_get_trace; params.data = speq; + if (spe->synth_opts.last_branch) { + size_t sz = sizeof(struct branch_stack); + + /* Allocate up to two entries for PBT + TGT */ + sz += sizeof(struct branch_entry) * + min(spe->synth_opts.last_branch_sz, 2U); + speq->last_branch = zalloc(sz); + if (!speq->last_branch) + goto out_free; + } + /* create new decoder */ speq->decoder = arm_spe_decoder_new(¶ms); if (!speq->decoder) @@ -240,6 +269,7 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe, out_free: zfree(&speq->event_buf); + zfree(&speq->last_branch); free(speq); return NULL; @@ -290,15 +320,28 @@ static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid) return 0; } -static u64 *arm_spe__get_metadata_by_cpu(struct arm_spe *spe, u64 cpu) +static u64 *arm_spe__get_metadata_by_cpu(struct arm_spe *spe, int cpu) { u64 i; if (!spe->metadata) return NULL; + /* CPU ID is -1 for per-thread mode */ + if (cpu < 0) { + /* + * On the heterogeneous system, due to CPU ID is -1, + * cannot confirm the data source packet is supported. + */ + if (!spe->is_homogeneous) + return NULL; + + /* In homogeneous system, simply use CPU0's metadata */ + return spe->metadata[0]; + } + for (i = 0; i < spe->metadata_nr_cpu; i++) - if (spe->metadata[i][ARM_SPE_CPU] == cpu) + if (spe->metadata[i][ARM_SPE_CPU] == (u64)cpu) return spe->metadata[i]; return NULL; @@ -308,17 +351,28 @@ static struct simd_flags arm_spe__synth_simd_flags(const struct arm_spe_record * { struct simd_flags simd_flags = {}; - if ((record->op & ARM_SPE_OP_LDST) && (record->op & ARM_SPE_OP_SVE_LDST)) - simd_flags.arch |= SIMD_OP_FLAGS_ARCH_SVE; - - if ((record->op & ARM_SPE_OP_OTHER) && (record->op & ARM_SPE_OP_SVE_OTHER)) + if (record->op & ARM_SPE_OP_SVE) simd_flags.arch |= SIMD_OP_FLAGS_ARCH_SVE; - - if (record->type & ARM_SPE_SVE_PARTIAL_PRED) - simd_flags.pred |= SIMD_OP_FLAGS_PRED_PARTIAL; - - if (record->type & ARM_SPE_SVE_EMPTY_PRED) - simd_flags.pred |= SIMD_OP_FLAGS_PRED_EMPTY; + else if (record->op & ARM_SPE_OP_SME) + simd_flags.arch |= SIMD_OP_FLAGS_ARCH_SME; + else if (record->op & (ARM_SPE_OP_ASE | ARM_SPE_OP_SIMD_FP)) + simd_flags.arch |= SIMD_OP_FLAGS_ARCH_ASE; + + if (record->op & ARM_SPE_OP_SVE) { + if (!(record->op & ARM_SPE_OP_PRED)) + simd_flags.pred = SIMD_OP_FLAGS_PRED_DISABLED; + else if (record->type & ARM_SPE_SVE_PARTIAL_PRED) + simd_flags.pred = SIMD_OP_FLAGS_PRED_PARTIAL; + else if (record->type & ARM_SPE_SVE_EMPTY_PRED) + simd_flags.pred = SIMD_OP_FLAGS_PRED_EMPTY; + else + simd_flags.pred = SIMD_OP_FLAGS_PRED_FULL; + } else { + if (record->type & ARM_SPE_SVE_PARTIAL_PRED) + simd_flags.pred = SIMD_OP_FLAGS_PRED_PARTIAL; + else if (record->type & ARM_SPE_SVE_EMPTY_PRED) + simd_flags.pred = SIMD_OP_FLAGS_PRED_EMPTY; + } return simd_flags; } @@ -337,7 +391,7 @@ static void arm_spe_prep_sample(struct arm_spe *spe, sample->cpumode = arm_spe_cpumode(spe, sample->ip); sample->pid = speq->pid; sample->tid = speq->tid; - sample->period = 1; + sample->period = spe->synth_opts.period; sample->cpu = speq->cpu; sample->simd_flags = arm_spe__synth_simd_flags(record); @@ -346,6 +400,88 @@ static void arm_spe_prep_sample(struct arm_spe *spe, event->sample.header.size = sizeof(struct perf_event_header); } +static void arm_spe__prep_branch_stack(struct arm_spe_queue *speq) +{ + struct arm_spe *spe = speq->spe; + struct arm_spe_record *record = &speq->decoder->record; + struct branch_stack *bstack = speq->last_branch; + struct branch_flags *bs_flags; + unsigned int last_branch_sz = spe->synth_opts.last_branch_sz; + bool have_tgt = !!(speq->flags & PERF_IP_FLAG_BRANCH); + bool have_pbt = last_branch_sz >= (have_tgt + 1U) && record->prev_br_tgt; + size_t sz = sizeof(struct branch_stack) + + sizeof(struct branch_entry) * min(last_branch_sz, 2U) /* PBT + TGT */; + int i = 0; + + /* Clean up branch stack */ + memset(bstack, 0x0, sz); + + if (!have_tgt && !have_pbt) + return; + + if (have_tgt) { + bstack->entries[i].from = record->from_ip; + bstack->entries[i].to = record->to_ip; + + bs_flags = &bstack->entries[i].flags; + bs_flags->value = 0; + + if (record->op & ARM_SPE_OP_BR_CR_BL) { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND_CALL; + else + bs_flags->type |= PERF_BR_CALL; + /* + * Indirect branch instruction without link (e.g. BR), + * take this case as function return. + */ + } else if (record->op & ARM_SPE_OP_BR_CR_RET || + record->op & ARM_SPE_OP_BR_INDIRECT) { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND_RET; + else + bs_flags->type |= PERF_BR_RET; + } else if (record->op & ARM_SPE_OP_BR_CR_NON_BL_RET) { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND; + else + bs_flags->type |= PERF_BR_UNCOND; + } else { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND; + else + bs_flags->type |= PERF_BR_UNKNOWN; + } + + if (record->type & ARM_SPE_BRANCH_MISS) { + bs_flags->mispred = 1; + bs_flags->predicted = 0; + } else { + bs_flags->mispred = 0; + bs_flags->predicted = 1; + } + + if (record->type & ARM_SPE_BRANCH_NOT_TAKEN) + bs_flags->not_taken = 1; + + if (record->type & ARM_SPE_IN_TXN) + bs_flags->in_tx = 1; + + bs_flags->cycles = min(record->latency, 0xFFFFU); + i++; + } + + if (have_pbt) { + bs_flags = &bstack->entries[i].flags; + bs_flags->type |= PERF_BR_UNKNOWN; + bstack->entries[i].to = record->prev_br_tgt; + i++; + } + + bstack->nr = i; + bstack->hw_idx = -1ULL; +} + static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type) { event->header.size = perf_event__sample_event_size(sample, type, 0); @@ -374,23 +510,28 @@ arm_spe_deliver_synth_event(struct arm_spe *spe, } static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, - u64 spe_events_id, u64 data_src) + u64 spe_events_id, + union perf_mem_data_src data_src) { struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; sample.stream_id = spe_events_id; sample.addr = record->virt_addr; sample.phys_addr = record->phys_addr; - sample.data_src = data_src; + sample.data_src = data_src.val; sample.weight = record->latency; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, @@ -399,8 +540,10 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; @@ -408,50 +551,57 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, sample.addr = record->to_ip; sample.weight = record->latency; sample.flags = speq->flags; + sample.branch_stack = speq->last_branch; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, - u64 spe_events_id, u64 data_src) + u64 spe_events_id, + union perf_mem_data_src data_src) { struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; - - /* - * Handles perf instruction sampling period. - */ - speq->period_instructions++; - if (speq->period_instructions < spe->instructions_sample_period) - return 0; - speq->period_instructions = 0; + struct perf_sample sample; + int ret; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; sample.stream_id = spe_events_id; sample.addr = record->to_ip; sample.phys_addr = record->phys_addr; - sample.data_src = data_src; - sample.period = spe->instructions_sample_period; + sample.data_src = data_src.val; sample.weight = record->latency; sample.flags = speq->flags; + sample.branch_stack = speq->last_branch; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static const struct midr_range common_ds_encoding_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A715), MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A720AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A725), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_OLYMPUS), {}, }; @@ -460,6 +610,11 @@ static const struct midr_range ampereone_ds_encoding_cpus[] = { {}, }; +static const struct midr_range hisi_hip_ds_encoding_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_HISI_HIP12), + {}, +}; + static void arm_spe__sample_flags(struct arm_spe_queue *speq) { const struct arm_spe_record *record = &speq->decoder->record; @@ -470,6 +625,26 @@ static void arm_spe__sample_flags(struct arm_spe_queue *speq) if (record->type & ARM_SPE_BRANCH_MISS) speq->flags |= PERF_IP_FLAG_BRANCH_MISS; + + if (record->type & ARM_SPE_BRANCH_NOT_TAKEN) + speq->flags |= PERF_IP_FLAG_NOT_TAKEN; + + if (record->type & ARM_SPE_IN_TXN) + speq->flags |= PERF_IP_FLAG_IN_TX; + + if (record->op & ARM_SPE_OP_BR_COND) + speq->flags |= PERF_IP_FLAG_CONDITIONAL; + + if (record->op & ARM_SPE_OP_BR_CR_BL) + speq->flags |= PERF_IP_FLAG_CALL; + else if (record->op & ARM_SPE_OP_BR_CR_RET) + speq->flags |= PERF_IP_FLAG_RETURN; + /* + * Indirect branch instruction without link (e.g. BR), + * take it as a function return. + */ + else if (record->op & ARM_SPE_OP_BR_INDIRECT) + speq->flags |= PERF_IP_FLAG_RETURN; } } @@ -534,8 +709,8 @@ static void arm_spe__synth_data_source_common(const struct arm_spe_record *recor * socket */ case ARM_SPE_COMMON_DS_REMOTE: - data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1; - data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE; + data_src->mem_lvl = PERF_MEM_LVL_NA; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_NA; data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; break; @@ -587,35 +762,217 @@ static void arm_spe__synth_data_source_ampereone(const struct arm_spe_record *re arm_spe__synth_data_source_common(&common_record, data_src); } +static void arm_spe__synth_data_source_hisi_hip(const struct arm_spe_record *record, + union perf_mem_data_src *data_src) +{ + /* Use common synthesis method to handle store operations */ + if (record->op & ARM_SPE_OP_ST) { + arm_spe__synth_data_source_common(record, data_src); + return; + } + + switch (record->source) { + case ARM_SPE_HISI_HIP_PEER_CPU: + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2; + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; + break; + case ARM_SPE_HISI_HIP_PEER_CPU_HITM: + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2; + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; + break; + case ARM_SPE_HISI_HIP_L3: + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + data_src->mem_snoop = PERF_MEM_SNOOP_HIT; + break; + case ARM_SPE_HISI_HIP_L3_HITM: + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + break; + case ARM_SPE_HISI_HIP_PEER_CLUSTER: + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; + break; + case ARM_SPE_HISI_HIP_PEER_CLUSTER_HITM: + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; + break; + case ARM_SPE_HISI_HIP_REMOTE_SOCKET: + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE; + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; + break; + case ARM_SPE_HISI_HIP_REMOTE_SOCKET_HITM: + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE; + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; + break; + case ARM_SPE_HISI_HIP_LOCAL_MEM: + data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM; + data_src->mem_snoop = PERF_MEM_SNOOP_NONE; + break; + case ARM_SPE_HISI_HIP_REMOTE_MEM: + data_src->mem_lvl = PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM; + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; + break; + case ARM_SPE_HISI_HIP_NC_DEV: + data_src->mem_lvl = PERF_MEM_LVL_IO | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_IO; + data_src->mem_snoop = PERF_MEM_SNOOP_NONE; + break; + case ARM_SPE_HISI_HIP_L2: + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2; + data_src->mem_snoop = PERF_MEM_SNOOP_NONE; + break; + case ARM_SPE_HISI_HIP_L2_HITM: + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2; + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + break; + case ARM_SPE_HISI_HIP_L1: + data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1; + data_src->mem_snoop = PERF_MEM_SNOOP_NONE; + break; + default: + break; + } +} + static const struct data_source_handle data_source_handles[] = { DS(common_ds_encoding_cpus, data_source_common), DS(ampereone_ds_encoding_cpus, data_source_ampereone), + DS(hisi_hip_ds_encoding_cpus, data_source_hisi_hip), }; -static void arm_spe__synth_memory_level(const struct arm_spe_record *record, - union perf_mem_data_src *data_src) +static void arm_spe__synth_ld_memory_level(const struct arm_spe_record *record, + union perf_mem_data_src *data_src) { - if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) { - data_src->mem_lvl = PERF_MEM_LVL_L3; + /* + * To find a cache hit, search in ascending order from the lower level + * caches to the higher level caches. This reflects the best scenario + * for a cache hit. + */ + if (arm_spe_is_cache_hit(record->type, L1D)) { + data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1; + } else if (record->type & ARM_SPE_RECENTLY_FETCHED) { + data_src->mem_lvl = PERF_MEM_LVL_LFB | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_LFB; + } else if (arm_spe_is_cache_hit(record->type, L2D)) { + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2; + } else if (arm_spe_is_cache_hit(record->type, LLC)) { + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + /* + * To find a cache miss, search in descending order from the higher + * level cache to the lower level cache. This represents the worst + * scenario for a cache miss. + */ + } else if (arm_spe_is_cache_miss(record->type, LLC)) { + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_MISS; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + } else if (arm_spe_is_cache_miss(record->type, L2D)) { + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_MISS; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2; + } else if (arm_spe_is_cache_miss(record->type, L1D)) { + data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1; + } +} - if (record->type & ARM_SPE_LLC_MISS) - data_src->mem_lvl |= PERF_MEM_LVL_MISS; - else - data_src->mem_lvl |= PERF_MEM_LVL_HIT; - } else if (record->type & (ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS)) { +static void arm_spe__synth_st_memory_level(const struct arm_spe_record *record, + union perf_mem_data_src *data_src) +{ + /* Record the greatest level info for a store operation. */ + if (arm_spe_is_cache_level(record->type, LLC)) { + data_src->mem_lvl = PERF_MEM_LVL_L3; + data_src->mem_lvl |= arm_spe_is_cache_miss(record->type, LLC) ? + PERF_MEM_LVL_MISS : PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + } else if (arm_spe_is_cache_level(record->type, L2D)) { + data_src->mem_lvl = PERF_MEM_LVL_L2; + data_src->mem_lvl |= arm_spe_is_cache_miss(record->type, L2D) ? + PERF_MEM_LVL_MISS : PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2; + } else if (arm_spe_is_cache_level(record->type, L1D)) { data_src->mem_lvl = PERF_MEM_LVL_L1; + data_src->mem_lvl |= arm_spe_is_cache_miss(record->type, L1D) ? + PERF_MEM_LVL_MISS : PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1; + } +} - if (record->type & ARM_SPE_L1D_MISS) - data_src->mem_lvl |= PERF_MEM_LVL_MISS; - else - data_src->mem_lvl |= PERF_MEM_LVL_HIT; +static void arm_spe__synth_memory_level(struct arm_spe_queue *speq, + const struct arm_spe_record *record, + union perf_mem_data_src *data_src) +{ + struct arm_spe *spe = speq->spe; + + /* + * The data source packet contains more info for cache levels for + * peer snooping. So respect the memory level if has been set by + * data source parsing. + */ + if (!data_src->mem_lvl) { + if (data_src->mem_op == PERF_MEM_OP_LOAD) + arm_spe__synth_ld_memory_level(record, data_src); + if (data_src->mem_op == PERF_MEM_OP_STORE) + arm_spe__synth_st_memory_level(record, data_src); + } + + if (!data_src->mem_lvl) { + data_src->mem_lvl = PERF_MEM_LVL_NA; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_NA; + } + + /* + * If 'mem_snoop' has been set by data source packet, skip to set + * it at here. + */ + if (!data_src->mem_snoop) { + if (record->type & ARM_SPE_DATA_SNOOPED) { + if (record->type & ARM_SPE_HITM) + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + else + data_src->mem_snoop = PERF_MEM_SNOOP_HIT; + } else { + u64 *metadata = + arm_spe__get_metadata_by_cpu(spe, speq->cpu); + + /* + * Set NA ("Not available") mode if no meta data or the + * SNOOPED event is not supported. + */ + if (!metadata || + !(metadata[ARM_SPE_CAP_EVENT_FILTER] & ARM_SPE_DATA_SNOOPED)) + data_src->mem_snoop = PERF_MEM_SNOOP_NA; + else + data_src->mem_snoop = PERF_MEM_SNOOP_NONE; + } } - if (record->type & ARM_SPE_REMOTE_ACCESS) - data_src->mem_lvl |= PERF_MEM_LVL_REM_CCE1; + if (!data_src->mem_remote) { + if (record->type & ARM_SPE_REMOTE_ACCESS) + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; + } } -static bool arm_spe__synth_ds(struct arm_spe_queue *speq, +static void arm_spe__synth_ds(struct arm_spe_queue *speq, const struct arm_spe_record *record, union perf_mem_data_src *data_src) { @@ -629,55 +986,43 @@ static bool arm_spe__synth_ds(struct arm_spe_queue *speq, const char *cpuid; pr_warning_once("Old SPE metadata, re-record to improve decode accuracy\n"); - cpuid = perf_env__cpuid(spe->session->evlist->env); + cpuid = perf_env__cpuid(perf_session__env(spe->session)); midr = strtol(cpuid, NULL, 16); } else { - /* CPU ID is -1 for per-thread mode */ - if (speq->cpu < 0) { - /* - * On the heterogeneous system, due to CPU ID is -1, - * cannot confirm the data source packet is supported. - */ - if (!spe->is_homogeneous) - return false; - - /* In homogeneous system, simply use CPU0's metadata */ - if (spe->metadata) - metadata = spe->metadata[0]; - } else { - metadata = arm_spe__get_metadata_by_cpu(spe, speq->cpu); - } - + metadata = arm_spe__get_metadata_by_cpu(spe, speq->cpu); if (!metadata) - return false; + return; midr = metadata[ARM_SPE_CPU_MIDR]; } for (i = 0; i < ARRAY_SIZE(data_source_handles); i++) { if (is_midr_in_range_list(midr, data_source_handles[i].midr_ranges)) { - data_source_handles[i].ds_synth(record, data_src); - return true; + return data_source_handles[i].ds_synth(record, data_src); } } - return false; + return; } -static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq, - const struct arm_spe_record *record) +static union perf_mem_data_src +arm_spe__synth_data_source(struct arm_spe_queue *speq, + const struct arm_spe_record *record) { - union perf_mem_data_src data_src = { .mem_op = PERF_MEM_OP_NA }; + union perf_mem_data_src data_src = {}; + + if (!is_mem_op(record->op)) + return data_src; if (record->op & ARM_SPE_OP_LD) data_src.mem_op = PERF_MEM_OP_LOAD; else if (record->op & ARM_SPE_OP_ST) data_src.mem_op = PERF_MEM_OP_STORE; else - return 0; + data_src.mem_op = PERF_MEM_OP_NA; - if (!arm_spe__synth_ds(speq, record, &data_src)) - arm_spe__synth_memory_level(record, &data_src); + arm_spe__synth_ds(speq, record, &data_src); + arm_spe__synth_memory_level(speq, record, &data_src); if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) { data_src.mem_dtlb = PERF_MEM_TLB_WK; @@ -688,16 +1033,24 @@ static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq, data_src.mem_dtlb |= PERF_MEM_TLB_HIT; } - return data_src.val; + return data_src; } static int arm_spe_sample(struct arm_spe_queue *speq) { const struct arm_spe_record *record = &speq->decoder->record; struct arm_spe *spe = speq->spe; - u64 data_src; + union perf_mem_data_src data_src; int err; + /* + * Discard all samples until period is reached + */ + speq->sample_count++; + if (speq->sample_count < spe->synth_opts.period) + return 0; + speq->sample_count = 0; + arm_spe__sample_flags(speq); data_src = arm_spe__synth_data_source(speq, record); @@ -749,6 +1102,10 @@ static int arm_spe_sample(struct arm_spe_queue *speq) } } + if (spe->synth_opts.last_branch && + (spe->sample_branch || spe->sample_instructions)) + arm_spe__prep_branch_stack(speq); + if (spe->sample_branch && (record->op & ARM_SPE_OP_BRANCH_ERET)) { err = arm_spe__synth_branch_sample(speq, spe->branch_id); if (err) @@ -763,11 +1120,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq) return err; } - /* - * When data_src is zero it means the record is not a memory operation, - * skip to synthesize memory sample for this case. - */ - if (spe->sample_memory && data_src) { + if (spe->sample_memory && is_mem_op(record->op)) { err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src); if (err) return err; @@ -1240,6 +1593,7 @@ static void arm_spe_free_queue(void *priv) thread__zput(speq->thread); arm_spe_decoder_free(speq->decoder); zfree(&speq->event_buf); + zfree(&speq->last_branch); free(speq); } @@ -1296,6 +1650,7 @@ static const char * const metadata_per_cpu_fmts[] = { [ARM_SPE_CPU_MIDR] = " MIDR :0x%"PRIx64"\n", [ARM_SPE_CPU_PMU_TYPE] = " PMU Type :%"PRId64"\n", [ARM_SPE_CAP_MIN_IVAL] = " Min Interval :%"PRId64"\n", + [ARM_SPE_CAP_EVENT_FILTER] = " Event Filter :0x%"PRIx64"\n", }; static void arm_spe_print_info(struct arm_spe *spe, __u64 *arr) @@ -1392,12 +1747,10 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) attr.exclude_guest = evsel->core.attr.exclude_guest; attr.sample_id_all = evsel->core.attr.sample_id_all; attr.read_format = evsel->core.attr.read_format; + attr.sample_period = spe->synth_opts.period; /* create new id val to be a fixed offset from evsel id */ - id = evsel->core.id[0] + 1000000000; - - if (!id) - id = 1; + id = auxtrace_synth_id_range_start(evsel); if (spe->synth_opts.flc) { spe->sample_flc = true; @@ -1459,6 +1812,19 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) id += 1; } + if (spe->synth_opts.last_branch) { + if (spe->synth_opts.last_branch_sz > 2) + pr_debug("Arm SPE supports only two bstack entries (PBT+TGT).\n"); + + attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } + if (spe->synth_opts.branches) { spe->sample_branch = true; @@ -1495,25 +1861,15 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) } if (spe->synth_opts.instructions) { - if (spe->synth_opts.period_type != PERF_ITRACE_PERIOD_INSTRUCTIONS) { - pr_warning("Only instruction-based sampling period is currently supported by Arm SPE.\n"); - goto synth_instructions_out; - } - if (spe->synth_opts.period > 1) - pr_warning("Arm SPE has a hardware-based sample period.\n" - "Additional instruction events will be discarded by --itrace\n"); - spe->sample_instructions = true; attr.config = PERF_COUNT_HW_INSTRUCTIONS; - attr.sample_period = spe->synth_opts.period; - spe->instructions_sample_period = attr.sample_period; + err = perf_session__deliver_synth_attr_event(session, &attr, id); if (err) return err; spe->instructions_id = id; arm_spe_set_event_name(evlist, id, "instructions"); } -synth_instructions_out: return 0; } @@ -1622,10 +1978,23 @@ int arm_spe_process_auxtrace_info(union perf_event *event, if (dump_trace) return 0; - if (session->itrace_synth_opts && session->itrace_synth_opts->set) + if (session->itrace_synth_opts && session->itrace_synth_opts->set) { spe->synth_opts = *session->itrace_synth_opts; - else + } else { itrace_synth_opts__set_default(&spe->synth_opts, false); + /* Default nanoseconds period not supported */ + spe->synth_opts.period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS; + spe->synth_opts.period = 1; + } + + if (spe->synth_opts.period_type != PERF_ITRACE_PERIOD_INSTRUCTIONS) { + ui__error("You must only use i (instructions) --itrace period with Arm SPE. e.g --itrace=i1i\n"); + err = -EINVAL; + goto err_free_queues; + } + if (spe->synth_opts.period > 1) + ui__warning("Arm SPE has a hardware-based sampling period.\n\n" + "--itrace periods > 1i downsample by an interval of n SPE samples rather than n instructions.\n"); err = arm_spe_synth_events(spe, session); if (err) diff --git a/tools/perf/util/arm-spe.h b/tools/perf/util/arm-spe.h index 390679a4af2f..3966df1856d8 100644 --- a/tools/perf/util/arm-spe.h +++ b/tools/perf/util/arm-spe.h @@ -47,6 +47,8 @@ enum { ARM_SPE_CPU_PMU_TYPE, /* Minimal interval */ ARM_SPE_CAP_MIN_IVAL, + /* Event filter */ + ARM_SPE_CAP_EVENT_FILTER, ARM_SPE_CPU_PRIV_MAX, }; diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 4940be4a0569..858ce2b01812 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -2,8 +2,8 @@ #include "arm64-frame-pointer-unwind-support.h" #include "callchain.h" #include "event.h" -#include "perf_regs.h" // SMPL_REG_MASK #include "unwind.h" +#include <string.h> #define perf_event_arm_regs perf_event_arm64_regs #include "../../arch/arm64/include/uapi/asm/perf_regs.h" @@ -14,10 +14,17 @@ struct entries { size_t length; }; +#define SMPL_REG_MASK(b) (1ULL << (b)) + static bool get_leaf_frame_caller_enabled(struct perf_sample *sample) { - return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs - && sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR); + struct regs_dump *regs; + + if (callchain_param.record_mode != CALLCHAIN_FP) + return false; + + regs = perf_sample__user_regs(sample); + return regs->regs && regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_LR); } static int add_entry(struct unwind_entry *entry, void *arg) @@ -32,7 +39,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr { int ret; struct entries entries = {}; - struct regs_dump old_regs = sample->user_regs; + struct regs_dump old_regs, *regs; if (!get_leaf_frame_caller_enabled(sample)) return 0; @@ -42,19 +49,20 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr * and set its mask. SP is not used when doing the unwinding but it * still needs to be set to prevent failures. */ - - if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) { - sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC); - sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1]; + regs = perf_sample__user_regs(sample); + memcpy(&old_regs, regs, sizeof(*regs)); + if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) { + regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC); + regs->cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1]; } - if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) { - sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP); - sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; + if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) { + regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP); + regs->cache_regs[PERF_REG_ARM64_SP] = 0; } ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); - sample->user_regs = old_regs; + memcpy(regs, &old_regs, sizeof(*regs)); if (ret || entries.length != 2) return ret; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 4d1633d87eff..a224687ffbc1 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -55,12 +55,29 @@ #include "hisi-ptt.h" #include "s390-cpumsf.h" #include "util/mmap.h" +#include "powerpc-vpadtl.h" #include <linux/ctype.h> #include "symbol/kallsyms.h" #include <internal/lib.h> #include "util/sample.h" +#define AUXTRACE_SYNTH_EVENT_ID_OFFSET 1000000000ULL + +/* + * Event IDs are allocated sequentially, so a big offset from any + * existing ID will reach a unused range. + */ +u64 auxtrace_synth_id_range_start(struct evsel *evsel) +{ + u64 id = evsel->core.id[0] + AUXTRACE_SYNTH_EVENT_ID_OFFSET; + + if (!id) + id = 1; + + return id; +} + /* * Make a group from 'leader' to 'last', requiring that the events were not * already grouped to a different leader. @@ -185,10 +202,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, if (per_cpu) { mp->cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx); - if (evlist->core.threads) - mp->tid = perf_thread_map__pid(evlist->core.threads, 0); - else - mp->tid = -1; + mp->tid = perf_thread_map__pid(evlist->core.threads, 0); } else { mp->cpu.cpu = -1; mp->tid = perf_thread_map__pid(evlist->core.threads, idx); @@ -1173,16 +1187,19 @@ static int auxtrace_queue_data_cb(struct perf_session *session, if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE) return 0; + perf_sample__init(&sample, /*all=*/false); err = evlist__parse_sample(session->evlist, event, &sample); if (err) - return err; - - if (!sample.aux_sample.size) - return 0; + goto out; - offset += sample.aux_sample.data - (void *)event; + if (sample.aux_sample.size) { + offset += sample.aux_sample.data - (void *)event; - return session->auxtrace->queue_data(session, &sample, NULL, offset); + err = session->auxtrace->queue_data(session, &sample, NULL, offset); + } +out: + perf_sample__exit(&sample); + return err; } int auxtrace_queue_data(struct perf_session *session, bool samples, bool events) @@ -1362,7 +1379,8 @@ static void unleader_auxtrace(struct perf_session *session) } } -int perf_event__process_auxtrace_info(struct perf_session *session, +int perf_event__process_auxtrace_info(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { enum auxtrace_type type = event->auxtrace_info.type; @@ -1390,6 +1408,9 @@ int perf_event__process_auxtrace_info(struct perf_session *session, case PERF_AUXTRACE_HISI_PTT: err = hisi_ptt_process_auxtrace_info(event, session); break; + case PERF_AUXTRACE_VPA_DTL: + err = powerpc_vpadtl_process_auxtrace_info(event, session); + break; case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; @@ -1403,7 +1424,8 @@ int perf_event__process_auxtrace_info(struct perf_session *session, return 0; } -s64 perf_event__process_auxtrace(struct perf_session *session, +s64 perf_event__process_auxtrace(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { s64 err; @@ -1800,7 +1822,8 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats) } } -int perf_event__process_auxtrace_error(struct perf_session *session, +int perf_event__process_auxtrace_error(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { if (auxtrace__dont_decode(session)) @@ -1887,7 +1910,7 @@ int __weak compat_auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail) } static int __auxtrace_mmap__read(struct mmap *map, - struct auxtrace_record *itr, + struct auxtrace_record *itr, struct perf_env *env, const struct perf_tool *tool, process_auxtrace_t fn, bool snapshot, size_t snapshot_size) { @@ -1897,7 +1920,7 @@ static int __auxtrace_mmap__read(struct mmap *map, size_t size, head_off, old_off, len1, len2, padding; union perf_event ev; void *data1, *data2; - int kernel_is_64_bit = perf_env__kernel_is_64_bit(evsel__env(NULL)); + int kernel_is_64_bit = perf_env__kernel_is_64_bit(env); head = auxtrace_mmap__read_head(mm, kernel_is_64_bit); @@ -1999,17 +2022,18 @@ static int __auxtrace_mmap__read(struct mmap *map, } int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, - const struct perf_tool *tool, process_auxtrace_t fn) + struct perf_env *env, const struct perf_tool *tool, + process_auxtrace_t fn) { - return __auxtrace_mmap__read(map, itr, tool, fn, false, 0); + return __auxtrace_mmap__read(map, itr, env, tool, fn, false, 0); } int auxtrace_mmap__read_snapshot(struct mmap *map, - struct auxtrace_record *itr, + struct auxtrace_record *itr, struct perf_env *env, const struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size) { - return __auxtrace_mmap__read(map, itr, tool, fn, true, snapshot_size); + return __auxtrace_mmap__read(map, itr, env, tool, fn, true, snapshot_size); } /** diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index b0db84d27b25..6947f3f284c0 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -8,21 +8,17 @@ #define __PERF_AUXTRACE_H #include <sys/types.h> -#include <errno.h> -#include <stdbool.h> -#include <stddef.h> #include <stdio.h> // FILE -#include <linux/list.h> #include <linux/perf_event.h> #include <linux/types.h> -#include <perf/cpumap.h> -#include <asm/bitsperlong.h> #include <asm/barrier.h> +#include <perf/cpumap.h> union perf_event; struct perf_session; struct evlist; struct evsel; +struct perf_env; struct perf_tool; struct mmap; struct perf_sample; @@ -49,6 +45,7 @@ enum auxtrace_type { PERF_AUXTRACE_ARM_SPE, PERF_AUXTRACE_S390_CPUMSF, PERF_AUXTRACE_HISI_PTT, + PERF_AUXTRACE_VPA_DTL, }; enum itrace_period_type { @@ -457,8 +454,6 @@ struct addr_filters { struct auxtrace_cache; -#ifdef HAVE_AUXTRACE_SUPPORT - u64 compat_auxtrace_mmap__read_head(struct auxtrace_mmap *mm); int compat_auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail); @@ -512,10 +507,11 @@ typedef int (*process_auxtrace_t)(const struct perf_tool *tool, size_t len1, void *data2, size_t len2); int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr, - const struct perf_tool *tool, process_auxtrace_t fn); + struct perf_env *env, const struct perf_tool *tool, + process_auxtrace_t fn); int auxtrace_mmap__read_snapshot(struct mmap *map, - struct auxtrace_record *itr, + struct auxtrace_record *itr, struct perf_env *env, const struct perf_tool *tool, process_auxtrace_t fn, size_t snapshot_size); @@ -612,11 +608,14 @@ void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int int code, int cpu, pid_t pid, pid_t tid, u64 ip, const char *msg, u64 timestamp); -int perf_event__process_auxtrace_info(struct perf_session *session, +int perf_event__process_auxtrace_info(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); -s64 perf_event__process_auxtrace(struct perf_session *session, +s64 perf_event__process_auxtrace(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); -int perf_event__process_auxtrace_error(struct perf_session *session, +int perf_event__process_auxtrace_error(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, const char *str, int unset); @@ -645,6 +644,7 @@ void auxtrace__free_events(struct perf_session *session); void auxtrace__free(struct perf_session *session); bool auxtrace__evsel_is_auxtrace(struct perf_session *session, struct evsel *evsel); +u64 auxtrace_synth_id_range_start(struct evsel *evsel); #define ITRACE_HELP \ " i[period]: synthesize instructions events\n" \ @@ -699,212 +699,4 @@ void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts) opts->range_num = 0; } -#else -#include "debug.h" - -static inline struct auxtrace_record * -auxtrace_record__init(struct evlist *evlist __maybe_unused, - int *err) -{ - *err = 0; - return NULL; -} - -static inline -void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused) -{ -} - -static inline -int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused, - struct evlist *evlist __maybe_unused, - struct record_opts *opts __maybe_unused) -{ - return 0; -} - -static inline -int perf_event__process_auxtrace_info(struct perf_session *session __maybe_unused, - union perf_event *event __maybe_unused) -{ - return 0; -} - -static inline -s64 perf_event__process_auxtrace(struct perf_session *session __maybe_unused, - union perf_event *event __maybe_unused) -{ - return 0; -} - -static inline -int perf_event__process_auxtrace_error(struct perf_session *session __maybe_unused, - union perf_event *event __maybe_unused) -{ - return 0; -} - -static inline -void perf_session__auxtrace_error_inc(struct perf_session *session - __maybe_unused, - union perf_event *event - __maybe_unused) -{ -} - -static inline -void events_stats__auxtrace_error_warn(const struct events_stats *stats - __maybe_unused) -{ -} - -static inline -int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts __maybe_unused, - const char *str __maybe_unused, int unset __maybe_unused) -{ - pr_err("AUX area tracing not supported\n"); - return -EINVAL; -} - -static inline -int itrace_parse_synth_opts(const struct option *opt __maybe_unused, - const char *str __maybe_unused, - int unset __maybe_unused) -{ - pr_err("AUX area tracing not supported\n"); - return -EINVAL; -} - -static inline -int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, - struct record_opts *opts __maybe_unused, - const char *str) -{ - if (!str) - return 0; - pr_err("AUX area tracing not supported\n"); - return -EINVAL; -} - -static inline -int auxtrace_parse_sample_options(struct auxtrace_record *itr __maybe_unused, - struct evlist *evlist __maybe_unused, - struct record_opts *opts __maybe_unused, - const char *str) -{ - if (!str) - return 0; - pr_err("AUX area tracing not supported\n"); - return -EINVAL; -} - -static inline -int auxtrace_parse_aux_action(struct evlist *evlist __maybe_unused) -{ - pr_err("AUX area tracing not supported\n"); - return -EINVAL; -} - -static inline -int auxtrace__process_event(struct perf_session *session __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_sample *sample __maybe_unused, - const struct perf_tool *tool __maybe_unused) -{ - return 0; -} - -static inline -void auxtrace__dump_auxtrace_sample(struct perf_session *session __maybe_unused, - struct perf_sample *sample __maybe_unused) -{ -} - -static inline -int auxtrace__flush_events(struct perf_session *session __maybe_unused, - const struct perf_tool *tool __maybe_unused) -{ - return 0; -} - -static inline -void auxtrace__free_events(struct perf_session *session __maybe_unused) -{ -} - -static inline -void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused) -{ -} - -static inline -void auxtrace__free(struct perf_session *session __maybe_unused) -{ -} - -static inline -int auxtrace_index__write(int fd __maybe_unused, - struct list_head *head __maybe_unused) -{ - return -EINVAL; -} - -static inline -int auxtrace_index__process(int fd __maybe_unused, - u64 size __maybe_unused, - struct perf_session *session __maybe_unused, - bool needs_swap __maybe_unused) -{ - return -EINVAL; -} - -static inline -void auxtrace_index__free(struct list_head *head __maybe_unused) -{ -} - -static inline -bool auxtrace__evsel_is_auxtrace(struct perf_session *session __maybe_unused, - struct evsel *evsel __maybe_unused) -{ - return false; -} - -static inline -int auxtrace_parse_filters(struct evlist *evlist __maybe_unused) -{ - return 0; -} - -int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, - struct auxtrace_mmap_params *mp, - void *userpg, int fd); -void auxtrace_mmap__munmap(struct auxtrace_mmap *mm); -void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp, - off_t auxtrace_offset, - unsigned int auxtrace_pages, - bool auxtrace_overwrite); -void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, - struct evlist *evlist, - struct evsel *evsel, int idx); - -#define ITRACE_HELP "" - -static inline -void itrace_synth_opts__set_time_range(struct itrace_synth_opts *opts - __maybe_unused, - struct perf_time_interval *ptime_range - __maybe_unused, - int range_num __maybe_unused) -{ -} - -static inline -void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts - __maybe_unused) -{ -} - -#endif - #endif diff --git a/tools/perf/util/blake2s.c b/tools/perf/util/blake2s.c new file mode 100644 index 000000000000..ce5d89a19376 --- /dev/null +++ b/tools/perf/util/blake2s.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + * + * This is an implementation of the BLAKE2s hash and PRF functions. + * + * Information: https://blake2.net/ + */ + +#include "blake2s.h" +#include <linux/kernel.h> + +static inline u32 ror32(u32 v, int n) +{ + return (v >> n) | (v << (32 - n)); +} + +static inline void le32_to_cpu_array(u32 a[], size_t n) +{ + for (size_t i = 0; i < n; i++) + a[i] = le32_to_cpu((__force __le32)a[i]); +} + +static inline void cpu_to_le32_array(u32 a[], size_t n) +{ + for (size_t i = 0; i < n; i++) + a[i] = (__force u32)cpu_to_le32(a[i]); +} + +static const u8 blake2s_sigma[10][16] = { + { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, + { 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3 }, + { 11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4 }, + { 7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8 }, + { 9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13 }, + { 2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9 }, + { 12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11 }, + { 13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10 }, + { 6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5 }, + { 10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0 }, +}; + +static inline void blake2s_increment_counter(struct blake2s_ctx *ctx, u32 inc) +{ + ctx->t[0] += inc; + ctx->t[1] += (ctx->t[0] < inc); +} + +static void blake2s_compress(struct blake2s_ctx *ctx, + const u8 *data, size_t nblocks, u32 inc) +{ + u32 m[16]; + u32 v[16]; + int i; + + while (nblocks > 0) { + blake2s_increment_counter(ctx, inc); + memcpy(m, data, BLAKE2S_BLOCK_SIZE); + le32_to_cpu_array(m, ARRAY_SIZE(m)); + memcpy(v, ctx->h, 32); + v[ 8] = BLAKE2S_IV0; + v[ 9] = BLAKE2S_IV1; + v[10] = BLAKE2S_IV2; + v[11] = BLAKE2S_IV3; + v[12] = BLAKE2S_IV4 ^ ctx->t[0]; + v[13] = BLAKE2S_IV5 ^ ctx->t[1]; + v[14] = BLAKE2S_IV6 ^ ctx->f[0]; + v[15] = BLAKE2S_IV7 ^ ctx->f[1]; + +#define G(r, i, a, b, c, d) do { \ + a += b + m[blake2s_sigma[r][2 * i + 0]]; \ + d = ror32(d ^ a, 16); \ + c += d; \ + b = ror32(b ^ c, 12); \ + a += b + m[blake2s_sigma[r][2 * i + 1]]; \ + d = ror32(d ^ a, 8); \ + c += d; \ + b = ror32(b ^ c, 7); \ +} while (0) + +#define ROUND(r) do { \ + G(r, 0, v[0], v[ 4], v[ 8], v[12]); \ + G(r, 1, v[1], v[ 5], v[ 9], v[13]); \ + G(r, 2, v[2], v[ 6], v[10], v[14]); \ + G(r, 3, v[3], v[ 7], v[11], v[15]); \ + G(r, 4, v[0], v[ 5], v[10], v[15]); \ + G(r, 5, v[1], v[ 6], v[11], v[12]); \ + G(r, 6, v[2], v[ 7], v[ 8], v[13]); \ + G(r, 7, v[3], v[ 4], v[ 9], v[14]); \ +} while (0) + ROUND(0); + ROUND(1); + ROUND(2); + ROUND(3); + ROUND(4); + ROUND(5); + ROUND(6); + ROUND(7); + ROUND(8); + ROUND(9); + +#undef G +#undef ROUND + + for (i = 0; i < 8; ++i) + ctx->h[i] ^= v[i] ^ v[i + 8]; + + data += BLAKE2S_BLOCK_SIZE; + --nblocks; + } +} + +static inline void blake2s_set_lastblock(struct blake2s_ctx *ctx) +{ + ctx->f[0] = -1; +} + +void blake2s_update(struct blake2s_ctx *ctx, const u8 *in, size_t inlen) +{ + const size_t fill = BLAKE2S_BLOCK_SIZE - ctx->buflen; + + if (unlikely(!inlen)) + return; + if (inlen > fill) { + memcpy(ctx->buf + ctx->buflen, in, fill); + blake2s_compress(ctx, ctx->buf, 1, BLAKE2S_BLOCK_SIZE); + ctx->buflen = 0; + in += fill; + inlen -= fill; + } + if (inlen > BLAKE2S_BLOCK_SIZE) { + const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); + + blake2s_compress(ctx, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); + in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); + inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); + } + memcpy(ctx->buf + ctx->buflen, in, inlen); + ctx->buflen += inlen; +} + +void blake2s_final(struct blake2s_ctx *ctx, u8 *out) +{ + blake2s_set_lastblock(ctx); + memset(ctx->buf + ctx->buflen, 0, + BLAKE2S_BLOCK_SIZE - ctx->buflen); /* Padding */ + blake2s_compress(ctx, ctx->buf, 1, ctx->buflen); + cpu_to_le32_array(ctx->h, ARRAY_SIZE(ctx->h)); + memcpy(out, ctx->h, ctx->outlen); + memset(ctx, 0, sizeof(*ctx)); +} diff --git a/tools/perf/util/blake2s.h b/tools/perf/util/blake2s.h new file mode 100644 index 000000000000..a1fe81a4bea8 --- /dev/null +++ b/tools/perf/util/blake2s.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#ifndef _CRYPTO_BLAKE2S_H +#define _CRYPTO_BLAKE2S_H + +#include <string.h> +#include <linux/types.h> + +#define BLAKE2S_BLOCK_SIZE 64 + +struct blake2s_ctx { + u32 h[8]; + u32 t[2]; + u32 f[2]; + u8 buf[BLAKE2S_BLOCK_SIZE]; + unsigned int buflen; + unsigned int outlen; +}; + +enum blake2s_iv { + BLAKE2S_IV0 = 0x6A09E667UL, + BLAKE2S_IV1 = 0xBB67AE85UL, + BLAKE2S_IV2 = 0x3C6EF372UL, + BLAKE2S_IV3 = 0xA54FF53AUL, + BLAKE2S_IV4 = 0x510E527FUL, + BLAKE2S_IV5 = 0x9B05688CUL, + BLAKE2S_IV6 = 0x1F83D9ABUL, + BLAKE2S_IV7 = 0x5BE0CD19UL, +}; + +static inline void __blake2s_init(struct blake2s_ctx *ctx, size_t outlen, + const void *key, size_t keylen) +{ + ctx->h[0] = BLAKE2S_IV0 ^ (0x01010000 | keylen << 8 | outlen); + ctx->h[1] = BLAKE2S_IV1; + ctx->h[2] = BLAKE2S_IV2; + ctx->h[3] = BLAKE2S_IV3; + ctx->h[4] = BLAKE2S_IV4; + ctx->h[5] = BLAKE2S_IV5; + ctx->h[6] = BLAKE2S_IV6; + ctx->h[7] = BLAKE2S_IV7; + ctx->t[0] = 0; + ctx->t[1] = 0; + ctx->f[0] = 0; + ctx->f[1] = 0; + ctx->buflen = 0; + ctx->outlen = outlen; + if (keylen) { + memcpy(ctx->buf, key, keylen); + memset(&ctx->buf[keylen], 0, BLAKE2S_BLOCK_SIZE - keylen); + ctx->buflen = BLAKE2S_BLOCK_SIZE; + } +} + +static inline void blake2s_init(struct blake2s_ctx *ctx, size_t outlen) +{ + __blake2s_init(ctx, outlen, NULL, 0); +} + +static inline void blake2s_init_key(struct blake2s_ctx *ctx, size_t outlen, + const void *key, size_t keylen) +{ + __blake2s_init(ctx, outlen, key, keylen); +} + +void blake2s_update(struct blake2s_ctx *ctx, const u8 *in, size_t inlen); + +void blake2s_final(struct blake2s_ctx *ctx, u8 *out); + +#endif /* _CRYPTO_BLAKE2S_H */ diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c index 649392bee7ed..8d3a9a661f26 100644 --- a/tools/perf/util/block-info.c +++ b/tools/perf/util/block-info.c @@ -303,7 +303,7 @@ static int block_range_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, char buf[128]; char *start_line, *end_line; - symbol_conf.disable_add2line_warn = true; + symbol_conf.addr2line_disable_warn = true; start_line = map__srcline(he->ms.map, bi->sym->start + bi->start, he->ms.sym); diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c index 15c42196c24c..7c559fcfd7e0 100644 --- a/tools/perf/util/block-range.c +++ b/tools/perf/util/block-range.c @@ -4,7 +4,7 @@ #include <assert.h> #include <stdlib.h> -struct { +static struct { struct rb_root root; u64 blocks; } block_ranges; diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index c81444059ad0..a27945c279ef 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -1,13 +1,21 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <stddef.h> +#include <stdint.h> +#include <stdio.h> #include <stdlib.h> +#include <string.h> #include <bpf/bpf.h> #include <bpf/btf.h> #include <bpf/libbpf.h> +#include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> +#include <linux/perf_event.h> #include <linux/string.h> +#include <linux/zalloc.h> #include <internal/lib.h> +#include <perf/event.h> #include <symbol/kallsyms.h> #include "bpf-event.h" #include "bpf-utils.h" @@ -151,6 +159,362 @@ static int synthesize_bpf_prog_name(char *buf, int size, return name_len; } +#ifdef HAVE_LIBBPF_STRINGS_SUPPORT + +#define BPF_METADATA_PREFIX "bpf_metadata_" +#define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1) + +static bool name_has_bpf_metadata_prefix(const char **s) +{ + if (strncmp(*s, BPF_METADATA_PREFIX, BPF_METADATA_PREFIX_LEN) != 0) + return false; + *s += BPF_METADATA_PREFIX_LEN; + return true; +} + +struct bpf_metadata_map { + struct btf *btf; + const struct btf_type *datasec; + void *rodata; + size_t rodata_size; + unsigned int num_vars; +}; + +static int bpf_metadata_read_map_data(__u32 map_id, struct bpf_metadata_map *map) +{ + int map_fd; + struct bpf_map_info map_info; + __u32 map_info_len; + int key; + struct btf *btf; + const struct btf_type *datasec; + struct btf_var_secinfo *vsi; + unsigned int vlen, vars; + void *rodata; + + map_fd = bpf_map_get_fd_by_id(map_id); + if (map_fd < 0) + return -1; + + memset(&map_info, 0, sizeof(map_info)); + map_info_len = sizeof(map_info); + if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len) < 0) + goto out_close; + + /* If it's not an .rodata map, don't bother. */ + if (map_info.type != BPF_MAP_TYPE_ARRAY || + map_info.key_size != sizeof(int) || + map_info.max_entries != 1 || + !map_info.btf_value_type_id || + !strstr(map_info.name, ".rodata")) { + goto out_close; + } + + btf = btf__load_from_kernel_by_id(map_info.btf_id); + if (!btf) + goto out_close; + datasec = btf__type_by_id(btf, map_info.btf_value_type_id); + if (!btf_is_datasec(datasec)) + goto out_free_btf; + + /* + * If there aren't any variables with the "bpf_metadata_" prefix, + * don't bother. + */ + vlen = btf_vlen(datasec); + vsi = btf_var_secinfos(datasec); + vars = 0; + for (unsigned int i = 0; i < vlen; i++, vsi++) { + const struct btf_type *t_var = btf__type_by_id(btf, vsi->type); + const char *name = btf__name_by_offset(btf, t_var->name_off); + + if (name_has_bpf_metadata_prefix(&name)) + vars++; + } + if (vars == 0) + goto out_free_btf; + + rodata = zalloc(map_info.value_size); + if (!rodata) + goto out_free_btf; + key = 0; + if (bpf_map_lookup_elem(map_fd, &key, rodata)) { + free(rodata); + goto out_free_btf; + } + close(map_fd); + + map->btf = btf; + map->datasec = datasec; + map->rodata = rodata; + map->rodata_size = map_info.value_size; + map->num_vars = vars; + return 0; + +out_free_btf: + btf__free(btf); +out_close: + close(map_fd); + return -1; +} + +struct format_btf_ctx { + char *buf; + size_t buf_size; + size_t buf_idx; +}; + +static void format_btf_cb(void *arg, const char *fmt, va_list ap) +{ + int n; + struct format_btf_ctx *ctx = (struct format_btf_ctx *)arg; + + n = vsnprintf(ctx->buf + ctx->buf_idx, ctx->buf_size - ctx->buf_idx, + fmt, ap); + ctx->buf_idx += n; + if (ctx->buf_idx >= ctx->buf_size) + ctx->buf_idx = ctx->buf_size; +} + +static void format_btf_variable(struct btf *btf, char *buf, size_t buf_size, + const struct btf_type *t, const void *btf_data) +{ + struct format_btf_ctx ctx = { + .buf = buf, + .buf_idx = 0, + .buf_size = buf_size, + }; + const struct btf_dump_type_data_opts opts = { + .sz = sizeof(struct btf_dump_type_data_opts), + .skip_names = 1, + .compact = 1, + .emit_strings = 1, + }; + struct btf_dump *d; + size_t btf_size; + + d = btf_dump__new(btf, format_btf_cb, &ctx, NULL); + btf_size = btf__resolve_size(btf, t->type); + btf_dump__dump_type_data(d, t->type, btf_data, btf_size, &opts); + btf_dump__free(d); +} + +static void bpf_metadata_fill_event(struct bpf_metadata_map *map, + struct perf_record_bpf_metadata *bpf_metadata_event) +{ + struct btf_var_secinfo *vsi; + unsigned int i, vlen; + + memset(bpf_metadata_event->prog_name, 0, BPF_PROG_NAME_LEN); + vlen = btf_vlen(map->datasec); + vsi = btf_var_secinfos(map->datasec); + + for (i = 0; i < vlen; i++, vsi++) { + const struct btf_type *t_var = btf__type_by_id(map->btf, + vsi->type); + const char *name = btf__name_by_offset(map->btf, + t_var->name_off); + const __u64 nr_entries = bpf_metadata_event->nr_entries; + struct perf_record_bpf_metadata_entry *entry; + + if (!name_has_bpf_metadata_prefix(&name)) + continue; + + if (nr_entries >= (__u64)map->num_vars) + break; + + entry = &bpf_metadata_event->entries[nr_entries]; + memset(entry, 0, sizeof(*entry)); + snprintf(entry->key, BPF_METADATA_KEY_LEN, "%s", name); + format_btf_variable(map->btf, entry->value, + BPF_METADATA_VALUE_LEN, t_var, + map->rodata + vsi->offset); + bpf_metadata_event->nr_entries++; + } +} + +static void bpf_metadata_free_map_data(struct bpf_metadata_map *map) +{ + btf__free(map->btf); + free(map->rodata); +} + +static struct bpf_metadata *bpf_metadata_alloc(__u32 nr_prog_tags, + __u32 nr_variables) +{ + struct bpf_metadata *metadata; + size_t event_size; + + metadata = zalloc(sizeof(struct bpf_metadata)); + if (!metadata) + return NULL; + + metadata->prog_names = calloc(nr_prog_tags, sizeof(char *)); + if (!metadata->prog_names) { + bpf_metadata_free(metadata); + return NULL; + } + for (__u32 prog_index = 0; prog_index < nr_prog_tags; prog_index++) { + metadata->prog_names[prog_index] = zalloc(BPF_PROG_NAME_LEN); + if (!metadata->prog_names[prog_index]) { + bpf_metadata_free(metadata); + return NULL; + } + metadata->nr_prog_names++; + } + + event_size = sizeof(metadata->event->bpf_metadata) + + nr_variables * sizeof(metadata->event->bpf_metadata.entries[0]); + metadata->event = zalloc(event_size); + if (!metadata->event) { + bpf_metadata_free(metadata); + return NULL; + } + metadata->event->bpf_metadata = (struct perf_record_bpf_metadata) { + .header = { + .type = PERF_RECORD_BPF_METADATA, + .size = event_size, + }, + .nr_entries = 0, + }; + + return metadata; +} + +static struct bpf_metadata *bpf_metadata_create(struct bpf_prog_info *info) +{ + struct bpf_metadata *metadata; + const __u32 *map_ids = (__u32 *)(uintptr_t)info->map_ids; + + for (__u32 map_index = 0; map_index < info->nr_map_ids; map_index++) { + struct bpf_metadata_map map; + + if (bpf_metadata_read_map_data(map_ids[map_index], &map) != 0) + continue; + + metadata = bpf_metadata_alloc(info->nr_prog_tags, map.num_vars); + if (!metadata) + continue; + + bpf_metadata_fill_event(&map, &metadata->event->bpf_metadata); + + for (__u32 index = 0; index < info->nr_prog_tags; index++) { + synthesize_bpf_prog_name(metadata->prog_names[index], + BPF_PROG_NAME_LEN, info, + map.btf, index); + } + + bpf_metadata_free_map_data(&map); + + return metadata; + } + + return NULL; +} + +static int synthesize_perf_record_bpf_metadata(const struct bpf_metadata *metadata, + const struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + const size_t event_size = metadata->event->header.size; + union perf_event *event; + int err = 0; + + event = zalloc(event_size + machine->id_hdr_size); + if (!event) + return -1; + memcpy(event, metadata->event, event_size); + memset((void *)event + event->header.size, 0, machine->id_hdr_size); + event->header.size += machine->id_hdr_size; + for (__u32 index = 0; index < metadata->nr_prog_names; index++) { + memcpy(event->bpf_metadata.prog_name, + metadata->prog_names[index], BPF_PROG_NAME_LEN); + err = perf_tool__process_synth_event(tool, event, machine, + process); + if (err != 0) + break; + } + + free(event); + return err; +} + +void bpf_metadata_free(struct bpf_metadata *metadata) +{ + if (metadata == NULL) + return; + for (__u32 index = 0; index < metadata->nr_prog_names; index++) + free(metadata->prog_names[index]); + free(metadata->prog_names); + free(metadata->event); + free(metadata); +} + +#else /* HAVE_LIBBPF_STRINGS_SUPPORT */ + +static struct bpf_metadata *bpf_metadata_create(struct bpf_prog_info *info __maybe_unused) +{ + return NULL; +} + +static int synthesize_perf_record_bpf_metadata(const struct bpf_metadata *metadata __maybe_unused, + const struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +void bpf_metadata_free(struct bpf_metadata *metadata __maybe_unused) +{ +} + +#endif /* HAVE_LIBBPF_STRINGS_SUPPORT */ + +struct bpf_metadata_final_ctx { + const struct perf_tool *tool; + perf_event__handler_t process; + struct machine *machine; +}; + +static void synthesize_final_bpf_metadata_cb(struct bpf_prog_info_node *node, + void *data) +{ + struct bpf_metadata_final_ctx *ctx = (struct bpf_metadata_final_ctx *)data; + struct bpf_metadata *metadata = node->metadata; + int err; + + if (metadata == NULL) + return; + err = synthesize_perf_record_bpf_metadata(metadata, ctx->tool, + ctx->process, ctx->machine); + if (err != 0) { + const char *prog_name = metadata->prog_names[0]; + + if (prog_name != NULL) + pr_warning("Couldn't synthesize final BPF metadata for %s.\n", prog_name); + else + pr_warning("Couldn't synthesize final BPF metadata.\n"); + } + bpf_metadata_free(metadata); + node->metadata = NULL; +} + +void perf_event__synthesize_final_bpf_metadata(struct perf_session *session, + perf_event__handler_t process) +{ + struct perf_env *env = &session->header.env; + struct bpf_metadata_final_ctx ctx = { + .tool = session->tool, + .process = process, + .machine = &session->machines.host, + }; + + perf_env__iterate_bpf_prog_info(env, synthesize_final_bpf_metadata_cb, + &ctx); +} + /* * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf * program. One PERF_RECORD_BPF_EVENT is generated for the program. And @@ -173,6 +537,7 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, const struct perf_tool *tool = session->tool; struct bpf_prog_info_node *info_node; struct perf_bpil *info_linear; + struct bpf_metadata *metadata; struct bpf_prog_info *info; struct btf *btf = NULL; struct perf_env *env; @@ -184,7 +549,7 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, * for perf-record and perf-report use header.env; * otherwise, use global perf_env. */ - env = session->data ? &session->header.env : &perf_env; + env = perf_session__env(session); arrays = 1UL << PERF_BPIL_JITED_KSYMS; arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS; @@ -193,6 +558,7 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, arrays |= 1UL << PERF_BPIL_JITED_INSNS; arrays |= 1UL << PERF_BPIL_LINE_INFO; arrays |= 1UL << PERF_BPIL_JITED_LINE_INFO; + arrays |= 1UL << PERF_BPIL_MAP_IDS; info_linear = get_bpf_prog_info_linear(fd, arrays); if (IS_ERR_OR_NULL(info_linear)) { @@ -289,10 +655,17 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, } info_node->info_linear = info_linear; + info_node->metadata = NULL; if (!perf_env__insert_bpf_prog_info(env, info_node)) { - free(info_linear); + /* + * Insert failed, likely because of a duplicate event + * made by the sideband thread. Ignore synthesizing the + * metadata. + */ free(info_node); + goto out; } + /* info_linear is now owned by info_node and shouldn't be freed below. */ info_linear = NULL; /* @@ -301,6 +674,15 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, */ err = perf_tool__process_synth_event(tool, event, machine, process); + + /* Synthesize PERF_RECORD_BPF_METADATA */ + metadata = bpf_metadata_create(info); + if (metadata != NULL) { + err = synthesize_perf_record_bpf_metadata(metadata, + tool, process, + machine); + bpf_metadata_free(metadata); + } } out: @@ -351,7 +733,8 @@ kallsyms_process_symbol(void *data, const char *_name, char type __maybe_unused, u64 start) { char disp[KSYM_NAME_LEN]; - char *module, *name; + const char *module; + char *name; unsigned long id; int err = 0; @@ -405,11 +788,10 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, err = 0; break; } - pr_debug("%s: can't get next program: %s%s\n", - __func__, strerror(errno), - errno == EINVAL ? " -- kernel too old?" : ""); /* don't report error on old kernel or EPERM */ err = (errno == EINVAL || errno == EPERM) ? 0 : -1; + pr_debug("%s: can\'t get next program: %m%s\n", + __func__, errno == EINVAL ? " -- kernel too old?" : ""); break; } fd = bpf_prog_get_fd_by_id(id); @@ -442,27 +824,25 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, .tool = session->tool, }; - if (kallsyms__parse(kallsyms_filename, &arg, kallsyms_process_symbol)) { - pr_err("%s: failed to synthesize bpf images: %s\n", - __func__, strerror(errno)); - } + if (kallsyms__parse(kallsyms_filename, &arg, kallsyms_process_symbol)) + pr_err("%s: failed to synthesize bpf images: %m\n", __func__); free(event); return err; } -static void perf_env__add_bpf_info(struct perf_env *env, u32 id) +static int perf_env__add_bpf_info(struct perf_env *env, u32 id) { struct bpf_prog_info_node *info_node; struct perf_bpil *info_linear; struct btf *btf = NULL; u64 arrays; u32 btf_id; - int fd; + int fd, err = 0; fd = bpf_prog_get_fd_by_id(id); if (fd < 0) - return; + return -EINVAL; arrays = 1UL << PERF_BPIL_JITED_KSYMS; arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS; @@ -471,10 +851,12 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) arrays |= 1UL << PERF_BPIL_JITED_INSNS; arrays |= 1UL << PERF_BPIL_LINE_INFO; arrays |= 1UL << PERF_BPIL_JITED_LINE_INFO; + arrays |= 1UL << PERF_BPIL_MAP_IDS; info_linear = get_bpf_prog_info_linear(fd, arrays); if (IS_ERR_OR_NULL(info_linear)) { pr_debug("%s: failed to get BPF program info. aborting\n", __func__); + err = PTR_ERR(info_linear); goto out; } @@ -483,39 +865,48 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) info_node = malloc(sizeof(struct bpf_prog_info_node)); if (info_node) { info_node->info_linear = info_linear; + info_node->metadata = bpf_metadata_create(&info_linear->info); if (!perf_env__insert_bpf_prog_info(env, info_node)) { + pr_debug("%s: duplicate add bpf info request for id %u\n", + __func__, btf_id); free(info_linear); free(info_node); + goto out; } - } else + } else { free(info_linear); + err = -ENOMEM; + goto out; + } if (btf_id == 0) goto out; btf = btf__load_from_kernel_by_id(btf_id); - if (libbpf_get_error(btf)) { - pr_debug("%s: failed to get BTF of id %u, aborting\n", - __func__, btf_id); - goto out; + if (!btf) { + err = -errno; + pr_debug("%s: failed to get BTF of id %u %d\n", __func__, btf_id, err); + } else { + perf_env__fetch_btf(env, btf_id, btf); } - perf_env__fetch_btf(env, btf_id, btf); out: btf__free(btf); close(fd); + return err; } static int bpf_event__sb_cb(union perf_event *event, void *data) { struct perf_env *env = data; + int ret = 0; if (event->header.type != PERF_RECORD_BPF_EVENT) return -1; switch (event->bpf.type) { case PERF_BPF_EVENT_PROG_LOAD: - perf_env__add_bpf_info(env, event->bpf.id); + ret = perf_env__add_bpf_info(env, event->bpf.id); case PERF_BPF_EVENT_PROG_UNLOAD: /* @@ -529,7 +920,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data) break; } - return 0; + return ret; } int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env) diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index e2f0420905f5..60d2c6637af5 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -17,8 +17,15 @@ struct record_opts; struct evlist; struct target; +struct bpf_metadata { + union perf_event *event; + char **prog_names; + __u64 nr_prog_names; +}; + struct bpf_prog_info_node { struct perf_bpil *info_linear; + struct bpf_metadata *metadata; struct rb_node rb_node; }; @@ -36,6 +43,7 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env); void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, struct perf_env *env, FILE *fp); +void bpf_metadata_free(struct bpf_metadata *metadata); #else static inline int machine__process_bpf(struct machine *machine __maybe_unused, union perf_event *event __maybe_unused, @@ -56,5 +64,10 @@ static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info _ { } + +static inline void bpf_metadata_free(struct bpf_metadata *metadata __maybe_unused) +{ + +} #endif // HAVE_LIBBPF_SUPPORT #endif diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index a4fdf6911ec1..1a2e7b388d57 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -52,9 +52,11 @@ #include <internal/xyarray.h> #include <perf/threadmap.h> +#include "util/cap.h" #include "util/debug.h" #include "util/evsel.h" #include "util/target.h" +#include "util/bpf-utils.h" #include "util/bpf-filter.h" #include <util/bpf-filter-flex.h> @@ -449,7 +451,13 @@ int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target) struct bpf_program *prog; struct bpf_link *link; struct perf_bpf_filter_entry *entry; - bool needs_idx_hash = !target__has_cpu(target) && !target->uid_str; + bool needs_idx_hash = !target__has_cpu(target); +#if LIBBPF_CURRENT_VERSION_GEQ(1, 7) + DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts, + .dont_enable = true); +#else + DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); +#endif entry = calloc(MAX_FILTERS, sizeof(*entry)); if (entry == NULL) @@ -521,7 +529,8 @@ int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target) prog = skel->progs.perf_sample_filter; for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) { for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) { - link = bpf_program__attach_perf_event(prog, FD(evsel, x, y)); + link = bpf_program__attach_perf_event_opts(prog, FD(evsel, x, y), + &pe_opts); if (IS_ERR(link)) { pr_err("Failed to attach perf sample-filter program\n"); ret = PTR_ERR(link); @@ -618,11 +627,38 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(enum perf_bpf_filter_term return expr; } +static bool check_bpf_filter_capable(void) +{ + bool used_root; + + if (perf_cap__capable(CAP_BPF, &used_root)) + return true; + + if (!used_root) { + /* Check if root already pinned the filter programs and maps */ + int fd = get_pinned_fd("filters"); + + if (fd >= 0) { + close(fd); + return true; + } + } + + pr_err("Error: BPF filter only works for %s!\n" + "\tPlease run 'perf record --setup-filter pin' as root first.\n", + used_root ? "root" : "users with the CAP_BPF capability"); + + return false; +} + int perf_bpf_filter__parse(struct list_head *expr_head, const char *str) { YY_BUFFER_STATE buffer; int ret; + if (!check_bpf_filter_capable()) + return -EPERM; + buffer = perf_bpf_filter__scan_string(str); ret = perf_bpf_filter_parse(expr_head); diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index 916ed7770b73..818c554b91b2 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include "bpf_skel/sample-filter.h" +#include "util/debug.h" struct perf_bpf_filter_expr { struct list_head list; @@ -35,9 +36,13 @@ int perf_bpf_filter__unpin(void); #else /* !HAVE_BPF_SKEL */ +#include <errno.h> + static inline int perf_bpf_filter__parse(struct list_head *expr_head __maybe_unused, const char *str __maybe_unused) { + pr_err("Error: BPF filter is requested but perf is not built with BPF.\n" + "\tPlease make sure to build with libbpf and BPF skeleton.\n"); return -EOPNOTSUPP; } static inline int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused, diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index f313404f95a9..6aa65ade3385 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -76,7 +76,7 @@ static int path_or_error(void) num_dec [0-9]+ num_hex 0[Xx][0-9a-fA-F]+ space [ \t]+ -path [^ \t\n]+ +path [^ \t\n,]+ ident [_a-zA-Z][_a-zA-Z0-9]+ %% diff --git a/tools/perf/util/bpf-trace-summary.c b/tools/perf/util/bpf-trace-summary.c new file mode 100644 index 000000000000..cf6e1e4402d5 --- /dev/null +++ b/tools/perf/util/bpf-trace-summary.c @@ -0,0 +1,465 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <errno.h> +#include <inttypes.h> +#include <math.h> +#include <stdio.h> +#include <stdlib.h> + +#include "dwarf-regs.h" /* for EM_HOST */ +#include "syscalltbl.h" +#include "util/cgroup.h" +#include "util/hashmap.h" +#include "util/trace.h" +#include "util/util.h" +#include <bpf/bpf.h> +#include <linux/rbtree.h> +#include <linux/time64.h> +#include <tools/libc_compat.h> /* reallocarray */ + +#include "bpf_skel/syscall_summary.h" +#include "bpf_skel/syscall_summary.skel.h" + + +static struct syscall_summary_bpf *skel; +static struct rb_root cgroups = RB_ROOT; + +int trace_prepare_bpf_summary(enum trace_summary_mode mode) +{ + skel = syscall_summary_bpf__open(); + if (skel == NULL) { + fprintf(stderr, "failed to open syscall summary bpf skeleton\n"); + return -1; + } + + if (mode == SUMMARY__BY_THREAD) + skel->rodata->aggr_mode = SYSCALL_AGGR_THREAD; + else if (mode == SUMMARY__BY_CGROUP) + skel->rodata->aggr_mode = SYSCALL_AGGR_CGROUP; + else + skel->rodata->aggr_mode = SYSCALL_AGGR_CPU; + + if (cgroup_is_v2("perf_event") > 0) + skel->rodata->use_cgroup_v2 = 1; + + if (syscall_summary_bpf__load(skel) < 0) { + fprintf(stderr, "failed to load syscall summary bpf skeleton\n"); + return -1; + } + + if (syscall_summary_bpf__attach(skel) < 0) { + fprintf(stderr, "failed to attach syscall summary bpf skeleton\n"); + return -1; + } + + if (mode == SUMMARY__BY_CGROUP) + read_all_cgroups(&cgroups); + + return 0; +} + +void trace_start_bpf_summary(void) +{ + skel->bss->enabled = 1; +} + +void trace_end_bpf_summary(void) +{ + skel->bss->enabled = 0; +} + +struct syscall_node { + int syscall_nr; + struct syscall_stats stats; +}; + +static double rel_stddev(struct syscall_stats *stat) +{ + double variance, average; + + if (stat->count < 2) + return 0; + + average = (double)stat->total_time / stat->count; + + variance = stat->squared_sum; + variance -= (stat->total_time * stat->total_time) / stat->count; + variance /= stat->count - 1; + + return 100 * sqrt(variance / stat->count) / average; +} + +/* + * The syscall_data is to maintain syscall stats ordered by total time. + * It supports different summary modes like per-thread or global. + * + * For per-thread stats, it uses two-level data strurcture - + * syscall_data is keyed by TID and has an array of nodes which + * represents each syscall for the thread. + * + * For global stats, it's still two-level technically but we don't need + * per-cpu analysis so it's keyed by the syscall number to combine stats + * from different CPUs. And syscall_data always has a syscall_node so + * it can effectively work as flat hierarchy. + * + * For per-cgroup stats, it uses two-level data structure like thread + * syscall_data is keyed by CGROUP and has an array of node which + * represents each syscall for the cgroup. + */ +struct syscall_data { + u64 key; /* tid if AGGR_THREAD, syscall-nr if AGGR_CPU, cgroup if AGGR_CGROUP */ + int nr_events; + int nr_nodes; + u64 total_time; + struct syscall_node *nodes; +}; + +static int datacmp(const void *a, const void *b) +{ + const struct syscall_data * const *sa = a; + const struct syscall_data * const *sb = b; + + return (*sa)->total_time > (*sb)->total_time ? -1 : 1; +} + +static int nodecmp(const void *a, const void *b) +{ + const struct syscall_node *na = a; + const struct syscall_node *nb = b; + + return na->stats.total_time > nb->stats.total_time ? -1 : 1; +} + +static size_t sc_node_hash(long key, void *ctx __maybe_unused) +{ + return key; +} + +static bool sc_node_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return key1 == key2; +} + +static int print_common_stats(struct syscall_data *data, int max_summary, FILE *fp) +{ + int printed = 0; + + if (max_summary == 0 || max_summary > data->nr_nodes) + max_summary = data->nr_nodes; + + for (int i = 0; i < max_summary; i++) { + struct syscall_node *node = &data->nodes[i]; + struct syscall_stats *stat = &node->stats; + double total = (double)(stat->total_time) / NSEC_PER_MSEC; + double min = (double)(stat->min_time) / NSEC_PER_MSEC; + double max = (double)(stat->max_time) / NSEC_PER_MSEC; + double avg = total / stat->count; + const char *name; + + /* TODO: support other ABIs */ + name = syscalltbl__name(EM_HOST, node->syscall_nr); + if (name) + printed += fprintf(fp, " %-15s", name); + else + printed += fprintf(fp, " syscall:%-7d", node->syscall_nr); + + printed += fprintf(fp, " %8u %6u %9.3f %9.3f %9.3f %9.3f %9.2f%%\n", + stat->count, stat->error, total, min, avg, max, + rel_stddev(stat)); + } + return printed; +} + +static int update_thread_stats(struct hashmap *hash, struct syscall_key *map_key, + struct syscall_stats *map_data) +{ + struct syscall_data *data; + struct syscall_node *nodes; + + if (!hashmap__find(hash, map_key->cpu_or_tid, &data)) { + data = zalloc(sizeof(*data)); + if (data == NULL) + return -ENOMEM; + + data->key = map_key->cpu_or_tid; + if (hashmap__add(hash, data->key, data) < 0) { + free(data); + return -ENOMEM; + } + } + + /* update thread total stats */ + data->nr_events += map_data->count; + data->total_time += map_data->total_time; + + nodes = reallocarray(data->nodes, data->nr_nodes + 1, sizeof(*nodes)); + if (nodes == NULL) + return -ENOMEM; + + data->nodes = nodes; + nodes = &data->nodes[data->nr_nodes++]; + nodes->syscall_nr = map_key->nr; + + /* each thread has an entry for each syscall, just use the stat */ + memcpy(&nodes->stats, map_data, sizeof(*map_data)); + return 0; +} + +static int print_thread_stat(struct syscall_data *data, int max_summary, FILE *fp) +{ + int printed = 0; + + qsort(data->nodes, data->nr_nodes, sizeof(*data->nodes), nodecmp); + + printed += fprintf(fp, " thread (%d), ", (int)data->key); + printed += fprintf(fp, "%d events\n\n", data->nr_events); + + printed += fprintf(fp, " syscall calls errors total min avg max stddev\n"); + printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n"); + printed += fprintf(fp, " --------------- -------- ------ -------- --------- --------- --------- ------\n"); + + printed += print_common_stats(data, max_summary, fp); + printed += fprintf(fp, "\n\n"); + + return printed; +} + +static int print_thread_stats(struct syscall_data **data, int nr_data, int max_summary, FILE *fp) +{ + int printed = 0; + + for (int i = 0; i < nr_data; i++) + printed += print_thread_stat(data[i], max_summary, fp); + + return printed; +} + +static int update_total_stats(struct hashmap *hash, struct syscall_key *map_key, + struct syscall_stats *map_data) +{ + struct syscall_data *data; + struct syscall_stats *stat; + + if (!hashmap__find(hash, map_key->nr, &data)) { + data = zalloc(sizeof(*data)); + if (data == NULL) + return -ENOMEM; + + data->nodes = zalloc(sizeof(*data->nodes)); + if (data->nodes == NULL) { + free(data); + return -ENOMEM; + } + + data->nr_nodes = 1; + data->key = map_key->nr; + data->nodes->syscall_nr = data->key; + + if (hashmap__add(hash, data->key, data) < 0) { + free(data->nodes); + free(data); + return -ENOMEM; + } + } + + /* update total stats for this syscall */ + data->nr_events += map_data->count; + data->total_time += map_data->total_time; + + /* This is sum of the same syscall from different CPUs */ + stat = &data->nodes->stats; + + stat->total_time += map_data->total_time; + stat->squared_sum += map_data->squared_sum; + stat->count += map_data->count; + stat->error += map_data->error; + + if (stat->max_time < map_data->max_time) + stat->max_time = map_data->max_time; + if (stat->min_time > map_data->min_time || stat->min_time == 0) + stat->min_time = map_data->min_time; + + return 0; +} + +static int print_total_stats(struct syscall_data **data, int nr_data, int max_summary, FILE *fp) +{ + int printed = 0; + int nr_events = 0; + + for (int i = 0; i < nr_data; i++) + nr_events += data[i]->nr_events; + + printed += fprintf(fp, " total, %d events\n\n", nr_events); + + printed += fprintf(fp, " syscall calls errors total min avg max stddev\n"); + printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n"); + printed += fprintf(fp, " --------------- -------- ------ -------- --------- --------- --------- ------\n"); + + if (max_summary == 0 || max_summary > nr_data) + max_summary = nr_data; + + for (int i = 0; i < max_summary; i++) + printed += print_common_stats(data[i], max_summary, fp); + + printed += fprintf(fp, "\n\n"); + return printed; +} + +static int update_cgroup_stats(struct hashmap *hash, struct syscall_key *map_key, + struct syscall_stats *map_data) +{ + struct syscall_data *data; + struct syscall_node *nodes; + + if (!hashmap__find(hash, map_key->cgroup, &data)) { + data = zalloc(sizeof(*data)); + if (data == NULL) + return -ENOMEM; + + data->key = map_key->cgroup; + if (hashmap__add(hash, data->key, data) < 0) { + free(data); + return -ENOMEM; + } + } + + /* update thread total stats */ + data->nr_events += map_data->count; + data->total_time += map_data->total_time; + + nodes = reallocarray(data->nodes, data->nr_nodes + 1, sizeof(*nodes)); + if (nodes == NULL) + return -ENOMEM; + + data->nodes = nodes; + nodes = &data->nodes[data->nr_nodes++]; + nodes->syscall_nr = map_key->nr; + + /* each thread has an entry for each syscall, just use the stat */ + memcpy(&nodes->stats, map_data, sizeof(*map_data)); + return 0; +} + +static int print_cgroup_stat(struct syscall_data *data, int max_summary, FILE *fp) +{ + int printed = 0; + struct cgroup *cgrp = __cgroup__find(&cgroups, data->key); + + qsort(data->nodes, data->nr_nodes, sizeof(*data->nodes), nodecmp); + + if (cgrp) + printed += fprintf(fp, " cgroup %s,", cgrp->name); + else + printed += fprintf(fp, " cgroup id:%lu,", (unsigned long)data->key); + + printed += fprintf(fp, " %d events\n\n", data->nr_events); + + printed += fprintf(fp, " syscall calls errors total min avg max stddev\n"); + printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n"); + printed += fprintf(fp, " --------------- -------- ------ -------- --------- --------- --------- ------\n"); + + printed += print_common_stats(data, max_summary, fp); + printed += fprintf(fp, "\n\n"); + + return printed; +} + +static int print_cgroup_stats(struct syscall_data **data, int nr_data, int max_summary, FILE *fp) +{ + int printed = 0; + + for (int i = 0; i < nr_data; i++) + printed += print_cgroup_stat(data[i], max_summary, fp); + + return printed; +} + +int trace_print_bpf_summary(FILE *fp, int max_summary) +{ + struct bpf_map *map = skel->maps.syscall_stats_map; + struct syscall_key *prev_key, key; + struct syscall_data **data = NULL; + struct hashmap schash; + struct hashmap_entry *entry; + int nr_data = 0; + int printed = 0; + int i; + size_t bkt; + + hashmap__init(&schash, sc_node_hash, sc_node_equal, /*ctx=*/NULL); + + printed = fprintf(fp, "\n Summary of events:\n\n"); + + /* get stats from the bpf map */ + prev_key = NULL; + while (!bpf_map__get_next_key(map, prev_key, &key, sizeof(key))) { + struct syscall_stats stat; + + if (!bpf_map__lookup_elem(map, &key, sizeof(key), &stat, sizeof(stat), 0)) { + switch (skel->rodata->aggr_mode) { + case SYSCALL_AGGR_THREAD: + update_thread_stats(&schash, &key, &stat); + break; + case SYSCALL_AGGR_CPU: + update_total_stats(&schash, &key, &stat); + break; + case SYSCALL_AGGR_CGROUP: + update_cgroup_stats(&schash, &key, &stat); + break; + default: + break; + } + } + + prev_key = &key; + } + + nr_data = hashmap__size(&schash); + data = calloc(nr_data, sizeof(*data)); + if (data == NULL) + goto out; + + i = 0; + hashmap__for_each_entry(&schash, entry, bkt) + data[i++] = entry->pvalue; + + qsort(data, nr_data, sizeof(*data), datacmp); + + switch (skel->rodata->aggr_mode) { + case SYSCALL_AGGR_THREAD: + printed += print_thread_stats(data, nr_data, max_summary, fp); + break; + case SYSCALL_AGGR_CPU: + printed += print_total_stats(data, nr_data, max_summary, fp); + break; + case SYSCALL_AGGR_CGROUP: + printed += print_cgroup_stats(data, nr_data, max_summary, fp); + break; + default: + break; + } + + for (i = 0; i < nr_data && data; i++) { + free(data[i]->nodes); + free(data[i]); + } + free(data); + +out: + hashmap__clear(&schash); + return printed; +} + +void trace_cleanup_bpf_summary(void) +{ + if (!RB_EMPTY_ROOT(&cgroups)) { + struct cgroup *cgrp, *tmp; + + rbtree_postorder_for_each_entry_safe(cgrp, tmp, &cgroups, node) + cgroup__put(cgrp); + + cgroups = RB_ROOT; + } + + syscall_summary_bpf__destroy(skel); +} diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c index 80b1d2b3729b..d6d2c9c190f7 100644 --- a/tools/perf/util/bpf-utils.c +++ b/tools/perf/util/bpf-utils.c @@ -20,7 +20,7 @@ struct bpil_array_desc { */ }; -static struct bpil_array_desc bpil_array_desc[] = { +static const struct bpil_array_desc bpil_array_desc[] = { [PERF_BPIL_JITED_INSNS] = { offsetof(struct bpf_prog_info, jited_prog_insns), offsetof(struct bpf_prog_info, jited_prog_len), @@ -115,7 +115,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) __u32 info_len = sizeof(info); __u32 data_len = 0; int i, err; - void *ptr; + __u8 *ptr; if (arrays >> PERF_BPIL_LAST_ARRAY) return ERR_PTR(-EINVAL); @@ -123,18 +123,18 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) /* step 1: get array dimensions */ err = bpf_obj_get_info_by_fd(fd, &info, &info_len); if (err) { - pr_debug("can't get prog info: %s", strerror(errno)); + pr_debug("can't get prog info: %m\n"); return ERR_PTR(-EFAULT); } + if (info.type >= __MAX_BPF_PROG_TYPE) + pr_debug("%s:%d: unexpected program type %u\n", __func__, __LINE__, info.type); /* step 2: calculate total size of all arrays */ for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { + const struct bpil_array_desc *desc = &bpil_array_desc[i]; bool include_array = (arrays & (1UL << i)) > 0; - struct bpil_array_desc *desc; __u32 count, size; - desc = bpil_array_desc + i; - /* kernel is too old to support this field */ if (info_len < desc->array_offset + sizeof(__u32) || info_len < desc->count_offset + sizeof(__u32) || @@ -163,19 +163,20 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) ptr = info_linear->data; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; __u32 count, size; if ((arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); bpf_prog_info_set_offset_u32(&info_linear->info, desc->count_offset, count); bpf_prog_info_set_offset_u32(&info_linear->info, desc->size_offset, size); + assert(ptr >= info_linear->data); + assert(ptr < &info_linear->data[data_len]); bpf_prog_info_set_offset_u64(&info_linear->info, desc->array_offset, ptr_to_u64(ptr)); @@ -185,31 +186,49 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) /* step 5: call syscall again to get required arrays */ err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len); if (err) { - pr_debug("can't get prog info: %s", strerror(errno)); + pr_debug("can't get prog info: %m\n"); free(info_linear); return ERR_PTR(-EFAULT); } + if (info_linear->info.type >= __MAX_BPF_PROG_TYPE) { + pr_debug("%s:%d: unexpected program type %u\n", + __func__, __LINE__, info_linear->info.type); + } /* step 6: verify the data */ + ptr = info_linear->data; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; - __u32 v1, v2; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; + __u32 count1, count2, size1, size2; + __u64 ptr2; if ((arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; - v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset); - v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + count1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + count2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->count_offset); - if (v1 != v2) - pr_warning("%s: mismatch in element count\n", __func__); + if (count1 != count2) { + pr_warning("%s: mismatch in element count %u vs %u\n", __func__, count1, count2); + free(info_linear); + return ERR_PTR(-ERANGE); + } - v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); - v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + size1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + size2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->size_offset); - if (v1 != v2) - pr_warning("%s: mismatch in rec size\n", __func__); + if (size1 != size2) { + pr_warning("%s: mismatch in rec size %u vs %u\n", __func__, size1, size2); + free(info_linear); + return ERR_PTR(-ERANGE); + } + ptr2 = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset); + if (ptr_to_u64(ptr) != ptr2) { + pr_warning("%s: mismatch in array %p vs %llx\n", __func__, ptr, ptr2); + free(info_linear); + return ERR_PTR(-ERANGE); + } + ptr += roundup(count1 * size1, sizeof(__u64)); } /* step 7: update info_len and data_len */ @@ -224,13 +243,12 @@ void bpil_addr_to_offs(struct perf_bpil *info_linear) int i; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; __u64 addr, offs; if ((info_linear->arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; addr = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset); offs = addr - ptr_to_u64(info_linear->data); @@ -244,13 +262,12 @@ void bpil_offs_to_addr(struct perf_bpil *info_linear) int i; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; __u64 addr, offs; if ((info_linear->arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; offs = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset); addr = offs + ptr_to_u64(info_linear->data); diff --git a/tools/perf/util/bpf-utils.h b/tools/perf/util/bpf-utils.h index 86a5055cdfad..a8bc1a232968 100644 --- a/tools/perf/util/bpf-utils.h +++ b/tools/perf/util/bpf-utils.h @@ -8,6 +8,16 @@ #ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> +#include <bpf/libbpf_version.h> + +#define LIBBPF_CURRENT_VERSION_GEQ(major, minor) \ + (LIBBPF_MAJOR_VERSION > (major) || \ + (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor))) + +#if LIBBPF_CURRENT_VERSION_GEQ(1, 7) +// libbpf 1.7+ support the btf_dump_type_data_opts.emit_strings option. +#define HAVE_LIBBPF_STRINGS_SUPPORT 1 +#endif /* * Get bpf_prog_info in continuous memory diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 73fcafbffc6a..34b6b0da18b7 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -6,10 +6,14 @@ #include <limits.h> #include <unistd.h> #include <sys/file.h> +#include <sys/resource.h> #include <sys/time.h> #include <linux/err.h> +#include <linux/list.h> #include <linux/zalloc.h> #include <api/fs/fs.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> #include <perf/bpf_perf.h> #include "bpf_counter.h" @@ -28,13 +32,67 @@ #include "bpf_skel/bperf_leader.skel.h" #include "bpf_skel/bperf_follower.skel.h" +struct bpf_counter { + void *skel; + struct list_head list; +}; + #define ATTR_MAP_SIZE 16 -static inline void *u64_to_ptr(__u64 ptr) +static void *u64_to_ptr(__u64 ptr) { return (void *)(unsigned long)ptr; } + +void set_max_rlimit(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + setrlimit(RLIMIT_MEMLOCK, &rinf); +} + +static __u32 bpf_link_get_id(int fd) +{ + struct bpf_link_info link_info = { .id = 0, }; + __u32 link_info_len = sizeof(link_info); + + bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); + return link_info.id; +} + +static __u32 bpf_link_get_prog_id(int fd) +{ + struct bpf_link_info link_info = { .id = 0, }; + __u32 link_info_len = sizeof(link_info); + + bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); + return link_info.prog_id; +} + +static __u32 bpf_map_get_id(int fd) +{ + struct bpf_map_info map_info = { .id = 0, }; + __u32 map_info_len = sizeof(map_info); + + bpf_obj_get_info_by_fd(fd, &map_info, &map_info_len); + return map_info.id; +} + +/* trigger the leader program on a cpu */ +int bperf_trigger_reading(int prog_fd, int cpu) +{ + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .ctx_in = NULL, + .ctx_size_in = 0, + .flags = BPF_F_TEST_RUN_ON_CPU, + .cpu = cpu, + .retval = 0, + ); + + return bpf_prog_test_run_opts(prog_fd, &opts); +} + static struct bpf_counter *bpf_counter_alloc(void) { struct bpf_counter *counter; @@ -236,7 +294,8 @@ static int bpf_program_profiler__read(struct evsel *evsel) struct perf_counts_values *counts; int reading_map_fd; __u32 key = 0; - int err, idx, bpf_cpu; + int err, bpf_cpu; + unsigned int idx; if (list_empty(&evsel->bpf_counter_list)) return -EAGAIN; @@ -260,11 +319,12 @@ static int bpf_program_profiler__read(struct evsel *evsel) } for (bpf_cpu = 0; bpf_cpu < num_cpu_bpf; bpf_cpu++) { - idx = perf_cpu_map__idx(evsel__cpus(evsel), - (struct perf_cpu){.cpu = bpf_cpu}); - if (idx == -1) + int i = perf_cpu_map__idx(evsel__cpus(evsel), + (struct perf_cpu){.cpu = bpf_cpu}); + + if (i == -1) continue; - counts = perf_counts(evsel->counts, idx, 0); + counts = perf_counts(evsel->counts, i, 0); counts->val += values[bpf_cpu].counter; counts->ena += values[bpf_cpu].enabled; counts->run += values[bpf_cpu].running; @@ -278,6 +338,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx { struct bpf_prog_profiler_bpf *skel; struct bpf_counter *counter; + int cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx).cpu; int ret; list_for_each_entry(counter, &evsel->bpf_counter_list, list) { @@ -285,14 +346,14 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx assert(skel != NULL); ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu_map_idx, &fd, BPF_ANY); + &cpu, &fd, BPF_ANY); if (ret) return ret; } return 0; } -struct bpf_counter_ops bpf_program_profiler_ops = { +static struct bpf_counter_ops bpf_program_profiler_ops = { .load = bpf_program_profiler__load, .enable = bpf_program_profiler__enable, .disable = bpf_program_profiler__disable, @@ -393,7 +454,6 @@ static int bperf_check_target(struct evsel *evsel, return 0; } -static struct perf_cpu_map *all_cpu_map; static __u32 filter_entry_cnt; static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, @@ -402,6 +462,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, struct bperf_leader_bpf *skel = bperf_leader_bpf__open(); int link_fd, diff_map_fd, err; struct bpf_link *link = NULL; + struct perf_thread_map *threads; if (!skel) { pr_err("Failed to open leader skeleton\n"); @@ -437,7 +498,11 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, * following evsel__open_per_cpu call */ evsel->leader_skel = skel; - evsel__open_per_cpu(evsel, all_cpu_map, -1); + assert(!perf_cpu_map__has_any_cpu_or_is_empty(evsel->core.cpus)); + /* Always open system wide. */ + threads = thread_map__new_by_tid(-1); + evsel__open(evsel, evsel->core.cpus, threads); + perf_thread_map__put(threads); out: bperf_leader_bpf__destroy(skel); @@ -475,12 +540,6 @@ static int bperf__load(struct evsel *evsel, struct target *target) if (bperf_check_target(evsel, target, &filter_type, &filter_entry_cnt)) return -1; - if (!all_cpu_map) { - all_cpu_map = perf_cpu_map__new_online_cpus(); - if (!all_cpu_map) - return -1; - } - evsel->bperf_leader_prog_fd = -1; evsel->bperf_leader_link_fd = -1; @@ -598,9 +657,10 @@ out: static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { struct bperf_leader_bpf *skel = evsel->leader_skel; + int cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx).cpu; return bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu_map_idx, &fd, BPF_ANY); + &cpu, &fd, BPF_ANY); } /* @@ -609,13 +669,12 @@ static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) */ static int bperf_sync_counters(struct evsel *evsel) { - int num_cpu, i, cpu; + struct perf_cpu cpu; + unsigned int idx; + + perf_cpu_map__for_each_cpu(cpu, idx, evsel->core.cpus) + bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu.cpu); - num_cpu = perf_cpu_map__nr(all_cpu_map); - for (i = 0; i < num_cpu; i++) { - cpu = perf_cpu_map__cpu(all_cpu_map, i).cpu; - bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); - } return 0; } @@ -638,13 +697,11 @@ static int bperf__read(struct evsel *evsel) struct bpf_perf_event_value values[num_cpu_bpf]; struct perf_counts_values *counts; int reading_map_fd, err = 0; - __u32 i; - int j; bperf_sync_counters(evsel); reading_map_fd = bpf_map__fd(skel->maps.accum_readings); - for (i = 0; i < filter_entry_cnt; i++) { + for (__u32 i = 0; i < filter_entry_cnt; i++) { struct perf_cpu entry; __u32 cpu; @@ -652,9 +709,10 @@ static int bperf__read(struct evsel *evsel) if (err) goto out; switch (evsel->follower_skel->bss->type) { - case BPERF_FILTER_GLOBAL: - assert(i == 0); + case BPERF_FILTER_GLOBAL: { + unsigned int j; + assert(i == 0); perf_cpu_map__for_each_cpu(entry, j, evsel__cpus(evsel)) { counts = perf_counts(evsel->counts, j, 0); counts->val = values[entry.cpu].counter; @@ -662,6 +720,7 @@ static int bperf__read(struct evsel *evsel) counts->run = values[entry.cpu].running; } break; + } case BPERF_FILTER_CPU: cpu = perf_cpu_map__cpu(evsel__cpus(evsel), i).cpu; assert(cpu >= 0); @@ -774,7 +833,7 @@ static int bperf__destroy(struct evsel *evsel) * the leader prog. */ -struct bpf_counter_ops bperf_ops = { +static struct bpf_counter_ops bperf_ops = { .load = bperf__load, .enable = bperf__enable, .disable = bperf__disable, @@ -785,7 +844,7 @@ struct bpf_counter_ops bperf_ops = { extern struct bpf_counter_ops bperf_cgrp_ops; -static inline bool bpf_counter_skip(struct evsel *evsel) +static bool bpf_counter_skip(struct evsel *evsel) { return evsel->bpf_counter_ops == NULL; } diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h index c6d21c07b14c..658d8e7d507e 100644 --- a/tools/perf/util/bpf_counter.h +++ b/tools/perf/util/bpf_counter.h @@ -2,18 +2,10 @@ #ifndef __PERF_BPF_COUNTER_H #define __PERF_BPF_COUNTER_H 1 -#include <linux/list.h> -#include <sys/resource.h> - -#ifdef HAVE_LIBBPF_SUPPORT -#include <bpf/bpf.h> -#include <bpf/btf.h> -#include <bpf/libbpf.h> -#endif - struct evsel; struct target; -struct bpf_counter; + +#ifdef HAVE_BPF_SKEL typedef int (*bpf_counter_evsel_op)(struct evsel *evsel); typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel, @@ -22,6 +14,7 @@ typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel, int cpu_map_idx, int fd); +/* Shared ops between bpf_counter, bpf_counter_cgroup, etc. */ struct bpf_counter_ops { bpf_counter_evsel_target_op load; bpf_counter_evsel_op enable; @@ -31,13 +24,6 @@ struct bpf_counter_ops { bpf_counter_evsel_install_pe_op install_pe; }; -struct bpf_counter { - void *skel; - struct list_head list; -}; - -#ifdef HAVE_BPF_SKEL - int bpf_counter__load(struct evsel *evsel, struct target *target); int bpf_counter__enable(struct evsel *evsel); int bpf_counter__disable(struct evsel *evsel); @@ -45,6 +31,9 @@ int bpf_counter__read(struct evsel *evsel); void bpf_counter__destroy(struct evsel *evsel); int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd); +int bperf_trigger_reading(int prog_fd, int cpu); +void set_max_rlimit(void); + #else /* HAVE_BPF_SKEL */ #include <linux/err.h> @@ -83,55 +72,4 @@ static inline int bpf_counter__install_pe(struct evsel *evsel __maybe_unused, #endif /* HAVE_BPF_SKEL */ -static inline void set_max_rlimit(void) -{ - struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - - setrlimit(RLIMIT_MEMLOCK, &rinf); -} - -#ifdef HAVE_BPF_SKEL - -static inline __u32 bpf_link_get_id(int fd) -{ - struct bpf_link_info link_info = { .id = 0, }; - __u32 link_info_len = sizeof(link_info); - - bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); - return link_info.id; -} - -static inline __u32 bpf_link_get_prog_id(int fd) -{ - struct bpf_link_info link_info = { .id = 0, }; - __u32 link_info_len = sizeof(link_info); - - bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); - return link_info.prog_id; -} - -static inline __u32 bpf_map_get_id(int fd) -{ - struct bpf_map_info map_info = { .id = 0, }; - __u32 map_info_len = sizeof(map_info); - - bpf_obj_get_info_by_fd(fd, &map_info, &map_info_len); - return map_info.id; -} - -/* trigger the leader program on a cpu */ -static inline int bperf_trigger_reading(int prog_fd, int cpu) -{ - DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, - .ctx_in = NULL, - .ctx_size_in = 0, - .flags = BPF_F_TEST_RUN_ON_CPU, - .cpu = cpu, - .retval = 0, - ); - - return bpf_prog_test_run_opts(prog_fd, &opts); -} -#endif /* HAVE_BPF_SKEL */ - #endif /* __PERF_BPF_COUNTER_H */ diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 6ff42619de12..519fee3dc3d0 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -4,15 +4,16 @@ /* Copyright (c) 2021 Google */ #include <assert.h> +#include <errno.h> #include <limits.h> #include <unistd.h> #include <sys/file.h> #include <sys/time.h> #include <sys/resource.h> #include <linux/err.h> -#include <linux/zalloc.h> #include <linux/perf_event.h> #include <api/fs/fs.h> +#include <bpf/bpf.h> #include <perf/bpf_perf.h> #include "affinity.h" @@ -26,6 +27,7 @@ #include "cpumap.h" #include "thread_map.h" +#include "bpf_skel/bperf_cgroup.h" #include "bpf_skel/bperf_cgroup.skel.h" static struct perf_event_attr cgrp_switch_attr = { @@ -41,43 +43,75 @@ static struct bperf_cgroup_bpf *skel; #define FD(evt, cpu) (*(int *)xyarray__entry(evt->core.fd, cpu, 0)) +static void setup_rodata(struct bperf_cgroup_bpf *sk, int evlist_size) +{ + int map_size, total_cpus = cpu__max_cpu().cpu; + + sk->rodata->num_cpus = total_cpus; + sk->rodata->num_events = evlist_size / nr_cgroups; + + if (cgroup_is_v2("perf_event") > 0) + sk->rodata->use_cgroup_v2 = 1; + + BUG_ON(evlist_size % nr_cgroups != 0); + + /* we need one copy of events per cpu for reading */ + map_size = total_cpus * evlist_size / nr_cgroups; + bpf_map__set_max_entries(sk->maps.events, map_size); + bpf_map__set_max_entries(sk->maps.cgrp_idx, nr_cgroups); + /* previous result is saved in a per-cpu array */ + map_size = evlist_size / nr_cgroups; + bpf_map__set_max_entries(sk->maps.prev_readings, map_size); + /* cgroup result needs all events (per-cpu) */ + map_size = evlist_size; + bpf_map__set_max_entries(sk->maps.cgrp_readings, map_size); +} + +static void test_max_events_program_load(void) +{ +#ifndef NDEBUG + /* + * Test that the program verifies with the maximum number of events. If + * this test fails unfortunately perf needs recompiling with a lower + * BPERF_CGROUP__MAX_EVENTS to avoid BPF verifier issues. + */ + int err, max_events = BPERF_CGROUP__MAX_EVENTS * nr_cgroups; + struct bperf_cgroup_bpf *test_skel = bperf_cgroup_bpf__open(); + + if (!test_skel) { + pr_err("Failed to open cgroup skeleton\n"); + return; + } + setup_rodata(test_skel, max_events); + err = bperf_cgroup_bpf__load(test_skel); + if (err) { + pr_err("Failed to load cgroup skeleton with max events %d.\n", + BPERF_CGROUP__MAX_EVENTS); + } + bperf_cgroup_bpf__destroy(test_skel); +#endif +} + static int bperf_load_program(struct evlist *evlist) { struct bpf_link *link; struct evsel *evsel; struct cgroup *cgrp, *leader_cgrp; - int i, j; + unsigned int i; struct perf_cpu cpu; int total_cpus = cpu__max_cpu().cpu; - int map_size, map_fd; - int prog_fd, err; + int map_fd, prog_fd, err; + + set_max_rlimit(); + + test_max_events_program_load(); skel = bperf_cgroup_bpf__open(); if (!skel) { pr_err("Failed to open cgroup skeleton\n"); return -1; } - - skel->rodata->num_cpus = total_cpus; - skel->rodata->num_events = evlist->core.nr_entries / nr_cgroups; - - if (cgroup_is_v2("perf_event") > 0) - skel->rodata->use_cgroup_v2 = 1; - - BUG_ON(evlist->core.nr_entries % nr_cgroups != 0); - - /* we need one copy of events per cpu for reading */ - map_size = total_cpus * evlist->core.nr_entries / nr_cgroups; - bpf_map__set_max_entries(skel->maps.events, map_size); - bpf_map__set_max_entries(skel->maps.cgrp_idx, nr_cgroups); - /* previous result is saved in a per-cpu array */ - map_size = evlist->core.nr_entries / nr_cgroups; - bpf_map__set_max_entries(skel->maps.prev_readings, map_size); - /* cgroup result needs all events (per-cpu) */ - map_size = evlist->core.nr_entries; - bpf_map__set_max_entries(skel->maps.cgrp_readings, map_size); - - set_max_rlimit(); + setup_rodata(skel, evlist->core.nr_entries); err = bperf_cgroup_bpf__load(skel); if (err) { @@ -111,6 +145,8 @@ static int bperf_load_program(struct evlist *evlist) evlist__for_each_entry(evlist, evsel) { if (cgrp == NULL || evsel->cgrp == leader_cgrp) { + unsigned int j; + leader_cgrp = evsel->cgrp; evsel->cgrp = NULL; @@ -185,7 +221,8 @@ static int bperf_cgrp__load(struct evsel *evsel, } static int bperf_cgrp__install_pe(struct evsel *evsel __maybe_unused, - int cpu __maybe_unused, int fd __maybe_unused) + int cpu_map_idx __maybe_unused, + int fd __maybe_unused) { /* nothing to do */ return 0; @@ -198,7 +235,7 @@ static int bperf_cgrp__install_pe(struct evsel *evsel __maybe_unused, static int bperf_cgrp__sync_counters(struct evlist *evlist) { struct perf_cpu cpu; - int idx; + unsigned int idx; int prog_fd = bpf_program__fd(skel->progs.trigger_read); perf_cpu_map__for_each_cpu(cpu, idx, evlist->core.all_cpus) @@ -250,7 +287,7 @@ static int bperf_cgrp__read(struct evsel *evsel) evlist__for_each_entry(evlist, evsel) { __u32 idx = evsel->core.idx; - int i; + unsigned int i; struct perf_cpu cpu; err = bpf_map_lookup_elem(reading_map_fd, &idx, values); diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index 25fc280e414a..c456d24efa30 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -1,8 +1,10 @@ -#include <stdio.h> +#include <errno.h> #include <fcntl.h> #include <stdint.h> +#include <stdio.h> #include <stdlib.h> +#include <bpf/bpf.h> #include <linux/err.h> #include "util/ftrace.h" @@ -21,15 +23,26 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) { int fd, err; int i, ncpus = 1, ntasks = 1; - struct filter_entry *func; + struct filter_entry *func = NULL; - if (!list_is_singular(&ftrace->filters)) { - pr_err("ERROR: %s target function(s).\n", - list_empty(&ftrace->filters) ? "No" : "Too many"); - return -1; - } + if (!list_empty(&ftrace->filters)) { + if (!list_is_singular(&ftrace->filters)) { + pr_err("ERROR: Too many target functions.\n"); + return -1; + } + func = list_first_entry(&ftrace->filters, struct filter_entry, list); + } else { + int count = 0; + struct list_head *pos; - func = list_first_entry(&ftrace->filters, struct filter_entry, list); + list_for_each(pos, &ftrace->event_pair) + count++; + + if (count != 2) { + pr_err("ERROR: Needs two target events.\n"); + return -1; + } + } skel = func_latency_bpf__open(); if (!skel) { @@ -39,6 +52,10 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) skel->rodata->bucket_range = ftrace->bucket_range; skel->rodata->min_latency = ftrace->min_latency; + skel->rodata->bucket_num = ftrace->bucket_num; + if (ftrace->bucket_range && ftrace->bucket_num) { + bpf_map__set_max_entries(skel->maps.latency, ftrace->bucket_num); + } /* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { @@ -89,20 +106,44 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) skel->bss->min = INT64_MAX; - skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin, - false, func->name); - if (IS_ERR(skel->links.func_begin)) { - pr_err("Failed to attach fentry program\n"); - err = PTR_ERR(skel->links.func_begin); - goto out; - } + if (func) { + skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin, + false, func->name); + if (IS_ERR(skel->links.func_begin)) { + pr_err("Failed to attach fentry program\n"); + err = PTR_ERR(skel->links.func_begin); + goto out; + } - skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end, - true, func->name); - if (IS_ERR(skel->links.func_end)) { - pr_err("Failed to attach fexit program\n"); - err = PTR_ERR(skel->links.func_end); - goto out; + skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end, + true, func->name); + if (IS_ERR(skel->links.func_end)) { + pr_err("Failed to attach fexit program\n"); + err = PTR_ERR(skel->links.func_end); + goto out; + } + } else { + struct filter_entry *event; + + event = list_first_entry(&ftrace->event_pair, struct filter_entry, list); + + skel->links.event_begin = bpf_program__attach_raw_tracepoint(skel->progs.event_begin, + event->name); + if (IS_ERR(skel->links.event_begin)) { + pr_err("Failed to attach first tracepoint program\n"); + err = PTR_ERR(skel->links.event_begin); + goto out; + } + + event = list_next_entry(event, list); + + skel->links.event_end = bpf_program__attach_raw_tracepoint(skel->progs.event_end, + event->name); + if (IS_ERR(skel->links.event_end)) { + pr_err("Failed to attach second tracepoint program\n"); + err = PTR_ERR(skel->links.event_end); + goto out; + } } /* XXX: we don't actually use this fd - just for poll() */ @@ -124,7 +165,7 @@ int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) return 0; } -int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, +int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace, int buckets[], struct stats *stats) { int i, fd, err; @@ -138,7 +179,7 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, if (hist == NULL) return -ENOMEM; - for (idx = 0; idx < NUM_BUCKET; idx++) { + for (idx = 0; idx < skel->rodata->bucket_num; idx++) { err = bpf_map_lookup_elem(fd, &idx, hist); if (err) { buckets[idx] = 0; @@ -154,6 +195,12 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, stats->n = skel->bss->count; stats->max = skel->bss->max; stats->min = skel->bss->min; + + if (!ftrace->use_nsec) { + stats->mean /= 1000; + stats->max /= 1000; + stats->min /= 1000; + } } free(hist); diff --git a/tools/perf/util/bpf_kwork.c b/tools/perf/util/bpf_kwork.c index 5cff755c71fa..d3a2e548f2b6 100644 --- a/tools/perf/util/bpf_kwork.c +++ b/tools/perf/util/bpf_kwork.c @@ -148,7 +148,8 @@ static bool valid_kwork_class_type(enum kwork_class_type type) static int setup_filters(struct perf_kwork *kwork) { if (kwork->cpu_list != NULL) { - int idx, nr_cpus; + unsigned int idx; + int nr_cpus; struct perf_cpu_map *map; struct perf_cpu cpu; int fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter); diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c index b6f187dd9136..189a29d2bc96 100644 --- a/tools/perf/util/bpf_kwork_top.c +++ b/tools/perf/util/bpf_kwork_top.c @@ -123,7 +123,8 @@ static bool valid_kwork_class_type(enum kwork_class_type type) static int setup_filters(struct perf_kwork *kwork) { if (kwork->cpu_list) { - int idx, nr_cpus, fd; + unsigned int idx; + int nr_cpus, fd; struct perf_cpu_map *map; struct perf_cpu cpu; diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index fc8666222399..cbd7435579fe 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -12,6 +12,7 @@ #include "util/lock-contention.h" #include <linux/zalloc.h> #include <linux/string.h> +#include <api/fs/fs.h> #include <bpf/bpf.h> #include <bpf/btf.h> #include <inttypes.h> @@ -35,28 +36,26 @@ static bool slab_cache_equal(long key1, long key2, void *ctx __maybe_unused) static void check_slab_cache_iter(struct lock_contention *con) { - struct btf *btf = btf__load_vmlinux_btf(); s32 ret; hashmap__init(&slab_hash, slab_cache_hash, slab_cache_equal, /*ctx=*/NULL); - if (btf == NULL) { - pr_debug("BTF loading failed: %s\n", strerror(errno)); + con->btf = btf__load_vmlinux_btf(); + if (con->btf == NULL) { + pr_debug("BTF loading failed: %m\n"); return; } - ret = btf__find_by_name_kind(btf, "bpf_iter__kmem_cache", BTF_KIND_STRUCT); + ret = btf__find_by_name_kind(con->btf, "bpf_iter__kmem_cache", BTF_KIND_STRUCT); if (ret < 0) { bpf_program__set_autoload(skel->progs.slab_cache_iter, false); pr_debug("slab cache iterator is not available: %d\n", ret); - goto out; + return; } has_slab_iter = true; bpf_map__set_max_entries(skel->maps.slab_caches, con->map_nr_entries); -out: - btf__free(btf); } static void run_slab_cache_iter(void) @@ -109,6 +108,78 @@ static void exit_slab_cache_iter(void) hashmap__clear(&slab_hash); } +static void init_numa_data(struct lock_contention *con) +{ + struct symbol *sym; + struct map *kmap; + char *buf = NULL, *p; + size_t len; + long last = -1; + int ret; + + if (!con->btf) + return; + + /* + * 'struct zone' is embedded in 'struct pglist_data' as an array. + * As we may not have full information of the struct zone in the + * (fake) vmlinux.h, let's get the actual size from BTF. + */ + ret = btf__find_by_name_kind(con->btf, "zone", BTF_KIND_STRUCT); + if (ret < 0) { + pr_debug("cannot get type of struct zone: %d\n", ret); + return; + } + + ret = btf__resolve_size(con->btf, ret); + if (ret < 0) { + pr_debug("cannot get size of struct zone: %d\n", ret); + return; + } + skel->rodata->sizeof_zone = ret; + + /* UMA system doesn't have 'node_data[]' - just use contig_page_data. */ + sym = machine__find_kernel_symbol_by_name(con->machine, + "contig_page_data", + &kmap); + if (sym) { + skel->rodata->contig_page_data_addr = map__unmap_ip(kmap, sym->start); + map__put(kmap); + return; + } + + /* + * The 'node_data' is an array of pointers to struct pglist_data. + * It needs to follow the pointer for each node in BPF to get the + * address of struct pglist_data and its zones. + */ + sym = machine__find_kernel_symbol_by_name(con->machine, + "node_data", + &kmap); + if (sym == NULL) + return; + + skel->rodata->node_data_addr = map__unmap_ip(kmap, sym->start); + map__put(kmap); + + /* get the number of online nodes using the last node number + 1 */ + ret = sysfs__read_str("devices/system/node/online", &buf, &len); + if (ret < 0) { + pr_debug("failed to read online node: %d\n", ret); + return; + } + + p = buf; + while (p && *p) { + last = strtol(p, &p, 0); + + if (p && (*p == ',' || *p == '-' || *p == '\n')) + p++; + } + skel->rodata->nr_nodes = last + 1; + free(buf); +} + int lock_contention_prepare(struct lock_contention *con) { int i, fd; @@ -116,6 +187,9 @@ int lock_contention_prepare(struct lock_contention *con) struct evlist *evlist = con->evlist; struct target *target = con->target; + /* make sure it loads the kernel map before lookup */ + map__load(machine__kernel_map(con->machine)); + skel = lock_contention_bpf__open(); if (!skel) { pr_err("Failed to open lock-contention BPF skeleton\n"); @@ -131,10 +205,20 @@ int lock_contention_prepare(struct lock_contention *con) else bpf_map__set_max_entries(skel->maps.task_data, 1); - if (con->save_callstack) + if (con->save_callstack) { bpf_map__set_max_entries(skel->maps.stacks, con->map_nr_entries); - else + if (con->owner) { + bpf_map__set_value_size(skel->maps.stack_buf, con->max_stack * sizeof(u64)); + bpf_map__set_key_size(skel->maps.owner_stacks, + con->max_stack * sizeof(u64)); + bpf_map__set_max_entries(skel->maps.owner_stacks, con->map_nr_entries); + bpf_map__set_max_entries(skel->maps.owner_data, con->map_nr_entries); + bpf_map__set_max_entries(skel->maps.owner_stat, con->map_nr_entries); + skel->rodata->max_stack = con->max_stack; + } + } else { bpf_map__set_max_entries(skel->maps.stacks, 1); + } if (target__has_cpu(target)) { skel->rodata->has_cpu = 1; @@ -183,6 +267,27 @@ int lock_contention_prepare(struct lock_contention *con) skel->rodata->has_addr = 1; } + /* resolve lock name in delays */ + if (con->nr_delays) { + struct symbol *sym; + struct map *kmap; + + for (i = 0; i < con->nr_delays; i++) { + sym = machine__find_kernel_symbol_by_name(con->machine, + con->delays[i].sym, + &kmap); + if (sym == NULL) { + pr_warning("ignore unknown symbol: %s\n", + con->delays[i].sym); + continue; + } + + con->delays[i].addr = map__unmap_ip(kmap, sym->start); + } + skel->rodata->lock_delay = 1; + bpf_map__set_max_entries(skel->maps.lock_delays, con->nr_delays); + } + bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus); bpf_map__set_max_entries(skel->maps.task_filter, ntasks); bpf_map__set_max_entries(skel->maps.type_filter, ntypes); @@ -208,6 +313,8 @@ int lock_contention_prepare(struct lock_contention *con) bpf_map__set_max_entries(skel->maps.slab_filter, nslabs); + init_numa_data(con); + if (lock_contention_bpf__load(skel) < 0) { pr_err("Failed to load lock-contention BPF skeleton\n"); return -1; @@ -272,6 +379,13 @@ int lock_contention_prepare(struct lock_contention *con) bpf_map_update_elem(fd, &con->filters->cgrps[i], &val, BPF_ANY); } + if (con->nr_delays) { + fd = bpf_map__fd(skel->maps.lock_delays); + + for (i = 0; i < con->nr_delays; i++) + bpf_map_update_elem(fd, &con->delays[i].addr, &con->delays[i].time, BPF_ANY); + } + if (con->aggr_mode == LOCK_AGGR_CGROUP) read_all_cgroups(&con->cgroups); @@ -450,7 +564,6 @@ static const char *lock_contention_get_name(struct lock_contention *con, { int idx = 0; u64 addr; - const char *name = ""; static char name_buf[KSYM_NAME_LEN]; struct symbol *sym; struct map *kmap; @@ -465,13 +578,14 @@ static const char *lock_contention_get_name(struct lock_contention *con, if (pid) { struct thread *t = machine__findnew_thread(machine, /*pid=*/-1, pid); - if (t == NULL) - return name; - if (!bpf_map_lookup_elem(task_fd, &pid, &task) && - thread__set_comm(t, task.comm, /*timestamp=*/0)) - name = task.comm; + if (t != NULL && + !bpf_map_lookup_elem(task_fd, &pid, &task) && + thread__set_comm(t, task.comm, /*timestamp=*/0)) { + snprintf(name_buf, sizeof(name_buf), "%s", task.comm); + return name_buf; + } } - return name; + return ""; } if (con->aggr_mode == LOCK_AGGR_ADDR) { @@ -495,6 +609,11 @@ static const char *lock_contention_get_name(struct lock_contention *con, return "rq_lock"; } + if (!bpf_map_lookup_elem(lock_fd, &key->lock_addr_or_cgroup, &flags)) { + if (flags == LOCK_CLASS_ZONE_LOCK) + return "zone_lock"; + } + /* look slab_hash for dynamic locks in a slab object */ if (hashmap__find(&slab_hash, flags & LCB_F_SLAB_ID_MASK, &slab_data)) { snprintf(name_buf, sizeof(name_buf), "&%s", slab_data->name); @@ -539,6 +658,63 @@ static const char *lock_contention_get_name(struct lock_contention *con, return name_buf; } +struct lock_stat *pop_owner_stack_trace(struct lock_contention *con) +{ + int stacks_fd, stat_fd; + u64 *stack_trace = NULL; + s32 stack_id; + struct contention_key ckey = {}; + struct contention_data cdata = {}; + size_t stack_size = con->max_stack * sizeof(*stack_trace); + struct lock_stat *st = NULL; + + stacks_fd = bpf_map__fd(skel->maps.owner_stacks); + stat_fd = bpf_map__fd(skel->maps.owner_stat); + if (!stacks_fd || !stat_fd) + goto out_err; + + stack_trace = zalloc(stack_size); + if (stack_trace == NULL) + goto out_err; + + if (bpf_map_get_next_key(stacks_fd, NULL, stack_trace)) + goto out_err; + + bpf_map_lookup_elem(stacks_fd, stack_trace, &stack_id); + ckey.stack_id = stack_id; + bpf_map_lookup_elem(stat_fd, &ckey, &cdata); + + st = zalloc(sizeof(struct lock_stat)); + if (!st) + goto out_err; + + st->name = strdup(stack_trace[0] ? lock_contention_get_name(con, NULL, stack_trace, 0) : + "unknown"); + if (!st->name) + goto out_err; + + st->flags = cdata.flags; + st->nr_contended = cdata.count; + st->wait_time_total = cdata.total_time; + st->wait_time_max = cdata.max_time; + st->wait_time_min = cdata.min_time; + st->callstack = stack_trace; + + if (cdata.count) + st->avg_wait_time = cdata.total_time / cdata.count; + + bpf_map_delete_elem(stacks_fd, stack_trace); + bpf_map_delete_elem(stat_fd, &ckey); + + return st; + +out_err: + free(stack_trace); + free(st); + + return NULL; +} + int lock_contention_read(struct lock_contention *con) { int fd, stack, err = 0; @@ -579,9 +755,6 @@ int lock_contention_read(struct lock_contention *con) bpf_prog_test_run_opts(prog_fd, &opts); } - /* make sure it loads the kernel map */ - maps__load_first(machine->kmaps); - prev_key = NULL; while (!bpf_map_get_next_key(fd, prev_key, &key)) { s64 ls_key; @@ -676,6 +849,7 @@ int lock_contention_finish(struct lock_contention *con) } exit_slab_cache_iter(); + btf__free(con->btf); return 0; } diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c deleted file mode 100644 index 578f27d2d6b4..000000000000 --- a/tools/perf/util/bpf_map.c +++ /dev/null @@ -1,69 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -#include "util/bpf_map.h" -#include <bpf/bpf.h> -#include <bpf/libbpf.h> -#include <linux/err.h> -#include <linux/kernel.h> -#include <stdbool.h> -#include <stdlib.h> -#include <unistd.h> - -static bool bpf_map__is_per_cpu(enum bpf_map_type type) -{ - return type == BPF_MAP_TYPE_PERCPU_HASH || - type == BPF_MAP_TYPE_PERCPU_ARRAY || - type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; -} - -static void *bpf_map__alloc_value(const struct bpf_map *map) -{ - if (bpf_map__is_per_cpu(bpf_map__type(map))) - return malloc(round_up(bpf_map__value_size(map), 8) * - sysconf(_SC_NPROCESSORS_CONF)); - - return malloc(bpf_map__value_size(map)); -} - -int bpf_map__fprintf(struct bpf_map *map, FILE *fp) -{ - void *prev_key = NULL, *key, *value; - int fd = bpf_map__fd(map), err; - int printed = 0; - - if (fd < 0) - return fd; - - err = -ENOMEM; - key = malloc(bpf_map__key_size(map)); - if (key == NULL) - goto out; - - value = bpf_map__alloc_value(map); - if (value == NULL) - goto out_free_key; - - while ((err = bpf_map_get_next_key(fd, prev_key, key) == 0)) { - int intkey = *(int *)key; - - if (!bpf_map_lookup_elem(fd, key, value)) { - bool boolval = *(bool *)value; - if (boolval) - printed += fprintf(fp, "[%d] = %d,\n", intkey, boolval); - } else { - printed += fprintf(fp, "[%d] = ERROR,\n", intkey); - } - - prev_key = key; - } - - if (err == ENOENT) - err = printed; - - free(value); -out_free_key: - free(key); -out: - return err; -} diff --git a/tools/perf/util/bpf_map.h b/tools/perf/util/bpf_map.h deleted file mode 100644 index c2f7c13cba23..000000000000 --- a/tools/perf/util/bpf_map.h +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) -#ifndef __PERF_BPF_MAP_H -#define __PERF_BPF_MAP_H 1 - -#include <stdio.h> -struct bpf_map; - -#ifdef HAVE_LIBBPF_SUPPORT - -int bpf_map__fprintf(struct bpf_map *map, FILE *fp); - -#else - -#include <linux/compiler.h> - -static inline int bpf_map__fprintf(struct bpf_map *map __maybe_unused, FILE *fp __maybe_unused) -{ - return 0; -} - -#endif // HAVE_LIBBPF_SUPPORT - -#endif // __PERF_BPF_MAP_H diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c index 4269b41d1771..a3b699a5322f 100644 --- a/tools/perf/util/bpf_off_cpu.c +++ b/tools/perf/util/bpf_off_cpu.c @@ -13,6 +13,9 @@ #include "util/cgroup.h" #include "util/strlist.h" #include <bpf/bpf.h> +#include <bpf/btf.h> +#include <internal/xyarray.h> +#include <linux/time64.h> #include "bpf_skel/off_cpu.skel.h" @@ -36,34 +39,25 @@ union off_cpu_data { u64 array[1024 / sizeof(u64)]; }; +static u64 off_cpu_raw[MAX_STACKS + 5]; + static int off_cpu_config(struct evlist *evlist) { + char off_cpu_event[64]; struct evsel *evsel; - struct perf_event_attr attr = { - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - .size = sizeof(attr), /* to capture ABI version */ - }; - char *evname = strdup(OFFCPU_EVENT); - if (evname == NULL) - return -ENOMEM; - - evsel = evsel__new(&attr); - if (!evsel) { - free(evname); - return -ENOMEM; + scnprintf(off_cpu_event, sizeof(off_cpu_event), "bpf-output/name=%s/", OFFCPU_EVENT); + if (parse_event(evlist, off_cpu_event)) { + pr_err("Failed to open off-cpu event\n"); + return -1; } - evsel->core.attr.freq = 1; - evsel->core.attr.sample_period = 1; - /* off-cpu analysis depends on stack trace */ - evsel->core.attr.sample_type = PERF_SAMPLE_CALLCHAIN; - - evlist__add(evlist, evsel); - - free(evsel->name); - evsel->name = evname; + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_offcpu_event(evsel)) { + evsel->core.system_wide = true; + break; + } + } return 0; } @@ -71,6 +65,9 @@ static int off_cpu_config(struct evlist *evlist) static void off_cpu_start(void *arg) { struct evlist *evlist = arg; + struct evsel *evsel; + struct perf_cpu pcpu; + unsigned int i; /* update task filter for the given workload */ if (skel->rodata->has_task && skel->rodata->uses_tgid && @@ -84,6 +81,26 @@ static void off_cpu_start(void *arg) bpf_map_update_elem(fd, &pid, &val, BPF_ANY); } + /* update BPF perf_event map */ + evsel = evlist__find_evsel_by_str(evlist, OFFCPU_EVENT); + if (evsel == NULL) { + pr_err("%s evsel not found\n", OFFCPU_EVENT); + return; + } + + perf_cpu_map__for_each_cpu(pcpu, i, evsel->core.cpus) { + int err; + int cpu_nr = pcpu.cpu; + + err = bpf_map__update_elem(skel->maps.offcpu_output, &cpu_nr, sizeof(int), + xyarray__entry(evsel->core.fd, cpu_nr, 0), + sizeof(int), BPF_ANY); + if (err) { + pr_err("Failed to update perf event map for direct off-cpu dumping\n"); + return; + } + } + skel->bss->enabled = 1; } @@ -277,6 +294,8 @@ int off_cpu_prepare(struct evlist *evlist, struct target *target, } } + skel->bss->offcpu_thresh_ns = opts->off_cpu_thresh_ns; + err = off_cpu_bpf__attach(skel); if (err) { pr_err("Failed to attach off-cpu BPF skeleton\n"); @@ -300,6 +319,7 @@ int off_cpu_write(struct perf_session *session) { int bytes = 0, size; int fd, stack; + u32 raw_size; u64 sample_type, val, sid = 0; struct evsel *evsel; struct perf_data_file *file = &session->data->file; @@ -339,46 +359,54 @@ int off_cpu_write(struct perf_session *session) while (!bpf_map_get_next_key(fd, &prev, &key)) { int n = 1; /* start from perf_event_header */ - int ip_pos = -1; bpf_map_lookup_elem(fd, &key, &val); + /* zero-fill some of the fields, will be overwritten by raw_data when parsing */ if (sample_type & PERF_SAMPLE_IDENTIFIER) data.array[n++] = sid; - if (sample_type & PERF_SAMPLE_IP) { - ip_pos = n; + if (sample_type & PERF_SAMPLE_IP) data.array[n++] = 0; /* will be updated */ - } if (sample_type & PERF_SAMPLE_TID) - data.array[n++] = (u64)key.pid << 32 | key.tgid; + data.array[n++] = 0; if (sample_type & PERF_SAMPLE_TIME) data.array[n++] = tstamp; - if (sample_type & PERF_SAMPLE_ID) - data.array[n++] = sid; if (sample_type & PERF_SAMPLE_CPU) data.array[n++] = 0; if (sample_type & PERF_SAMPLE_PERIOD) - data.array[n++] = val; - if (sample_type & PERF_SAMPLE_CALLCHAIN) { - int len = 0; - - /* data.array[n] is callchain->nr (updated later) */ - data.array[n + 1] = PERF_CONTEXT_USER; - data.array[n + 2] = 0; - - bpf_map_lookup_elem(stack, &key.stack_id, &data.array[n + 2]); - while (data.array[n + 2 + len]) + data.array[n++] = 0; + if (sample_type & PERF_SAMPLE_RAW) { + /* + * [ size ][ data ] + * [ data ] + * [ data ] + * [ data ] + * [ data ][ empty] + */ + int len = 0, i = 0; + void *raw_data = (void *)data.array + n * sizeof(u64); + + off_cpu_raw[i++] = (u64)key.pid << 32 | key.tgid; + off_cpu_raw[i++] = val; + + /* off_cpu_raw[i] is callchain->nr (updated later) */ + off_cpu_raw[i + 1] = PERF_CONTEXT_USER; + off_cpu_raw[i + 2] = 0; + + bpf_map_lookup_elem(stack, &key.stack_id, &off_cpu_raw[i + 2]); + while (off_cpu_raw[i + 2 + len]) len++; - /* update length of callchain */ - data.array[n] = len + 1; + off_cpu_raw[i] = len + 1; + i += len + 2; + + off_cpu_raw[i++] = key.cgroup_id; - /* update sample ip with the first callchain entry */ - if (ip_pos >= 0) - data.array[ip_pos] = data.array[n + 2]; + raw_size = i * sizeof(u64) + sizeof(u32); /* 4 bytes for alignment */ + memcpy(raw_data, &raw_size, sizeof(raw_size)); + memcpy(raw_data + sizeof(u32), off_cpu_raw, i * sizeof(u64)); - /* calculate sample callchain data array length */ - n += len + 2; + n += i + 1; } if (sample_type & PERF_SAMPLE_CGROUP) data.array[n++] = key.cgroup_id; diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index e4352881e3fa..2a6e61864ee0 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -7,7 +7,6 @@ */ #include "vmlinux.h" -#include "../trace_augment.h" #include <bpf/bpf_helpers.h> #include <linux/limits.h> @@ -27,6 +26,8 @@ #define MAX_CPUS 4096 +#define TRACE_AUG_MAX_BUF 32 /* for buffer augmentation in perf trace */ + /* bpf-output associated map */ struct __augmented_syscalls__ { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -44,7 +45,7 @@ struct syscalls_sys_enter { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); __type(key, __u32); __type(value, __u32); - __uint(max_entries, 512); + __uint(max_entries, 1024); } syscalls_sys_enter SEC(".maps"); /* @@ -56,7 +57,7 @@ struct syscalls_sys_exit { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); __type(key, __u32); __type(value, __u32); - __uint(max_entries, 512); + __uint(max_entries, 1024); } syscalls_sys_exit SEC(".maps"); struct syscall_enter_args { diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c index 57cab7647a9a..c2298a2decc9 100644 --- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -1,14 +1,12 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook // Copyright (c) 2021 Google +#include "bperf_cgroup.h" #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_core_read.h> -#define MAX_LEVELS 10 // max cgroup hierarchy level: arbitrary -#define MAX_EVENTS 32 // max events per cgroup: arbitrary - // NOTE: many of map and global data will be modified before loading // from the userspace (perf tool) using the skeleton helpers. @@ -97,7 +95,7 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_subsys_id], cgroup); level = BPF_CORE_READ(cgrp, level); - for (cnt = 0; i < MAX_LEVELS; i++) { + for (cnt = 0; i < BPERF_CGROUP__MAX_LEVELS; i++) { __u64 cgrp_id; if (i > level) @@ -123,7 +121,7 @@ static inline int get_cgroup_v2_idx(__u32 *cgrps, int size) __u32 *elem; int cnt; - for (cnt = 0; i < MAX_LEVELS; i++) { + for (cnt = 0; i < BPERF_CGROUP__MAX_LEVELS; i++) { __u64 cgrp_id = bpf_get_current_ancestor_cgroup_id(i); if (cgrp_id == 0) @@ -148,17 +146,17 @@ static int bperf_cgroup_count(void) register int c = 0; struct bpf_perf_event_value val, delta, *prev_val, *cgrp_val; __u32 cpu = bpf_get_smp_processor_id(); - __u32 cgrp_idx[MAX_LEVELS]; + __u32 cgrp_idx[BPERF_CGROUP__MAX_LEVELS]; int cgrp_cnt; __u32 key, cgrp; long err; if (use_cgroup_v2) - cgrp_cnt = get_cgroup_v2_idx(cgrp_idx, MAX_LEVELS); + cgrp_cnt = get_cgroup_v2_idx(cgrp_idx, BPERF_CGROUP__MAX_LEVELS); else - cgrp_cnt = get_cgroup_v1_idx(cgrp_idx, MAX_LEVELS); + cgrp_cnt = get_cgroup_v1_idx(cgrp_idx, BPERF_CGROUP__MAX_LEVELS); - for ( ; idx < MAX_EVENTS; idx++) { + for ( ; idx < BPERF_CGROUP__MAX_EVENTS; idx++) { if (idx == num_events) break; @@ -186,7 +184,7 @@ static int bperf_cgroup_count(void) delta.enabled = val.enabled - prev_val->enabled; delta.running = val.running - prev_val->running; - for (c = 0; c < MAX_LEVELS; c++) { + for (c = 0; c < BPERF_CGROUP__MAX_LEVELS; c++) { if (c == cgrp_cnt) break; diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.h b/tools/perf/util/bpf_skel/bperf_cgroup.h new file mode 100644 index 000000000000..3fb84b19d39a --- /dev/null +++ b/tools/perf/util/bpf_skel/bperf_cgroup.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Data structures shared between BPF and tools. */ +#ifndef __BPERF_CGROUP_H +#define __BPERF_CGROUP_H + +// These constants impact code size of bperf_cgroup.bpf.c that may result in BPF +// verifier issues. They are exposed to control the size and also to disable BPF +// counters when the number of user events is too large. + +// max cgroup hierarchy level: arbitrary +#define BPERF_CGROUP__MAX_LEVELS 10 +// max events per cgroup: arbitrary +#define BPERF_CGROUP__MAX_EVENTS 128 + +#endif /* __BPERF_CGROUP_H */ diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c index fb144811b34f..621e2022c8bc 100644 --- a/tools/perf/util/bpf_skel/func_latency.bpf.c +++ b/tools/perf/util/bpf_skel/func_latency.bpf.c @@ -50,35 +50,91 @@ const volatile int use_nsec = 0; const volatile unsigned int bucket_range; const volatile unsigned int min_latency; const volatile unsigned int max_latency; +const volatile unsigned int bucket_num = NUM_BUCKET; -SEC("kprobe/func") -int BPF_PROG(func_begin) +static bool can_record(void) { - __u64 key, now; - - if (!enabled) - return 0; - - key = bpf_get_current_pid_tgid(); - if (has_cpu) { __u32 cpu = bpf_get_smp_processor_id(); __u8 *ok; ok = bpf_map_lookup_elem(&cpu_filter, &cpu); if (!ok) - return 0; + return false; } if (has_task) { - __u32 pid = key & 0xffffffff; + __u32 pid = bpf_get_current_pid_tgid(); __u8 *ok; ok = bpf_map_lookup_elem(&task_filter, &pid); if (!ok) - return 0; + return false; + } + return true; +} + +static void update_latency(__s64 delta) +{ + __u64 val = delta; + __u32 key = 0; + __u64 *hist; + __u64 cmp_base = use_nsec ? 1 : 1000; + + if (delta < 0) + return; + + if (bucket_range != 0) { + val = delta / cmp_base; + + if (min_latency > 0) { + if (val > min_latency) + val -= min_latency; + else + goto do_lookup; + } + + // Less than 1 unit (ms or ns), or, in the future, + // than the min latency desired. + if (val > 0) { // 1st entry: [ 1 unit .. bucket_range units ) + key = val / bucket_range + 1; + if (key >= bucket_num) + key = bucket_num - 1; + } + + goto do_lookup; + } + // calculate index using delta + for (key = 0; key < (bucket_num - 1); key++) { + if (delta < (cmp_base << key)) + break; } +do_lookup: + hist = bpf_map_lookup_elem(&latency, &key); + if (!hist) + return; + + __sync_fetch_and_add(hist, 1); + + __sync_fetch_and_add(&total, delta); // always in nsec + __sync_fetch_and_add(&count, 1); + + if (delta > max) + max = delta; + if (delta < min) + min = delta; +} + +SEC("kprobe/func") +int BPF_PROG(func_begin) +{ + __u64 key, now; + + if (!enabled || !can_record()) + return 0; + + key = bpf_get_current_pid_tgid(); now = bpf_ktime_get_ns(); // overwrite timestamp for nested functions @@ -91,7 +147,6 @@ int BPF_PROG(func_end) { __u64 tid; __u64 *start; - __u64 cmp_base = use_nsec ? 1 : 1000; if (!enabled) return 0; @@ -100,61 +155,44 @@ int BPF_PROG(func_end) start = bpf_map_lookup_elem(&functime, &tid); if (start) { - __s64 delta = bpf_ktime_get_ns() - *start; - __u32 key = 0; - __u64 *hist; - + update_latency(bpf_ktime_get_ns() - *start); bpf_map_delete_elem(&functime, &tid); + } - if (delta < 0) - return 0; - - if (bucket_range != 0) { - delta /= cmp_base; - - if (min_latency > 0) { - if (delta > min_latency) - delta -= min_latency; - else - goto do_lookup; - } - - // Less than 1 unit (ms or ns), or, in the future, - // than the min latency desired. - if (delta > 0) { // 1st entry: [ 1 unit .. bucket_range units ) - // clang 12 doesn't like s64 / u32 division - key = (__u64)delta / bucket_range + 1; - if (key >= NUM_BUCKET || - delta >= max_latency - min_latency) - key = NUM_BUCKET - 1; - } - - delta += min_latency; - goto do_lookup; - } - // calculate index using delta - for (key = 0; key < (NUM_BUCKET - 1); key++) { - if (delta < (cmp_base << key)) - break; - } + return 0; +} -do_lookup: - hist = bpf_map_lookup_elem(&latency, &key); - if (!hist) - return 0; +SEC("raw_tp") +int BPF_PROG(event_begin) +{ + __u64 key, now; + + if (!enabled || !can_record()) + return 0; - *hist += 1; + key = bpf_get_current_pid_tgid(); + now = bpf_ktime_get_ns(); + + // overwrite timestamp for nested events + bpf_map_update_elem(&functime, &key, &now, BPF_ANY); + return 0; +} + +SEC("raw_tp") +int BPF_PROG(event_end) +{ + __u64 tid; + __u64 *start; - if (bucket_range == 0) - delta /= cmp_base; + if (!enabled) + return 0; - __sync_fetch_and_add(&total, delta); - __sync_fetch_and_add(&count, 1); + tid = bpf_get_current_pid_tgid(); - if (delta > max) - max = delta; - if (delta < min) - min = delta; + start = bpf_map_lookup_elem(&functime, &tid); + if (start) { + update_latency(bpf_ktime_get_ns() - *start); + bpf_map_delete_elem(&functime, &tid); } return 0; diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c index 73e32e063030..6673386302e2 100644 --- a/tools/perf/util/bpf_skel/kwork_top.bpf.c +++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c @@ -18,9 +18,7 @@ enum kwork_class_type { }; #define MAX_ENTRIES 102400 -#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 4096 -#endif #define PF_KTHREAD 0x00200000 #define MAX_COMMAND_LEN 16 diff --git a/tools/perf/util/bpf_skel/kwork_trace.bpf.c b/tools/perf/util/bpf_skel/kwork_trace.bpf.c index cbd79bc4b330..9ce9c8dddc4b 100644 --- a/tools/perf/util/bpf_skel/kwork_trace.bpf.c +++ b/tools/perf/util/bpf_skel/kwork_trace.bpf.c @@ -80,7 +80,7 @@ static __always_inline int local_strncmp(const char *s1, for (i = 0; i < sz; i++) { ret = (unsigned char)s1[i] - (unsigned char)s2[i]; - if (ret || !s1[i] || !s2[i]) + if (ret || !s1[i]) break; } diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 6533ea9b044c..96e7d853b9ed 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -11,6 +11,12 @@ /* for collect_lock_syms(). 4096 was rejected by the verifier */ #define MAX_CPUS 1024 +/* for collect_zone_lock(). It should be more than the actual zones. */ +#define MAX_ZONES 10 + +/* for do_lock_delay(). Arbitrarily set to 1 million. */ +#define MAX_LOOP (1U << 20) + /* lock contention flags from include/trace/events/lock.h */ #define LCB_F_SPIN (1U << 0) #define LCB_F_READ (1U << 1) @@ -27,6 +33,38 @@ struct { __uint(max_entries, MAX_ENTRIES); } stacks SEC(".maps"); +/* buffer for owner stacktrace */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, 1); +} stack_buf SEC(".maps"); + +/* a map for tracing owner stacktrace to owner stack id */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); // owner stacktrace + __uint(value_size, sizeof(__s32)); // owner stack id + __uint(max_entries, 1); +} owner_stacks SEC(".maps"); + +/* a map for tracing lock address to owner data */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); // lock address + __uint(value_size, sizeof(struct owner_tracing_data)); + __uint(max_entries, 1); +} owner_data SEC(".maps"); + +/* a map for contention_key (stores owner stack id) to contention data */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(struct contention_key)); + __uint(value_size, sizeof(struct contention_data)); + __uint(max_entries, 1); +} owner_stat SEC(".maps"); + /* maintain timestamp at the beginning of contention */ struct { __uint(type, BPF_MAP_TYPE_HASH); @@ -114,6 +152,13 @@ struct { __uint(max_entries, 1); } slab_caches SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, 1); +} lock_delays SEC(".maps"); + struct rw_semaphore___old { struct task_struct *owner; } __attribute__((preserve_access_index)); @@ -143,6 +188,8 @@ const volatile int needs_callstack; const volatile int stack_skip; const volatile int lock_owner; const volatile int use_cgroup_v2; +const volatile int max_stack; +const volatile int lock_delay; /* determine the key of lock stat */ const volatile int aggr_mode; @@ -164,6 +211,9 @@ int data_fail; int task_map_full; int data_map_full; +struct task_struct *bpf_task_from_pid(s32 pid) __ksym __weak; +void bpf_task_release(struct task_struct *p) __ksym __weak; + static inline __u64 get_current_cgroup_id(void) { struct task_struct *task; @@ -348,6 +398,35 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) return 0; } +static inline long delay_callback(__u64 idx, void *arg) +{ + __u64 target = *(__u64 *)arg; + + if (target <= bpf_ktime_get_ns()) + return 1; + + /* just to kill time */ + (void)bpf_get_prandom_u32(); + + return 0; +} + +static inline void do_lock_delay(__u64 duration) +{ + __u64 target = bpf_ktime_get_ns() + duration; + + bpf_loop(MAX_LOOP, delay_callback, &target, /*flags=*/0); +} + +static inline void check_lock_delay(__u64 lock) +{ + __u64 *delay; + + delay = bpf_map_lookup_elem(&lock_delays, &lock); + if (delay) + do_lock_delay(*delay); +} + static inline struct tstamp_data *get_tstamp_elem(__u32 flags) { __u32 pid; @@ -387,6 +466,61 @@ static inline struct tstamp_data *get_tstamp_elem(__u32 flags) return pelem; } +static inline s32 get_owner_stack_id(u64 *stacktrace) +{ + s32 *id, new_id; + static s64 id_gen = 1; + + id = bpf_map_lookup_elem(&owner_stacks, stacktrace); + if (id) + return *id; + + new_id = (s32)__sync_fetch_and_add(&id_gen, 1); + + bpf_map_update_elem(&owner_stacks, stacktrace, &new_id, BPF_NOEXIST); + + id = bpf_map_lookup_elem(&owner_stacks, stacktrace); + if (id) + return *id; + + return -1; +} + +static inline void update_contention_data(struct contention_data *data, u64 duration, u32 count) +{ + __sync_fetch_and_add(&data->total_time, duration); + __sync_fetch_and_add(&data->count, count); + + /* FIXME: need atomic operations */ + if (data->max_time < duration) + data->max_time = duration; + if (data->min_time > duration) + data->min_time = duration; +} + +static inline void update_owner_stat(u32 id, u64 duration, u32 flags) +{ + struct contention_key key = { + .stack_id = id, + .pid = 0, + .lock_addr_or_cgroup = 0, + }; + struct contention_data *data = bpf_map_lookup_elem(&owner_stat, &key); + + if (!data) { + struct contention_data first = { + .total_time = duration, + .max_time = duration, + .min_time = duration, + .count = 1, + .flags = flags, + }; + bpf_map_update_elem(&owner_stat, &key, &first, BPF_NOEXIST); + } else { + update_contention_data(data, duration, 1); + } +} + SEC("tp_btf/contention_begin") int contention_begin(u64 *ctx) { @@ -404,6 +538,72 @@ int contention_begin(u64 *ctx) pelem->flags = (__u32)ctx[1]; if (needs_callstack) { + u32 i = 0; + u32 id = 0; + int owner_pid; + u64 *buf; + struct task_struct *task; + struct owner_tracing_data *otdata; + + if (!lock_owner) + goto skip_owner; + + task = get_lock_owner(pelem->lock, pelem->flags); + if (!task) + goto skip_owner; + + owner_pid = BPF_CORE_READ(task, pid); + + buf = bpf_map_lookup_elem(&stack_buf, &i); + if (!buf) + goto skip_owner; + for (i = 0; i < max_stack; i++) + buf[i] = 0x0; + + if (!bpf_task_from_pid) + goto skip_owner; + + task = bpf_task_from_pid(owner_pid); + if (!task) + goto skip_owner; + + bpf_get_task_stack(task, buf, max_stack * sizeof(unsigned long), 0); + bpf_task_release(task); + + otdata = bpf_map_lookup_elem(&owner_data, &pelem->lock); + id = get_owner_stack_id(buf); + + /* + * Contention just happens, or corner case `lock` is owned by process not + * `owner_pid`. For the corner case we treat it as unexpected internal error and + * just ignore the precvious tracing record. + */ + if (!otdata || otdata->pid != owner_pid) { + struct owner_tracing_data first = { + .pid = owner_pid, + .timestamp = pelem->timestamp, + .count = 1, + .stack_id = id, + }; + bpf_map_update_elem(&owner_data, &pelem->lock, &first, BPF_ANY); + } + /* Contention is ongoing and new waiter joins */ + else { + __sync_fetch_and_add(&otdata->count, 1); + + /* + * The owner is the same, but stacktrace might be changed. In this case we + * store/update `owner_stat` based on current owner stack id. + */ + if (id != otdata->stack_id) { + update_owner_stat(id, pelem->timestamp - otdata->timestamp, + pelem->flags); + + otdata->timestamp = pelem->timestamp; + otdata->stack_id = id; + } + } +skip_owner: pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP | stack_skip); if (pelem->stack_id < 0) @@ -440,6 +640,7 @@ int contention_end(u64 *ctx) struct tstamp_data *pelem; struct contention_key key = {}; struct contention_data *data; + __u64 timestamp; __u64 duration; bool need_delete = false; @@ -467,12 +668,88 @@ int contention_end(u64 *ctx) need_delete = true; } - duration = bpf_ktime_get_ns() - pelem->timestamp; + timestamp = bpf_ktime_get_ns(); + duration = timestamp - pelem->timestamp; if ((__s64)duration < 0) { __sync_fetch_and_add(&time_fail, 1); goto out; } + if (needs_callstack && lock_owner) { + struct owner_tracing_data *otdata = bpf_map_lookup_elem(&owner_data, &pelem->lock); + + if (!otdata) + goto skip_owner; + + /* Update `owner_stat` */ + update_owner_stat(otdata->stack_id, timestamp - otdata->timestamp, pelem->flags); + + /* No contention is occurring, delete `lock` entry in `owner_data` */ + if (otdata->count <= 1) + bpf_map_delete_elem(&owner_data, &pelem->lock); + /* + * Contention is still ongoing, with a new owner (current task). `owner_data` + * should be updated accordingly. + */ + else { + u32 i = 0; + s32 ret = (s32)ctx[1]; + u64 *buf; + + otdata->timestamp = timestamp; + __sync_fetch_and_add(&otdata->count, -1); + + buf = bpf_map_lookup_elem(&stack_buf, &i); + if (!buf) + goto skip_owner; + for (i = 0; i < (u32)max_stack; i++) + buf[i] = 0x0; + + /* + * `ret` has the return code of the lock function. + * If `ret` is negative, the current task terminates lock waiting without + * acquiring it. Owner is not changed, but we still need to update the owner + * stack. + */ + if (ret < 0) { + s32 id = 0; + struct task_struct *task; + + if (!bpf_task_from_pid) + goto skip_owner; + + task = bpf_task_from_pid(otdata->pid); + if (!task) + goto skip_owner; + + bpf_get_task_stack(task, buf, + max_stack * sizeof(unsigned long), 0); + bpf_task_release(task); + + id = get_owner_stack_id(buf); + + /* + * If owner stack is changed, update owner stack id for this lock. + */ + if (id != otdata->stack_id) + otdata->stack_id = id; + } + /* + * Otherwise, update tracing data with the current task, which is the new + * owner. + */ + else { + otdata->pid = pid; + /* + * We don't want to retrieve callstack here, since it is where the + * current task acquires the lock and provides no additional + * information. We simply assign -1 to invalidate it. + */ + otdata->stack_id = -1; + } + } + } +skip_owner: switch (aggr_mode) { case LOCK_AGGR_CALLER: key.stack_id = pelem->stack_id; @@ -556,16 +833,12 @@ int contention_end(u64 *ctx) } found: - __sync_fetch_and_add(&data->total_time, duration); - __sync_fetch_and_add(&data->count, 1); - - /* FIXME: need atomic operations */ - if (data->max_time < duration) - data->max_time = duration; - if (data->min_time > duration) - data->min_time = duration; + update_contention_data(data, duration, 1); out: + if (lock_delay) + check_lock_delay(pelem->lock); + pelem->lock = 0; if (need_delete) bpf_map_delete_elem(&tstamp, &pid); @@ -574,6 +847,11 @@ out: extern struct rq runqueues __ksym; +const volatile __u64 contig_page_data_addr; +const volatile __u64 node_data_addr; +const volatile int nr_nodes; +const volatile int sizeof_zone; + struct rq___old { raw_spinlock_t lock; } __attribute__((preserve_access_index)); @@ -582,6 +860,59 @@ struct rq___new { raw_spinlock_t __lock; } __attribute__((preserve_access_index)); +static void collect_zone_lock(void) +{ + __u64 nr_zones, zone_off; + __u64 lock_addr, lock_off; + __u32 lock_flag = LOCK_CLASS_ZONE_LOCK; + + zone_off = offsetof(struct pglist_data, node_zones); + lock_off = offsetof(struct zone, lock); + + if (contig_page_data_addr) { + struct pglist_data *contig_page_data; + + contig_page_data = (void *)(long)contig_page_data_addr; + nr_zones = BPF_CORE_READ(contig_page_data, nr_zones); + + for (int i = 0; i < MAX_ZONES; i++) { + __u64 zone_addr; + + if (i >= nr_zones) + break; + + zone_addr = contig_page_data_addr + (sizeof_zone * i) + zone_off; + lock_addr = zone_addr + lock_off; + + bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY); + } + } else if (nr_nodes > 0) { + struct pglist_data **node_data = (void *)(long)node_data_addr; + + for (int i = 0; i < nr_nodes; i++) { + struct pglist_data *pgdat = NULL; + int err; + + err = bpf_core_read(&pgdat, sizeof(pgdat), &node_data[i]); + if (err < 0 || pgdat == NULL) + break; + + nr_zones = BPF_CORE_READ(pgdat, nr_zones); + for (int k = 0; k < MAX_ZONES; k++) { + __u64 zone_addr; + + if (k >= nr_zones) + break; + + zone_addr = (__u64)(void *)pgdat + (sizeof_zone * k) + zone_off; + lock_addr = zone_addr + lock_off; + + bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY); + } + } + } +} + SEC("raw_tp/bpf_test_finish") int BPF_PROG(collect_lock_syms) { @@ -603,6 +934,9 @@ int BPF_PROG(collect_lock_syms) lock_flag = LOCK_CLASS_RQLOCK; bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY); } + + collect_zone_lock(); + return 0; } diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index c15f734d7fc4..28c5e5aced7f 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -3,6 +3,13 @@ #ifndef UTIL_BPF_SKEL_LOCK_DATA_H #define UTIL_BPF_SKEL_LOCK_DATA_H +struct owner_tracing_data { + u32 pid; // Who has the lock. + u32 count; // How many waiters for this lock. + u64 timestamp; // The time while the owner acquires lock and contention is going on. + s32 stack_id; // Identifier for `owner_stat`, which stores as value in `owner_stacks` +}; + struct tstamp_data { u64 timestamp; u64 lock; @@ -60,6 +67,7 @@ enum lock_aggr_mode { enum lock_class_sym { LOCK_CLASS_NONE, LOCK_CLASS_RQLOCK, + LOCK_CLASS_ZONE_LOCK, }; struct slab_cache_data { diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index c152116df72f..72763bb8d1de 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -18,10 +18,19 @@ #define MAX_STACKS 32 #define MAX_ENTRIES 102400 +#define MAX_CPUS 4096 +#define MAX_OFFCPU_LEN 37 + +// We have a 'struct stack' in vmlinux.h when building with GEN_VMLINUX_H=1 +struct __stack { + u64 array[MAX_STACKS]; +}; + struct tstamp_data { __u32 stack_id; __u32 state; __u64 timestamp; + struct __stack stack; }; struct offcpu_key { @@ -39,6 +48,24 @@ struct { __uint(max_entries, MAX_ENTRIES); } stacks SEC(".maps"); +struct offcpu_data { + u64 array[MAX_OFFCPU_LEN]; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __uint(max_entries, MAX_CPUS); +} offcpu_output SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct offcpu_data)); + __uint(max_entries, 1); +} offcpu_payload SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_TASK_STORAGE); __uint(map_flags, BPF_F_NO_PREALLOC); @@ -97,6 +124,8 @@ const volatile bool uses_cgroup_v1 = false; int perf_subsys_id = -1; +__u64 offcpu_thresh_ns; + /* * Old kernel used to call it task_struct->state and now it's '__state'. * Use BPF CO-RE "ignored suffix rule" to deal with it like below: @@ -183,6 +212,47 @@ static inline int can_record(struct task_struct *t, int state) return 1; } +static inline int copy_stack(struct __stack *from, struct offcpu_data *to, int n) +{ + int len = 0; + + for (int i = 0; i < MAX_STACKS && from->array[i]; ++i, ++len) + to->array[n + 2 + i] = from->array[i]; + + return len; +} + +/** + * off_cpu_dump - dump off-cpu samples to ring buffer + * @data: payload for dumping off-cpu samples + * @key: off-cpu data + * @stack: stack trace of the task before being scheduled out + * + * If the threshold of off-cpu time is reached, acquire tid, period, callchain, and cgroup id + * information of the task, and dump it as a raw sample to perf ring buffer + */ +static int off_cpu_dump(void *ctx, struct offcpu_data *data, struct offcpu_key *key, + struct __stack *stack, __u64 delta) +{ + int n = 0, len = 0; + + data->array[n++] = (u64)key->tgid << 32 | key->pid; + data->array[n++] = delta; + + /* data->array[n] is callchain->nr (updated later) */ + data->array[n + 1] = PERF_CONTEXT_USER; + data->array[n + 2] = 0; + len = copy_stack(stack, data, n); + + /* update length of callchain */ + data->array[n] = len + 1; + n += len + 2; + + data->array[n++] = key->cgroup_id; + + return bpf_perf_event_output(ctx, &offcpu_output, BPF_F_CURRENT_CPU, data, n * sizeof(u64)); +} + static int off_cpu_stat(u64 *ctx, struct task_struct *prev, struct task_struct *next, int state) { @@ -207,6 +277,16 @@ static int off_cpu_stat(u64 *ctx, struct task_struct *prev, pelem->state = state; pelem->stack_id = stack_id; + /* + * If stacks are successfully collected by bpf_get_stackid(), collect them once more + * in task_storage for direct off-cpu sample dumping + */ + if (stack_id > 0 && bpf_get_stack(ctx, &pelem->stack, MAX_STACKS * sizeof(u64), BPF_F_USER_STACK)) { + /* + * This empty if block is used to avoid 'result unused warning' from bpf_get_stack(). + * If the collection fails, continue with the logic for the next task. + */ + } next: pelem = bpf_task_storage_get(&tstamp, next, NULL, 0); @@ -221,11 +301,19 @@ next: __u64 delta = ts - pelem->timestamp; __u64 *total; - total = bpf_map_lookup_elem(&off_cpu, &key); - if (total) - *total += delta; - else - bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY); + if (delta >= offcpu_thresh_ns) { + int zero = 0; + struct offcpu_data *data = bpf_map_lookup_elem(&offcpu_payload, &zero); + + if (data) + off_cpu_dump(ctx, data, &key, &pelem->stack, delta); + } else { + total = bpf_map_lookup_elem(&off_cpu, &key); + if (total) + *total += delta; + else + bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY); + } /* prevent to reuse the timestamp later */ pelem->timestamp = 0; diff --git a/tools/perf/util/bpf_skel/perf_version.h b/tools/perf/util/bpf_skel/perf_version.h new file mode 100644 index 000000000000..1ed5b2e59bf5 --- /dev/null +++ b/tools/perf/util/bpf_skel/perf_version.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ + +#ifndef __PERF_VERSION_H__ +#define __PERF_VERSION_H__ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +/* + * This is used by tests/shell/record_bpf_metadata.sh + * to verify that BPF metadata generation works. + * + * PERF_VERSION is defined by a build rule at compile time. + */ +const char bpf_metadata_perf_version[] SEC(".rodata") = PERF_VERSION; + +#endif /* __PERF_VERSION_H__ */ diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index b195e6efeb8b..e5666d4c1722 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -164,7 +164,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, if (entry->part == 8) { union perf_mem_data_src___new *data = (void *)&kctx->data->data_src; - if (bpf_core_field_exists(data->mem_hops)) + if (__builtin_preserve_field_info(data->mem_hops, BPF_FIELD_EXISTS)) return data->mem_hops; return 0; diff --git a/tools/perf/util/bpf_skel/syscall_summary.bpf.c b/tools/perf/util/bpf_skel/syscall_summary.bpf.c new file mode 100644 index 000000000000..4172f3c9fc48 --- /dev/null +++ b/tools/perf/util/bpf_skel/syscall_summary.bpf.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Trace raw_syscalls tracepoints to collect system call statistics. + */ + +#include "vmlinux.h" +#include "syscall_summary.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +/* This is to calculate a delta between sys-enter and sys-exit for each thread */ +struct syscall_trace { + int nr; /* syscall number is only available at sys-enter */ + int unused; + u64 timestamp; +}; + +#define MAX_ENTRIES (128 * 1024) + +struct syscall_trace_map { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); /* tid */ + __type(value, struct syscall_trace); + __uint(max_entries, MAX_ENTRIES); +} syscall_trace_map SEC(".maps"); + +struct syscall_stats_map { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct syscall_key); + __type(value, struct syscall_stats); + __uint(max_entries, MAX_ENTRIES); +} syscall_stats_map SEC(".maps"); + +int enabled; /* controlled from userspace */ + +const volatile enum syscall_aggr_mode aggr_mode; +const volatile int use_cgroup_v2; + +int perf_subsys_id = -1; + +static inline __u64 get_current_cgroup_id(void) +{ + struct task_struct *task; + struct cgroup *cgrp; + + if (use_cgroup_v2) + return bpf_get_current_cgroup_id(); + + task = bpf_get_current_task_btf(); + + if (perf_subsys_id == -1) { +#if __has_builtin(__builtin_preserve_enum_value) + perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id, + perf_event_cgrp_id); +#else + perf_subsys_id = perf_event_cgrp_id; +#endif + } + + cgrp = BPF_CORE_READ(task, cgroups, subsys[perf_subsys_id], cgroup); + return BPF_CORE_READ(cgrp, kn, id); +} + +static void update_stats(int cpu_or_tid, u64 cgroup_id, int nr, s64 duration, + long ret) +{ + struct syscall_key key = { + .cpu_or_tid = cpu_or_tid, + .cgroup = cgroup_id, + .nr = nr, + }; + struct syscall_stats *stats; + + stats = bpf_map_lookup_elem(&syscall_stats_map, &key); + if (stats == NULL) { + struct syscall_stats zero = {}; + + bpf_map_update_elem(&syscall_stats_map, &key, &zero, BPF_NOEXIST); + stats = bpf_map_lookup_elem(&syscall_stats_map, &key); + if (stats == NULL) + return; + } + + __sync_fetch_and_add(&stats->count, 1); + if (ret < 0) + __sync_fetch_and_add(&stats->error, 1); + + if (duration > 0) { + __sync_fetch_and_add(&stats->total_time, duration); + __sync_fetch_and_add(&stats->squared_sum, duration * duration); + if (stats->max_time < duration) + stats->max_time = duration; + if (stats->min_time > duration || stats->min_time == 0) + stats->min_time = duration; + } + + return; +} + +SEC("tp_btf/sys_enter") +int sys_enter(u64 *ctx) +{ + int tid; + struct syscall_trace st; + + if (!enabled) + return 0; + + st.nr = ctx[1]; /* syscall number */ + st.unused = 0; + st.timestamp = bpf_ktime_get_ns(); + + tid = bpf_get_current_pid_tgid(); + bpf_map_update_elem(&syscall_trace_map, &tid, &st, BPF_ANY); + + return 0; +} + +static int do_exit(long ret) +{ + int tid; + int key = 0; + u64 cgroup = 0; + struct syscall_trace *st; + s64 delta; + + if (!enabled) + return 0; + + tid = bpf_get_current_pid_tgid(); + st = bpf_map_lookup_elem(&syscall_trace_map, &tid); + if (st == NULL) + return 0; + + if (aggr_mode == SYSCALL_AGGR_THREAD) + key = tid; + else if (aggr_mode == SYSCALL_AGGR_CGROUP) + cgroup = get_current_cgroup_id(); + else + key = bpf_get_smp_processor_id(); + + delta = bpf_ktime_get_ns() - st->timestamp; + update_stats(key, cgroup, st->nr, delta, ret); + + bpf_map_delete_elem(&syscall_trace_map, &tid); + return 0; +} + +SEC("tp_btf/sys_exit") +int sys_exit(u64 *ctx) +{ + long ret = ctx[1]; /* return value of the syscall */ + + return do_exit(ret); +} + +SEC("tp_btf/sched_process_exit") +int process_exit(u64 *ctx) +{ + return do_exit(0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/perf/util/bpf_skel/syscall_summary.h b/tools/perf/util/bpf_skel/syscall_summary.h new file mode 100644 index 000000000000..72ccccb45925 --- /dev/null +++ b/tools/perf/util/bpf_skel/syscall_summary.h @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Data structures shared between BPF and tools. */ +#ifndef UTIL_BPF_SKEL_SYSCALL_SUMMARY_H +#define UTIL_BPF_SKEL_SYSCALL_SUMMARY_H + +enum syscall_aggr_mode { + SYSCALL_AGGR_THREAD, + SYSCALL_AGGR_CPU, + SYSCALL_AGGR_CGROUP, +}; + +struct syscall_key { + u64 cgroup; + int cpu_or_tid; + int nr; +}; + +struct syscall_stats { + u64 total_time; + u64 squared_sum; + u64 max_time; + u64 min_time; + u32 count; + u32 error; +}; + +#endif /* UTIL_BPF_SKEL_SYSCALL_SUMMARY_H */ diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h index 7b81d3173917..a59ce912be18 100644 --- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h @@ -203,4 +203,13 @@ struct bpf_iter__kmem_cache { struct kmem_cache *s; } __attribute__((preserve_access_index)); +struct zone { + spinlock_t lock; +} __attribute__((preserve_access_index)); + +struct pglist_data { + struct zone node_zones[6]; /* value for all possible config */ + int nr_zones; +} __attribute__((preserve_access_index)); + #endif // __VMLINUX_H diff --git a/tools/perf/util/bpf_trace_augment.c b/tools/perf/util/bpf_trace_augment.c new file mode 100644 index 000000000000..9e706f0fa53d --- /dev/null +++ b/tools/perf/util/bpf_trace_augment.c @@ -0,0 +1,143 @@ +#include <bpf/libbpf.h> +#include <internal/xyarray.h> + +#include "util/debug.h" +#include "util/evlist.h" +#include "util/trace_augment.h" + +#include "bpf_skel/augmented_raw_syscalls.skel.h" + +static struct augmented_raw_syscalls_bpf *skel; +static struct evsel *bpf_output; + +int augmented_syscalls__prepare(void) +{ + struct bpf_program *prog; + char buf[128]; + int err; + + skel = augmented_raw_syscalls_bpf__open(); + if (!skel) { + pr_debug("Failed to open augmented syscalls BPF skeleton\n"); + return -errno; + } + + /* + * Disable attaching the BPF programs except for sys_enter and + * sys_exit that tail call into this as necessary. + */ + bpf_object__for_each_program(prog, skel->obj) { + if (prog != skel->progs.sys_enter && prog != skel->progs.sys_exit) + bpf_program__set_autoattach(prog, /*autoattach=*/false); + } + + err = augmented_raw_syscalls_bpf__load(skel); + if (err < 0) { + libbpf_strerror(err, buf, sizeof(buf)); + pr_debug("Failed to load augmented syscalls BPF skeleton: %s\n", buf); + return err; + } + + augmented_raw_syscalls_bpf__attach(skel); + return 0; +} + +int augmented_syscalls__create_bpf_output(struct evlist *evlist) +{ + int err = parse_event(evlist, "bpf-output/no-inherit=1,name=__augmented_syscalls__/"); + + if (err) { + pr_err("ERROR: Setup BPF output event failed: %d\n", err); + return err; + } + + bpf_output = evlist__last(evlist); + assert(evsel__name_is(bpf_output, "__augmented_syscalls__")); + + return 0; +} + +void augmented_syscalls__setup_bpf_output(void) +{ + struct perf_cpu cpu; + unsigned int i; + + if (bpf_output == NULL) + return; + + /* + * Set up the __augmented_syscalls__ BPF map to hold for each + * CPU the bpf-output event's file descriptor. + */ + perf_cpu_map__for_each_cpu(cpu, i, bpf_output->core.cpus) { + int mycpu = cpu.cpu; + + bpf_map__update_elem(skel->maps.__augmented_syscalls__, + &mycpu, sizeof(mycpu), + xyarray__entry(bpf_output->core.fd, + mycpu, 0), + sizeof(__u32), BPF_ANY); + } +} + +int augmented_syscalls__set_filter_pids(unsigned int nr, pid_t *pids) +{ + bool value = true; + int err = 0; + + if (skel == NULL) + return 0; + + for (size_t i = 0; i < nr; ++i) { + err = bpf_map__update_elem(skel->maps.pids_filtered, &pids[i], + sizeof(*pids), &value, sizeof(value), + BPF_ANY); + if (err) + break; + } + return err; +} + +int augmented_syscalls__get_map_fds(int *enter_fd, int *exit_fd, int *beauty_fd) +{ + if (skel == NULL) + return -1; + + *enter_fd = bpf_map__fd(skel->maps.syscalls_sys_enter); + *exit_fd = bpf_map__fd(skel->maps.syscalls_sys_exit); + *beauty_fd = bpf_map__fd(skel->maps.beauty_map_enter); + + if (*enter_fd < 0 || *exit_fd < 0 || *beauty_fd < 0) { + pr_err("Error: failed to get syscall or beauty map fd\n"); + return -1; + } + + return 0; +} + +struct bpf_program *augmented_syscalls__unaugmented(void) +{ + return skel->progs.syscall_unaugmented; +} + +struct bpf_program *augmented_syscalls__find_by_title(const char *name) +{ + struct bpf_program *pos; + const char *sec_name; + + if (skel->obj == NULL) + return NULL; + + bpf_object__for_each_program(pos, skel->obj) { + sec_name = bpf_program__section_name(pos); + if (sec_name && !strcmp(sec_name, name)) + return pos; + } + + return NULL; +} + +void augmented_syscalls__cleanup(void) +{ + augmented_raw_syscalls_bpf__destroy(skel); +} diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c index ab760e267d41..3712be067464 100644 --- a/tools/perf/util/branch.c +++ b/tools/perf/util/branch.c @@ -46,7 +46,7 @@ const char *branch_new_type_name(int new_type) "FAULT_DATA", "FAULT_INST", /* - * TODO: This switch should happen on 'session->header.env.arch' + * TODO: This switch should happen on 'perf_session__env(session)->arch' * instead, because an arm64 platform perf recording could be * opened for analysis on other platforms as well. */ diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index b80c12c74bbb..a1d4736497c4 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -25,7 +25,8 @@ struct branch_flags { u64 spec:2; u64 new_type:4; u64 priv:3; - u64 reserved:31; + u64 not_taken:1; + u64 reserved:30; }; }; }; @@ -65,6 +66,9 @@ static inline struct branch_entry *perf_sample__branch_entries(struct perf_sampl { u64 *entry = (u64 *)sample->branch_stack; + if (entry == NULL) + return NULL; + entry++; if (sample->no_hw_idx) return (struct branch_entry *)entry; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e763e8d99a43..fdb35133fde4 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -42,10 +42,20 @@ static bool no_buildid_cache; +static int mark_dso_hit_callback(struct callchain_cursor_node *node, void *data __maybe_unused) +{ + struct map *map = node->ms.map; + + if (map) + dso__set_hit(map__dso(map)); + + return 0; +} + int build_id__mark_dso_hit(const struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, - struct evsel *evsel __maybe_unused, + struct evsel *evsel, struct machine *machine) { struct addr_location al; @@ -63,31 +73,36 @@ int build_id__mark_dso_hit(const struct perf_tool *tool __maybe_unused, dso__set_hit(map__dso(al.map)); addr_location__exit(&al); + + sample__for_each_callchain_node(thread, evsel, sample, PERF_MAX_STACK_DEPTH, + /*symbols=*/false, mark_dso_hit_callback, /*data=*/NULL); + + thread__put(thread); return 0; } -int build_id__sprintf(const struct build_id *build_id, char *bf) +int build_id__snprintf(const struct build_id *build_id, char *bf, size_t bf_size) { - char *bid = bf; - const u8 *raw = build_id->data; - size_t i; + size_t offs = 0; - bf[0] = 0x0; - - for (i = 0; i < build_id->size; ++i) { - sprintf(bid, "%02x", *raw); - ++raw; - bid += 2; + if (build_id->size == 0) { + /* Ensure bf is always \0 terminated. */ + if (bf_size > 0) + bf[0] = '\0'; + return 0; } - return (bid - bf) + 1; + for (size_t i = 0; i < build_id->size && offs < bf_size; ++i) + offs += snprintf(bf + offs, bf_size - offs, "%02x", build_id->data[i]); + + return offs; } -int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id) +int sysfs__snprintf_build_id(const char *root_dir, char *sbuild_id, size_t sbuild_id_size) { char notes[PATH_MAX]; - struct build_id bid; + struct build_id bid = { .size = 0, }; int ret; if (!root_dir) @@ -99,19 +114,19 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id) if (ret < 0) return ret; - return build_id__sprintf(&bid, sbuild_id); + return build_id__snprintf(&bid, sbuild_id, sbuild_id_size); } -int filename__sprintf_build_id(const char *pathname, char *sbuild_id) +int filename__snprintf_build_id(const char *pathname, char *sbuild_id, size_t sbuild_id_size) { - struct build_id bid; + struct build_id bid = { .size = 0, }; int ret; ret = filename__read_build_id(pathname, &bid); if (ret < 0) return ret; - return build_id__sprintf(&bid, sbuild_id); + return build_id__snprintf(&bid, sbuild_id, sbuild_id_size); } /* asnprintf consolidates asprintf and snprintf */ @@ -212,9 +227,9 @@ static bool build_id_cache__valid_id(char *sbuild_id) return false; if (!strcmp(pathname, DSO__NAME_KALLSYMS)) - ret = sysfs__sprintf_build_id("/", real_sbuild_id); + ret = sysfs__snprintf_build_id("/", real_sbuild_id, sizeof(real_sbuild_id)); else if (pathname[0] == '/') - ret = filename__sprintf_build_id(pathname, real_sbuild_id); + ret = filename__snprintf_build_id(pathname, real_sbuild_id, sizeof(real_sbuild_id)); else ret = -EINVAL; /* Should we support other special DSO cache? */ if (ret >= 0) @@ -243,7 +258,7 @@ char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size, if (!dso__has_build_id(dso)) return NULL; - build_id__sprintf(dso__bid_const(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); linkname = build_id_cache__linkname(sbuild_id, NULL, 0); if (!linkname) return NULL; @@ -326,7 +341,7 @@ static int machine__write_buildid_table_cb(struct dso *dso, void *data) } in_kernel = dso__kernel(dso) || is_kernel_module(name, PERF_RECORD_MISC_CPUMODE_UNKNOWN); - return write_buildid(name, name_len, dso__bid(dso), args->machine->pid, + return write_buildid(name, name_len, &dso__id(dso)->build_id, args->machine->pid, in_kernel ? args->kmisc : args->umisc, args->fd); } @@ -769,7 +784,7 @@ static int build_id_cache__add_b(const struct build_id *bid, { char sbuild_id[SBUILD_ID_SIZE]; - build_id__sprintf(bid, sbuild_id); + build_id__snprintf(bid, sbuild_id, sizeof(sbuild_id)); return __build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms, is_vdso, proper_name, root_dir); @@ -841,7 +856,7 @@ static int filename__read_build_id_ns(const char *filename, static bool dso__build_id_mismatch(struct dso *dso, const char *name) { - struct build_id bid; + struct build_id bid = { .size = 0, }; bool ret = false; mutex_lock(dso__lock(dso)); @@ -864,7 +879,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine, char *allocated_name = NULL; int ret = 0; - if (!dso__has_build_id(dso)) + if (!dso__has_build_id(dso) || !dso__hit(dso)) return 0; if (dso__is_kcore(dso)) { @@ -951,7 +966,10 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) void build_id__init(struct build_id *bid, const u8 *data, size_t size) { - WARN_ON(size > BUILD_ID_SIZE); + if (size > BUILD_ID_SIZE) { + pr_debug("Truncating build_id size from %zd\n", size); + size = BUILD_ID_SIZE; + } memcpy(bid->data, data, size); bid->size = size; } diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index a212497bfdb0..47e621cebe1b 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -13,7 +13,7 @@ struct build_id { u8 data[BUILD_ID_SIZE]; - size_t size; + u8 size; }; struct dso; @@ -21,10 +21,10 @@ struct feat_fd; struct nsinfo; void build_id__init(struct build_id *bid, const u8 *data, size_t size); -int build_id__sprintf(const struct build_id *build_id, char *bf); +int build_id__snprintf(const struct build_id *build_id, char *bf, size_t bf_size); bool build_id__is_defined(const struct build_id *bid); -int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id); -int filename__sprintf_build_id(const char *pathname, char *sbuild_id); +int sysfs__snprintf_build_id(const char *root_dir, char *sbuild_id, size_t sbuild_id_size); +int filename__snprintf_build_id(const char *pathname, char *sbuild_id, size_t sbuild_id_size); char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, size_t size); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 0c7564747a14..f031cbbeeba8 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -30,7 +30,9 @@ #include "map.h" #include "callchain.h" #include "branch.h" +#include "record.h" #include "symbol.h" +#include "thread.h" #include "util.h" #include "../perf.h" @@ -169,7 +171,7 @@ static int get_stack_size(const char *str, unsigned long *_size) static int __parse_callchain_report_opt(const char *arg, bool allow_record_opt) { - char *tok; + char *tok, *arg_copy; char *endptr, *saveptr = NULL; bool minpcnt_set = false; bool record_opt_set = false; @@ -181,12 +183,17 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt) if (!arg) return 0; - while ((tok = strtok_r((char *)arg, ",", &saveptr)) != NULL) { + arg_copy = strdup(arg); + if (!arg_copy) + return -ENOMEM; + + tok = strtok_r(arg_copy, ",", &saveptr); + while (tok) { if (!strncmp(tok, "none", strlen(tok))) { callchain_param.mode = CHAIN_NONE; callchain_param.enabled = false; symbol_conf.use_callchain = false; - return 0; + goto out; } if (!parse_callchain_mode(tok) || @@ -213,30 +220,35 @@ try_numbers: unsigned long size = 0; if (get_stack_size(tok, &size) < 0) - return -1; + goto err_out; callchain_param.dump_size = size; try_stack_size = false; } else if (!minpcnt_set) { /* try to get the min percent */ callchain_param.min_percent = strtod(tok, &endptr); if (tok == endptr) - return -1; + goto err_out; minpcnt_set = true; } else { /* try print limit at last */ callchain_param.print_limit = strtoul(tok, &endptr, 0); if (tok == endptr) - return -1; + goto err_out; } next: - arg = NULL; + tok = strtok_r(NULL, ",", &saveptr); } if (callchain_register_param(&callchain_param) < 0) { pr_err("Can't register callchain params\n"); - return -1; + goto err_out; } +out: + free(arg_copy); return 0; +err_out: + free(arg_copy); + return -1; } int parse_callchain_report_opt(const char *arg) @@ -256,14 +268,12 @@ int parse_callchain_record(const char *arg, struct callchain_param *param) int ret = -1; /* We need buffer that we know we can write to. */ - buf = malloc(strlen(arg) + 1); + buf = strdup(arg); if (!buf) return -ENOMEM; - strcpy(buf, arg); - - tok = strtok_r((char *)buf, ",", &saveptr); - name = tok ? : (char *)buf; + tok = strtok_r(buf, ",", &saveptr); + name = tok ? : buf; do { /* Framepointer style */ @@ -275,9 +285,13 @@ int parse_callchain_record(const char *arg, struct callchain_param *param) if (tok) { unsigned long size; - size = strtoul(tok, &name, 0); - if (size < (unsigned) sysctl__max_stack()) - param->max_stack = size; + if (!strncmp(tok, "defer", sizeof("defer"))) { + param->defer = true; + } else { + size = strtoul(tok, &name, 0); + if (size < (unsigned) sysctl__max_stack()) + param->max_stack = size; + } } break; @@ -314,6 +328,50 @@ int parse_callchain_record(const char *arg, struct callchain_param *param) } while (0); free(buf); + + if (param->defer && param->record_mode != CALLCHAIN_FP) { + pr_err("callchain: deferred callchain only works with FP\n"); + return -EINVAL; + } + + return ret; +} + +static void callchain_debug(const struct callchain_param *callchain) +{ + static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" }; + + pr_debug("callchain: type %s\n", str[callchain->record_mode]); + + if (callchain->record_mode == CALLCHAIN_DWARF) + pr_debug("callchain: stack dump size %d\n", + callchain->dump_size); +} + +int record_opts__parse_callchain(struct record_opts *record, + struct callchain_param *callchain, + const char *arg, bool unset) +{ + int ret; + + callchain->enabled = !unset; + + /* --no-call-graph */ + if (unset) { + callchain->record_mode = CALLCHAIN_NONE; + pr_debug("callchain: disabled\n"); + return 0; + } + + ret = parse_callchain_record_opt(arg, callchain); + if (!ret) { + /* Enable data address sampling for DWARF unwind. */ + if (callchain->record_mode == CALLCHAIN_DWARF && + !record->record_data_mmap_set) + record->record_data_mmap = true; + callchain_debug(callchain); + } + return ret; } @@ -589,9 +647,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) return -ENOMEM; } call->ip = cursor_node->ip; - call->ms = cursor_node->ms; - call->ms.map = map__get(call->ms.map); - call->ms.maps = maps__get(call->ms.maps); + map_symbol__copy(&call->ms, &cursor_node->ms); call->srcline = cursor_node->srcline; if (cursor_node->branch) { @@ -1034,7 +1090,7 @@ merge_chain_branch(struct callchain_cursor *cursor, list_for_each_entry_safe(list, next_list, &src->val, list) { struct map_symbol ms = { - .maps = maps__get(list->ms.maps), + .thread = thread__get(list->ms.thread), .map = map__get(list->ms.map), }; callchain_cursor_append(cursor, list->ip, &ms, false, NULL, 0, 0, 0, list->srcline); @@ -1094,9 +1150,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, node->ip = ip; map_symbol__exit(&node->ms); - node->ms = *ms; - node->ms.maps = maps__get(ms->maps); - node->ms.map = map__get(ms->map); + map_symbol__copy(&node->ms, ms); node->branch = branch; node->nr_loop_iter = nr_loop_iter; node->iter_cycles = iter_cycles; @@ -1141,10 +1195,11 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { - struct machine *machine = node->ms.maps ? maps__machine(node->ms.maps) : NULL; + struct machine *machine = NULL; + + if (node->ms.thread) + machine = maps__machine(thread__maps(node->ms.thread)); - maps__put(al->maps); - al->maps = maps__get(node->ms.maps); map__put(al->map); al->map = map__get(node->ms.map); al->sym = node->ms.sym; @@ -1157,7 +1212,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * if (al->map == NULL) goto out; } - if (maps__equal(al->maps, machine__kernel_maps(machine))) { + if (maps__equal(thread__maps(al->thread), machine__kernel_maps(machine))) { if (machine__is_host(machine)) { al->cpumode = PERF_RECORD_MISC_KERNEL; al->level = 'k'; @@ -1564,7 +1619,7 @@ int callchain_node__make_parent_list(struct callchain_node *node) goto out; *new = *chain; new->has_children = false; - new->ms.map = map__get(new->ms.map); + map_symbol__copy(&new->ms, &chain->ms); list_add_tail(&new->list, &head); } parent = parent->parent; @@ -1673,7 +1728,7 @@ void callchain_cursor_reset(struct callchain_cursor *cursor) map_symbol__exit(&node->ms); } -void callchain_param_setup(u64 sample_type, const char *arch) +void callchain_param_setup(u64 sample_type, uint16_t e_machine) { if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { if ((sample_type & PERF_SAMPLE_REGS_USER) && @@ -1695,7 +1750,7 @@ void callchain_param_setup(u64 sample_type, const char *arch) * erroneous entries. Always skipping the LR and starting from the FP * can result in missing entries. */ - if (callchain_param.record_mode == CALLCHAIN_FP && !strcmp(arch, "arm64")) + if (callchain_param.record_mode == CALLCHAIN_FP && e_machine == EM_AARCH64) dwarf_callchain_users = true; } @@ -1832,3 +1887,42 @@ int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel, } return 0; } + +/* + * This function merges earlier samples (@sample_orig) waiting for deferred + * user callchains with the matching callchain record (@sample_callchain) + * which is delivered now. The @sample_orig->callchain should be released + * after use if ->deferred_callchain is set. + */ +int sample__merge_deferred_callchain(struct perf_sample *sample_orig, + struct perf_sample *sample_callchain) +{ + u64 nr_orig = sample_orig->callchain->nr - 1; + u64 nr_deferred = sample_callchain->callchain->nr; + struct ip_callchain *callchain; + + if (sample_orig->merged_callchain) { + /* Already merged. */ + return -EINVAL; + } + + if (sample_orig->callchain->nr < 2) { + sample_orig->deferred_callchain = false; + return -EINVAL; + } + + callchain = calloc(1 + nr_orig + nr_deferred, sizeof(u64)); + if (callchain == NULL) + return -ENOMEM; + + callchain->nr = nr_orig + nr_deferred; + /* copy original including PERF_CONTEXT_USER_DEFERRED (but the cookie) */ + memcpy(callchain->ips, sample_orig->callchain->ips, nr_orig * sizeof(u64)); + /* copy deferred user callchains */ + memcpy(&callchain->ips[nr_orig], sample_callchain->callchain->ips, + nr_deferred * sizeof(u64)); + + sample_orig->merged_callchain = true; + sample_orig->callchain = callchain; + return 0; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 86ed9e4d04f9..06d463ccc7a0 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -9,11 +9,13 @@ struct addr_location; struct evsel; +struct hist_entry; +struct hists; struct ip_callchain; struct map; struct perf_sample; +struct record_opts; struct thread; -struct hists; #define HELP_PAD "\t\t\t\t" @@ -98,6 +100,7 @@ extern bool dwarf_callchain_users; struct callchain_param { bool enabled; + bool defer; enum perf_call_graph_mode record_mode; u32 dump_size; enum chain_mode mode; @@ -236,14 +239,6 @@ struct callchain_cursor *get_tls_callchain_cursor(void); int callchain_cursor__copy(struct callchain_cursor *dst, struct callchain_cursor *src); -struct option; -struct hist_entry; - -int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); -int record_callchain_opt(const struct option *opt, const char *arg, int unset); - -struct record_opts; - int record_opts__parse_callchain(struct record_opts *record, struct callchain_param *callchain, const char *arg, bool unset); @@ -302,7 +297,7 @@ int callchain_branch_counts(struct callchain_root *root, u64 *branch_count, u64 *predicted_count, u64 *abort_count, u64 *cycles_count); -void callchain_param_setup(u64 sample_type, const char *arch); +void callchain_param_setup(u64 sample_type, uint16_t e_machine); bool callchain_cnode_matched(struct callchain_node *base_cnode, struct callchain_node *pair_cnode); @@ -317,4 +312,7 @@ int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel, struct perf_sample *sample, int max_stack, bool symbols, callchain_iter_fn cb, void *data); +int sample__merge_deferred_callchain(struct perf_sample *sample_orig, + struct perf_sample *sample_callchain); + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c index 69d9a2bcd40b..ac6d1d9a523d 100644 --- a/tools/perf/util/cap.c +++ b/tools/perf/util/cap.c @@ -7,7 +7,6 @@ #include "debug.h" #include <errno.h> #include <string.h> -#include <linux/capability.h> #include <sys/syscall.h> #include <unistd.h> @@ -29,8 +28,7 @@ bool perf_cap__capable(int cap, bool *used_root) header.version == _LINUX_CAPABILITY_VERSION_1) continue; - pr_debug2("capget syscall failed (%s - %d) fall back on root check\n", - strerror(errno), errno); + pr_debug2("capget syscall failed (%m) fall back on root check\n"); *used_root = true; return geteuid() == 0; } diff --git a/tools/perf/util/cap.h b/tools/perf/util/cap.h index 0c6a1ff55f07..c1b8ac033ccc 100644 --- a/tools/perf/util/cap.h +++ b/tools/perf/util/cap.h @@ -3,6 +3,7 @@ #define __PERF_CAP_H #include <stdbool.h> +#include <linux/capability.h> /* For older systems */ #ifndef CAP_SYSLOG @@ -13,6 +14,10 @@ #define CAP_PERFMON 38 #endif +#ifndef CAP_BPF +#define CAP_BPF 39 +#endif + /* Query if a capability is supported, used_root is set if the fallback root check was used. */ bool perf_cap__capable(int cap, bool *used_root); diff --git a/tools/perf/util/capstone.c b/tools/perf/util/capstone.c new file mode 100644 index 000000000000..25cf6e15ec27 --- /dev/null +++ b/tools/perf/util/capstone.c @@ -0,0 +1,571 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "capstone.h" +#include "annotate.h" +#include "addr_location.h" +#include "debug.h" +#include "disasm.h" +#include "dso.h" +#include "machine.h" +#include "map.h" +#include "namespaces.h" +#include "print_insn.h" +#include "symbol.h" +#include "thread.h" +#include <dlfcn.h> +#include <errno.h> +#include <fcntl.h> +#include <inttypes.h> +#include <string.h> + +#include <capstone/capstone.h> + +#ifdef LIBCAPSTONE_DLOPEN +static void *perf_cs_dll_handle(void) +{ + static bool dll_handle_init; + static void *dll_handle; + + if (!dll_handle_init) { + dll_handle_init = true; + dll_handle = dlopen("libcapstone.so", RTLD_LAZY); + if (!dll_handle) + pr_debug("dlopen failed for libcapstone.so\n"); + } + return dll_handle; +} +#endif + +static enum cs_err perf_cs_open(enum cs_arch arch, enum cs_mode mode, csh *handle) +{ +#ifndef LIBCAPSTONE_DLOPEN + return cs_open(arch, mode, handle); +#else + static bool fn_init; + static enum cs_err (*fn)(enum cs_arch arch, enum cs_mode mode, csh *handle); + + if (!fn_init) { + fn = dlsym(perf_cs_dll_handle(), "cs_open"); + if (!fn) + pr_debug("dlsym failed for cs_open\n"); + fn_init = true; + } + if (!fn) + return CS_ERR_HANDLE; + return fn(arch, mode, handle); +#endif +} + +static enum cs_err perf_cs_option(csh handle, enum cs_opt_type type, size_t value) +{ +#ifndef LIBCAPSTONE_DLOPEN + return cs_option(handle, type, value); +#else + static bool fn_init; + static enum cs_err (*fn)(csh handle, enum cs_opt_type type, size_t value); + + if (!fn_init) { + fn = dlsym(perf_cs_dll_handle(), "cs_option"); + if (!fn) + pr_debug("dlsym failed for cs_option\n"); + fn_init = true; + } + if (!fn) + return CS_ERR_HANDLE; + return fn(handle, type, value); +#endif +} + +static size_t perf_cs_disasm(csh handle, const uint8_t *code, size_t code_size, + uint64_t address, size_t count, struct cs_insn **insn) +{ +#ifndef LIBCAPSTONE_DLOPEN + return cs_disasm(handle, code, code_size, address, count, insn); +#else + static bool fn_init; + static enum cs_err (*fn)(csh handle, const uint8_t *code, size_t code_size, + uint64_t address, size_t count, struct cs_insn **insn); + + if (!fn_init) { + fn = dlsym(perf_cs_dll_handle(), "cs_disasm"); + if (!fn) + pr_debug("dlsym failed for cs_disasm\n"); + fn_init = true; + } + if (!fn) + return CS_ERR_HANDLE; + return fn(handle, code, code_size, address, count, insn); +#endif +} + +static void perf_cs_free(struct cs_insn *insn, size_t count) +{ +#ifndef LIBCAPSTONE_DLOPEN + cs_free(insn, count); +#else + static bool fn_init; + static void (*fn)(struct cs_insn *insn, size_t count); + + if (!fn_init) { + fn = dlsym(perf_cs_dll_handle(), "cs_free"); + if (!fn) + pr_debug("dlsym failed for cs_free\n"); + fn_init = true; + } + if (!fn) + return; + fn(insn, count); +#endif +} + +static enum cs_err perf_cs_close(csh *handle) +{ +#ifndef LIBCAPSTONE_DLOPEN + return cs_close(handle); +#else + static bool fn_init; + static enum cs_err (*fn)(csh *handle); + + if (!fn_init) { + fn = dlsym(perf_cs_dll_handle(), "cs_close"); + if (!fn) + pr_debug("dlsym failed for cs_close\n"); + fn_init = true; + } + if (!fn) + return CS_ERR_HANDLE; + return fn(handle); +#endif +} + +static int capstone_init(struct machine *machine, csh *cs_handle, bool is64, + bool disassembler_style) +{ + enum cs_arch arch; + enum cs_mode mode; + + if (machine__is(machine, "x86_64") && is64) { + arch = CS_ARCH_X86; + mode = CS_MODE_64; + } else if (machine__normalized_is(machine, "x86")) { + arch = CS_ARCH_X86; + mode = CS_MODE_32; + } else if (machine__normalized_is(machine, "arm64")) { + arch = CS_ARCH_ARM64; + mode = CS_MODE_ARM; + } else if (machine__normalized_is(machine, "arm")) { + arch = CS_ARCH_ARM; + mode = CS_MODE_ARM + CS_MODE_V8; + } else if (machine__normalized_is(machine, "s390")) { + arch = CS_ARCH_SYSZ; + mode = CS_MODE_BIG_ENDIAN; + } else { + return -1; + } + + if (perf_cs_open(arch, mode, cs_handle) != CS_ERR_OK) { + pr_warning_once("cs_open failed\n"); + return -1; + } + + if (machine__normalized_is(machine, "x86")) { + /* + * In case of using capstone_init while symbol__disassemble + * setting CS_OPT_SYNTAX_ATT depends if disassembler_style opts + * is set via annotation args + */ + if (disassembler_style) + perf_cs_option(*cs_handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT); + /* + * Resolving address operands to symbols is implemented + * on x86 by investigating instruction details. + */ + perf_cs_option(*cs_handle, CS_OPT_DETAIL, CS_OPT_ON); + } + + return 0; +} + +static size_t print_insn_x86(struct thread *thread, u8 cpumode, struct cs_insn *insn, + int print_opts, FILE *fp) +{ + struct addr_location al; + size_t printed = 0; + + if (insn->detail && insn->detail->x86.op_count == 1) { + struct cs_x86_op *op = &insn->detail->x86.operands[0]; + + addr_location__init(&al); + if (op->type == X86_OP_IMM && + thread__find_symbol(thread, cpumode, op->imm, &al)) { + printed += fprintf(fp, "%s ", insn[0].mnemonic); + printed += symbol__fprintf_symname_offs(al.sym, &al, fp); + if (print_opts & PRINT_INSN_IMM_HEX) + printed += fprintf(fp, " [%#" PRIx64 "]", op->imm); + addr_location__exit(&al); + return printed; + } + addr_location__exit(&al); + } + + printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str); + return printed; +} + + +ssize_t capstone__fprintf_insn_asm(struct machine *machine __maybe_unused, + struct thread *thread __maybe_unused, + u8 cpumode __maybe_unused, bool is64bit __maybe_unused, + const uint8_t *code __maybe_unused, + size_t code_size __maybe_unused, + uint64_t ip __maybe_unused, int *lenp __maybe_unused, + int print_opts __maybe_unused, FILE *fp __maybe_unused) +{ + size_t printed; + struct cs_insn *insn; + csh cs_handle; + size_t count; + int ret; + + /* TODO: Try to initiate capstone only once but need a proper place. */ + ret = capstone_init(machine, &cs_handle, is64bit, true); + if (ret < 0) + return ret; + + count = perf_cs_disasm(cs_handle, code, code_size, ip, 1, &insn); + if (count > 0) { + if (machine__normalized_is(machine, "x86")) + printed = print_insn_x86(thread, cpumode, &insn[0], print_opts, fp); + else + printed = fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str); + if (lenp) + *lenp = insn->size; + perf_cs_free(insn, count); + } else { + printed = -1; + } + + perf_cs_close(&cs_handle); + return printed; +} + +static void print_capstone_detail(struct cs_insn *insn, char *buf, size_t len, + struct annotate_args *args, u64 addr) +{ + int i; + struct map *map = args->ms->map; + struct symbol *sym; + + /* TODO: support more architectures */ + if (!arch__is_x86(args->arch)) + return; + + if (insn->detail == NULL) + return; + + for (i = 0; i < insn->detail->x86.op_count; i++) { + struct cs_x86_op *op = &insn->detail->x86.operands[i]; + u64 orig_addr; + + if (op->type != X86_OP_MEM) + continue; + + /* only print RIP-based global symbols for now */ + if (op->mem.base != X86_REG_RIP) + continue; + + /* get the target address */ + orig_addr = addr + insn->size + op->mem.disp; + addr = map__objdump_2mem(map, orig_addr); + + if (dso__kernel(map__dso(map))) { + /* + * The kernel maps can be split into sections, let's + * find the map first and the search the symbol. + */ + map = maps__find(map__kmaps(map), addr); + if (map == NULL) + continue; + } + + /* convert it to map-relative address for search */ + addr = map__map_ip(map, addr); + + sym = map__find_symbol(map, addr); + if (sym == NULL) + continue; + + if (addr == sym->start) { + scnprintf(buf, len, "\t# %"PRIx64" <%s>", + orig_addr, sym->name); + } else { + scnprintf(buf, len, "\t# %"PRIx64" <%s+%#"PRIx64">", + orig_addr, sym->name, addr - sym->start); + } + break; + } +} + +struct find_file_offset_data { + u64 ip; + u64 offset; +}; + +/* This will be called for each PHDR in an ELF binary */ +static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg) +{ + struct find_file_offset_data *data = arg; + + if (start <= data->ip && data->ip < start + len) { + data->offset = pgoff + data->ip - start; + return 1; + } + return 0; +} + +int symbol__disassemble_capstone(const char *filename __maybe_unused, + struct symbol *sym __maybe_unused, + struct annotate_args *args __maybe_unused) +{ + struct annotation *notes = symbol__annotation(sym); + struct map *map = args->ms->map; + struct dso *dso = map__dso(map); + u64 start = map__rip_2objdump(map, sym->start); + u64 offset; + int i, count, free_count; + bool is_64bit = false; + bool needs_cs_close = false; + /* Malloc-ed buffer containing instructions read from disk. */ + u8 *code_buf = NULL; + /* Pointer to code to be disassembled. */ + const u8 *buf; + u64 buf_len; + csh handle; + struct cs_insn *insn = NULL; + char disasm_buf[512]; + struct disasm_line *dl; + bool disassembler_style = false; + + if (args->options->objdump_path) + return -1; + + buf = dso__read_symbol(dso, filename, map, sym, + &code_buf, &buf_len, &is_64bit); + if (buf == NULL) + return errno; + + /* add the function address and name */ + scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", + start, sym->name); + + args->offset = -1; + args->line = disasm_buf; + args->line_nr = 0; + args->fileloc = NULL; + args->ms->sym = sym; + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + if (!args->options->disassembler_style || + !strcmp(args->options->disassembler_style, "att")) + disassembler_style = true; + + if (capstone_init(maps__machine(thread__maps(args->ms->thread)), &handle, is_64bit, + disassembler_style) < 0) + goto err; + + needs_cs_close = true; + + free_count = count = perf_cs_disasm(handle, buf, buf_len, start, buf_len, &insn); + for (i = 0, offset = 0; i < count; i++) { + int printed; + + printed = scnprintf(disasm_buf, sizeof(disasm_buf), + " %-7s %s", + insn[i].mnemonic, insn[i].op_str); + print_capstone_detail(&insn[i], disasm_buf + printed, + sizeof(disasm_buf) - printed, args, + start + offset); + + args->offset = offset; + args->line = disasm_buf; + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + offset += insn[i].size; + } + + /* It failed in the middle: probably due to unknown instructions */ + if (offset != buf_len) { + struct list_head *list = ¬es->src->source; + + /* Discard all lines and fallback to objdump */ + while (!list_empty(list)) { + dl = list_first_entry(list, struct disasm_line, al.node); + + list_del_init(&dl->al.node); + disasm_line__free(dl); + } + count = -1; + } + +out: + if (needs_cs_close) { + perf_cs_close(&handle); + if (free_count > 0) + perf_cs_free(insn, free_count); + } + free(code_buf); + return count < 0 ? count : 0; + +err: + if (needs_cs_close) { + struct disasm_line *tmp; + + /* + * It probably failed in the middle of the above loop. + * Release any resources it might add. + */ + list_for_each_entry_safe(dl, tmp, ¬es->src->source, al.node) { + list_del(&dl->al.node); + disasm_line__free(dl); + } + } + count = -1; + goto out; +} + +int symbol__disassemble_capstone_powerpc(const char *filename __maybe_unused, + struct symbol *sym __maybe_unused, + struct annotate_args *args __maybe_unused) +{ + struct annotation *notes = symbol__annotation(sym); + struct map *map = args->ms->map; + struct dso *dso = map__dso(map); + struct nscookie nsc; + u64 start = map__rip_2objdump(map, sym->start); + u64 end = map__rip_2objdump(map, sym->end); + u64 len = end - start; + u64 offset; + int i, fd, count; + bool is_64bit = false; + bool needs_cs_close = false; + u8 *buf = NULL; + struct find_file_offset_data data = { + .ip = start, + }; + csh handle; + char disasm_buf[512]; + struct disasm_line *dl; + u32 *line; + bool disassembler_style = false; + + if (args->options->objdump_path) + return -1; + + nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); + fd = open(filename, O_RDONLY); + nsinfo__mountns_exit(&nsc); + if (fd < 0) + return -1; + + if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, + &is_64bit) == 0) + goto err; + + if (!args->options->disassembler_style || + !strcmp(args->options->disassembler_style, "att")) + disassembler_style = true; + + if (capstone_init(maps__machine(thread__maps(args->ms->thread)), &handle, is_64bit, + disassembler_style) < 0) + goto err; + + needs_cs_close = true; + + buf = malloc(len); + if (buf == NULL) + goto err; + + count = pread(fd, buf, len, data.offset); + close(fd); + fd = -1; + + if ((u64)count != len) + goto err; + + line = (u32 *)buf; + + /* add the function address and name */ + scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", + start, sym->name); + + args->offset = -1; + args->line = disasm_buf; + args->line_nr = 0; + args->fileloc = NULL; + args->ms->sym = sym; + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + /* + * TODO: enable disassm for powerpc + * count = cs_disasm(handle, buf, len, start, len, &insn); + * + * For now, only binary code is saved in disassembled line + * to be used in "type" and "typeoff" sort keys. Each raw code + * is 32 bit instruction. So use "len/4" to get the number of + * entries. + */ + count = len/4; + + for (i = 0, offset = 0; i < count; i++) { + args->offset = offset; + sprintf(args->line, "%x", line[i]); + + dl = disasm_line__new(args); + if (dl == NULL) + break; + + annotation_line__add(&dl->al, ¬es->src->source); + + offset += 4; + } + + /* It failed in the middle */ + if (offset != len) { + struct list_head *list = ¬es->src->source; + + /* Discard all lines and fallback to objdump */ + while (!list_empty(list)) { + dl = list_first_entry(list, struct disasm_line, al.node); + + list_del_init(&dl->al.node); + disasm_line__free(dl); + } + count = -1; + } + +out: + if (needs_cs_close) + perf_cs_close(&handle); + free(buf); + return count < 0 ? count : 0; + +err: + if (fd >= 0) + close(fd); + count = -1; + goto out; +} diff --git a/tools/perf/util/capstone.h b/tools/perf/util/capstone.h new file mode 100644 index 000000000000..7c0baaa01a73 --- /dev/null +++ b/tools/perf/util/capstone.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_CAPSTONE_H +#define __PERF_CAPSTONE_H + +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <linux/compiler.h> +#include <linux/types.h> + +struct annotate_args; +struct machine; +struct symbol; +struct thread; + +#ifdef HAVE_LIBCAPSTONE_SUPPORT +ssize_t capstone__fprintf_insn_asm(struct machine *machine, struct thread *thread, u8 cpumode, + bool is64bit, const uint8_t *code, size_t code_size, + uint64_t ip, int *lenp, int print_opts, FILE *fp); +int symbol__disassemble_capstone(const char *filename, struct symbol *sym, + struct annotate_args *args); +int symbol__disassemble_capstone_powerpc(const char *filename, struct symbol *sym, + struct annotate_args *args); + +#else /* !HAVE_LIBCAPSTONE_SUPPORT */ +static inline ssize_t capstone__fprintf_insn_asm(struct machine *machine __maybe_unused, + struct thread *thread __maybe_unused, + u8 cpumode __maybe_unused, + bool is64bit __maybe_unused, + const uint8_t *code __maybe_unused, + size_t code_size __maybe_unused, + uint64_t ip __maybe_unused, + int *lenp __maybe_unused, + int print_opts __maybe_unused, + FILE *fp __maybe_unused) +{ + return -1; +} + +static inline int symbol__disassemble_capstone(const char *filename __maybe_unused, + struct symbol *sym __maybe_unused, + struct annotate_args *args __maybe_unused) +{ + return -1; +} + +static inline int symbol__disassemble_capstone_powerpc(const char *filename __maybe_unused, + struct symbol *sym __maybe_unused, + struct annotate_args *args __maybe_unused) +{ + return -1; +} + +#endif /* HAVE_LIBCAPSTONE_SUPPORT */ + +#endif /* __PERF_CAPSTONE_H */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index fbcc0626f9ce..1b5664d1481f 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -10,6 +10,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/statfs.h> +#include <errno.h> #include <fcntl.h> #include <stdlib.h> #include <string.h> @@ -413,11 +414,9 @@ static bool has_pattern_string(const char *str) return !!strpbrk(str, "{}[]()|*+?^$"); } -int evlist__expand_cgroup(struct evlist *evlist, const char *str, - struct rblist *metric_events, bool open_cgroup) +int evlist__expand_cgroup(struct evlist *evlist, const char *str, bool open_cgroup) { struct evlist *orig_list, *tmp_list; - struct evsel *pos, *evsel, *leader; struct rblist orig_metric_events; struct cgroup *cgrp = NULL; struct cgroup_name *cn; @@ -440,12 +439,8 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, evlist__splice_list_tail(orig_list, &evlist->core.entries); evlist->core.nr_entries = 0; - if (metric_events) { - orig_metric_events = *metric_events; - rblist__init(metric_events); - } else { - rblist__init(&orig_metric_events); - } + orig_metric_events = evlist->metric_events; + metricgroup__rblist_init(&evlist->metric_events); if (has_pattern_string(str)) prefix_len = match_cgroups(str); @@ -456,6 +451,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, goto out_err; list_for_each_entry(cn, &cgroup_list, list) { + struct evsel *pos; char *name; if (!cn->used) @@ -471,31 +467,45 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, if (cgrp == NULL) continue; - leader = NULL; + /* copy the list and set to the new cgroup. */ evlist__for_each_entry(orig_list, pos) { - evsel = evsel__clone(/*dest=*/NULL, pos); + struct evsel *evsel = evsel__clone(/*dest=*/NULL, pos); + if (evsel == NULL) goto out_err; + /* stash the copy during the copying. */ + pos->priv = evsel; cgroup__put(evsel->cgrp); evsel->cgrp = cgroup__get(cgrp); - if (evsel__is_group_leader(pos)) - leader = evsel; - evsel__set_leader(evsel, leader); - evlist__add(tmp_list, evsel); } + /* update leader information using stashed pointer to copy. */ + evlist__for_each_entry(orig_list, pos) { + struct evsel *evsel = pos->priv; + + if (evsel__leader(pos)) + evsel__set_leader(evsel, evsel__leader(pos)->priv); + + if (pos->metric_leader) + evsel->metric_leader = pos->metric_leader->priv; + + if (pos->first_wildcard_match) + evsel->first_wildcard_match = pos->first_wildcard_match->priv; + } + /* the stashed copy is no longer used. */ + evlist__for_each_entry(orig_list, pos) + pos->priv = NULL; + /* cgroup__new() has a refcount, release it here */ cgroup__put(cgrp); nr_cgroups++; - if (metric_events) { - if (metricgroup__copy_metric_events(tmp_list, cgrp, - metric_events, - &orig_metric_events) < 0) - goto out_err; - } + if (metricgroup__copy_metric_events(tmp_list, cgrp, + &evlist->metric_events, + &orig_metric_events) < 0) + goto out_err; evlist__splice_list_tail(evlist, &tmp_list->core.entries); tmp_list->core.nr_entries = 0; @@ -512,7 +522,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, out_err: evlist__delete(orig_list); evlist__delete(tmp_list); - rblist__exit(&orig_metric_events); + metricgroup__rblist_exit(&orig_metric_events); release_cgroup_list(); return ret; diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index de8882d6e8d3..7b1bda22878c 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -28,8 +28,7 @@ struct rblist; struct cgroup *cgroup__new(const char *name, bool do_open); struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name); -int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups, - struct rblist *metric_events, bool open_cgroup); +int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups, bool open_cgroup); void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup); diff --git a/tools/perf/util/clockid.h b/tools/perf/util/clockid.h index 9b49b4711c76..33dbd8673c1c 100644 --- a/tools/perf/util/clockid.h +++ b/tools/perf/util/clockid.h @@ -1,8 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ - #ifndef __PERF_CLOCKID_H #define __PERF_CLOCKID_H +#include <time.h> + struct option; int parse_clockid(const struct option *opt, const char *str, int unset); diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 9a7248dbe2d7..0319546decca 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -30,11 +30,6 @@ extern int perf_use_color_default; -/* - * Use this instead of perf_default_config if you need the value of color.ui. - */ -int perf_color_default_config(const char *var, const char *value, void *cb); - int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty); int color_vsnprintf(char *bf, size_t size, const char *color, const char *fmt, va_list args); diff --git a/tools/perf/util/color_config.c b/tools/perf/util/color_config.c index dc09ba7cb31e..301031ddc025 100644 --- a/tools/perf/util/color_config.c +++ b/tools/perf/util/color_config.c @@ -35,14 +35,3 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) } return 0; } - -int perf_color_default_config(const char *var, const char *value, - void *cb __maybe_unused) -{ - if (!strcmp(var, "color.ui")) { - perf_use_color_default = perf_config_colorbool(var, value, -1); - return 0; - } - - return 0; -} diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 49b79cf0c5cc..9880247a2c33 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -5,6 +5,8 @@ #include <internal/rc_check.h> #include <linux/refcount.h> #include <linux/zalloc.h> +#include <tools/libc_compat.h> // reallocarray + #include "rwsem.h" DECLARE_RC_STRUCT(comm_str) { @@ -22,6 +24,7 @@ static struct comm_strs { static void comm_strs__remove_if_last(struct comm_str *cs); static void comm_strs__init(void) + NO_THREAD_SAFETY_ANALYSIS /* Inherently single threaded due to pthread_once. */ { init_rwsem(&_comm_strs.lock); _comm_strs.capacity = 16; @@ -117,6 +120,7 @@ static void comm_strs__remove_if_last(struct comm_str *cs) } static struct comm_str *__comm_strs__find(struct comm_strs *comm_strs, const char *str) + SHARED_LOCKS_REQUIRED(comm_strs->lock) { struct comm_str **result; diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h index b29109cd3609..6cfecfca16f2 100644 --- a/tools/perf/util/compress.h +++ b/tools/perf/util/compress.h @@ -4,7 +4,9 @@ #include <stdbool.h> #include <stddef.h> +#include <stdio.h> #include <sys/types.h> +#include <linux/compiler.h> #ifdef HAVE_ZSTD_SUPPORT #include <zstd.h> #endif @@ -15,8 +17,26 @@ bool gzip_is_compressed(const char *input); #endif #ifdef HAVE_LZMA_SUPPORT +int lzma_decompress_stream_to_file(FILE *input, int output_fd); int lzma_decompress_to_file(const char *input, int output_fd); bool lzma_is_compressed(const char *input); +#else +static inline +int lzma_decompress_stream_to_file(FILE *input __maybe_unused, + int output_fd __maybe_unused) +{ + return -1; +} +static inline +int lzma_decompress_to_file(const char *input __maybe_unused, + int output_fd __maybe_unused) +{ + return -1; +} +static inline int lzma_is_compressed(const char *input __maybe_unused) +{ + return false; +} #endif struct zstd_data { diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 2d07c9257a1a..087002fb1b9b 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -19,7 +19,7 @@ #include "util/hist.h" /* perf_hist_config */ #include "util/stat.h" /* perf_stat__set_big_num */ #include "util/evsel.h" /* evsel__hw_names, evsel__use_bpf_counters */ -#include "util/srcline.h" /* addr2line_timeout_ms */ +#include "srcline.h" #include "build-id.h" #include "debug.h" #include "config.h" @@ -37,6 +37,8 @@ #define METRIC_ONLY_LEN 20 +static struct stats walltime_nsecs_stats; + struct perf_stat_config stat_config = { .aggr_mode = AGGR_GLOBAL, .aggr_level = MAX_CACHE_LVL + 1, @@ -45,7 +47,6 @@ struct perf_stat_config stat_config = { .run_count = 1, .metric_only_len = METRIC_ONLY_LEN, .walltime_nsecs_stats = &walltime_nsecs_stats, - .ru_stats = &ru_stats, .big_num = true, .ctl_fd = -1, .ctl_fd_ack = -1, @@ -457,7 +458,10 @@ static int perf_default_core_config(const char *var, const char *value) proc_map_timeout = strtoul(value, NULL, 10); if (!strcmp(var, "core.addr2line-timeout")) - addr2line_timeout_ms = strtoul(value, NULL, 10); + symbol_conf.addr2line_timeout_ms = strtoul(value, NULL, 10); + + if (!strcmp(var, "core.addr2line-disable-warn")) + symbol_conf.addr2line_disable_warn = perf_config_bool(var, value); /* Add other config variables here. */ return 0; @@ -518,6 +522,9 @@ int perf_default_config(const char *var, const char *value, if (strstarts(var, "stat.")) return perf_stat_config(var, value); + if (strstarts(var, "addr2line.")) + return addr2line_configure(var, value, dummy); + /* Add other config variables here. */ return 0; } @@ -856,12 +863,6 @@ void perf_config__exit(void) config_set = NULL; } -void perf_config__refresh(void) -{ - perf_config__exit(); - perf_config__init(); -} - static void perf_config_item__delete(struct perf_config_item *item) { zfree(&item->name); diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index a727c95cb119..987b47cf54c3 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -49,7 +49,6 @@ 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__exit(void); -void perf_config__refresh(void); int perf_config__set_variable(const char *var, const char *value); /** diff --git a/tools/perf/util/cpu-set-sched.h b/tools/perf/util/cpu-set-sched.h deleted file mode 100644 index 8cf4e40d322a..000000000000 --- a/tools/perf/util/cpu-set-sched.h +++ /dev/null @@ -1,50 +0,0 @@ -// SPDX-License-Identifier: LGPL-2.1 -// Definitions taken from glibc for use with older systems, same licensing. -#ifndef _CPU_SET_SCHED_PERF_H -#define _CPU_SET_SCHED_PERF_H - -#include <features.h> -#include <sched.h> - -#ifndef CPU_EQUAL -#ifndef __CPU_EQUAL_S -#if __GNUC_PREREQ (2, 91) -# define __CPU_EQUAL_S(setsize, cpusetp1, cpusetp2) \ - (__builtin_memcmp (cpusetp1, cpusetp2, setsize) == 0) -#else -# define __CPU_EQUAL_S(setsize, cpusetp1, cpusetp2) \ - (__extension__ \ - ({ const __cpu_mask *__arr1 = (cpusetp1)->__bits; \ - const __cpu_mask *__arr2 = (cpusetp2)->__bits; \ - size_t __imax = (setsize) / sizeof (__cpu_mask); \ - size_t __i; \ - for (__i = 0; __i < __imax; ++__i) \ - if (__arr1[__i] != __arr2[__i]) \ - break; \ - __i == __imax; })) -#endif -#endif // __CPU_EQUAL_S - -#define CPU_EQUAL(cpusetp1, cpusetp2) \ - __CPU_EQUAL_S (sizeof (cpu_set_t), cpusetp1, cpusetp2) -#endif // CPU_EQUAL - -#ifndef CPU_OR -#ifndef __CPU_OP_S -#define __CPU_OP_S(setsize, destset, srcset1, srcset2, op) \ - (__extension__ \ - ({ cpu_set_t *__dest = (destset); \ - const __cpu_mask *__arr1 = (srcset1)->__bits; \ - const __cpu_mask *__arr2 = (srcset2)->__bits; \ - size_t __imax = (setsize) / sizeof (__cpu_mask); \ - size_t __i; \ - for (__i = 0; __i < __imax; ++__i) \ - ((__cpu_mask *) __dest->__bits)[__i] = __arr1[__i] op __arr2[__i]; \ - __dest; })) -#endif // __CPU_OP_S - -#define CPU_OR(destset, srcset1, srcset2) \ - __CPU_OP_S (sizeof (cpu_set_t), destset, srcset1, srcset2, |) -#endif // CPU_OR - -#endif // _CPU_SET_SCHED_PERF_H diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 5c329ad614e9..11922e1ded84 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -67,19 +67,23 @@ static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_m struct perf_cpu_map *map; map = perf_cpu_map__empty_new(data->cpus_data.nr); - if (map) { - unsigned i; - - for (i = 0; i < data->cpus_data.nr; i++) { - /* - * Special treatment for -1, which is not real cpu number, - * and we need to use (int) -1 to initialize map[i], - * otherwise it would become 65535. - */ - if (data->cpus_data.cpu[i] == (u16) -1) - RC_CHK_ACCESS(map)->map[i].cpu = -1; - else - RC_CHK_ACCESS(map)->map[i].cpu = (int) data->cpus_data.cpu[i]; + if (!map) + return NULL; + + for (unsigned int i = 0; i < data->cpus_data.nr; i++) { + /* + * Special treatment for -1, which is not real cpu number, + * and we need to use (int) -1 to initialize map[i], + * otherwise it would become 65535. + */ + if (data->cpus_data.cpu[i] == (u16) -1) { + RC_CHK_ACCESS(map)->map[i].cpu = -1; + } else if (data->cpus_data.cpu[i] < INT16_MAX) { + RC_CHK_ACCESS(map)->map[i].cpu = (int16_t) data->cpus_data.cpu[i]; + } else { + pr_err("Invalid cpumap entry %u\n", data->cpus_data.cpu[i]); + perf_cpu_map__put(map); + return NULL; } } @@ -106,8 +110,15 @@ static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_ int cpu; perf_record_cpu_map_data__read_one_mask(data, i, local_copy); - for_each_set_bit(cpu, local_copy, 64) - RC_CHK_ACCESS(map)->map[j++].cpu = cpu + cpus_per_i; + for_each_set_bit(cpu, local_copy, 64) { + if (cpu + cpus_per_i < INT16_MAX) { + RC_CHK_ACCESS(map)->map[j++].cpu = cpu + cpus_per_i; + } else { + pr_err("Invalid cpumap entry %d\n", cpu + cpus_per_i); + perf_cpu_map__put(map); + return NULL; + } + } } return map; @@ -127,8 +138,15 @@ static struct perf_cpu_map *cpu_map__from_range(const struct perf_record_cpu_map RC_CHK_ACCESS(map)->map[i++].cpu = -1; for (int cpu = data->range_cpu_data.start_cpu; cpu <= data->range_cpu_data.end_cpu; - i++, cpu++) - RC_CHK_ACCESS(map)->map[i].cpu = cpu; + i++, cpu++) { + if (cpu < INT16_MAX) { + RC_CHK_ACCESS(map)->map[i].cpu = cpu; + } else { + pr_err("Invalid cpumap entry %d\n", cpu); + perf_cpu_map__put(map); + return NULL; + } + } return map; } @@ -236,7 +254,7 @@ struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, aggr_cpu_id_get_t get_id, void *data, bool needs_sort) { - int idx; + unsigned int idx; struct perf_cpu cpu; struct cpu_aggr_map *c = cpu_aggr_map__empty_new(perf_cpu_map__nr(cpus)); @@ -262,7 +280,7 @@ struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, } } /* Trim. */ - if (c->nr != perf_cpu_map__nr(cpus)) { + if (c->nr != (int)perf_cpu_map__nr(cpus)) { struct cpu_aggr_map *trimmed_c = realloc(c, sizeof(struct cpu_aggr_map) + sizeof(struct aggr_cpu_id) * c->nr); @@ -427,7 +445,7 @@ static void set_max_cpu_num(void) { const char *mnt; char path[PATH_MAX]; - int ret = -1; + int max, ret = -1; /* set up default */ max_cpu_num.cpu = 4096; @@ -444,10 +462,12 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_cpu_num.cpu); + ret = get_max_num(path, &max); if (ret) goto out; + max_cpu_num.cpu = max; + /* get the highest present cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt); if (ret >= PATH_MAX) { @@ -455,8 +475,14 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_present_cpu_num.cpu); + ret = get_max_num(path, &max); + if (!ret && max > INT16_MAX) { + pr_err("Read out of bounds max cpus of %d\n", max); + ret = -1; + } + if (!ret) + max_present_cpu_num.cpu = (int16_t)max; out: if (ret) pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu); @@ -605,9 +631,9 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) #define COMMA first ? "" : "," - for (i = 0; i < perf_cpu_map__nr(map) + 1; i++) { - struct perf_cpu cpu = { .cpu = INT_MAX }; - bool last = i == perf_cpu_map__nr(map); + for (i = 0; i < (int)perf_cpu_map__nr(map) + 1; i++) { + struct perf_cpu cpu = { .cpu = INT16_MAX }; + bool last = i == (int)perf_cpu_map__nr(map); if (!last) cpu = perf_cpu_map__cpu(map, i); @@ -653,21 +679,26 @@ static char hex_char(unsigned char val) size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) { - int idx; + unsigned int idx; char *ptr = buf; unsigned char *bitmap; struct perf_cpu c, last_cpu = perf_cpu_map__max(map); - if (buf == NULL) + if (buf == NULL || size == 0) return 0; + if (last_cpu.cpu < 0) { + buf[0] = '\0'; + return 0; + } + bitmap = zalloc(last_cpu.cpu / 8 + 1); if (bitmap == NULL) { buf[0] = '\0'; return 0; } - perf_cpu_map__for_each_cpu(c, idx, map) + perf_cpu_map__for_each_cpu_skip_any(c, idx, map) bitmap[c.cpu / 8] |= 1 << (c.cpu % 8); for (int cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) { @@ -696,7 +727,7 @@ struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ if (!online) online = perf_cpu_map__new_online_cpus(); /* from /sys/devices/system/cpu/online */ - return online; + return perf_cpu_map__get(online); } bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b) diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index 8bbeb2dc76fd..e0091804fe98 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -191,7 +191,7 @@ bool cpu_topology__core_wide(const struct cpu_topology *topology, const char *core_cpu_list = topology->core_cpus_list[i]; struct perf_cpu_map *core_cpus = perf_cpu_map__new(core_cpu_list); struct perf_cpu cpu; - int idx; + unsigned int idx; bool has_first, first = true; perf_cpu_map__for_each_cpu(cpu, idx, core_cpus) { diff --git a/tools/perf/util/cs-etm-decoder/Build b/tools/perf/util/cs-etm-decoder/Build index 056d665f7f88..27550db2aa4c 100644 --- a/tools/perf/util/cs-etm-decoder/Build +++ b/tools/perf/util/cs-etm-decoder/Build @@ -1 +1 @@ -perf-util-$(CONFIG_AUXTRACE) += cs-etm-decoder.o +perf-util-y += cs-etm-decoder.o diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index b85a8837bddc..dee3020ceaa9 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -22,12 +22,15 @@ /* use raw logging */ #ifdef CS_DEBUG_RAW #define CS_LOG_RAW_FRAMES +#define CS_PKT_MON 1 #ifdef CS_RAW_PACKED #define CS_RAW_DEBUG_FLAGS (OCSD_DFRMTR_UNPACKED_RAW_OUT | \ OCSD_DFRMTR_PACKED_RAW_OUT) #else #define CS_RAW_DEBUG_FLAGS (OCSD_DFRMTR_UNPACKED_RAW_OUT) #endif +#else +#define CS_PKT_MON 0 #endif /* @@ -237,46 +240,24 @@ cs_etm_decoder__init_def_logger_printing(struct cs_etm_decoder_params *d_params, (void *)decoder, cs_etm_decoder__print_str_cb); if (ret != 0) - ret = -1; - - return 0; -} + return -1; #ifdef CS_LOG_RAW_FRAMES -static void -cs_etm_decoder__init_raw_frame_logging(struct cs_etm_decoder_params *d_params, - struct cs_etm_decoder *decoder) -{ - /* Only log these during a --dump operation */ - if (d_params->operation == CS_ETM_OPERATION_PRINT) { - /* set up a library default logger to process the - * raw frame printer we add later - */ - ocsd_def_errlog_init(OCSD_ERR_SEV_ERROR, 1); - - /* no stdout / err / file output */ - ocsd_def_errlog_config_output(C_API_MSGLOGOUT_FLG_NONE, NULL); - - /* set the string CB for the default logger, - * passes strings to perf print logger. - */ - ocsd_def_errlog_set_strprint_cb(decoder->dcd_tree, - (void *)decoder, - cs_etm_decoder__print_str_cb); - + /* + * Only log raw frames if --dump operation and hardware is actually + * generating formatted CoreSight trace frames + */ + if ((d_params->operation == CS_ETM_OPERATION_PRINT) && + (d_params->formatted == true)) { /* use the built in library printer for the raw frames */ - ocsd_dt_set_raw_frame_printer(decoder->dcd_tree, - CS_RAW_DEBUG_FLAGS); + ret = ocsd_dt_set_raw_frame_printer(decoder->dcd_tree, + CS_RAW_DEBUG_FLAGS); + if (ret != 0) + return -1; } -} -#else -static void -cs_etm_decoder__init_raw_frame_logging( - struct cs_etm_decoder_params *d_params __maybe_unused, - struct cs_etm_decoder *decoder __maybe_unused) -{ -} #endif + return 0; +} static ocsd_datapath_resp_t cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq, @@ -549,7 +530,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq, /* * Process the PE_CONTEXT packets if we have a valid contextID or VMID. * If the kernel is running at EL2, the PID is traced in CONTEXTIDR_EL2 - * as VMID, Bit ETM_OPT_CTXTID2 is set in this case. + * as VMID, Format attribute 'contextid2' is set in this case. */ switch (cs_etm__get_pid_fmt(etmq)) { case CS_ETM_PIDFMT_CTXTID: @@ -588,6 +569,7 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( const ocsd_generic_trace_elem *elem) { ocsd_datapath_resp_t resp = OCSD_RESP_CONT; + ocsd_gen_trc_elem_t type; struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context; struct cs_etm_queue *etmq = decoder->data; struct cs_etm_packet_queue *packet_queue; @@ -597,52 +579,29 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( if (!packet_queue) return OCSD_RESP_FATAL_SYS_ERR; - switch (elem->elem_type) { - case OCSD_GEN_TRC_ELEM_UNKNOWN: - break; - case OCSD_GEN_TRC_ELEM_EO_TRACE: - case OCSD_GEN_TRC_ELEM_NO_SYNC: - case OCSD_GEN_TRC_ELEM_TRACE_ON: + type = elem->elem_type; + + if (type == OCSD_GEN_TRC_ELEM_EO_TRACE || + type == OCSD_GEN_TRC_ELEM_NO_SYNC || + type == OCSD_GEN_TRC_ELEM_TRACE_ON) resp = cs_etm_decoder__buffer_discontinuity(etmq, packet_queue, trace_chan_id); - break; - case OCSD_GEN_TRC_ELEM_INSTR_RANGE: + else if (type == OCSD_GEN_TRC_ELEM_INSTR_RANGE) resp = cs_etm_decoder__buffer_range(etmq, packet_queue, elem, trace_chan_id); - break; - case OCSD_GEN_TRC_ELEM_EXCEPTION: + else if (type == OCSD_GEN_TRC_ELEM_EXCEPTION) resp = cs_etm_decoder__buffer_exception(etmq, packet_queue, elem, trace_chan_id); - break; - case OCSD_GEN_TRC_ELEM_EXCEPTION_RET: + else if (type == OCSD_GEN_TRC_ELEM_EXCEPTION_RET) resp = cs_etm_decoder__buffer_exception_ret(etmq, packet_queue, trace_chan_id); - break; - case OCSD_GEN_TRC_ELEM_TIMESTAMP: + else if (type == OCSD_GEN_TRC_ELEM_TIMESTAMP) resp = cs_etm_decoder__do_hard_timestamp(etmq, elem, trace_chan_id, indx); - break; - case OCSD_GEN_TRC_ELEM_PE_CONTEXT: + else if (type == OCSD_GEN_TRC_ELEM_PE_CONTEXT) resp = cs_etm_decoder__set_tid(etmq, packet_queue, elem, trace_chan_id); - break; - /* Unused packet types */ - case OCSD_GEN_TRC_ELEM_I_RANGE_NOPATH: - case OCSD_GEN_TRC_ELEM_ADDR_NACC: - case OCSD_GEN_TRC_ELEM_CYCLE_COUNT: - case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN: - case OCSD_GEN_TRC_ELEM_EVENT: - case OCSD_GEN_TRC_ELEM_SWTRACE: - case OCSD_GEN_TRC_ELEM_CUSTOM: - case OCSD_GEN_TRC_ELEM_SYNC_MARKER: - case OCSD_GEN_TRC_ELEM_MEMTRANS: -#if (OCSD_VER_NUM >= 0x010400) - case OCSD_GEN_TRC_ELEM_INSTRUMENTATION: -#endif - default: - break; - } return resp; } @@ -708,7 +667,7 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params, trace_config, &csid)) return -1; - if (ocsd_dt_set_pkt_protocol_printer(decoder->dcd_tree, csid, 0)) + if (ocsd_dt_set_pkt_protocol_printer(decoder->dcd_tree, csid, CS_PKT_MON)) return -1; return 0; @@ -760,9 +719,6 @@ cs_etm_decoder__new(int decoders, struct cs_etm_decoder_params *d_params, if (ret != 0) goto err_free_decoder; - /* init raw frame logging if required */ - cs_etm_decoder__init_raw_frame_logging(d_params, decoder); - for (i = 0; i < decoders; i++) { ret = cs_etm_decoder__create_etm_decoder(d_params, &t_params[i], diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 0bf9e5c27b59..8a639d2e51a4 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -6,7 +6,6 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ -#include <linux/kernel.h> #include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/coresight-pmu.h> @@ -195,7 +194,7 @@ int cs_etm__get_cpu(struct cs_etm_queue *etmq, u8 trace_chan_id, int *cpu) * CS_ETM_PIDFMT_CTXTID2: CONTEXTIDR_EL2 is traced. * CS_ETM_PIDFMT_NONE: No context IDs * - * It's possible that the two bits ETM_OPT_CTXTID and ETM_OPT_CTXTID2 + * It's possible that the two format attributes 'contextid1' and 'contextid2' * are enabled at the same time when the session runs on an EL2 kernel. * This means the CONTEXTIDR_EL1 and CONTEXTIDR_EL2 both will be * recorded in the trace data, the tool will selectively use @@ -211,15 +210,15 @@ static enum cs_etm_pid_fmt cs_etm__init_pid_fmt(u64 *metadata) if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) { val = metadata[CS_ETM_ETMCR]; /* CONTEXTIDR is traced */ - if (val & BIT(ETM_OPT_CTXTID)) + if (val & ETMCR_CTXTID) return CS_ETM_PIDFMT_CTXTID; } else { val = metadata[CS_ETMV4_TRCCONFIGR]; /* CONTEXTIDR_EL2 is traced */ - if (val & (BIT(ETM4_CFG_BIT_VMID) | BIT(ETM4_CFG_BIT_VMID_OPT))) + if (val & (TRCCONFIGR_VMID | TRCCONFIGR_VMIDOPT)) return CS_ETM_PIDFMT_CTXTID2; /* CONTEXTIDR_EL1 is traced */ - else if (val & BIT(ETM4_CFG_BIT_CTXTID)) + else if (val & TRCCONFIGR_CID) return CS_ETM_PIDFMT_CTXTID; } @@ -506,20 +505,27 @@ static int cs_etm__process_aux_output_hw_id(struct perf_session *session, evsel = evlist__event2evsel(session->evlist, event); if (!evsel) return -EINVAL; + perf_sample__init(&sample, /*all=*/false); err = evsel__parse_sample(evsel, event, &sample); if (err) - return err; + goto out; cpu = sample.cpu; if (cpu == -1) { /* no CPU in the sample - possibly recorded with an old version of perf */ pr_err("CS_ETM: no CPU AUX_OUTPUT_HW_ID sample. Use compatible perf to record."); - return -EINVAL; + err = -EINVAL; + goto out; } - if (FIELD_GET(CS_AUX_HW_ID_MINOR_VERSION_MASK, hw_id) == 0) - return cs_etm__process_trace_id_v0(etm, cpu, hw_id); + if (FIELD_GET(CS_AUX_HW_ID_MINOR_VERSION_MASK, hw_id) == 0) { + err = cs_etm__process_trace_id_v0(etm, cpu, hw_id); + goto out; + } - return cs_etm__process_trace_id_v0_1(etm, cpu, hw_id); + err = cs_etm__process_trace_id_v0_1(etm, cpu, hw_id); +out: + perf_sample__exit(&sample); + return err; } void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, @@ -770,7 +776,7 @@ static void cs_etm__packet_dump(const char *pkt_string, void *data) char queue_nr[64]; if (verbose) - snprintf(queue_nr, sizeof(queue_nr), "Qnr:%d; ", etmq->queue_nr); + snprintf(queue_nr, sizeof(queue_nr), "Qnr:%u; ", etmq->queue_nr); else queue_nr[0] = '\0'; @@ -1560,8 +1566,9 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, int ret = 0; struct cs_etm_auxtrace *etm = etmq->etm; union perf_event *event = tidq->event_buf; - struct perf_sample sample = {.ip = 0,}; + struct perf_sample sample; + perf_sample__init(&sample, /*all=*/true); event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = cs_etm__cpu_mode(etmq, addr, tidq->el); event->sample.header.size = sizeof(struct perf_event_header); @@ -1598,6 +1605,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, "CS ETM Trace: failed to deliver instruction event, error %d\n", ret); + perf_sample__exit(&sample); return ret; } @@ -1717,10 +1725,7 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, attr.read_format = evsel->core.attr.read_format; /* create new id val to be a fixed offset from evsel id */ - id = evsel->core.id[0] + 1000000000; - - if (!id) - id = 1; + id = auxtrace_synth_id_range_start(evsel); if (etm->synth_opts.branches) { attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; @@ -2909,29 +2914,21 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, return 0; } -static int cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm) +static void cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm) { - struct evsel *evsel; - struct evlist *evlist = etm->session->evlist; + /* Take first ETM as all options will be the same for all ETMs */ + u64 *metadata = etm->metadata[0]; /* Override timeless mode with user input from --itrace=Z */ if (etm->synth_opts.timeless_decoding) { etm->timeless_decoding = true; - return 0; + return; } - /* - * Find the cs_etm evsel and look at what its timestamp setting was - */ - evlist__for_each_entry(evlist, evsel) - if (cs_etm__evsel_is_auxtrace(etm->session, evsel)) { - etm->timeless_decoding = - !(evsel->core.attr.config & BIT(ETM_OPT_TS)); - return 0; - } - - pr_err("CS ETM: Couldn't find ETM evsel\n"); - return -EINVAL; + if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) + etm->timeless_decoding = !(metadata[CS_ETM_ETMCR] & ETMCR_TIMESTAMP_EN); + else + etm->timeless_decoding = !(metadata[CS_ETMV4_TRCCONFIGR] & TRCCONFIGR_TS); } /* @@ -3080,7 +3077,7 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o if (aux_offset >= auxtrace_event->offset && aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) { - struct cs_etm_queue *etmq = etm->queues.queue_array[auxtrace_event->idx].priv; + struct cs_etm_queue *etmq = cs_etm__get_queue(etm, auxtrace_event->cpu); /* * If this AUX event was inside this buffer somewhere, create a new auxtrace event @@ -3089,6 +3086,7 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o auxtrace_fragment.auxtrace = *auxtrace_event; auxtrace_fragment.auxtrace.size = aux_size; auxtrace_fragment.auxtrace.offset = aux_offset; + auxtrace_fragment.auxtrace.idx = etmq->queue_nr; file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size; pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64 @@ -3151,9 +3149,10 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf evsel = evlist__event2evsel(session->evlist, event); if (!evsel) return -EINVAL; + perf_sample__init(&sample, /*all=*/false); ret = evsel__parse_sample(evsel, event, &sample); if (ret) - return ret; + goto out; /* * Loop through the auxtrace index to find the buffer that matches up with this aux event. @@ -3168,7 +3167,7 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf * 1 ('not found') */ if (ret != 1) - return ret; + goto out; } } @@ -3178,7 +3177,10 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf */ pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64 " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu); - return 0; + ret = 0; +out: + perf_sample__exit(&sample); + return ret; } static int cs_etm__queue_aux_records(struct perf_session *session) @@ -3489,9 +3491,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace; session->auxtrace = &etm->auxtrace; - err = cs_etm__setup_timeless_decoding(etm); - if (err) - return err; + cs_etm__setup_timeless_decoding(etm); etm->tc.time_shift = tc->time_shift; etm->tc.time_mult = tc->time_mult; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index a8caeea720aa..aa9bb4a32eca 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -230,6 +230,21 @@ struct cs_etm_packet_queue { /* CoreSight trace ID is currently the bottom 7 bits of the value */ #define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) +/* ETMv4 CONFIGR register bits */ +#define TRCCONFIGR_BB BIT(3) +#define TRCCONFIGR_CCI BIT(4) +#define TRCCONFIGR_CID BIT(6) +#define TRCCONFIGR_VMID BIT(7) +#define TRCCONFIGR_TS BIT(11) +#define TRCCONFIGR_RS BIT(12) +#define TRCCONFIGR_VMIDOPT BIT(15) + +/* ETMv3 ETMCR register bits */ +#define ETMCR_CYC_ACC BIT(12) +#define ETMCR_CTXTID BIT(14) +#define ETMCR_TIMESTAMP_EN BIT(28) +#define ETMCR_RETURN_STACK BIT(29) + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 5e7ff09fbc95..3b8f2df823a9 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -34,6 +34,8 @@ #include "util.h" #include "clockid.h" #include "util/sample.h" +#include "util/time-utils.h" +#include "header.h" #ifdef HAVE_LIBTRACEEVENT #include <event-parse.h> @@ -91,9 +93,14 @@ struct convert { struct perf_tool tool; struct ctf_writer writer; + struct perf_time_interval *ptime_range; + int range_size; + int range_num; + u64 events_size; u64 events_count; u64 non_sample_count; + u64 skipped; /* Ordered events configured queue size. */ u64 queue_size; @@ -811,6 +818,11 @@ static int process_sample_event(const struct perf_tool *tool, if (WARN_ONCE(!priv, "Failed to setup all events.\n")) return 0; + if (perf_time__ranges_skip_sample(c->ptime_range, c->range_num, sample->time)) { + ++c->skipped; + return 0; + } + event_class = priv->event_class; /* update stats */ @@ -1169,6 +1181,10 @@ static int add_event(struct ctf_writer *cw, struct evsel *evsel) const char *name = evsel__name(evsel); int ret; + if (evsel->priv) { + pr_err("Error: attempt to add already added event %s\n", name); + return -1; + } pr("Adding event '%s' (type %d)\n", name, evsel->core.attr.type); event_class = bt_ctf_event_class_create(name); @@ -1211,13 +1227,28 @@ err: return -1; } -static int setup_events(struct ctf_writer *cw, struct perf_session *session) +enum setup_events_type { + SETUP_EVENTS_ALL, + SETUP_EVENTS_NOT_TRACEPOINT, + SETUP_EVENTS_TRACEPOINT_ONLY, +}; + +static int setup_events(struct ctf_writer *cw, struct perf_session *session, + enum setup_events_type type) { struct evlist *evlist = session->evlist; struct evsel *evsel; int ret; evlist__for_each_entry(evlist, evsel) { + bool is_tracepoint = evsel->core.attr.type == PERF_TYPE_TRACEPOINT; + + if (is_tracepoint && type == SETUP_EVENTS_NOT_TRACEPOINT) + continue; + + if (!is_tracepoint && type == SETUP_EVENTS_TRACEPOINT_ONLY) + continue; + ret = add_event(cw, evsel); if (ret) return ret; @@ -1327,7 +1358,8 @@ static void cleanup_events(struct perf_session *session) struct evsel_priv *priv; priv = evsel->priv; - bt_ctf_event_class_put(priv->event_class); + if (priv) + bt_ctf_event_class_put(priv->event_class); zfree(&evsel->priv); } @@ -1338,16 +1370,16 @@ static void cleanup_events(struct perf_session *session) static int setup_streams(struct ctf_writer *cw, struct perf_session *session) { struct ctf_stream **stream; - struct perf_header *ph = &session->header; + struct perf_env *env = perf_session__env(session); int ncpus; /* * Try to get the number of cpus used in the data file, * if not present fallback to the MAX_CPUS. */ - ncpus = ph->env.nr_cpus_avail ?: MAX_CPUS; + ncpus = env->nr_cpus_avail ?: MAX_CPUS; - stream = zalloc(sizeof(*stream) * ncpus); + stream = calloc(ncpus, sizeof(*stream)); if (!stream) { pr_err("Failed to allocate streams.\n"); return -ENOMEM; @@ -1371,20 +1403,20 @@ static void free_streams(struct ctf_writer *cw) static int ctf_writer__setup_env(struct ctf_writer *cw, struct perf_session *session) { - struct perf_header *header = &session->header; + struct perf_env *env = perf_session__env(session); struct bt_ctf_writer *writer = cw->writer; #define ADD(__n, __v) \ do { \ - if (bt_ctf_writer_add_environment_field(writer, __n, __v)) \ + if (__v && bt_ctf_writer_add_environment_field(writer, __n, __v)) \ return -1; \ } while (0) - ADD("host", header->env.hostname); + ADD("host", env->hostname); ADD("sysname", "Linux"); - ADD("release", header->env.os_release); - ADD("version", header->env.version); - ADD("machine", header->env.arch); + ADD("release", env->os_release); + ADD("version", env->version); + ADD("machine", env->arch); ADD("domain", "kernel"); ADD("tracer_name", "perf"); @@ -1392,6 +1424,81 @@ do { \ return 0; } +static int process_feature_event(const struct perf_tool *tool, + struct perf_session *session, + union perf_event *event) +{ + struct convert *c = container_of(tool, struct convert, tool); + struct ctf_writer *cw = &c->writer; + struct perf_record_header_feature *fe = &event->feat; + int ret = perf_event__process_feature(tool, session, event); + + if (ret) + return ret; + + switch (fe->feat_id) { + case HEADER_EVENT_DESC: + /* + * In non-pipe mode (not here) the evsels combine the desc with + * the perf_event_attr when it is parsed. In pipe mode the + * perf_event_attr events appear first and then the event desc + * feature events that set the names appear after. Once we have + * the full evsel data we can generate the babeltrace + * events. For tracepoint events we still don't have the tracing + * data and so need to wait until the tracing data event to add + * those events to babeltrace. + */ + return setup_events(cw, session, SETUP_EVENTS_NOT_TRACEPOINT); + case HEADER_HOSTNAME: + if (session->header.env.hostname) { + return bt_ctf_writer_add_environment_field(cw->writer, "host", + session->header.env.hostname); + } + break; + case HEADER_OSRELEASE: + if (session->header.env.os_release) { + return bt_ctf_writer_add_environment_field(cw->writer, "release", + session->header.env.os_release); + } + break; + case HEADER_VERSION: + if (session->header.env.version) { + return bt_ctf_writer_add_environment_field(cw->writer, "version", + session->header.env.version); + } + break; + case HEADER_ARCH: + if (session->header.env.arch) { + return bt_ctf_writer_add_environment_field(cw->writer, "machine", + session->header.env.arch); + } + break; + default: + break; + } + return 0; +} + +static int process_tracing_data(const struct perf_tool *tool, + struct perf_session *session, + union perf_event *event) +{ + struct convert *c = container_of(tool, struct convert, tool); + struct ctf_writer *cw = &c->writer; + int ret; + + ret = perf_event__process_tracing_data(tool, session, event); + if (ret < 0) + return ret; + + /* + * Now the attr was set up by the attr event, the name by the feature + * event desc event and the tracepoint data set up above, the tracepoint + * babeltrace events can be added. + */ + return setup_events(cw, session, SETUP_EVENTS_TRACEPOINT_ONLY); +} + static int ctf_writer__setup_clock(struct ctf_writer *cw, struct perf_session *session, bool tod) @@ -1401,7 +1508,7 @@ static int ctf_writer__setup_clock(struct ctf_writer *cw, int64_t offset = 0; if (tod) { - struct perf_env *env = &session->header.env; + struct perf_env *env = perf_session__env(session); if (!env->clock.enabled) { pr_err("Can't provide --tod time, missing clock data. " @@ -1621,9 +1728,12 @@ int bt_convert__perf2ctf(const char *input, const char *path, c.tool.exit = perf_event__process_exit; c.tool.fork = perf_event__process_fork; c.tool.lost = perf_event__process_lost; - c.tool.tracing_data = perf_event__process_tracing_data; + c.tool.tracing_data = process_tracing_data; c.tool.build_id = perf_event__process_build_id; c.tool.namespaces = perf_event__process_namespaces; + c.tool.finished_round = perf_event__process_finished_round; + c.tool.attr = perf_event__process_attr; + c.tool.feature = process_feature_event; c.tool.ordering_requires_timestamps = true; if (opts->all) { @@ -1644,6 +1754,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, if (IS_ERR(session)) return PTR_ERR(session); + if (opts->time_str) { + err = perf_time__parse_for_ranges(opts->time_str, session, + &c.ptime_range, + &c.range_size, + &c.range_num); + if (err < 0) + goto free_session; + } + /* CTF writer */ if (ctf_writer__init(cw, path, session, opts->tod)) goto free_session; @@ -1657,8 +1776,11 @@ int bt_convert__perf2ctf(const char *input, const char *path, if (ctf_writer__setup_env(cw, session)) goto free_writer; - /* CTF events setup */ - if (setup_events(cw, session)) + /* + * CTF events setup. Note, in pipe mode no events exist yet (they come + * in via header feature events) and so this does nothing. + */ + if (setup_events(cw, session, SETUP_EVENTS_ALL)) goto free_writer; if (opts->all && setup_non_sample_events(cw, session)) @@ -1673,12 +1795,10 @@ int bt_convert__perf2ctf(const char *input, const char *path, else pr_err("Error during conversion.\n"); - fprintf(stderr, - "[ perf data convert: Converted '%s' into CTF data '%s' ]\n", + fprintf(stderr, "[ perf data convert: Converted '%s' into CTF data '%s' ]\n", data.path, path); - fprintf(stderr, - "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples", + fprintf(stderr, "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples", (double) c.events_size / 1024.0 / 1024.0, c.events_count); @@ -1687,6 +1807,14 @@ int bt_convert__perf2ctf(const char *input, const char *path, else fprintf(stderr, ", %" PRIu64 " non-samples) ]\n", c.non_sample_count); + if (c.skipped) { + fprintf(stderr, "[ perf data convert: Skipped %" PRIu64 " samples ]\n", + c.skipped); + } + + if (c.ptime_range) + zfree(&c.ptime_range); + cleanup_events(session); perf_session__delete(session); ctf_writer__cleanup(cw); @@ -1696,6 +1824,9 @@ int bt_convert__perf2ctf(const char *input, const char *path, free_writer: ctf_writer__cleanup(cw); free_session: + if (c.ptime_range) + zfree(&c.ptime_range); + perf_session__delete(session); pr_err("Error during conversion setup.\n"); return err; diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c index d9f805bf6fb0..d526c91312ed 100644 --- a/tools/perf/util/data-convert-json.c +++ b/tools/perf/util/data-convert-json.c @@ -25,6 +25,7 @@ #include "util/session.h" #include "util/symbol.h" #include "util/thread.h" +#include "util/time-utils.h" #include "util/tool.h" #ifdef HAVE_LIBTRACEEVENT @@ -35,13 +36,21 @@ struct convert_json { struct perf_tool tool; FILE *out; bool first; + struct perf_time_interval *ptime_range; + int range_size; + int range_num; + u64 events_count; + u64 skipped; }; // Outputs a JSON-encoded string surrounded by quotes with characters escaped. static void output_json_string(FILE *out, const char *s) { fputc('"', out); + if (!s) + goto out; + while (*s) { switch (*s) { @@ -65,6 +74,7 @@ static void output_json_string(FILE *out, const char *s) ++s; } +out: fputc('"', out); } @@ -165,6 +175,11 @@ static int process_sample_event(const struct perf_tool *tool, return -1; } + if (perf_time__ranges_skip_sample(c->ptime_range, c->range_num, sample->time)) { + ++c->skipped; + return 0; + } + ++c->events_count; if (c->first) @@ -257,7 +272,8 @@ static int process_sample_event(const struct perf_tool *tool, static void output_headers(struct perf_session *session, struct convert_json *c) { struct stat st; - struct perf_header *header = &session->header; + const struct perf_header *header = &session->header; + const struct perf_env *env = perf_session__env(session); int ret; int fd = perf_data__fd(session->data); int i; @@ -280,37 +296,37 @@ static void output_headers(struct perf_session *session, struct convert_json *c) output_json_key_format(out, true, 2, "data-size", "%" PRIu64, header->data_size); output_json_key_format(out, true, 2, "feat-offset", "%" PRIu64, header->feat_offset); - output_json_key_string(out, true, 2, "hostname", header->env.hostname); - output_json_key_string(out, true, 2, "os-release", header->env.os_release); - output_json_key_string(out, true, 2, "arch", header->env.arch); + output_json_key_string(out, true, 2, "hostname", env->hostname); + output_json_key_string(out, true, 2, "os-release", env->os_release); + output_json_key_string(out, true, 2, "arch", env->arch); - if (header->env.cpu_desc) - output_json_key_string(out, true, 2, "cpu-desc", header->env.cpu_desc); + if (env->cpu_desc) + output_json_key_string(out, true, 2, "cpu-desc", env->cpu_desc); - output_json_key_string(out, true, 2, "cpuid", header->env.cpuid); - output_json_key_format(out, true, 2, "nrcpus-online", "%u", header->env.nr_cpus_online); - output_json_key_format(out, true, 2, "nrcpus-avail", "%u", header->env.nr_cpus_avail); + output_json_key_string(out, true, 2, "cpuid", env->cpuid); + output_json_key_format(out, true, 2, "nrcpus-online", "%u", env->nr_cpus_online); + output_json_key_format(out, true, 2, "nrcpus-avail", "%u", env->nr_cpus_avail); - if (header->env.clock.enabled) { + if (env->clock.enabled) { output_json_key_format(out, true, 2, "clockid", - "%u", header->env.clock.clockid); + "%u", env->clock.clockid); output_json_key_format(out, true, 2, "clock-time", - "%" PRIu64, header->env.clock.clockid_ns); + "%" PRIu64, env->clock.clockid_ns); output_json_key_format(out, true, 2, "real-time", - "%" PRIu64, header->env.clock.tod_ns); + "%" PRIu64, env->clock.tod_ns); } - output_json_key_string(out, true, 2, "perf-version", header->env.version); + output_json_key_string(out, true, 2, "perf-version", env->version); output_json_key_format(out, true, 2, "cmdline", "["); - for (i = 0; i < header->env.nr_cmdline; i++) { + for (i = 0; i < env->nr_cmdline; i++) { output_json_delimiters(out, i != 0, 3); - output_json_string(c->out, header->env.cmdline_argv[i]); + output_json_string(c->out, env->cmdline_argv[i]); } output_json_format(out, false, 2, "]"); } -int bt_convert__perf2json(const char *input_name, const char *output_name, +int bt_convert__perf2json(const char *_input_name, const char *output_name, struct perf_data_convert_opts *opts __maybe_unused) { struct perf_session *session; @@ -319,10 +335,14 @@ int bt_convert__perf2json(const char *input_name, const char *output_name, struct convert_json c = { .first = true, .events_count = 0, + .ptime_range = NULL, + .range_size = 0, + .range_num = 0, + .skipped = 0, }; struct perf_data data = { .mode = PERF_DATA_MODE_READ, - .path = input_name, + .path = _input_name, .force = opts->force, }; @@ -344,6 +364,8 @@ int bt_convert__perf2json(const char *input_name, const char *output_name, c.tool.auxtrace_info = perf_event__process_auxtrace_info; c.tool.auxtrace = perf_event__process_auxtrace; c.tool.event_update = perf_event__process_event_update; + c.tool.attr = perf_event__process_attr; + c.tool.feature = perf_event__process_feature; c.tool.ordering_requires_timestamps = true; if (opts->all) { @@ -376,12 +398,20 @@ int bt_convert__perf2json(const char *input_name, const char *output_name, fprintf(stderr, "Error creating perf session!\n"); goto err_fclose; } - - if (symbol__init(&session->header.env) < 0) { + if (symbol__init(perf_session__env(session)) < 0) { fprintf(stderr, "Symbol init error!\n"); goto err_session_delete; } + if (opts->time_str) { + ret = perf_time__parse_for_ranges(opts->time_str, session, + &c.ptime_range, + &c.range_size, + &c.range_num); + if (ret < 0) + goto err_session_delete; + } + // The opening brace is printed manually because it isn't delimited from a // previous value (i.e. we don't want a leading newline) fputc('{', c.out); @@ -403,15 +433,23 @@ int bt_convert__perf2json(const char *input_name, const char *output_name, output_json_format(c.out, false, 0, "}"); fputc('\n', c.out); - fprintf(stderr, - "[ perf data convert: Converted '%s' into JSON data '%s' ]\n", - data.path, output_name); + fprintf(stderr, "[ perf data convert: Converted '%s' into JSON data '%s' ]\n", + data.path, output_name); fprintf(stderr, - "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n", - (ftell(c.out)) / 1024.0 / 1024.0, c.events_count); + "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n", + (ftell(c.out)) / 1024.0 / 1024.0, c.events_count); + + if (c.skipped) { + fprintf(stderr, "[ perf data convert: Skipped %" PRIu64 " samples ]\n", + c.skipped); + } ret = 0; + + if (c.ptime_range) + zfree(&c.ptime_range); + err_session_delete: perf_session__delete(session); err_fclose: diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h index 1b4c5f598415..ee651fa680a1 100644 --- a/tools/perf/util/data-convert.h +++ b/tools/perf/util/data-convert.h @@ -8,6 +8,7 @@ struct perf_data_convert_opts { bool force; bool all; bool tod; + const char *time_str; }; #ifdef HAVE_LIBBABELTRACE_SUPPORT diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 98661ede2a73..94dc534a7386 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -20,18 +20,33 @@ #include "rlimit.h" #include <internal/lib.h> -static void close_dir(struct perf_data_file *files, int nr) +static void perf_data_file__close(struct perf_data_file *file) { - while (--nr >= 0) { - close(files[nr].fd); - zfree(&files[nr].path); + if (file->use_stdio) { + if (file->fptr) { + fclose(file->fptr); + file->fptr = NULL; + } + } else { + close(file->fd); + file->fd = -1; } + zfree(&file->path); +} + +static void close_dir(struct perf_data_file *files, int nr) +{ + while (--nr >= 0) + perf_data_file__close(&files[nr]); + free(files); } void perf_data__close_dir(struct perf_data *data) { close_dir(data->dir.files, data->dir.nr); + data->dir.files = NULL; + data->dir.nr = 0; } int perf_data__create_dir(struct perf_data *data, int nr) @@ -43,7 +58,7 @@ int perf_data__create_dir(struct perf_data *data, int nr) if (WARN_ON(!data->is_dir)) return -EINVAL; - files = zalloc(nr * sizeof(*files)); + files = calloc(nr, sizeof(*files)); if (!files) return -ENOMEM; @@ -132,16 +147,21 @@ int perf_data__open_dir(struct perf_data *data) files = file; file = &files[nr++]; - file->path = strdup(path); + *file = (struct perf_data_file){ + .path = strdup(path), + .fd = -1, + .size = st.st_size, + .use_stdio = false, + }; if (!file->path) goto out_err; ret = open(file->path, O_RDONLY); - if (ret < 0) + if (ret < 0) { + ret = -errno; goto out_err; - + } file->fd = ret; - file->size = st.st_size; } closedir(dir); @@ -158,26 +178,6 @@ out_err: return ret; } -int perf_data__update_dir(struct perf_data *data) -{ - int i; - - if (WARN_ON(!data->is_dir)) - return -EINVAL; - - for (i = 0; i < data->dir.nr; i++) { - struct perf_data_file *file = &data->dir.files[i]; - struct stat st; - - if (fstat(file->fd, &st)) - return -1; - - file->size = st.st_size; - } - - return 0; -} - static bool check_pipe(struct perf_data *data) { struct stat st; @@ -194,7 +194,7 @@ static bool check_pipe(struct perf_data *data) } if (is_pipe) { - if (data->use_stdio) { + if (data->file.use_stdio) { const char *mode; mode = perf_data__is_read(data) ? "r" : "w"; @@ -202,7 +202,7 @@ static bool check_pipe(struct perf_data *data) if (data->file.fptr == NULL) { data->file.fd = fd; - data->use_stdio = false; + data->file.use_stdio = false; } /* @@ -233,17 +233,15 @@ static int check_backup(struct perf_data *data) ret = rm_rf_perf_data(oldname); if (ret) { - pr_err("Can't remove old data: %s (%s)\n", - ret == -2 ? - "Unknown file found" : strerror(errno), - oldname); + if (ret == -2) + pr_err("Can't remove old data: Unknown file found (%s)\n", oldname); + else + pr_err("Can't remove old data: %m (%s)\n", oldname); return -1; } if (rename(data->path, oldname)) { - pr_err("Can't move data: %s (%s to %s)\n", - strerror(errno), - data->path, oldname); + pr_err("Can't move data: %m (%s to %s)\n", data->path, oldname); return -1; } } @@ -266,14 +264,12 @@ static int open_file_read(struct perf_data *data) int flags = data->in_place_update ? O_RDWR : O_RDONLY; struct stat st; int fd; - char sbuf[STRERR_BUFSIZE]; fd = open(data->file.path, flags); if (fd < 0) { int err = errno; - pr_err("failed to open %s: %s", data->file.path, - str_error_r(err, sbuf, sizeof(sbuf))); + pr_err("failed to open %s: %m", data->file.path); if (err == ENOENT && !strcmp(data->file.path, "perf.data")) pr_err(" (try 'perf record' first)"); pr_err("\n"); @@ -305,15 +301,10 @@ static int open_file_read(struct perf_data *data) static int open_file_write(struct perf_data *data) { - int fd; - char sbuf[STRERR_BUFSIZE]; - - fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC, - S_IRUSR|S_IWUSR); + int fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC, S_IRUSR|S_IWUSR); if (fd < 0) - pr_err("failed to open %s : %s\n", data->file.path, - str_error_r(errno, sbuf, sizeof(sbuf))); + pr_err("failed to open %s : %m\n", data->file.path); return fd; } @@ -373,7 +364,7 @@ int perf_data__open(struct perf_data *data) return 0; /* currently it allows stdio for pipe only */ - data->use_stdio = false; + data->file.use_stdio = false; if (!data->path) data->path = "perf.data"; @@ -393,41 +384,57 @@ void perf_data__close(struct perf_data *data) if (perf_data__is_dir(data)) perf_data__close_dir(data); - zfree(&data->file.path); - - if (data->use_stdio) - fclose(data->file.fptr); - else - close(data->file.fd); + perf_data_file__close(&data->file); } -ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size) +static ssize_t perf_data_file__read(struct perf_data_file *file, void *buf, size_t size) { - if (data->use_stdio) { - if (fread(buf, size, 1, data->file.fptr) == 1) + if (file->use_stdio) { + if (fread(buf, size, 1, file->fptr) == 1) return size; - return feof(data->file.fptr) ? 0 : -1; + return feof(file->fptr) ? 0 : -1; } - return readn(data->file.fd, buf, size); + return readn(file->fd, buf, size); +} + +ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size) +{ + return perf_data_file__read(&data->file, buf, size); } ssize_t perf_data_file__write(struct perf_data_file *file, void *buf, size_t size) { + if (file->use_stdio) { + if (fwrite(buf, size, /*nmemb=*/1, file->fptr) == 1) + return size; + return -1; + } return writen(file->fd, buf, size); } ssize_t perf_data__write(struct perf_data *data, void *buf, size_t size) { - if (data->use_stdio) { - if (fwrite(buf, size, 1, data->file.fptr) == 1) - return size; - return -1; - } return perf_data_file__write(&data->file, buf, size); } +off_t perf_data_file__seek(struct perf_data_file *file, off_t offset, int whence) +{ + if (file->use_stdio) { + off_t res = fseeko(file->fptr, offset, whence); + + return res < 0 ? -1 : ftello(file->fptr); + } + return lseek(file->fd, offset, whence); +} + +off_t perf_data__seek(struct perf_data *data, off_t offset, int whence) +{ + /* Note, a pipe fd will fail with -1 with errno of ESPIPE. */ + return perf_data_file__seek(&data->file, offset, whence); +} + int perf_data__switch(struct perf_data *data, const char *postfix, size_t pos, bool at_exit, @@ -449,19 +456,18 @@ int perf_data__switch(struct perf_data *data, pr_warning("Failed to rename %s to %s\n", data->path, *new_filepath); if (!at_exit) { - close(data->file.fd); + perf_data_file__close(&data->file); ret = perf_data__open(data); if (ret < 0) goto out; - if (lseek(data->file.fd, pos, SEEK_SET) == (off_t)-1) { + if (perf_data__seek(data, pos, SEEK_SET) == (off_t)-1) { ret = -errno; - pr_debug("Failed to lseek to %zu: %s", - pos, strerror(errno)); + pr_debug("Failed to seek to %zu: %m", pos); goto out; } } - ret = data->file.fd; + ret = perf_data__fd(data); out: return ret; } diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 110f3ebde30f..8299fb5fa7da 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -17,32 +17,70 @@ enum perf_dir_version { PERF_DIR_VERSION = 1, }; +/** + * struct perf_data_file: A wrapper around a file used for perf.data reading or writing. Generally + * part of struct perf_data. + */ struct perf_data_file { + /** + * @path: Path of file. Generally a copy of perf_data.path but for a + * directory it is the file within the directory. + */ char *path; union { + /** @fd: File descriptor for read/writes. Valid if use_stdio is false. */ int fd; + /** + * @fptr: Stdio FILE. Valid if use_stdio is true, currently just + * pipes in perf inject. + */ FILE *fptr; }; + /** @size: Size of file when opened. */ unsigned long size; + /** @use_stdio: Use buffered stdio operations. */ + bool use_stdio; }; +/** + * struct perf_data: A wrapper around a file used for perf.data reading or writing. + */ struct perf_data { + /** @path: Path to open and of the file. NULL implies 'perf.data' will be used. */ const char *path; + /** @file: Underlying file to be used. */ struct perf_data_file file; + /** @is_pipe: Underlying file is a pipe. */ bool is_pipe; + /** @is_dir: Underlying file is a directory. */ bool is_dir; + /** @force: Ignore opening a file creating created by a different user. */ bool force; - bool use_stdio; + /** @in_place_update: A file opened for reading but will be written to. */ bool in_place_update; + /** @mode: Read or write mode. */ enum perf_data_mode mode; struct { + /** @version: perf_dir_version. */ u64 version; + /** @files: perf data files for the directory. */ struct perf_data_file *files; + /** @nr: Number of perf data files for the directory. */ int nr; } dir; }; +static inline int perf_data_file__fd(struct perf_data_file *file) +{ + return file->use_stdio ? fileno(file->fptr) : file->fd; +} + +ssize_t perf_data_file__write(struct perf_data_file *file, + void *buf, size_t size); +off_t perf_data_file__seek(struct perf_data_file *file, off_t offset, int whence); + + static inline bool perf_data__is_read(struct perf_data *data) { return data->mode == PERF_DATA_MODE_READ; @@ -70,10 +108,7 @@ static inline bool perf_data__is_single_file(struct perf_data *data) static inline int perf_data__fd(struct perf_data *data) { - if (data->use_stdio) - return fileno(data->file.fptr); - - return data->file.fd; + return perf_data_file__fd(&data->file); } int perf_data__open(struct perf_data *data); @@ -81,8 +116,7 @@ void perf_data__close(struct perf_data *data); ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size); ssize_t perf_data__write(struct perf_data *data, void *buf, size_t size); -ssize_t perf_data_file__write(struct perf_data_file *file, - void *buf, size_t size); +off_t perf_data__seek(struct perf_data *data, off_t offset, int whence); /* * If at_exit is set, only rename current perf.data to * perf.data.<postfix>, continue write on original data. @@ -97,11 +131,12 @@ int perf_data__switch(struct perf_data *data, int perf_data__create_dir(struct perf_data *data, int nr); int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); -int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); -bool has_kcore_dir(const char *path); char *perf_data__kallsyms_name(struct perf_data *data); char *perf_data__guest_kallsyms_name(struct perf_data *data, pid_t machine_pid); + +bool has_kcore_dir(const char *path); bool is_perf_data(const char *path); + #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 50f916374d87..cc2bb1af4243 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -19,7 +19,6 @@ #include "callchain.h" #include "call-path.h" #include "db-export.h" -#include <linux/zalloc.h> int db_export__init(struct db_export *dbe) { @@ -181,7 +180,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, if (al->map) { struct dso *dso = map__dso(al->map); - err = db_export__dso(dbe, dso, maps__machine(al->maps)); + err = db_export__dso(dbe, dso, maps__machine(thread__maps(al->thread))); if (err) return err; *dso_db_id = dso__db_id(dso); @@ -254,8 +253,8 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, addr_location__init(&al); al.sym = node->ms.sym; al.map = map__get(node->ms.map); - al.maps = maps__get(thread__maps(thread)); al.addr = node->ip; + al.thread = thread__get(thread); if (al.map && !al.sym) al.sym = dso__find_symbol(map__dso(al.map), al.addr); @@ -358,14 +357,18 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, }; struct thread *main_thread; struct comm *comm = NULL; - struct machine *machine; + struct machine *machine = NULL; int err; + if (thread__maps(thread)) + machine = maps__machine(thread__maps(thread)); + if (!machine) + return -1; + err = db_export__evsel(dbe, evsel); if (err) return err; - machine = maps__machine(al->maps); err = db_export__machine(dbe, machine); if (err) return err; diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 995f6bb05b5f..6b5ffe81f141 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -14,11 +14,19 @@ #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif +#include "addr_location.h" #include "color.h" -#include "event.h" #include "debug.h" +#include "env.h" +#include "event.h" +#include "machine.h" +#include "map.h" #include "print_binary.h" +#include "srcline.h" +#include "symbol.h" +#include "synthetic-events.h" #include "target.h" +#include "thread.h" #include "trace-event.h" #include "ui/helpline.h" #include "ui/ui.h" @@ -40,14 +48,14 @@ int debug_ordered_events; static int redirect_to_stderr; int debug_data_convert; static FILE *_debug_file; -bool debug_display_time; +static bool debug_display_time; int debug_type_profile; FILE *debug_file(void) { if (!_debug_file) { - pr_warning_once("debug_file not set"); debug_set_file(stderr); + pr_warning_once("debug_file not set"); } return _debug_file; } @@ -298,21 +306,66 @@ void perf_debug_setup(void) libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper); } +void __dump_stack(FILE *file, void **stackdump, size_t stackdump_size) +{ + /* TODO: async safety. printf, malloc, etc. aren't safe inside a signal handler. */ + pid_t pid = getpid(); + struct machine *machine; + struct thread *thread = NULL; + struct perf_env host_env; + + perf_env__init(&host_env); + machine = machine__new_live(&host_env, /*kernel_maps=*/false, pid); + + if (machine) + thread = machine__find_thread(machine, pid, pid); + +#ifdef HAVE_BACKTRACE_SUPPORT + if (!machine || !thread) { + /* + * Backtrace functions are async signal safe. Fall back on them + * if machine/thread creation fails. + */ + backtrace_symbols_fd(stackdump, stackdump_size, fileno(file)); + machine__delete(machine); + perf_env__exit(&host_env); + return; + } +#endif + + for (size_t i = 0; i < stackdump_size; i++) { + struct addr_location al; + u64 addr = (u64)(uintptr_t)stackdump[i]; + bool printed = false; + + addr_location__init(&al); + if (thread && thread__find_map(thread, PERF_RECORD_MISC_USER, addr, &al)) { + al.sym = map__find_symbol(al.map, al.addr); + if (al.sym) { + fprintf(file, " #%zd %p in %s ", i, stackdump[i], al.sym->name); + printed = true; + } + } + if (!printed) + fprintf(file, " #%zd %p ", i, stackdump[i]); + + map__fprintf_srcline(al.map, al.addr, "", file); + fprintf(file, "\n"); + addr_location__exit(&al); + } + thread__put(thread); + machine__delete(machine); + perf_env__exit(&host_env); +} + /* Obtain a backtrace and print it to stdout. */ #ifdef HAVE_BACKTRACE_SUPPORT void dump_stack(void) { - void *array[16]; - size_t size = backtrace(array, ARRAY_SIZE(array)); - char **strings = backtrace_symbols(array, size); - size_t i; - - printf("Obtained %zd stack frames.\n", size); - - for (i = 0; i < size; i++) - printf("%s\n", strings[i]); + void *stackdump[32]; + size_t size = backtrace(stackdump, ARRAY_SIZE(stackdump)); - free(strings); + __dump_stack(stdout, stackdump, size); } #else void dump_stack(void) {} diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index a4026d1fd6a3..6b737e195ce1 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -85,6 +85,7 @@ void debug_set_display_time(bool set); void perf_debug_setup(void); int perf_quiet_option(void); +void __dump_stack(FILE *file, void **stackdump, size_t stackdump_size); void dump_stack(void); void sighandler_dump_stack(int sig); diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c index 19acf4775d35..0e35c13abd04 100644 --- a/tools/perf/util/debuginfo.c +++ b/tools/perf/util/debuginfo.c @@ -88,30 +88,33 @@ static struct debuginfo *__debuginfo__new(const char *path) return dbg; } -enum dso_binary_type distro_dwarf_types[] = { - DSO_BINARY_TYPE__FEDORA_DEBUGINFO, - DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, - DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, - DSO_BINARY_TYPE__BUILDID_DEBUGINFO, - DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, - DSO_BINARY_TYPE__NOT_FOUND, -}; - struct debuginfo *debuginfo__new(const char *path) { - enum dso_binary_type *type; + static const enum dso_binary_type distro_dwarf_types[] = { + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__NOT_FOUND, + }; + const enum dso_binary_type *type; char buf[PATH_MAX], nil = '\0'; struct dso *dso; struct debuginfo *dinfo = NULL; - struct build_id bid; + struct build_id bid = { .size = 0}; /* Try to open distro debuginfo files */ dso = dso__new(path); if (!dso) goto out; - /* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */ - if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0) + /* + * Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO. Don't block + * incase the path isn't for a regular file. + */ + assert(!dso__has_build_id(dso)); + if (filename__read_build_id(path, &bid) > 0) dso__set_build_id(dso, &bid); for (type = distro_dwarf_types; @@ -125,8 +128,12 @@ struct debuginfo *debuginfo__new(const char *path) dso__put(dso); out: + if (dinfo) + return dinfo; + /* if failed to open all distro debuginfo, open given binary */ - return dinfo ? : __debuginfo__new(path); + symbol__join_symfs(buf, path); + return __debuginfo__new(buf); } void debuginfo__delete(struct debuginfo *dbg) diff --git a/tools/perf/util/demangle-cxx.h b/tools/perf/util/demangle-cxx.h index 26b5b66c0b4e..9359937a881a 100644 --- a/tools/perf/util/demangle-cxx.h +++ b/tools/perf/util/demangle-cxx.h @@ -2,6 +2,8 @@ #ifndef __PERF_DEMANGLE_CXX #define __PERF_DEMANGLE_CXX 1 +#include <stdbool.h> + #ifdef __cplusplus extern "C" { #endif diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c index ddf33d58bcd3..c3cb327ed562 100644 --- a/tools/perf/util/demangle-java.c +++ b/tools/perf/util/demangle-java.c @@ -158,7 +158,7 @@ char * java_demangle_sym(const char *str, int flags) { char *buf, *ptr; - char *p; + const char *p; size_t len, l1 = 0; if (!str) diff --git a/tools/perf/util/demangle-rust-v0.c b/tools/perf/util/demangle-rust-v0.c new file mode 100644 index 000000000000..19924d85407d --- /dev/null +++ b/tools/perf/util/demangle-rust-v0.c @@ -0,0 +1,2042 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +// The contents of this file come from the Rust rustc-demangle library, hosted +// in the <https://github.com/rust-lang/rustc-demangle> repository, licensed +// under "Apache-2.0 OR MIT". For copyright details, see +// <https://github.com/rust-lang/rustc-demangle/blob/main/README.md>. +// Please note that the file should be kept as close as possible to upstream. + +// Code for demangling Rust symbols. This code is mostly +// a line-by-line translation of the Rust code in `rustc-demangle`. + +// you can find the latest version of this code in https://github.com/rust-lang/rustc-demangle + +#include <stdint.h> +#include <stddef.h> +#include <string.h> +#include <stdbool.h> +#include <sys/param.h> +#include <stdio.h> + +#include "demangle-rust-v0.h" + +#if defined(__GNUC__) || defined(__clang__) +#define NODISCARD __attribute__((warn_unused_result)) +#else +#define NODISCARD +#endif + +#define MAX_DEPTH 500 + +typedef enum { + DemangleOk, + DemangleInvalid, + DemangleRecursed, + DemangleBug, +} demangle_status; + +struct demangle_v0 { + const char *mangled; + size_t mangled_len; +}; + +struct demangle_legacy { + const char *mangled; + size_t mangled_len; + size_t elements; +}; + +// private version of memrchr to avoid _GNU_SOURCE +static void *demangle_memrchr(const void *s, int c, size_t n) { + const uint8_t *s_ = s; + for (; n != 0; n--) { + if (s_[n-1] == c) { + return (void*)&s_[n-1]; + } + } + return NULL; +} + + +static bool unicode_iscontrol(uint32_t ch) { + // this is *technically* a unicode table, but + // some unicode properties are simpler than you might think + return ch < 0x20 || (ch >= 0x7f && ch < 0xa0); +} + +// "good enough" tables, the only consequence is that when printing +// *constant strings*, some characters are printed as `\u{abcd}` rather than themselves. +// +// I'm leaving these here to allow easily replacing them with actual +// tables if desired. +static bool unicode_isprint(uint32_t ch) { + if (ch < 0x20) { + return false; + } + if (ch < 0x7f) { + return true; + } + return false; +} + +static bool unicode_isgraphemextend(uint32_t ch) { + (void)ch; + return false; +} + +static bool str_isascii(const char *s, size_t s_len) { + for (size_t i = 0; i < s_len; i++) { + if (s[i] & 0x80) { + return false; + } + } + + return true; +} + +typedef enum { + PunycodeOk, + PunycodeError +} punycode_status; + +struct parser { + // the parser assumes that `sym` has a safe "terminating byte". It might be NUL, + // but it might also be something else if a symbol is "truncated". + const char *sym; + size_t sym_len; + size_t next; + uint32_t depth; +}; + +struct printer { + demangle_status status; // if status == 0 parser is valid + struct parser parser; + char *out; // NULL for no output [in which case out_len is not decremented] + size_t out_len; + uint32_t bound_lifetime_depth; + bool alternate; +}; + +static NODISCARD overflow_status printer_print_path(struct printer *printer, bool in_value); +static NODISCARD overflow_status printer_print_type(struct printer *printer); +static NODISCARD overflow_status printer_print_const(struct printer *printer, bool in_value); + +static NODISCARD demangle_status try_parse_path(struct parser *parser) { + struct printer printer = { + DemangleOk, + *parser, + NULL, + SIZE_MAX, + 0, + false + }; + overflow_status ignore = printer_print_path(&printer, false); // can't fail since no output + (void)ignore; + *parser = printer.parser; + return printer.status; +} + +NODISCARD static demangle_status rust_demangle_v0_demangle(const char *s, size_t s_len, struct demangle_v0 *res, const char **rest) { + if (s_len > strlen(s)) { + // s_len only exists to shorten the string, this is not a buffer API + return DemangleInvalid; + } + + const char *inner; + size_t inner_len; + if (s_len >= 2 && !strncmp(s, "_R", strlen("_R"))) { + inner = s+2; + inner_len = s_len - 2; + } else if (s_len >= 1 && !strncmp(s, "R", strlen("R"))) { + // On Windows, dbghelp strips leading underscores, so we accept "R..." + // form too. + inner = s+1; + inner_len = s_len - 1; + } else if (s_len >= 3 && !strncmp(s, "__R", strlen("__R"))) { + // On OSX, symbols are prefixed with an extra _ + inner = s+3; + inner_len = s_len - 3; + } else { + return DemangleInvalid; + } + + // Paths always start with uppercase characters. + if (*inner < 'A' || *inner > 'Z') { + return DemangleInvalid; + } + + if (!str_isascii(inner, inner_len)) { + return DemangleInvalid; + } + + struct parser parser = { inner, inner_len, 0, 0 }; + + demangle_status status = try_parse_path(&parser); + if (status != DemangleOk) return status; + char next = parser.sym[parser.next]; + + // Instantiating crate (paths always start with uppercase characters). + if (parser.next < parser.sym_len && next >= 'A' && next <= 'Z') { + status = try_parse_path(&parser); + if (status != DemangleOk) return status; + } + + res->mangled = inner; + res->mangled_len = inner_len; + if (rest) { + *rest = parser.sym + parser.next; + } + + return DemangleOk; +} + +// This might require `len` to be up to 3 characters bigger than the real output len in case of utf-8 +NODISCARD static overflow_status rust_demangle_v0_display_demangle(struct demangle_v0 res, char *out, size_t len, bool alternate) { + struct printer printer = { + DemangleOk, + { + res.mangled, + res.mangled_len, + 0, + 0 + }, + out, + len, + 0, + alternate + }; + if (printer_print_path(&printer, true) == OverflowOverflow) { + return OverflowOverflow; + } + if (printer.out_len < OVERFLOW_MARGIN) { + return OverflowOverflow; + } + *printer.out = '\0'; + return OverflowOk; +} + +static size_t code_to_utf8(unsigned char *buffer, uint32_t code) +{ + if (code <= 0x7F) { + buffer[0] = code; + return 1; + } + if (code <= 0x7FF) { + buffer[0] = 0xC0 | (code >> 6); /* 110xxxxx */ + buffer[1] = 0x80 | (code & 0x3F); /* 10xxxxxx */ + return 2; + } + if (code <= 0xFFFF) { + buffer[0] = 0xE0 | (code >> 12); /* 1110xxxx */ + buffer[1] = 0x80 | ((code >> 6) & 0x3F); /* 10xxxxxx */ + buffer[2] = 0x80 | (code & 0x3F); /* 10xxxxxx */ + return 3; + } + if (code <= 0x10FFFF) { + buffer[0] = 0xF0 | (code >> 18); /* 11110xxx */ + buffer[1] = 0x80 | ((code >> 12) & 0x3F); /* 10xxxxxx */ + buffer[2] = 0x80 | ((code >> 6) & 0x3F); /* 10xxxxxx */ + buffer[3] = 0x80 | (code & 0x3F); /* 10xxxxxx */ + return 4; + } + return 0; +} + + +// return length of char at byte, or SIZE_MAX if invalid. buf should have 4 valid characters +static NODISCARD size_t utf8_next_char(uint8_t *s, uint32_t *ch) { + uint8_t byte = *s; + // UTF8-1 = %x00-7F + // UTF8-2 = %xC2-DF UTF8-tail + // UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) / + // %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail ) + // UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) / + // %xF4 %x80-8F 2( UTF8-tail ) + if (byte < 0x80) { + *ch = byte; + return 1; + } else if (byte < 0xc2) { + return SIZE_MAX; + } else if (byte < 0xe0) { + if (s[1] >= 0x80 && s[1] < 0xc0) { + *ch = ((byte&0x1f)<<6) + (s[1] & 0x3f); + return 2; + } + return SIZE_MAX; + } if (byte < 0xf0) { + if (!(s[1] >= 0x80 && s[1] < 0xc0) || !(s[2] >= 0x80 && s[2] < 0xc0)) { + return SIZE_MAX; // basic validation + } + if (byte == 0xe0 && s[1] < 0xa0) { + return SIZE_MAX; // overshort + } + if (byte == 0xed && s[1] >= 0xa0) { + return SIZE_MAX; // surrogate + } + *ch = ((byte&0x0f)<<12) + ((s[1] & 0x3f)<<6) + (s[2] & 0x3f); + return 3; + } else if (byte < 0xf5) { + if (!(s[1] >= 0x80 && s[1] < 0xc0) || !(s[2] >= 0x80 && s[2] < 0xc0) || !(s[3] >= 0x80 && s[3] < 0xc0)) { + return SIZE_MAX; // basic validation + } + if (byte == 0xf0 && s[1] < 0x90) { + return SIZE_MAX; // overshort + } + if (byte == 0xf4 && s[1] >= 0x90) { + return SIZE_MAX; // over max + } + *ch = ((byte&0x07)<<18) + ((s[1] & 0x3f)<<12) + ((s[2] & 0x3f)<<6) + (s[3]&0x3f); + return 4; + } else { + return SIZE_MAX; + } +} + +static NODISCARD bool validate_char(uint32_t n) { + return ((n ^ 0xd800) - 0x800) < 0x110000 - 0x800; +} + +#define SMALL_PUNYCODE_LEN 128 + +static NODISCARD punycode_status punycode_decode(const char *start, size_t ascii_len, const char *punycode_start, size_t punycode_len, uint32_t (*out_)[SMALL_PUNYCODE_LEN], size_t *out_len) { + uint32_t *out = *out_; + + if (punycode_len == 0) { + return PunycodeError; + } + + if (ascii_len > SMALL_PUNYCODE_LEN) { + return PunycodeError; + } + for (size_t i = 0; i < ascii_len; i++) { + out[i] = start[i]; + } + size_t len = ascii_len; + + size_t base = 36, t_min = 1, t_max = 26, skew = 38, damp = 700, bias = 72, i = 0, n = 0x80; + for (;;) { + size_t delta = 0, w = 1, k = 0; + for (;;) { + k += base; + size_t biased = k < bias ? 0 : k - bias; + size_t t = MIN(MAX(biased, t_min), t_max); + size_t d; + if (punycode_len == 0) { + return PunycodeError; + } + char nx = *punycode_start++; + punycode_len--; + if ('a' <= nx && nx <= 'z') { + d = nx - 'a'; + } else if ('0' <= nx && nx <= '9') { + d = 26 + (nx - '0'); + } else { + return PunycodeError; + } + if (w == 0 || d > SIZE_MAX / w || d*w > SIZE_MAX - delta) { + return PunycodeError; + } + delta += d * w; + if (d < t) { + break; + } + if (base < t || w == 0 || (base - t) > SIZE_MAX / w) { + return PunycodeError; + } + w *= (base - t); + } + + len += 1; + if (i > SIZE_MAX - delta) { + return PunycodeError; + } + i += delta; + if (n > SIZE_MAX - i / len) { + return PunycodeError; + } + n += i / len; + i %= len; + + // char validation + if (n > UINT32_MAX || !validate_char((uint32_t)n)) { + return PunycodeError; + } + + // insert new character + if (len > SMALL_PUNYCODE_LEN) { + return PunycodeError; + } + memmove(out + i + 1, out + i, (len - i - 1) * sizeof(uint32_t)); + out[i] = (uint32_t)n; + + // start i index at incremented position + i++; + + // If there are no more deltas, decoding is complete. + if (punycode_len == 0) { + *out_len = len; + return PunycodeOk; + } + + // Perform bias adaptation. + delta /= damp; + damp = 2; + + delta += delta / len; + k = 0; + while (delta > ((base - t_min) * t_max) / 2) { + delta /= base - t_min; + k += base; + } + bias = k + ((base - t_min + 1) * delta) / (delta + skew); + } +} + +struct ident { + const char *ascii_start; + size_t ascii_len; + const char *punycode_start; + size_t punycode_len; +}; + +static NODISCARD overflow_status display_ident(const char *ascii_start, size_t ascii_len, const char *punycode_start, size_t punycode_len, uint8_t *out, size_t *out_len) { + uint32_t outbuf[SMALL_PUNYCODE_LEN]; + + size_t wide_len; + size_t out_buflen = *out_len; + + if (punycode_len == 0) { + if (ascii_len > out_buflen) { + return OverflowOverflow; + } + memcpy(out, ascii_start, ascii_len); + *out_len = ascii_len; + } else if (punycode_decode(ascii_start, ascii_len, punycode_start, punycode_len, &outbuf, &wide_len) == PunycodeOk) { + size_t narrow_len = 0; + for (size_t i = 0; i < wide_len; i++) { + if (out_buflen - narrow_len < 4) { + return OverflowOverflow; + } + unsigned char *pos = &out[narrow_len]; + narrow_len += code_to_utf8(pos, outbuf[i]); + } + *out_len = narrow_len; + } else { + size_t narrow_len = 0; + if (out_buflen < strlen("punycode{")) { + return OverflowOverflow; + } + memcpy(out, "punycode{", strlen("punycode{")); + narrow_len = strlen("punycode{"); + if (ascii_len > 0) { + if (out_buflen - narrow_len < ascii_len || out_buflen - narrow_len - ascii_len < 1) { + return OverflowOverflow; + } + memcpy(out + narrow_len, ascii_start, ascii_len); + narrow_len += ascii_len; + out[narrow_len] = '-'; + narrow_len++; + } + if (out_buflen - narrow_len < punycode_len || out_buflen - narrow_len - punycode_len < 1) { + return OverflowOverflow; + } + memcpy(out + narrow_len, punycode_start, punycode_len); + narrow_len += punycode_len; + out[narrow_len] = '}'; + narrow_len++; + *out_len = narrow_len; + } + + return OverflowOk; +} + +static NODISCARD bool try_parse_uint(const char *buf, size_t len, uint64_t *result) { + size_t cur = 0; + for(;cur < len && buf[cur] == '0';cur++); + uint64_t result_val = 0; + if (len - cur > 16) return false; + for(;cur < len;cur++) { + char c = buf[cur]; + result_val <<= 4; + if ('0' <= c && c <= '9') { + result_val += c - '0'; + } else if ('a' <= c && c <= 'f') { + result_val += 10 + (c - 'a'); + } else { + return false; + } + } + *result = result_val; + return true; +} + +static NODISCARD bool dinibble2int(const char *buf, uint8_t *result) { + uint8_t result_val = 0; + for (int i = 0; i < 2; i++) { + char c = buf[i]; + result_val <<= 4; + if ('0' <= c && c <= '9') { + result_val += c - '0'; + } else if ('a' <= c && c <= 'f') { + result_val += 10 + (c - 'a'); + } else { + return false; + } + } + *result = result_val; + return true; +} + + +typedef enum { + NtsOk = 0, + NtsOverflow = 1, + NtsInvalid = 2 +} nibbles_to_string_status; + +// '\u{10ffff}', +margin +#define ESCAPED_SIZE 12 + +static NODISCARD size_t char_to_string(uint32_t ch, uint8_t quote, bool first, char (*buf)[ESCAPED_SIZE]) { + // encode the character + char *escaped_buf = *buf; + escaped_buf[0] = '\\'; + size_t escaped_len = 2; + switch (ch) { + case '\0': + escaped_buf[1] = '0'; + break; + case '\t': + escaped_buf[1] = 't'; + break; + case '\r': + escaped_buf[1] = 'r'; + break; + case '\n': + escaped_buf[1] = 'n'; + break; + case '\\': + escaped_buf[1] = '\\'; + break; + default: + if (ch == quote) { + escaped_buf[1] = ch; + } else if (!unicode_isprint(ch) || (first && unicode_isgraphemextend(ch))) { + int hexlen = snprintf(escaped_buf, ESCAPED_SIZE, "\\u{%x}", (unsigned int)ch); + if (hexlen < 0) { + return 0; // (snprintf shouldn't fail!) + } + escaped_len = hexlen; + } else { + // printable character + escaped_buf[0] = ch; + escaped_len = 1; + } + break; + } + + return escaped_len; +} + +// convert nibbles to a single/double-quoted string +static NODISCARD nibbles_to_string_status nibbles_to_string(const char *buf, size_t len, uint8_t *out, size_t *out_len) { + uint8_t quote = '"'; + bool first = true; + + if ((len % 2) != 0) { + return NtsInvalid; // odd number of nibbles + } + + size_t cur_out_len = 0; + + // write starting quote + if (out != NULL) { + cur_out_len = *out_len; + if (cur_out_len == 0) { + return NtsOverflow; + } + *out++ = quote; + cur_out_len--; + } + + uint8_t conv_buf[4] = {0}; + size_t conv_buf_len = 0; + while (len > 1 || conv_buf_len > 0) { + while (len > 1 && conv_buf_len < sizeof(conv_buf)) { + if (!dinibble2int(buf, &conv_buf[conv_buf_len])) { + return NtsInvalid; + } + conv_buf_len++; + buf += 2; + len -= 2; + } + + // conv_buf is full here if possible, process 1 UTF-8 character + uint32_t ch = 0; + size_t consumed = utf8_next_char(conv_buf, &ch); + if (consumed > conv_buf_len) { + // either SIZE_MAX (invalid UTF-8) or finished input buffer and + // there are still bytes remaining, in both cases invalid + return NtsInvalid; + } + + // "consume" the character + memmove(conv_buf, conv_buf+consumed, conv_buf_len-consumed); + conv_buf_len -= consumed; + + char escaped_buf[ESCAPED_SIZE]; + size_t escaped_len = char_to_string(ch, '"', first, &escaped_buf); + if (out != NULL) { + if (cur_out_len < escaped_len) { + return NtsOverflow; + } + memcpy(out, escaped_buf, escaped_len); + out += escaped_len; + cur_out_len -= escaped_len; + } + first = false; + } + + // write ending quote + if (out != NULL) { + if (cur_out_len == 0) { + return NtsOverflow; + } + *out++ = quote; + cur_out_len--; + *out_len -= cur_out_len; // subtract remaining space to get used space + } + + return NtsOk; +} + +static const char* basic_type(uint8_t tag) { + switch(tag) { + case 'b': + return "bool"; + case 'c': + return "char"; + case 'e': + return "str"; + case 'u': + return "()"; + case 'a': + return "i8"; + case 's': + return "i16"; + case 'l': + return "i32"; + case 'x': + return "i64"; + case 'n': + return "i128"; + case 'i': + return "isize"; + case 'h': + return "u8"; + case 't': + return "u16"; + case 'm': + return "u32"; + case 'y': + return "u64"; + case 'o': + return "u128"; + case 'j': + return "usize"; + case 'f': + return "f32"; + case 'd': + return "f64"; + case 'z': + return "!"; + case 'p': + return "_"; + case 'v': + return "..."; + default: + return NULL; + } +} + +static NODISCARD demangle_status parser_push_depth(struct parser *parser) { + parser->depth++; + if (parser->depth > MAX_DEPTH) { + return DemangleRecursed; + } else { + return DemangleOk; + } +} + +static demangle_status parser_pop_depth(struct parser *parser) { + parser->depth--; + return DemangleOk; +} + +static uint8_t parser_peek(struct parser const *parser) { + if (parser->next == parser->sym_len) { + return 0; // add a "pseudo nul terminator" to avoid peeking past the end of a symbol + } else { + return parser->sym[parser->next]; + } +} + +static bool parser_eat(struct parser *parser, uint8_t ch) { + if (parser_peek(parser) == ch) { + if (ch != 0) { // safety: make sure we don't skip past the NUL terminator + parser->next++; + } + return true; + } else { + return false; + } +} + +static uint8_t parser_next(struct parser *parser) { + // don't advance after end of input, and return an imaginary NUL terminator + if (parser->next == parser->sym_len) { + return 0; + } else { + return parser->sym[parser->next++]; + } +} + +static NODISCARD demangle_status parser_ch(struct parser *parser, uint8_t *next) { + // don't advance after end of input + if (parser->next == parser->sym_len) { + return DemangleInvalid; + } else { + *next = parser->sym[parser->next++]; + return DemangleOk; + } +} + +struct buf { + const char *start; + size_t len; +}; + +static NODISCARD demangle_status parser_hex_nibbles(struct parser *parser, struct buf *buf) { + size_t start = parser->next; + for (;;) { + uint8_t ch = parser_next(parser); + if (ch == '_') { + break; + } + if (!(('0' <= ch && ch <= '9') || ('a' <= ch && ch <= 'f'))) { + return DemangleInvalid; + } + } + buf->start = parser->sym + start; + buf->len = parser->next - start - 1; // skip final _ + return DemangleOk; +} + +static NODISCARD demangle_status parser_digit_10(struct parser *parser, uint8_t *out) { + uint8_t ch = parser_peek(parser); + if ('0' <= ch && ch <= '9') { + *out = ch - '0'; + parser->next++; + return DemangleOk; + } else { + return DemangleInvalid; + } +} + +static NODISCARD demangle_status parser_digit_62(struct parser *parser, uint64_t *out) { + uint8_t ch = parser_peek(parser); + if ('0' <= ch && ch <= '9') { + *out = ch - '0'; + parser->next++; + return DemangleOk; + } else if ('a' <= ch && ch <= 'z') { + *out = 10 + (ch - 'a'); + parser->next++; + return DemangleOk; + } else if ('A' <= ch && ch <= 'Z') { + *out = 10 + 26 + (ch - 'A'); + parser->next++; + return DemangleOk; + } else { + return DemangleInvalid; + } +} + +static NODISCARD demangle_status parser_integer_62(struct parser *parser, uint64_t *out) { + if (parser_eat(parser, '_')) { + *out = 0; + return DemangleOk; + } + + uint64_t x = 0; + demangle_status status; + while (!parser_eat(parser, '_')) { + uint64_t d; + if ((status = parser_digit_62(parser, &d)) != DemangleOk) { + return status; + } + if (x > UINT64_MAX / 62) { + return DemangleInvalid; + } + x *= 62; + if (x > UINT64_MAX - d) { + return DemangleInvalid; + } + x += d; + } + if (x == UINT64_MAX) { + return DemangleInvalid; + } + *out = x + 1; + return DemangleOk; +} + +static NODISCARD demangle_status parser_opt_integer_62(struct parser *parser, uint8_t tag, uint64_t *out) { + if (!parser_eat(parser, tag)) { + *out = 0; + return DemangleOk; + } + + demangle_status status; + if ((status = parser_integer_62(parser, out)) != DemangleOk) { + return status; + } + if (*out == UINT64_MAX) { + return DemangleInvalid; + } + *out = *out + 1; + return DemangleOk; +} + +static NODISCARD demangle_status parser_disambiguator(struct parser *parser, uint64_t *out) { + return parser_opt_integer_62(parser, 's', out); +} + +typedef uint8_t parser_namespace_type; + +static NODISCARD demangle_status parser_namespace(struct parser *parser, parser_namespace_type *out) { + uint8_t next = parser_next(parser); + if ('A' <= next && next <= 'Z') { + *out = next; + return DemangleOk; + } else if ('a' <= next && next <= 'z') { + *out = 0; + return DemangleOk; + } else { + return DemangleInvalid; + } +} + +static NODISCARD demangle_status parser_backref(struct parser *parser, struct parser *out) { + size_t start = parser->next; + if (start == 0) { + return DemangleBug; + } + size_t s_start = start - 1; + uint64_t i; + demangle_status status = parser_integer_62(parser, &i); + if (status != DemangleOk) { + return status; + } + if (i >= s_start) { + return DemangleInvalid; + } + struct parser res = { + .sym = parser->sym, + .sym_len = parser->sym_len, + .next = (size_t)i, + .depth = parser->depth + }; + status = parser_push_depth(&res); + if (status != DemangleOk) { + return status; + } + *out = res; + return DemangleOk; +} + +static NODISCARD demangle_status parser_ident(struct parser *parser, struct ident *out) { + bool is_punycode = parser_eat(parser, 'u'); + size_t len; + uint8_t d; + demangle_status status = parser_digit_10(parser, &d); + len = d; + if (status != DemangleOk) { + return status; + } + if (len) { + for (;;) { + status = parser_digit_10(parser, &d); + if (status != DemangleOk) { + break; + } + if (len > SIZE_MAX / 10) { + return DemangleInvalid; + } + len *= 10; + if (len > SIZE_MAX - d) { + return DemangleInvalid; + } + len += d; + } + } + + // Skip past the optional `_` separator. + parser_eat(parser, '_'); + + size_t start = parser->next; + if (parser->sym_len - parser->next < len) { + return DemangleInvalid; + } + parser->next += len; + + const char *ident = &parser->sym[start]; + + if (is_punycode) { + const char *underscore = demangle_memrchr(ident, '_', (size_t)len); + if (underscore == NULL) { + *out = (struct ident){ + .ascii_start="", + .ascii_len=0, + .punycode_start=ident, + .punycode_len=len + }; + } else { + size_t ascii_len = underscore - ident; + // ascii_len <= len - 1 since `_` is in the first len bytes + size_t punycode_len = len - 1 - ascii_len; + *out = (struct ident){ + .ascii_start=ident, + .ascii_len=ascii_len, + .punycode_start=underscore + 1, + .punycode_len=punycode_len + }; + } + if (out->punycode_len == 0) { + return DemangleInvalid; + } + return DemangleOk; + } else { + *out = (struct ident) { + .ascii_start=ident, + .ascii_len=(size_t)len, + .punycode_start="", + .punycode_len=0, + }; + return DemangleOk; + } +} + +#define INVALID_SYNTAX "{invalid syntax}" + +static const char *demangle_error_message(demangle_status status) { + switch (status) { + case DemangleInvalid: + return INVALID_SYNTAX; + case DemangleBug: + return "{bug}"; + case DemangleRecursed: + return "{recursion limit reached}"; + default: + return "{unknown error}"; + } +} + +#define PRINT(print_fn) \ + do { \ + if ((print_fn) == OverflowOverflow) { \ + return OverflowOverflow; \ + } \ + } while(0) + +#define PRINT_CH(printer, s) PRINT(printer_print_ch((printer), (s))) +#define PRINT_STR(printer, s) PRINT(printer_print_str((printer), (s))) +#define PRINT_U64(printer, s) PRINT(printer_print_u64((printer), (s))) +#define PRINT_IDENT(printer, s) PRINT(printer_print_ident((printer), (s))) + +#define INVALID(printer) \ + do { \ + PRINT_STR((printer), INVALID_SYNTAX); \ + (printer)->status = DemangleInvalid; \ + return OverflowOk; \ + } while(0) + +#define PARSE(printer, method, ...) \ + do { \ + if ((printer)->status != DemangleOk) { \ + PRINT_STR((printer), "?"); \ + return OverflowOk; \ + } else { \ + demangle_status _parse_status = method(&(printer)->parser, ## __VA_ARGS__); \ + if (_parse_status != DemangleOk) { \ + PRINT_STR((printer), demangle_error_message(_parse_status)); \ + (printer)->status = _parse_status; \ + return OverflowOk; \ + } \ + } \ + } while(0) + +#define PRINT_SEP_LIST(printer, body, sep) \ + do { \ + size_t _sep_list_i; \ + PRINT_SEP_LIST_COUNT(printer, _sep_list_i, body, sep); \ + } while(0) + +#define PRINT_SEP_LIST_COUNT(printer, count, body, sep) \ + do { \ + count = 0; \ + while ((printer)->status == DemangleOk && !printer_eat((printer), 'E')) { \ + if (count > 0) { PRINT_STR(printer, sep); } \ + body; \ + count++; \ + } \ + } while(0) + +static bool printer_eat(struct printer *printer, uint8_t b) { + if (printer->status != DemangleOk) { + return false; + } + + return parser_eat(&printer->parser, b); +} + +static void printer_pop_depth(struct printer *printer) { + if (printer->status == DemangleOk) { + parser_pop_depth(&printer->parser); + } +} + +static NODISCARD overflow_status printer_print_buf(struct printer *printer, const char *start, size_t len) { + if (printer->out == NULL) { + return OverflowOk; + } + if (printer->out_len < len) { + return OverflowOverflow; + } + + memcpy(printer->out, start, len); + printer->out += len; + printer->out_len -= len; + return OverflowOk; +} + +static NODISCARD overflow_status printer_print_str(struct printer *printer, const char *buf) { + return printer_print_buf(printer, buf, strlen(buf)); +} + +static NODISCARD overflow_status printer_print_ch(struct printer *printer, char ch) { + return printer_print_buf(printer, &ch, 1); +} + +static NODISCARD overflow_status printer_print_u64(struct printer *printer, uint64_t n) { + char buf[32] = {0}; + sprintf(buf, "%llu", (unsigned long long)n); // printing uint64 uses 21 < 32 chars + return printer_print_str(printer, buf); +} + +static NODISCARD overflow_status printer_print_ident(struct printer *printer, struct ident *ident) { + if (printer->out == NULL) { + return OverflowOk; + } + + size_t out_len = printer->out_len; + overflow_status status; + if ((status = display_ident(ident->ascii_start, ident->ascii_len, ident->punycode_start, ident->punycode_len, (uint8_t*)printer->out, &out_len)) != OverflowOk) { + return status; + } + printer->out += out_len; + printer->out_len -= out_len; + return OverflowOk; +} + +typedef overflow_status (*printer_fn)(struct printer *printer); +typedef overflow_status (*backref_fn)(struct printer *printer, bool *arg); + +static NODISCARD overflow_status printer_print_backref(struct printer *printer, backref_fn func, bool *arg) { + struct parser backref; + PARSE(printer, parser_backref, &backref); + + if (printer->out == NULL) { + return OverflowOk; + } + + struct parser orig_parser = printer->parser; + demangle_status orig_status = printer->status; // fixme not sure this is needed match for Ok on the Rust side + printer->parser = backref; + printer->status = DemangleOk; + overflow_status status = func(printer, arg); + printer->parser = orig_parser; + printer->status = orig_status; + + return status; +} + +static NODISCARD overflow_status printer_print_lifetime_from_index(struct printer *printer, uint64_t lt) { + // Bound lifetimes aren't tracked when skipping printing. + if (printer->out == NULL) { + return OverflowOk; + } + + PRINT_STR(printer, "'"); + if (lt == 0) { + PRINT_STR(printer, "_"); + return OverflowOk; + } + + if (printer->bound_lifetime_depth < lt) { + INVALID(printer); + } else { + uint64_t depth = printer->bound_lifetime_depth - lt; + if (depth < 26) { + PRINT_CH(printer, 'a' + depth); + } else { + PRINT_STR(printer, "_"); + PRINT_U64(printer, depth); + } + + return OverflowOk; + } +} + +static NODISCARD overflow_status printer_in_binder(struct printer *printer, printer_fn func) { + uint64_t bound_lifetimes; + PARSE(printer, parser_opt_integer_62, 'G', &bound_lifetimes); + + // Don't track bound lifetimes when skipping printing. + if (printer->out == NULL) { + return func(printer); + } + + if (bound_lifetimes > 0) { + PRINT_STR(printer, "for<"); + for (uint64_t i = 0; i < bound_lifetimes; i++) { + if (i > 0) { + PRINT_STR(printer, ", "); + } + printer->bound_lifetime_depth++; + PRINT(printer_print_lifetime_from_index(printer, 1)); + } + PRINT_STR(printer, "> "); + } + + overflow_status r = func(printer); + printer->bound_lifetime_depth -= bound_lifetimes; + + return r; +} + +static NODISCARD overflow_status printer_print_generic_arg(struct printer *printer) { + if (printer_eat(printer, 'L')) { + uint64_t lt; + PARSE(printer, parser_integer_62, <); + return printer_print_lifetime_from_index(printer, lt); + } else if (printer_eat(printer, 'K')) { + return printer_print_const(printer, false); + } else { + return printer_print_type(printer); + } +} + +static NODISCARD overflow_status printer_print_generic_args(struct printer *printer) { + PRINT_STR(printer, "<"); + PRINT_SEP_LIST(printer, PRINT(printer_print_generic_arg(printer)), ", "); + PRINT_STR(printer, ">"); + return OverflowOk; +} + +static NODISCARD overflow_status printer_print_path_out_of_value(struct printer *printer, bool *_arg) { + (void)_arg; + return printer_print_path(printer, false); +} + +static NODISCARD overflow_status printer_print_path_in_value(struct printer *printer, bool *_arg) { + (void)_arg; + return printer_print_path(printer, true); +} + +static NODISCARD overflow_status printer_print_path(struct printer *printer, bool in_value) { + PARSE(printer, parser_push_depth); + uint8_t tag; + PARSE(printer, parser_ch, &tag); + + overflow_status st; + uint64_t dis; + struct ident name; + parser_namespace_type ns; + char *orig_out; + + switch(tag) { + case 'C': + PARSE(printer, parser_disambiguator, &dis); + PARSE(printer, parser_ident, &name); + + PRINT_IDENT(printer, &name); + + if (printer->out != NULL && !printer->alternate && dis != 0) { + PRINT_STR(printer, "["); + char buf[24] = {0}; + sprintf(buf, "%llx", (unsigned long long)dis); + PRINT_STR(printer, buf); + PRINT_STR(printer, "]"); + } + break; + case 'N': + PARSE(printer, parser_namespace, &ns); + if ((st = printer_print_path(printer, in_value)) != OverflowOk) { + return st; + } + + // HACK(eddyb) if the parser is already marked as having errored, + // `parse!` below will print a `?` without its preceding `::` + // (because printing the `::` is skipped in certain conditions, + // i.e. a lowercase namespace with an empty identifier), + // so in order to get `::?`, the `::` has to be printed here. + if (printer->status != DemangleOk) { + PRINT_STR(printer, "::"); + } + + PARSE(printer, parser_disambiguator, &dis); + PARSE(printer, parser_ident, &name); + // Special namespace, like closures and shims + if (ns) { + PRINT_STR(printer, "::{"); + if (ns == 'C') { + PRINT_STR(printer, "closure"); + } else if (ns == 'S') { + PRINT_STR(printer, "shim"); + } else { + PRINT_CH(printer, ns); + } + if (name.ascii_len != 0 || name.punycode_len != 0) { + PRINT_STR(printer, ":"); + PRINT_IDENT(printer, &name); + } + PRINT_STR(printer, "#"); + PRINT_U64(printer, dis); + PRINT_STR(printer, "}"); + } else { + // Implementation-specific/unspecified namespaces + if (name.ascii_len != 0 || name.punycode_len != 0) { + PRINT_STR(printer, "::"); + PRINT_IDENT(printer, &name); + } + } + break; + case 'M': + case 'X': + // for impls, ignore the impls own path + PARSE(printer, parser_disambiguator, &dis); + orig_out = printer->out; + printer->out = NULL; + PRINT(printer_print_path(printer, false)); + printer->out = orig_out; + + // fallthru + case 'Y': + PRINT_STR(printer, "<"); + PRINT(printer_print_type(printer)); + if (tag != 'M') { + PRINT_STR(printer, " as "); + PRINT(printer_print_path(printer, false)); + } + PRINT_STR(printer, ">"); + break; + case 'I': + PRINT(printer_print_path(printer, in_value)); + if (in_value) { + PRINT_STR(printer, "::"); + } + PRINT(printer_print_generic_args(printer)); + break; + case 'B': + PRINT(printer_print_backref(printer, in_value ? printer_print_path_in_value : printer_print_path_out_of_value, NULL)); + break; + default: + INVALID(printer); + break; + } + + printer_pop_depth(printer); + return OverflowOk; +} + +static NODISCARD overflow_status printer_print_const_uint(struct printer *printer, uint8_t tag) { + struct buf hex; + PARSE(printer, parser_hex_nibbles, &hex); + + uint64_t val; + if (try_parse_uint(hex.start, hex.len, &val)) { + PRINT_U64(printer, val); + } else { + PRINT_STR(printer, "0x"); + PRINT(printer_print_buf(printer, hex.start, hex.len)); + } + + if (printer->out != NULL && !printer->alternate) { + const char *ty = basic_type(tag); + if (/* safety */ ty != NULL) { + PRINT_STR(printer, ty); + } + } + + return OverflowOk; +} + +static NODISCARD overflow_status printer_print_const_str_literal(struct printer *printer) { + struct buf hex; + PARSE(printer, parser_hex_nibbles, &hex); + + size_t out_len = SIZE_MAX; + nibbles_to_string_status nts_status = nibbles_to_string(hex.start, hex.len, NULL, &out_len); + switch (nts_status) { + case NtsOk: + if (printer->out != NULL) { + out_len = printer->out_len; + nts_status = nibbles_to_string(hex.start, hex.len, (uint8_t*)printer->out, &out_len); + if (nts_status != NtsOk) { + return OverflowOverflow; + } + printer->out += out_len; + printer->out_len -= out_len; + } + return OverflowOk; + case NtsOverflow: + // technically if there is a string of size `SIZE_MAX/6` whose escaped version overflows + // SIZE_MAX but has an invalid char, this will be a "fake" overflow. In practice, + // that is not going to happen and a fuzzer will not generate strings of this length. + return OverflowOverflow; + case NtsInvalid: + default: + INVALID(printer); + } +} + +static NODISCARD overflow_status printer_print_const_struct(struct printer *printer) { + uint64_t dis; + struct ident name; + PARSE(printer, parser_disambiguator, &dis); + PARSE(printer, parser_ident, &name); + PRINT_IDENT(printer, &name); + PRINT_STR(printer, ": "); + return printer_print_const(printer, true); +} + +static NODISCARD overflow_status printer_print_const_out_of_value(struct printer *printer, bool *_arg) { + (void)_arg; + return printer_print_const(printer, false); +} + +static NODISCARD overflow_status printer_print_const_in_value(struct printer *printer, bool *_arg) { + (void)_arg; + return printer_print_const(printer, true); +} + +static NODISCARD overflow_status printer_print_const(struct printer *printer, bool in_value) { + uint8_t tag; + + PARSE(printer, parser_ch, &tag); + PARSE(printer, parser_push_depth); + + struct buf hex; + uint64_t val; + size_t count; + + bool opened_brace = false; +#define OPEN_BRACE_IF_OUTSIDE_EXPR \ + do { if (!in_value) { \ + opened_brace = true; \ + PRINT_STR(printer, "{"); \ + } } while(0) + + switch(tag) { + case 'p': + PRINT_STR(printer, "_"); + break; + // Primitive leaves with hex-encoded values (see `basic_type`). + case 'a': + case 's': + case 'l': + case 'x': + case 'n': + case 'i': + if (printer_eat(printer, 'n')) { + PRINT_STR(printer, "-"); + } + /* fallthrough */ + case 'h': + case 't': + case 'm': + case 'y': + case 'o': + case 'j': + PRINT(printer_print_const_uint(printer, tag)); + break; + case 'b': + PARSE(printer, parser_hex_nibbles, &hex); + if (try_parse_uint(hex.start, hex.len, &val)) { + if (val == 0) { + PRINT_STR(printer, "false"); + } else if (val == 1) { + PRINT_STR(printer, "true"); + } else { + INVALID(printer); + } + } else { + INVALID(printer); + } + break; + case 'c': + PARSE(printer, parser_hex_nibbles, &hex); + if (try_parse_uint(hex.start, hex.len, &val) + && val < UINT32_MAX + && validate_char((uint32_t)val)) + { + char escaped_buf[ESCAPED_SIZE]; + size_t escaped_size = char_to_string((uint32_t)val, '\'', true, &escaped_buf); + + PRINT_STR(printer, "'"); + PRINT(printer_print_buf(printer, escaped_buf, escaped_size)); + PRINT_STR(printer, "'"); + } else { + INVALID(printer); + } + break; + case 'e': + OPEN_BRACE_IF_OUTSIDE_EXPR; + PRINT_STR(printer, "*"); + PRINT(printer_print_const_str_literal(printer)); + break; + case 'R': + case 'Q': + if (tag == 'R' && printer_eat(printer, 'e')) { + PRINT(printer_print_const_str_literal(printer)); + } else { + OPEN_BRACE_IF_OUTSIDE_EXPR; + PRINT_STR(printer, "&"); + if (tag != 'R') { + PRINT_STR(printer, "mut "); + } + PRINT(printer_print_const(printer, true)); + } + break; + case 'A': + OPEN_BRACE_IF_OUTSIDE_EXPR; + PRINT_STR(printer, "["); + PRINT_SEP_LIST(printer, PRINT(printer_print_const(printer, true)), ", "); + PRINT_STR(printer, "]"); + break; + case 'T': + OPEN_BRACE_IF_OUTSIDE_EXPR; + PRINT_STR(printer, "("); + PRINT_SEP_LIST_COUNT(printer, count, PRINT(printer_print_const(printer, true)), ", "); + if (count == 1) { + PRINT_STR(printer, ","); + } + PRINT_STR(printer, ")"); + break; + case 'V': + OPEN_BRACE_IF_OUTSIDE_EXPR; + PRINT(printer_print_path(printer, true)); + PARSE(printer, parser_ch, &tag); + switch(tag) { + case 'U': + break; + case 'T': + PRINT_STR(printer, "("); + PRINT_SEP_LIST(printer, PRINT(printer_print_const(printer, true)), ", "); + PRINT_STR(printer, ")"); + break; + case 'S': + PRINT_STR(printer, " { "); + PRINT_SEP_LIST(printer, PRINT(printer_print_const_struct(printer)), ", "); + PRINT_STR(printer, " }"); + break; + default: + INVALID(printer); + } + break; + case 'B': + PRINT(printer_print_backref(printer, in_value ? printer_print_const_in_value : printer_print_const_out_of_value, NULL)); + break; + default: + INVALID(printer); + } +#undef OPEN_BRACE_IF_OUTSIDE_EXPR + + if (opened_brace) { + PRINT_STR(printer, "}"); + } + printer_pop_depth(printer); + + return OverflowOk; +} + +/// A trait in a trait object may have some "existential projections" +/// (i.e. associated type bindings) after it, which should be printed +/// in the `<...>` of the trait, e.g. `dyn Trait<T, U, Assoc=X>`. +/// To this end, this method will keep the `<...>` of an 'I' path +/// open, by omitting the `>`, and return `Ok(true)` in that case. +static NODISCARD overflow_status printer_print_maybe_open_generics(struct printer *printer, bool *open) { + if (printer_eat(printer, 'B')) { + // NOTE(eddyb) the closure may not run if printing is being skipped, + // but in that case the returned boolean doesn't matter. + *open = false; + return printer_print_backref(printer, printer_print_maybe_open_generics, open); + } else if(printer_eat(printer, 'I')) { + PRINT(printer_print_path(printer, false)); + PRINT_STR(printer, "<"); + PRINT_SEP_LIST(printer, PRINT(printer_print_generic_arg(printer)), ", "); + *open = true; + return OverflowOk; + } else { + PRINT(printer_print_path(printer, false)); + *open = false; + return OverflowOk; + } +} + +static NODISCARD overflow_status printer_print_dyn_trait(struct printer *printer) { + bool open; + PRINT(printer_print_maybe_open_generics(printer, &open)); + + while (printer_eat(printer, 'p')) { + if (!open) { + PRINT_STR(printer, "<"); + open = true; + } else { + PRINT_STR(printer, ", "); + } + + struct ident name; + PARSE(printer, parser_ident, &name); + + PRINT_IDENT(printer, &name); + PRINT_STR(printer, " = "); + PRINT(printer_print_type(printer)); + } + + if (open) { + PRINT_STR(printer, ">"); + } + + return OverflowOk; +} + +static NODISCARD overflow_status printer_print_object_bounds(struct printer *printer) { + PRINT_SEP_LIST(printer, PRINT(printer_print_dyn_trait(printer)), " + "); + return OverflowOk; +} + +static NODISCARD overflow_status printer_print_function_type(struct printer *printer) { + bool is_unsafe = printer_eat(printer, 'U'); + const char *abi; + size_t abi_len; + if (printer_eat(printer, 'K')) { + if (printer_eat(printer, 'C')) { + abi = "C"; + abi_len = 1; + } else { + struct ident abi_ident; + PARSE(printer, parser_ident, &abi_ident); + if (abi_ident.ascii_len == 0 || abi_ident.punycode_len != 0) { + INVALID(printer); + } + abi = abi_ident.ascii_start; + abi_len = abi_ident.ascii_len; + } + } else { + abi = NULL; + abi_len = 0; + } + + if (is_unsafe) { + PRINT_STR(printer, "unsafe "); + } + + if (abi != NULL) { + PRINT_STR(printer, "extern \""); + + // replace _ with - + while (abi_len > 0) { + const char *minus = memchr(abi, '_', abi_len); + if (minus == NULL) { + PRINT(printer_print_buf(printer, (const char*)abi, abi_len)); + break; + } else { + size_t space_to_minus = minus - abi; + PRINT(printer_print_buf(printer, (const char*)abi, space_to_minus)); + PRINT_STR(printer, "-"); + abi = minus + 1; + abi_len -= (space_to_minus + 1); + } + } + + PRINT_STR(printer, "\" "); + } + + PRINT_STR(printer, "fn("); + PRINT_SEP_LIST(printer, PRINT(printer_print_type(printer)), ", "); + PRINT_STR(printer, ")"); + + if (printer_eat(printer, 'u')) { + // Skip printing the return type if it's 'u', i.e. `()`. + } else { + PRINT_STR(printer, " -> "); + PRINT(printer_print_type(printer)); + } + + return OverflowOk; +} + +static NODISCARD overflow_status printer_print_type_backref(struct printer *printer, bool *_arg) { + (void)_arg; + return printer_print_type(printer); +} + +static NODISCARD overflow_status printer_print_type(struct printer *printer) { + uint8_t tag; + PARSE(printer, parser_ch, &tag); + + const char *basic_ty = basic_type(tag); + if (basic_ty) { + return printer_print_str(printer, basic_ty); + } + + uint64_t count; + uint64_t lt; + + PARSE(printer, parser_push_depth); + switch (tag) { + case 'R': + case 'Q': + PRINT_STR(printer, "&"); + if (printer_eat(printer, 'L')) { + PARSE(printer, parser_integer_62, <); + if (lt != 0) { + PRINT(printer_print_lifetime_from_index(printer, lt)); + PRINT_STR(printer, " "); + } + } + if (tag != 'R') { + PRINT_STR(printer, "mut "); + } + PRINT(printer_print_type(printer)); + break; + case 'P': + case 'O': + PRINT_STR(printer, "*"); + if (tag != 'P') { + PRINT_STR(printer, "mut "); + } else { + PRINT_STR(printer, "const "); + } + PRINT(printer_print_type(printer)); + break; + case 'A': + case 'S': + PRINT_STR(printer, "["); + PRINT(printer_print_type(printer)); + if (tag == 'A') { + PRINT_STR(printer, "; "); + PRINT(printer_print_const(printer, true)); + } + PRINT_STR(printer, "]"); + break; + case 'T': + PRINT_STR(printer, "("); + PRINT_SEP_LIST_COUNT(printer, count, PRINT(printer_print_type(printer)), ", "); + if (count == 1) { + PRINT_STR(printer, ","); + } + PRINT_STR(printer, ")"); + break; + case 'F': + PRINT(printer_in_binder(printer, printer_print_function_type)); + break; + case 'D': + PRINT_STR(printer, "dyn "); + PRINT(printer_in_binder(printer, printer_print_object_bounds)); + + if (!printer_eat(printer, 'L')) { + INVALID(printer); + } + PARSE(printer, parser_integer_62, <); + + if (lt != 0) { + PRINT_STR(printer, " + "); + PRINT(printer_print_lifetime_from_index(printer, lt)); + } + break; + case 'B': + PRINT(printer_print_backref(printer, printer_print_type_backref, NULL)); + break; + default: + // Go back to the tag, so `print_path` also sees it. + if (printer->status == DemangleOk && /* safety */ printer->parser.next > 0) { + printer->parser.next--; + } + PRINT(printer_print_path(printer, false)); + } + + printer_pop_depth(printer); + return OverflowOk; +} + +NODISCARD static demangle_status rust_demangle_legacy_demangle(const char *s, size_t s_len, struct demangle_legacy *res, const char **rest) +{ + if (s_len > strlen(s)) { + // s_len only exists to shorten the string, this is not a buffer API + return DemangleInvalid; + } + + const char *inner; + size_t inner_len; + if (s_len >= 3 && !strncmp(s, "_ZN", 3)) { + inner = s + 3; + inner_len = s_len - 3; + } else if (s_len >= 2 && !strncmp(s, "ZN", 2)) { + // On Windows, dbghelp strips leading underscores, so we accept "ZN...E" + // form too. + inner = s + 2; + inner_len = s_len - 2; + } else if (s_len >= 4 && !strncmp(s, "__ZN", 4)) { + // On OSX, symbols are prefixed with an extra _ + inner = s + 4; + inner_len = s_len - 4; + } else { + return DemangleInvalid; + } + + if (!str_isascii(inner, inner_len)) { + return DemangleInvalid; + } + + size_t elements = 0; + const char *chars = inner; + size_t chars_len = inner_len; + if (chars_len == 0) { + return DemangleInvalid; + } + char c; + while ((c = *chars) != 'E') { + // Decode an identifier element's length + if (c < '0' || c > '9') { + return DemangleInvalid; + } + size_t len = 0; + while (c >= '0' && c <= '9') { + size_t d = c - '0'; + if (len > SIZE_MAX / 10) { + return DemangleInvalid; + } + len *= 10; + if (len > SIZE_MAX - d) { + return DemangleInvalid; + } + len += d; + + chars++; + chars_len--; + if (chars_len == 0) { + return DemangleInvalid; + } + c = *chars; + } + + // Advance by the length + if (chars_len <= len) { + return DemangleInvalid; + } + chars += len; + chars_len -= len; + elements++; + } + *res = (struct demangle_legacy) { inner, inner_len, elements }; + *rest = chars + 1; + return DemangleOk; +} + +static bool is_rust_hash(const char *s, size_t len) { + if (len == 0 || s[0] != 'h') { + return false; + } + + for (size_t i = 1; i < len; i++) { + if (!((s[i] >= '0' && s[i] <= '9') || (s[i] >= 'a' && s[i] <= 'f') || (s[i] >= 'A' && s[i] <= 'F'))) { + return false; + } + } + + return true; +} + +NODISCARD static overflow_status rust_demangle_legacy_display_demangle(struct demangle_legacy res, char *out, size_t len, bool alternate) +{ + struct printer printer = { + // not actually using the parser part of the printer, just keeping it to share the format functions + DemangleOk, + { NULL }, + out, + len, + 0, + alternate + }; + const char *inner = res.mangled; + for (size_t element = 0; element < res.elements; element++) { + size_t i = 0; + const char *rest; + for (rest = inner; rest < res.mangled + res.mangled_len && *rest >= '0' && *rest <= '9'; rest++) { + i *= 10; + i += *rest - '0'; + } + if ((size_t)(res.mangled + res.mangled_len - rest) < i) { + // safety: shouldn't reach this place if the input string is validated. bail out. + // safety: we knwo rest <= res.mangled + res.mangled_len from the for-loop above + break; + } + + size_t len = i; + inner = rest + len; + + // From here on, inner contains a pointer to the next element, rest[:len] to the current one + if (alternate && element + 1 == res.elements && is_rust_hash(rest, i)) { + break; + } + if (element != 0) { + PRINT_STR(&printer, "::"); + } + + if (len >= 2 && !strncmp(rest, "_$", 2)) { + rest++; + len--; + } + + while (len > 0) { + if (rest[0] == '.') { + if (len >= 2 && rest[1] == '.') { + PRINT_STR(&printer, "::"); + rest += 2; + len -= 2; + } else { + PRINT_STR(&printer, "."); + rest += 1; + len -= 1; + } + } else if (rest[0] == '$') { + const char *escape = memchr(rest + 1, '$', len - 1); + if (escape == NULL) { + break; + } + const char *escape_start = rest + 1; + size_t escape_len = escape - (rest + 1); + + size_t next_len = len - (escape + 1 - rest); + const char *next_rest = escape + 1; + + char ch; + if ((escape_len == 2 && escape_start[0] == 'S' && escape_start[1] == 'P')) { + ch = '@'; + } else if ((escape_len == 2 && escape_start[0] == 'B' && escape_start[1] == 'P')) { + ch = '*'; + } else if ((escape_len == 2 && escape_start[0] == 'R' && escape_start[1] == 'F')) { + ch = '&'; + } else if ((escape_len == 2 && escape_start[0] == 'L' && escape_start[1] == 'T')) { + ch = '<'; + } else if ((escape_len == 2 && escape_start[0] == 'G' && escape_start[1] == 'T')) { + ch = '>'; + } else if ((escape_len == 2 && escape_start[0] == 'L' && escape_start[1] == 'P')) { + ch = '('; + } else if ((escape_len == 2 && escape_start[0] == 'R' && escape_start[1] == 'P')) { + ch = ')'; + } else if ((escape_len == 1 && escape_start[0] == 'C')) { + ch = ','; + } else { + if (escape_len > 1 && escape_start[0] == 'u') { + escape_start++; + escape_len--; + uint64_t val; + if (try_parse_uint(escape_start, escape_len, &val) + && val < UINT32_MAX + && validate_char((uint32_t)val)) + { + if (!unicode_iscontrol(val)) { + uint8_t wchr[4]; + size_t wchr_len = code_to_utf8(wchr, (uint32_t)val); + PRINT(printer_print_buf(&printer, (const char*)wchr, wchr_len)); + len = next_len; + rest = next_rest; + continue; + } + } + } + break; // print the rest of this element raw + } + PRINT_CH(&printer, ch); + len = next_len; + rest = next_rest; + } else { + size_t j = 0; + for (;j < len && rest[j] != '$' && rest[j] != '.';j++); + if (j == len) { + break; + } + PRINT(printer_print_buf(&printer, rest, j)); + rest += j; + len -= j; + } + } + PRINT(printer_print_buf(&printer, rest, len)); + } + + if (printer.out_len < OVERFLOW_MARGIN) { + return OverflowOverflow; + } + *printer.out = '\0'; + return OverflowOk; +} + +static bool is_symbol_like(const char *s, size_t len) { + // rust-demangle definition of symbol like: control characters and space are not symbol-like, all else is + for (size_t i = 0; i < len; i++) { + char ch = s[i]; + if (!(ch >= 0x21 && ch <= 0x7e)) { + return false; + } + } + return true; +} + +void rust_demangle_demangle(const char *s, struct demangle *res) +{ + // During ThinLTO LLVM may import and rename internal symbols, so strip out + // those endings first as they're one of the last manglings applied to symbol + // names. + const char *llvm = ".llvm."; + const char *found_llvm = strstr(s, llvm); + size_t s_len = strlen(s); + if (found_llvm) { + const char *all_hex_ptr = found_llvm + strlen(".llvm."); + bool all_hex = true; + for (;*all_hex_ptr;all_hex_ptr++) { + if (!(('0' <= *all_hex_ptr && *all_hex_ptr <= '9') || + ('A' <= *all_hex_ptr && *all_hex_ptr <= 'F') || + *all_hex_ptr == '@')) { + all_hex = false; + break; + } + } + + if (all_hex) { + s_len = found_llvm - s; + } + } + + const char *suffix; + struct demangle_legacy legacy; + demangle_status st = rust_demangle_legacy_demangle(s, s_len, &legacy, &suffix); + if (st == DemangleOk) { + *res = (struct demangle) { + .style=DemangleStyleLegacy, + .mangled=legacy.mangled, + .mangled_len=legacy.mangled_len, + .elements=legacy.elements, + .original=s, + .original_len=s_len, + .suffix=suffix, + .suffix_len=s_len - (suffix - s), + }; + } else { + struct demangle_v0 v0; + st = rust_demangle_v0_demangle(s, s_len, &v0, &suffix); + if (st == DemangleOk) { + *res = (struct demangle) { + .style=DemangleStyleV0, + .mangled=v0.mangled, + .mangled_len=v0.mangled_len, + .elements=0, + .original=s, + .original_len=s_len, + .suffix=suffix, + .suffix_len=s_len - (suffix - s), + }; + } else { + *res = (struct demangle) { + .style=DemangleStyleUnknown, + .mangled=NULL, + .mangled_len=0, + .elements=0, + .original=s, + .original_len=s_len, + .suffix=s, + .suffix_len=0, + }; + } + } + + // Output like LLVM IR adds extra period-delimited words. See if + // we are in that case and save the trailing words if so. + if (res->suffix_len) { + if (res->suffix[0] == '.' && is_symbol_like(res->suffix, res->suffix_len)) { + // Keep the suffix + } else { + // Reset the suffix and invalidate the demangling + res->style = DemangleStyleUnknown; + res->suffix_len = 0; + } + } +} + +bool rust_demangle_is_known(struct demangle *res) { + return res->style != DemangleStyleUnknown; +} + +overflow_status rust_demangle_display_demangle(struct demangle const *res, char *out, size_t len, bool alternate) { + size_t original_len = res->original_len; + size_t out_len; + switch (res->style) { + case DemangleStyleUnknown: + if (len < original_len) { + return OverflowOverflow; + } else { + memcpy(out, res->original, original_len); + out += original_len; + len -= original_len; + break; + } + break; + case DemangleStyleLegacy: { + struct demangle_legacy legacy = { + res->mangled, + res->mangled_len, + res->elements + }; + if (rust_demangle_legacy_display_demangle(legacy, out, len, alternate) == OverflowOverflow) { + return OverflowOverflow; + } + out_len = strlen(out); + out += out_len; + len -= out_len; + break; + } + case DemangleStyleV0: { + struct demangle_v0 v0 = { + res->mangled, + res->mangled_len + }; + if (rust_demangle_v0_display_demangle(v0, out, len, alternate) == OverflowOverflow) { + return OverflowOverflow; + } + out_len = strlen(out); + out += out_len; + len -= out_len; + break; + } + } + size_t suffix_len = res->suffix_len; + if (len < suffix_len || len - suffix_len < OVERFLOW_MARGIN) { + return OverflowOverflow; + } + memcpy(out, res->suffix, suffix_len); + out[suffix_len] = 0; + return OverflowOk; +} diff --git a/tools/perf/util/demangle-rust-v0.h b/tools/perf/util/demangle-rust-v0.h new file mode 100644 index 000000000000..d0092818610a --- /dev/null +++ b/tools/perf/util/demangle-rust-v0.h @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +// The contents of this file come from the Rust rustc-demangle library, hosted +// in the <https://github.com/rust-lang/rustc-demangle> repository, licensed +// under "Apache-2.0 OR MIT". For copyright details, see +// <https://github.com/rust-lang/rustc-demangle/blob/main/README.md>. +// Please note that the file should be kept as close as possible to upstream. + +#ifndef _H_DEMANGLE_V0_H +#define _H_DEMANGLE_V0_H + +#ifdef __cplusplus +extern "C" { +#endif + +#include <stddef.h> + +#if defined(__GNUC__) || defined(__clang__) +#define DEMANGLE_NODISCARD __attribute__((warn_unused_result)) +#else +#define DEMANGLE_NODISCARD +#endif + +typedef enum { + OverflowOk, + OverflowOverflow +} overflow_status; + +enum demangle_style { + DemangleStyleUnknown = 0, + DemangleStyleLegacy, + DemangleStyleV0, +}; + +// Not using a union here to make the struct easier to copy-paste if needed. +struct demangle { + enum demangle_style style; + // points to the "mangled" part of the name, + // not including `ZN` or `R` prefixes. + const char *mangled; + size_t mangled_len; + // In DemangleStyleLegacy, is the number of path elements + size_t elements; + // while it's called "original", it will not contain `.llvm.9D1C9369@@16` suffixes + // that are to be ignored. + const char *original; + size_t original_len; + // Contains the part after the mangled name that is to be outputted, + // which can be `.exit.i.i` suffixes LLVM sometimes adds. + const char *suffix; + size_t suffix_len; +}; + +// if the length of the output buffer is less than `output_len-OVERFLOW_MARGIN`, +// the demangler will return `OverflowOverflow` even if there is no overflow. +#define OVERFLOW_MARGIN 4 + +/// Demangle a C string that refers to a Rust symbol and put the demangle intermediate result in `res`. +/// Beware that `res` contains references into `s`. If `s` is modified (or free'd) before calling +/// `rust_demangle_display_demangle` behavior is undefined. +/// +/// Use `rust_demangle_display_demangle` to convert it to an actual string. +void rust_demangle_demangle(const char *s, struct demangle *res); + +/// Write the string in a `struct demangle` into a buffer. +/// +/// Return `OverflowOk` if the output buffer was sufficiently big, `OverflowOverflow` if it wasn't. +/// This function is `O(n)` in the length of the input + *output* [$], but the demangled output of demangling a symbol can +/// be exponentially[$$] large, therefore it is recommended to have a sane bound (`rust-demangle` +/// uses 1,000,000 bytes) on `len`. +/// +/// `alternate`, if true, uses the less verbose alternate formatting (Rust `{:#}`) is used, which does not show +/// symbol hashes and types of constant ints. +/// +/// [$] It's `O(n * MAX_DEPTH)`, but `MAX_DEPTH` is a constant 300 and therefore it's `O(n)` +/// [$$] Technically, bounded by `O(n^MAX_DEPTH)`, but this is practically exponential. +DEMANGLE_NODISCARD overflow_status rust_demangle_display_demangle(struct demangle const *res, char *out, size_t len, bool alternate); + +/// Returns true if `res` refers to a known valid Rust demangling style, false if it's an unknown style. +bool rust_demangle_is_known(struct demangle *res); + +#undef DEMANGLE_NODISCARD + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c deleted file mode 100644 index a659fc69f73a..000000000000 --- a/tools/perf/util/demangle-rust.c +++ /dev/null @@ -1,269 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <string.h> -#include "debug.h" - -#include "demangle-rust.h" - -/* - * Mangled Rust symbols look like this: - * - * _$LT$std..sys..fd..FileDesc$u20$as$u20$core..ops..Drop$GT$::drop::hc68340e1baa4987a - * - * The original symbol is: - * - * <std::sys::fd::FileDesc as core::ops::Drop>::drop - * - * The last component of the path is a 64-bit hash in lowercase hex, prefixed - * with "h". Rust does not have a global namespace between crates, an illusion - * which Rust maintains by using the hash to distinguish things that would - * otherwise have the same symbol. - * - * Any path component not starting with a XID_Start character is prefixed with - * "_". - * - * The following escape sequences are used: - * - * "," => $C$ - * "@" => $SP$ - * "*" => $BP$ - * "&" => $RF$ - * "<" => $LT$ - * ">" => $GT$ - * "(" => $LP$ - * ")" => $RP$ - * " " => $u20$ - * "'" => $u27$ - * "[" => $u5b$ - * "]" => $u5d$ - * "~" => $u7e$ - * - * A double ".." means "::" and a single "." means "-". - * - * The only characters allowed in the mangled symbol are a-zA-Z0-9 and _.:$ - */ - -static const char *hash_prefix = "::h"; -static const size_t hash_prefix_len = 3; -static const size_t hash_len = 16; - -static bool is_prefixed_hash(const char *start); -static bool looks_like_rust(const char *sym, size_t len); -static bool unescape(const char **in, char **out, const char *seq, char value); - -/* - * INPUT: - * sym: symbol that has been through BFD-demangling - * - * This function looks for the following indicators: - * - * 1. The hash must consist of "h" followed by 16 lowercase hex digits. - * - * 2. As a sanity check, the hash must use between 5 and 15 of the 16 possible - * hex digits. This is true of 99.9998% of hashes so once in your life you - * may see a false negative. The point is to notice path components that - * could be Rust hashes but are probably not, like "haaaaaaaaaaaaaaaa". In - * this case a false positive (non-Rust symbol has an important path - * component removed because it looks like a Rust hash) is worse than a - * false negative (the rare Rust symbol is not demangled) so this sets the - * balance in favor of false negatives. - * - * 3. There must be no characters other than a-zA-Z0-9 and _.:$ - * - * 4. There must be no unrecognized $-sign sequences. - * - * 5. There must be no sequence of three or more dots in a row ("..."). - */ -bool -rust_is_mangled(const char *sym) -{ - size_t len, len_without_hash; - - if (!sym) - return false; - - len = strlen(sym); - if (len <= hash_prefix_len + hash_len) - /* Not long enough to contain "::h" + hash + something else */ - return false; - - len_without_hash = len - (hash_prefix_len + hash_len); - if (!is_prefixed_hash(sym + len_without_hash)) - return false; - - return looks_like_rust(sym, len_without_hash); -} - -/* - * A hash is the prefix "::h" followed by 16 lowercase hex digits. The hex - * digits must comprise between 5 and 15 (inclusive) distinct digits. - */ -static bool is_prefixed_hash(const char *str) -{ - const char *end; - bool seen[16]; - size_t i; - int count; - - if (strncmp(str, hash_prefix, hash_prefix_len)) - return false; - str += hash_prefix_len; - - memset(seen, false, sizeof(seen)); - for (end = str + hash_len; str < end; str++) - if (*str >= '0' && *str <= '9') - seen[*str - '0'] = true; - else if (*str >= 'a' && *str <= 'f') - seen[*str - 'a' + 10] = true; - else - return false; - - /* Count how many distinct digits seen */ - count = 0; - for (i = 0; i < 16; i++) - if (seen[i]) - count++; - - return count >= 5 && count <= 15; -} - -static bool looks_like_rust(const char *str, size_t len) -{ - const char *end = str + len; - - while (str < end) - switch (*str) { - case '$': - if (!strncmp(str, "$C$", 3)) - str += 3; - else if (!strncmp(str, "$SP$", 4) - || !strncmp(str, "$BP$", 4) - || !strncmp(str, "$RF$", 4) - || !strncmp(str, "$LT$", 4) - || !strncmp(str, "$GT$", 4) - || !strncmp(str, "$LP$", 4) - || !strncmp(str, "$RP$", 4)) - str += 4; - else if (!strncmp(str, "$u20$", 5) - || !strncmp(str, "$u27$", 5) - || !strncmp(str, "$u5b$", 5) - || !strncmp(str, "$u5d$", 5) - || !strncmp(str, "$u7e$", 5)) - str += 5; - else - return false; - break; - case '.': - /* Do not allow three or more consecutive dots */ - if (!strncmp(str, "...", 3)) - return false; - /* Fall through */ - case 'a' ... 'z': - case 'A' ... 'Z': - case '0' ... '9': - case '_': - case ':': - str++; - break; - default: - return false; - } - - return true; -} - -/* - * INPUT: - * sym: symbol for which rust_is_mangled(sym) returns true - * - * The input is demangled in-place because the mangled name is always longer - * than the demangled one. - */ -void -rust_demangle_sym(char *sym) -{ - const char *in; - char *out; - const char *end; - - if (!sym) - return; - - in = sym; - out = sym; - end = sym + strlen(sym) - (hash_prefix_len + hash_len); - - while (in < end) - switch (*in) { - case '$': - if (!(unescape(&in, &out, "$C$", ',') - || unescape(&in, &out, "$SP$", '@') - || unescape(&in, &out, "$BP$", '*') - || unescape(&in, &out, "$RF$", '&') - || unescape(&in, &out, "$LT$", '<') - || unescape(&in, &out, "$GT$", '>') - || unescape(&in, &out, "$LP$", '(') - || unescape(&in, &out, "$RP$", ')') - || unescape(&in, &out, "$u20$", ' ') - || unescape(&in, &out, "$u27$", '\'') - || unescape(&in, &out, "$u5b$", '[') - || unescape(&in, &out, "$u5d$", ']') - || unescape(&in, &out, "$u7e$", '~'))) { - pr_err("demangle-rust: unexpected escape sequence"); - goto done; - } - break; - case '_': - /* - * If this is the start of a path component and the next - * character is an escape sequence, ignore the - * underscore. The mangler inserts an underscore to make - * sure the path component begins with a XID_Start - * character. - */ - if ((in == sym || in[-1] == ':') && in[1] == '$') - in++; - else - *out++ = *in++; - break; - case '.': - if (in[1] == '.') { - /* ".." becomes "::" */ - *out++ = ':'; - *out++ = ':'; - in += 2; - } else { - /* "." becomes "-" */ - *out++ = '-'; - in++; - } - break; - case 'a' ... 'z': - case 'A' ... 'Z': - case '0' ... '9': - case ':': - *out++ = *in++; - break; - default: - pr_err("demangle-rust: unexpected character '%c' in symbol\n", - *in); - goto done; - } - -done: - *out = '\0'; -} - -static bool unescape(const char **in, char **out, const char *seq, char value) -{ - size_t len = strlen(seq); - - if (strncmp(*in, seq, len)) - return false; - - **out = value; - - *in += len; - *out += 1; - - return true; -} diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h deleted file mode 100644 index 2fca618b1aa5..000000000000 --- a/tools/perf/util/demangle-rust.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERF_DEMANGLE_RUST -#define __PERF_DEMANGLE_RUST 1 - -bool rust_is_mangled(const char *str); -void rust_demangle_sym(char *str); - -#endif /* __PERF_DEMANGLE_RUST */ diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index 50c5c206b70e..59ba88e1f744 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -1,5 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only #include <ctype.h> +#include <elf.h> +#ifndef EF_CSKY_ABIMASK +#define EF_CSKY_ABIMASK 0XF0000000 +#endif #include <errno.h> #include <fcntl.h> #include <inttypes.h> @@ -9,47 +13,45 @@ #include <unistd.h> #include <linux/string.h> +#include <linux/zalloc.h> #include <subcmd/run-command.h> #include "annotate.h" #include "annotate-data.h" #include "build-id.h" +#include "capstone.h" #include "debug.h" #include "disasm.h" -#include "disasm_bpf.h" #include "dso.h" #include "dwarf-regs.h" #include "env.h" #include "evsel.h" +#include "libbfd.h" +#include "llvm.h" #include "map.h" #include "maps.h" #include "namespaces.h" #include "srcline.h" #include "symbol.h" +#include "thread.h" #include "util.h" static regex_t file_lineno; /* These can be referred from the arch-dependent code */ -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 struct ins_ops load_store_ops; -static struct ins_ops arithmetic_ops; - -static int jump__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name); -static int call__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name); +const struct ins_ops call_ops; +const struct ins_ops dec_ops; +const struct ins_ops jump_ops; +const struct ins_ops mov_ops; +const struct ins_ops nop_ops; +const struct ins_ops lock_ops; +const struct ins_ops ret_ops; +const struct ins_ops load_store_ops; +const struct ins_ops arithmetic_ops; static void ins__sort(struct arch *arch); static int disasm_line__parse(char *line, const char **namep, char **rawp); -static int disasm_line__parse_powerpc(struct disasm_line *dl); -static char *expand_tabs(char *line, char **storage, size_t *storage_len); +static int disasm_line__parse_powerpc(struct disasm_line *dl, struct annotate_args *args); static __attribute__((constructor)) void symbol__init_regexpr(void) { @@ -65,7 +67,8 @@ static int arch__grow_instructions(struct arch *arch) 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)); + new_instructions = realloc((void *)arch->instructions, + new_nr_allocated * sizeof(struct ins)); if (new_instructions == NULL) return -1; @@ -80,11 +83,11 @@ grow_from_non_allocated_table: if (new_instructions == NULL) return -1; - memcpy(new_instructions, arch->instructions, arch->nr_instructions); + memcpy(new_instructions, arch->instructions, arch->nr_instructions * sizeof(struct ins)); goto out_update_instructions; } -static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops) +int arch__associate_ins_ops(struct arch *arch, const char *name, const struct ins_ops *ops) { struct ins *ins; @@ -92,7 +95,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i arch__grow_instructions(arch)) return -1; - ins = &arch->instructions[arch->nr_instructions]; + ins = (struct ins *)&arch->instructions[arch->nr_instructions]; ins->name = strdup(name); if (!ins->name) return -1; @@ -104,130 +107,100 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i return 0; } -#include "arch/arc/annotate/instructions.c" -#include "arch/arm/annotate/instructions.c" -#include "arch/arm64/annotate/instructions.c" -#include "arch/csky/annotate/instructions.c" -#include "arch/loongarch/annotate/instructions.c" -#include "arch/mips/annotate/instructions.c" -#include "arch/x86/annotate/instructions.c" -#include "arch/powerpc/annotate/instructions.c" -#include "arch/riscv64/annotate/instructions.c" -#include "arch/s390/annotate/instructions.c" -#include "arch/sparc/annotate/instructions.c" - -static struct arch architectures[] = { - { - .name = "arc", - .init = arc__annotate_init, - }, - { - .name = "arm", - .init = arm__annotate_init, - }, - { - .name = "arm64", - .init = arm64__annotate_init, - }, - { - .name = "csky", - .init = csky__annotate_init, - }, - { - .name = "mips", - .init = mips__annotate_init, - .objdump = { - .comment_char = '#', - }, - }, - { - .name = "x86", - .init = x86__annotate_init, - .instructions = x86__instructions, - .nr_instructions = ARRAY_SIZE(x86__instructions), - .insn_suffix = "bwlq", - .objdump = { - .comment_char = '#', - .register_char = '%', - .memory_ref_char = '(', - .imm_char = '$', - }, -#ifdef HAVE_LIBDW_SUPPORT - .update_insn_state = update_insn_state_x86, -#endif - }, - { - .name = "powerpc", - .init = powerpc__annotate_init, -#ifdef HAVE_LIBDW_SUPPORT - .update_insn_state = update_insn_state_powerpc, -#endif - }, - { - .name = "riscv64", - .init = riscv64__annotate_init, - }, - { - .name = "s390", - .init = s390__annotate_init, - .objdump = { - .comment_char = '#', - }, - }, - { - .name = "sparc", - .init = sparc__annotate_init, - .objdump = { - .comment_char = '#', - }, - }, - { - .name = "loongarch", - .init = loongarch__annotate_init, - .objdump = { - .comment_char = '#', - }, - }, -}; +static int e_machine_and_eflags__cmp(const struct e_machine_and_e_flags *val1, + const struct e_machine_and_e_flags *val2) +{ + if (val1->e_machine == val2->e_machine) { + if (val1->e_machine != EM_CSKY) + return 0; + if ((val1->e_flags & EF_CSKY_ABIMASK) < (val2->e_flags & EF_CSKY_ABIMASK)) + return -1; + return (val1->e_flags & EF_CSKY_ABIMASK) > (val2->e_flags & EF_CSKY_ABIMASK); + } + return val1->e_machine < val2->e_machine ? -1 : 1; +} -static int arch__key_cmp(const void *name, const void *archp) +static int arch__key_cmp(const void *key, const void *archp) { - const struct arch *arch = archp; + const struct arch *const *arch = archp; - return strcmp(name, arch->name); + return e_machine_and_eflags__cmp(key, &(*arch)->id); } static int arch__cmp(const void *a, const void *b) { - const struct arch *aa = a; - const struct arch *ab = b; + const struct arch *const *aa = a; + const struct arch *const *ab = b; + + return e_machine_and_eflags__cmp(&(*aa)->id, &(*ab)->id); +} + +const struct arch *arch__find(uint16_t e_machine, uint32_t e_flags, const char *cpuid) +{ + static const struct arch *(*const arch_new_fn[])(const struct e_machine_and_e_flags *id, + const char *cpuid) = { + [EM_386] = arch__new_x86, + [EM_ARC] = arch__new_arc, + [EM_ARM] = arch__new_arm, + [EM_AARCH64] = arch__new_arm64, + [EM_CSKY] = arch__new_csky, + [EM_LOONGARCH] = arch__new_loongarch, + [EM_MIPS] = arch__new_mips, + [EM_PPC64] = arch__new_powerpc, + [EM_PPC] = arch__new_powerpc, + [EM_RISCV] = arch__new_riscv64, + [EM_S390] = arch__new_s390, + [EM_SPARC] = arch__new_sparc, + [EM_SPARCV9] = arch__new_sparc, + [EM_X86_64] = arch__new_x86, + }; + static const struct arch **archs; + static size_t num_archs; + struct e_machine_and_e_flags key = { + .e_machine = e_machine, + .e_flags = e_flags, + }; + const struct arch *result = NULL, **tmp; - return strcmp(aa->name, ab->name); -} + if (num_archs > 0) { + tmp = bsearch(&key, archs, num_archs, sizeof(*archs), arch__key_cmp); + if (tmp) + result = *tmp; + } -static void arch__sort(void) -{ - const int nmemb = ARRAY_SIZE(architectures); + if (result) + return result; - qsort(architectures, nmemb, sizeof(struct arch), arch__cmp); -} + if (e_machine >= ARRAY_SIZE(arch_new_fn) || arch_new_fn[e_machine] == NULL) { + errno = ENOTSUP; + return NULL; + } -struct arch *arch__find(const char *name) -{ - const int nmemb = ARRAY_SIZE(architectures); - static bool sorted; + tmp = reallocarray(archs, num_archs + 1, sizeof(*archs)); + if (!tmp) + return NULL; - if (!sorted) { - arch__sort(); - sorted = true; + result = arch_new_fn[e_machine](&key, cpuid); + if (!result) { + pr_err("%s: failed to initialize %s (%u) arch priv area\n", + __func__, result->name, e_machine); + free(tmp); + return NULL; } + archs = tmp; + archs[num_archs++] = result; + qsort(archs, num_archs, sizeof(*archs), arch__cmp); + return result; +} - return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp); +bool arch__is_x86(const struct arch *arch) +{ + return arch->id.e_machine == EM_386 || arch->id.e_machine == EM_X86_64; } -bool arch__is(struct arch *arch, const char *name) +bool arch__is_powerpc(const struct arch *arch) { - return !strcmp(arch->name, name); + return arch->id.e_machine == EM_PPC || arch->id.e_machine == EM_PPC64; } static void ins_ops__delete(struct ins_operands *ops) @@ -240,13 +213,13 @@ static void ins_ops__delete(struct ins_operands *ops) zfree(&ops->target.name); } -static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name) +int ins__raw_scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) { return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw); } -int ins__scnprintf(struct ins *ins, char *bf, size_t size, +int ins__scnprintf(const struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name) { if (ins->ops->scnprintf) @@ -255,7 +228,7 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size, return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name); } -bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2) +bool ins__is_fused(const struct arch *arch, const char *ins1, const char *ins2) { if (!arch || !arch->ins_is_fused) return false; @@ -263,14 +236,12 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2) return arch->ins_is_fused(arch, ins1, ins2); } -static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, +static int call__parse(const struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, struct disasm_line *dl __maybe_unused) { char *endptr, *tok, *name; struct map *map = ms->map; - struct addr_map_symbol target = { - .ms = { .map = map, }, - }; + struct addr_map_symbol target; ops->target.addr = strtoull(ops->raw, &endptr, 16); @@ -295,12 +266,16 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s if (ops->target.name == NULL) return -1; find_target: - target.addr = map__objdump_2mem(map, ops->target.addr); + target = (struct addr_map_symbol) { + .ms = { .map = map__get(map), }, + .addr = map__objdump_2mem(map, ops->target.addr), + }; - if (maps__find_ams(ms->maps, &target) == 0 && + if (maps__find_ams(thread__maps(ms->thread), &target) == 0 && map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; + addr_map_symbol__exit(&target); return 0; indirect_call: @@ -316,8 +291,8 @@ indirect_call: goto find_target; } -static int call__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name) +int call__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) { if (ops->target.sym) return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name); @@ -331,14 +306,15 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size, return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr); } -static struct ins_ops call_ops = { +const struct ins_ops call_ops = { .parse = call__parse, .scnprintf = call__scnprintf, + .is_call = true, }; bool ins__is_call(const struct ins *ins) { - return ins->ops == &call_ops || ins->ops == &s390_call_ops || ins->ops == &loongarch_call_ops; + return ins->ops && ins->ops->is_call; } /* @@ -359,13 +335,13 @@ static inline const char *validate_comma(const char *c, struct ins_operands *ops return c; } -static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, +static int jump__parse(const struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, struct disasm_line *dl __maybe_unused) { struct map *map = ms->map; struct symbol *sym = ms->sym; struct addr_map_symbol target = { - .ms = { .map = map, }, + .ms = { .map = map__get(map), }, }; const char *c = strchr(ops->raw, ','); u64 start, end; @@ -390,13 +366,16 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * skip over possible up to 2 operands to get to address, e.g.: * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0> */ - if (c++ != NULL) { + if (c != NULL) { + c++; ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); c = validate_comma(c, ops); - if (c++ != NULL) + if (c != NULL) { + c++; ops->target.addr = strtoull(c, NULL, 16); + } } } else { ops->target.addr = strtoull(ops->raw, NULL, 16); @@ -406,7 +385,7 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s start = map__unmap_ip(map, sym->start); end = map__unmap_ip(map, sym->end); - ops->target.outside = target.addr < start || target.addr > end; + ops->target.outside = target.addr < start || target.addr >= end; /* * FIXME: things like this in _cpp_lex_token (gcc's cc1 program): @@ -426,7 +405,7 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * Actual navigation will come next, with further understanding of how * the symbol searching and disassembly should be done. */ - if (maps__find_ams(ms->maps, &target) == 0 && + if (maps__find_ams(thread__maps(ms->thread), &target) == 0 && map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; @@ -436,12 +415,12 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s } else { ops->target.offset_avail = false; } - + addr_map_symbol__exit(&target); return 0; } -static int jump__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name) +int jump__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) { const char *c; @@ -473,7 +452,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, ops->target.offset); } -static void jump__delete(struct ins_operands *ops __maybe_unused) +void jump__delete(struct ins_operands *ops __maybe_unused) { /* * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the @@ -481,15 +460,16 @@ static void jump__delete(struct ins_operands *ops __maybe_unused) */ } -static struct ins_ops jump_ops = { +const struct ins_ops jump_ops = { .free = jump__delete, .parse = jump__parse, .scnprintf = jump__scnprintf, + .is_jump = true, }; bool ins__is_jump(const struct ins *ins) { - return ins->ops == &jump_ops || ins->ops == &loongarch_jump_ops; + return ins->ops && ins->ops->is_jump; } static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep) @@ -519,7 +499,7 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep) return 0; } -static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, +static int lock__parse(const struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, struct disasm_line *dl __maybe_unused) { ops->locked.ops = zalloc(sizeof(*ops->locked.ops)); @@ -545,7 +525,7 @@ out_free_ops: return 0; } -static int lock__scnprintf(struct ins *ins, char *bf, size_t size, +static int lock__scnprintf(const struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name) { int printed; @@ -573,7 +553,7 @@ static void lock__delete(struct ins_operands *ops) zfree(&ops->target.name); } -static struct ins_ops lock_ops = { +const struct ins_ops lock_ops = { .free = lock__delete, .parse = lock__parse, .scnprintf = lock__scnprintf, @@ -586,7 +566,7 @@ static struct ins_ops lock_ops = { * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check * the input string after 'memory_ref_char' if exists. */ -static bool check_multi_regs(struct arch *arch, const char *op) +static bool check_multi_regs(const struct arch *arch, const char *op) { int count = 0; @@ -607,8 +587,9 @@ static bool check_multi_regs(struct arch *arch, const char *op) return count > 1; } -static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused, - struct disasm_line *dl __maybe_unused) +static int mov__parse(const struct arch *arch, struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *comment, prev; @@ -673,105 +654,22 @@ out_free_source: return -1; } -static int mov__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name) +int mov__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name) { return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name, ops->source.name ?: ops->source.raw, ops->target.name ?: ops->target.raw); } -static struct ins_ops mov_ops = { +const struct ins_ops mov_ops = { .parse = mov__parse, .scnprintf = mov__scnprintf, }; -#define PPC_22_30(R) (((R) >> 1) & 0x1ff) -#define MINUS_EXT_XO_FORM 234 -#define SUB_EXT_XO_FORM 232 -#define ADD_ZERO_EXT_XO_FORM 202 -#define SUB_ZERO_EXT_XO_FORM 200 - -static int arithmetic__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name) -{ - return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, - ops->raw); -} - -/* - * Sets the fields: multi_regs and "mem_ref". - * "mem_ref" is set for ops->source which is later used to - * fill the objdump->memory_ref-char field. This ops is currently - * used by powerpc and since binary instruction code is used to - * extract opcode, regs and offset, no other parsing is needed here. - * - * Dont set multi regs for 4 cases since it has only one operand - * for source: - * - Add to Minus One Extended XO-form ( Ex: addme, addmeo ) - * - Subtract From Minus One Extended XO-form ( Ex: subfme ) - * - Add to Zero Extended XO-form ( Ex: addze, addzeo ) - * - Subtract From Zero Extended XO-form ( Ex: subfze ) - */ -static int arithmetic__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, - struct map_symbol *ms __maybe_unused, struct disasm_line *dl) -{ - int opcode = PPC_OP(dl->raw.raw_insn); - - ops->source.mem_ref = false; - if (opcode == 31) { - if ((opcode != MINUS_EXT_XO_FORM) && (opcode != SUB_EXT_XO_FORM) \ - && (opcode != ADD_ZERO_EXT_XO_FORM) && (opcode != SUB_ZERO_EXT_XO_FORM)) - ops->source.multi_regs = true; - } - - ops->target.mem_ref = false; - ops->target.multi_regs = false; - - return 0; -} - -static struct ins_ops arithmetic_ops = { - .parse = arithmetic__parse, - .scnprintf = arithmetic__scnprintf, -}; - -static int load_store__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name) -{ - return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, - ops->raw); -} - -/* - * Sets the fields: multi_regs and "mem_ref". - * "mem_ref" is set for ops->source which is later used to - * fill the objdump->memory_ref-char field. This ops is currently - * used by powerpc and since binary instruction code is used to - * extract opcode, regs and offset, no other parsing is needed here - */ -static int load_store__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, - struct map_symbol *ms __maybe_unused, struct disasm_line *dl __maybe_unused) -{ - ops->source.mem_ref = true; - ops->source.multi_regs = false; - /* opcode 31 is of X form */ - if (PPC_OP(dl->raw.raw_insn) == 31) - ops->source.multi_regs = true; - - ops->target.mem_ref = false; - ops->target.multi_regs = false; - - return 0; -} - -static struct ins_ops load_store_ops = { - .parse = load_store__parse, - .scnprintf = load_store__scnprintf, -}; - -static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused, - struct disasm_line *dl __maybe_unused) +static int dec__parse(const struct arch *arch __maybe_unused, struct ins_operands *ops, + struct map_symbol *ms __maybe_unused, + struct disasm_line *dl __maybe_unused) { char *target, *comment, *s, prev; @@ -798,33 +696,33 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops return 0; } -static int dec__scnprintf(struct ins *ins, char *bf, size_t size, +static int dec__scnprintf(const struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name) { return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name ?: ops->target.raw); } -static struct ins_ops dec_ops = { +const struct ins_ops dec_ops = { .parse = dec__parse, .scnprintf = dec__scnprintf, }; -static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size, +static int nop__scnprintf(const struct ins *ins __maybe_unused, char *bf, size_t size, struct ins_operands *ops __maybe_unused, int max_ins_name) { return scnprintf(bf, size, "%-*s", max_ins_name, "nop"); } -static struct ins_ops nop_ops = { +const struct ins_ops nop_ops = { .scnprintf = nop__scnprintf, }; -static struct ins_ops ret_ops = { +const struct ins_ops ret_ops = { .scnprintf = ins__raw_scnprintf, }; -bool ins__is_nop(const struct ins *ins) +static bool ins__is_nop(const struct ins *ins) { return ins->ops == &nop_ops; } @@ -858,20 +756,21 @@ static void ins__sort(struct arch *arch) { const int nmemb = arch->nr_instructions; - qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp); + qsort((void *)arch->instructions, nmemb, sizeof(struct ins), ins__cmp); } -static struct ins_ops *__ins__find(struct arch *arch, const char *name, struct disasm_line *dl) +static const struct ins_ops *__ins__find(const struct arch *arch, const char *name, + struct disasm_line *dl) { - struct ins *ins; + const struct ins *ins; const int nmemb = arch->nr_instructions; - if (arch__is(arch, "powerpc")) { + if (arch__is_powerpc(arch)) { /* * For powerpc, identify the instruction ops * from the opcode using raw_insn. */ - struct ins_ops *ops; + const struct ins_ops *ops; ops = check_ppc_insn(dl); if (ops) @@ -879,8 +778,8 @@ static struct ins_ops *__ins__find(struct arch *arch, const char *name, struct d } if (!arch->sorted_instructions) { - ins__sort(arch); - arch->sorted_instructions = true; + ins__sort((struct arch *)arch); + ((struct arch *)arch)->sorted_instructions = true; } ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp); @@ -907,17 +806,18 @@ static struct ins_ops *__ins__find(struct arch *arch, const char *name, struct d return ins ? ins->ops : NULL; } -struct ins_ops *ins__find(struct arch *arch, const char *name, struct disasm_line *dl) +const struct ins_ops *ins__find(const struct arch *arch, const char *name, struct disasm_line *dl) { - struct ins_ops *ops = __ins__find(arch, name, dl); + const struct ins_ops *ops = __ins__find(arch, name, dl); if (!ops && arch->associate_instruction_ops) - ops = arch->associate_instruction_ops(arch, name); + ops = arch->associate_instruction_ops((struct arch *)arch, name); return ops; } -static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms) +static void disasm_line__init_ins(struct disasm_line *dl, const struct arch *arch, + struct map_symbol *ms) { dl->ins.ops = ins__find(arch, dl->ins.name, dl); @@ -968,24 +868,25 @@ out: #define PPC_OP(op) (((op) >> 26) & 0x3F) #define RAW_BYTES 11 -static int disasm_line__parse_powerpc(struct disasm_line *dl) +static int disasm_line__parse_powerpc(struct disasm_line *dl, struct annotate_args *args) { char *line = dl->al.line; const char **namep = &dl->ins.name; char **rawp = &dl->ops.raw; char *tmp_raw_insn, *name_raw_insn = skip_spaces(line); char *name = skip_spaces(name_raw_insn + RAW_BYTES); - int objdump = 0; + int disasm = 0; + int ret = 0; - if (strlen(line) > RAW_BYTES) - objdump = 1; + if (args->options->disassembler_used) + disasm = 1; if (name_raw_insn[0] == '\0') return -1; - if (objdump) { - disasm_line__parse(name, namep, rawp); - } else + if (disasm) + ret = disasm_line__parse(name, namep, rawp); + else *namep = ""; tmp_raw_insn = strndup(name_raw_insn, 11); @@ -995,10 +896,10 @@ static int disasm_line__parse_powerpc(struct disasm_line *dl) remove_spaces(tmp_raw_insn); sscanf(tmp_raw_insn, "%x", &dl->raw.raw_insn); - if (objdump) + if (disasm) dl->raw.raw_insn = be32_to_cpu(dl->raw.raw_insn); - return 0; + return ret; } static void annotation_line__init(struct annotation_line *al, @@ -1008,13 +909,14 @@ static void annotation_line__init(struct annotation_line *al, al->offset = args->offset; al->line = strdup(args->line); al->line_nr = args->line_nr; - al->fileloc = args->fileloc; + al->fileloc = args->fileloc ? strdup(args->fileloc) : NULL; al->data_nr = nr; } static void annotation_line__exit(struct annotation_line *al) { zfree_srcline(&al->path); + zfree(&al->fileloc); zfree(&al->line); zfree(&al->cycles); zfree(&al->br_cntr); @@ -1041,7 +943,7 @@ static size_t disasm_line_size(int nr) struct disasm_line *disasm_line__new(struct annotate_args *args) { struct disasm_line *dl = NULL; - struct annotation *notes = symbol__annotation(args->ms.sym); + struct annotation *notes = symbol__annotation(args->ms->sym); int nr = notes->src->nr_events; dl = zalloc(disasm_line_size(nr)); @@ -1050,23 +952,22 @@ struct disasm_line *disasm_line__new(struct annotate_args *args) annotation_line__init(&dl->al, args, nr); if (dl->al.line == NULL) - goto out_delete; + goto out_free_line; if (args->offset != -1) { - if (arch__is(args->arch, "powerpc")) { - if (disasm_line__parse_powerpc(dl) < 0) + if (arch__is_powerpc(args->arch)) { + if (disasm_line__parse_powerpc(dl, args) < 0) goto out_free_line; } else if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) goto out_free_line; - disasm_line__init_ins(dl, args->arch, &args->ms); + disasm_line__init_ins(dl, args->arch, args->ms); } return dl; out_free_line: - zfree(&dl->al.line); -out_delete: + annotation_line__exit(&dl->al); free(dl); return NULL; } @@ -1114,7 +1015,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct annotate_args *args, char *parsed_line, int *line_nr, char **fileloc) { - struct map *map = args->ms.map; + struct map *map = args->ms->map; struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; char *tmp; @@ -1146,7 +1047,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, args->line = parsed_line; args->line_nr = *line_nr; args->fileloc = *fileloc; - args->ms.sym = sym; + args->ms->sym = sym; dl = disasm_line__new(args); (*line_nr)++; @@ -1164,12 +1065,14 @@ static int symbol__parse_objdump_line(struct symbol *sym, if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) { struct addr_map_symbol target = { .addr = dl->ops.target.addr, - .ms = { .map = map, }, + .ms = { .map = map__get(map), }, }; - if (!maps__find_ams(args->ms.maps, &target) && + if (!maps__find_ams(thread__maps(args->ms->thread), &target) && target.ms.sym->start == target.al_addr) dl->ops.target.sym = target.ms.sym; + + addr_map_symbol__exit(&target); } annotation_line__add(&dl->al, ¬es->src->source); @@ -1217,7 +1120,7 @@ int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, s char *build_id_msg = NULL; if (dso__has_build_id(dso)) { - build_id__sprintf(dso__bid(dso), bf + 15); + build_id__snprintf(dso__bid(dso), bf + 15, sizeof(bf) - 15); build_id_msg = bf; } scnprintf(buf, buflen, @@ -1329,425 +1232,11 @@ fallback: return 0; } -#ifdef HAVE_LIBCAPSTONE_SUPPORT -#include <capstone/capstone.h> - -int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style); - -static int open_capstone_handle(struct annotate_args *args, bool is_64bit, - csh *handle) -{ - struct annotation_options *opt = args->options; - cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32; - - /* TODO: support more architectures */ - if (!arch__is(args->arch, "x86")) - return -1; - - if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK) - return -1; - - if (!opt->disassembler_style || - !strcmp(opt->disassembler_style, "att")) - cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT); - - /* - * Resolving address operands to symbols is implemented - * on x86 by investigating instruction details. - */ - cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON); - - return 0; -} -#endif - -#if defined(HAVE_LIBCAPSTONE_SUPPORT) || defined(HAVE_LIBLLVM_SUPPORT) -struct find_file_offset_data { - u64 ip; - u64 offset; -}; - -/* This will be called for each PHDR in an ELF binary */ -static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg) -{ - struct find_file_offset_data *data = arg; - - if (start <= data->ip && data->ip < start + len) { - data->offset = pgoff + data->ip - start; - return 1; - } - return 0; -} - -static u8 * -read_symbol(const char *filename, struct map *map, struct symbol *sym, - u64 *len, bool *is_64bit) -{ - struct dso *dso = map__dso(map); - struct nscookie nsc; - u64 start = map__rip_2objdump(map, sym->start); - u64 end = map__rip_2objdump(map, sym->end); - int fd, count; - u8 *buf = NULL; - struct find_file_offset_data data = { - .ip = start, - }; - - *is_64bit = false; - - nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); - fd = open(filename, O_RDONLY); - nsinfo__mountns_exit(&nsc); - if (fd < 0) - return NULL; - - if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, - is_64bit) == 0) - goto err; - - *len = end - start; - buf = malloc(*len); - if (buf == NULL) - goto err; - - count = pread(fd, buf, *len, data.offset); - close(fd); - fd = -1; - - if ((u64)count != *len) - goto err; - - return buf; - -err: - if (fd >= 0) - close(fd); - free(buf); - return NULL; -} -#endif - -#if !defined(HAVE_LIBCAPSTONE_SUPPORT) || !defined(HAVE_LIBLLVM_SUPPORT) -static void symbol__disassembler_missing(const char *disassembler, const char *filename, - struct symbol *sym) -{ - pr_debug("The %s disassembler isn't linked in for %s in %s\n", - disassembler, sym->name, filename); -} -#endif - -#ifdef HAVE_LIBCAPSTONE_SUPPORT -static void print_capstone_detail(cs_insn *insn, char *buf, size_t len, - struct annotate_args *args, u64 addr) -{ - int i; - struct map *map = args->ms.map; - struct symbol *sym; - - /* TODO: support more architectures */ - if (!arch__is(args->arch, "x86")) - return; - - if (insn->detail == NULL) - return; - - for (i = 0; i < insn->detail->x86.op_count; i++) { - cs_x86_op *op = &insn->detail->x86.operands[i]; - u64 orig_addr; - - if (op->type != X86_OP_MEM) - continue; - - /* only print RIP-based global symbols for now */ - if (op->mem.base != X86_REG_RIP) - continue; - - /* get the target address */ - orig_addr = addr + insn->size + op->mem.disp; - addr = map__objdump_2mem(map, orig_addr); - - if (dso__kernel(map__dso(map))) { - /* - * The kernel maps can be splitted into sections, - * let's find the map first and the search the symbol. - */ - map = maps__find(map__kmaps(map), addr); - if (map == NULL) - continue; - } - - /* convert it to map-relative address for search */ - addr = map__map_ip(map, addr); - - sym = map__find_symbol(map, addr); - if (sym == NULL) - continue; - - if (addr == sym->start) { - scnprintf(buf, len, "\t# %"PRIx64" <%s>", - orig_addr, sym->name); - } else { - scnprintf(buf, len, "\t# %"PRIx64" <%s+%#"PRIx64">", - orig_addr, sym->name, addr - sym->start); - } - break; - } -} - -static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct map *map = args->ms.map; - struct dso *dso = map__dso(map); - struct nscookie nsc; - u64 start = map__rip_2objdump(map, sym->start); - u64 end = map__rip_2objdump(map, sym->end); - u64 len = end - start; - u64 offset; - int i, fd, count; - bool is_64bit = false; - bool needs_cs_close = false; - u8 *buf = NULL; - struct find_file_offset_data data = { - .ip = start, - }; - csh handle; - char disasm_buf[512]; - struct disasm_line *dl; - u32 *line; - bool disassembler_style = false; - - if (args->options->objdump_path) - return -1; - - nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); - fd = open(filename, O_RDONLY); - nsinfo__mountns_exit(&nsc); - if (fd < 0) - return -1; - - if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, - &is_64bit) == 0) - goto err; - - if (!args->options->disassembler_style || - !strcmp(args->options->disassembler_style, "att")) - disassembler_style = true; - - if (capstone_init(maps__machine(args->ms.maps), &handle, is_64bit, disassembler_style) < 0) - goto err; - - needs_cs_close = true; - - buf = malloc(len); - if (buf == NULL) - goto err; - - count = pread(fd, buf, len, data.offset); - close(fd); - fd = -1; - - if ((u64)count != len) - goto err; - - line = (u32 *)buf; - - /* add the function address and name */ - scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", - start, sym->name); - - args->offset = -1; - args->line = disasm_buf; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - /* - * TODO: enable disassm for powerpc - * count = cs_disasm(handle, buf, len, start, len, &insn); - * - * For now, only binary code is saved in disassembled line - * to be used in "type" and "typeoff" sort keys. Each raw code - * is 32 bit instruction. So use "len/4" to get the number of - * entries. - */ - count = len/4; - - for (i = 0, offset = 0; i < count; i++) { - args->offset = offset; - sprintf(args->line, "%x", line[i]); - - dl = disasm_line__new(args); - if (dl == NULL) - break; - - annotation_line__add(&dl->al, ¬es->src->source); - - offset += 4; - } - - /* It failed in the middle */ - if (offset != len) { - struct list_head *list = ¬es->src->source; - - /* Discard all lines and fallback to objdump */ - while (!list_empty(list)) { - dl = list_first_entry(list, struct disasm_line, al.node); - - list_del_init(&dl->al.node); - disasm_line__free(dl); - } - count = -1; - } - -out: - if (needs_cs_close) - cs_close(&handle); - free(buf); - return count < 0 ? count : 0; - -err: - if (fd >= 0) - close(fd); - count = -1; - goto out; -} - -static int symbol__disassemble_capstone(char *filename, struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct map *map = args->ms.map; - u64 start = map__rip_2objdump(map, sym->start); - u64 len; - u64 offset; - int i, count, free_count; - bool is_64bit = false; - bool needs_cs_close = false; - u8 *buf = NULL; - csh handle; - cs_insn *insn = NULL; - char disasm_buf[512]; - struct disasm_line *dl; - - if (args->options->objdump_path) - return -1; - - buf = read_symbol(filename, map, sym, &len, &is_64bit); - if (buf == NULL) - return -1; - - /* add the function address and name */ - scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", - start, sym->name); - - args->offset = -1; - args->line = disasm_buf; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - if (open_capstone_handle(args, is_64bit, &handle) < 0) - goto err; - - needs_cs_close = true; - - free_count = count = cs_disasm(handle, buf, len, start, len, &insn); - for (i = 0, offset = 0; i < count; i++) { - int printed; - - printed = scnprintf(disasm_buf, sizeof(disasm_buf), - " %-7s %s", - insn[i].mnemonic, insn[i].op_str); - print_capstone_detail(&insn[i], disasm_buf + printed, - sizeof(disasm_buf) - printed, args, - start + offset); - - args->offset = offset; - args->line = disasm_buf; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - offset += insn[i].size; - } - - /* It failed in the middle: probably due to unknown instructions */ - if (offset != len) { - struct list_head *list = ¬es->src->source; - - /* Discard all lines and fallback to objdump */ - while (!list_empty(list)) { - dl = list_first_entry(list, struct disasm_line, al.node); - - list_del_init(&dl->al.node); - disasm_line__free(dl); - } - count = -1; - } - -out: - if (needs_cs_close) { - cs_close(&handle); - if (free_count > 0) - cs_free(insn, free_count); - } - free(buf); - return count < 0 ? count : 0; - -err: - if (needs_cs_close) { - struct disasm_line *tmp; - - /* - * It probably failed in the middle of the above loop. - * Release any resources it might add. - */ - list_for_each_entry_safe(dl, tmp, ¬es->src->source, al.node) { - list_del(&dl->al.node); - disasm_line__free(dl); - } - } - count = -1; - goto out; -} -#else // HAVE_LIBCAPSTONE_SUPPORT -static int symbol__disassemble_capstone(char *filename, struct symbol *sym, - struct annotate_args *args __maybe_unused) -{ - symbol__disassembler_missing("capstone", filename, sym); - return -1; -} - -static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym, - struct annotate_args *args __maybe_unused) -{ - symbol__disassembler_missing("capstone powerpc", filename, sym); - return -1; -} -#endif // HAVE_LIBCAPSTONE_SUPPORT - static int symbol__disassemble_raw(char *filename, struct symbol *sym, struct annotate_args *args) { struct annotation *notes = symbol__annotation(sym); - struct map *map = args->ms.map; + struct map *map = args->ms->map; struct dso *dso = map__dso(map); u64 start = map__rip_2objdump(map, sym->start); u64 end = map__rip_2objdump(map, sym->end); @@ -1784,7 +1273,7 @@ static int symbol__disassemble_raw(char *filename, struct symbol *sym, args->line = disasm_buf; args->line_nr = 0; args->fileloc = NULL; - args->ms.sym = sym; + args->ms->sym = sym; dl = disasm_line__new(args); if (dl == NULL) @@ -1829,201 +1318,12 @@ err: goto out; } -#ifdef HAVE_LIBLLVM_SUPPORT -#include <llvm-c/Disassembler.h> -#include <llvm-c/Target.h> -#include "util/llvm-c-helpers.h" - -struct symbol_lookup_storage { - u64 branch_addr; - u64 pcrel_load_addr; -}; - -/* - * Whenever LLVM wants to resolve an address into a symbol, it calls this - * callback. We don't ever actually _return_ anything (in particular, because - * it puts quotation marks around what we return), but we use this as a hint - * that there is a branch or PC-relative address in the expression that we - * should add some textual annotation for after the instruction. The caller - * will use this information to add the actual annotation. - */ -static const char * -symbol_lookup_callback(void *disinfo, uint64_t value, - uint64_t *ref_type, - uint64_t address __maybe_unused, - const char **ref __maybe_unused) -{ - struct symbol_lookup_storage *storage = disinfo; - - if (*ref_type == LLVMDisassembler_ReferenceType_In_Branch) - storage->branch_addr = value; - else if (*ref_type == LLVMDisassembler_ReferenceType_In_PCrel_Load) - storage->pcrel_load_addr = value; - *ref_type = LLVMDisassembler_ReferenceType_InOut_None; - return NULL; -} - -static int symbol__disassemble_llvm(char *filename, struct symbol *sym, - struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct map *map = args->ms.map; - struct dso *dso = map__dso(map); - u64 start = map__rip_2objdump(map, sym->start); - u8 *buf; - u64 len; - u64 pc; - bool is_64bit; - char triplet[64]; - char disasm_buf[2048]; - size_t disasm_len; - struct disasm_line *dl; - LLVMDisasmContextRef disasm = NULL; - struct symbol_lookup_storage storage; - char *line_storage = NULL; - size_t line_storage_len = 0; - int ret = -1; - - if (args->options->objdump_path) - return -1; - - LLVMInitializeAllTargetInfos(); - LLVMInitializeAllTargetMCs(); - LLVMInitializeAllDisassemblers(); - - buf = read_symbol(filename, map, sym, &len, &is_64bit); - if (buf == NULL) - return -1; - - if (arch__is(args->arch, "x86")) { - if (is_64bit) - scnprintf(triplet, sizeof(triplet), "x86_64-pc-linux"); - else - scnprintf(triplet, sizeof(triplet), "i686-pc-linux"); - } else { - scnprintf(triplet, sizeof(triplet), "%s-linux-gnu", - args->arch->name); - } - - disasm = LLVMCreateDisasm(triplet, &storage, 0, NULL, - symbol_lookup_callback); - if (disasm == NULL) - goto err; - - if (args->options->disassembler_style && - !strcmp(args->options->disassembler_style, "intel")) - LLVMSetDisasmOptions(disasm, - LLVMDisassembler_Option_AsmPrinterVariant); - - /* - * This needs to be set after AsmPrinterVariant, due to a bug in LLVM; - * setting AsmPrinterVariant makes a new instruction printer, making it - * forget about the PrintImmHex flag (which is applied before if both - * are given to the same call). - */ - LLVMSetDisasmOptions(disasm, LLVMDisassembler_Option_PrintImmHex); - - /* add the function address and name */ - scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", - start, sym->name); - - args->offset = -1; - args->line = disasm_buf; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - pc = start; - for (u64 offset = 0; offset < len; ) { - unsigned int ins_len; - - storage.branch_addr = 0; - storage.pcrel_load_addr = 0; - - ins_len = LLVMDisasmInstruction(disasm, buf + offset, - len - offset, pc, - disasm_buf, sizeof(disasm_buf)); - if (ins_len == 0) - goto err; - disasm_len = strlen(disasm_buf); - - if (storage.branch_addr != 0) { - char *name = llvm_name_for_code(dso, filename, - storage.branch_addr); - if (name != NULL) { - disasm_len += scnprintf(disasm_buf + disasm_len, - sizeof(disasm_buf) - - disasm_len, - " <%s>", name); - free(name); - } - } - if (storage.pcrel_load_addr != 0) { - char *name = llvm_name_for_data(dso, filename, - storage.pcrel_load_addr); - disasm_len += scnprintf(disasm_buf + disasm_len, - sizeof(disasm_buf) - disasm_len, - " # %#"PRIx64, - storage.pcrel_load_addr); - if (name) { - disasm_len += scnprintf(disasm_buf + disasm_len, - sizeof(disasm_buf) - - disasm_len, - " <%s>", name); - free(name); - } - } - - args->offset = offset; - args->line = expand_tabs(disasm_buf, &line_storage, - &line_storage_len); - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - - llvm_addr2line(filename, pc, &args->fileloc, - (unsigned int *)&args->line_nr, false, NULL); - - dl = disasm_line__new(args); - if (dl == NULL) - goto err; - - annotation_line__add(&dl->al, ¬es->src->source); - - free(args->fileloc); - pc += ins_len; - offset += ins_len; - } - - ret = 0; - -err: - LLVMDisasmDispose(disasm); - free(buf); - free(line_storage); - return ret; -} -#else // HAVE_LIBLLVM_SUPPORT -static int symbol__disassemble_llvm(char *filename, struct symbol *sym, - struct annotate_args *args __maybe_unused) -{ - symbol__disassembler_missing("LLVM", filename, sym); - return -1; -} -#endif // HAVE_LIBLLVM_SUPPORT - /* * Possibly create a new version of line with tabs expanded. Returns the * existing or new line, storage is updated if a new line is allocated. If * allocation fails then NULL is returned. */ -static char *expand_tabs(char *line, char **storage, size_t *storage_len) +char *expand_tabs(char *line, char **storage, size_t *storage_len) { size_t i, src, dst, len, new_storage_len, num_tabs; char *new_line; @@ -2078,11 +1378,28 @@ static char *expand_tabs(char *line, char **storage, size_t *storage_len) return new_line; } +static int symbol__disassemble_bpf_image(struct symbol *sym, struct annotate_args *args) +{ + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *dl; + + args->offset = -1; + args->line = strdup("to be implemented"); + args->line_nr = 0; + args->fileloc = NULL; + dl = disasm_line__new(args); + if (dl) + annotation_line__add(&dl->al, ¬es->src->source); + + zfree(&args->line); + return 0; +} + static int symbol__disassemble_objdump(const char *filename, struct symbol *sym, struct annotate_args *args) { struct annotation_options *opts = &annotate_opts; - struct map *map = args->ms.map; + struct map *map = args->ms->map; struct dso *dso = map__dso(map); char *command; FILE *file; @@ -2102,6 +1419,12 @@ static int symbol__disassemble_objdump(const char *filename, struct symbol *sym, struct child_process objdump_process; int err; + if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) + return symbol__disassemble_bpf_libbfd(sym, args); + + if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) + return symbol__disassemble_bpf_image(sym, args); + err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 @@ -2219,7 +1542,7 @@ out_free_command: int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *options = args->options; - struct map *map = args->ms.map; + struct map *map = args->ms->map; struct dso *dso = map__dso(map); char symfs_filename[PATH_MAX]; bool delete_extract = false; @@ -2236,11 +1559,7 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) pr_debug("annotating [%p] %30s : [%p] %30s\n", dso, dso__long_name(dso), sym, sym->name); - if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) { - return symbol__disassemble_bpf(sym, args); - } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) { - return symbol__disassemble_bpf_image(sym, args); - } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) { + if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) { return SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE; } else if (dso__is_kcore(dso)) { kce.addr = map__rip_2objdump(map, sym->start); @@ -2269,7 +1588,7 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) * and typeoff, disassemble to mnemonic notation is not required in * case of powerpc. */ - if (arch__is(args->arch, "powerpc")) { + if (arch__is_powerpc(args->arch)) { extern const char *sort_order; if (sort_order && !strstr(sort_order, "sym")) { @@ -2283,22 +1602,33 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) } } + /* FIXME: LLVM and CAPSTONE should support source code */ + if (options->annotate_src && !options->hide_src_code) { + err = symbol__disassemble_objdump(symfs_filename, sym, args); + if (err == 0) + goto out_remove_tmp; + } + err = -1; for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers) && err != 0; i++) { enum perf_disassembler dis = options->disassemblers[i]; switch (dis) { case PERF_DISASM_LLVM: + args->options->disassembler_used = PERF_DISASM_LLVM; err = symbol__disassemble_llvm(symfs_filename, sym, args); break; case PERF_DISASM_CAPSTONE: + args->options->disassembler_used = PERF_DISASM_CAPSTONE; err = symbol__disassemble_capstone(symfs_filename, sym, args); break; case PERF_DISASM_OBJDUMP: + args->options->disassembler_used = PERF_DISASM_OBJDUMP; err = symbol__disassemble_objdump(symfs_filename, sym, args); break; case PERF_DISASM_UNKNOWN: /* End of disassemblers. */ default: + args->options->disassembler_used = PERF_DISASM_UNKNOWN; goto out_remove_tmp; } if (err == 0) diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h index c135db2416b5..25756e3f47e4 100644 --- a/tools/perf/util/disasm.h +++ b/tools/perf/util/disasm.h @@ -17,21 +17,23 @@ struct data_loc_info; struct type_state; struct disasm_line; +struct e_machine_and_e_flags { + uint32_t e_flags; + uint16_t e_machine; +}; + 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; - const char *insn_suffix; - void *priv; - unsigned int model; - unsigned int family; - int (*init)(struct arch *arch, char *cpuid); - bool (*ins_is_fused)(struct arch *arch, const char *ins1, - const char *ins2); + /** @name: name such as "x86" or "powerpc". */ + const char *name; + const struct ins *instructions; + size_t nr_instructions; + size_t nr_instructions_allocated; + const char *insn_suffix; + unsigned int model; + unsigned int family; + /** @id: ELF machine and flags associated with arch. */ + struct e_machine_and_e_flags id; + bool sorted_instructions; struct { char comment_char; char skip_functions_char; @@ -39,20 +41,19 @@ struct arch { char memory_ref_char; char imm_char; } objdump; + bool (*ins_is_fused)(const struct arch *arch, const char *ins1, + const char *ins2); + const struct ins_ops *(*associate_instruction_ops)(struct arch *arch, const char *name); #ifdef HAVE_LIBDW_SUPPORT void (*update_insn_state)(struct type_state *state, struct data_loc_info *dloc, Dwarf_Die *cu_die, struct disasm_line *dl); #endif - /** @e_machine: ELF machine associated with arch. */ - unsigned int e_machine; - /** @e_flags: Optional ELF flags associated with arch. */ - unsigned int e_flags; }; struct ins { const char *name; - struct ins_ops *ops; + const struct ins_ops *ops; }; struct ins_operands { @@ -89,16 +90,17 @@ struct ins_operands { struct ins_ops { void (*free)(struct ins_operands *ops); - int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, + int (*parse)(const struct arch *arch, struct ins_operands *ops, struct map_symbol *ms, struct disasm_line *dl); - int (*scnprintf)(struct ins *ins, char *bf, size_t size, + int (*scnprintf)(const struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name); + bool is_jump; + bool is_call; }; struct annotate_args { - struct arch *arch; - struct map_symbol ms; - struct evsel *evsel; + const struct arch *arch; + struct map_symbol *ms; struct annotation_options *options; s64 offset; char *line; @@ -106,26 +108,63 @@ struct annotate_args { char *fileloc; }; -struct arch *arch__find(const char *name); -bool arch__is(struct arch *arch, const char *name); +const struct arch *arch__find(uint16_t e_machine, uint32_t e_flags, const char *cpuid); +bool arch__is_x86(const struct arch *arch); +bool arch__is_powerpc(const struct arch *arch); -struct ins_ops *ins__find(struct arch *arch, const char *name, struct disasm_line *dl); -int ins__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name); +extern const struct ins_ops call_ops; +extern const struct ins_ops dec_ops; +extern const struct ins_ops jump_ops; +extern const struct ins_ops mov_ops; +extern const struct ins_ops nop_ops; +extern const struct ins_ops lock_ops; +extern const struct ins_ops ret_ops; + +int arch__associate_ins_ops(struct arch *arch, const char *name, const struct ins_ops *ops); + +const struct arch *arch__new_arc(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_arm(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_arm64(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_csky(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_loongarch(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_mips(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_powerpc(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_riscv64(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_s390(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_sparc(const struct e_machine_and_e_flags *id, const char *cpuid); +const struct arch *arch__new_x86(const struct e_machine_and_e_flags *id, const char *cpuid); + +const struct ins_ops *ins__find(const struct arch *arch, const char *name, struct disasm_line *dl); bool ins__is_call(const struct ins *ins); bool ins__is_jump(const struct ins *ins); -bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2); -bool ins__is_nop(const struct ins *ins); +bool ins__is_fused(const struct arch *arch, const char *ins1, const char *ins2); bool ins__is_ret(const struct ins *ins); bool ins__is_lock(const struct ins *ins); +const struct ins_ops *check_ppc_insn(struct disasm_line *dl); + struct disasm_line *disasm_line__new(struct annotate_args *args); void disasm_line__free(struct disasm_line *dl); int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name); +int ins__raw_scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name); +int ins__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name); +int call__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name); +int jump__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name); +int mov__scnprintf(const struct ins *ins, char *bf, size_t size, + struct ins_operands *ops, int max_ins_name); + +void jump__delete(struct ins_operands *ops); + int symbol__disassemble(struct symbol *sym, struct annotate_args *args); +char *expand_tabs(char *line, char **storage, size_t *storage_len); + #endif /* __PERF_UTIL_DISASM_H */ diff --git a/tools/perf/util/disasm_bpf.c b/tools/perf/util/disasm_bpf.c deleted file mode 100644 index 1fee71c79b62..000000000000 --- a/tools/perf/util/disasm_bpf.c +++ /dev/null @@ -1,195 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include "util/annotate.h" -#include "util/disasm_bpf.h" -#include "util/symbol.h" -#include <linux/zalloc.h> -#include <string.h> - -#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) -#define PACKAGE "perf" -#include <bfd.h> -#include <bpf/bpf.h> -#include <bpf/btf.h> -#include <bpf/libbpf.h> -#include <dis-asm.h> -#include <errno.h> -#include <linux/btf.h> -#include <tools/dis-asm-compat.h> - -#include "util/bpf-event.h" -#include "util/bpf-utils.h" -#include "util/debug.h" -#include "util/dso.h" -#include "util/map.h" -#include "util/env.h" -#include "util/util.h" - -int symbol__disassemble_bpf(struct symbol *sym, struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct bpf_prog_linfo *prog_linfo = NULL; - struct bpf_prog_info_node *info_node; - int len = sym->end - sym->start; - disassembler_ftype disassemble; - struct map *map = args->ms.map; - struct perf_bpil *info_linear; - struct disassemble_info info; - struct dso *dso = map__dso(map); - int pc = 0, count, sub_id; - struct btf *btf = NULL; - char tpath[PATH_MAX]; - size_t buf_size; - int nr_skip = 0; - char *buf; - bfd *bfdf; - int ret; - FILE *s; - - if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO) - return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; - - pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, - sym->name, sym->start, sym->end - sym->start); - - memset(tpath, 0, sizeof(tpath)); - perf_exe(tpath, sizeof(tpath)); - - bfdf = bfd_openr(tpath, NULL); - if (bfdf == NULL) - abort(); - - if (!bfd_check_format(bfdf, bfd_object)) - abort(); - - s = open_memstream(&buf, &buf_size); - if (!s) { - ret = errno; - goto out; - } - init_disassemble_info_compat(&info, s, - (fprintf_ftype) fprintf, - fprintf_styled); - info.arch = bfd_get_arch(bfdf); - info.mach = bfd_get_mach(bfdf); - - info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env, - dso__bpf_prog(dso)->id); - if (!info_node) { - ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; - goto out; - } - info_linear = info_node->info_linear; - sub_id = dso__bpf_prog(dso)->sub_id; - - info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns); - info.buffer_length = info_linear->info.jited_prog_len; - - if (info_linear->info.nr_line_info) - prog_linfo = bpf_prog_linfo__new(&info_linear->info); - - if (info_linear->info.btf_id) { - struct btf_node *node; - - node = perf_env__find_btf(dso__bpf_prog(dso)->env, - info_linear->info.btf_id); - if (node) - btf = btf__new((__u8 *)(node->data), - node->data_size); - } - - disassemble_init_for_target(&info); - -#ifdef DISASM_FOUR_ARGS_SIGNATURE - disassemble = disassembler(info.arch, - bfd_big_endian(bfdf), - info.mach, - bfdf); -#else - disassemble = disassembler(bfdf); -#endif - if (disassemble == NULL) - abort(); - - fflush(s); - do { - const struct bpf_line_info *linfo = NULL; - struct disasm_line *dl; - size_t prev_buf_size; - const char *srcline; - u64 addr; - - addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id]; - count = disassemble(pc, &info); - - if (prog_linfo) - linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, - addr, sub_id, - nr_skip); - - if (linfo && btf) { - srcline = btf__name_by_offset(btf, linfo->line_off); - nr_skip++; - } else - srcline = NULL; - - fprintf(s, "\n"); - prev_buf_size = buf_size; - fflush(s); - - if (!annotate_opts.hide_src_code && srcline) { - args->offset = -1; - args->line = strdup(srcline); - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - dl = disasm_line__new(args); - if (dl) { - annotation_line__add(&dl->al, - ¬es->src->source); - } - } - - args->offset = pc; - args->line = buf + prev_buf_size; - args->line_nr = 0; - args->fileloc = NULL; - args->ms.sym = sym; - dl = disasm_line__new(args); - if (dl) - annotation_line__add(&dl->al, ¬es->src->source); - - pc += count; - } while (count > 0 && pc < len); - - ret = 0; -out: - free(prog_linfo); - btf__free(btf); - fclose(s); - bfd_close(bfdf); - return ret; -} -#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) -int symbol__disassemble_bpf(struct symbol *sym __maybe_unused, struct annotate_args *args __maybe_unused) -{ - return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF; -} -#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT) - -int symbol__disassemble_bpf_image(struct symbol *sym, struct annotate_args *args) -{ - struct annotation *notes = symbol__annotation(sym); - struct disasm_line *dl; - - args->offset = -1; - args->line = strdup("to be implemented"); - args->line_nr = 0; - args->fileloc = NULL; - dl = disasm_line__new(args); - if (dl) - annotation_line__add(&dl->al, ¬es->src->source); - - zfree(&args->line); - return 0; -} diff --git a/tools/perf/util/disasm_bpf.h b/tools/perf/util/disasm_bpf.h deleted file mode 100644 index 2ecb19545388..000000000000 --- a/tools/perf/util/disasm_bpf.h +++ /dev/null @@ -1,12 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#ifndef __PERF_DISASM_BPF_H -#define __PERF_DISASM_BPF_H - -struct symbol; -struct annotate_args; - -int symbol__disassemble_bpf(struct symbol *sym, struct annotate_args *args); -int symbol__disassemble_bpf_image(struct symbol *sym, struct annotate_args *args); - -#endif /* __PERF_DISASM_BPF_H */ diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index ddacef881af2..dc31b5e7149e 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -234,8 +234,7 @@ static const __u8 *dlfilter__insn(void *ctx, __u32 *len) struct machine *machine = maps__machine(thread__maps(al->thread)); if (machine) - script_fetch_insn(d->sample, al->thread, machine, - /*native_arch=*/true); + perf_sample__fetch_insn(d->sample, al->thread, machine); } } @@ -513,6 +512,7 @@ int dlfilter__do_filter_event(struct dlfilter *d, d->d_addr_al = &d_addr_al; d_sample.size = sizeof(d_sample); + d_sample.p_stage_cyc = sample->weight3; d_ip_al.size = 0; /* To indicate d_ip_al is not initialized */ d_addr_al.size = 0; /* To indicate d_addr_al is not initialized */ @@ -526,7 +526,6 @@ int dlfilter__do_filter_event(struct dlfilter *d, ASSIGN(period); ASSIGN(weight); ASSIGN(ins_lat); - ASSIGN(p_stage_cyc); ASSIGN(transaction); ASSIGN(insn_cnt); ASSIGN(cyc_cnt); diff --git a/tools/perf/util/drm_pmu.c b/tools/perf/util/drm_pmu.c new file mode 100644 index 000000000000..b8badae7015c --- /dev/null +++ b/tools/perf/util/drm_pmu.c @@ -0,0 +1,685 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#include "drm_pmu.h" +#include "counts.h" +#include "cpumap.h" +#include "debug.h" +#include "evsel.h" +#include "pmu.h" +#include <perf/threadmap.h> +#include <api/fs/fs.h> +#include <api/io.h> +#include <ctype.h> +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <unistd.h> +#include <linux/unistd.h> +#include <linux/kcmp.h> +#include <linux/string.h> +#include <linux/zalloc.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/sysmacros.h> +#include <sys/types.h> + +enum drm_pmu_unit { + DRM_PMU_UNIT_BYTES, + DRM_PMU_UNIT_CAPACITY, + DRM_PMU_UNIT_CYCLES, + DRM_PMU_UNIT_HZ, + DRM_PMU_UNIT_NS, + + DRM_PMU_UNIT_MAX, +}; + +struct drm_pmu_event { + const char *name; + const char *desc; + enum drm_pmu_unit unit; +}; + +struct drm_pmu { + struct perf_pmu pmu; + struct drm_pmu_event *events; + int num_events; +}; + +static const char * const drm_pmu_unit_strs[DRM_PMU_UNIT_MAX] = { + "bytes", + "capacity", + "cycles", + "hz", + "ns", +}; + +static const char * const drm_pmu_scale_unit_strs[DRM_PMU_UNIT_MAX] = { + "1bytes", + "1capacity", + "1cycles", + "1hz", + "1ns", +}; + +bool perf_pmu__is_drm(const struct perf_pmu *pmu) +{ + return pmu && pmu->type >= PERF_PMU_TYPE_DRM_START && + pmu->type <= PERF_PMU_TYPE_DRM_END; +} + +bool evsel__is_drm(const struct evsel *evsel) +{ + return perf_pmu__is_drm(evsel->pmu); +} + +static struct drm_pmu *add_drm_pmu(struct list_head *pmus, char *line, size_t line_len) +{ + struct drm_pmu *drm; + struct perf_pmu *pmu; + const char *name; + __u32 max_drm_pmu_type = 0, type; + int i = 12; + + if (line[line_len - 1] == '\n') + line[line_len - 1] = '\0'; + while (isspace(line[i])) + i++; + + line[--i] = '_'; + line[--i] = 'm'; + line[--i] = 'r'; + line[--i] = 'd'; + name = &line[i]; + + list_for_each_entry(pmu, pmus, list) { + if (!perf_pmu__is_drm(pmu)) + continue; + if (pmu->type > max_drm_pmu_type) + max_drm_pmu_type = pmu->type; + if (!strcmp(pmu->name, name)) { + /* PMU already exists. */ + return NULL; + } + } + + if (max_drm_pmu_type != 0) + type = max_drm_pmu_type + 1; + else + type = PERF_PMU_TYPE_DRM_START; + + if (type > PERF_PMU_TYPE_DRM_END) { + zfree(&drm); + pr_err("Unable to encode DRM PMU type for %s\n", name); + return NULL; + } + + drm = zalloc(sizeof(*drm)); + if (!drm) + return NULL; + + if (perf_pmu__init(&drm->pmu, type, name) != 0) { + perf_pmu__delete(&drm->pmu); + return NULL; + } + + drm->pmu.cpus = perf_cpu_map__new_int(0); + if (!drm->pmu.cpus) { + perf_pmu__delete(&drm->pmu); + return NULL; + } + return drm; +} + + +static int add_event(struct drm_pmu_event **events, int *num_events, + const char *line, enum drm_pmu_unit unit, const char *desc) +{ + const char *colon = strchr(line, ':'); + struct drm_pmu_event *tmp; + + if (!colon) + return -EINVAL; + + tmp = reallocarray(*events, *num_events + 1, sizeof(struct drm_pmu_event)); + if (!tmp) + return -ENOMEM; + tmp[*num_events].unit = unit; + tmp[*num_events].desc = desc; + tmp[*num_events].name = strndup(line, colon - line); + if (!tmp[*num_events].name) + return -ENOMEM; + (*num_events)++; + *events = tmp; + return 0; +} + +static int read_drm_pmus_cb(void *args, int fdinfo_dir_fd, const char *fd_name) +{ + struct list_head *pmus = args; + char buf[640]; + struct io io; + char *line = NULL; + size_t line_len; + struct drm_pmu *drm = NULL; + struct drm_pmu_event *events = NULL; + int num_events = 0; + + io__init(&io, openat(fdinfo_dir_fd, fd_name, O_RDONLY), buf, sizeof(buf)); + if (io.fd == -1) { + /* Failed to open file, ignore. */ + return 0; + } + + while (io__getline(&io, &line, &line_len) > 0) { + if (strstarts(line, "drm-driver:")) { + drm = add_drm_pmu(pmus, line, line_len); + if (!drm) + break; + continue; + } + /* + * Note the string matching below is alphabetical, with more + * specific matches appearing before less specific. + */ + if (strstarts(line, "drm-active-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_BYTES, + "Total memory active in one or more engines"); + continue; + } + if (strstarts(line, "drm-cycles-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_CYCLES, + "Busy cycles"); + continue; + } + if (strstarts(line, "drm-engine-capacity-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_CAPACITY, + "Engine capacity"); + continue; + } + if (strstarts(line, "drm-engine-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_NS, + "Utilization in ns"); + continue; + } + if (strstarts(line, "drm-maxfreq-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_HZ, + "Maximum frequency"); + continue; + } + if (strstarts(line, "drm-purgeable-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_BYTES, + "Size of resident and purgeable memory buffers"); + continue; + } + if (strstarts(line, "drm-resident-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_BYTES, + "Size of resident memory buffers"); + continue; + } + if (strstarts(line, "drm-shared-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_BYTES, + "Size of shared memory buffers"); + continue; + } + if (strstarts(line, "drm-total-cycles-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_BYTES, + "Total busy cycles"); + continue; + } + if (strstarts(line, "drm-total-")) { + add_event(&events, &num_events, line, DRM_PMU_UNIT_BYTES, + "Size of shared and private memory"); + continue; + } + if (verbose > 1 && strstarts(line, "drm-") && + !strstarts(line, "drm-client-id:") && + !strstarts(line, "drm-pdev:")) + pr_debug("Unhandled DRM PMU fdinfo line match '%s'\n", line); + } + if (drm) { + drm->events = events; + drm->num_events = num_events; + list_add_tail(&drm->pmu.list, pmus); + } + free(line); + if (io.fd != -1) + close(io.fd); + return 0; +} + +void drm_pmu__exit(struct perf_pmu *pmu) +{ + struct drm_pmu *drm = container_of(pmu, struct drm_pmu, pmu); + + free(drm->events); +} + +bool drm_pmu__have_event(const struct perf_pmu *pmu, const char *name) +{ + struct drm_pmu *drm = container_of(pmu, struct drm_pmu, pmu); + + if (!strstarts(name, "drm-")) + return false; + + for (int i = 0; i < drm->num_events; i++) { + if (!strcasecmp(drm->events[i].name, name)) + return true; + } + return false; +} + +int drm_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb) +{ + struct drm_pmu *drm = container_of(pmu, struct drm_pmu, pmu); + + for (int i = 0; i < drm->num_events; i++) { + char encoding_buf[128]; + struct pmu_event_info info = { + .pmu = pmu, + .name = drm->events[i].name, + .alias = NULL, + .scale_unit = drm_pmu_scale_unit_strs[drm->events[i].unit], + .desc = drm->events[i].desc, + .long_desc = NULL, + .encoding_desc = encoding_buf, + .topic = "drm", + .pmu_name = pmu->name, + .event_type_desc = "DRM event", + }; + int ret; + + snprintf(encoding_buf, sizeof(encoding_buf), "%s/config=0x%x/", pmu->name, i); + + ret = cb(state, &info); + if (ret) + return ret; + } + return 0; +} + +size_t drm_pmu__num_events(const struct perf_pmu *pmu) +{ + const struct drm_pmu *drm = container_of(pmu, struct drm_pmu, pmu); + + return drm->num_events; +} + +static int drm_pmu__index_for_event(const struct drm_pmu *drm, const char *name) +{ + for (int i = 0; i < drm->num_events; i++) { + if (!strcmp(drm->events[i].name, name)) + return i; + } + return -1; +} + +static int drm_pmu__config_term(const struct drm_pmu *drm, + struct perf_event_attr *attr, + struct parse_events_term *term, + struct parse_events_error *err) +{ + if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) { + int i = drm_pmu__index_for_event(drm, term->config); + + if (i >= 0) { + attr->config = i; + return 0; + } + } + if (err) { + char *err_str; + + parse_events_error__handle(err, term->err_val, + asprintf(&err_str, + "unexpected drm event term (%s) %s", + parse_events__term_type_str(term->type_term), + term->config) < 0 + ? strdup("unexpected drm event term") + : err_str, + NULL); + } + return -EINVAL; +} + +int drm_pmu__config_terms(const struct perf_pmu *pmu, + struct perf_event_attr *attr, + struct parse_events_terms *terms, + struct parse_events_error *err) +{ + struct drm_pmu *drm = container_of(pmu, struct drm_pmu, pmu); + struct parse_events_term *term; + + list_for_each_entry(term, &terms->terms, list) { + if (drm_pmu__config_term(drm, attr, term, err)) + return -EINVAL; + } + + return 0; +} + +int drm_pmu__check_alias(const struct perf_pmu *pmu, struct parse_events_terms *terms, + struct perf_pmu_info *info, struct parse_events_error *err) +{ + struct drm_pmu *drm = container_of(pmu, struct drm_pmu, pmu); + struct parse_events_term *term = + list_first_entry(&terms->terms, struct parse_events_term, list); + + if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) { + int i = drm_pmu__index_for_event(drm, term->config); + + if (i >= 0) { + info->unit = drm_pmu_unit_strs[drm->events[i].unit]; + info->scale = 1; + return 0; + } + } + if (err) { + char *err_str; + + parse_events_error__handle(err, term->err_val, + asprintf(&err_str, + "unexpected drm event term (%s) %s", + parse_events__term_type_str(term->type_term), + term->config) < 0 + ? strdup("unexpected drm event term") + : err_str, + NULL); + } + return -EINVAL; +} + +struct minor_info { + unsigned int *minors; + int minors_num, minors_len; +}; + +static int for_each_drm_fdinfo_in_dir(int (*cb)(void *args, int fdinfo_dir_fd, const char *fd_name), + void *args, int proc_dir, const char *pid_name, + struct minor_info *minors) +{ + char buf[256]; + DIR *fd_dir; + struct dirent *fd_entry; + int fd_dir_fd, fdinfo_dir_fd = -1; + + + scnprintf(buf, sizeof(buf), "%s/fd", pid_name); + fd_dir_fd = openat(proc_dir, buf, O_DIRECTORY); + if (fd_dir_fd == -1) + return 0; /* Presumably lost race to open. */ + fd_dir = fdopendir(fd_dir_fd); + if (!fd_dir) { + close(fd_dir_fd); + return -ENOMEM; + } + while ((fd_entry = readdir(fd_dir)) != NULL) { + struct stat stat; + unsigned int minor; + bool is_dup = false; + int ret; + + if (fd_entry->d_type != DT_LNK) + continue; + + if (fstatat(fd_dir_fd, fd_entry->d_name, &stat, 0) != 0) + continue; + + if ((stat.st_mode & S_IFMT) != S_IFCHR || major(stat.st_rdev) != 226) + continue; + + minor = minor(stat.st_rdev); + for (int i = 0; i < minors->minors_num; i++) { + if (minor(stat.st_rdev) == minors->minors[i]) { + is_dup = true; + break; + } + } + if (is_dup) + continue; + + if (minors->minors_num == minors->minors_len) { + unsigned int *tmp = reallocarray(minors->minors, minors->minors_len + 4, + sizeof(unsigned int)); + + if (tmp) { + minors->minors = tmp; + minors->minors_len += 4; + } + } + minors->minors[minors->minors_num++] = minor; + if (fdinfo_dir_fd == -1) { + /* Open fdinfo dir if we have a DRM fd. */ + scnprintf(buf, sizeof(buf), "%s/fdinfo", pid_name); + fdinfo_dir_fd = openat(proc_dir, buf, O_DIRECTORY); + if (fdinfo_dir_fd == -1) + continue; + } + ret = cb(args, fdinfo_dir_fd, fd_entry->d_name); + if (ret) + goto close_fdinfo; + } + +close_fdinfo: + if (fdinfo_dir_fd != -1) + close(fdinfo_dir_fd); + closedir(fd_dir); + return 0; +} + +static int for_each_drm_fdinfo(bool skip_all_duplicates, + int (*cb)(void *args, int fdinfo_dir_fd, const char *fd_name), + void *args) +{ + DIR *proc_dir; + struct dirent *proc_entry; + int ret; + /* + * minors maintains an array of DRM minor device numbers seen for a pid, + * or for all pids if skip_all_duplicates is true, so that duplicates + * are ignored. + */ + struct minor_info minors = { + .minors = NULL, + .minors_num = 0, + .minors_len = 0, + }; + + proc_dir = opendir(procfs__mountpoint()); + if (!proc_dir) + return 0; + + /* Walk through the /proc directory. */ + while ((proc_entry = readdir(proc_dir)) != NULL) { + if (proc_entry->d_type != DT_DIR || + !isdigit(proc_entry->d_name[0])) + continue; + if (!skip_all_duplicates) { + /* Reset the seen minor numbers for each pid. */ + minors.minors_num = 0; + } + ret = for_each_drm_fdinfo_in_dir(cb, args, + dirfd(proc_dir), proc_entry->d_name, + &minors); + if (ret) + break; + } + free(minors.minors); + closedir(proc_dir); + return ret; +} + +int perf_pmus__read_drm_pmus(struct list_head *pmus) +{ + return for_each_drm_fdinfo(/*skip_all_duplicates=*/true, read_drm_pmus_cb, pmus); +} + +int evsel__drm_pmu_open(struct evsel *evsel, + struct perf_thread_map *threads, + int start_cpu_map_idx, int end_cpu_map_idx) +{ + (void)evsel; + (void)threads; + (void)start_cpu_map_idx; + (void)end_cpu_map_idx; + return 0; +} + +static uint64_t read_count_and_apply_unit(const char *count_and_unit, enum drm_pmu_unit unit) +{ + char *unit_ptr = NULL; + uint64_t count = strtoul(count_and_unit, &unit_ptr, 10); + + if (!unit_ptr) + return 0; + + while (isblank(*unit_ptr)) + unit_ptr++; + + switch (unit) { + case DRM_PMU_UNIT_BYTES: + if (*unit_ptr == '\0') + assert(count == 0); /* Generally undocumented, happens for 0. */ + else if (!strcmp(unit_ptr, "KiB")) + count *= 1024; + else if (!strcmp(unit_ptr, "MiB")) + count *= 1024 * 1024; + else + pr_err("Unexpected bytes unit '%s'\n", unit_ptr); + break; + case DRM_PMU_UNIT_CAPACITY: + /* No units expected. */ + break; + case DRM_PMU_UNIT_CYCLES: + /* No units expected. */ + break; + case DRM_PMU_UNIT_HZ: + if (!strcmp(unit_ptr, "Hz")) + count *= 1; + else if (!strcmp(unit_ptr, "KHz")) + count *= 1000; + else if (!strcmp(unit_ptr, "MHz")) + count *= 1000000; + else + pr_err("Unexpected hz unit '%s'\n", unit_ptr); + break; + case DRM_PMU_UNIT_NS: + /* Only unit ns expected. */ + break; + case DRM_PMU_UNIT_MAX: + default: + break; + } + return count; +} + +static uint64_t read_drm_event(int fdinfo_dir_fd, const char *fd_name, + const char *match, enum drm_pmu_unit unit) +{ + char buf[640]; + struct io io; + char *line = NULL; + size_t line_len; + uint64_t count = 0; + + io__init(&io, openat(fdinfo_dir_fd, fd_name, O_RDONLY), buf, sizeof(buf)); + if (io.fd == -1) { + /* Failed to open file, ignore. */ + return 0; + } + while (io__getline(&io, &line, &line_len) > 0) { + size_t i = strlen(match); + + if (strncmp(line, match, i)) + continue; + if (line[i] != ':') + continue; + while (isblank(line[++i])) + ; + if (line[line_len - 1] == '\n') + line[line_len - 1] = '\0'; + count = read_count_and_apply_unit(&line[i], unit); + break; + } + free(line); + close(io.fd); + return count; +} + +struct read_drm_event_cb_args { + const char *match; + uint64_t count; + enum drm_pmu_unit unit; +}; + +static int read_drm_event_cb(void *vargs, int fdinfo_dir_fd, const char *fd_name) +{ + struct read_drm_event_cb_args *args = vargs; + + args->count += read_drm_event(fdinfo_dir_fd, fd_name, args->match, args->unit); + return 0; +} + +static uint64_t drm_pmu__read_system_wide(struct drm_pmu *drm, struct evsel *evsel) +{ + struct read_drm_event_cb_args args = { + .count = 0, + .match = drm->events[evsel->core.attr.config].name, + .unit = drm->events[evsel->core.attr.config].unit, + }; + + for_each_drm_fdinfo(/*skip_all_duplicates=*/false, read_drm_event_cb, &args); + return args.count; +} + +static uint64_t drm_pmu__read_for_pid(struct drm_pmu *drm, struct evsel *evsel, int pid) +{ + struct read_drm_event_cb_args args = { + .count = 0, + .match = drm->events[evsel->core.attr.config].name, + .unit = drm->events[evsel->core.attr.config].unit, + }; + struct minor_info minors = { + .minors = NULL, + .minors_num = 0, + .minors_len = 0, + }; + int proc_dir = open(procfs__mountpoint(), O_DIRECTORY); + char pid_name[12]; + int ret; + + if (proc_dir < 0) + return 0; + + snprintf(pid_name, sizeof(pid_name), "%d", pid); + ret = for_each_drm_fdinfo_in_dir(read_drm_event_cb, &args, proc_dir, pid_name, &minors); + free(minors.minors); + close(proc_dir); + return ret == 0 ? args.count : 0; +} + +int evsel__drm_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) +{ + struct drm_pmu *drm = container_of(evsel->pmu, struct drm_pmu, pmu); + struct perf_counts_values *count, *old_count = NULL; + int pid = perf_thread_map__pid(evsel->core.threads, thread); + uint64_t counter; + + if (pid != -1) + counter = drm_pmu__read_for_pid(drm, evsel, pid); + else + counter = drm_pmu__read_system_wide(drm, evsel); + + if (evsel->prev_raw_counts) + old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); + + count = perf_counts(evsel->counts, cpu_map_idx, thread); + if (old_count) { + count->val = old_count->val + counter; + count->run = old_count->run + 1; + count->ena = old_count->ena + 1; + } else { + count->val = counter; + count->run++; + count->ena++; + } + return 0; +} diff --git a/tools/perf/util/drm_pmu.h b/tools/perf/util/drm_pmu.h new file mode 100644 index 000000000000..e7f366fca8a4 --- /dev/null +++ b/tools/perf/util/drm_pmu.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __DRM_PMU_H +#define __DRM_PMU_H +/* + * Linux DRM clients expose information through usage stats as documented in + * Documentation/gpu/drm-usage-stats.rst (available online at + * https://docs.kernel.org/gpu/drm-usage-stats.html). This is a tool like PMU + * that exposes DRM information. + */ + +#include "pmu.h" +#include <stdbool.h> + +struct list_head; +struct perf_thread_map; + +void drm_pmu__exit(struct perf_pmu *pmu); +bool drm_pmu__have_event(const struct perf_pmu *pmu, const char *name); +int drm_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb); +size_t drm_pmu__num_events(const struct perf_pmu *pmu); +int drm_pmu__config_terms(const struct perf_pmu *pmu, + struct perf_event_attr *attr, + struct parse_events_terms *terms, + struct parse_events_error *err); +int drm_pmu__check_alias(const struct perf_pmu *pmu, struct parse_events_terms *terms, + struct perf_pmu_info *info, struct parse_events_error *err); + + +bool perf_pmu__is_drm(const struct perf_pmu *pmu); +bool evsel__is_drm(const struct evsel *evsel); + +int perf_pmus__read_drm_pmus(struct list_head *pmus); + +int evsel__drm_pmu_open(struct evsel *evsel, + struct perf_thread_map *threads, + int start_cpu_map_idx, int end_cpu_map_idx); +int evsel__drm_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread); + +#endif /* __DRM_PMU_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 5c6e85fdae0d..b791e1b6b2cf 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -32,6 +32,7 @@ #include "string2.h" #include "vdso.h" #include "annotate-data.h" +#include "libdw.h" static const char * const debuglink_paths[] = { "%.0s%s", @@ -67,6 +68,7 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', [DSO_BINARY_TYPE__GUEST_KMODULE_COMP] = 'M', [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', + [DSO_BINARY_TYPE__GNU_DEBUGDATA] = 'n', }; if (dso == NULL || dso__symtab_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) @@ -93,6 +95,7 @@ bool dso__is_object_file(const struct dso *dso) case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: case DSO_BINARY_TYPE__GUEST_KMODULE: case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: @@ -109,7 +112,7 @@ bool dso__is_object_file(const struct dso *dso) int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, - char *root_dir, char *filename, size_t size) + const char *root_dir, char *filename, size_t size) { char build_id_hex[SBUILD_ID_SIZE]; int ret = 0; @@ -215,7 +218,7 @@ int dso__read_binary_type_filename(const struct dso *dso, break; } - build_id__sprintf(dso__bid_const(dso), build_id_hex); + build_id__snprintf(dso__bid(dso), build_id_hex, sizeof(build_id_hex)); len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/"); snprintf(filename + len, size - len, "%.2s/%s.debug", build_id_hex, build_id_hex + 2); @@ -224,6 +227,7 @@ int dso__read_binary_type_filename(const struct dso *dso, case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: __symbol__join_symfs(filename, size, dso__long_name(dso)); break; @@ -490,11 +494,25 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, /* * Global list of open DSOs and the counter. */ +struct mutex _dso__data_open_lock; static LIST_HEAD(dso__data_open); -static long dso__data_open_cnt; -static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER; +static long dso__data_open_cnt GUARDED_BY(_dso__data_open_lock); -static void dso__list_add(struct dso *dso) +static void dso__data_open_lock_init(void) +{ + mutex_init(&_dso__data_open_lock); +} + +static struct mutex *dso__data_open_lock(void) LOCK_RETURNED(_dso__data_open_lock) +{ + static pthread_once_t data_open_lock_once = PTHREAD_ONCE_INIT; + + pthread_once(&data_open_lock_once, dso__data_open_lock_init); + + return &_dso__data_open_lock; +} + +static void dso__list_add(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { list_add_tail(&dso__data(dso)->open_entry, &dso__data_open); #ifdef REFCNT_CHECKING @@ -505,11 +523,13 @@ static void dso__list_add(struct dso *dso) dso__data_open_cnt++; } -static void dso__list_del(struct dso *dso) +static void dso__list_del(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { list_del_init(&dso__data(dso)->open_entry); #ifdef REFCNT_CHECKING + mutex_unlock(dso__data_open_lock()); dso__put(dso__data(dso)->dso); + mutex_lock(dso__data_open_lock()); #endif WARN_ONCE(dso__data_open_cnt <= 0, "DSO data fd counter out of bounds."); @@ -518,18 +538,15 @@ static void dso__list_del(struct dso *dso) static void close_first_dso(void); -static int do_open(char *name) +static int do_open(char *name) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { - int fd; - char sbuf[STRERR_BUFSIZE]; - do { - fd = open(name, O_RDONLY|O_CLOEXEC); + int fd = open(name, O_RDONLY|O_CLOEXEC); + if (fd >= 0) return fd; - pr_debug("dso open failed: %s\n", - str_error_r(errno, sbuf, sizeof(sbuf))); + pr_debug("dso open failed: %m\n"); if (!dso__data_open_cnt || errno != EMFILE) break; @@ -544,19 +561,15 @@ char *dso__filename_with_chroot(const struct dso *dso, const char *filename) return filename_with_chroot(nsinfo__pid(dso__nsinfo_const(dso)), filename); } -static int __open_dso(struct dso *dso, struct machine *machine) +static char *dso__get_filename(struct dso *dso, const char *root_dir, + bool *decomp) { - int fd = -EINVAL; - char *root_dir = (char *)""; char *name = malloc(PATH_MAX); - bool decomp = false; - if (!name) - return -ENOMEM; + *decomp = false; - mutex_lock(dso__lock(dso)); - if (machine) - root_dir = machine->root_dir; + if (name == NULL) + return NULL; if (dso__read_binary_type_filename(dso, dso__binary_type(dso), root_dir, name, PATH_MAX)) @@ -581,20 +594,38 @@ static int __open_dso(struct dso *dso, struct machine *machine) size_t len = sizeof(newpath); if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) { - fd = -(*dso__load_errno(dso)); + errno = *dso__load_errno(dso); goto out; } - decomp = true; + *decomp = true; strcpy(name, newpath); } + return name; + +out: + free(name); + return NULL; +} - fd = do_open(name); +static int __open_dso(struct dso *dso, struct machine *machine) + EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) +{ + int fd = -EINVAL; + char *name; + bool decomp = false; + + mutex_lock(dso__lock(dso)); + + name = dso__get_filename(dso, machine ? machine->root_dir : "", &decomp); + if (name) + fd = do_open(name); + else + fd = -errno; if (decomp) unlink(name); -out: mutex_unlock(dso__lock(dso)); free(name); return fd; @@ -610,6 +641,7 @@ static void check_data_close(void); * list/count of open DSO objects. */ static int open_dso(struct dso *dso, struct machine *machine) + EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { int fd; struct nscookie nsc; @@ -635,7 +667,7 @@ static int open_dso(struct dso *dso, struct machine *machine) return fd; } -static void close_data_fd(struct dso *dso) +static void close_data_fd(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { if (dso__data(dso)->fd >= 0) { close(dso__data(dso)->fd); @@ -652,12 +684,12 @@ static void close_data_fd(struct dso *dso) * Close @dso's data file descriptor and updates * list/count of open DSO objects. */ -static void close_dso(struct dso *dso) +static void close_dso(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { close_data_fd(dso); } -static void close_first_dso(void) +static void close_first_dso(void) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { struct dso_data *dso_data; struct dso *dso; @@ -702,7 +734,7 @@ void reset_fd_limit(void) fd_limit = 0; } -static bool may_cache_fd(void) +static bool may_cache_fd(void) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { if (!fd_limit) fd_limit = get_fd_limit(); @@ -718,7 +750,7 @@ static bool may_cache_fd(void) * for opened dso file descriptors. The limit is half * of the RLIMIT_NOFILE files opened. */ -static void check_data_close(void) +static void check_data_close(void) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { bool cache_fd = may_cache_fd(); @@ -734,12 +766,13 @@ static void check_data_close(void) */ void dso__data_close(struct dso *dso) { - pthread_mutex_lock(&dso__data_open_lock); + mutex_lock(dso__data_open_lock()); close_dso(dso); - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); } static void try_to_open_dso(struct dso *dso, struct machine *machine) + EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { enum dso_binary_type binary_type_data[] = { DSO_BINARY_TYPE__BUILD_ID_CACHE, @@ -781,25 +814,27 @@ out: * returns file descriptor. It should be paired with * dso__data_put_fd() if it returns non-negative value. */ -int dso__data_get_fd(struct dso *dso, struct machine *machine) +bool dso__data_get_fd(struct dso *dso, struct machine *machine, int *fd) { + *fd = -1; if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR) - return -1; + return false; - if (pthread_mutex_lock(&dso__data_open_lock) < 0) - return -1; + mutex_lock(dso__data_open_lock()); try_to_open_dso(dso, machine); - if (dso__data(dso)->fd < 0) - pthread_mutex_unlock(&dso__data_open_lock); + *fd = dso__data(dso)->fd; + if (*fd >= 0) + return true; - return dso__data(dso)->fd; + mutex_unlock(dso__data_open_lock()); + return false; } void dso__data_put_fd(struct dso *dso __maybe_unused) { - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); } bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by) @@ -951,7 +986,7 @@ static ssize_t file_read(struct dso *dso, struct machine *machine, { ssize_t ret; - pthread_mutex_lock(&dso__data_open_lock); + mutex_lock(dso__data_open_lock()); /* * dso__data(dso)->fd might be closed if other thread opened another @@ -967,7 +1002,7 @@ static ssize_t file_read(struct dso *dso, struct machine *machine, ret = pread(dso__data(dso)->fd, data, DSO__DATA_CACHE_SIZE, offset); out: - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); return ret; } @@ -1073,9 +1108,8 @@ static int file_size(struct dso *dso, struct machine *machine) { int ret = 0; struct stat st; - char sbuf[STRERR_BUFSIZE]; - pthread_mutex_lock(&dso__data_open_lock); + mutex_lock(dso__data_open_lock()); /* * dso__data(dso)->fd might be closed if other thread opened another @@ -1091,15 +1125,14 @@ static int file_size(struct dso *dso, struct machine *machine) if (fstat(dso__data(dso)->fd, &st) < 0) { ret = -errno; - pr_err("dso cache fstat failed: %s\n", - str_error_r(errno, sbuf, sizeof(sbuf))); + pr_err("dso cache fstat failed: %m\n"); dso__data(dso)->status = DSO_DATA_STATUS_ERROR; goto out; } dso__data(dso)->file_size = st.st_size; out: - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); return ret; } @@ -1170,6 +1203,149 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, return data_read_write_offset(dso, machine, offset, data, size, true); } +static enum dso_swap_type dso_swap_type__from_elf_data(unsigned char eidata) +{ + static const unsigned int endian = 1; + + switch (eidata) { + case ELFDATA2LSB: + /* We are big endian, DSO is little endian. */ + return (*(unsigned char const *)&endian != 1) ? DSO_SWAP__YES : DSO_SWAP__NO; + case ELFDATA2MSB: + /* We are little endian, DSO is big endian. */ + return (*(unsigned char const *)&endian != 0) ? DSO_SWAP__YES : DSO_SWAP__NO; + default: + return DSO_SWAP__UNSET; + } +} + +/* Reads e_machine from fd, optionally caching data in dso. */ +uint16_t dso__read_e_machine(struct dso *optional_dso, int fd, uint32_t *e_flags) +{ + uint16_t e_machine = EM_NONE; + unsigned char e_ident[EI_NIDENT]; + enum dso_swap_type swap_type; + bool need_e_flags; + + if (e_flags) + *e_flags = 0; + + { + _Static_assert(offsetof(Elf32_Ehdr, e_ident) == 0, "Unexpected offset"); + _Static_assert(offsetof(Elf64_Ehdr, e_ident) == 0, "Unexpected offset"); + } + if (pread(fd, &e_ident, sizeof(e_ident), 0) != sizeof(e_ident)) + return EM_NONE; // Read failed. + + if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) + return EM_NONE; // Not an ELF file. + + if (e_ident[EI_CLASS] == ELFCLASSNONE || e_ident[EI_CLASS] >= ELFCLASSNUM) + return EM_NONE; // Bad ELF class (32 or 64-bit objects). + + if (e_ident[EI_VERSION] != EV_CURRENT) + return EM_NONE; // Bad ELF version. + + swap_type = dso_swap_type__from_elf_data(e_ident[EI_DATA]); + if (swap_type == DSO_SWAP__UNSET) + return EM_NONE; // Bad ELF data encoding. + + /* Cache the need for swapping. */ + if (optional_dso) { + assert(dso__needs_swap(optional_dso) == DSO_SWAP__UNSET || + dso__needs_swap(optional_dso) == swap_type); + dso__set_needs_swap(optional_dso, swap_type); + } + + { + _Static_assert(offsetof(Elf32_Ehdr, e_machine) == 18, "Unexpected offset"); + _Static_assert(offsetof(Elf64_Ehdr, e_machine) == 18, "Unexpected offset"); + } + if (pread(fd, &e_machine, sizeof(e_machine), 18) != sizeof(e_machine)) + return EM_NONE; // e_machine read failed. + + e_machine = DSO_SWAP_TYPE__SWAP(swap_type, uint16_t, e_machine); + if (e_machine >= EM_NUM) + return EM_NONE; // Bad ELF machine number. + +#ifdef NDEBUG + /* In production code the e_flags are only needed on CSKY. */ + need_e_flags = e_flags && e_machine == EM_CSKY; +#else + /* Debug code will always read the e_flags. */ + need_e_flags = e_flags != NULL; +#endif + if (need_e_flags) { + off_t offset = e_ident[EI_CLASS] == ELFCLASS32 + ? offsetof(Elf32_Ehdr, e_flags) + : offsetof(Elf64_Ehdr, e_flags); + + if (pread(fd, e_flags, sizeof(*e_flags), offset) != sizeof(*e_flags)) { + *e_flags = 0; + return EM_NONE; // e_flags read failed. + } + } + return e_machine; +} + +uint16_t dso__e_machine(struct dso *dso, struct machine *machine, uint32_t *e_flags) +{ + uint16_t e_machine = EM_NONE; + int fd; + + switch (dso__binary_type(dso)) { + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: + case DSO_BINARY_TYPE__KCORE: + case DSO_BINARY_TYPE__GUEST_KCORE: + case DSO_BINARY_TYPE__BPF_PROG_INFO: + case DSO_BINARY_TYPE__BPF_IMAGE: + case DSO_BINARY_TYPE__OOL: + case DSO_BINARY_TYPE__JAVA_JIT: + if (e_flags) + *e_flags = EF_HOST; + return EM_HOST; + case DSO_BINARY_TYPE__DEBUGLINK: + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + break; + case DSO_BINARY_TYPE__NOT_FOUND: + default: + if (e_flags) + *e_flags = 0; + return EM_NONE; + } + + mutex_lock(dso__data_open_lock()); + + /* + * dso__data(dso)->fd might be closed if other thread opened another + * file (dso) due to open file limit (RLIMIT_NOFILE). + */ + try_to_open_dso(dso, machine); + fd = dso__data(dso)->fd; + if (fd >= 0) + e_machine = dso__read_e_machine(dso, fd, e_flags); + else if (e_flags) + *e_flags = 0; + + mutex_unlock(dso__data_open_lock()); + return e_machine; +} + /** * dso__data_read_addr - Read data from dso address * @dso: dso object @@ -1263,6 +1439,16 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name, return dso; } +static void __dso__set_long_name_id(struct dso *dso, const char *name, bool name_allocated) +{ + if (dso__long_name_allocated(dso)) + free((char *)dso__long_name(dso)); + + RC_CHK_ACCESS(dso)->long_name = name; + RC_CHK_ACCESS(dso)->long_name_len = strlen(name); + dso__set_long_name_allocated(dso, name_allocated); +} + static void dso__set_long_name_id(struct dso *dso, const char *name, bool name_allocated) { struct dsos *dsos = dso__dsos(dso); @@ -1276,81 +1462,86 @@ static void dso__set_long_name_id(struct dso *dso, const char *name, bool name_a * renaming the dso. */ down_write(&dsos->lock); - } - - if (dso__long_name_allocated(dso)) - free((char *)dso__long_name(dso)); - - RC_CHK_ACCESS(dso)->long_name = name; - RC_CHK_ACCESS(dso)->long_name_len = strlen(name); - dso__set_long_name_allocated(dso, name_allocated); - - if (dsos) { + __dso__set_long_name_id(dso, name, name_allocated); dsos->sorted = false; up_write(&dsos->lock); + } else { + __dso__set_long_name_id(dso, name, name_allocated); } } static int __dso_id__cmp(const struct dso_id *a, const struct dso_id *b) { - if (a->maj > b->maj) return -1; - if (a->maj < b->maj) return 1; - - if (a->min > b->min) return -1; - if (a->min < b->min) return 1; + if (a->mmap2_valid && b->mmap2_valid) { + if (a->maj > b->maj) return -1; + if (a->maj < b->maj) return 1; - if (a->ino > b->ino) return -1; - if (a->ino < b->ino) return 1; + if (a->min > b->min) return -1; + if (a->min < b->min) return 1; - /* - * Synthesized MMAP events have zero ino_generation, avoid comparing - * them with MMAP events with actual ino_generation. - * - * I found it harmful because the mismatch resulted in a new - * dso that did not have a build ID whereas the original dso did have a - * build ID. The build ID was essential because the object was not found - * otherwise. - Adrian - */ - if (a->ino_generation && b->ino_generation) { + if (a->ino > b->ino) return -1; + if (a->ino < b->ino) return 1; + } + if (a->mmap2_ino_generation_valid && b->mmap2_ino_generation_valid) { if (a->ino_generation > b->ino_generation) return -1; if (a->ino_generation < b->ino_generation) return 1; } - + if (build_id__is_defined(&a->build_id) && build_id__is_defined(&b->build_id)) { + if (a->build_id.size != b->build_id.size) + return a->build_id.size < b->build_id.size ? -1 : 1; + return memcmp(a->build_id.data, b->build_id.data, a->build_id.size); + } return 0; } -bool dso_id__empty(const struct dso_id *id) -{ - if (!id) - return true; - - return !id->maj && !id->min && !id->ino && !id->ino_generation; -} +const struct dso_id dso_id_empty = { + { + .maj = 0, + .min = 0, + .ino = 0, + .ino_generation = 0, + }, + .mmap2_valid = false, + .mmap2_ino_generation_valid = false, + { + .size = 0, + } +}; -void __dso__inject_id(struct dso *dso, const struct dso_id *id) +void __dso__improve_id(struct dso *dso, const struct dso_id *id) { struct dsos *dsos = dso__dsos(dso); struct dso_id *dso_id = dso__id(dso); + bool changed = false; /* dsos write lock held by caller. */ - dso_id->maj = id->maj; - dso_id->min = id->min; - dso_id->ino = id->ino; - dso_id->ino_generation = id->ino_generation; - - if (dsos) + if (id->mmap2_valid && !dso_id->mmap2_valid) { + dso_id->maj = id->maj; + dso_id->min = id->min; + dso_id->ino = id->ino; + dso_id->mmap2_valid = true; + changed = true; + } + if (id->mmap2_ino_generation_valid && !dso_id->mmap2_ino_generation_valid) { + dso_id->ino_generation = id->ino_generation; + dso_id->mmap2_ino_generation_valid = true; + changed = true; + } + if (build_id__is_defined(&id->build_id) && !build_id__is_defined(&dso_id->build_id)) { + dso_id->build_id = id->build_id; + changed = true; + } + if (changed && dsos) dsos->sorted = false; } int dso_id__cmp(const struct dso_id *a, const struct dso_id *b) { - /* - * The second is always dso->id, so zeroes if not set, assume passing - * NULL for a means a zeroed id - */ - if (dso_id__empty(a) || dso_id__empty(b)) + if (a == &dso_id_empty || b == &dso_id_empty) { + /* There is no valid data to compare so the comparison always returns identical. */ return 0; + } return __dso_id__cmp(a, b); } @@ -1365,6 +1556,16 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) dso__set_long_name_id(dso, name, name_allocated); } +static void __dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) +{ + if (dso__short_name_allocated(dso)) + free((char *)dso__short_name(dso)); + + RC_CHK_ACCESS(dso)->short_name = name; + RC_CHK_ACCESS(dso)->short_name_len = strlen(name); + dso__set_short_name_allocated(dso, name_allocated); +} + void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) { struct dsos *dsos = dso__dsos(dso); @@ -1378,17 +1579,11 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) * renaming the dso. */ down_write(&dsos->lock); - } - if (dso__short_name_allocated(dso)) - free((char *)dso__short_name(dso)); - - RC_CHK_ACCESS(dso)->short_name = name; - RC_CHK_ACCESS(dso)->short_name_len = strlen(name); - dso__set_short_name_allocated(dso, name_allocated); - - if (dsos) { + __dso__set_short_name(dso, name, name_allocated); dsos->sorted = false; up_write(&dsos->lock); + } else { + __dso__set_short_name(dso, name, name_allocated); } } @@ -1447,7 +1642,6 @@ struct dso *dso__new_id(const char *name, const struct dso_id *id) dso->loaded = 0; dso->rel = 0; dso->sorted_by_name = 0; - dso->has_build_id = 0; dso->has_srcline = 1; dso->a2l_fails = 1; dso->kernel = DSO_SPACE__USER; @@ -1501,6 +1695,7 @@ void dso__delete(struct dso *dso) auxtrace_cache__free(RC_CHK_ACCESS(dso)->auxtrace_cache); dso_cache__free(dso); dso__free_a2l(dso); + dso__free_libdw(dso); dso__free_symsrc_filename(dso); nsinfo__zput(RC_CHK_ACCESS(dso)->nsinfo); mutex_destroy(dso__lock(dso)); @@ -1519,21 +1714,36 @@ struct dso *dso__get(struct dso *dso) void dso__put(struct dso *dso) { +#ifdef REFCNT_CHECKING + if (dso && dso__data(dso) && refcount_read(&RC_CHK_ACCESS(dso)->refcnt) == 2) + dso__data_close(dso); +#endif if (dso && refcount_dec_and_test(&RC_CHK_ACCESS(dso)->refcnt)) dso__delete(dso); else RC_CHK_PUT(dso); } -void dso__set_build_id(struct dso *dso, struct build_id *bid) +int dso__swap_init(struct dso *dso, unsigned char eidata) +{ + enum dso_swap_type type = dso_swap_type__from_elf_data(eidata); + + dso__set_needs_swap(dso, type); + if (type == DSO_SWAP__UNSET) { + pr_err("unrecognized DSO data encoding %d\n", eidata); + return -EINVAL; + } + return 0; +} + +void dso__set_build_id(struct dso *dso, const struct build_id *bid) { - RC_CHK_ACCESS(dso)->bid = *bid; - RC_CHK_ACCESS(dso)->has_build_id = 1; + dso__id(dso)->build_id = *bid; } -bool dso__build_id_equal(const struct dso *dso, struct build_id *bid) +bool dso__build_id_equal(const struct dso *dso, const struct build_id *bid) { - const struct build_id *dso_bid = dso__bid_const(dso); + const struct build_id *dso_bid = dso__bid(dso); if (dso_bid->size > bid->size && dso_bid->size == BUILD_ID_SIZE) { /* @@ -1552,18 +1762,20 @@ bool dso__build_id_equal(const struct dso *dso, struct build_id *bid) void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine) { char path[PATH_MAX]; + struct build_id bid = { .size = 0, }; if (machine__is_default_guest(machine)) return; sprintf(path, "%s/sys/kernel/notes", machine->root_dir); - if (sysfs__read_build_id(path, dso__bid(dso)) == 0) - dso__set_has_build_id(dso); + sysfs__read_build_id(path, &bid); + dso__set_build_id(dso, &bid); } int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir) { char filename[PATH_MAX]; + struct build_id bid = { .size = 0, }; /* * kernel module short names are of the form "[module]" and * we need just "module" here. @@ -1574,9 +1786,8 @@ int dso__kernel_module_get_build_id(struct dso *dso, "%s/sys/module/%.*s/notes/.note.gnu.build-id", root_dir, (int)strlen(name) - 1, name); - if (sysfs__read_build_id(filename, dso__bid(dso)) == 0) - dso__set_has_build_id(dso); - + sysfs__read_build_id(filename, &bid); + dso__set_build_id(dso, &bid); return 0; } @@ -1584,7 +1795,7 @@ static size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) { char sbuild_id[SBUILD_ID_SIZE]; - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); return fprintf(fp, "%s", sbuild_id); } @@ -1608,11 +1819,10 @@ size_t dso__fprintf(struct dso *dso, FILE *fp) enum dso_type dso__type(struct dso *dso, struct machine *machine) { - int fd; + int fd = -1; enum dso_type type = DSO__TYPE_UNKNOWN; - fd = dso__data_get_fd(dso, machine); - if (fd >= 0) { + if (dso__data_get_fd(dso, machine, &fd)) { type = dso__type_fd(fd); dso__data_put_fd(dso); } @@ -1637,10 +1847,8 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen) BUG_ON(buflen == 0); if (errnum >= 0) { - const char *err = str_error_r(errnum, buf, buflen); - - if (err != buf) - scnprintf(buf, buflen, "%s", err); + errno = errnum; + scnprintf(buf, buflen, "%m"); return 0; } @@ -1664,3 +1872,135 @@ bool is_perf_pid_map_name(const char *dso_name) return perf_pid_map_tid(dso_name, &tid); } + +struct find_file_offset_data { + u64 ip; + u64 offset; +}; + +/* This will be called for each PHDR in an ELF binary */ +static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg) +{ + struct find_file_offset_data *data = arg; + + if (start <= data->ip && data->ip < start + len) { + data->offset = pgoff + data->ip - start; + return 1; + } + return 0; +} + +static const u8 *__dso__read_symbol(struct dso *dso, const char *symfs_filename, + u64 start, size_t len, + u8 **out_buf, u64 *out_buf_len, bool *is_64bit) +{ + struct nscookie nsc; + int fd; + ssize_t count; + struct find_file_offset_data data = { + .ip = start, + }; + u8 *code_buf = NULL; + int saved_errno; + + nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); + fd = open(symfs_filename, O_RDONLY); + saved_errno = errno; + nsinfo__mountns_exit(&nsc); + if (fd < 0) { + errno = saved_errno; + return NULL; + } + if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data, is_64bit) <= 0) { + close(fd); + errno = ENOENT; + return NULL; + } + code_buf = malloc(len); + if (code_buf == NULL) { + close(fd); + errno = ENOMEM; + return NULL; + } + count = pread(fd, code_buf, len, data.offset); + saved_errno = errno; + close(fd); + if ((u64)count != len) { + free(code_buf); + errno = saved_errno; + return NULL; + } + *out_buf = code_buf; + *out_buf_len = len; + return code_buf; +} + +/* + * Read a symbol into memory for disassembly by a library like capstone of + * libLLVM. If memory is allocated out_buf holds it. + */ +const u8 *dso__read_symbol(struct dso *dso, const char *symfs_filename, + const struct map *map, const struct symbol *sym, + u8 **out_buf, u64 *out_buf_len, bool *is_64bit) +{ + u64 start = map__rip_2objdump(map, sym->start); + u64 end = map__rip_2objdump(map, sym->end); + size_t len = end - start; + + *out_buf = NULL; + *out_buf_len = 0; + *is_64bit = false; + + if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) { + /* + * Note, there is fallback BPF image disassembly in the objdump + * version but it currently does nothing. + */ + errno = EOPNOTSUPP; + return NULL; + } + if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_PROG_INFO) { +#ifdef HAVE_LIBBPF_SUPPORT + struct bpf_prog_info_node *info_node; + struct perf_bpil *info_linear; + + *is_64bit = sizeof(void *) == sizeof(u64); + info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env, + dso__bpf_prog(dso)->id); + if (!info_node) { + errno = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; + return NULL; + } + info_linear = info_node->info_linear; + assert(len <= info_linear->info.jited_prog_len); + *out_buf_len = len; + return (const u8 *)(uintptr_t)(info_linear->info.jited_prog_insns); +#else + pr_debug("No BPF program disassembly support\n"); + errno = EOPNOTSUPP; + return NULL; +#endif + } + return __dso__read_symbol(dso, symfs_filename, start, len, + out_buf, out_buf_len, is_64bit); +} + +struct debuginfo *dso__debuginfo(struct dso *dso) +{ + char *name; + bool decomp = false; + struct debuginfo *dinfo = NULL; + + mutex_lock(dso__lock(dso)); + + name = dso__get_filename(dso, "", &decomp); + if (name) + dinfo = debuginfo__new(name); + + if (decomp) + unlink(name); + + mutex_unlock(dso__lock(dso)); + free(name); + return dinfo; +} diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bb8e8f444054..ede691e9a249 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -10,6 +10,7 @@ #include <stdio.h> #include <linux/bitops.h> #include "build-id.h" +#include "debuginfo.h" #include "mutex.h" #include <internal/rc_check.h> @@ -20,30 +21,88 @@ struct perf_env; #define DSO__NAME_KALLSYMS "[kernel.kallsyms]" #define DSO__NAME_KCORE "[kernel.kcore]" +/** + * enum dso_binary_type - The kind of DSO generally associated with a memory + * region (struct map). + */ enum dso_binary_type { + /** @DSO_BINARY_TYPE__KALLSYMS: Symbols from /proc/kallsyms file. */ DSO_BINARY_TYPE__KALLSYMS = 0, + /** @DSO_BINARY_TYPE__GUEST_KALLSYMS: Guest /proc/kallsyms file. */ DSO_BINARY_TYPE__GUEST_KALLSYMS, + /** @DSO_BINARY_TYPE__VMLINUX: Path to kernel /boot/vmlinux file. */ DSO_BINARY_TYPE__VMLINUX, + /** @DSO_BINARY_TYPE__GUEST_VMLINUX: Path to guest kernel /boot/vmlinux file. */ DSO_BINARY_TYPE__GUEST_VMLINUX, + /** @DSO_BINARY_TYPE__JAVA_JIT: Symbols from /tmp/perf.map file. */ DSO_BINARY_TYPE__JAVA_JIT, + /** + * @DSO_BINARY_TYPE__DEBUGLINK: Debug file readable from the file path + * in the .gnu_debuglink ELF section of the dso. + */ DSO_BINARY_TYPE__DEBUGLINK, + /** + * @DSO_BINARY_TYPE__BUILD_ID_CACHE: File named after buildid located in + * the buildid cache with an elf filename. + */ DSO_BINARY_TYPE__BUILD_ID_CACHE, + /** + * @DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: File named after buildid + * located in the buildid cache with a debug filename. + */ DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__FEDORA_DEBUGINFO: Debug file in /usr/lib/debug + * with .debug suffix. + */ DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + /** @DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: Debug file in /usr/lib/debug. */ DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: dso__long_name debuginfo + * file in /usr/lib/debug/lib rather than the expected + * /usr/lib/debug/usr/lib. + */ DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__BUILDID_DEBUGINFO: File named after buildid located + * in /usr/lib/debug/.build-id/. + */ DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__GNU_DEBUGDATA: MiniDebuginfo where a compressed + * ELF file is placed in a .gnu_debugdata section. + */ + DSO_BINARY_TYPE__GNU_DEBUGDATA, + /** @DSO_BINARY_TYPE__SYSTEM_PATH_DSO: A regular executable/shared-object file. */ DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + /** @DSO_BINARY_TYPE__GUEST_KMODULE: Guest kernel module .ko file. */ DSO_BINARY_TYPE__GUEST_KMODULE, + /** @DSO_BINARY_TYPE__GUEST_KMODULE_COMP: Guest kernel module .ko.gz file. */ DSO_BINARY_TYPE__GUEST_KMODULE_COMP, + /** @DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: Kernel module .ko file. */ DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + /** @DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: Kernel module .ko.gz file. */ DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP, + /** @DSO_BINARY_TYPE__KCORE: /proc/kcore file. */ DSO_BINARY_TYPE__KCORE, + /** @DSO_BINARY_TYPE__GUEST_KCORE: Guest /proc/kcore file. */ DSO_BINARY_TYPE__GUEST_KCORE, + /** + * @DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: Openembedded/Yocto -dbg + * package debug info. + */ DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + /** @DSO_BINARY_TYPE__BPF_PROG_INFO: jitted BPF code. */ DSO_BINARY_TYPE__BPF_PROG_INFO, + /** @DSO_BINARY_TYPE__BPF_IMAGE: jitted BPF trampoline or dispatcher code. */ DSO_BINARY_TYPE__BPF_IMAGE, + /** + * @DSO_BINARY_TYPE__OOL: out of line code such as kprobe-replaced + * instructions or optimized kprobes or ftrace trampolines. + */ DSO_BINARY_TYPE__OOL, + /** @DSO_BINARY_TYPE__NOT_FOUND: Unknown DSO kind. */ DSO_BINARY_TYPE__NOT_FOUND, }; @@ -101,12 +160,11 @@ enum dso_load_errno { __DSO_LOAD_ERRNO__END, }; -#define DSO__SWAP(dso, type, val) \ +#define DSO_SWAP_TYPE__SWAP(swap_type, type, val) \ ({ \ type ____r = val; \ - enum dso_swap_type ___dst = dso__needs_swap(dso); \ - BUG_ON(___dst == DSO_SWAP__UNSET); \ - if (___dst == DSO_SWAP__YES) { \ + BUG_ON(swap_type == DSO_SWAP__UNSET); \ + if (swap_type == DSO_SWAP__YES) { \ switch (sizeof(____r)) { \ case 2: \ ____r = bswap_16(val); \ @@ -124,17 +182,38 @@ enum dso_load_errno { ____r; \ }) +#define DSO__SWAP(dso, type, val) DSO_SWAP_TYPE__SWAP(dso__needs_swap(dso), type, val) + #define DSO__DATA_CACHE_SIZE 4096 #define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1) -/* - * Data about backing storage DSO, comes from PERF_RECORD_MMAP2 meta events +/** + * struct dso_id + * + * Data about backing storage DSO, comes from PERF_RECORD_MMAP2 meta events, + * reading from /proc/pid/maps or synthesis of build_ids from DSOs. Possibly + * incomplete at any particular use. */ struct dso_id { - u32 maj; - u32 min; - u64 ino; - u64 ino_generation; + /* Data related to the mmap2 event or read from /proc/pid/maps. */ + struct { + u32 maj; + u32 min; + u64 ino; + u64 ino_generation; + }; + /** @mmap2_valid: Are the maj, min and ino fields valid? */ + bool mmap2_valid; + /** + * @mmap2_ino_generation_valid: Is the ino_generation valid? Generally + * false for /proc/pid/maps mmap event. + */ + bool mmap2_ino_generation_valid; + /** + * @build_id: A possibly populated build_id. build_id__is_defined checks + * whether it is populated. + */ + struct build_id build_id; }; struct dso_cache { @@ -154,10 +233,12 @@ struct dso_data { int status; u32 status_seen; u64 file_size; +#ifdef HAVE_LIBUNWIND_SUPPORT u64 elf_base_addr; u64 debug_frame_offset; u64 eh_frame_hdr_addr; u64 eh_frame_hdr_offset; +#endif }; struct dso_bpf_prog { @@ -183,16 +264,13 @@ DECLARE_RC_STRUCT(dso) { u64 addr; struct symbol *symbol; } last_find_result; - struct build_id bid; u64 text_offset; u64 text_end; const char *short_name; const char *long_name; void *a2l; + void *libdw; char *symsrc_filename; -#if defined(__powerpc__) - void *dwfl; /* DWARF debug info */ -#endif struct nsinfo *nsinfo; struct auxtrace_cache *auxtrace_cache; union { /* Tool specific area */ @@ -216,12 +294,12 @@ DECLARE_RC_STRUCT(dso) { enum dso_swap_type needs_swap:2; bool is_kmod:1; u8 adjust_symbols:1; - u8 has_build_id:1; u8 header_build_id:1; u8 has_srcline:1; u8 hit:1; u8 annotate_warned:1; u8 auxtrace_warned:1; + u8 debuginfo_warned:1; u8 short_name_allocated:1; u8 long_name_allocated:1; u8 is_64_bit:1; @@ -231,6 +309,11 @@ DECLARE_RC_STRUCT(dso) { char name[]; }; +extern struct mutex _dso__data_open_lock; +extern const struct dso_id dso_id_empty; + +int dso_id__cmp(const struct dso_id *a, const struct dso_id *b); + /* dso__for_each_symbol - iterate over the symbols of given type * * @dso: the 'struct dso *' in which symbols are iterated @@ -250,6 +333,26 @@ static inline void dso__set_a2l(struct dso *dso, void *val) RC_CHK_ACCESS(dso)->a2l = val; } +static inline void *dso__libdw(const struct dso *dso) +{ + return RC_CHK_ACCESS(dso)->libdw; +} + +static inline void dso__set_libdw(struct dso *dso, void *val) +{ + RC_CHK_ACCESS(dso)->libdw = val; +} + +struct Dwfl; +#ifdef HAVE_LIBDW_SUPPORT +struct Dwfl *dso__libdw_dwfl(struct dso *dso); +#else +static inline struct Dwfl *dso__libdw_dwfl(struct dso *dso __maybe_unused) +{ + return NULL; +} +#endif + static inline unsigned int dso__a2l_fails(const struct dso *dso) { return RC_CHK_ACCESS(dso)->a2l_fails; @@ -280,6 +383,16 @@ static inline void dso__set_annotate_warned(struct dso *dso) RC_CHK_ACCESS(dso)->annotate_warned = 1; } +static inline bool dso__debuginfo_warned(const struct dso *dso) +{ + return RC_CHK_ACCESS(dso)->debuginfo_warned; +} + +static inline void dso__set_debuginfo_warned(struct dso *dso) +{ + RC_CHK_ACCESS(dso)->debuginfo_warned = 1; +} + static inline bool dso__auxtrace_warned(const struct dso *dso) { return RC_CHK_ACCESS(dso)->auxtrace_warned; @@ -300,31 +413,11 @@ static inline void dso__set_auxtrace_cache(struct dso *dso, struct auxtrace_cach RC_CHK_ACCESS(dso)->auxtrace_cache = cache; } -static inline struct build_id *dso__bid(struct dso *dso) -{ - return &RC_CHK_ACCESS(dso)->bid; -} - -static inline const struct build_id *dso__bid_const(const struct dso *dso) -{ - return &RC_CHK_ACCESS(dso)->bid; -} - static inline struct dso_bpf_prog *dso__bpf_prog(struct dso *dso) { return &RC_CHK_ACCESS(dso)->bpf_prog; } -static inline bool dso__has_build_id(const struct dso *dso) -{ - return RC_CHK_ACCESS(dso)->has_build_id; -} - -static inline void dso__set_has_build_id(struct dso *dso) -{ - RC_CHK_ACCESS(dso)->has_build_id = true; -} - static inline bool dso__has_srcline(const struct dso *dso) { return RC_CHK_ACCESS(dso)->has_srcline; @@ -400,6 +493,16 @@ static inline const struct dso_id *dso__id_const(const struct dso *dso) return &RC_CHK_ACCESS(dso)->id; } +static inline const struct build_id *dso__bid(const struct dso *dso) +{ + return &dso__id_const(dso)->build_id; +} + +static inline bool dso__has_build_id(const struct dso *dso) +{ + return build_id__is_defined(dso__bid(dso)); +} + static inline struct rb_root_cached *dso__inlined_nodes(struct dso *dso) { return &RC_CHK_ACCESS(dso)->inlined_nodes; @@ -637,9 +740,6 @@ static inline void dso__set_text_offset(struct dso *dso, u64 val) RC_CHK_ACCESS(dso)->text_offset = val; } -int dso_id__cmp(const struct dso_id *a, const struct dso_id *b); -bool dso_id__empty(const struct dso_id *id); - struct dso *dso__new_id(const char *name, const struct dso_id *id); struct dso *dso__new(const char *name); void dso__delete(struct dso *dso); @@ -647,12 +747,12 @@ void dso__delete(struct dso *dso); int dso__cmp_id(struct dso *a, struct dso *b); void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated); void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated); -void __dso__inject_id(struct dso *dso, const struct dso_id *id); +void __dso__improve_id(struct dso *dso, const struct dso_id *id); int dso__name_len(const struct dso *dso); struct dso *dso__get(struct dso *dso); -void dso__put(struct dso *dso); +void dso__put(struct dso *dso) LOCKS_EXCLUDED(_dso__data_open_lock); static inline void __dso__zput(struct dso **dso) { @@ -675,15 +775,17 @@ bool dso__sorted_by_name(const struct dso *dso); void dso__set_sorted_by_name(struct dso *dso); void dso__sort_by_name(struct dso *dso); -void dso__set_build_id(struct dso *dso, struct build_id *bid); -bool dso__build_id_equal(const struct dso *dso, struct build_id *bid); +int dso__swap_init(struct dso *dso, unsigned char eidata); + +void dso__set_build_id(struct dso *dso, const struct build_id *bid); +bool dso__build_id_equal(const struct dso *dso, const struct build_id *bid); void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine); int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, - char *root_dir, char *filename, size_t size); + const char *root_dir, char *filename, size_t size); bool is_kernel_module(const char *pathname, int cpumode); bool dso__needs_decompress(struct dso *dso); int dso__decompress_kmodule_fd(struct dso *dso, const char *name); @@ -732,8 +834,8 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, * The current usage of the dso__data_* interface is as follows: * * Get DSO's fd: - * int fd = dso__data_get_fd(dso, machine); - * if (fd >= 0) { + * int fd; + * if (dso__data_get_fd(dso, machine, &fd)) { * USE 'fd' SOMEHOW * dso__data_put_fd(dso); * } @@ -755,14 +857,17 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, * * TODO */ -int dso__data_get_fd(struct dso *dso, struct machine *machine); -void dso__data_put_fd(struct dso *dso); -void dso__data_close(struct dso *dso); +bool dso__data_get_fd(struct dso *dso, struct machine *machine, int *fd) + EXCLUSIVE_TRYLOCK_FUNCTION(true, _dso__data_open_lock); +void dso__data_put_fd(struct dso *dso) UNLOCK_FUNCTION(_dso__data_open_lock); +void dso__data_close(struct dso *dso) LOCKS_EXCLUDED(_dso__data_open_lock); int dso__data_file_size(struct dso *dso, struct machine *machine); off_t dso__data_size(struct dso *dso, struct machine *machine); ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size); +uint16_t dso__read_e_machine(struct dso *optional_dso, int fd, uint32_t *e_flags); +uint16_t dso__e_machine(struct dso *dso, struct machine *machine, uint32_t *e_flags); ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); @@ -808,7 +913,9 @@ static inline bool dso__is_kcore(const struct dso *dso) static inline bool dso__is_kallsyms(const struct dso *dso) { - return RC_CHK_ACCESS(dso)->kernel && RC_CHK_ACCESS(dso)->long_name[0] != '/'; + enum dso_binary_type bt = dso__binary_type(dso); + + return bt == DSO_BINARY_TYPE__KALLSYMS || bt == DSO_BINARY_TYPE__GUEST_KALLSYMS; } bool dso__is_object_file(const struct dso *dso); @@ -828,4 +935,10 @@ u64 dso__findnew_global_type(struct dso *dso, u64 addr, u64 offset); bool perf_pid_map_tid(const char *dso_name, int *tid); bool is_perf_pid_map_name(const char *dso_name); +struct debuginfo *dso__debuginfo(struct dso *dso); + +const u8 *dso__read_symbol(struct dso *dso, const char *symfs_filename, + const struct map *map, const struct symbol *sym, + u8 **out_buf, u64 *out_buf_len, bool *is_64bit); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c index e0998e2a7c4e..e927e707abac 100644 --- a/tools/perf/util/dsos.c +++ b/tools/perf/util/dsos.c @@ -6,7 +6,6 @@ #include "vdso.h" #include "namespaces.h" #include <errno.h> -#include <libgen.h> #include <stdlib.h> #include <string.h> #include <symbol.h> // filename__read_build_id @@ -72,6 +71,7 @@ static int dsos__read_build_ids_cb(struct dso *dso, void *data) { struct dsos__read_build_ids_cb_args *args = data; struct nscookie nsc; + struct build_id bid = { .size = 0, }; if (args->with_hits && !dso__hit(dso) && !dso__is_vdso(dso)) return 0; @@ -80,15 +80,15 @@ static int dsos__read_build_ids_cb(struct dso *dso, void *data) return 0; } nsinfo__mountns_enter(dso__nsinfo(dso), &nsc); - if (filename__read_build_id(dso__long_name(dso), dso__bid(dso)) > 0) { + if (filename__read_build_id(dso__long_name(dso), &bid) > 0) { + dso__set_build_id(dso, &bid); args->have_build_id = true; - dso__set_has_build_id(dso); } else if (errno == ENOENT && dso__nsinfo(dso)) { char *new_name = dso__filename_with_chroot(dso, dso__long_name(dso)); - if (new_name && filename__read_build_id(new_name, dso__bid(dso)) > 0) { + if (new_name && filename__read_build_id(new_name, &bid) > 0) { + dso__set_build_id(dso, &bid); args->have_build_id = true; - dso__set_has_build_id(dso); } free(new_name); } @@ -157,6 +157,7 @@ static struct dso *__dsos__find_by_longname_id(struct dsos *dsos, const char *name, const struct dso_id *id, bool write_locked) + SHARED_LOCKS_REQUIRED(dsos->lock) { struct dsos__key key = { .long_name = name, @@ -194,6 +195,9 @@ static struct dso *__dsos__find_by_longname_id(struct dsos *dsos, int __dsos__add(struct dsos *dsos, struct dso *dso) { + if (!dso) + return -EINVAL; + if (dsos->cnt == dsos->allocated) { unsigned int to_allocate = 2; struct dso **temp; @@ -262,6 +266,7 @@ static int dsos__find_id_cb(struct dso *dso, void *data) static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, const struct dso_id *id, bool cmp_short, bool write_locked) + SHARED_LOCKS_REQUIRED(dsos->lock) { struct dso *res; @@ -284,41 +289,28 @@ struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short) struct dso *res; down_read(&dsos->lock); - res = __dsos__find_id(dsos, name, NULL, cmp_short, /*write_locked=*/false); + res = __dsos__find_id(dsos, name, &dso_id_empty, cmp_short, /*write_locked=*/false); up_read(&dsos->lock); return res; } static void dso__set_basename(struct dso *dso) { - char *base, *lname; + bool allocated = false; + const char *base; int tid; if (perf_pid_map_tid(dso__long_name(dso), &tid)) { - if (asprintf(&base, "[JIT] tid %d", tid) < 0) - return; - } else { - /* - * basename() may modify path buffer, so we must pass - * a copy. - */ - lname = strdup(dso__long_name(dso)); - if (!lname) - return; + char *jitname; - /* - * basename() may return a pointer to internal - * storage which is reused in subsequent calls - * so copy the result. - */ - base = strdup(basename(lname)); - - free(lname); - - if (!base) + if (asprintf(&jitname, "[JIT] tid %d", tid) < 0) return; + allocated = true; + base = jitname; + } else { + base = perf_basename(dso__long_name(dso)); } - dso__set_short_name(dso, base, true); + dso__set_short_name(dso, base, allocated); } static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, const struct dso_id *id) @@ -338,11 +330,12 @@ static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, const } static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, const struct dso_id *id) + SHARED_LOCKS_REQUIRED(dsos->lock) { struct dso *dso = __dsos__find_id(dsos, name, id, false, /*write_locked=*/true); - if (dso && dso_id__empty(dso__id(dso)) && !dso_id__empty(id)) - __dso__inject_id(dso, id); + if (dso) + __dso__improve_id(dso, id); return dso ? dso : __dsos__addnew_id(dsos, name, id); } @@ -370,7 +363,7 @@ static int dsos__fprintf_buildid_cb(struct dso *dso, void *data) if (args->skip && args->skip(dso, args->parm)) return 0; - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); args->ret += fprintf(args->fp, "%-40s %s\n", sbuild_id, dso__long_name(dso)); return 0; } @@ -433,7 +426,8 @@ struct dso *dsos__findnew_module_dso(struct dsos *dsos, down_write(&dsos->lock); - dso = __dsos__find_id(dsos, m->name, NULL, /*cmp_short=*/true, /*write_locked=*/true); + dso = __dsos__find_id(dsos, m->name, &dso_id_empty, /*cmp_short=*/true, + /*write_locked=*/true); if (dso) { up_write(&dsos->lock); return dso; diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c deleted file mode 100644 index c1cc0ade48d0..000000000000 --- a/tools/perf/util/dump-insn.c +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/compiler.h> -#include "dump-insn.h" - -/* Fallback code */ - -__weak -const char *dump_insn(struct perf_insn *x __maybe_unused, - u64 ip __maybe_unused, u8 *inbuf __maybe_unused, - int inlen __maybe_unused, int *lenp) -{ - if (lenp) - *lenp = 0; - return "?"; -} - -__weak -int arch_is_uncond_branch(const unsigned char *buf __maybe_unused, - size_t len __maybe_unused, - int x86_64 __maybe_unused) -{ - return 0; -} diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 559c953ca172..92db2fccc788 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -303,6 +303,33 @@ Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) return vr_die; } +/** + * die_get_pointer_type - Get a pointer/array type die + * @type_die: a DIE of a type + * @die_mem: where to store a type DIE + * + * Get a pointer/array type DIE from @type_die. If the type is a typedef or + * qualifier (const, volatile, etc.), follow the chain to find the underlying + * pointer type. + */ +Dwarf_Die *die_get_pointer_type(Dwarf_Die *type_die, Dwarf_Die *die_mem) +{ + int tag; + + do { + tag = dwarf_tag(type_die); + if (tag == DW_TAG_pointer_type || tag == DW_TAG_array_type) + return type_die; + if (tag != DW_TAG_typedef && tag != DW_TAG_const_type && + tag != DW_TAG_restrict_type && tag != DW_TAG_volatile_type && + tag != DW_TAG_shared_type) + return NULL; + type_die = die_get_type(type_die, die_mem); + } while (type_die); + + return NULL; +} + /* Get attribute and translate it as a udata */ static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name, Dwarf_Word *result) @@ -1378,6 +1405,8 @@ struct find_var_data { Dwarf_Addr addr; /* Target register */ unsigned reg; + /* Access data type */ + Dwarf_Die type; /* Access offset, set for global data */ int offset; /* True if the current register is the frame base */ @@ -1388,40 +1417,71 @@ struct find_var_data { #define DWARF_OP_DIRECT_REGS 32 static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data, - u64 addr_offset, u64 addr_type, bool is_pointer) + s64 addr_offset, s64 addr_type, bool is_pointer) { - Dwarf_Die type_die; Dwarf_Word size; + Dwarf_Die ptr_die; + Dwarf_Die *ptr_type; + s64 offset = addr_offset - addr_type; - if (addr_offset == addr_type) { - /* Update offset relative to the start of the variable */ - data->offset = 0; - return true; - } - - if (addr_offset < addr_type) + if (offset < 0) return false; - if (die_get_real_type(die_mem, &type_die) == NULL) + if (__die_get_real_type(die_mem, &data->type) == NULL) return false; - if (is_pointer && dwarf_tag(&type_die) == DW_TAG_pointer_type) { + ptr_type = die_get_pointer_type(&data->type, &ptr_die); + if (is_pointer && ptr_type) { /* Get the target type of the pointer */ - if (die_get_real_type(&type_die, &type_die) == NULL) + if (__die_get_real_type(ptr_type, &data->type) == NULL) return false; } - if (dwarf_aggregate_size(&type_die, &size) < 0) + if (offset == 0) { + /* Update offset relative to the start of the variable */ + data->offset = 0; + return true; + } + + if (dwarf_aggregate_size(&data->type, &size) < 0) return false; - if (addr_offset >= addr_type + size) + if ((u64)offset >= size) return false; /* Update offset relative to the start of the variable */ - data->offset = addr_offset - addr_type; + data->offset = offset; return true; } +/** + * is_breg_access_indirect - Check if breg based access implies type + * dereference + * @ops: DWARF operations array + * @nops: Number of operations in @ops + * + * Returns true if the DWARF expression evaluates to the variable's + * value, so the memory access on that register needs type dereference. + * Returns false if the expression evaluates to the variable's address. + * This is called after check_allowed_ops. + */ +static bool is_breg_access_indirect(Dwarf_Op *ops, size_t nops) +{ + /* only the base register */ + if (nops == 1) + return false; + + if (nops == 2 && ops[1].atom == DW_OP_stack_value) + return true; + + if (nops == 3 && (ops[1].atom == DW_OP_deref || + ops[1].atom == DW_OP_deref_size) && + ops[2].atom == DW_OP_stack_value) + return false; + /* unreachable, OP not supported */ + return false; +} + /* Only checks direct child DIEs in the given scope. */ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg) { @@ -1450,7 +1510,7 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg) if (data->is_fbreg && ops->atom == DW_OP_fbreg && check_allowed_ops(ops, nops) && match_var_offset(die_mem, data, data->offset, ops->number, - /*is_pointer=*/false)) + is_breg_access_indirect(ops, nops))) return DIE_FIND_CB_END; /* Only match with a simple case */ @@ -1462,11 +1522,11 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg) /*is_pointer=*/true)) return DIE_FIND_CB_END; - /* Local variables accessed by a register + offset */ + /* variables accessed by a register + offset */ if (ops->atom == (DW_OP_breg0 + data->reg) && check_allowed_ops(ops, nops) && match_var_offset(die_mem, data, data->offset, ops->number, - /*is_pointer=*/false)) + is_breg_access_indirect(ops, nops))) return DIE_FIND_CB_END; } else { /* pointer variables saved in a register 32 or above */ @@ -1476,11 +1536,11 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg) /*is_pointer=*/true)) return DIE_FIND_CB_END; - /* Local variables accessed by a register + offset */ + /* variables accessed by a register + offset */ if (ops->atom == DW_OP_bregx && data->reg == ops->number && check_allowed_ops(ops, nops) && match_var_offset(die_mem, data, data->offset, ops->number2, - /*is_poitner=*/false)) + is_breg_access_indirect(ops, nops))) return DIE_FIND_CB_END; } } @@ -1500,7 +1560,7 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg) * when the variable is in the stack. */ Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg, - int *poffset, bool is_fbreg, + Dwarf_Die *type_die, int *poffset, bool is_fbreg, Dwarf_Die *die_mem) { struct find_var_data data = { @@ -1512,8 +1572,10 @@ Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg, Dwarf_Die *result; result = die_find_child(sc_die, __die_find_var_reg_cb, &data, die_mem); - if (result) + if (result) { *poffset = data.offset; + *type_die = data.type; + } return result; } @@ -1557,7 +1619,8 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg) * This is usually for global variables. */ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr, - Dwarf_Die *die_mem, int *offset) + Dwarf_Die *die_mem, Dwarf_Die *type_die, + int *offset) { struct find_var_data data = { .addr = addr, @@ -1565,8 +1628,10 @@ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr, Dwarf_Die *result; result = die_find_child(sc_die, __die_find_var_addr_cb, &data, die_mem); - if (result) + if (result) { *offset = data.offset; + *type_die = data.type; + } return result; } @@ -1576,10 +1641,11 @@ static int __die_collect_vars_cb(Dwarf_Die *die_mem, void *arg) Dwarf_Die type_die; int tag = dwarf_tag(die_mem); Dwarf_Attribute attr; - Dwarf_Addr base, start, end; + Dwarf_Addr base, start, end = 0; Dwarf_Op *ops; size_t nops; struct die_var_type *vt; + ptrdiff_t off; if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter) return DIE_FIND_CB_SIBLING; @@ -1587,30 +1653,40 @@ static int __die_collect_vars_cb(Dwarf_Die *die_mem, void *arg) if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL) return DIE_FIND_CB_SIBLING; - /* - * Only collect the first location as it can reconstruct the - * remaining state by following the instructions. - * start = 0 means it covers the whole range. - */ - if (dwarf_getlocations(&attr, 0, &base, &start, &end, &ops, &nops) <= 0) + if (__die_get_real_type(die_mem, &type_die) == NULL) return DIE_FIND_CB_SIBLING; - if (!check_allowed_ops(ops, nops)) - return DIE_FIND_CB_SIBLING; - - if (die_get_real_type(die_mem, &type_die) == NULL) - return DIE_FIND_CB_SIBLING; + /* + * Collect all location entries as variables may have different + * locations across different address ranges. + */ + off = 0; + while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) { + if (!check_allowed_ops(ops, nops)) + continue; - vt = malloc(sizeof(*vt)); - if (vt == NULL) - return DIE_FIND_CB_END; + vt = malloc(sizeof(*vt)); + if (vt == NULL) + return DIE_FIND_CB_END; - vt->die_off = dwarf_dieoffset(&type_die); - vt->addr = start; - vt->reg = reg_from_dwarf_op(ops); - vt->offset = offset_from_dwarf_op(ops); - vt->next = *var_types; - *var_types = vt; + /* Usually a register holds the value of a variable */ + vt->is_reg_var_addr = false; + + if (((ops->atom >= DW_OP_breg0 && ops->atom <= DW_OP_breg31) || + ops->atom == DW_OP_bregx || ops->atom == DW_OP_fbreg) && + !is_breg_access_indirect(ops, nops)) + /* The register contains an address of the variable. */ + vt->is_reg_var_addr = true; + + vt->die_off = dwarf_dieoffset(&type_die); + vt->addr = start; + vt->end = end; + vt->has_range = (end != 0 || start != 0); + vt->reg = reg_from_dwarf_op(ops); + vt->offset = offset_from_dwarf_op(ops); + vt->next = *var_types; + *var_types = vt; + } return DIE_FIND_CB_SIBLING; } @@ -1669,6 +1745,8 @@ static int __die_collect_global_vars_cb(Dwarf_Die *die_mem, void *arg) vt->die_off = dwarf_dieoffset(&type_die); vt->addr = ops->number; + vt->end = 0; + vt->has_range = false; vt->reg = -1; vt->offset = 0; vt->next = *var_types; @@ -1920,6 +1998,7 @@ struct find_scope_data { static int __die_find_scope_cb(Dwarf_Die *die_mem, void *arg) { struct find_scope_data *data = arg; + int tag = dwarf_tag(die_mem); if (dwarf_haspc(die_mem, data->pc)) { Dwarf_Die *tmp; @@ -1933,6 +2012,14 @@ static int __die_find_scope_cb(Dwarf_Die *die_mem, void *arg) data->nr++; return DIE_FIND_CB_CHILD; } + + /* + * If the DIE doesn't have the PC, we still need to check its children + * and siblings if it's a container like a namespace. + */ + if (tag == DW_TAG_namespace) + return DIE_FIND_CB_CONTINUE; + return DIE_FIND_CB_SIBLING; } @@ -2044,13 +2131,28 @@ Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset, tag = dwarf_tag(&mb_type); - if (tag == DW_TAG_structure_type || tag == DW_TAG_union_type) { + if (tag == DW_TAG_structure_type || tag == DW_TAG_union_type || + tag == DW_TAG_array_type) { Dwarf_Word loc; /* Update offset for the start of the member struct */ if (die_get_data_member_location(member, &loc) == 0) offset -= loc; } + + /* Handle array types: resolve to the element type by one level */ + if (tag == DW_TAG_array_type) { + Dwarf_Word size; + + if (die_get_real_type(&mb_type, &mb_type) == NULL) + return NULL; + + if (dwarf_aggregate_size(&mb_type, &size) < 0) + return NULL; + + offset = offset % size; + tag = dwarf_tag(&mb_type); + } } *die_mem = mb_type; return die_mem; diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 892c8c5c23fc..a79968a2e573 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -60,6 +60,8 @@ Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem); Dwarf_Die *__die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem); /* Get a type die, but skip qualifiers and typedef */ Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem); +/* Get a pointer/array type, following typedefs/qualifiers */ +Dwarf_Die *die_get_pointer_type(Dwarf_Die *type_die, Dwarf_Die *die_mem); /* Check whether the DIE is signed or not */ bool die_is_signed_type(Dwarf_Die *tp_die); @@ -146,8 +148,12 @@ struct die_var_type { struct die_var_type *next; u64 die_off; u64 addr; + u64 end; /* end address of location range */ int reg; int offset; + /* Whether the register holds a address to the type */ + bool is_reg_var_addr; + bool has_range; /* whether end is valid */ }; /* Return type info of a member at offset */ @@ -161,12 +167,13 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf); /* Find a variable saved in the 'reg' at given address */ Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg, - int *poffset, bool is_fbreg, + Dwarf_Die *type_die, int *poffset, bool is_fbreg, Dwarf_Die *die_mem); /* Find a (global) variable located in the 'addr' */ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr, - Dwarf_Die *die_mem, int *offset); + Dwarf_Die *die_mem, Dwarf_Die *type_die, + int *offset); /* Save all variables and parameters in this scope */ void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types); diff --git a/tools/perf/util/dwarf-regs-arch/Build b/tools/perf/util/dwarf-regs-arch/Build new file mode 100644 index 000000000000..ceb68ae86fd8 --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/Build @@ -0,0 +1,9 @@ +perf-util-$(CONFIG_LIBDW) += dwarf-regs-arm64.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-arm.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-csky.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-loongarch.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-mips.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-powerpc.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-riscv.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-s390.o +perf-util-$(CONFIG_LIBDW) += dwarf-regs-x86.o diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-arm.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-arm.c new file mode 100644 index 000000000000..42c6c0635612 --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-arm.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <dwarf-regs.h> +#include "../../../arch/arm/include/uapi/asm/perf_regs.h" + +int __get_dwarf_regnum_for_perf_regnum_arm(int perf_regnum) +{ + if (perf_regnum < 0 || perf_regnum >= PERF_REG_ARM_MAX) + return -ENOENT; + + return perf_regnum; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-arm64.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-arm64.c new file mode 100644 index 000000000000..593ca7d4fccc --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-arm64.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <dwarf-regs.h> +#include "../../../arch/arm64/include/uapi/asm/perf_regs.h" + +int __get_dwarf_regnum_for_perf_regnum_arm64(int perf_regnum) +{ + if (perf_regnum < 0 || perf_regnum >= PERF_REG_ARM64_MAX) + return -ENOENT; + + return perf_regnum; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-csky.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-csky.c new file mode 100644 index 000000000000..cb44b774f8d9 --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-csky.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. +// Mapping of DWARF debug register numbers into register names. + +#include <errno.h> +#include <stddef.h> +#include <dwarf-regs.h> +// Ensure the V2 perf reg definitions are included. +#undef __CSKYABIV2__ +#define __CSKYABIV2__ 1 +#include "../../../arch/csky/include/uapi/asm/perf_regs.h" + +#define CSKY_ABIV2_MAX_REGS 73 +static const char * const csky_dwarf_regs_table_abiv2[CSKY_ABIV2_MAX_REGS] = { + /* r0 ~ r8 */ + "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", "%regs2", "%regs3", + /* r9 ~ r15 */ + "%regs4", "%regs5", "%regs6", "%regs7", "%regs8", "%regs9", "%sp", + "%lr", + /* r16 ~ r23 */ + "%exregs0", "%exregs1", "%exregs2", "%exregs3", "%exregs4", + "%exregs5", "%exregs6", "%exregs7", + /* r24 ~ r31 */ + "%exregs8", "%exregs9", "%exregs10", "%exregs11", "%exregs12", + "%exregs13", "%exregs14", "%tls", + "%pc", NULL, NULL, NULL, "%hi", "%lo", NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "%epc", +}; + +#define CSKY_ABIV1_MAX_REGS 57 +static const char * const csky_dwarf_regs_table_abiv1[CSKY_ABIV1_MAX_REGS] = { + /* r0 ~ r8 */ + "%sp", "%regs9", "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", + /* r9 ~ r15 */ + "%regs2", "%regs3", "%regs4", "%regs5", "%regs6", "%regs7", "%regs8", + "%lr", + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "%epc", +}; + +const char *__get_csky_regstr(unsigned int n, unsigned int flags) +{ + if (flags & EF_CSKY_ABIV2) + return (n < CSKY_ABIV2_MAX_REGS) ? csky_dwarf_regs_table_abiv2[n] : NULL; + + return (n < CSKY_ABIV1_MAX_REGS) ? csky_dwarf_regs_table_abiv1[n] : NULL; +} + +static int __get_dwarf_regnum(const char *const *regstr, size_t num_regstr, const char *name) +{ + for (size_t i = 0; i < num_regstr; i++) { + if (regstr[i] && !strcmp(regstr[i], name)) + return i; + } + return -ENOENT; +} + +int __get_csky_regnum(const char *name, unsigned int flags) +{ + if (flags & EF_CSKY_ABIV2) + return __get_dwarf_regnum(csky_dwarf_regs_table_abiv2, CSKY_ABIV2_MAX_REGS, name); + + return __get_dwarf_regnum(csky_dwarf_regs_table_abiv1, CSKY_ABIV1_MAX_REGS, name); +} + +int __get_dwarf_regnum_for_perf_regnum_csky(int perf_regnum, unsigned int flags) +{ + static const int dwarf_csky_regnums[][2] = { + [PERF_REG_CSKY_TLS] = {-ENOENT, 31}, + [PERF_REG_CSKY_LR] = {15, 15}, + [PERF_REG_CSKY_PC] = {-ENOENT, 32}, + /* TODO: PERF_REG_CSKY_SR */ + [PERF_REG_CSKY_SP] = {0, 14}, + /* TODO: PERF_REG_CSKY_ORIG_A0 */ + [PERF_REG_CSKY_A0] = {2, 0}, + [PERF_REG_CSKY_A1] = {3, 1}, + [PERF_REG_CSKY_A2] = {4, 2}, + [PERF_REG_CSKY_A3] = {5, 3}, + [PERF_REG_CSKY_REGS0] = {6, 4}, + [PERF_REG_CSKY_REGS1] = {7, 5}, + [PERF_REG_CSKY_REGS2] = {8, 6}, + [PERF_REG_CSKY_REGS3] = {9, 7}, + [PERF_REG_CSKY_REGS4] = {10, 8}, + [PERF_REG_CSKY_REGS5] = {11, 9}, + [PERF_REG_CSKY_REGS6] = {12, 10}, + [PERF_REG_CSKY_REGS7] = {13, 11}, + [PERF_REG_CSKY_REGS8] = {14, 12}, + [PERF_REG_CSKY_REGS9] = {1, 13}, + [PERF_REG_CSKY_EXREGS0] = {-ENOENT, 16}, + [PERF_REG_CSKY_EXREGS1] = {-ENOENT, 17}, + [PERF_REG_CSKY_EXREGS2] = {-ENOENT, 18}, + [PERF_REG_CSKY_EXREGS3] = {-ENOENT, 19}, + [PERF_REG_CSKY_EXREGS4] = {-ENOENT, 20}, + [PERF_REG_CSKY_EXREGS5] = {-ENOENT, 21}, + [PERF_REG_CSKY_EXREGS6] = {-ENOENT, 22}, + [PERF_REG_CSKY_EXREGS7] = {-ENOENT, 23}, + [PERF_REG_CSKY_EXREGS8] = {-ENOENT, 24}, + [PERF_REG_CSKY_EXREGS9] = {-ENOENT, 25}, + [PERF_REG_CSKY_EXREGS10] = {-ENOENT, 26}, + [PERF_REG_CSKY_EXREGS11] = {-ENOENT, 27}, + [PERF_REG_CSKY_EXREGS12] = {-ENOENT, 28}, + [PERF_REG_CSKY_EXREGS13] = {-ENOENT, 29}, + [PERF_REG_CSKY_EXREGS14] = {-ENOENT, 30}, + /* TODO: PERF_REG_CSKY_HI */ + /* TODO: PERF_REG_CSKY_LO */ + /* TODO: PERF_REG_CSKY_DCSR */ + }; + int idx = 0; + + if (flags & EF_CSKY_ABIV2) + idx++; + + if (perf_regnum < 0 || perf_regnum > (int)ARRAY_SIZE(dwarf_csky_regnums) || + dwarf_csky_regnums[perf_regnum][idx] == 0) + return -ENOENT; + + return dwarf_csky_regnums[perf_regnum][idx]; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-loongarch.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-loongarch.c new file mode 100644 index 000000000000..203077b740a0 --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-loongarch.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <dwarf-regs.h> +#include "../../../arch/loongarch/include/uapi/asm/perf_regs.h" + +int __get_dwarf_regnum_for_perf_regnum_loongarch(int perf_regnum) +{ + if (perf_regnum < 0 || perf_regnum >= PERF_REG_LOONGARCH_MAX) + return -ENOENT; + + return perf_regnum; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-mips.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-mips.c new file mode 100644 index 000000000000..3bb916b45c66 --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-mips.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <dwarf-regs.h> +#include "../../../arch/mips/include/uapi/asm/perf_regs.h" + +int __get_dwarf_regnum_for_perf_regnum_mips(int perf_regnum) +{ + if (perf_regnum == PERF_REG_MIPS_PC) + return 37; + if (perf_regnum < 0 || perf_regnum >= PERF_REG_MIPS_MAX) + return -ENOENT; + + return perf_regnum; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-powerpc.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-powerpc.c new file mode 100644 index 000000000000..51892a09725b --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-powerpc.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2010 Ian Munsie, IBM Corporation. + */ +#include <errno.h> +#include <dwarf-regs.h> +#include "../../../arch/powerpc/include/uapi/asm/perf_regs.h" + +#define PPC_OP(op) (((op) >> 26) & 0x3F) +#define PPC_RA(a) (((a) >> 16) & 0x1f) +#define PPC_RT(t) (((t) >> 21) & 0x1f) +#define PPC_RB(b) (((b) >> 11) & 0x1f) +#define PPC_D(D) ((D) & 0xfffe) +#define PPC_DS(DS) ((DS) & 0xfffc) +#define OP_LD 58 +#define OP_STD 62 + +static int get_source_reg(u32 raw_insn) +{ + return PPC_RA(raw_insn); +} + +static int get_target_reg(u32 raw_insn) +{ + return PPC_RT(raw_insn); +} + +static int get_offset_opcode(u32 raw_insn) +{ + int opcode = PPC_OP(raw_insn); + + /* DS- form */ + if ((opcode == OP_LD) || (opcode == OP_STD)) + return PPC_DS(raw_insn); + else + return PPC_D(raw_insn); +} + +/* + * Fills the required fields for op_loc depending on if it + * is a source or target. + * D form: ins RT,D(RA) -> src_reg1 = RA, offset = D, dst_reg1 = RT + * DS form: ins RT,DS(RA) -> src_reg1 = RA, offset = DS, dst_reg1 = RT + * X form: ins RT,RA,RB -> src_reg1 = RA, src_reg2 = RB, dst_reg1 = RT + */ +void get_powerpc_regs(u32 raw_insn, int is_source, + struct annotated_op_loc *op_loc) +{ + if (is_source) + op_loc->reg1 = get_source_reg(raw_insn); + else + op_loc->reg1 = get_target_reg(raw_insn); + + if (op_loc->multi_regs) + op_loc->reg2 = PPC_RB(raw_insn); + + /* TODO: Implement offset handling for X Form */ + if ((op_loc->mem_ref) && (PPC_OP(raw_insn) != 31)) + op_loc->offset = get_offset_opcode(raw_insn); +} + +int __get_dwarf_regnum_for_perf_regnum_powerpc(int perf_regnum) +{ + static const int dwarf_powerpc_regnums[] = { + [PERF_REG_POWERPC_R0] = 0, + [PERF_REG_POWERPC_R1] = 1, + [PERF_REG_POWERPC_R2] = 2, + [PERF_REG_POWERPC_R3] = 3, + [PERF_REG_POWERPC_R4] = 4, + [PERF_REG_POWERPC_R5] = 5, + [PERF_REG_POWERPC_R6] = 6, + [PERF_REG_POWERPC_R7] = 7, + [PERF_REG_POWERPC_R8] = 8, + [PERF_REG_POWERPC_R9] = 9, + [PERF_REG_POWERPC_R10] = 10, + [PERF_REG_POWERPC_R11] = 11, + [PERF_REG_POWERPC_R12] = 12, + [PERF_REG_POWERPC_R13] = 13, + [PERF_REG_POWERPC_R14] = 14, + [PERF_REG_POWERPC_R15] = 15, + [PERF_REG_POWERPC_R16] = 16, + [PERF_REG_POWERPC_R17] = 17, + [PERF_REG_POWERPC_R18] = 18, + [PERF_REG_POWERPC_R19] = 19, + [PERF_REG_POWERPC_R20] = 20, + [PERF_REG_POWERPC_R21] = 21, + [PERF_REG_POWERPC_R22] = 22, + [PERF_REG_POWERPC_R23] = 23, + [PERF_REG_POWERPC_R24] = 24, + [PERF_REG_POWERPC_R25] = 25, + [PERF_REG_POWERPC_R26] = 26, + [PERF_REG_POWERPC_R27] = 27, + [PERF_REG_POWERPC_R28] = 28, + [PERF_REG_POWERPC_R29] = 29, + [PERF_REG_POWERPC_R30] = 30, + [PERF_REG_POWERPC_R31] = 31, + /* TODO: PERF_REG_POWERPC_NIP */ + [PERF_REG_POWERPC_MSR] = 66, + /* TODO: PERF_REG_POWERPC_ORIG_R3 */ + [PERF_REG_POWERPC_CTR] = 109, + [PERF_REG_POWERPC_LINK] = 108, /* Note, previously in perf encoded as 65? */ + [PERF_REG_POWERPC_XER] = 101, + /* TODO: PERF_REG_POWERPC_CCR */ + /* TODO: PERF_REG_POWERPC_SOFTE */ + /* TODO: PERF_REG_POWERPC_TRAP */ + /* TODO: PERF_REG_POWERPC_DAR */ + /* TODO: PERF_REG_POWERPC_DSISR */ + /* TODO: PERF_REG_POWERPC_SIER */ + /* TODO: PERF_REG_POWERPC_MMCRA */ + /* TODO: PERF_REG_POWERPC_MMCR0 */ + /* TODO: PERF_REG_POWERPC_MMCR1 */ + /* TODO: PERF_REG_POWERPC_MMCR2 */ + /* TODO: PERF_REG_POWERPC_MMCR3 */ + /* TODO: PERF_REG_POWERPC_SIER2 */ + /* TODO: PERF_REG_POWERPC_SIER3 */ + /* TODO: PERF_REG_POWERPC_PMC1 */ + /* TODO: PERF_REG_POWERPC_PMC2 */ + /* TODO: PERF_REG_POWERPC_PMC3 */ + /* TODO: PERF_REG_POWERPC_PMC4 */ + /* TODO: PERF_REG_POWERPC_PMC5 */ + /* TODO: PERF_REG_POWERPC_PMC6 */ + /* TODO: PERF_REG_POWERPC_SDAR */ + /* TODO: PERF_REG_POWERPC_SIAR */ + }; + + if (perf_regnum == 0) + return 0; + + if (perf_regnum < 0 || perf_regnum > (int)ARRAY_SIZE(dwarf_powerpc_regnums) || + dwarf_powerpc_regnums[perf_regnum] == 0) + return -ENOENT; + + return dwarf_powerpc_regnums[perf_regnum]; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-riscv.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-riscv.c new file mode 100644 index 000000000000..090db51aba41 --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-riscv.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <dwarf-regs.h> +#include "../../../arch/riscv/include/uapi/asm/perf_regs.h" + +int __get_dwarf_regnum_for_perf_regnum_riscv(int perf_regnum) +{ + if (perf_regnum < 0 || perf_regnum >= PERF_REG_RISCV_MAX) + return -ENOENT; + + return perf_regnum; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-s390.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-s390.c new file mode 100644 index 000000000000..310a37451bdc --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-s390.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <dwarf-regs.h> +#include "../../../arch/s390/include/uapi/asm/perf_regs.h" + +int __get_dwarf_regnum_for_perf_regnum_s390(int perf_regnum) +{ + static const int dwarf_s390_regnums[] = { + [PERF_REG_S390_R0] = 0, + [PERF_REG_S390_R1] = 1, + [PERF_REG_S390_R2] = 2, + [PERF_REG_S390_R3] = 3, + [PERF_REG_S390_R4] = 4, + [PERF_REG_S390_R5] = 5, + [PERF_REG_S390_R6] = 6, + [PERF_REG_S390_R7] = 7, + [PERF_REG_S390_R8] = 8, + [PERF_REG_S390_R9] = 9, + [PERF_REG_S390_R10] = 10, + [PERF_REG_S390_R11] = 11, + [PERF_REG_S390_R12] = 12, + [PERF_REG_S390_R13] = 13, + [PERF_REG_S390_R14] = 14, + [PERF_REG_S390_R15] = 15, + [PERF_REG_S390_FP0] = 16, + [PERF_REG_S390_FP1] = 20, + [PERF_REG_S390_FP2] = 17, + [PERF_REG_S390_FP3] = 21, + [PERF_REG_S390_FP4] = 18, + [PERF_REG_S390_FP5] = 22, + [PERF_REG_S390_FP6] = 19, + [PERF_REG_S390_FP7] = 23, + [PERF_REG_S390_FP8] = 24, + [PERF_REG_S390_FP9] = 28, + [PERF_REG_S390_FP10] = 25, + [PERF_REG_S390_FP11] = 29, + [PERF_REG_S390_FP12] = 26, + [PERF_REG_S390_FP13] = 30, + [PERF_REG_S390_FP14] = 27, + [PERF_REG_S390_FP15] = 31, + [PERF_REG_S390_MASK] = 64, + [PERF_REG_S390_PC] = 65, + }; + + if (perf_regnum == 0) + return 0; + + if (perf_regnum < 0 || perf_regnum > (int)ARRAY_SIZE(dwarf_s390_regnums) || + dwarf_s390_regnums[perf_regnum] == 0) + return -ENOENT; + + return dwarf_s390_regnums[perf_regnum]; +} diff --git a/tools/perf/util/dwarf-regs-arch/dwarf-regs-x86.c b/tools/perf/util/dwarf-regs-arch/dwarf-regs-x86.c new file mode 100644 index 000000000000..cadef120aeb4 --- /dev/null +++ b/tools/perf/util/dwarf-regs-arch/dwarf-regs-x86.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * dwarf-regs.c : Mapping of DWARF debug register numbers into register names. + * Extracted from probe-finder.c + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + */ + +#include <errno.h> /* for EINVAL */ +#include <string.h> /* for strcmp */ +#include <linux/kernel.h> /* for ARRAY_SIZE */ +#include <dwarf-regs.h> +#include "../../../arch/x86/include/uapi/asm/perf_regs.h" + +struct dwarf_regs_idx { + const char *name; + int dwarf_regnum; +}; + +static const struct dwarf_regs_idx i386_regidx_table[] = { + { "eax", 0 }, { "ax", 0 }, { "al", 0 }, + { "ecx", 1 }, { "cx", 1 }, { "cl", 1 }, + { "edx", 2 }, { "dx", 2 }, { "dl", 2 }, + { "ebx", 3 }, { "bx", 3 }, { "bl", 3 }, + { "esp", 4 }, { "sp", 4 }, { "$stack", 4}, + { "ebp", 5 }, { "bp", 5 }, + { "esi", 6 }, { "si", 6 }, + { "edi", 7 }, { "di", 7 }, + // 8 - Return Address RA + { "eflags", 9}, { "flags", 9}, + // 10 - reserved + { "st0", 11}, + { "st1", 12}, + { "st2", 13}, + { "st3", 14}, + { "st4", 15}, + { "st5", 16}, + { "st6", 17}, + { "st7", 18}, + // 19-20 - reserved + { "xmm0", 21}, + { "xmm1", 22}, + { "xmm2", 23}, + { "xmm3", 24}, + { "xmm4", 25}, + { "xmm5", 26}, + { "xmm6", 27}, + { "xmm7", 28}, + { "mm0", 29}, + { "mm1", 30}, + { "mm2", 31}, + { "mm3", 32}, + { "mm4", 33}, + { "mm5", 34}, + { "mm6", 35}, + { "mm7", 36}, + // 37-38 - unknown + { "mxcsr", 39}, // 128-bit Media Control and Status + { "es", 40}, + { "cs", 41}, + { "ss", 42}, + { "ds", 43}, + { "fs", 44}, + { "gs", 45}, + // 46-47 - reserved + { "tr", 48}, // Task Register + { "ldtr", 49}, // LDT Register + // 50-92 - reserved + { "fs.base", 92}, + { "gs.base", 93}, + // End of regular dwarf registers. + { "eip", DWARF_REG_PC }, { "ip", DWARF_REG_PC }, +}; + +static const struct dwarf_regs_idx x86_64_regidx_table[] = { + { "rax", 0 }, { "eax", 0 }, { "ax", 0 }, { "al", 0 }, + { "rdx", 1 }, { "edx", 1 }, { "dx", 1 }, { "dl", 1 }, + { "rcx", 2 }, { "ecx", 2 }, { "cx", 2 }, { "cl", 2 }, + { "rbx", 3 }, { "edx", 3 }, { "bx", 3 }, { "bl", 3 }, + { "rsi", 4 }, { "esi", 4 }, { "si", 4 }, { "sil", 4 }, + { "rdi", 5 }, { "edi", 5 }, { "di", 5 }, { "dil", 5 }, + { "rbp", 6 }, { "ebp", 6 }, { "bp", 6 }, { "bpl", 6 }, + { "rsp", 7 }, { "esp", 7 }, { "sp", 7 }, { "spl", 7 }, + { "r8", 8 }, { "r8d", 8 }, { "r8w", 8 }, { "r8b", 8 }, + { "r9", 9 }, { "r9d", 9 }, { "r9w", 9 }, { "r9b", 9 }, + { "r10", 10 }, { "r10d", 10 }, { "r10w", 10 }, { "r10b", 10 }, + { "r11", 11 }, { "r11d", 11 }, { "r11w", 11 }, { "r11b", 11 }, + { "r12", 12 }, { "r12d", 12 }, { "r12w", 12 }, { "r12b", 12 }, + { "r13", 13 }, { "r13d", 13 }, { "r13w", 13 }, { "r13b", 13 }, + { "r14", 14 }, { "r14d", 14 }, { "r14w", 14 }, { "r14b", 14 }, + { "r15", 15 }, { "r15d", 15 }, { "r15w", 15 }, { "r15b", 15 }, + // 16 - Return Address RA + { "xmm0", 17}, + { "xmm1", 18}, + { "xmm2", 19}, + { "xmm3", 20}, + { "xmm4", 21}, + { "xmm5", 22}, + { "xmm6", 23}, + { "xmm7", 24}, + { "xmm8", 25}, + { "xmm9", 26}, + { "xmm10", 27}, + { "xmm11", 28}, + { "xmm12", 29}, + { "xmm13", 30}, + { "xmm14", 31}, + { "xmm15", 32}, + { "st0", 33}, + { "st1", 34}, + { "st2", 35}, + { "st3", 36}, + { "st4", 37}, + { "st5", 38}, + { "st6", 39}, + { "st7", 40}, + { "mm0", 41}, + { "mm1", 42}, + { "mm2", 43}, + { "mm3", 44}, + { "mm4", 45}, + { "mm5", 46}, + { "mm6", 47}, + { "mm7", 48}, + { "rflags", 49}, { "eflags", 49}, { "flags", 49}, + { "es", 50}, + { "cs", 51}, + { "ss", 52}, + { "ds", 53}, + { "fs", 54}, + { "gs", 55}, + // 56-47 - reserved + { "fs.base", 58}, + { "gs.base", 59}, + // 60-61 - reserved + { "tr", 62}, // Task Register + { "ldtr", 63}, // LDT Register + { "mxcsr", 64}, // 128-bit Media Control and Status + { "fcw", 65}, // x87 Control Word + { "fsw", 66}, // x87 Status Word + // End of regular dwarf registers. + { "rip", DWARF_REG_PC }, { "eip", DWARF_REG_PC }, { "ip", DWARF_REG_PC }, +}; + +static int get_regnum(const struct dwarf_regs_idx *entries, size_t num_entries, const char *name) +{ + if (*name != '%') + return -EINVAL; + + name++; + for (size_t i = 0; i < num_entries; i++) { + if (!strcmp(entries[i].name, name)) + return entries[i].dwarf_regnum; + } + return -ENOENT; +} + +int __get_dwarf_regnum_i386(const char *name) +{ + return get_regnum(i386_regidx_table, ARRAY_SIZE(i386_regidx_table), name); +} + +int __get_dwarf_regnum_x86_64(const char *name) +{ + return get_regnum(x86_64_regidx_table, ARRAY_SIZE(x86_64_regidx_table), name); +} + +int __get_dwarf_regnum_for_perf_regnum_i386(int perf_regnum) +{ + static const int dwarf_i386_regnums[] = { + [PERF_REG_X86_AX] = 0, + [PERF_REG_X86_BX] = 3, + [PERF_REG_X86_CX] = 1, + [PERF_REG_X86_DX] = 2, + [PERF_REG_X86_SI] = 6, + [PERF_REG_X86_DI] = 7, + [PERF_REG_X86_BP] = 5, + [PERF_REG_X86_SP] = 4, + [PERF_REG_X86_IP] = 8, + [PERF_REG_X86_FLAGS] = 9, + [PERF_REG_X86_CS] = 41, + [PERF_REG_X86_SS] = 42, + [PERF_REG_X86_DS] = 43, + [PERF_REG_X86_ES] = 40, + [PERF_REG_X86_FS] = 44, + [PERF_REG_X86_GS] = 45, + [PERF_REG_X86_XMM0] = 21, + [PERF_REG_X86_XMM1] = 22, + [PERF_REG_X86_XMM2] = 23, + [PERF_REG_X86_XMM3] = 24, + [PERF_REG_X86_XMM4] = 25, + [PERF_REG_X86_XMM5] = 26, + [PERF_REG_X86_XMM6] = 27, + [PERF_REG_X86_XMM7] = 28, + }; + + if (perf_regnum == 0) + return 0; + + if (perf_regnum < 0 || perf_regnum > (int)ARRAY_SIZE(dwarf_i386_regnums) || + dwarf_i386_regnums[perf_regnum] == 0) + return -ENOENT; + + return dwarf_i386_regnums[perf_regnum]; +} + +int __get_dwarf_regnum_for_perf_regnum_x86_64(int perf_regnum) +{ + static const int dwarf_x86_64_regnums[] = { + [PERF_REG_X86_AX] = 0, + [PERF_REG_X86_BX] = 3, + [PERF_REG_X86_CX] = 2, + [PERF_REG_X86_DX] = 1, + [PERF_REG_X86_SI] = 4, + [PERF_REG_X86_DI] = 5, + [PERF_REG_X86_BP] = 6, + [PERF_REG_X86_SP] = 7, + [PERF_REG_X86_IP] = 16, + [PERF_REG_X86_FLAGS] = 49, + [PERF_REG_X86_CS] = 51, + [PERF_REG_X86_SS] = 52, + [PERF_REG_X86_DS] = 53, + [PERF_REG_X86_ES] = 50, + [PERF_REG_X86_FS] = 54, + [PERF_REG_X86_GS] = 55, + [PERF_REG_X86_R8] = 8, + [PERF_REG_X86_R9] = 9, + [PERF_REG_X86_R10] = 10, + [PERF_REG_X86_R11] = 11, + [PERF_REG_X86_R12] = 12, + [PERF_REG_X86_R13] = 13, + [PERF_REG_X86_R14] = 14, + [PERF_REG_X86_R15] = 15, + [PERF_REG_X86_XMM0] = 17, + [PERF_REG_X86_XMM1] = 18, + [PERF_REG_X86_XMM2] = 19, + [PERF_REG_X86_XMM3] = 20, + [PERF_REG_X86_XMM4] = 21, + [PERF_REG_X86_XMM5] = 22, + [PERF_REG_X86_XMM6] = 23, + [PERF_REG_X86_XMM7] = 24, + [PERF_REG_X86_XMM8] = 25, + [PERF_REG_X86_XMM9] = 26, + [PERF_REG_X86_XMM10] = 27, + [PERF_REG_X86_XMM11] = 28, + [PERF_REG_X86_XMM12] = 29, + [PERF_REG_X86_XMM13] = 30, + [PERF_REG_X86_XMM14] = 31, + [PERF_REG_X86_XMM15] = 32, + }; + + if (perf_regnum == 0) + return 0; + + if (perf_regnum < 0 || perf_regnum > (int)ARRAY_SIZE(dwarf_x86_64_regnums) || + dwarf_x86_64_regnums[perf_regnum] == 0) + return -ENOENT; + + return dwarf_x86_64_regnums[perf_regnum]; +} diff --git a/tools/perf/util/dwarf-regs-csky.c b/tools/perf/util/dwarf-regs-csky.c deleted file mode 100644 index d38ef1f07f3e..000000000000 --- a/tools/perf/util/dwarf-regs-csky.c +++ /dev/null @@ -1,50 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. -// Mapping of DWARF debug register numbers into register names. - -#include <stddef.h> -#include <dwarf-regs.h> - -#define CSKY_ABIV2_MAX_REGS 73 -const char *csky_dwarf_regs_table_abiv2[CSKY_ABIV2_MAX_REGS] = { - /* r0 ~ r8 */ - "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", "%regs2", "%regs3", - /* r9 ~ r15 */ - "%regs4", "%regs5", "%regs6", "%regs7", "%regs8", "%regs9", "%sp", - "%lr", - /* r16 ~ r23 */ - "%exregs0", "%exregs1", "%exregs2", "%exregs3", "%exregs4", - "%exregs5", "%exregs6", "%exregs7", - /* r24 ~ r31 */ - "%exregs8", "%exregs9", "%exregs10", "%exregs11", "%exregs12", - "%exregs13", "%exregs14", "%tls", - "%pc", NULL, NULL, NULL, "%hi", "%lo", NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - "%epc", -}; - -#define CSKY_ABIV1_MAX_REGS 57 -const char *csky_dwarf_regs_table_abiv1[CSKY_ABIV1_MAX_REGS] = { - /* r0 ~ r8 */ - "%sp", "%regs9", "%a0", "%a1", "%a2", "%a3", "%regs0", "%regs1", - /* r9 ~ r15 */ - "%regs2", "%regs3", "%regs4", "%regs5", "%regs6", "%regs7", "%regs8", - "%lr", - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - "%epc", -}; - -const char *get_csky_regstr(unsigned int n, unsigned int flags) -{ - if (flags & EF_CSKY_ABIV2) - return (n < CSKY_ABIV2_MAX_REGS) ? csky_dwarf_regs_table_abiv2[n] : NULL; - - return (n < CSKY_ABIV1_MAX_REGS) ? csky_dwarf_regs_table_abiv1[n] : NULL; -} diff --git a/tools/perf/util/dwarf-regs-powerpc.c b/tools/perf/util/dwarf-regs-powerpc.c deleted file mode 100644 index caf77a234c78..000000000000 --- a/tools/perf/util/dwarf-regs-powerpc.c +++ /dev/null @@ -1,61 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Mapping of DWARF debug register numbers into register names. - * - * Copyright (C) 2010 Ian Munsie, IBM Corporation. - */ - -#include <dwarf-regs.h> - -#define PPC_OP(op) (((op) >> 26) & 0x3F) -#define PPC_RA(a) (((a) >> 16) & 0x1f) -#define PPC_RT(t) (((t) >> 21) & 0x1f) -#define PPC_RB(b) (((b) >> 11) & 0x1f) -#define PPC_D(D) ((D) & 0xfffe) -#define PPC_DS(DS) ((DS) & 0xfffc) -#define OP_LD 58 -#define OP_STD 62 - -static int get_source_reg(u32 raw_insn) -{ - return PPC_RA(raw_insn); -} - -static int get_target_reg(u32 raw_insn) -{ - return PPC_RT(raw_insn); -} - -static int get_offset_opcode(u32 raw_insn) -{ - int opcode = PPC_OP(raw_insn); - - /* DS- form */ - if ((opcode == OP_LD) || (opcode == OP_STD)) - return PPC_DS(raw_insn); - else - return PPC_D(raw_insn); -} - -/* - * Fills the required fields for op_loc depending on if it - * is a source or target. - * D form: ins RT,D(RA) -> src_reg1 = RA, offset = D, dst_reg1 = RT - * DS form: ins RT,DS(RA) -> src_reg1 = RA, offset = DS, dst_reg1 = RT - * X form: ins RT,RA,RB -> src_reg1 = RA, src_reg2 = RB, dst_reg1 = RT - */ -void get_powerpc_regs(u32 raw_insn, int is_source, - struct annotated_op_loc *op_loc) -{ - if (is_source) - op_loc->reg1 = get_source_reg(raw_insn); - else - op_loc->reg1 = get_target_reg(raw_insn); - - if (op_loc->multi_regs) - op_loc->reg2 = PPC_RB(raw_insn); - - /* TODO: Implement offset handling for X Form */ - if ((op_loc->mem_ref) && (PPC_OP(raw_insn) != 31)) - op_loc->offset = get_offset_opcode(raw_insn); -} diff --git a/tools/perf/util/dwarf-regs-x86.c b/tools/perf/util/dwarf-regs-x86.c deleted file mode 100644 index 7a55c65e8da6..000000000000 --- a/tools/perf/util/dwarf-regs-x86.c +++ /dev/null @@ -1,50 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * dwarf-regs.c : Mapping of DWARF debug register numbers into register names. - * Extracted from probe-finder.c - * - * Written by Masami Hiramatsu <mhiramat@redhat.com> - */ - -#include <errno.h> /* for EINVAL */ -#include <string.h> /* for strcmp */ -#include <linux/kernel.h> /* for ARRAY_SIZE */ -#include <dwarf-regs.h> - -struct dwarf_regs_idx { - const char *name; - int idx; -}; - -static const struct dwarf_regs_idx x86_regidx_table[] = { - { "rax", 0 }, { "eax", 0 }, { "ax", 0 }, { "al", 0 }, - { "rdx", 1 }, { "edx", 1 }, { "dx", 1 }, { "dl", 1 }, - { "rcx", 2 }, { "ecx", 2 }, { "cx", 2 }, { "cl", 2 }, - { "rbx", 3 }, { "edx", 3 }, { "bx", 3 }, { "bl", 3 }, - { "rsi", 4 }, { "esi", 4 }, { "si", 4 }, { "sil", 4 }, - { "rdi", 5 }, { "edi", 5 }, { "di", 5 }, { "dil", 5 }, - { "rbp", 6 }, { "ebp", 6 }, { "bp", 6 }, { "bpl", 6 }, - { "rsp", 7 }, { "esp", 7 }, { "sp", 7 }, { "spl", 7 }, - { "r8", 8 }, { "r8d", 8 }, { "r8w", 8 }, { "r8b", 8 }, - { "r9", 9 }, { "r9d", 9 }, { "r9w", 9 }, { "r9b", 9 }, - { "r10", 10 }, { "r10d", 10 }, { "r10w", 10 }, { "r10b", 10 }, - { "r11", 11 }, { "r11d", 11 }, { "r11w", 11 }, { "r11b", 11 }, - { "r12", 12 }, { "r12d", 12 }, { "r12w", 12 }, { "r12b", 12 }, - { "r13", 13 }, { "r13d", 13 }, { "r13w", 13 }, { "r13b", 13 }, - { "r14", 14 }, { "r14d", 14 }, { "r14w", 14 }, { "r14b", 14 }, - { "r15", 15 }, { "r15d", 15 }, { "r15w", 15 }, { "r15b", 15 }, - { "rip", DWARF_REG_PC }, -}; - -int get_x86_regnum(const char *name) -{ - unsigned int i; - - if (*name != '%') - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(x86_regidx_table); i++) - if (!strcmp(x86_regidx_table[i].name, name + 1)) - return x86_regidx_table[i].idx; - return -ENOENT; -} diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index 28a1cfdf26d4..797f455eba0d 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -27,11 +27,11 @@ #include "../arch/mips/include/dwarf-regs-table.h" #include "../arch/loongarch/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, unsigned int flags) { + #define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL) + if (machine == EM_NONE) { /* Generic arch - use host arch */ machine = EM_HOST; @@ -46,7 +46,7 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int case EM_AARCH64: return __get_dwarf_regstr(aarch64_regstr_tbl, n); case EM_CSKY: - return get_csky_regstr(n, flags); + return __get_csky_regstr(n, flags); case EM_SH: return __get_dwarf_regstr(sh_regstr_tbl, n); case EM_S390: @@ -69,22 +69,28 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int pr_err("ELF MACHINE %x is not supported.\n", machine); } return NULL; + + #undef __get_dwarf_regstr } -#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 -__weak int get_arch_regnum(const char *name __maybe_unused) +static int __get_dwarf_regnum(const char *const *regstr, size_t num_regstr, const char *name) { - return -ENOTSUP; + for (size_t i = 0; i < num_regstr; i++) { + if (regstr[i] && !strcmp(regstr[i], name)) + return i; + } + return -ENOENT; } -#endif /* Return DWARF register number from architecture register name */ -int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags __maybe_unused) +int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags) { char *regname = strdup(name); int reg = -1; char *p; + #define _get_dwarf_regnum(tbl, name) __get_dwarf_regnum(tbl, ARRAY_SIZE(tbl), name) + if (regname == NULL) return -EINVAL; @@ -98,19 +104,134 @@ int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags machine = EM_HOST; } switch (machine) { -#if EM_HOST != EM_X86_64 && EM_HOST != EM_386 - case EM_HOST: - reg = get_arch_regnum(regname); - break; -#endif case EM_X86_64: - fallthrough; + reg = __get_dwarf_regnum_x86_64(name); + break; case EM_386: - reg = get_x86_regnum(regname); + reg = __get_dwarf_regnum_i386(name); + break; + case EM_ARM: + reg = _get_dwarf_regnum(arm_regstr_tbl, name); + break; + case EM_AARCH64: + reg = _get_dwarf_regnum(aarch64_regstr_tbl, name); + break; + case EM_CSKY: + reg = __get_csky_regnum(name, flags); + break; + case EM_SH: + reg = _get_dwarf_regnum(sh_regstr_tbl, name); + break; + case EM_S390: + reg = _get_dwarf_regnum(s390_regstr_tbl, name); + break; + case EM_PPC: + case EM_PPC64: + reg = _get_dwarf_regnum(powerpc_regstr_tbl, name); + break; + case EM_RISCV: + reg = _get_dwarf_regnum(riscv_regstr_tbl, name); + break; + case EM_SPARC: + case EM_SPARCV9: + reg = _get_dwarf_regnum(sparc_regstr_tbl, name); + break; + case EM_XTENSA: + reg = _get_dwarf_regnum(xtensa_regstr_tbl, name); + break; + case EM_MIPS: + reg = _get_dwarf_regnum(mips_regstr_tbl, name); + break; + case EM_LOONGARCH: + reg = _get_dwarf_regnum(loongarch_regstr_tbl, name); break; default: pr_err("ELF MACHINE %x is not supported.\n", machine); } free(regname); return reg; + + #undef _get_dwarf_regnum +} + +static int get_libdw_frame_nregs(unsigned int machine, unsigned int flags __maybe_unused) +{ + switch (machine) { + case EM_X86_64: + return 17; + case EM_386: + return 9; + case EM_ARM: + return 16; + case EM_AARCH64: + return 97; + case EM_CSKY: + return 38; + case EM_S390: + return 32; + case EM_PPC: + case EM_PPC64: + return 145; + case EM_RISCV: + return 66; + case EM_SPARC: + case EM_SPARCV9: + return 103; + case EM_LOONGARCH: + return 74; + case EM_MIPS: + return 71; + default: + return 0; + } +} + +int get_dwarf_regnum_for_perf_regnum(int perf_regnum, unsigned int machine, + unsigned int flags, bool only_libdw_supported) +{ + int reg; + + switch (machine) { + case EM_X86_64: + reg = __get_dwarf_regnum_for_perf_regnum_x86_64(perf_regnum); + break; + case EM_386: + reg = __get_dwarf_regnum_for_perf_regnum_i386(perf_regnum); + break; + case EM_ARM: + reg = __get_dwarf_regnum_for_perf_regnum_arm(perf_regnum); + break; + case EM_AARCH64: + reg = __get_dwarf_regnum_for_perf_regnum_arm64(perf_regnum); + break; + case EM_CSKY: + reg = __get_dwarf_regnum_for_perf_regnum_csky(perf_regnum, flags); + break; + case EM_PPC: + case EM_PPC64: + reg = __get_dwarf_regnum_for_perf_regnum_powerpc(perf_regnum); + break; + case EM_RISCV: + reg = __get_dwarf_regnum_for_perf_regnum_riscv(perf_regnum); + break; + case EM_S390: + reg = __get_dwarf_regnum_for_perf_regnum_s390(perf_regnum); + break; + case EM_LOONGARCH: + reg = __get_dwarf_regnum_for_perf_regnum_loongarch(perf_regnum); + break; + case EM_MIPS: + reg = __get_dwarf_regnum_for_perf_regnum_mips(perf_regnum); + break; + default: + pr_err("ELF MACHINE %x is not supported.\n", machine); + return -ENOENT; + } + if (reg >= 0 && only_libdw_supported) { + int nregs = get_libdw_frame_nregs(machine, flags); + + if (reg >= nregs) + reg = -ENOENT; + } + return reg; } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index cae4f6d63318..1e54e2c86360 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -3,8 +3,10 @@ #include "debug.h" #include "env.h" #include "util/header.h" -#include "linux/compiler.h" +#include "util/rwsem.h" +#include <linux/compiler.h> #include <linux/ctype.h> +#include <linux/rbtree.h> #include <linux/string.h> #include <linux/zalloc.h> #include "cgroup.h" @@ -17,8 +19,6 @@ #include "strbuf.h" #include "trace/beauty/beauty.h" -struct perf_env perf_env; - #ifdef HAVE_LIBBPF_SUPPORT #include "bpf-event.h" #include "bpf-utils.h" @@ -89,6 +89,20 @@ out: return node; } +void perf_env__iterate_bpf_prog_info(struct perf_env *env, + void (*cb)(struct bpf_prog_info_node *node, + void *data), + void *data) +{ + struct rb_node *first; + + down_read(&env->bpf_progs.lock); + first = rb_first(&env->bpf_progs.infos); + for (struct rb_node *node = first; node != NULL; node = rb_next(node)) + (*cb)(rb_entry(node, struct bpf_prog_info_node, rb_node), data); + up_read(&env->bpf_progs.lock); +} + bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) { bool ret; @@ -174,6 +188,7 @@ static void perf_env__purge_bpf(struct perf_env *env) next = rb_next(&node->rb_node); rb_erase(&node->rb_node, root); zfree(&node->info_linear); + bpf_metadata_free(node->metadata); free(node); } @@ -201,6 +216,34 @@ static void perf_env__purge_bpf(struct perf_env *env __maybe_unused) } #endif // HAVE_LIBBPF_SUPPORT +void free_cpu_domain_info(struct cpu_domain_map **cd_map, u32 schedstat_version, u32 nr) +{ + if (!cd_map) + return; + + for (u32 i = 0; i < nr; i++) { + if (!cd_map[i]) + continue; + + for (u32 j = 0; j < cd_map[i]->nr_domains; j++) { + struct domain_info *d_info = cd_map[i]->domains[j]; + + if (!d_info) + continue; + + if (schedstat_version >= 17) + zfree(&d_info->dname); + + zfree(&d_info->cpumask); + zfree(&d_info->cpulist); + zfree(&d_info); + } + zfree(&cd_map[i]->domains); + zfree(&cd_map[i]); + } + zfree(&cd_map); +} + void perf_env__exit(struct perf_env *env) { int i, j; @@ -250,10 +293,12 @@ void perf_env__exit(struct perf_env *env) zfree(&env->pmu_caps[i].pmu_name); } zfree(&env->pmu_caps); + free_cpu_domain_info(env->cpu_domain, env->schedstat_version, env->nr_cpus_avail); } void perf_env__init(struct perf_env *env) { + memset(env, 0, sizeof(*env)); #ifdef HAVE_LIBBPF_SUPPORT env->bpf_progs.infos = RB_ROOT; env->bpf_progs.btfs = RB_ROOT; @@ -416,6 +461,116 @@ static int perf_env__read_nr_cpus_avail(struct perf_env *env) return env->nr_cpus_avail ? 0 : -ENOENT; } +static int __perf_env__read_core_pmu_caps(const struct perf_pmu *pmu, + int *nr_caps, char ***caps, + unsigned int *max_branches, + unsigned int *br_cntr_nr, + unsigned int *br_cntr_width) +{ + struct perf_pmu_caps *pcaps = NULL; + char *ptr, **tmp; + int ret = 0; + + *nr_caps = 0; + *caps = NULL; + + if (!pmu->nr_caps) + return 0; + + *caps = calloc(pmu->nr_caps, sizeof(char *)); + if (!*caps) + return -ENOMEM; + + tmp = *caps; + list_for_each_entry(pcaps, &pmu->caps, list) { + if (asprintf(&ptr, "%s=%s", pcaps->name, pcaps->value) < 0) { + ret = -ENOMEM; + goto error; + } + + *tmp++ = ptr; + + if (!strcmp(pcaps->name, "branches")) + *max_branches = atoi(pcaps->value); + else if (!strcmp(pcaps->name, "branch_counter_nr")) + *br_cntr_nr = atoi(pcaps->value); + else if (!strcmp(pcaps->name, "branch_counter_width")) + *br_cntr_width = atoi(pcaps->value); + } + *nr_caps = pmu->nr_caps; + return 0; +error: + while (tmp-- != *caps) + zfree(tmp); + zfree(caps); + *nr_caps = 0; + return ret; +} + +int perf_env__read_core_pmu_caps(struct perf_env *env) +{ + struct pmu_caps *pmu_caps; + struct perf_pmu *pmu = NULL; + int nr_pmu, i = 0, j; + int ret; + + nr_pmu = perf_pmus__num_core_pmus(); + + if (!nr_pmu) + return -ENODEV; + + if (nr_pmu == 1) { + pmu = perf_pmus__find_core_pmu(); + if (!pmu) + return -ENODEV; + ret = perf_pmu__caps_parse(pmu); + if (ret < 0) + return ret; + return __perf_env__read_core_pmu_caps(pmu, &env->nr_cpu_pmu_caps, + &env->cpu_pmu_caps, + &env->max_branches, + &env->br_cntr_nr, + &env->br_cntr_width); + } + + pmu_caps = calloc(nr_pmu, sizeof(*pmu_caps)); + if (!pmu_caps) + return -ENOMEM; + + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + if (perf_pmu__caps_parse(pmu) <= 0) + continue; + ret = __perf_env__read_core_pmu_caps(pmu, &pmu_caps[i].nr_caps, + &pmu_caps[i].caps, + &pmu_caps[i].max_branches, + &pmu_caps[i].br_cntr_nr, + &pmu_caps[i].br_cntr_width); + if (ret) + goto error; + + pmu_caps[i].pmu_name = strdup(pmu->name); + if (!pmu_caps[i].pmu_name) { + ret = -ENOMEM; + goto error; + } + i++; + } + + env->nr_pmus_with_caps = nr_pmu; + env->pmu_caps = pmu_caps; + + return 0; +error: + for (i = 0; i < nr_pmu; i++) { + for (j = 0; j < pmu_caps[i].nr_caps; j++) + zfree(&pmu_caps[i].caps[j]); + zfree(&pmu_caps[i].caps); + zfree(&pmu_caps[i].pmu_name); + } + zfree(&pmu_caps); + return ret; +} + const char *perf_env__raw_arch(struct perf_env *env) { return env && !perf_env__read_arch(env) ? env->arch : "unknown"; @@ -543,7 +698,7 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu) for (i = 0; i < env->nr_numa_nodes; i++) { nn = &env->numa_nodes[i]; - nr = max(nr, perf_cpu_map__max(nn->map).cpu); + nr = max(nr, (int)perf_cpu_map__max(nn->map).cpu); } nr++; @@ -563,7 +718,7 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu) for (i = 0; i < env->nr_numa_nodes; i++) { struct perf_cpu tmp; - int j; + unsigned int j; nn = &env->numa_nodes[i]; perf_cpu_map__for_each_cpu(tmp, j, nn->map) @@ -676,3 +831,25 @@ bool x86__is_amd_cpu(void) return is_amd; } + +bool perf_env__is_x86_intel_cpu(struct perf_env *env) +{ + static int is_intel; /* 0: Uninitialized, 1: Yes, -1: No */ + + if (is_intel == 0) + is_intel = env->cpuid && strstarts(env->cpuid, "GenuineIntel") ? 1 : -1; + + return is_intel >= 1 ? true : false; +} + +bool x86__is_intel_cpu(void) +{ + struct perf_env env = { .total_mem = 0, }; + bool is_intel; + + perf_env__cpuid(&env); + is_intel = perf_env__is_x86_intel_cpu(&env); + perf_env__exit(&env); + + return is_intel; +} diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index d90e343cf1fa..c7052ac1f856 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -54,6 +54,19 @@ struct pmu_caps { char *pmu_name; }; +struct domain_info { + u32 domain; + char *dname; + char *cpumask; + char *cpulist; +}; + +struct cpu_domain_map { + u32 cpu; + u32 nr_domains; + struct domain_info **domains; +}; + typedef const char *(arch_syscalls__strerrno_t)(int err); struct perf_env { @@ -61,6 +74,9 @@ struct perf_env { char *os_release; char *version; char *arch; + /* e_machine expanded from 16 to 32-bits for alignment. */ + u32 e_machine; + u32 e_flags; int nr_cpus_online; int nr_cpus_avail; char *cpu_desc; @@ -70,6 +86,8 @@ struct perf_env { unsigned int max_branches; unsigned int br_cntr_nr; unsigned int br_cntr_width; + unsigned int schedstat_version; + unsigned int max_sched_domains; int kernel_is_64_bit; int nr_cmdline; @@ -92,7 +110,9 @@ struct perf_env { char **cpu_pmu_caps; struct cpu_topology_map *cpu; struct cpu_cache_level *caches; + struct cpu_domain_map **cpu_domain; int caches_cnt; + unsigned int cln_size; u32 comp_ratio; u32 comp_ver; u32 comp_type; @@ -150,8 +170,8 @@ enum perf_compress_type { struct bpf_prog_info_node; struct btf_node; -extern struct perf_env perf_env; - +int perf_env__read_core_pmu_caps(struct perf_env *env); +void free_cpu_domain_info(struct cpu_domain_map **cd_map, u32 schedstat_version, u32 nr); void perf_env__exit(struct perf_env *env); int perf_env__kernel_is_64_bit(struct perf_env *env); @@ -174,16 +194,22 @@ const char *perf_env__raw_arch(struct perf_env *env); int perf_env__nr_cpus_avail(struct perf_env *env); void perf_env__init(struct perf_env *env); +#ifdef HAVE_LIBBPF_SUPPORT bool __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); bool perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); +void perf_env__iterate_bpf_prog_info(struct perf_env *env, + void (*cb)(struct bpf_prog_info_node *node, + void *data), + void *data); bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id); +#endif // HAVE_LIBBPF_SUPPORT int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu); char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name, @@ -196,5 +222,7 @@ void perf_env__find_br_cntr_info(struct perf_env *env, bool x86__is_amd_cpu(void); bool perf_env__is_x86_amd_cpu(struct perf_env *env); +bool x86__is_intel_cpu(void); +bool perf_env__is_x86_intel_cpu(struct perf_env *env); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index aac96d5d1917..66f4843bb235 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,15 +1,17 @@ #include <errno.h> #include <fcntl.h> #include <inttypes.h> +#include <linux/compiler.h> #include <linux/kernel.h> #include <linux/types.h> #include <perf/cpumap.h> +#include <perf/event.h> +#include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <linux/perf_event.h> -#include <linux/zalloc.h> #include "cpumap.h" #include "dso.h" #include "event.h" @@ -58,6 +60,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_CGROUP] = "CGROUP", [PERF_RECORD_TEXT_POKE] = "TEXT_POKE", [PERF_RECORD_AUX_OUTPUT_HW_ID] = "AUX_OUTPUT_HW_ID", + [PERF_RECORD_CALLCHAIN_DEFERRED] = "CALLCHAIN_DEFERRED", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -77,6 +80,10 @@ static const char *perf_event__names[] = { [PERF_RECORD_HEADER_FEATURE] = "FEATURE", [PERF_RECORD_COMPRESSED] = "COMPRESSED", [PERF_RECORD_FINISHED_INIT] = "FINISHED_INIT", + [PERF_RECORD_COMPRESSED2] = "COMPRESSED2", + [PERF_RECORD_BPF_METADATA] = "BPF_METADATA", + [PERF_RECORD_SCHEDSTAT_CPU] = "SCHEDSTAT_CPU", + [PERF_RECORD_SCHEDSTAT_DOMAIN] = "SCHEDSTAT_DOMAIN", }; const char *perf_event__name(unsigned int id) @@ -329,7 +336,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) build_id__init(&bid, event->mmap2.build_id, event->mmap2.build_id_size); - build_id__sprintf(&bid, sbuild_id); + build_id__snprintf(&bid, sbuild_id, sizeof(sbuild_id)); return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 " <%s>]: %c%c%c%c %s\n", @@ -448,12 +455,13 @@ int perf_event__exit_del_thread(const struct perf_tool *tool __maybe_unused, size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp) { - return fprintf(fp, " offset: %#"PRI_lx64" size: %#"PRI_lx64" flags: %#"PRI_lx64" [%s%s%s]\n", + return fprintf(fp, " offset: %#"PRI_lx64" size: %#"PRI_lx64" flags: %#"PRI_lx64" [%s%s%s%s]\n", event->aux.aux_offset, event->aux.aux_size, event->aux.flags, event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "", event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "", - event->aux.flags & PERF_AUX_FLAG_PARTIAL ? "P" : ""); + event->aux.flags & PERF_AUX_FLAG_PARTIAL ? "P" : "", + event->aux.flags & PERF_AUX_FLAG_COLLISION ? "C" : ""); } size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp) @@ -503,6 +511,20 @@ size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp) event->bpf.type, event->bpf.flags, event->bpf.id); } +size_t perf_event__fprintf_bpf_metadata(union perf_event *event, FILE *fp) +{ + struct perf_record_bpf_metadata *metadata = &event->bpf_metadata; + size_t ret; + + ret = fprintf(fp, " prog %s\n", metadata->prog_name); + for (__u32 i = 0; i < metadata->nr_entries; i++) { + ret += fprintf(fp, " entry %d: %20s = %s\n", i, + metadata->entries[i].key, + metadata->entries[i].value); + } + return ret; +} + static int text_poke_printer(enum binary_printer_ops op, unsigned int val, void *extra, FILE *fp) { @@ -550,6 +572,56 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *ma return ret; } +size_t perf_event__fprintf_schedstat_cpu(union perf_event *event, FILE *fp) +{ + struct perf_record_schedstat_cpu *cs = &event->schedstat_cpu; + size_t size = fprintf(fp, "\ncpu%u ", cs->cpu); + __u16 version = cs->version; + +#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver) \ + size += fprintf(fp, "%" PRIu64 " ", (uint64_t)cs->_ver._name) + + if (version == 15) { +#include <perf/schedstat-v15.h> + return size; + } else if (version == 16) { +#include <perf/schedstat-v16.h> + return size; + } else if (version == 17) { +#include <perf/schedstat-v17.h> + return size; + } +#undef CPU_FIELD + + return fprintf(fp, "Unsupported /proc/schedstat version %d.\n", + event->schedstat_cpu.version); +} + +size_t perf_event__fprintf_schedstat_domain(union perf_event *event, FILE *fp) +{ + struct perf_record_schedstat_domain *ds = &event->schedstat_domain; + __u16 version = ds->version; + size_t size = fprintf(fp, "\ndomain%u ", ds->domain); + +#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver) \ + size += fprintf(fp, "%" PRIu64 " ", (uint64_t)ds->_ver._name) + + if (version == 15) { +#include <perf/schedstat-v15.h> + return size; + } else if (version == 16) { +#include <perf/schedstat-v16.h> + return size; + } else if (version == 17) { +#include <perf/schedstat-v17.h> + return size; + } +#undef DOMAIN_FIELD + + return fprintf(fp, "Unsupported /proc/schedstat version %d.\n", + event->schedstat_domain.version); +} + size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp) { size_t ret = fprintf(fp, "PERF_RECORD_%s", @@ -600,6 +672,9 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL case PERF_RECORD_AUX_OUTPUT_HW_ID: ret += perf_event__fprintf_aux_output_hw_id(event, fp); break; + case PERF_RECORD_BPF_METADATA: + ret += perf_event__fprintf_bpf_metadata(event, fp); + break; default: ret += fprintf(fp, "\n"); } @@ -622,7 +697,6 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct machine *machine = maps__machine(maps); bool load_map = false; - maps__zput(al->maps); map__zput(al->map); thread__zput(al->thread); al->thread = thread__get(thread); @@ -660,7 +734,6 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return NULL; } - al->maps = maps__get(maps); al->map = maps__find(maps, al->addr); if (al->map != NULL) { /* @@ -767,6 +840,17 @@ int machine__resolve(struct machine *machine, struct addr_location *al, al->socket = env->cpu[al->cpu].socket_id; } + /* Account for possible out-of-order switch events. */ + al->parallelism = max(1, min(machine->parallelism, machine__nr_cpus_avail(machine))); + if (test_bit(al->parallelism, symbol_conf.parallelism_filter)) + al->filtered |= (1 << HIST_FILTER__PARALLELISM); + /* + * Multiply it by some const to avoid precision loss or dealing + * with floats. The multiplier does not matter otherwise since + * we only print it as percents. + */ + al->latency = sample->period * 1000 / al->parallelism; + if (al->map) { if (symbol_conf.dso_list && (!dso || !(strlist__has_entry(symbol_conf.dso_list, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 2744c54f404e..2ea83fdf8a03 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -67,9 +67,15 @@ enum { PERF_IP_FLAG_INTR_DISABLE = 1ULL << 13, PERF_IP_FLAG_INTR_TOGGLE = 1ULL << 14, PERF_IP_FLAG_BRANCH_MISS = 1ULL << 15, + PERF_IP_FLAG_NOT_TAKEN = 1ULL << 16, }; -#define PERF_IP_FLAG_CHARS "bcrosyiABExghDt" +#define PERF_IP_FLAG_CHARS "bcrosyiABExghDtmn" + +#define PERF_ADDITIONAL_STATE_MASK \ + (PERF_IP_FLAG_IN_TX | \ + PERF_IP_FLAG_INTR_DISABLE | \ + PERF_IP_FLAG_INTR_TOGGLE) #define PERF_BRANCH_MASK (\ PERF_IP_FLAG_BRANCH |\ @@ -85,6 +91,10 @@ enum { PERF_IP_FLAG_VMENTRY |\ PERF_IP_FLAG_VMEXIT) +#define PERF_IP_FLAG_BRANCH_EVENT_MASK \ + (PERF_IP_FLAG_BRANCH_MISS | \ + PERF_IP_FLAG_NOT_TAKEN) + #define PERF_MEM_DATA_SRC_NONE \ (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ @@ -107,6 +117,7 @@ enum perf_synth_id { PERF_SYNTH_INTEL_PSB, PERF_SYNTH_INTEL_EVT, PERF_SYNTH_INTEL_IFLAG_CHG, + PERF_SYNTH_POWERPC_VPA_DTL, }; /* @@ -244,6 +255,25 @@ struct perf_synth_intel_iflag_chg { u64 branch_ip; /* If via_branch */ }; +/* + * The powerpc VPA DTL entries are of below format + */ +struct powerpc_vpadtl_entry { + u8 dispatch_reason; + u8 preempt_reason; + u16 processor_id; + u32 enqueue_to_dispatch_time; + u32 ready_to_enqueue_time; + u32 waiting_to_ready_time; + u64 timebase; + u64 fault_addr; + u64 srr0; + u64 srr1; +}; + +extern const char *dispatch_reasons[11]; +extern const char *preempt_reasons[10]; + static inline void *perf_synth__raw_data(void *p) { return p + 4; @@ -360,7 +390,10 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp); size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp); size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_bpf_metadata(union perf_event *event, FILE *fp); size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *machine,FILE *fp); +size_t perf_event__fprintf_schedstat_cpu(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_schedstat_domain(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp); int kallsyms__get_function_start(const char *kallsyms_filename, @@ -380,11 +413,6 @@ extern unsigned int proc_map_timeout; #define PAGE_SIZE_NAME_LEN 32 char *get_page_size_name(u64 size, char *str); -void arch_perf_parse_sample_weight(struct perf_sample *data, const __u64 *array, u64 type); -void arch_perf_synthesize_sample_weight(const struct perf_sample *data, __u64 *array, u64 type); -const char *arch_perf_header_entry(const char *se_header); -int arch_support_sort_key(const char *sort_key); - static inline bool perf_event_header__cpumode_is_guest(u8 cpumode) { return cpumode == PERF_RECORD_MISC_GUEST_KERNEL || diff --git a/tools/perf/util/events_stats.h b/tools/perf/util/events_stats.h index eabd7913c309..dcff697ed252 100644 --- a/tools/perf/util/events_stats.h +++ b/tools/perf/util/events_stats.h @@ -57,6 +57,8 @@ struct events_stats { struct hists_stats { u64 total_period; u64 total_non_filtered_period; + u64 total_latency; + u64 total_non_filtered_latency; u32 nr_samples; u32 nr_non_filtered_samples; u32 nr_lost_samples; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f0dd174e2deb..ee971d15b3c6 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -13,6 +13,7 @@ #include "util/mmap.h" #include "thread_map.h" #include "target.h" +#include "dwarf-regs.h" #include "evlist.h" #include "evsel.h" #include "record.h" @@ -35,6 +36,8 @@ #include "util/util.h" #include "util/env.h" #include "util/intel-tpebs.h" +#include "util/metricgroup.h" +#include "util/strbuf.h" #include <signal.h> #include <unistd.h> #include <sched.h> @@ -82,6 +85,8 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, evlist->ctl_fd.ack = -1; evlist->ctl_fd.pos = -1; evlist->nr_br_cntr = -1; + metricgroup__rblist_init(&evlist->metric_events); + INIT_LIST_HEAD(&evlist->deferred_samples); } struct evlist *evlist__new(void) @@ -94,30 +99,47 @@ struct evlist *evlist__new(void) return evlist; } -struct evlist *evlist__new_default(void) +struct evlist *evlist__new_default(const struct target *target, bool sample_callchains) { struct evlist *evlist = evlist__new(); bool can_profile_kernel; + struct perf_pmu *pmu = NULL; + struct evsel *evsel; + char buf[256]; int err; if (!evlist) return NULL; can_profile_kernel = perf_event_paranoid_check(1); - err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu"); - if (err) { - evlist__delete(evlist); - return NULL; + + if (EM_HOST == EM_S390 && sample_callchains) { + snprintf(buf, sizeof(buf), "software/%s/%s", + target__has_cpu(target) ? "cpu-clock" : "task-clock", + can_profile_kernel ? "P" : "Pu"); + err = parse_event(evlist, buf); + if (err) + goto out_err; + } else { + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + snprintf(buf, sizeof(buf), "%s/cycles/%s", pmu->name, + can_profile_kernel ? "P" : "Pu"); + err = parse_event(evlist, buf); + if (err) + goto out_err; + } } + /* If there is only 1 event a sample identifier isn't necessary. */ if (evlist->core.nr_entries > 1) { - struct evsel *evsel; - evlist__for_each_entry(evlist, evsel) evsel__set_sample_id(evsel, /*can_sample_identifier=*/false); } return evlist; +out_err: + evlist__delete(evlist); + return NULL; } struct evlist *evlist__new_dummy(void) @@ -172,6 +194,7 @@ static void evlist__purge(struct evlist *evlist) void evlist__exit(struct evlist *evlist) { + metricgroup__rblist_exit(&evlist->metric_events); event_enable_timer__exit(&evlist->eet); zfree(&evlist->mmap); zfree(&evlist->overwrite_mmap); @@ -183,7 +206,6 @@ void evlist__delete(struct evlist *evlist) if (evlist == NULL) return; - tpebs_delete(); evlist__free_stats(evlist); evlist__munmap(evlist); evlist__close(evlist); @@ -347,36 +369,107 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, } #endif -struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity) +/* + * Should sched_setaffinity be used with evlist__for_each_cpu? Determine if + * migrating the thread will avoid possibly numerous IPIs. + */ +static bool evlist__use_affinity(struct evlist *evlist) { - struct evlist_cpu_iterator itr = { + struct evsel *pos; + struct perf_cpu_map *used_cpus = NULL; + bool ret = false; + + if (evlist->no_affinity || !evlist->core.user_requested_cpus || + cpu_map__is_dummy(evlist->core.user_requested_cpus)) + return false; + + evlist__for_each_entry(evlist, pos) { + struct perf_cpu_map *intersect; + + if (!perf_pmu__benefits_from_affinity(pos->pmu)) + continue; + + if (evsel__is_dummy_event(pos)) { + /* + * The dummy event is opened on all CPUs so assume >1 + * event with shared CPUs. + */ + ret = true; + break; + } + if (evsel__is_retire_lat(pos)) { + /* + * Retirement latency events are similar to tool ones in + * their implementation, and so don't require affinity. + */ + continue; + } + if (perf_cpu_map__is_empty(used_cpus)) { + /* First benefitting event, we want >1 on a common CPU. */ + used_cpus = perf_cpu_map__get(pos->core.cpus); + continue; + } + if ((pos->core.attr.read_format & PERF_FORMAT_GROUP) && + evsel__leader(pos) != pos) { + /* Skip members of the same sample group. */ + continue; + } + intersect = perf_cpu_map__intersect(used_cpus, pos->core.cpus); + if (!perf_cpu_map__is_empty(intersect)) { + /* >1 event with shared CPUs. */ + perf_cpu_map__put(intersect); + ret = true; + break; + } + perf_cpu_map__put(intersect); + perf_cpu_map__merge(&used_cpus, pos->core.cpus); + } + perf_cpu_map__put(used_cpus); + return ret; +} + +void evlist_cpu_iterator__init(struct evlist_cpu_iterator *itr, struct evlist *evlist) +{ + *itr = (struct evlist_cpu_iterator){ .container = evlist, .evsel = NULL, .cpu_map_idx = 0, .evlist_cpu_map_idx = 0, .evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus), .cpu = (struct perf_cpu){ .cpu = -1}, - .affinity = affinity, + .affinity = NULL, }; if (evlist__empty(evlist)) { /* Ensure the empty list doesn't iterate. */ - itr.evlist_cpu_map_idx = itr.evlist_cpu_map_nr; - } else { - itr.evsel = evlist__first(evlist); - if (itr.affinity) { - itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0); - affinity__set(itr.affinity, itr.cpu.cpu); - itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu); - /* - * If this CPU isn't in the evsel's cpu map then advance - * through the list. - */ - if (itr.cpu_map_idx == -1) - evlist_cpu_iterator__next(&itr); - } + itr->evlist_cpu_map_idx = itr->evlist_cpu_map_nr; + return; + } + + if (evlist__use_affinity(evlist)) { + if (affinity__setup(&itr->saved_affinity) == 0) + itr->affinity = &itr->saved_affinity; } - return itr; + itr->evsel = evlist__first(evlist); + itr->cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0); + if (itr->affinity) + affinity__set(itr->affinity, itr->cpu.cpu); + itr->cpu_map_idx = perf_cpu_map__idx(itr->evsel->core.cpus, itr->cpu); + /* + * If this CPU isn't in the evsel's cpu map then advance + * through the list. + */ + if (itr->cpu_map_idx == -1) + evlist_cpu_iterator__next(itr); +} + +void evlist_cpu_iterator__exit(struct evlist_cpu_iterator *itr) +{ + if (!itr->affinity) + return; + + affinity__cleanup(itr->affinity); + itr->affinity = NULL; } void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr) @@ -406,14 +499,11 @@ void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr) */ if (evlist_cpu_itr->cpu_map_idx == -1) evlist_cpu_iterator__next(evlist_cpu_itr); + } else { + evlist_cpu_iterator__exit(evlist_cpu_itr); } } -bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr) -{ - return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr; -} - static int evsel__strcmp(struct evsel *pos, char *evsel_name) { if (!evsel_name) @@ -441,19 +531,11 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name, bool excl { struct evsel *pos; struct evlist_cpu_iterator evlist_cpu_itr; - struct affinity saved_affinity, *affinity = NULL; bool has_imm = false; - // See explanation in evlist__close() - if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) { - if (affinity__setup(&saved_affinity) < 0) - return; - affinity = &saved_affinity; - } - /* Disable 'immediate' events last */ for (int imm = 0; imm <= 1; imm++) { - evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) { + evlist__for_each_cpu(evlist_cpu_itr, evlist) { pos = evlist_cpu_itr.evsel; if (evsel__strcmp(pos, evsel_name)) continue; @@ -471,7 +553,6 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name, bool excl break; } - affinity__cleanup(affinity); evlist__for_each_entry(evlist, pos) { if (evsel__strcmp(pos, evsel_name)) continue; @@ -511,16 +592,8 @@ static void __evlist__enable(struct evlist *evlist, char *evsel_name, bool excl_ { struct evsel *pos; struct evlist_cpu_iterator evlist_cpu_itr; - struct affinity saved_affinity, *affinity = NULL; - - // See explanation in evlist__close() - if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) { - if (affinity__setup(&saved_affinity) < 0) - return; - affinity = &saved_affinity; - } - evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) { + evlist__for_each_cpu(evlist_cpu_itr, evlist) { pos = evlist_cpu_itr.evsel; if (evsel__strcmp(pos, evsel_name)) continue; @@ -530,7 +603,6 @@ static void __evlist__enable(struct evlist *evlist, char *evsel_name, bool excl_ continue; evsel__enable_cpu(pos, evlist_cpu_itr.cpu_map_idx); } - affinity__cleanup(affinity); evlist__for_each_entry(evlist, pos) { if (evsel__strcmp(pos, evsel_name)) continue; @@ -753,9 +825,8 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist, bool overwrite) { int i; - struct mmap *map; + struct mmap *map = calloc(evlist->core.nr_mmaps, sizeof(struct mmap)); - map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap)); if (!map) return NULL; @@ -1006,8 +1077,7 @@ int evlist__create_maps(struct evlist *evlist, struct target *target) * per-thread data. thread_map__new_str will call * thread_map__new_all_cpus to enumerate all threads. */ - threads = thread_map__new_str(target->pid, target->tid, target->uid, - all_threads); + threads = thread_map__new_str(target->pid, target->tid, all_threads); if (!threads) return -1; @@ -1328,28 +1398,14 @@ void evlist__close(struct evlist *evlist) { struct evsel *evsel; struct evlist_cpu_iterator evlist_cpu_itr; - struct affinity affinity; - /* - * With perf record core.user_requested_cpus is usually NULL. - * Use the old method to handle this for now. - */ - if (!evlist->core.user_requested_cpus || - cpu_map__is_dummy(evlist->core.user_requested_cpus)) { - evlist__for_each_entry_reverse(evlist, evsel) - evsel__close(evsel); - return; - } - - if (affinity__setup(&affinity) < 0) - return; - - evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) { + evlist__for_each_cpu(evlist_cpu_itr, evlist) { + if (evlist_cpu_itr.cpu_map_idx == 0 && evsel__is_retire_lat(evlist_cpu_itr.evsel)) + evsel__tpebs_close(evlist_cpu_itr.evsel); perf_evsel__close_cpu(&evlist_cpu_itr.evsel->core, evlist_cpu_itr.cpu_map_idx); } - affinity__cleanup(&affinity); evlist__for_each_entry_reverse(evlist, evsel) { perf_evsel__free_fd(&evsel->core); perf_evsel__free_id(&evsel->core); @@ -1373,19 +1429,18 @@ static int evlist__create_syswide_maps(struct evlist *evlist) */ cpus = perf_cpu_map__new_online_cpus(); if (!cpus) - goto out; + return -ENOMEM; threads = perf_thread_map__new_dummy(); - if (!threads) - goto out_put; + if (!threads) { + perf_cpu_map__put(cpus); + return -ENOMEM; + } perf_evlist__set_maps(&evlist->core, cpus, threads); - perf_thread_map__put(threads); -out_put: perf_cpu_map__put(cpus); -out: - return -ENOMEM; + return 0; } int evlist__open(struct evlist *evlist) @@ -1576,8 +1631,11 @@ int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct struct evsel *evsel = evlist__event2evsel(evlist, event); int ret; - if (!evsel) + if (!evsel) { + /* Ensure the sample is okay for perf_sample__exit. */ + perf_sample__init(sample, /*all=*/false); return -EFAULT; + } ret = evsel__parse_sample(evsel, event, sample); if (ret) return ret; @@ -1604,14 +1662,14 @@ int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *even int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size) { int printed, value; - char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); switch (err) { case EACCES: case EPERM: + errno = err; printed = scnprintf(buf, size, - "Error:\t%s.\n" - "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg); + "Error:\t%m.\n" + "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting."); value = perf_event_paranoid(); @@ -1638,16 +1696,18 @@ int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size if (first->core.attr.sample_freq < (u64)max_freq) goto out_default; + errno = err; printed = scnprintf(buf, size, - "Error:\t%s.\n" + "Error:\t%m.\n" "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n" "Hint:\tThe current value is %d and %" PRIu64 " is being requested.", - emsg, max_freq, first->core.attr.sample_freq); + max_freq, first->core.attr.sample_freq); break; } default: out_default: - scnprintf(buf, size, "%s", emsg); + errno = err; + scnprintf(buf, size, "%m"); break; } @@ -1656,17 +1716,17 @@ out_default: int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size) { - char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); int pages_attempted = evlist->core.mmap_len / 1024, pages_max_per_user, printed = 0; switch (err) { case EPERM: sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user); + errno = err; printed += scnprintf(buf + printed, size - printed, - "Error:\t%s.\n" + "Error:\t%m.\n" "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n" "Hint:\tTried using %zd kB.\n", - emsg, pages_max_per_user, pages_attempted); + pages_max_per_user, pages_attempted); if (pages_attempted >= pages_max_per_user) { printed += scnprintf(buf + printed, size - printed, @@ -1678,7 +1738,8 @@ int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size "Hint:\tTry using a smaller -m/--mmap-pages value."); break; default: - scnprintf(buf, size, "%s", emsg); + errno = err; + scnprintf(buf, size, "%m"); break; } @@ -1910,8 +1971,8 @@ static int evlist__parse_control_fifo(const char *str, int *ctl_fd, int *ctl_fd_ */ fd = open(s, O_RDWR | O_NONBLOCK | O_CLOEXEC); if (fd < 0) { - pr_err("Failed to open '%s'\n", s); ret = -errno; + pr_err("Failed to open '%s': %m\n", s); goto out_free; } *ctl_fd = fd; @@ -1921,7 +1982,7 @@ static int evlist__parse_control_fifo(const char *str, int *ctl_fd, int *ctl_fd_ /* O_RDWR | O_NONBLOCK means the other end need not be open */ fd = open(p, O_RDWR | O_NONBLOCK | O_CLOEXEC); if (fd < 0) { - pr_err("Failed to open '%s'\n", p); + pr_err("Failed to open '%s': %m\n", p); ret = -errno; goto out_free; } @@ -1935,7 +1996,8 @@ out_free: int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close) { - char *comma = NULL, *endptr = NULL; + const char *comma = NULL; + char *endptr = NULL; *ctl_fd_close = false; @@ -2353,7 +2415,7 @@ int evlist__parse_event_enable_time(struct evlist *evlist, struct record_opts *o eet->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_CLOEXEC); if (eet->timerfd == -1) { err = -errno; - pr_err("timerfd_create failed: %s\n", strerror(errno)); + pr_err("timerfd_create failed: %m\n"); goto free_eet_times; } @@ -2388,7 +2450,7 @@ static int event_enable_timer__set_timer(struct event_enable_timer *eet, int ms) if (timerfd_settime(eet->timerfd, 0, &its, NULL) < 0) { err = -errno; - pr_err("timerfd_settime failed: %s\n", strerror(errno)); + pr_err("timerfd_settime failed: %m\n"); } return err; } @@ -2469,23 +2531,36 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx) return NULL; } -int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf) +void evlist__format_evsels(struct evlist *evlist, struct strbuf *sb, size_t max_length) { - struct evsel *evsel; - int printed = 0; + struct evsel *evsel, *leader = NULL; + bool first = true; evlist__for_each_entry(evlist, evsel) { + struct evsel *new_leader = evsel__leader(evsel); + if (evsel__is_dummy_event(evsel)) continue; - if (size > (strlen(evsel__name(evsel)) + (printed ? 2 : 1))) { - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "," : "", evsel__name(evsel)); - } else { - printed += scnprintf(bf + printed, size - printed, "%s...", printed ? "," : ""); - break; + + if (leader != new_leader && leader && leader->core.nr_members > 1) + strbuf_addch(sb, '}'); + + if (!first) + strbuf_addch(sb, ','); + + if (sb->len > max_length) { + strbuf_addstr(sb, "..."); + return; } - } + if (leader != new_leader && new_leader->core.nr_members > 1) + strbuf_addch(sb, '{'); - return printed; + strbuf_addstr(sb, evsel__name(evsel)); + first = false; + leader = new_leader; + } + if (leader && leader->core.nr_members > 1) + strbuf_addch(sb, '}'); } void evlist__check_mem_load_aux(struct evlist *evlist) @@ -2535,51 +2610,61 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis return; evlist__for_each_entry(evlist, pos) { - struct perf_cpu_map *intersect, *to_test; - const struct perf_pmu *pmu = evsel__find_pmu(pos); + evsel__warn_user_requested_cpus(pos, user_requested_cpus); + } + perf_cpu_map__put(user_requested_cpus); +} - to_test = pmu && pmu->is_core ? pmu->cpus : cpu_map__online(); - intersect = perf_cpu_map__intersect(to_test, user_requested_cpus); - if (!perf_cpu_map__equal(intersect, user_requested_cpus)) { - char buf[128]; +/* Should uniquify be disabled for the evlist? */ +static bool evlist__disable_uniquify(const struct evlist *evlist) +{ + struct evsel *counter; + struct perf_pmu *last_pmu = NULL; + bool first = true; - cpu_map__snprint(to_test, buf, sizeof(buf)); - pr_warning("WARNING: A requested CPU in '%s' is not supported by PMU '%s' (CPUs %s) for event '%s'\n", - cpu_list, pmu ? pmu->name : "cpu", buf, evsel__name(pos)); + evlist__for_each_entry(evlist, counter) { + /* If PMUs vary then uniquify can be useful. */ + if (!first && counter->pmu != last_pmu) + return false; + first = false; + if (counter->pmu) { + /* Allow uniquify for uncore PMUs. */ + if (!counter->pmu->is_core) + return false; + /* Keep hybrid event names uniquified for clarity. */ + if (perf_pmus__num_core_pmus() > 1) + return false; } - perf_cpu_map__put(intersect); + last_pmu = counter->pmu; } - perf_cpu_map__put(user_requested_cpus); + return true; } -void evlist__uniquify_name(struct evlist *evlist) +static bool evlist__set_needs_uniquify(struct evlist *evlist, const struct perf_stat_config *config) { - char *new_name, empty_attributes[2] = ":", *attributes; - struct evsel *pos; - - if (perf_pmus__num_core_pmus() == 1) - return; + struct evsel *counter; + bool needs_uniquify = false; - evlist__for_each_entry(evlist, pos) { - if (!evsel__is_hybrid(pos)) - continue; + if (evlist__disable_uniquify(evlist)) { + evlist__for_each_entry(evlist, counter) + counter->uniquified_name = true; + return false; + } - if (strchr(pos->name, '/')) - continue; + evlist__for_each_entry(evlist, counter) { + if (evsel__set_needs_uniquify(counter, config)) + needs_uniquify = true; + } + return needs_uniquify; +} - attributes = strchr(pos->name, ':'); - if (attributes) - *attributes = '\0'; - else - attributes = empty_attributes; +void evlist__uniquify_evsel_names(struct evlist *evlist, const struct perf_stat_config *config) +{ + if (evlist__set_needs_uniquify(evlist, config)) { + struct evsel *pos; - if (asprintf(&new_name, "%s/%s/%s", pos->pmu ? pos->pmu->name : "", - pos->name, attributes + 1)) { - free(pos->name); - pos->name = new_name; - } else { - *attributes = ':'; - } + evlist__for_each_entry(evlist, pos) + evsel__uniquify_counter(pos); } } @@ -2594,3 +2679,17 @@ bool evlist__has_bpf_output(struct evlist *evlist) return false; } + +bool evlist__needs_bpf_sb_event(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_dummy_event(evsel)) + continue; + if (!evsel->core.attr.exclude_kernel) + return true; + } + + return false; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index adddb1db1ad2..e507f5f20ef6 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -10,8 +10,10 @@ #include <internal/evlist.h> #include <internal/evsel.h> #include <perf/evlist.h> +#include "affinity.h" #include "events_stats.h" #include "evsel.h" +#include "rblist.h" #include <pthread.h> #include <signal.h> #include <unistd.h> @@ -19,7 +21,9 @@ struct pollfd; struct thread_map; struct perf_cpu_map; +struct perf_stat_config; struct record_opts; +struct strbuf; struct target; /* @@ -55,6 +59,7 @@ struct event_enable_timer; struct evlist { struct perf_evlist core; bool enabled; + bool no_affinity; int id_pos; int is_pos; int nr_br_cntr; @@ -68,7 +73,7 @@ struct evlist { struct mmap *overwrite_mmap; struct evsel *selected; struct events_stats stats; - struct perf_env *env; + struct perf_session *session; void (*trace_event_sample_raw)(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); @@ -84,6 +89,13 @@ struct evlist { int pos; /* index at evlist core object to check signals */ } ctl_fd; struct event_enable_timer *eet; + /** + * @metric_events: A list of struct metric_event which each have a list + * of struct metric_expr. + */ + struct rblist metric_events; + /* samples with deferred_callchain would wait here. */ + struct list_head deferred_samples; }; struct evsel_str_handler { @@ -92,7 +104,7 @@ struct evsel_str_handler { }; struct evlist *evlist__new(void); -struct evlist *evlist__new_default(void); +struct evlist *evlist__new_default(const struct target *target, bool sample_callchains); struct evlist *evlist__new_dummy(void); void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, struct perf_thread_map *threads); @@ -103,6 +115,7 @@ void evlist__add(struct evlist *evlist, struct evsel *entry); void evlist__remove(struct evlist *evlist, struct evsel *evsel); int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs); +int arch_evlist__add_required_events(struct list_head *list); int evlist__add_dummy(struct evlist *evlist); struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide); @@ -352,6 +365,8 @@ struct evlist_cpu_iterator { struct perf_cpu cpu; /** If present, used to set the affinity when switching between CPUs. */ struct affinity *affinity; + /** Maybe be used to hold affinity state prior to iterating. */ + struct affinity saved_affinity; }; /** @@ -359,22 +374,31 @@ struct evlist_cpu_iterator { * affinity, iterate over all CPUs and then the evlist * for each evsel on that CPU. When switching between * CPUs the affinity is set to the CPU to avoid IPIs - * during syscalls. + * during syscalls. The affinity is set up and removed + * automatically, if the loop is broken a call to + * evlist_cpu_iterator__exit is necessary. * @evlist_cpu_itr: the iterator instance. * @evlist: evlist instance to iterate. - * @affinity: NULL or used to set the affinity to the current CPU. */ -#define evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) \ - for ((evlist_cpu_itr) = evlist__cpu_begin(evlist, affinity); \ +#define evlist__for_each_cpu(evlist_cpu_itr, evlist) \ + for (evlist_cpu_iterator__init(&(evlist_cpu_itr), evlist); \ !evlist_cpu_iterator__end(&evlist_cpu_itr); \ evlist_cpu_iterator__next(&evlist_cpu_itr)) -/** Returns an iterator set to the first CPU/evsel of evlist. */ -struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity); +/** Setup an iterator set to the first CPU/evsel of evlist. */ +void evlist_cpu_iterator__init(struct evlist_cpu_iterator *itr, struct evlist *evlist); +/** + * Cleans up the iterator, automatically done by evlist_cpu_iterator__next when + * the end of the list is reached. Multiple calls are safe. + */ +void evlist_cpu_iterator__exit(struct evlist_cpu_iterator *itr); /** Move to next element in iterator, updating CPU, evsel and the affinity. */ void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr); /** Returns true when iterator is at the end of the CPUs and evlist. */ -bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr); +static inline bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr) +{ + return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr; +} struct evsel *evlist__get_tracking_event(struct evlist *evlist); void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); @@ -430,10 +454,11 @@ int event_enable_timer__process(struct event_enable_timer *eet); struct evsel *evlist__find_evsel(struct evlist *evlist, int idx); -int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf); +void evlist__format_evsels(struct evlist *evlist, struct strbuf *sb, size_t max_length); void evlist__check_mem_load_aux(struct evlist *evlist); void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list); -void evlist__uniquify_name(struct evlist *evlist); +void evlist__uniquify_evsel_names(struct evlist *evlist, const struct perf_stat_config *config); bool evlist__has_bpf_output(struct evlist *evlist); +bool evlist__needs_bpf_sb_event(struct evlist *evlist); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index bc144388f892..2ee87fd84d3e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -34,6 +34,7 @@ #include "callchain.h" #include "cgroup.h" #include "counts.h" +#include "dwarf-regs.h" #include "event.h" #include "evsel.h" #include "time-utils.h" @@ -48,6 +49,7 @@ #include "record.h" #include "debug.h" #include "trace-event.h" +#include "session.h" #include "stat.h" #include "string2.h" #include "memswap.h" @@ -56,8 +58,10 @@ #include "off_cpu.h" #include "pmu.h" #include "pmus.h" +#include "drm_pmu.h" #include "hwmon_pmu.h" #include "tool_pmu.h" +#include "tp_pmu.h" #include "rlimit.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" @@ -237,6 +241,16 @@ set_methods: return 0; } +const char *evsel__pmu_name(const struct evsel *evsel) +{ + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu) + return pmu->name; + + return event_type(evsel->core.attr.type); +} + #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) int __evsel__sample_size(u64 sample_type) @@ -389,11 +403,11 @@ void evsel__init(struct evsel *evsel, evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); evsel->cmdline_group_boundary = false; - evsel->metric_events = NULL; evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->group_pmu_name = NULL; evsel->skippable = false; + evsel->supported = true; evsel->alternate_hw_config = PERF_COUNT_HW_MAX; evsel->script_output_type = -1; // FIXME: OUTPUT_TYPE_UNSET, see builtin-script.c } @@ -477,7 +491,7 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) return NULL; evsel->core.cpus = perf_cpu_map__get(orig->core.cpus); - evsel->core.own_cpus = perf_cpu_map__get(orig->core.own_cpus); + evsel->core.pmu_cpus = perf_cpu_map__get(orig->core.pmu_cpus); evsel->core.threads = perf_thread_map__get(orig->core.threads); evsel->core.nr_members = orig->core.nr_members; evsel->core.system_wide = orig->core.system_wide; @@ -511,10 +525,21 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) } evsel->cgrp = cgroup__get(orig->cgrp); #ifdef HAVE_LIBTRACEEVENT + if (orig->tp_sys) { + evsel->tp_sys = strdup(orig->tp_sys); + if (evsel->tp_sys == NULL) + goto out_err; + } + if (orig->tp_name) { + evsel->tp_name = strdup(orig->tp_name); + if (evsel->tp_name == NULL) + goto out_err; + } evsel->tp_format = orig->tp_format; #endif evsel->handler = orig->handler; evsel->core.leader = orig->core.leader; + evsel->metric_leader = orig->metric_leader; evsel->max_events = orig->max_events; zfree(&evsel->unit); @@ -532,11 +557,11 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) evsel->exclude_GH = orig->exclude_GH; evsel->sample_read = orig->sample_read; - evsel->auto_merge_stats = orig->auto_merge_stats; evsel->collect_stat = orig->collect_stat; evsel->weak_group = orig->weak_group; evsel->use_config_name = orig->use_config_name; evsel->pmu = orig->pmu; + evsel->first_wildcard_match = orig->first_wildcard_match; if (evsel__copy_config_terms(evsel, orig) < 0) goto out_err; @@ -550,24 +575,6 @@ out_err: return NULL; } -static int trace_event__id(const char *sys, const char *name) -{ - char *tp_dir = get_events_file(sys); - char path[PATH_MAX]; - int id, err; - - if (!tp_dir) - return -1; - - scnprintf(path, PATH_MAX, "%s/%s/id", tp_dir, name); - put_events_file(tp_dir); - err = filename__read_int(path, &id); - if (err) - return err; - - return id; -} - /* * Returns pointer with encoded error via <linux/err.h> interface. */ @@ -601,7 +608,7 @@ struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool event_attr_init(&attr); if (format) { - id = trace_event__id(sys, name); + id = tp_pmu__id(sys, name); if (id < 0) { err = id; goto out_free; @@ -634,12 +641,17 @@ struct tep_event *evsel__tp_format(struct evsel *evsel) if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return NULL; - tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + if (!evsel->tp_sys) + tp_format = trace_event__tp_format_id(evsel->core.attr.config); + else + tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + if (IS_ERR(tp_format)) { int err = -PTR_ERR(evsel->tp_format); - pr_err("Error getting tracepoint format '%s' '%s'(%d)\n", - evsel__name(evsel), strerror(err), err); + errno = err; + pr_err("Error getting tracepoint format '%s': %m\n", + evsel__name(evsel)); return NULL; } evsel->tp_format = tp_format; @@ -914,7 +926,8 @@ const char *evsel__name(struct evsel *evsel) break; case PERF_TYPE_TRACEPOINT: - scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint"); + scnprintf(bf, sizeof(bf), "unknown tracepoint id=%#"PRIx64, + evsel->core.attr.config); break; case PERF_TYPE_BREAKPOINT: @@ -926,8 +939,8 @@ const char *evsel__name(struct evsel *evsel) break; default: - scnprintf(bf, sizeof(bf), "unknown attr type: %d", - evsel->core.attr.type); + scnprintf(bf, sizeof(bf), "unknown event PMU=%d config=%#"PRIx64, + evsel->core.attr.type, evsel->core.attr.config); break; } @@ -996,12 +1009,24 @@ int evsel__group_desc(struct evsel *evsel, char *buf, size_t size) return ret; } -static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *param) +uint16_t evsel__e_machine(struct evsel *evsel, uint32_t *e_flags) +{ + struct perf_session *session = evsel__session(evsel); + + return perf_session__e_machine(session, e_flags); +} + +static void __evsel__config_callchain(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *param) { bool function = evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->core.attr; + if (EM_HOST == EM_S390 && param->record_mode == CALLCHAIN_FP) { + pr_warning_once( + "Framepointer unwinding lacks kernel support. Use '--call-graph dwarf'\n"); + } + evsel__set_sample_bit(evsel, CALLCHAIN); attr->sample_max_stack = param->max_stack; @@ -1031,18 +1056,18 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o if (param->record_mode == CALLCHAIN_DWARF) { if (!function) { - const char *arch = perf_env__arch(evsel__env(evsel)); + uint16_t e_machine = evsel__e_machine(evsel, /*e_flags=*/NULL); evsel__set_sample_bit(evsel, REGS_USER); evsel__set_sample_bit(evsel, STACK_USER); if (opts->sample_user_regs && - DWARF_MINIMAL_REGS(arch) != arch__user_reg_mask()) { - attr->sample_regs_user |= DWARF_MINIMAL_REGS(arch); + DWARF_MINIMAL_REGS(e_machine) != perf_user_reg_mask(EM_HOST)) { + attr->sample_regs_user |= DWARF_MINIMAL_REGS(e_machine); pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, " "specifying a subset with --user-regs may render DWARF unwinding unreliable, " "so the minimal registers set (IP, SP) is explicitly forced.\n"); } else { - attr->sample_regs_user |= arch__user_reg_mask(); + attr->sample_regs_user |= perf_user_reg_mask(EM_HOST); } attr->sample_stack_user = param->dump_size; attr->exclude_callchain_user = 1; @@ -1056,16 +1081,19 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o pr_info("Disabling user space callchains for function trace event.\n"); attr->exclude_callchain_user = 1; } + + if (param->defer && !attr->exclude_callchain_user) + attr->defer_callchain = 1; } -void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *param) +void evsel__config_callchain(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *param) { if (param->enabled) return __evsel__config_callchain(evsel, opts, param); } -static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param) +static void evsel__reset_callgraph(struct evsel *evsel, const struct callchain_param *param) { struct perf_event_attr *attr = &evsel->core.attr; @@ -1082,8 +1110,73 @@ static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param * } } +static void evsel__apply_ratio_to_prev(struct evsel *evsel, + struct perf_event_attr *attr, + const struct record_opts *opts, + const char *buf) +{ + struct perf_event_attr *prev_attr = NULL; + struct evsel *evsel_prev = NULL; + u64 type = evsel->core.attr.sample_type; + u64 prev_type = 0; + double rtp; + + rtp = strtod(buf, NULL); + if (rtp <= 0) { + pr_err("Invalid ratio-to-prev value %lf\n", rtp); + return; + } + if (evsel == evsel__leader(evsel)) { + pr_err("Invalid use of ratio-to-prev term without preceding element in group\n"); + return; + } + if (!evsel->pmu->is_core) { + pr_err("Event using ratio-to-prev term must have a core PMU\n"); + return; + } + + evsel_prev = evsel__prev(evsel); + if (!evsel_prev) { + pr_err("Previous event does not exist.\n"); + return; + } + + if (evsel_prev->pmu->type != evsel->pmu->type) { + pr_err("Compared events (\"%s\", \"%s\") must have same PMU\n", + evsel->name, evsel_prev->name); + return; + } + + prev_attr = &evsel_prev->core.attr; + prev_type = evsel_prev->core.attr.sample_type; + + if (!(prev_type & PERF_SAMPLE_PERIOD)) { + attr->sample_period = prev_attr->sample_period * rtp; + attr->freq = 0; + evsel__reset_sample_bit(evsel, PERIOD); + } else if (!(type & PERF_SAMPLE_PERIOD)) { + prev_attr->sample_period = attr->sample_period / rtp; + prev_attr->freq = 0; + evsel__reset_sample_bit(evsel_prev, PERIOD); + } else { + if (opts->user_interval != ULLONG_MAX) { + prev_attr->sample_period = opts->user_interval; + attr->sample_period = prev_attr->sample_period * rtp; + prev_attr->freq = 0; + attr->freq = 0; + evsel__reset_sample_bit(evsel_prev, PERIOD); + evsel__reset_sample_bit(evsel, PERIOD); + } else { + pr_err("Event period term or count (-c) must be set when using ratio-to-prev term.\n"); + return; + } + } + + arch_evsel__apply_ratio_to_prev(evsel, attr); +} + static void evsel__apply_config_terms(struct evsel *evsel, - struct record_opts *opts, bool track) + const struct record_opts *opts, bool track) { struct evsel_config_term *term; struct list_head *config_terms = &evsel->config_terms; @@ -1095,6 +1188,7 @@ static void evsel__apply_config_terms(struct evsel *evsel, u32 dump_size = 0; int max_stack = 0; const char *callgraph_buf = NULL; + const char *rtp_buf = NULL; list_for_each_entry(term, config_terms, list) { switch (term->type) { @@ -1163,7 +1257,14 @@ static void evsel__apply_config_terms(struct evsel *evsel, case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: /* Already applied by auxtrace */ break; - case EVSEL__CONFIG_TERM_CFG_CHG: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG1: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG2: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG3: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG4: + break; + case EVSEL__CONFIG_TERM_RATIO_TO_PREV: + rtp_buf = term->val.str; break; default: break; @@ -1216,6 +1317,8 @@ static void evsel__apply_config_terms(struct evsel *evsel, evsel__config_callchain(evsel, opts, ¶m); } } + if (rtp_buf) + evsel__apply_ratio_to_prev(evsel, attr, opts, rtp_buf); } struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evsel_term_type type) @@ -1230,6 +1333,109 @@ struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evs return found_term; } +/* + * Set @config_name to @val as long as the user hasn't already set or cleared it + * by passing a config term on the command line. + * + * @val is the value to put into the bits specified by @config_name rather than + * the bit pattern. It is shifted into position by this function, so to set + * something to true, pass 1 for val rather than a pre shifted value. + */ +void evsel__set_config_if_unset(struct evsel *evsel, const char *config_name, + u64 val) +{ + u64 user_bits = 0; + struct evsel_config_term *term = evsel__get_config_term(evsel, + USR_CHG_CONFIG); + struct perf_pmu_format *format = pmu_find_format(&evsel->pmu->format, + config_name); + int fbit; + __u64 *vp; + + if (!format) + return; + + switch (format->value) { + case PERF_PMU_FORMAT_VALUE_CONFIG: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG); + vp = &evsel->core.attr.config; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG1: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG1); + vp = &evsel->core.attr.config1; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG2: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG2); + vp = &evsel->core.attr.config2; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG3: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG3); + vp = &evsel->core.attr.config3; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG4: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG4); + vp = &evsel->core.attr.config4; + break; + default: + pr_err("Unknown format value: %d\n", format->value); + return; + } + + if (!format) + return; + + if (term) + user_bits = term->val.cfg_chg; + + /* Do nothing if the user changed the value */ + for_each_set_bit(fbit, format->bits, PERF_PMU_FORMAT_BITS) + if ((1ULL << fbit) & user_bits) + return; + + /* Otherwise replace it */ + perf_pmu__format_pack(format->bits, val, vp, /*zero=*/true); +} + + +int evsel__get_config_val(const struct evsel *evsel, const char *config_name, + u64 *val) +{ + struct perf_pmu_format *format = pmu_find_format(&evsel->pmu->format, config_name); + + if (!format || bitmap_empty(format->bits, PERF_PMU_FORMAT_BITS)) { + pr_err("Unknown/empty format name: %s\n", config_name); + *val = 0; + return -EINVAL; + } + + switch (format->value) { + case PERF_PMU_FORMAT_VALUE_CONFIG: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG1: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config1); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG2: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config2); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG3: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config3); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG4: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config4); + return 0; + default: + pr_err("Unknown format value: %d\n", format->value); + *val = 0; + return -EINVAL; + } +} + void __weak arch_evsel__set_sample_weight(struct evsel *evsel) { evsel__set_sample_bit(evsel, WEIGHT); @@ -1240,7 +1446,12 @@ void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused, { } -static void evsel__set_default_freq_period(struct record_opts *opts, +void __weak arch_evsel__apply_ratio_to_prev(struct evsel *evsel __maybe_unused, + struct perf_event_attr *attr __maybe_unused) +{ +} + +static void evsel__set_default_freq_period(const struct record_opts *opts, struct perf_event_attr *attr) { if (opts->freq) { @@ -1251,9 +1462,10 @@ static void evsel__set_default_freq_period(struct record_opts *opts, } } -static bool evsel__is_offcpu_event(struct evsel *evsel) +bool evsel__is_offcpu_event(struct evsel *evsel) { - return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT); + return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT) && + evsel->core.attr.sample_type & PERF_SAMPLE_RAW; } /* @@ -1284,8 +1496,8 @@ static bool evsel__is_offcpu_event(struct evsel *evsel) * enable/disable events specifically, as there's no * initial traced exec call. */ -void evsel__config(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *callchain) +void evsel__config(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *callchain) { struct evsel *leader = evsel__leader(evsel); struct perf_event_attr *attr = &evsel->core.attr; @@ -1355,10 +1567,11 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, attr->inherit_stat = 1; } - if (opts->sample_address) { + if (opts->sample_address) evsel__set_sample_bit(evsel, ADDR); + + if (opts->record_data_mmap) attr->mmap_data = track; - } /* * We don't allow user space callchains for function trace @@ -1401,7 +1614,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, evsel__set_sample_bit(evsel, CPU); } - if (opts->sample_address) + if (opts->sample_data_src) evsel__set_sample_bit(evsel, DATA_SRC); if (opts->sample_phys_addr) @@ -1416,14 +1629,16 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, attr->branch_sample_type = opts->branch_stack; } - if (opts->sample_weight) + if (opts->sample_weight || evsel->retire_lat) { arch_evsel__set_sample_weight(evsel); - + evsel->retire_lat = false; + } attr->task = track; attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; attr->build_id = track && opts->build_id; + attr->defer_output = track && callchain && callchain->defer; /* * ksymbol is tracked separately with text poke because it needs to be @@ -1500,7 +1715,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, attr->exclude_user = 1; } - if (evsel->core.own_cpus || evsel->unit) + if (evsel->core.pmu_cpus || evsel->unit) evsel->core.attr.read_format |= PERF_FORMAT_ID; /* @@ -1530,8 +1745,10 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (evsel__is_dummy_event(evsel)) evsel__reset_sample_bit(evsel, BRANCH_STACK); - if (evsel__is_offcpu_event(evsel)) + if (evsel__is_offcpu_event(evsel)) { evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES; + attr->inherit = 0; + } arch__post_evsel_config(evsel, attr); } @@ -1628,10 +1845,21 @@ static void evsel__free_config_terms(struct evsel *evsel) free_config_terms(&evsel->config_terms); } +static void (*evsel__priv_destructor)(void *priv); + +void evsel__set_priv_destructor(void (*destructor)(void *priv)) +{ + assert(evsel__priv_destructor == NULL); + + evsel__priv_destructor = destructor; +} + void evsel__exit(struct evsel *evsel) { assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); + if (evsel__is_retire_lat(evsel)) + evsel__tpebs_close(evsel); bpf_counter__destroy(evsel); perf_bpf_filter__destroy(evsel); evsel__free_counts(evsel); @@ -1639,9 +1867,7 @@ void evsel__exit(struct evsel *evsel) perf_evsel__free_id(&evsel->core); evsel__free_config_terms(evsel); cgroup__put(evsel->cgrp); - perf_cpu_map__put(evsel->core.cpus); - perf_cpu_map__put(evsel->core.own_cpus); - perf_thread_map__put(evsel->core.threads); + perf_evsel__exit(&evsel->core); zfree(&evsel->group_name); zfree(&evsel->name); #ifdef HAVE_LIBTRACEEVENT @@ -1655,7 +1881,8 @@ void evsel__exit(struct evsel *evsel) evsel__zero_per_pkg(evsel); hashmap__free(evsel->per_pkg_mask); evsel->per_pkg_mask = NULL; - zfree(&evsel->metric_events); + if (evsel__priv_destructor) + evsel__priv_destructor(evsel->priv); perf_evsel__object.fini(evsel); if (evsel__tool_event(evsel) == TOOL_PMU__EVENT_SYSTEM_TIME || evsel__tool_event(evsel) == TOOL_PMU__EVENT_USER_TIME) @@ -1694,11 +1921,6 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread) return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count); } -static int evsel__read_retire_lat(struct evsel *evsel, int cpu_map_idx, int thread) -{ - return tpebs_set_evsel(evsel, cpu_map_idx, thread); -} - static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, u64 val, u64 ena, u64 run, u64 lost) { @@ -1706,8 +1928,8 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, count = perf_counts(counter->counts, cpu_map_idx, thread); - if (counter->retire_lat) { - evsel__read_retire_lat(counter, cpu_map_idx, thread); + if (evsel__is_retire_lat(counter)) { + evsel__tpebs_read(counter, cpu_map_idx, thread); perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true); return; } @@ -1844,16 +2066,19 @@ bool __evsel__match(const struct evsel *evsel, u32 type, u64 config) u32 e_type = evsel->core.attr.type; u64 e_config = evsel->core.attr.config; - if (e_type != type) { - return type == PERF_TYPE_HARDWARE && evsel->pmu && evsel->pmu->is_core && - evsel->alternate_hw_config == config; - } - - if ((type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE) && - perf_pmus__supports_extended_type()) + if (e_type == type && e_config == config) + return true; + if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE) + return false; + if ((e_type == PERF_TYPE_HARDWARE || e_type == PERF_TYPE_HW_CACHE) && + perf_pmus__supports_extended_type()) e_config &= PERF_HW_EVENT_MASK; - - return e_config == config; + if (e_type == type && e_config == config) + return true; + if (type == PERF_TYPE_HARDWARE && evsel->pmu && evsel->pmu->is_core && + evsel->alternate_hw_config == config) + return true; + return false; } int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) @@ -1864,8 +2089,11 @@ int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) if (evsel__is_hwmon(evsel)) return evsel__hwmon_pmu_read(evsel, cpu_map_idx, thread); + if (evsel__is_drm(evsel)) + return evsel__drm_pmu_read(evsel, cpu_map_idx, thread); + if (evsel__is_retire_lat(evsel)) - return evsel__read_retire_lat(evsel, cpu_map_idx, thread); + return evsel__tpebs_read(evsel, cpu_map_idx, thread); if (evsel->core.attr.read_format & PERF_FORMAT_GROUP) return evsel__read_group(evsel, cpu_map_idx, thread); @@ -1919,7 +2147,7 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) struct evsel *leader = evsel__leader(evsel); int fd; - if (evsel__is_group_leader(evsel)) + if (!evsel->supported || evsel__is_group_leader(evsel)) return -1; /* @@ -1933,7 +2161,7 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1 && !leader->skippable); + BUG_ON(fd == -1 && leader->supported); /* * When the leader has been skipped, return -2 to distinguish from no @@ -2099,6 +2327,10 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, static void evsel__disable_missing_features(struct evsel *evsel) { + if (perf_missing_features.defer_callchain && evsel->core.attr.defer_callchain) + evsel->core.attr.defer_callchain = 0; + if (perf_missing_features.defer_callchain && evsel->core.attr.defer_output) + evsel->core.attr.defer_output = 0; if (perf_missing_features.inherit_sample_read && evsel->core.attr.inherit && (evsel->core.attr.sample_type & PERF_SAMPLE_READ)) evsel->core.attr.inherit = 0; @@ -2373,8 +2605,15 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu /* Please add new feature detection here. */ + attr.defer_callchain = true; + if (has_attr_feature(&attr, /*flags=*/0)) + goto found; + perf_missing_features.defer_callchain = true; + pr_debug2("switching off deferred callchain support\n"); + attr.defer_callchain = false; + attr.inherit = true; - attr.sample_type = PERF_SAMPLE_READ; + attr.sample_type = PERF_SAMPLE_READ | PERF_SAMPLE_TID; if (has_attr_feature(&attr, /*flags=*/0)) goto found; perf_missing_features.inherit_sample_read = true; @@ -2484,6 +2723,10 @@ found: errno = old_errno; check: + if ((evsel->core.attr.defer_callchain || evsel->core.attr.defer_output) && + perf_missing_features.defer_callchain) + return true; + if (evsel->core.attr.inherit && (evsel->core.attr.sample_type & PERF_SAMPLE_READ) && perf_missing_features.inherit_sample_read) @@ -2542,25 +2785,6 @@ check: return false; } -static bool evsel__handle_error_quirks(struct evsel *evsel, int error) -{ - /* - * AMD core PMU tries to forward events with precise_ip to IBS PMU - * implicitly. But IBS PMU has more restrictions so it can fail with - * supported event attributes. Let's forward it back to the core PMU - * by clearing precise_ip only if it's from precise_max (:P). - */ - if ((error == -EINVAL || error == -ENOENT) && x86__is_amd_cpu() && - evsel->core.attr.precise_ip && evsel->precise_max) { - evsel->core.attr.precise_ip = 0; - pr_debug2_peo("removing precise_ip on AMD\n"); - display_attr(&evsel->core.attr); - return true; - } - - return false; -} - static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads, int start_cpu_map_idx, int end_cpu_map_idx) @@ -2570,12 +2794,14 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, enum rlimit_action set_rlimit = NO_CHANGE; struct perf_cpu cpu; - if (evsel__is_retire_lat(evsel)) - return tpebs_start(evsel->evlist); + if (evsel__is_retire_lat(evsel)) { + err = evsel__tpebs_open(evsel); + goto out; + } err = __evsel__prepare_open(evsel, cpus, threads); if (err) - return err; + goto out; if (cpus == NULL) cpus = empty_cpu_map; @@ -2595,14 +2821,22 @@ fallback_missing_features: display_attr(&evsel->core.attr); if (evsel__is_tool(evsel)) { - return evsel__tool_pmu_open(evsel, threads, + err = evsel__tool_pmu_open(evsel, threads, + start_cpu_map_idx, + end_cpu_map_idx); + goto out; + } + if (evsel__is_hwmon(evsel)) { + err = evsel__hwmon_pmu_open(evsel, threads, start_cpu_map_idx, end_cpu_map_idx); + goto out; } - if (evsel__is_hwmon(evsel)) { - return evsel__hwmon_pmu_open(evsel, threads, - start_cpu_map_idx, - end_cpu_map_idx); + if (evsel__is_drm(evsel)) { + err = evsel__drm_pmu_open(evsel, threads, + start_cpu_map_idx, + end_cpu_map_idx); + goto out; } for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { @@ -2660,8 +2894,8 @@ retry_open: PERF_EVENT_IOC_SET_BPF, bpf_fd); if (err && errno != EEXIST) { - pr_err("failed to attach bpf fd %d: %s\n", - bpf_fd, strerror(errno)); + pr_err("failed to attach bpf fd %d: %m\n", + bpf_fd); err = -EINVAL; goto out_close; } @@ -2681,7 +2915,8 @@ retry_open: } } - return 0; + err = 0; + goto out; try_fallback: if (evsel__ignore_missing_thread(evsel, perf_cpu_map__nr(cpus), @@ -2706,9 +2941,6 @@ try_fallback: if (evsel__precise_ip_fallback(evsel)) goto retry_open; - if (evsel__handle_error_quirks(evsel, err)) - goto retry_open; - out_close: if (err) threads->err_thread = thread; @@ -2723,6 +2955,9 @@ out_close: thread = nthreads; } while (--idx >= 0); errno = old_errno; +out: + if (err) + evsel->supported = false; return err; } @@ -2735,22 +2970,37 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, void evsel__close(struct evsel *evsel) { if (evsel__is_retire_lat(evsel)) - tpebs_delete(); + evsel__tpebs_close(evsel); perf_evsel__close(&evsel->core); perf_evsel__free_id(&evsel->core); } -int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx) +int evsel__open_per_cpu_and_thread(struct evsel *evsel, + struct perf_cpu_map *cpus, int cpu_map_idx, + struct perf_thread_map *threads) { if (cpu_map_idx == -1) - return evsel__open_cpu(evsel, cpus, NULL, 0, perf_cpu_map__nr(cpus)); + return evsel__open_cpu(evsel, cpus, threads, 0, perf_cpu_map__nr(cpus)); + + return evsel__open_cpu(evsel, cpus, threads, cpu_map_idx, cpu_map_idx + 1); +} - return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1); +int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx) +{ + struct perf_thread_map *threads = thread_map__new_by_tid(-1); + int ret = evsel__open_per_cpu_and_thread(evsel, cpus, cpu_map_idx, threads); + + perf_thread_map__put(threads); + return ret; } int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads) { - return evsel__open(evsel, NULL, threads); + struct perf_cpu_map *cpus = perf_cpu_map__new_any_cpu(); + int ret = evsel__open_per_cpu_and_thread(evsel, cpus, -1, threads); + + perf_cpu_map__put(cpus); + return ret; } static int perf_evsel__parse_id_sample(const struct evsel *evsel, @@ -2823,7 +3073,7 @@ static inline bool overflow(const void *endp, u16 max_size, const void *offset, #define OVERFLOW_CHECK(offset, size, max_size) \ do { \ if (overflow(endp, (max_size), (offset), (size))) \ - return -EFAULT; \ + goto out_efault; \ } while (0) #define OVERFLOW_CHECK_u64(offset) \ @@ -2843,11 +3093,18 @@ perf_event__check_size(union perf_event *event, unsigned int sample_size) return 0; } -void __weak arch_perf_parse_sample_weight(struct perf_sample *data, - const __u64 *array, - u64 type __maybe_unused) +static void perf_parse_sample_weight(struct perf_sample *data, const __u64 *array, u64 type) { - data->weight = *array; + union perf_sample_weight weight; + + weight.full = *array; + if (type & PERF_SAMPLE_WEIGHT_STRUCT) { + data->weight = weight.var1_dw; + data->ins_lat = weight.var2_w; + data->weight3 = weight.var3_w; + } else { + data->weight = weight.full; + } } u64 evsel__bitfield_swap_branch_flags(u64 value) @@ -2921,6 +3178,37 @@ static inline bool evsel__has_branch_counters(const struct evsel *evsel) return false; } +static int __set_offcpu_sample(struct perf_sample *data) +{ + u64 *array = data->raw_data; + u32 max_size = data->raw_size, *p32; + const void *endp = (void *)array + max_size; + + if (array == NULL) + return -EFAULT; + + OVERFLOW_CHECK_u64(array); + p32 = (void *)array++; + data->pid = p32[0]; + data->tid = p32[1]; + + OVERFLOW_CHECK_u64(array); + data->period = *array++; + + OVERFLOW_CHECK_u64(array); + data->callchain = (struct ip_callchain *)array++; + OVERFLOW_CHECK(array, data->callchain->nr * sizeof(u64), max_size); + data->ip = data->callchain->ips[1]; + array += data->callchain->nr; + + OVERFLOW_CHECK_u64(array); + data->cgroup = *array; + + return 0; +out_efault: + return -EFAULT; +} + int evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { @@ -2937,7 +3225,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, */ union u64_swap u; - memset(data, 0, sizeof(*data)); + perf_sample__init(data, /*all=*/true); + data->evsel = evsel; data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; data->period = evsel->core.attr.sample_period; @@ -2946,16 +3235,31 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->data_src = PERF_MEM_DATA_SRC_NONE; data->vcpu = -1; + if (event->header.type == PERF_RECORD_CALLCHAIN_DEFERRED) { + const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); + + data->callchain = (struct ip_callchain *)&event->callchain_deferred.nr; + if (data->callchain->nr > max_callchain_nr) + goto out_efault; + + data->deferred_cookie = event->callchain_deferred.cookie; + + if (evsel->core.attr.sample_id_all) + perf_evsel__parse_id_sample(evsel, event, data); + + return 0; + } + if (event->header.type != PERF_RECORD_SAMPLE) { - if (!evsel->core.attr.sample_id_all) - return 0; - return perf_evsel__parse_id_sample(evsel, event, data); + if (evsel->core.attr.sample_id_all) + perf_evsel__parse_id_sample(evsel, event, data); + return 0; } array = event->sample.array; if (perf_event__check_size(event, evsel->sample_size)) - return -EFAULT; + goto out_efault; if (type & PERF_SAMPLE_IDENTIFIER) { data->id = *array; @@ -3048,7 +3352,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, sizeof(struct sample_read_value); if (data->read.group.nr > max_group_nr) - return -EFAULT; + goto out_efault; sz = data->read.group.nr * sample_read_value_size(read_format); OVERFLOW_CHECK(array, sz, max_size); @@ -3070,12 +3374,25 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, if (type & PERF_SAMPLE_CALLCHAIN) { const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); + u64 callchain_nr; OVERFLOW_CHECK_u64(array); data->callchain = (struct ip_callchain *)array++; - if (data->callchain->nr > max_callchain_nr) - return -EFAULT; - sz = data->callchain->nr * sizeof(u64); + callchain_nr = data->callchain->nr; + if (callchain_nr > max_callchain_nr) + goto out_efault; + sz = callchain_nr * sizeof(u64); + /* + * Save the cookie for the deferred user callchain. The last 2 + * entries in the callchain should be the context marker and the + * cookie. The cookie will be used to match PERF_RECORD_ + * CALLCHAIN_DEFERRED later. + */ + if (evsel->core.attr.defer_callchain && callchain_nr >= 2 && + data->callchain->ips[callchain_nr - 2] == PERF_CONTEXT_USER_DEFERRED) { + data->deferred_cookie = data->callchain->ips[callchain_nr - 1]; + data->deferred_callchain = true; + } OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; } @@ -3121,7 +3438,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->branch_stack = (struct branch_stack *)array++; if (data->branch_stack->nr > max_branch_nr) - return -EFAULT; + goto out_efault; sz = data->branch_stack->nr * sizeof(struct branch_entry); if (evsel__has_branch_hw_idx(evsel)) { @@ -3164,17 +3481,19 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_REGS_USER) { + struct regs_dump *regs = perf_sample__user_regs(data); + OVERFLOW_CHECK_u64(array); - data->user_regs.abi = *array; + regs->abi = *array; array++; - if (data->user_regs.abi) { + if (regs->abi) { u64 mask = evsel->core.attr.sample_regs_user; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); - data->user_regs.mask = mask; - data->user_regs.regs = (u64 *)array; + regs->mask = mask; + regs->regs = (u64 *)array; array = (void *)array + sz; } } @@ -3196,13 +3515,13 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->user_stack.size = *array++; if (WARN_ONCE(data->user_stack.size > sz, "user stack dump failure\n")) - return -EFAULT; + goto out_efault; } } if (type & PERF_SAMPLE_WEIGHT_TYPE) { OVERFLOW_CHECK_u64(array); - arch_perf_parse_sample_weight(data, array, type); + perf_parse_sample_weight(data, array, type); array++; } @@ -3218,19 +3537,20 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } - data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE; if (type & PERF_SAMPLE_REGS_INTR) { + struct regs_dump *regs = perf_sample__intr_regs(data); + OVERFLOW_CHECK_u64(array); - data->intr_regs.abi = *array; + regs->abi = *array; array++; - if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { + if (regs->abi != PERF_SAMPLE_REGS_ABI_NONE) { u64 mask = evsel->core.attr.sample_regs_intr; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); - data->intr_regs.mask = mask; - data->intr_regs.regs = (u64 *)array; + regs->mask = mask; + regs->regs = (u64 *)array; array = (void *)array + sz; } } @@ -3272,7 +3592,15 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array = (void *)array + sz; } + if (evsel__is_offcpu_event(evsel)) { + if (__set_offcpu_sample(data)) + goto out_efault; + } + return 0; +out_efault: + perf_sample__exit(data); + return -EFAULT; } int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event, @@ -3472,25 +3800,42 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, { int paranoid; - if ((err == ENOENT || err == ENXIO || err == ENODEV) && - evsel->core.attr.type == PERF_TYPE_HARDWARE && - evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) { + if ((err == ENODEV || err == ENOENT || err == ENXIO) && + evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { /* - * If it's cycles then fall back to hrtimer based cpu-clock sw - * counter, which is always available even if no PMU support. - * - * PPC returns ENXIO until 2.6.37 (behavior changed with commit - * b0a873e). + * If it's the legacy hardware cycles event fails then fall back + * to hrtimer based cpu-clock sw counter, which is always + * available even if no PMU support. PPC returned ENXIO rather + * than ENODEV or ENOENT until 2.6.37. */ - evsel->core.attr.type = PERF_TYPE_SOFTWARE; + evsel->pmu = perf_pmus__find_by_type(PERF_TYPE_SOFTWARE); + assert(evsel->pmu); /* software is a "well-known" and can't fail PMU type. */ + + /* Configure the event. */ + evsel->core.attr.type = PERF_TYPE_SOFTWARE; evsel->core.attr.config = target__has_cpu(target) ? PERF_COUNT_SW_CPU_CLOCK : PERF_COUNT_SW_TASK_CLOCK; - scnprintf(msg, msgsize, - "The cycles event is not supported, trying to fall back to %s", - target__has_cpu(target) ? "cpu-clock" : "task-clock"); + evsel->core.is_pmu_core = false; + /* Remove excludes for new event. */ + if (evsel->fallenback_eacces) { + evsel->core.attr.exclude_kernel = 0; + evsel->core.attr.exclude_hv = 0; + evsel->fallenback_eacces = false; + } + if (evsel->fallenback_eopnotsupp) { + evsel->core.attr.exclude_guest = 0; + evsel->fallenback_eopnotsupp = false; + } + + /* Name is recomputed by evsel__name. */ zfree(&evsel->name); + + /* Log message. */ + scnprintf(msg, msgsize, + "The cycles event is not supported, trying to fall back to %s", + evsel__name(evsel)); return true; } else if (err == EACCES && !evsel->core.attr.exclude_kernel && (paranoid = perf_event_paranoid()) > 1) { @@ -3500,7 +3845,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, /* If event has exclude user then don't exclude kernel. */ if (evsel->core.attr.exclude_user) - return false; + goto no_fallback; /* Is there already the separator in the name. */ if (strchr(name, '/') || @@ -3508,7 +3853,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, sep = ""; if (asprintf(&new_name, "%s%su", name, sep) < 0) - return false; + goto no_fallback; free(evsel->name); evsel->name = new_name; @@ -3517,7 +3862,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, " samples", paranoid); evsel->core.attr.exclude_kernel = 1; evsel->core.attr.exclude_hv = 1; - + evsel->fallenback_eacces = true; return true; } else if (err == EOPNOTSUPP && !evsel->core.attr.exclude_guest && !evsel->exclude_GH) { @@ -3531,17 +3876,19 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, sep = ""; if (asprintf(&new_name, "%s%sH", name, sep) < 0) - return false; + goto no_fallback; free(evsel->name); evsel->name = new_name; /* Apple M1 requires exclude_guest */ - scnprintf(msg, msgsize, "trying to fall back to excluding guest samples"); + scnprintf(msg, msgsize, "Trying to fall back to excluding guest samples"); evsel->core.attr.exclude_guest = 1; - + evsel->fallenback_eopnotsupp = true; return true; } - +no_fallback: + scnprintf(msg, msgsize, "No fallback found for '%s' for error %d", + evsel__name(evsel), err); return false; } @@ -3654,6 +4001,7 @@ static int dump_perf_event_processes(char *msg, size_t size) } int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused, + int err __maybe_unused, char *msg __maybe_unused, size_t size __maybe_unused) { @@ -3663,7 +4011,7 @@ int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused, int evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size) { - char sbuf[STRERR_BUFSIZE]; + struct perf_pmu *pmu; int printed = 0, enforced = 0; int ret; @@ -3747,6 +4095,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "%s", "No hardware sampling interrupt available.\n"); #endif + if (!target__has_cpu(target)) + return scnprintf(msg, size, + "Unsupported event (%s) in per-thread mode, enable system wide with '-a'.", + evsel__name(evsel)); break; case EBUSY: if (find_process("oprofiled")) @@ -3774,7 +4126,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "The 'aux_action' feature is not supported, update the kernel."); if (perf_missing_features.aux_output) return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); - if (!target__has_cpu(target)) + pmu = evsel__find_pmu(evsel); + if (!pmu->is_core && !target__has_cpu(target)) return scnprintf(msg, size, "Invalid event (%s) in per-thread mode, enable system wide with '-a'.", evsel__name(evsel)); @@ -3787,21 +4140,27 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, break; } - ret = arch_evsel__open_strerror(evsel, msg, size); + ret = arch_evsel__open_strerror(evsel, err, msg, size); if (ret) return ret; + errno = err; return scnprintf(msg, size, - "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" - "\"dmesg | grep -i perf\" may provide additional information.\n", - err, str_error_r(err, sbuf, sizeof(sbuf)), evsel__name(evsel)); + "The sys_perf_event_open() syscall failed for event (%s): %m\n" + "\"dmesg | grep -i perf\" may provide additional information.\n", + evsel__name(evsel)); +} + +struct perf_session *evsel__session(struct evsel *evsel) +{ + return evsel && evsel->evlist ? evsel->evlist->session : NULL; } struct perf_env *evsel__env(struct evsel *evsel) { - if (evsel && evsel->evlist && evsel->evlist->env) - return evsel->evlist->env; - return &perf_env; + struct perf_session *session = evsel__session(evsel); + + return session ? perf_session__env(session) : NULL; } static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) @@ -3811,6 +4170,9 @@ static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) if (evsel__is_retire_lat(evsel)) return 0; + if (perf_pmu__kind(evsel->pmu) != PERF_PMU_KIND_PE) + return 0; + for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) { for (thread = 0; thread < xyarray__max_y(evsel->core.fd); thread++) { @@ -3856,14 +4218,16 @@ void evsel__zero_per_pkg(struct evsel *evsel) */ bool evsel__is_hybrid(const struct evsel *evsel) { - if (perf_pmus__num_core_pmus() == 1) + if (!evsel->core.is_pmu_core) return false; - return evsel->core.is_pmu_core; + return perf_pmus__num_core_pmus() > 1; } struct evsel *evsel__leader(const struct evsel *evsel) { + if (evsel->core.leader == NULL) + return NULL; return container_of(evsel->core.leader, struct evsel, core); } @@ -3882,6 +4246,17 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader) evsel->core.leader = &leader->core; } +bool evsel__is_aux_event(const struct evsel *evsel) +{ + struct perf_pmu *pmu; + + if (evsel->needs_auxtrace_mmap) + return true; + + pmu = evsel__find_pmu(evsel); + return pmu && pmu->auxtrace; +} + int evsel__source_count(const struct evsel *evsel) { struct evsel *pos; @@ -3912,3 +4287,152 @@ void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader) leader->core.nr_members--; } } + +bool evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_config *config) +{ + struct evsel *evsel; + + if (counter->needs_uniquify) { + /* Already set. */ + return true; + } + + if (counter->use_config_name || counter->is_libpfm_event) { + /* Original name will be used. */ + return false; + } + + if (!config->hybrid_merge && evsel__is_hybrid(counter)) { + /* Unique hybrid counters necessary. */ + counter->needs_uniquify = true; + return true; + } + + if (counter->core.attr.type < PERF_TYPE_MAX && counter->core.attr.type != PERF_TYPE_RAW) { + /* Legacy event, don't uniquify. */ + return false; + } + + if (counter->pmu && counter->pmu->is_core && + counter->alternate_hw_config != PERF_COUNT_HW_MAX) { + /* A sysfs or json event replacing a legacy event, don't uniquify. */ + return false; + } + + if (config->aggr_mode == AGGR_NONE) { + /* Always unique with no aggregation. */ + counter->needs_uniquify = true; + return true; + } + + if (counter->first_wildcard_match != NULL) { + /* + * If stats are merged then only the first_wildcard_match is + * displayed, there is no need to uniquify this evsel as the + * name won't be shown. + */ + return false; + } + + /* + * Do other non-merged events in the evlist have the same name? If so + * uniquify is necessary. + */ + evlist__for_each_entry(counter->evlist, evsel) { + if (evsel == counter || evsel->first_wildcard_match || evsel->pmu == counter->pmu) + continue; + + if (evsel__name_is(counter, evsel__name(evsel))) { + counter->needs_uniquify = true; + return true; + } + } + return false; +} + +void evsel__uniquify_counter(struct evsel *counter) +{ + const char *name, *pmu_name, *config; + char *new_name; + int len, ret; + + /* No uniquification necessary. */ + if (!counter->needs_uniquify) + return; + + /* The evsel was already uniquified. */ + if (counter->uniquified_name) + return; + + /* Avoid checking to uniquify twice. */ + counter->uniquified_name = true; + + name = evsel__name(counter); + config = strchr(name, '/'); + pmu_name = counter->pmu->name; + + /* Already prefixed by the PMU name? */ + len = pmu_name_len_no_suffix(pmu_name); + + if (!strncmp(name, pmu_name, len)) { + /* + * If the PMU name is there, then there is no sense in not + * having a slash. Do this for robustness. + */ + if (config == NULL) + config = name - 1; + + ret = asprintf(&new_name, "%s/%s", pmu_name, config + 1); + } else if (config) { + len = config - name; + if (config[1] == '/') { + /* case: event// */ + ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2); + } else { + /* case: event/.../ */ + ret = asprintf(&new_name, "%s/%.*s,%s", pmu_name, len, name, config + 1); + } + } else { + config = strchr(name, ':'); + if (config) { + /* case: event:.. */ + len = config - name; + + ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1); + } else { + /* case: event */ + ret = asprintf(&new_name, "%s/%s/", pmu_name, name); + } + } + if (ret > 0) { + free(counter->name); + counter->name = new_name; + } else { + /* ENOMEM from asprintf. */ + counter->uniquified_name = false; + } +} + +void evsel__warn_user_requested_cpus(struct evsel *evsel, struct perf_cpu_map *user_requested_cpus) +{ + struct perf_cpu_map *intersect, *online = NULL; + const struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu && pmu->is_core) { + intersect = perf_cpu_map__intersect(pmu->cpus, user_requested_cpus); + } else { + online = cpu_map__online(); + intersect = perf_cpu_map__intersect(online, user_requested_cpus); + } + if (!perf_cpu_map__equal(intersect, user_requested_cpus)) { + char buf1[128]; + char buf2[128]; + + cpu_map__snprint(user_requested_cpus, buf1, sizeof(buf1)); + cpu_map__snprint(online ?: pmu->cpus, buf2, sizeof(buf2)); + pr_warning("WARNING: A requested CPU in '%s' is not supported by PMU '%s' (CPUs %s) for event '%s'\n", + buf1, pmu ? pmu->name : "cpu", buf2, evsel__name(evsel)); + } + perf_cpu_map__put(intersect); + perf_cpu_map__put(online); +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 5e789fa80590..339b5c08a33d 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -16,6 +16,7 @@ struct bpf_object; struct cgroup; struct perf_counts; +struct perf_stat_config; struct perf_stat_evsel; union perf_event; struct bpf_counter_ops; @@ -69,6 +70,11 @@ struct evsel { const char *unit; struct cgroup *cgrp; const char *metric_id; + /* + * This point to the first evsel with the same name, intended to store the + * aggregated counts in aggregation mode. + */ + struct evsel *first_wildcard_match; /* parse modifier helper */ int exclude_GH; int sample_read; @@ -77,13 +83,13 @@ struct evsel { bool percore; bool precise_max; bool is_libpfm_event; - bool auto_merge_stats; bool collect_stat; bool weak_group; bool bpf_counter; bool use_config_name; bool skippable; bool retire_lat; + bool dont_regroup; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; @@ -94,7 +100,6 @@ struct evsel { * metric fields are similar, but needs more care as they can have * references to other metric (evsel). */ - struct evsel **metric_events; struct evsel *metric_leader; void *handler; @@ -114,11 +119,13 @@ struct evsel { bool ignore_missing_thread; bool forced_leader; bool cmdline_group_boundary; - bool merged_stat; bool reset_group; - bool errored; bool needs_auxtrace_mmap; bool default_metricgroup; /* A member of the Default metricgroup */ + bool default_show_events; /* If a default group member, show the event */ + bool needs_uniquify; + bool fallenback_eacces; + bool fallenback_eopnotsupp; struct hashmap *per_pkg_mask; int err; int script_output_type; @@ -176,6 +183,12 @@ struct evsel { /* For tool events */ /* Beginning time subtracted when the counter is read. */ union { + /* Defaults for retirement latency events. */ + struct _retirement_latency { + double mean; + double min; + double max; + } retirement_latency; /* duration_time is a single global time. */ __u64 start_time; /* @@ -210,6 +223,7 @@ struct perf_missing_features { bool branch_counters; bool aux_action; bool inherit_sample_read; + bool defer_callchain; }; extern struct perf_missing_features perf_missing_features; @@ -236,6 +250,7 @@ int evsel__object_config(size_t object_size, void (*fini)(struct evsel *evsel)); struct perf_pmu *evsel__find_pmu(const struct evsel *evsel); +const char *evsel__pmu_name(const struct evsel *evsel); bool evsel__is_aux_event(const struct evsel *evsel); struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx); @@ -268,12 +283,14 @@ void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx); void evsel__exit(struct evsel *evsel); void evsel__delete(struct evsel *evsel); +void evsel__set_priv_destructor(void (*destructor)(void *priv)); + struct callchain_param; -void evsel__config(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *callchain); -void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *callchain); +void evsel__config(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *callchain); +void evsel__config_callchain(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *callchain); int __evsel__sample_size(u64 sample_type); void evsel__calc_id_pos(struct evsel *evsel); @@ -327,7 +344,8 @@ void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier); void arch_evsel__set_sample_weight(struct evsel *evsel); void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr); -int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size); +int arch_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size); +void arch_evsel__apply_ratio_to_prev(struct evsel *evsel, struct perf_event_attr *attr); int evsel__set_filter(struct evsel *evsel, const char *filter); int evsel__append_tp_filter(struct evsel *evsel, const char *filter); @@ -337,6 +355,9 @@ int evsel__enable(struct evsel *evsel); int evsel__disable(struct evsel *evsel); int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx); +int evsel__open_per_cpu_and_thread(struct evsel *evsel, + struct perf_cpu_map *cpus, int cpu_map_idx, + struct perf_thread_map *threads); int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx); int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads); int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, @@ -525,7 +546,9 @@ static inline bool evsel__is_dummy_event(struct evsel *evsel) (evsel->core.attr.config == PERF_COUNT_SW_DUMMY); } +struct perf_session *evsel__session(struct evsel *evsel); struct perf_env *evsel__env(struct evsel *evsel); +uint16_t evsel__e_machine(struct evsel *evsel, uint32_t *e_flags); int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); @@ -540,6 +563,9 @@ void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader); bool arch_evsel__must_be_in_group(const struct evsel *evsel); +bool evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_config *config); +void evsel__uniquify_counter(struct evsel *counter); + /* * Macro to swap the bit-field postition and size. * Used when, @@ -552,7 +578,13 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel); ((((src) >> (pos)) & ((1ull << (size)) - 1)) << (63 - ((pos) + (size) - 1))) u64 evsel__bitfield_swap_branch_flags(u64 value); -void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel, - const char *config_name, u64 val); +int evsel__get_config_val(const struct evsel *evsel, const char *config_name, + u64 *val); +void evsel__set_config_if_unset(struct evsel *evsel, const char *config_name, + u64 val); + +bool evsel__is_offcpu_event(struct evsel *evsel); + +void evsel__warn_user_requested_cpus(struct evsel *evsel, struct perf_cpu_map *user_requested_cpus); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h index af52a1516d0b..7b565d76c0bc 100644 --- a/tools/perf/util/evsel_config.h +++ b/tools/perf/util/evsel_config.h @@ -27,7 +27,12 @@ enum evsel_term_type { EVSEL__CONFIG_TERM_AUX_OUTPUT, EVSEL__CONFIG_TERM_AUX_ACTION, EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE, - EVSEL__CONFIG_TERM_CFG_CHG, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG1, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG2, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG3, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG4, + EVSEL__CONFIG_TERM_RATIO_TO_PREV, }; struct evsel_config_term { @@ -48,6 +53,8 @@ struct evsel_config_term { u32 aux_sample_size; u64 cfg_chg; char *str; + int cpu; + u64 val; } val; bool weak; }; diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 103984b29b1e..5521d00bff2c 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -168,7 +168,10 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, node_al.addr = addr; node_al.map = map__get(map); - if (print_symoffset) { + if (sample->deferred_callchain && + sample->deferred_cookie == node->ip) { + printed += fprintf(fp, "(cookie)"); + } else if (print_symoffset) { printed += __symbol__fprintf_symname_offs(sym, &node_al, print_unknown_as_addr, true, fp); @@ -182,8 +185,12 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_dso && (!sym || !sym->inlined)) printed += map__fprintf_dsoname_dsoff(map, print_dsoff, addr, fp); - if (print_srcline) - printed += map__fprintf_srcline(map, addr, "\n ", fp); + if (print_srcline) { + if (node->srcline) + printed += fprintf(fp, "\n %s", node->srcline); + else + printed += map__fprintf_srcline(map, addr, "\n ", fp); + } if (sym && sym->inlined) printed += fprintf(fp, " (inlined)"); diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c index 40cb56a9347d..d4c06a3f825a 100644 --- a/tools/perf/util/evswitch.c +++ b/tools/perf/util/evswitch.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> +#include <errno.h> #include "evswitch.h" #include "evlist.h" diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index c221dcce6666..644769e92708 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -166,8 +166,12 @@ int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id, data_ptr->kind = EXPR_ID_DATA__VALUE; ret = hashmap__set(ctx->ids, id, data_ptr, &old_key, &old_data); - if (ret) + if (ret) { free(data_ptr); + } else if (old_data) { + data_ptr->val.val += old_data->val.val; + data_ptr->val.source_count += old_data->val.source_count; + } free(old_key); free(old_data); return ret; @@ -215,6 +219,8 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data) { + if (!ctx || !id) + return -1; return hashmap__find(ctx->ids, id, data) ? 0 : -1; } @@ -370,7 +376,8 @@ int expr__find_ids(const char *expr, const char *one, if (one) expr__del_id(ctx, one); - return ret; + /* A positive value means syntax error, convert to -EINVAL */ + return ret > 0 ? -EINVAL : ret; } double expr_id_data__value(const struct expr_id_data *data) @@ -395,16 +402,14 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx if (ev != TOOL_PMU__EVENT_NONE) { u64 count; - if (tool_pmu__read_event(ev, &count)) + if (tool_pmu__read_event(ev, /*evsel=*/NULL, + ctx->system_wide, ctx->user_requested_cpu_list, + &count)) result = count; else - pr_err("Failure to read '%s'", literal); - - } else if (!strcmp("#core_wide", literal)) { - result = core_wide(ctx->system_wide, ctx->user_requested_cpu_list) - ? 1.0 : 0.0; + pr_err("Failure to read '%s'\n", literal); } else { - pr_err("Unrecognized literal '%s'", literal); + pr_err("Unrecognized literal '%s'\n", literal); } pr_debug2("literal: %s = %f\n", literal, result); diff --git a/tools/perf/util/fncache.c b/tools/perf/util/fncache.c index 6225cbc52310..bf9559c55c63 100644 --- a/tools/perf/util/fncache.c +++ b/tools/perf/util/fncache.c @@ -1,53 +1,58 @@ // SPDX-License-Identifier: GPL-2.0-only /* Manage a cache of file names' existence */ +#include <pthread.h> #include <stdlib.h> -#include <unistd.h> #include <string.h> -#include <linux/list.h> +#include <unistd.h> +#include <linux/compiler.h> #include "fncache.h" +#include "hashmap.h" -struct fncache { - struct hlist_node nd; - bool res; - char name[]; -}; +static struct hashmap *fncache; -#define FNHSIZE 61 +static size_t fncache__hash(long key, void *ctx __maybe_unused) +{ + return str_hash((const char *)key); +} -static struct hlist_head fncache_hash[FNHSIZE]; +static bool fncache__equal(long key1, long key2, void *ctx __maybe_unused) +{ + return strcmp((const char *)key1, (const char *)key2) == 0; +} -unsigned shash(const unsigned char *s) +static void fncache__init(void) { - unsigned h = 0; - while (*s) - h = 65599 * h + *s++; - return h ^ (h >> 16); + fncache = hashmap__new(fncache__hash, fncache__equal, /*ctx=*/NULL); +} + +static struct hashmap *fncache__get(void) +{ + static pthread_once_t fncache_once = PTHREAD_ONCE_INIT; + + pthread_once(&fncache_once, fncache__init); + + return fncache; } static bool lookup_fncache(const char *name, bool *res) { - int h = shash((const unsigned char *)name) % FNHSIZE; - struct fncache *n; - - hlist_for_each_entry(n, &fncache_hash[h], nd) { - if (!strcmp(n->name, name)) { - *res = n->res; - return true; - } - } - return false; + long val; + + if (!hashmap__find(fncache__get(), name, &val)) + return false; + + *res = (val != 0); + return true; } static void update_fncache(const char *name, bool res) { - struct fncache *n = malloc(sizeof(struct fncache) + strlen(name) + 1); - int h = shash((const unsigned char *)name) % FNHSIZE; - - if (!n) - return; - strcpy(n->name, name); - n->res = res; - hlist_add_head(&n->nd, &fncache_hash[h]); + char *old_key = NULL, *key = strdup(name); + + if (key) { + hashmap__set(fncache__get(), key, res, &old_key, /*old_value*/NULL); + free(old_key); + } } /* No LRU, only use when bounded in some other way. */ diff --git a/tools/perf/util/fncache.h b/tools/perf/util/fncache.h index fe020beaefb1..b6a0f209493e 100644 --- a/tools/perf/util/fncache.h +++ b/tools/perf/util/fncache.h @@ -1,7 +1,6 @@ #ifndef _FCACHE_H #define _FCACHE_H 1 -unsigned shash(const unsigned char *s); bool file_available(const char *name); #endif diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h index 5dee2caba0fe..950f2efafad2 100644 --- a/tools/perf/util/ftrace.h +++ b/tools/perf/util/ftrace.h @@ -17,6 +17,7 @@ struct perf_ftrace { struct list_head notrace; struct list_head graph_funcs; struct list_head nograph_funcs; + struct list_head event_pair; struct hashmap *profile_hash; unsigned long percpu_buffer_size; bool inherit; @@ -24,9 +25,15 @@ struct perf_ftrace { unsigned int bucket_range; unsigned int min_latency; unsigned int max_latency; + unsigned int bucket_num; + bool hide_empty; int graph_depth; int func_stack_trace; int func_irq_info; + int graph_args; + int graph_retval; + int graph_retval_hex; + int graph_retaddr; int graph_nosleep_time; int graph_noirqs; int graph_verbose; diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index cdce7f173d00..14882def9704 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -12,14 +12,13 @@ #include <libelf.h> #include <string.h> #include <stdlib.h> -#include <unistd.h> #include <inttypes.h> -#include <fcntl.h> #include <err.h> #ifdef HAVE_LIBDW_SUPPORT #include <dwarf.h> #endif +#include "blake2s.h" #include "genelf.h" #include "../util/jitdump.h" #include <linux/compiler.h> @@ -28,25 +27,6 @@ #define NT_GNU_BUILD_ID 3 #endif -#define BUILD_ID_URANDOM /* different uuid for each run */ - -#ifdef HAVE_LIBCRYPTO_SUPPORT - -#define BUILD_ID_MD5 -#undef BUILD_ID_SHA /* does not seem to work well when linked with Java */ -#undef BUILD_ID_URANDOM /* different uuid for each run */ - -#ifdef BUILD_ID_SHA -#include <openssl/sha.h> -#endif - -#ifdef BUILD_ID_MD5 -#include <openssl/evp.h> -#include <openssl/md5.h> -#endif -#endif - - typedef struct { unsigned int namesz; /* Size of entry's owner string */ unsigned int descsz; /* Size of the note descriptor */ @@ -71,7 +51,7 @@ static char shd_string_table[] = { static struct buildid_note { Elf_Note desc; /* descsz: size of build-id, must be multiple of 4 */ char name[4]; /* GNU\0 */ - char build_id[20]; + u8 build_id[20]; } bnote; static Elf_Sym symtab[]={ @@ -92,65 +72,6 @@ static Elf_Sym symtab[]={ } }; -#ifdef BUILD_ID_URANDOM -static void -gen_build_id(struct buildid_note *note, - unsigned long load_addr __maybe_unused, - const void *code __maybe_unused, - size_t csize __maybe_unused) -{ - int fd; - size_t sz = sizeof(note->build_id); - ssize_t sret; - - fd = open("/dev/urandom", O_RDONLY); - if (fd == -1) - err(1, "cannot access /dev/urandom for buildid"); - - sret = read(fd, note->build_id, sz); - - close(fd); - - if (sret != (ssize_t)sz) - memset(note->build_id, 0, sz); -} -#endif - -#ifdef BUILD_ID_SHA -static void -gen_build_id(struct buildid_note *note, - unsigned long load_addr __maybe_unused, - const void *code, - size_t csize) -{ - if (sizeof(note->build_id) < SHA_DIGEST_LENGTH) - errx(1, "build_id too small for SHA1"); - - SHA1(code, csize, (unsigned char *)note->build_id); -} -#endif - -#ifdef BUILD_ID_MD5 -static void -gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize) -{ - EVP_MD_CTX *mdctx; - - if (sizeof(note->build_id) < 16) - errx(1, "build_id too small for MD5"); - - mdctx = EVP_MD_CTX_new(); - if (!mdctx) - errx(2, "failed to create EVP_MD_CTX"); - - EVP_DigestInit_ex(mdctx, EVP_md5(), NULL); - EVP_DigestUpdate(mdctx, &load_addr, sizeof(load_addr)); - EVP_DigestUpdate(mdctx, code, csize); - EVP_DigestFinal_ex(mdctx, (unsigned char *)note->build_id, NULL); - EVP_MD_CTX_free(mdctx); -} -#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) @@ -231,15 +152,34 @@ jit_add_eh_frame_info(Elf *e, void* unwinding, uint64_t unwinding_header_size, return 0; } +enum { + TAG_CODE = 0, + TAG_SYMTAB = 1, + TAG_STRSYM = 2, +}; + +/* + * Update the hash using the given data, also prepending a (tag, len) prefix to + * ensure that distinct input tuples reliably result in distinct hashes. + */ +static void blake2s_update_tagged(struct blake2s_ctx *ctx, int tag, + const void *data, size_t len) +{ + u64 prefix = ((u64)tag << 56) | len; + + blake2s_update(ctx, (const u8 *)&prefix, sizeof(prefix)); + blake2s_update(ctx, data, len); +} + /* * fd: file descriptor open for writing for the output file - * load_addr: code load address (could be zero, just used for buildid) + * load_addr: code load address (could be zero) * sym: function name (for native code - used as the symbol) * code: the native code * csize: the code size in bytes */ int -jit_write_elf(int fd, uint64_t load_addr, const char *sym, +jit_write_elf(int fd, uint64_t load_addr __maybe_unused, const char *sym, const void *code, int csize, void *debug __maybe_unused, int nr_debug_entries __maybe_unused, void *unwinding, uint64_t unwinding_header_size, uint64_t unwinding_size) @@ -252,6 +192,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, Elf_Shdr *shdr; uint64_t eh_frame_base_offset; char *strsym = NULL; + struct blake2s_ctx ctx; int symlen; int retval = -1; @@ -330,6 +271,9 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC; shdr->sh_entsize = 0; + blake2s_init(&ctx, sizeof(bnote.build_id)); + blake2s_update_tagged(&ctx, TAG_CODE, code, csize); + /* * Setup .eh_frame_hdr and .eh_frame */ @@ -413,6 +357,8 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, shdr->sh_entsize = sizeof(Elf_Sym); shdr->sh_link = unwinding ? 6 : 4; /* index of .strtab section */ + blake2s_update_tagged(&ctx, TAG_SYMTAB, symtab, sizeof(symtab)); + /* * setup symbols string table * 2 = 1 for 0 in 1st entry, 1 for the 0 at end of symbol for 2nd entry @@ -455,6 +401,8 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, shdr->sh_flags = 0; shdr->sh_entsize = 0; + blake2s_update_tagged(&ctx, TAG_STRSYM, strsym, symlen); + /* * setup build-id section */ @@ -473,7 +421,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, /* * build-id generation */ - gen_build_id(&bnote, load_addr, code, csize); + blake2s_final(&ctx, bnote.build_id); bnote.desc.namesz = sizeof(bnote.name); /* must include 0 termination */ bnote.desc.descsz = sizeof(bnote.build_id); bnote.desc.type = NT_GNU_BUILD_ID; @@ -519,6 +467,5 @@ error: free(strsym); - return retval; } diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh deleted file mode 100755 index 6a73c903d690..000000000000 --- a/tools/perf/util/generate-cmdlist.sh +++ /dev/null @@ -1,70 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -echo "/* Automatically generated by $0 */ -struct cmdname_help -{ - char name[16]; - char help[80]; -}; - -static struct cmdname_help common_cmds[] = {" - -sed -n -e 's/^perf-\([^ ]*\)[ ].* common.*/\1/p' command-list.txt | -sort | -while read cmd -do - sed -n ' - /^NAME/,/perf-'"$cmd"'/H - ${ - x - s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ - p - }' "Documentation/perf-$cmd.txt" -done - -echo "#ifdef HAVE_LIBELF_SUPPORT" -sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt | -sort | -while read cmd -do - sed -n ' - /^NAME/,/perf-'"$cmd"'/H - ${ - x - s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ - p - }' "Documentation/perf-$cmd.txt" -done -echo "#endif /* HAVE_LIBELF_SUPPORT */" - -echo "#if defined(HAVE_LIBTRACEEVENT)" -sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt | -sort | -while read cmd -do - sed -n ' - /^NAME/,/perf-'"$cmd"'/H - ${ - x - s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ - p - }' "Documentation/perf-$cmd.txt" -done -echo "#endif /* HAVE_LIBTRACEEVENT */" - -echo "#ifdef HAVE_LIBTRACEEVENT" -sed -n -e 's/^perf-\([^ ]*\)[ ].* traceevent.*/\1/p' command-list.txt | -sort | -while read cmd -do - sed -n ' - /^NAME/,/perf-'"$cmd"'/H - ${ - x - s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ - p - }' "Documentation/perf-$cmd.txt" -done -echo "#endif /* HAVE_LIBTRACEEVENT */" -echo "};" diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c deleted file mode 100644 index e68935e9ac8c..000000000000 --- a/tools/perf/util/get_current_dir_name.c +++ /dev/null @@ -1,18 +0,0 @@ -// SPDX-License-Identifier: LGPL-2.1 -// Copyright (C) 2018, 2019 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> -// -#ifndef HAVE_GET_CURRENT_DIR_NAME -#include "get_current_dir_name.h" -#include <limits.h> -#include <string.h> -#include <unistd.h> - -/* Android's 'bionic' library, for one, doesn't have this */ - -char *get_current_dir_name(void) -{ - char pwd[PATH_MAX]; - - return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd); -} -#endif // HAVE_GET_CURRENT_DIR_NAME diff --git a/tools/perf/util/get_current_dir_name.h b/tools/perf/util/get_current_dir_name.h deleted file mode 100644 index 69f7d5537d32..000000000000 --- a/tools/perf/util/get_current_dir_name.h +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: LGPL-2.1 -// Copyright (C) 2018, 2019 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> -// -#ifndef __PERF_GET_CURRENT_DIR_NAME_H -#ifndef HAVE_GET_CURRENT_DIR_NAME -char *get_current_dir_name(void); -#endif // HAVE_GET_CURRENT_DIR_NAME -#endif // __PERF_GET_CURRENT_DIR_NAME_H diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d06aa86352d3..f30e48eb3fc3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -44,6 +44,7 @@ #include "build-id.h" #include "data.h" #include <api/fs/fs.h> +#include <api/io_dir.h> #include "asm/bug.h" #include "tool.h" #include "time-utils.h" @@ -53,6 +54,7 @@ #include "bpf-event.h" #include "bpf-utils.h" #include "clockid.h" +#include "cacheline.h" #include <linux/ctype.h> #include <internal/lib.h> @@ -61,6 +63,15 @@ #include <event-parse.h> #endif +#define MAX_BPF_DATA_LEN (256 * 1024 * 1024) +#define MAX_BPF_PROGS 131072 +#define MAX_CACHE_ENTRIES 32768 +#define MAX_GROUP_DESC 32768 +#define MAX_NUMA_NODES 4096 +#define MAX_PMU_CAPS 512 +#define MAX_PMU_MAPPINGS 4096 +#define MAX_SCHED_DOMAINS 64 + /* * magic2 = "PERFILE2" * must be a numerical value to let the endianness @@ -75,6 +86,7 @@ static const u64 __perf_magic2 = 0x32454c4946524550ULL; static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; #define PERF_MAGIC __perf_magic2 +#define DNAME_LEN 16 const char perf_version_string[] = PERF_VERSION; @@ -304,16 +316,19 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) return 0; } -#ifdef HAVE_LIBTRACEEVENT static int write_tracing_data(struct feat_fd *ff, - struct evlist *evlist) + struct evlist *evlist __maybe_unused) { if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) return -1; +#ifdef HAVE_LIBTRACEEVENT return read_tracing_data(ff->fd, &evlist->core.entries); -} +#else + pr_err("ERROR: Trying to write tracing data without libtraceevent support.\n"); + return -1; #endif +} static int write_build_id(struct feat_fd *ff, struct evlist *evlist __maybe_unused) @@ -334,7 +349,6 @@ static int write_build_id(struct feat_fd *ff, pr_debug("failed to write buildid table\n"); return err; } - perf_session__cache_build_ids(session); return 0; } @@ -378,6 +392,21 @@ static int write_arch(struct feat_fd *ff, return do_write_string(ff, uts.machine); } +static int write_e_machine(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + /* e_machine expanded from 16 to 32-bits for alignment. */ + uint32_t e_flags; + uint32_t e_machine = perf_session__e_machine(evlist->session, &e_flags); + int ret; + + ret = do_write(ff, &e_machine, sizeof(e_machine)); + if (ret) + return ret; + + return do_write(ff, &e_flags, sizeof(e_flags)); +} + static int write_version(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { @@ -556,6 +585,7 @@ static int write_event_desc(struct feat_fd *ff, static int write_cmdline(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { + struct perf_env *env = &ff->ph->env; char pbuf[MAXPATHLEN], *buf; int i, ret, n; @@ -563,7 +593,7 @@ static int write_cmdline(struct feat_fd *ff, buf = perf_exe(pbuf, MAXPATHLEN); /* account for binary path */ - n = perf_env.nr_cmdline + 1; + n = env->nr_cmdline + 1; ret = do_write(ff, &n, sizeof(n)); if (ret < 0) @@ -573,8 +603,8 @@ static int write_cmdline(struct feat_fd *ff, if (ret < 0) return ret; - for (i = 0 ; i < perf_env.nr_cmdline; i++) { - ret = do_write_string(ff, perf_env.cmdline_argv[i]); + for (i = 0 ; i < env->nr_cmdline; i++) { + ret = do_write_string(ff, env->cmdline_argv[i]); if (ret < 0) return ret; } @@ -585,6 +615,7 @@ static int write_cmdline(struct feat_fd *ff, static int write_cpu_topology(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { + struct perf_env *env = &ff->ph->env; struct cpu_topology *tp; u32 i; int ret, j; @@ -612,17 +643,17 @@ static int write_cpu_topology(struct feat_fd *ff, break; } - ret = perf_env__read_cpu_topology_map(&perf_env); + ret = perf_env__read_cpu_topology_map(env); if (ret < 0) goto done; - for (j = 0; j < perf_env.nr_cpus_avail; j++) { - ret = do_write(ff, &perf_env.cpu[j].core_id, - sizeof(perf_env.cpu[j].core_id)); + for (j = 0; j < env->nr_cpus_avail; j++) { + ret = do_write(ff, &env->cpu[j].core_id, + sizeof(env->cpu[j].core_id)); if (ret < 0) return ret; - ret = do_write(ff, &perf_env.cpu[j].socket_id, - sizeof(perf_env.cpu[j].socket_id)); + ret = do_write(ff, &env->cpu[j].socket_id, + sizeof(env->cpu[j].socket_id)); if (ret < 0) return ret; } @@ -640,9 +671,9 @@ static int write_cpu_topology(struct feat_fd *ff, goto done; } - for (j = 0; j < perf_env.nr_cpus_avail; j++) { - ret = do_write(ff, &perf_env.cpu[j].die_id, - sizeof(perf_env.cpu[j].die_id)); + for (j = 0; j < env->nr_cpus_avail; j++) { + ret = do_write(ff, &env->cpu[j].die_id, + sizeof(env->cpu[j].die_id)); if (ret < 0) return ret; } @@ -1008,20 +1039,20 @@ static int write_dir_format(struct feat_fd *ff, return do_write(ff, &data->dir.version, sizeof(data->dir.version)); } -#ifdef HAVE_LIBBPF_SUPPORT -static int write_bpf_prog_info(struct feat_fd *ff, +static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, struct evlist *evlist __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT struct perf_env *env = &ff->ph->env; struct rb_root *root; struct rb_node *next; - int ret; + int ret = 0; down_read(&env->bpf_progs.lock); ret = do_write(ff, &env->bpf_progs.infos_cnt, sizeof(env->bpf_progs.infos_cnt)); - if (ret < 0) + if (ret < 0 || env->bpf_progs.infos_cnt == 0) goto out; root = &env->bpf_progs.infos; @@ -1049,22 +1080,27 @@ static int write_bpf_prog_info(struct feat_fd *ff, out: up_read(&env->bpf_progs.lock); return ret; +#else + pr_err("ERROR: Trying to write bpf_prog_info without libbpf support.\n"); + return -1; +#endif // HAVE_LIBBPF_SUPPORT } -static int write_bpf_btf(struct feat_fd *ff, +static int write_bpf_btf(struct feat_fd *ff __maybe_unused, struct evlist *evlist __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT struct perf_env *env = &ff->ph->env; struct rb_root *root; struct rb_node *next; - int ret; + int ret = 0; down_read(&env->bpf_progs.lock); ret = do_write(ff, &env->bpf_progs.btfs_cnt, sizeof(env->bpf_progs.btfs_cnt)); - if (ret < 0) + if (ret < 0 || env->bpf_progs.btfs_cnt == 0) goto out; root = &env->bpf_progs.btfs; @@ -1082,8 +1118,11 @@ static int write_bpf_btf(struct feat_fd *ff, out: up_read(&env->bpf_progs.lock); return ret; -} +#else + pr_err("ERROR: Trying to write btf data without libbpf support.\n"); + return -1; #endif // HAVE_LIBBPF_SUPPORT +} static int cpu_cache_level__sort(const void *a, const void *b) { @@ -1286,6 +1325,19 @@ out: return ret; } +static int write_cln_size(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + int cln_size = cacheline_size(); + + if (!cln_size) + cln_size = DEFAULT_CACHELINE_SIZE; + + ff->ph->env.cln_size = cln_size; + + return do_write(ff, &cln_size, sizeof(cln_size)); +} + static int write_stat(struct feat_fd *ff __maybe_unused, struct evlist *evlist __maybe_unused) { @@ -1311,11 +1363,11 @@ static int memory_node__read(struct memory_node *n, unsigned long idx) { unsigned int phys, size = 0; char path[PATH_MAX]; - struct dirent *ent; - DIR *dir; + struct io_dirent64 *ent; + struct io_dir dir; #define for_each_memory(mem, dir) \ - while ((ent = readdir(dir))) \ + while ((ent = io_dir__readdir(&dir)) != NULL) \ if (strcmp(ent->d_name, ".") && \ strcmp(ent->d_name, "..") && \ sscanf(ent->d_name, "memory%u", &mem) == 1) @@ -1324,9 +1376,9 @@ static int memory_node__read(struct memory_node *n, unsigned long idx) "%s/devices/system/node/node%lu", sysfs__mountpoint(), idx); - dir = opendir(path); - if (!dir) { - pr_warning("failed: can't open memory sysfs data\n"); + io_dir__init(&dir, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (dir.dirfd < 0) { + pr_warning("failed: can't open memory sysfs data '%s'\n", path); return -1; } @@ -1338,20 +1390,20 @@ static int memory_node__read(struct memory_node *n, unsigned long idx) n->set = bitmap_zalloc(size); if (!n->set) { - closedir(dir); + close(dir.dirfd); return -ENOMEM; } n->node = idx; n->size = size; - rewinddir(dir); + io_dir__rewinddir(&dir); for_each_memory(phys, dir) { __set_bit(phys, n->set); } - closedir(dir); + close(dir.dirfd); return 0; } @@ -1374,8 +1426,8 @@ static int memory_node__sort(const void *a, const void *b) static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) { char path[PATH_MAX]; - struct dirent *ent; - DIR *dir; + struct io_dirent64 *ent; + struct io_dir dir; int ret = 0; size_t cnt = 0, size = 0; struct memory_node *nodes = NULL; @@ -1383,14 +1435,14 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) scnprintf(path, PATH_MAX, "%s/devices/system/node/", sysfs__mountpoint()); - dir = opendir(path); - if (!dir) { + io_dir__init(&dir, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (dir.dirfd < 0) { pr_debug2("%s: couldn't read %s, does this arch have topology information?\n", __func__, path); return -1; } - while (!ret && (ent = readdir(dir))) { + while (!ret && (ent = io_dir__readdir(&dir))) { unsigned int idx; int r; @@ -1419,7 +1471,7 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) cnt += 1; } out: - closedir(dir); + close(dir.dirfd); if (!ret) { *cntp = cnt; *nodesp = nodes; @@ -1552,7 +1604,7 @@ static int __write_pmu_caps(struct feat_fd *ff, struct perf_pmu *pmu, static int write_cpu_pmu_caps(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { - struct perf_pmu *cpu_pmu = perf_pmus__find("cpu"); + struct perf_pmu *cpu_pmu = perf_pmus__find_core_pmu(); int ret; if (!cpu_pmu) @@ -1612,6 +1664,161 @@ static int write_pmu_caps(struct feat_fd *ff, return 0; } +struct cpu_domain_map **build_cpu_domain_map(u32 *schedstat_version, u32 *max_sched_domains, u32 nr) +{ + char dname[DNAME_LEN], cpumask[MAX_NR_CPUS]; + struct domain_info *domain_info; + struct cpu_domain_map **cd_map; + char cpulist[MAX_NR_CPUS]; + char *line = NULL; + u32 cpu, domain; + u32 dcount = 0; + size_t len; + FILE *fp; + + fp = fopen("/proc/schedstat", "r"); + if (!fp) { + pr_err("Failed to open /proc/schedstat\n"); + return NULL; + } + + cd_map = zalloc(sizeof(*cd_map) * nr); + if (!cd_map) + goto out; + + while (getline(&line, &len, fp) > 0) { + int retval; + + if (strncmp(line, "version", 7) == 0) { + retval = sscanf(line, "version %d\n", schedstat_version); + if (retval != 1) + continue; + + } else if (strncmp(line, "cpu", 3) == 0) { + retval = sscanf(line, "cpu%u %*s", &cpu); + if (retval == 1) { + cd_map[cpu] = zalloc(sizeof(*cd_map[cpu])); + if (!cd_map[cpu]) + goto out_free_line; + cd_map[cpu]->cpu = cpu; + } else + continue; + + dcount = 0; + } else if (strncmp(line, "domain", 6) == 0) { + struct domain_info **temp_domains; + + dcount++; + temp_domains = realloc(cd_map[cpu]->domains, dcount * sizeof(domain_info)); + if (!temp_domains) + goto out_free_line; + else + cd_map[cpu]->domains = temp_domains; + + domain_info = zalloc(sizeof(*domain_info)); + if (!domain_info) + goto out_free_line; + + cd_map[cpu]->domains[dcount - 1] = domain_info; + + if (*schedstat_version >= 17) { + retval = sscanf(line, "domain%u %s %s %*s", &domain, dname, + cpumask); + if (retval != 3) + continue; + + domain_info->dname = strdup(dname); + if (!domain_info->dname) + goto out_free_line; + } else { + retval = sscanf(line, "domain%u %s %*s", &domain, cpumask); + if (retval != 2) + continue; + } + + domain_info->domain = domain; + if (domain > *max_sched_domains) + *max_sched_domains = domain; + + domain_info->cpumask = strdup(cpumask); + if (!domain_info->cpumask) + goto out_free_line; + + cpumask_to_cpulist(cpumask, cpulist); + domain_info->cpulist = strdup(cpulist); + if (!domain_info->cpulist) + goto out_free_line; + + cd_map[cpu]->nr_domains = dcount; + } + } + +out_free_line: + free(line); +out: + fclose(fp); + return cd_map; +} + +static int write_cpu_domain_info(struct feat_fd *ff, + struct evlist *evlist __maybe_unused) +{ + u32 max_sched_domains = 0, schedstat_version = 0; + struct cpu_domain_map **cd_map; + u32 i, j, nr, ret; + + nr = cpu__max_present_cpu().cpu; + + cd_map = build_cpu_domain_map(&schedstat_version, &max_sched_domains, nr); + if (!cd_map) + return -1; + + ret = do_write(ff, &schedstat_version, sizeof(u32)); + if (ret < 0) + goto out; + + max_sched_domains += 1; + ret = do_write(ff, &max_sched_domains, sizeof(u32)); + if (ret < 0) + goto out; + + for (i = 0; i < nr; i++) { + if (!cd_map[i]) + continue; + + ret = do_write(ff, &cd_map[i]->cpu, sizeof(u32)); + if (ret < 0) + goto out; + + ret = do_write(ff, &cd_map[i]->nr_domains, sizeof(u32)); + if (ret < 0) + goto out; + + for (j = 0; j < cd_map[i]->nr_domains; j++) { + ret = do_write(ff, &cd_map[i]->domains[j]->domain, sizeof(u32)); + if (ret < 0) + goto out; + if (schedstat_version >= 17) { + ret = do_write_string(ff, cd_map[i]->domains[j]->dname); + if (ret < 0) + goto out; + } + + ret = do_write_string(ff, cd_map[i]->domains[j]->cpumask); + if (ret < 0) + goto out; + + ret = do_write_string(ff, cd_map[i]->domains[j]->cpulist); + if (ret < 0) + goto out; + } + } + +out: + free_cpu_domain_info(cd_map, schedstat_version, nr); + return ret; +} + static void print_hostname(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); @@ -1627,6 +1834,12 @@ static void print_arch(struct feat_fd *ff, FILE *fp) fprintf(fp, "# arch : %s\n", ff->ph->env.arch); } +static void print_e_machine(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# e_machine : %u\n", ff->ph->env.e_machine); + fprintf(fp, "# e_flags : %u\n", ff->ph->env.e_flags); +} + static void print_cpudesc(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# cpudesc : %s\n", ff->ph->env.cpu_desc); @@ -1801,9 +2014,9 @@ static void print_dir_format(struct feat_fd *ff, FILE *fp) fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version); } -#ifdef HAVE_LIBBPF_SUPPORT -static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) +static void print_bpf_prog_info(struct feat_fd *ff __maybe_unused, FILE *fp) { +#ifdef HAVE_LIBBPF_SUPPORT struct perf_env *env = &ff->ph->env; struct rb_root *root; struct rb_node *next; @@ -1813,6 +2026,9 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) root = &env->bpf_progs.infos; next = rb_first(root); + if (!next) + fprintf(fp, "# bpf_prog_info empty\n"); + while (next) { struct bpf_prog_info_node *node; @@ -1824,10 +2040,14 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) } up_read(&env->bpf_progs.lock); +#else + fprintf(fp, "# bpf_prog_info missing, no libbpf support\n"); +#endif // HAVE_LIBBPF_SUPPORT } -static void print_bpf_btf(struct feat_fd *ff, FILE *fp) +static void print_bpf_btf(struct feat_fd *ff __maybe_unused, FILE *fp) { +#ifdef HAVE_LIBBPF_SUPPORT struct perf_env *env = &ff->ph->env; struct rb_root *root; struct rb_node *next; @@ -1837,6 +2057,9 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp) root = &env->bpf_progs.btfs; next = rb_first(root); + if (!next) + printf("# btf info empty\n"); + while (next) { struct btf_node *node; @@ -1846,8 +2069,10 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp) } up_read(&env->bpf_progs.lock); -} +#else + fprintf(fp, "# bpf btf data missing, no libbpf support\n"); #endif // HAVE_LIBBPF_SUPPORT +} static void free_event_desc(struct evsel *events) { @@ -2076,6 +2301,11 @@ static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused) } } +static void print_cln_size(struct feat_fd *ff, FILE *fp) +{ + fprintf(fp, "# cacheline size: %u\n", ff->ph->env.cln_size); +} + static void print_compressed(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# compressed : %s, level = %d, ratio = %d\n", @@ -2110,17 +2340,18 @@ static void print_cpu_pmu_caps(struct feat_fd *ff, FILE *fp) static void print_pmu_caps(struct feat_fd *ff, FILE *fp) { + struct perf_env *env = &ff->ph->env; struct pmu_caps *pmu_caps; - for (int i = 0; i < ff->ph->env.nr_pmus_with_caps; i++) { - pmu_caps = &ff->ph->env.pmu_caps[i]; + for (int i = 0; i < env->nr_pmus_with_caps; i++) { + pmu_caps = &env->pmu_caps[i]; __print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps, pmu_caps->pmu_name); } - if (strcmp(perf_env__arch(&ff->ph->env), "x86") == 0 && - perf_env__has_pmu_mapping(&ff->ph->env, "ibs_op")) { - char *max_precise = perf_env__find_pmu_cap(&ff->ph->env, "cpu", "max_precise"); + if (strcmp(perf_env__arch(env), "x86") == 0 && + perf_env__has_pmu_mapping(env, "ibs_op")) { + char *max_precise = perf_env__find_pmu_cap(env, "cpu", "max_precise"); if (max_precise != NULL && atoi(max_precise) == 0) fprintf(fp, "# AMD systems uses ibs_op// PMU for some precise events, e.g.: cycles:p, see the 'perf list' man page for further details.\n"); @@ -2129,18 +2360,19 @@ static void print_pmu_caps(struct feat_fd *ff, FILE *fp) static void print_pmu_mappings(struct feat_fd *ff, FILE *fp) { + struct perf_env *env = &ff->ph->env; const char *delimiter = "# pmu mappings: "; char *str, *tmp; u32 pmu_num; u32 type; - pmu_num = ff->ph->env.nr_pmu_mappings; + pmu_num = env->nr_pmu_mappings; if (!pmu_num) { fprintf(fp, "# pmu mappings: not available\n"); return; } - str = ff->ph->env.pmu_mappings; + str = env->pmu_mappings; while (pmu_num) { type = strtoul(str, &tmp, 0); @@ -2222,17 +2454,51 @@ static void memory_node__fprintf(struct memory_node *n, static void print_mem_topology(struct feat_fd *ff, FILE *fp) { + struct perf_env *env = &ff->ph->env; struct memory_node *nodes; int i, nr; - nodes = ff->ph->env.memory_nodes; - nr = ff->ph->env.nr_memory_nodes; + nodes = env->memory_nodes; + nr = env->nr_memory_nodes; fprintf(fp, "# memory nodes (nr %d, block size 0x%llx):\n", - nr, ff->ph->env.memory_bsize); + nr, env->memory_bsize); for (i = 0; i < nr; i++) { - memory_node__fprintf(&nodes[i], ff->ph->env.memory_bsize, fp); + memory_node__fprintf(&nodes[i], env->memory_bsize, fp); + } +} + +static void print_cpu_domain_info(struct feat_fd *ff, FILE *fp) +{ + struct cpu_domain_map **cd_map = ff->ph->env.cpu_domain; + u32 nr = ff->ph->env.nr_cpus_avail; + struct domain_info *d_info; + u32 i, j; + + fprintf(fp, "# schedstat version : %u\n", ff->ph->env.schedstat_version); + fprintf(fp, "# Maximum sched domains : %u\n", ff->ph->env.max_sched_domains); + + for (i = 0; i < nr; i++) { + if (!cd_map[i]) + continue; + + fprintf(fp, "# cpu : %u\n", cd_map[i]->cpu); + fprintf(fp, "# nr_domains : %u\n", cd_map[i]->nr_domains); + + for (j = 0; j < cd_map[i]->nr_domains; j++) { + d_info = cd_map[i]->domains[j]; + if (!d_info) + continue; + + fprintf(fp, "# Domain : %u\n", d_info->domain); + + if (ff->ph->env.schedstat_version >= 17) + fprintf(fp, "# Domain name : %s\n", d_info->dname); + + fprintf(fp, "# Domain cpu map : %s\n", d_info->cpumask); + fprintf(fp, "# Domain cpu list : %s\n", d_info->cpulist); + } } } @@ -2290,7 +2556,7 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev, free(m.name); } - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); pr_debug("build id event received for %s: %s [%zu]\n", dso__long_name(dso), sbuild_id, size); dso__put(dso); @@ -2324,6 +2590,11 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, perf_event_header__bswap(&old_bev.header); len = old_bev.header.size - sizeof(old_bev); + if (len < 0 || len >= PATH_MAX) { + pr_warning("invalid build_id filename length %zd\n", len); + return -1; + } + if (readn(input, filename, len) != len) return -1; @@ -2366,6 +2637,11 @@ static int perf_header__read_build_ids(struct perf_header *header, perf_event_header__bswap(&bev.header); len = bev.header.size - sizeof(bev); + if (len < 0 || len >= PATH_MAX) { + pr_warning("invalid build_id filename length %zd\n", len); + goto out; + } + if (readn(input, filename, len) != len) goto out; /* @@ -2412,14 +2688,28 @@ FEAT_PROCESS_STR_FUN(arch, arch); FEAT_PROCESS_STR_FUN(cpudesc, cpu_desc); FEAT_PROCESS_STR_FUN(cpuid, cpuid); -#ifdef HAVE_LIBTRACEEVENT -static int process_tracing_data(struct feat_fd *ff, void *data) +static int process_e_machine(struct feat_fd *ff, void *data __maybe_unused) { + int ret; + + ret = do_read_u32(ff, &ff->ph->env.e_machine); + if (ret) + return ret; + + return do_read_u32(ff, &ff->ph->env.e_flags); +} + +static int process_tracing_data(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) +{ +#ifdef HAVE_LIBTRACEEVENT ssize_t ret = trace_report(ff->fd, data, false); return ret < 0 ? -1 : 0; -} +#else + pr_err("ERROR: Trying to read tracing data without libtraceevent support.\n"); + return -1; #endif +} static int process_build_id(struct feat_fd *ff, void *data __maybe_unused) { @@ -2430,6 +2720,7 @@ static int process_build_id(struct feat_fd *ff, void *data __maybe_unused) static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; int ret; u32 nr_cpus_avail, nr_cpus_online; @@ -2440,20 +2731,28 @@ static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused) ret = do_read_u32(ff, &nr_cpus_online); if (ret) return ret; - ff->ph->env.nr_cpus_avail = (int)nr_cpus_avail; - ff->ph->env.nr_cpus_online = (int)nr_cpus_online; + + if (nr_cpus_online > nr_cpus_avail) { + pr_err("Invalid HEADER_NRCPUS: nr_cpus_online (%u) > nr_cpus_avail (%u)\n", + nr_cpus_online, nr_cpus_avail); + return -1; + } + + env->nr_cpus_avail = (int)nr_cpus_avail; + env->nr_cpus_online = (int)nr_cpus_online; return 0; } static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; u64 total_mem; int ret; ret = do_read_u64(ff, &total_mem); if (ret) return -1; - ff->ph->env.total_mem = (unsigned long long)total_mem; + env->total_mem = (unsigned long long)total_mem; return 0; } @@ -2512,21 +2811,31 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused) return 0; } +/* + * Some arbitrary max for the number of command line arguments, + * Wildcards can expand and end up with tons of command line args. + */ +#define MAX_CMDLINE_NR 1048576 + static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; char *str, *cmdline = NULL, **argv = NULL; u32 nr, i, len = 0; if (do_read_u32(ff, &nr)) return -1; - ff->ph->env.nr_cmdline = nr; + if (nr > MAX_CMDLINE_NR) + return -1; + + env->nr_cmdline = nr; cmdline = zalloc(ff->size + nr + 1); if (!cmdline) return -1; - argv = zalloc(sizeof(char *) * (nr + 1)); + argv = calloc(nr + 1, sizeof(char *)); if (!argv) goto error; @@ -2540,8 +2849,8 @@ static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused) len += strlen(str) + 1; free(str); } - ff->ph->env.cmdline = cmdline; - ff->ph->env.cmdline_argv = (const char **) argv; + env->cmdline = cmdline; + env->cmdline_argv = (const char **) argv; return 0; error: @@ -2555,19 +2864,29 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) u32 nr, i; char *str = NULL; struct strbuf sb; - int cpu_nr = ff->ph->env.nr_cpus_avail; + struct perf_env *env = &ff->ph->env; + int cpu_nr = env->nr_cpus_avail; u64 size = 0; - struct perf_header *ph = ff->ph; - bool do_core_id_test = true; - ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu)); - if (!ph->env.cpu) + if (cpu_nr == 0) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: missing HEADER_NRCPUS\n"); + return -1; + } + + env->cpu = calloc(cpu_nr, sizeof(*env->cpu)); + if (!env->cpu) return -1; if (do_read_u32(ff, &nr)) goto free_cpu; - ph->env.nr_sibling_cores = nr; + if (nr > (u32)cpu_nr) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: nr_sibling_cores (%u) > nr_cpus_avail (%d)\n", + nr, cpu_nr); + goto free_cpu; + } + + env->nr_sibling_cores = nr; size += sizeof(u32); if (strbuf_init(&sb, 128) < 0) goto free_cpu; @@ -2583,12 +2902,18 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) size += string_size(str); zfree(&str); } - ph->env.sibling_cores = strbuf_detach(&sb, NULL); + env->sibling_cores = strbuf_detach(&sb, NULL); if (do_read_u32(ff, &nr)) - return -1; + goto free_cpu; - ph->env.nr_sibling_threads = nr; + if (nr > (u32)cpu_nr) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: nr_sibling_threads (%u) > nr_cpus_avail (%d)\n", + nr, cpu_nr); + goto free_cpu; + } + + env->nr_sibling_threads = nr; size += sizeof(u32); for (i = 0; i < nr; i++) { @@ -2602,43 +2927,28 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) size += string_size(str); zfree(&str); } - ph->env.sibling_threads = strbuf_detach(&sb, NULL); + env->sibling_threads = strbuf_detach(&sb, NULL); /* * The header may be from old perf, * which doesn't include core id and socket id information. */ if (ff->size <= size) { - zfree(&ph->env.cpu); + zfree(&env->cpu); return 0; } - /* On s390 the socket_id number is not related to the numbers of cpus. - * The socket_id number might be higher than the numbers of cpus. - * This depends on the configuration. - * AArch64 is the same. - */ - if (ph->env.arch && (!strncmp(ph->env.arch, "s390", 4) - || !strncmp(ph->env.arch, "aarch64", 7))) - do_core_id_test = false; - for (i = 0; i < (u32)cpu_nr; i++) { if (do_read_u32(ff, &nr)) goto free_cpu; - ph->env.cpu[i].core_id = nr; + env->cpu[i].core_id = nr; size += sizeof(u32); if (do_read_u32(ff, &nr)) goto free_cpu; - if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) { - pr_debug("socket_id number is too big." - "You may need to upgrade the perf tool.\n"); - goto free_cpu; - } - - ph->env.cpu[i].socket_id = nr; + env->cpu[i].socket_id = nr; size += sizeof(u32); } @@ -2650,9 +2960,15 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) return 0; if (do_read_u32(ff, &nr)) - return -1; + goto free_cpu; - ph->env.nr_sibling_dies = nr; + if (nr > (u32)cpu_nr) { + pr_err("Invalid HEADER_CPU_TOPOLOGY: nr_sibling_dies (%u) > nr_cpus_avail (%d)\n", + nr, cpu_nr); + goto free_cpu; + } + + env->nr_sibling_dies = nr; size += sizeof(u32); for (i = 0; i < nr; i++) { @@ -2666,13 +2982,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) size += string_size(str); zfree(&str); } - ph->env.sibling_dies = strbuf_detach(&sb, NULL); + env->sibling_dies = strbuf_detach(&sb, NULL); for (i = 0; i < (u32)cpu_nr; i++) { if (do_read_u32(ff, &nr)) goto free_cpu; - ph->env.cpu[i].die_id = nr; + env->cpu[i].die_id = nr; } return 0; @@ -2681,12 +2997,13 @@ error: strbuf_release(&sb); zfree(&str); free_cpu: - zfree(&ph->env.cpu); + zfree(&env->cpu); return -1; } static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; struct numa_node *nodes, *n; u32 nr, i; char *str; @@ -2695,7 +3012,19 @@ static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) if (do_read_u32(ff, &nr)) return -1; - nodes = zalloc(sizeof(*nodes) * nr); + if (nr > MAX_NUMA_NODES) { + pr_err("Invalid HEADER_NUMA_TOPOLOGY: nr_nodes (%u) > %u\n", + nr, MAX_NUMA_NODES); + return -1; + } + + if (ff->size < sizeof(u32) + nr * (sizeof(u32) + 2 * sizeof(u64))) { + pr_err("Invalid HEADER_NUMA_TOPOLOGY: section too small (%zu) for %u nodes\n", + ff->size, nr); + return -1; + } + + nodes = calloc(nr, sizeof(*nodes)); if (!nodes) return -ENOMEM; @@ -2721,8 +3050,8 @@ static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) if (!n->map) goto error; } - ff->ph->env.nr_numa_nodes = nr; - ff->ph->env.numa_nodes = nodes; + env->nr_numa_nodes = nr; + env->numa_nodes = nodes; return 0; error: @@ -2732,6 +3061,7 @@ error: static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; char *name; u32 pmu_num; u32 type; @@ -2745,7 +3075,19 @@ static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) return 0; } - ff->ph->env.nr_pmu_mappings = pmu_num; + if (pmu_num > MAX_PMU_MAPPINGS) { + pr_err("Invalid HEADER_PMU_MAPPINGS: pmu_num (%u) > %u\n", + pmu_num, MAX_PMU_MAPPINGS); + return -1; + } + + if (ff->size < sizeof(u32) + pmu_num * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_PMU_MAPPINGS: section too small (%zu) for %u PMUs\n", + ff->size, pmu_num); + return -1; + } + + env->nr_pmu_mappings = pmu_num; if (strbuf_init(&sb, 128) < 0) return -1; @@ -2764,12 +3106,14 @@ static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) goto error; if (!strcmp(name, "msr")) - ff->ph->env.msr_pmu_type = type; + env->msr_pmu_type = type; free(name); pmu_num--; } - ff->ph->env.pmu_mappings = strbuf_detach(&sb, NULL); + /* AMD may set it by evlist__has_amd_ibs() from perf_session__new() */ + free(env->pmu_mappings); + env->pmu_mappings = strbuf_detach(&sb, NULL); return 0; error: @@ -2779,6 +3123,7 @@ error: static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; size_t ret = -1; u32 i, nr, nr_groups; struct perf_session *session; @@ -2792,12 +3137,25 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) if (do_read_u32(ff, &nr_groups)) return -1; - ff->ph->env.nr_groups = nr_groups; if (!nr_groups) { pr_debug("group desc not available\n"); return 0; } + if (nr_groups > MAX_GROUP_DESC) { + pr_err("Invalid HEADER_GROUP_DESC: nr_groups (%u) > %u\n", + nr_groups, MAX_GROUP_DESC); + return -1; + } + + if (ff->size < sizeof(u32) + nr_groups * 3 * sizeof(u32)) { + pr_err("Invalid HEADER_GROUP_DESC: section too small (%zu) for %u groups\n", + ff->size, nr_groups); + return -1; + } + + env->nr_groups = nr_groups; + desc = calloc(nr_groups, sizeof(*desc)); if (!desc) return -1; @@ -2876,6 +3234,7 @@ static int process_auxtrace(struct feat_fd *ff, void *data __maybe_unused) static int process_cache(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; struct cpu_cache_level *caches; u32 cnt, i, version; @@ -2888,7 +3247,19 @@ static int process_cache(struct feat_fd *ff, void *data __maybe_unused) if (do_read_u32(ff, &cnt)) return -1; - caches = zalloc(sizeof(*caches) * cnt); + if (cnt > MAX_CACHE_ENTRIES) { + pr_err("Invalid HEADER_CACHE: cnt (%u) > %u\n", + cnt, MAX_CACHE_ENTRIES); + return -1; + } + + if (ff->size < 2 * sizeof(u32) + cnt * 7 * sizeof(u32)) { + pr_err("Invalid HEADER_CACHE: section too small (%zu) for %u entries\n", + ff->size, cnt); + return -1; + } + + caches = calloc(cnt, sizeof(*caches)); if (!caches) return -1; @@ -2916,8 +3287,8 @@ static int process_cache(struct feat_fd *ff, void *data __maybe_unused) #undef _R } - ff->ph->env.caches = caches; - ff->ph->env.caches_cnt = cnt; + env->caches = caches; + env->caches_cnt = cnt; return 0; out_free_caches: for (i = 0; i < cnt; i++) { @@ -2929,6 +3300,16 @@ out_free_caches: return -1; } +static int process_cln_size(struct feat_fd *ff, void *data __maybe_unused) +{ + struct perf_env *env = &ff->ph->env; + + if (do_read_u32(ff, &env->cln_size)) + return -1; + + return 0; +} + static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; @@ -2953,6 +3334,7 @@ static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused) static int process_mem_topology(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; struct memory_node *nodes; u64 version, i, nr, bsize; int ret = -1; @@ -2969,7 +3351,19 @@ static int process_mem_topology(struct feat_fd *ff, if (do_read_u64(ff, &nr)) return -1; - nodes = zalloc(sizeof(*nodes) * nr); + if (nr > MAX_NUMA_NODES) { + pr_err("Invalid HEADER_MEM_TOPOLOGY: nr_nodes (%llu) > %u\n", + (unsigned long long)nr, MAX_NUMA_NODES); + return -1; + } + + if (ff->size < 3 * sizeof(u64) + nr * 2 * sizeof(u64)) { + pr_err("Invalid HEADER_MEM_TOPOLOGY: section too small (%zu) for %llu nodes\n", + ff->size, (unsigned long long)nr); + return -1; + } + + nodes = calloc(nr, sizeof(*nodes)); if (!nodes) return -1; @@ -2991,9 +3385,9 @@ static int process_mem_topology(struct feat_fd *ff, nodes[i] = n; } - ff->ph->env.memory_bsize = bsize; - ff->ph->env.memory_nodes = nodes; - ff->ph->env.nr_memory_nodes = nr; + env->memory_bsize = bsize; + env->memory_nodes = nodes; + env->nr_memory_nodes = nr; ret = 0; out: @@ -3005,7 +3399,9 @@ out: static int process_clockid(struct feat_fd *ff, void *data __maybe_unused) { - if (do_read_u64(ff, &ff->ph->env.clock.clockid_res_ns)) + struct perf_env *env = &ff->ph->env; + + if (do_read_u64(ff, &env->clock.clockid_res_ns)) return -1; return 0; @@ -3014,6 +3410,7 @@ static int process_clockid(struct feat_fd *ff, static int process_clock_data(struct feat_fd *ff, void *_data __maybe_unused) { + struct perf_env *env = &ff->ph->env; u32 data32; u64 data64; @@ -3028,26 +3425,27 @@ static int process_clock_data(struct feat_fd *ff, if (do_read_u32(ff, &data32)) return -1; - ff->ph->env.clock.clockid = data32; + env->clock.clockid = data32; /* TOD ref time */ if (do_read_u64(ff, &data64)) return -1; - ff->ph->env.clock.tod_ns = data64; + env->clock.tod_ns = data64; /* clockid ref time */ if (do_read_u64(ff, &data64)) return -1; - ff->ph->env.clock.clockid_ns = data64; - ff->ph->env.clock.enabled = true; + env->clock.clockid_ns = data64; + env->clock.enabled = true; return 0; } static int process_hybrid_topology(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; struct hybrid_node *nodes, *n; u32 nr, i; @@ -3055,7 +3453,19 @@ static int process_hybrid_topology(struct feat_fd *ff, if (do_read_u32(ff, &nr)) return -1; - nodes = zalloc(sizeof(*nodes) * nr); + if (nr > MAX_PMU_MAPPINGS) { + pr_err("Invalid HEADER_HYBRID_TOPOLOGY: nr_nodes (%u) > %u\n", + nr, MAX_PMU_MAPPINGS); + return -1; + } + + if (ff->size < sizeof(u32) + nr * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_HYBRID_TOPOLOGY: section too small (%zu) for %u nodes\n", + ff->size, nr); + return -1; + } + + nodes = calloc(nr, sizeof(*nodes)); if (!nodes) return -ENOMEM; @@ -3071,8 +3481,8 @@ static int process_hybrid_topology(struct feat_fd *ff, goto error; } - ff->ph->env.nr_hybrid_nodes = nr; - ff->ph->env.hybrid_nodes = nodes; + env->nr_hybrid_nodes = nr; + env->hybrid_nodes = nodes; return 0; error: @@ -3100,9 +3510,9 @@ static int process_dir_format(struct feat_fd *ff, return do_read_u64(ff, &data->dir.version); } -#ifdef HAVE_LIBBPF_SUPPORT -static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) +static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT struct bpf_prog_info_node *info_node; struct perf_env *env = &ff->ph->env; struct perf_bpil *info_linear; @@ -3117,6 +3527,18 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) if (do_read_u32(ff, &count)) return -1; + if (count > MAX_BPF_PROGS) { + pr_err("Invalid HEADER_BPF_PROG_INFO: count (%u) > %u\n", + count, MAX_BPF_PROGS); + return -1; + } + + if (ff->size < sizeof(u32) + count * (2 * sizeof(u32) + sizeof(u64))) { + pr_err("Invalid HEADER_BPF_PROG_INFO: section too small (%zu) for %u entries\n", + ff->size, count); + return -1; + } + down_write(&env->bpf_progs.lock); for (i = 0; i < count; ++i) { @@ -3134,6 +3556,12 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) goto out; } + if (data_len > MAX_BPF_DATA_LEN) { + pr_warning("Invalid HEADER_BPF_PROG_INFO: data_len (%u) too large\n", + data_len); + goto out; + } + info_linear = malloc(sizeof(struct perf_bpil) + data_len); if (!info_linear) @@ -3158,6 +3586,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) /* after reading from file, translate offset to address */ bpil_offs_to_addr(info_linear); info_node->info_linear = info_linear; + info_node->metadata = NULL; if (!__perf_env__insert_bpf_prog_info(env, info_node)) { free(info_linear); free(info_node); @@ -3171,10 +3600,15 @@ out: free(info_node); up_write(&env->bpf_progs.lock); return err; +#else + pr_err("ERROR: Trying to read bpf_prog_info without libbpf support.\n"); + return -1; +#endif // HAVE_LIBBPF_SUPPORT } -static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) +static int process_bpf_btf(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT struct perf_env *env = &ff->ph->env; struct btf_node *node = NULL; u32 count, i; @@ -3188,6 +3622,17 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) if (do_read_u32(ff, &count)) return -1; + if (count > MAX_BPF_PROGS) { + pr_err("bpf btf count %u too large (max %u)\n", count, MAX_BPF_PROGS); + return -1; + } + + if (ff->size < sizeof(u32) + count * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_BPF_BTF: section too small (%zu) for %u entries\n", + ff->size, count); + return -1; + } + down_write(&env->bpf_progs.lock); for (i = 0; i < count; ++i) { @@ -3198,6 +3643,12 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) if (do_read_u32(ff, &data_size)) goto out; + if (data_size > MAX_BPF_DATA_LEN) { + pr_err("bpf btf data size %u too large (max %u)\n", + data_size, MAX_BPF_DATA_LEN); + goto out; + } + node = malloc(sizeof(struct btf_node) + data_size); if (!node) goto out; @@ -3218,25 +3669,30 @@ out: up_write(&env->bpf_progs.lock); free(node); return err; -} +#else + pr_err("ERROR: Trying to read btf data without libbpf support.\n"); + return -1; #endif // HAVE_LIBBPF_SUPPORT +} static int process_compressed(struct feat_fd *ff, void *data __maybe_unused) { - if (do_read_u32(ff, &(ff->ph->env.comp_ver))) + struct perf_env *env = &ff->ph->env; + + if (do_read_u32(ff, &(env->comp_ver))) return -1; - if (do_read_u32(ff, &(ff->ph->env.comp_type))) + if (do_read_u32(ff, &(env->comp_type))) return -1; - if (do_read_u32(ff, &(ff->ph->env.comp_level))) + if (do_read_u32(ff, &(env->comp_level))) return -1; - if (do_read_u32(ff, &(ff->ph->env.comp_ratio))) + if (do_read_u32(ff, &(env->comp_ratio))) return -1; - if (do_read_u32(ff, &(ff->ph->env.comp_mmap_len))) + if (do_read_u32(ff, &(env->comp_mmap_len))) return -1; return 0; @@ -3259,7 +3715,13 @@ static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps, if (!nr_pmu_caps) return 0; - *caps = zalloc(sizeof(char *) * nr_pmu_caps); + if (nr_pmu_caps > MAX_PMU_CAPS) { + pr_err("Invalid pmu caps: nr_pmu_caps (%u) > %u\n", + nr_pmu_caps, MAX_PMU_CAPS); + return -1; + } + + *caps = calloc(nr_pmu_caps, sizeof(char *)); if (!*caps) return -1; @@ -3308,19 +3770,21 @@ error: static int process_cpu_pmu_caps(struct feat_fd *ff, void *data __maybe_unused) { - int ret = __process_pmu_caps(ff, &ff->ph->env.nr_cpu_pmu_caps, - &ff->ph->env.cpu_pmu_caps, - &ff->ph->env.max_branches, - &ff->ph->env.br_cntr_nr, - &ff->ph->env.br_cntr_width); + struct perf_env *env = &ff->ph->env; + int ret = __process_pmu_caps(ff, &env->nr_cpu_pmu_caps, + &env->cpu_pmu_caps, + &env->max_branches, + &env->br_cntr_nr, + &env->br_cntr_width); - if (!ret && !ff->ph->env.cpu_pmu_caps) + if (!ret && !env->cpu_pmu_caps) pr_debug("cpu pmu capabilities not available\n"); return ret; } static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused) { + struct perf_env *env = &ff->ph->env; struct pmu_caps *pmu_caps; u32 nr_pmu, i; int ret; @@ -3334,7 +3798,19 @@ static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused) return 0; } - pmu_caps = zalloc(sizeof(*pmu_caps) * nr_pmu); + if (nr_pmu > MAX_PMU_MAPPINGS) { + pr_err("Invalid HEADER_PMU_CAPS: nr_pmu (%u) > %u\n", + nr_pmu, MAX_PMU_MAPPINGS); + return -1; + } + + if (ff->size < sizeof(u32) + nr_pmu * sizeof(u32)) { + pr_err("Invalid HEADER_PMU_CAPS: section too small (%zu) for %u PMUs\n", + ff->size, nr_pmu); + return -1; + } + + pmu_caps = calloc(nr_pmu, sizeof(*pmu_caps)); if (!pmu_caps) return -ENOMEM; @@ -3358,8 +3834,8 @@ static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused) } } - ff->ph->env.nr_pmus_with_caps = nr_pmu; - ff->ph->env.pmu_caps = pmu_caps; + env->nr_pmus_with_caps = nr_pmu; + env->pmu_caps = pmu_caps; return 0; err: @@ -3374,6 +3850,144 @@ err: return ret; } +static int process_cpu_domain_info(struct feat_fd *ff, void *data __maybe_unused) +{ + u32 schedstat_version, max_sched_domains, cpu, domain, nr_domains; + struct perf_env *env = &ff->ph->env; + char *dname, *cpumask, *cpulist; + struct cpu_domain_map **cd_map; + struct domain_info *d_info; + u32 nra, nr, i, j; + int ret; + + nra = env->nr_cpus_avail; + nr = env->nr_cpus_online; + + if (nra == 0 || nr == 0) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: missing HEADER_NRCPUS\n"); + return -1; + } + + if (ff->size < 2 * sizeof(u32) + nr * 2 * sizeof(u32)) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: section too small (%zu) for %u CPUs\n", + (size_t)ff->size, nr); + return -1; + } + + cd_map = calloc(nra, sizeof(*cd_map)); + if (!cd_map) + return -1; + + env->cpu_domain = cd_map; + + ret = do_read_u32(ff, &schedstat_version); + if (ret) + return ret; + + env->schedstat_version = schedstat_version; + + ret = do_read_u32(ff, &max_sched_domains); + if (ret) + return ret; + + /* + * Sanity check: real systems have at most ~10 sched domain levels + * (SMT, CLS, MC, PKG + NUMA hops). Reject obviously bogus values + * from malformed perf.data files before they cause excessive + * allocation in the per-CPU loop. + */ + if (max_sched_domains > MAX_SCHED_DOMAINS) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: max_sched_domains %u > %u\n", + max_sched_domains, MAX_SCHED_DOMAINS); + return -1; + } + + env->max_sched_domains = max_sched_domains; + + for (i = 0; i < nr; i++) { + if (do_read_u32(ff, &cpu)) + return -1; + + if (cpu >= nra) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: cpu %d >= nr_cpus_avail (%d)\n", cpu, nra); + return -1; + } + + if (cd_map[cpu]) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: duplicate cpu %u\n", cpu); + return -1; + } + + cd_map[cpu] = zalloc(sizeof(*cd_map[cpu])); + if (!cd_map[cpu]) + return -1; + + cd_map[cpu]->cpu = cpu; + + if (do_read_u32(ff, &nr_domains)) + return -1; + + if (nr_domains > max_sched_domains) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: nr_domains %u > max_sched_domains (%u)\n", + nr_domains, max_sched_domains); + return -1; + } + + cd_map[cpu]->nr_domains = nr_domains; + + cd_map[cpu]->domains = calloc(max_sched_domains, sizeof(*d_info)); + if (!cd_map[cpu]->domains) + return -1; + + for (j = 0; j < nr_domains; j++) { + if (do_read_u32(ff, &domain)) + return -1; + + if (domain >= max_sched_domains) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: domain %d >= max_sched_domains (%d)\n", + domain, max_sched_domains); + return -1; + } + + d_info = zalloc(sizeof(*d_info)); + if (!d_info) + return -1; + + if (cd_map[cpu]->domains[domain]) { + pr_err("Invalid HEADER_CPU_DOMAIN_INFO: duplicate domain %u for cpu %u\n", + domain, cpu); + free(d_info); + return -1; + } + + cd_map[cpu]->domains[domain] = d_info; + d_info->domain = domain; + + if (schedstat_version >= 17) { + dname = do_read_string(ff); + if (!dname) + return -1; + + d_info->dname = dname; + } + + cpumask = do_read_string(ff); + if (!cpumask) + return -1; + + d_info->cpumask = cpumask; + + cpulist = do_read_string(ff); + if (!cpulist) + return -1; + + d_info->cpulist = cpulist; + } + } + + return ret; +} + #define FEAT_OPR(n, func, __full_only) \ [HEADER_##n] = { \ .name = __stringify(n), \ @@ -3404,9 +4018,7 @@ err: const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE]; const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { -#ifdef HAVE_LIBTRACEEVENT FEAT_OPN(TRACING_DATA, tracing_data, false), -#endif FEAT_OPN(BUILD_ID, build_id, false), FEAT_OPR(HOSTNAME, hostname, false), FEAT_OPR(OSRELEASE, osrelease, false), @@ -3430,15 +4042,16 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), FEAT_OPR(CLOCKID, clockid, false), FEAT_OPN(DIR_FORMAT, dir_format, false), -#ifdef HAVE_LIBBPF_SUPPORT FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false), FEAT_OPR(BPF_BTF, bpf_btf, false), -#endif FEAT_OPR(COMPRESSED, compressed, false), FEAT_OPR(CPU_PMU_CAPS, cpu_pmu_caps, false), FEAT_OPR(CLOCK_DATA, clock_data, false), FEAT_OPN(HYBRID_TOPOLOGY, hybrid_topology, true), FEAT_OPR(PMU_CAPS, pmu_caps, false), + FEAT_OPR(CPU_DOMAIN_INFO, cpu_domain_info, true), + FEAT_OPR(E_MACHINE, e_machine, false), + FEAT_OPR(CLN_SIZE, cln_size, false), }; struct header_print_data { @@ -3446,6 +4059,13 @@ struct header_print_data { bool full; /* extended list of headers */ }; +const char *header_feat__name(unsigned int id) +{ + if (id < HEADER_LAST_FEATURE) + return feat_ops[id].name ?: "INVALID"; + return "INVALID"; +} + static int perf_file_section__fprintf_info(struct perf_file_section *section, struct perf_header *ph, int feat, int fd, void *data) @@ -3454,11 +4074,11 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section, struct feat_fd ff; if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { - pr_debug("Failed to lseek to %" PRIu64 " offset for feature " - "%d, continuing...\n", section->offset, feat); + pr_debug("Failed to lseek to %" PRIu64 " offset for feature %s (%d), continuing...\n", + section->offset, header_feat__name(feat), feat); return 0; } - if (feat >= HEADER_LAST_FEATURE) { + if (feat >= ph->last_feat) { pr_warning("unknown feature %d\n", feat); return 0; } @@ -3510,7 +4130,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) return 0; fprintf(fp, "# missing features: "); - for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) { + for_each_clear_bit(bit, header->adds_features, header->last_feat) { if (bit) fprintf(fp, "%s ", feat_ops[bit].name); } @@ -3657,6 +4277,7 @@ static int perf_session__do_write_header(struct perf_session *session, struct perf_header *header = &session->header; struct evsel *evsel; struct feat_fd ff = { + .ph = header, .fd = fd, }; u64 attr_offset = sizeof(f_header), attr_size = 0; @@ -3839,7 +4460,7 @@ int perf_header__process_sections(struct perf_header *header, int fd, if (err < 0) goto out_free; - for_each_set_bit(feat, header->adds_features, HEADER_LAST_FEATURE) { + for_each_set_bit(feat, header->adds_features, header->last_feat) { err = process(sec++, header, feat, fd, data); if (err < 0) goto out_free; @@ -4054,6 +4675,7 @@ int perf_file_header__read(struct perf_file_header *header, ph->data_offset = header->data.offset; ph->data_size = header->data.size; ph->feat_offset = header->data.offset + header->data.size; + ph->last_feat = HEADER_LAST_FEATURE; return 0; } @@ -4069,8 +4691,8 @@ static int perf_file_section__process(struct perf_file_section *section, }; if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { - pr_debug("Failed to lseek to %" PRIu64 " offset for feature " - "%d, continuing...\n", section->offset, feat); + pr_debug("Failed to lseek to %" PRIu64 " offset for feature %s (%d), continuing...\n", + section->offset, header_feat__name(feat), feat); return 0; } @@ -4103,6 +4725,8 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, if (ph->needs_swap) header->size = bswap_64(header->size); + /* The last feature is written out as a 0 sized event and will update this value. */ + ph->last_feat = 0; return 0; } @@ -4225,7 +4849,7 @@ int perf_session__read_header(struct perf_session *session) if (session->evlist == NULL) return -ENOMEM; - session->evlist->env = &header->env; + session->evlist->session = session; session->machines.host.env = &header->env; /* @@ -4335,47 +4959,91 @@ out_delete_evlist: return -ENOMEM; } -int perf_event__process_feature(struct perf_session *session, +int perf_event__process_feature(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { - const struct perf_tool *tool = session->tool; struct feat_fd ff = { .fd = 0 }; struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; + struct perf_header *header = &session->header; int type = fe->header.type; - u64 feat = fe->feat_id; + int feat = (int)fe->feat_id; int ret = 0; + bool print = dump_trace; + bool last_feature_mark = false; if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { pr_warning("invalid record type %d in pipe-mode\n", type); return 0; } - if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) { - pr_warning("invalid record type %d in pipe-mode\n", type); + if (feat == HEADER_RESERVED) { + pr_warning("invalid reserved record type in pipe-mode\n"); return -1; } - - if (!feat_ops[feat].process) + if (feat < 0 || feat == INT_MAX) { + pr_warning("invalid value for feature type %x\n", feat); + return -1; + } + if (feat >= header->last_feat) { + if (event->header.size == sizeof(*fe)) { + /* + * Either an unexpected zero size feature or the + * HEADER_LAST_FEATURE mark. + */ + if (feat > header->last_feat) + header->last_feat = min(feat, HEADER_LAST_FEATURE); + last_feature_mark = true; + } else { + /* + * A feature but beyond what is known as in + * bounds. Assume the last feature is 1 beyond this + * feature. + */ + session->header.last_feat = min(feat + 1, HEADER_LAST_FEATURE); + } + } + if (feat >= HEADER_LAST_FEATURE) { + if (!last_feature_mark) { + pr_warning("unknown feature %d for data file version (%s) in this version of perf (%s)\n", + feat, header->env.version, perf_version_string); + } return 0; - + } + if (event->header.size < sizeof(*fe)) { + pr_warning("feature header size too small\n"); + return -1; + } ff.buf = (void *)fe->data; ff.size = event->header.size - sizeof(*fe); - ff.ph = &session->header; + ff.ph = header; - if (feat_ops[feat].process(&ff, NULL)) { - ret = -1; + if (feat_ops[feat].process && feat_ops[feat].process(&ff, NULL)) { + // Processing failed, ignore when this is the last feature mark. + if (!last_feature_mark) + ret = -1; goto out; } - if (!feat_ops[feat].print || !tool->show_feat_hdr) - goto out; + if (session->tool->show_feat_hdr) { + if (!feat_ops[feat].full_only || + session->tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { + print = true; + } else { + fprintf(stdout, "# %s info available, use -I to display\n", + feat_ops[feat].name); + } + } - if (!feat_ops[feat].full_only || - tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { - feat_ops[feat].print(&ff, stdout); - } else { - fprintf(stdout, "# %s info available, use -I to display\n", - feat_ops[feat].name); + if (dump_trace) + printf(", "); + + if (print) { + if (feat_ops[feat].print) + feat_ops[feat].print(&ff, stdout); + else + printf("# %s", feat_ops[feat].name); } + out: free_event_desc(ff.events); return ret; @@ -4417,6 +5085,11 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) return ret; } +size_t perf_event__fprintf_attr(union perf_event *event, FILE *fp) +{ + return perf_event_attr__fprintf(fp, &event->attr.attr, __desc_attr__fprintf, NULL); +} + int perf_event__process_attr(const struct perf_tool *tool __maybe_unused, union perf_event *event, struct evlist **pevlist) @@ -4426,6 +5099,9 @@ int perf_event__process_attr(const struct perf_tool *tool __maybe_unused, struct evsel *evsel; struct evlist *evlist = *pevlist; + if (dump_trace) + perf_event__fprintf_attr(event, stdout); + if (evlist == NULL) { *pevlist = evlist = evlist__new(); if (evlist == NULL) @@ -4492,8 +5168,8 @@ int perf_event__process_event_update(const struct perf_tool *tool __maybe_unused case PERF_EVENT_UPDATE__CPUS: map = cpu_map__new_data(&ev->cpus.cpus); if (map) { - perf_cpu_map__put(evsel->core.own_cpus); - evsel->core.own_cpus = map; + perf_cpu_map__put(evsel->core.pmu_cpus); + evsel->core.pmu_cpus = map; } else pr_err("failed to get event_update cpus\n"); default: @@ -4504,7 +5180,8 @@ int perf_event__process_event_update(const struct perf_tool *tool __maybe_unused } #ifdef HAVE_LIBTRACEEVENT -int perf_event__process_tracing_data(struct perf_session *session, +int perf_event__process_tracing_data(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { ssize_t size_read, padding, size = event->tracing_data.size; @@ -4552,7 +5229,8 @@ int perf_event__process_tracing_data(struct perf_session *session, } #endif -int perf_event__process_build_id(struct perf_session *session, +int perf_event__process_build_id(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { __event_process_build_id(&event->build_id, diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 5201af6305f4..86b1a72026d3 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -53,6 +53,9 @@ enum { HEADER_CLOCK_DATA, HEADER_HYBRID_TOPOLOGY, HEADER_PMU_CAPS, + HEADER_CPU_DOMAIN_INFO, + HEADER_E_MACHINE, + HEADER_CLN_SIZE, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -107,6 +110,7 @@ struct perf_header { u64 data_size; u64 feat_offset; DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); + int last_feat; struct perf_env env; }; @@ -130,6 +134,8 @@ struct perf_header_feature_ops { extern const char perf_version_string[]; +const char *header_feat__name(unsigned int id); + int perf_session__read_header(struct perf_session *session); int perf_session__write_header(struct perf_session *session, struct evlist *evlist, @@ -168,19 +174,23 @@ int perf_header__process_sections(struct perf_header *header, int fd, int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); -int perf_event__process_feature(struct perf_session *session, +int perf_event__process_feature(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); int perf_event__process_attr(const struct perf_tool *tool, union perf_event *event, struct evlist **pevlist); int perf_event__process_event_update(const struct perf_tool *tool, union perf_event *event, struct evlist **pevlist); +size_t perf_event__fprintf_attr(union perf_event *event, FILE *fp); size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp); #ifdef HAVE_LIBTRACEEVENT -int perf_event__process_tracing_data(struct perf_session *session, +int perf_event__process_tracing_data(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); #endif -int perf_event__process_build_id(struct perf_session *session, +int perf_event__process_build_id(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); bool is_perf_magic(u64 magic); @@ -197,6 +207,8 @@ int write_padded(struct feat_fd *fd, const void *bf, int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp); +#define DEFAULT_CACHELINE_SIZE 64 + /* * arch specific callback */ @@ -207,4 +219,7 @@ char *get_cpuid_str(struct perf_cpu cpu); char *get_cpuid_allow_env_override(struct perf_cpu cpu); int strcmp_cpuid_str(const char *s1, const char *s2); + +struct cpu_domain_map **build_cpu_domain_map(u32 *schedstat_version, u32 *max_sched_domains, + u32 nr); #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/hisi-ptt-decoder/Build b/tools/perf/util/hisi-ptt-decoder/Build index 3298f7b7e308..2ee0eb731656 100644 --- a/tools/perf/util/hisi-ptt-decoder/Build +++ b/tools/perf/util/hisi-ptt-decoder/Build @@ -1 +1 @@ -perf-util-$(CONFIG_AUXTRACE) += hisi-ptt-pkt-decoder.o +perf-util-y += hisi-ptt-pkt-decoder.o diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0f30f843c566..747fdc455c80 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -43,6 +43,8 @@ static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he); static bool hists__filter_entry_by_socket(struct hists *hists, struct hist_entry *he); +static bool hists__filter_entry_by_parallelism(struct hists *hists, + struct hist_entry *he); u16 hists__col_len(struct hists *hists, enum hist_column col) { @@ -108,6 +110,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) len = thread__comm_len(h->thread); if (hists__new_col_len(hists, HISTC_COMM, len)) hists__set_col_len(hists, HISTC_THREAD, len + 8); + if (hists->hpp_list->comm_nodigit) + hists__new_col_len(hists, HISTC_COMM_NODIGIT, + (u16) sort__comm_nodigit_len(h)); if (h->ms.map) { len = dso__name_len(map__dso(h->ms.map)); @@ -207,6 +212,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_CGROUP, 6); hists__new_col_len(hists, HISTC_CGROUP_ID, 20); + hists__new_col_len(hists, HISTC_PARALLELISM, 11); hists__new_col_len(hists, HISTC_CPU, 3); hists__new_col_len(hists, HISTC_SOCKET, 6); hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); @@ -248,7 +254,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->cgroup) { const char *cgrp_name = "unknown"; - struct cgroup *cgrp = cgroup__find(maps__machine(h->ms.maps)->env, + struct cgroup *cgrp = cgroup__find(maps__machine(thread__maps(h->ms.thread))->env, h->cgroup); if (cgrp != NULL) cgrp_name = cgrp->name; @@ -302,9 +308,10 @@ static long hist_time(unsigned long htime) return htime; } -static void he_stat__add_period(struct he_stat *he_stat, u64 period) +static void he_stat__add_period(struct he_stat *he_stat, u64 period, u64 latency) { he_stat->period += period; + he_stat->latency += latency; he_stat->nr_events += 1; } @@ -319,6 +326,7 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->weight2 += src->weight2; dest->weight3 += src->weight3; dest->nr_events += src->nr_events; + dest->latency += src->latency; } static void he_stat__decay(struct he_stat *he_stat) @@ -328,6 +336,70 @@ static void he_stat__decay(struct he_stat *he_stat) he_stat->weight1 = (he_stat->weight1 * 7) / 8; he_stat->weight2 = (he_stat->weight2 * 7) / 8; he_stat->weight3 = (he_stat->weight3 * 7) / 8; + he_stat->latency = (he_stat->latency * 7) / 8; +} + +static int hists__update_mem_stat(struct hists *hists, struct hist_entry *he, + struct mem_info *mi, u64 period) +{ + if (hists->nr_mem_stats == 0) + return 0; + + if (he->mem_stat == NULL) { + he->mem_stat = calloc(hists->nr_mem_stats, sizeof(*he->mem_stat)); + if (he->mem_stat == NULL) + return -1; + } + + for (int i = 0; i < hists->nr_mem_stats; i++) { + int idx = mem_stat_index(hists->mem_stat_types[i], + mem_info__const_data_src(mi)->val); + + assert(0 <= idx && idx < MEM_STAT_LEN); + he->mem_stat[i].entries[idx] += period; + hists->mem_stat_total[i].entries[idx] += period; + } + return 0; +} + +static void hists__add_mem_stat(struct hists *hists, struct hist_entry *dst, + struct hist_entry *src) +{ + if (hists->nr_mem_stats == 0) + return; + + for (int i = 0; i < hists->nr_mem_stats; i++) { + for (int k = 0; k < MEM_STAT_LEN; k++) + dst->mem_stat[i].entries[k] += src->mem_stat[i].entries[k]; + } +} + +static int hists__clone_mem_stat(struct hists *hists, struct hist_entry *dst, + struct hist_entry *src) +{ + if (hists->nr_mem_stats == 0) + return 0; + + dst->mem_stat = calloc(hists->nr_mem_stats, sizeof(*dst->mem_stat)); + if (dst->mem_stat == NULL) + return -1; + + for (int i = 0; i < hists->nr_mem_stats; i++) { + for (int k = 0; k < MEM_STAT_LEN; k++) + dst->mem_stat[i].entries[k] = src->mem_stat[i].entries[k]; + } + return 0; +} + +static void hists__decay_mem_stat(struct hists *hists, struct hist_entry *he) +{ + if (hists->nr_mem_stats == 0) + return; + + for (int i = 0; i < hists->nr_mem_stats; i++) { + for (int k = 0; k < MEM_STAT_LEN; k++) + he->mem_stat[i].entries[k] = (he->mem_stat[i].entries[k] * 7) / 8; + } } static void hists__delete_entry(struct hists *hists, struct hist_entry *he); @@ -335,7 +407,7 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he); static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) { u64 prev_period = he->stat.period; - u64 diff; + u64 prev_latency = he->stat.latency; if (prev_period == 0) return true; @@ -344,13 +416,18 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) if (symbol_conf.cumulate_callchain) he_stat__decay(he->stat_acc); decay_callchain(he->callchain); - - diff = prev_period - he->stat.period; + hists__decay_mem_stat(hists, he); if (!he->depth) { - hists->stats.total_period -= diff; - if (!he->filtered) - hists->stats.total_non_filtered_period -= diff; + u64 period_diff = prev_period - he->stat.period; + u64 latency_diff = prev_latency - he->stat.latency; + + hists->stats.total_period -= period_diff; + hists->stats.total_latency -= latency_diff; + if (!he->filtered) { + hists->stats.total_non_filtered_period -= period_diff; + hists->stats.total_non_filtered_latency -= latency_diff; + } } if (!he->leaf) { @@ -365,7 +442,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) } } - return he->stat.period == 0; + return he->stat.period == 0 && he->stat.latency == 0; } static void hists__delete_entry(struct hists *hists, struct hist_entry *he) @@ -462,7 +539,7 @@ static int hist_entry__init(struct hist_entry *he, memset(&he->stat, 0, sizeof(he->stat)); } - he->ms.maps = maps__get(he->ms.maps); + he->ms.thread = thread__get(he->ms.thread); he->ms.map = map__get(he->ms.map); if (he->branch_info) { @@ -478,9 +555,9 @@ static int hist_entry__init(struct hist_entry *he, memcpy(he->branch_info, template->branch_info, sizeof(*he->branch_info)); - he->branch_info->from.ms.maps = maps__get(he->branch_info->from.ms.maps); + he->branch_info->from.ms.thread = thread__get(he->branch_info->from.ms.thread); he->branch_info->from.ms.map = map__get(he->branch_info->from.ms.map); - he->branch_info->to.ms.maps = maps__get(he->branch_info->to.ms.maps); + he->branch_info->to.ms.thread = thread__get(he->branch_info->to.ms.thread); he->branch_info->to.ms.map = map__get(he->branch_info->to.ms.map); } @@ -534,10 +611,8 @@ err_infos: map_symbol__exit(&he->branch_info->to.ms); zfree(&he->branch_info); } - if (he->mem_info) { - map_symbol__exit(&mem_info__iaddr(he->mem_info)->ms); - map_symbol__exit(&mem_info__daddr(he->mem_info)->ms); - } + if (he->mem_info) + mem_info__zput(he->mem_info); err: map_symbol__exit(&he->ms); zfree(&he->stat_acc); @@ -584,21 +659,24 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, return he; } -static u8 symbol__parent_filter(const struct symbol *parent) +static filter_mask_t symbol__parent_filter(const struct symbol *parent) { if (symbol_conf.exclude_other && parent == NULL) return 1 << HIST_FILTER__PARENT; return 0; } -static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period) +static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period, u64 latency) { if (!hist_entry__has_callchains(he) || !symbol_conf.use_callchain) return; he->hists->callchain_period += period; - if (!he->filtered) + he->hists->callchain_latency += latency; + if (!he->filtered) { he->hists->callchain_non_filtered_period += period; + he->hists->callchain_non_filtered_latency += latency; + } } static struct hist_entry *hists__findnew_entry(struct hists *hists, @@ -611,6 +689,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, struct hist_entry *he; int64_t cmp; u64 period = entry->stat.period; + u64 latency = entry->stat.latency; bool leftmost = true; p = &hists->entries_in->rb_root.rb_node; @@ -629,10 +708,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (!cmp) { if (sample_self) { he_stat__add_stat(&he->stat, &entry->stat); - hist_entry__add_callchain_period(he, period); + hist_entry__add_callchain_period(he, period, latency); } if (symbol_conf.cumulate_callchain) - he_stat__add_period(he->stat_acc, period); + he_stat__add_period(he->stat_acc, period, latency); block_info__delete(entry->block_info); @@ -669,7 +748,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, return NULL; if (sample_self) - hist_entry__add_callchain_period(he, period); + hist_entry__add_callchain_period(he, period, latency); hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); @@ -679,6 +758,10 @@ out: he_stat__add_cpumode_period(&he->stat, al->cpumode, period); if (symbol_conf.cumulate_callchain) he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period); + if (hists__update_mem_stat(hists, he, entry->mem_info, period) < 0) { + hist_entry__delete(he); + return NULL; + } return he; } @@ -730,7 +813,7 @@ __hists__add_entry(struct hists *hists, }, .cgroup = sample->cgroup, .ms = { - .maps = al->maps, + .thread = al->thread, .map = al->map, .sym = al->sym, }, @@ -741,12 +824,14 @@ __hists__add_entry(struct hists *hists, .ip = al->addr, .level = al->level, .code_page_size = sample->code_page_size, + .parallelism = al->parallelism, .stat = { .nr_events = 1, .period = sample->period, .weight1 = sample->weight, .weight2 = sample->ins_lat, - .weight3 = sample->p_stage_cyc, + .weight3 = sample->weight3, + .latency = al->latency, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent) | al->filtered, @@ -762,7 +847,7 @@ __hists__add_entry(struct hists *hists, .time = hist_time(sample->time), .weight = sample->weight, .ins_lat = sample->ins_lat, - .p_stage_cyc = sample->p_stage_cyc, + .weight3 = sample->weight3, .simd_flags = sample->simd_flags, }, *he = hists__findnew_entry(hists, &entry, al, sample_self); @@ -808,7 +893,7 @@ struct hist_entry *hists__add_entry_block(struct hists *hists, .block_info = block_info, .hists = hists, .ms = { - .maps = al->maps, + .thread = al->thread, .map = al->map, .sym = al->sym, }, @@ -938,8 +1023,8 @@ iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al) if (iter->curr >= iter->total) return 0; - maps__put(al->maps); - al->maps = maps__get(bi[i].to.ms.maps); + thread__put(al->thread); + al->thread = thread__get(bi[i].to.ms.thread); map__put(al->map); al->map = map__get(bi[i].to.ms.map); al->sym = bi[i].to.ms.sym; @@ -975,8 +1060,6 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a if (he == NULL) return -ENOMEM; - hists__inc_nr_samples(hists, he->filtered); - out: iter->he = he; iter->curr++; @@ -995,9 +1078,15 @@ static int iter_finish_branch_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { + struct evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); + for (int i = 0; i < iter->total; i++) branch_info__exit(&iter->bi[i]); + if (iter->he) + hists__inc_nr_samples(hists, iter->he->filtered); + zfree(&iter->bi); iter->he = NULL; @@ -1062,7 +1151,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter, * cumulated only one time to prevent entries more than 100% * overhead. */ - he_cache = malloc(sizeof(*he_cache) * (cursor->nr + 1)); + he_cache = calloc(cursor->nr + 1, sizeof(*he_cache)); if (he_cache == NULL) return -ENOMEM; @@ -1146,7 +1235,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .comm = thread__comm(al->thread), .ip = al->addr, .ms = { - .maps = al->maps, + .thread = al->thread, .map = al->map, .sym = al->sym, }, @@ -1365,6 +1454,16 @@ void hist_entry__delete(struct hist_entry *he) { struct hist_entry_ops *ops = he->ops; + if (symbol_conf.report_hierarchy) { + struct rb_root *root = &he->hroot_out.rb_root; + struct hist_entry *child, *tmp; + + rbtree_postorder_for_each_entry_safe(child, tmp, root, rb_node) + hist_entry__delete(child); + + *root = RB_ROOT; + } + thread__zput(he->thread); map_symbol__exit(&he->ms); @@ -1393,6 +1492,7 @@ void hist_entry__delete(struct hist_entry *he) free_callchain(he->callchain); zfree(&he->trace_output); zfree(&he->raw_data); + zfree(&he->mem_stat); ops->free(he); } @@ -1455,6 +1555,10 @@ static void hist_entry__check_and_remove_filter(struct hist_entry *he, if (symbol_conf.sym_list == NULL) return; break; + case HIST_FILTER__PARALLELISM: + if (__bitmap_weight(symbol_conf.parallelism_filter, MAX_NR_CPUS + 1) == 0) + return; + break; case HIST_FILTER__PARENT: case HIST_FILTER__GUEST: case HIST_FILTER__HOST: @@ -1513,6 +1617,9 @@ static void hist_entry__apply_hierarchy_filters(struct hist_entry *he) hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL, perf_hpp__is_sym_entry); + hist_entry__check_and_remove_filter(he, HIST_FILTER__PARALLELISM, + perf_hpp__is_parallelism_entry); + hists__apply_filters(he->hists, he); } @@ -1535,6 +1642,7 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists, cmp = hist_entry__collapse_hierarchy(hpp_list, iter, he); if (!cmp) { he_stat__add_stat(&iter->stat, &he->stat); + hists__add_mem_stat(hists, iter, he); return iter; } @@ -1576,6 +1684,11 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists, new->srcfile = NULL; } + if (hists__clone_mem_stat(hists, new, he) < 0) { + hist_entry__delete(new); + return NULL; + } + rb_link_node(&new->rb_node_in, parent, p); rb_insert_color_cached(&new->rb_node_in, root, leftmost); return new; @@ -1658,6 +1771,7 @@ static int hists__collapse_insert_entry(struct hists *hists, he_stat__add_stat(&iter->stat, &he->stat); if (symbol_conf.cumulate_callchain) he_stat__add_stat(iter->stat_acc, he->stat_acc); + hists__add_mem_stat(hists, iter, he); if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) { struct callchain_cursor *cursor = get_tls_callchain_cursor(); @@ -1709,6 +1823,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he) hists__filter_entry_by_thread(hists, he); hists__filter_entry_by_symbol(hists, he); hists__filter_entry_by_socket(hists, he); + hists__filter_entry_by_parallelism(hists, he); } int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) @@ -1756,12 +1871,14 @@ static void hists__reset_filter_stats(struct hists *hists) { hists->nr_non_filtered_entries = 0; hists->stats.total_non_filtered_period = 0; + hists->stats.total_non_filtered_latency = 0; } void hists__reset_stats(struct hists *hists) { hists->nr_entries = 0; hists->stats.total_period = 0; + hists->stats.total_latency = 0; hists__reset_filter_stats(hists); } @@ -1770,6 +1887,7 @@ static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h) { hists->nr_non_filtered_entries++; hists->stats.total_non_filtered_period += h->stat.period; + hists->stats.total_non_filtered_latency += h->stat.latency; } void hists__inc_stats(struct hists *hists, struct hist_entry *h) @@ -1779,6 +1897,7 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h) hists->nr_entries++; hists->stats.total_period += h->stat.period; + hists->stats.total_latency += h->stat.latency; } static void hierarchy_recalc_total_periods(struct hists *hists) @@ -1790,6 +1909,8 @@ static void hierarchy_recalc_total_periods(struct hists *hists) hists->stats.total_period = 0; hists->stats.total_non_filtered_period = 0; + hists->stats.total_latency = 0; + hists->stats.total_non_filtered_latency = 0; /* * recalculate total period using top-level entries only @@ -1801,8 +1922,11 @@ static void hierarchy_recalc_total_periods(struct hists *hists) node = rb_next(node); hists->stats.total_period += he->stat.period; - if (!he->filtered) + hists->stats.total_latency += he->stat.latency; + if (!he->filtered) { hists->stats.total_non_filtered_period += he->stat.period; + hists->stats.total_non_filtered_latency += he->stat.latency; + } } } @@ -2195,6 +2319,16 @@ static bool hists__filter_entry_by_socket(struct hists *hists, return false; } +static bool hists__filter_entry_by_parallelism(struct hists *hists, + struct hist_entry *he) +{ + if (test_bit(he->parallelism, hists->parallelism_filter)) { + he->filtered |= (1 << HIST_FILTER__PARALLELISM); + return true; + } + return false; +} + typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he); static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter) @@ -2364,6 +2498,16 @@ void hists__filter_by_socket(struct hists *hists) hists__filter_entry_by_socket); } +void hists__filter_by_parallelism(struct hists *hists) +{ + if (symbol_conf.report_hierarchy) + hists__filter_hierarchy(hists, HIST_FILTER__PARALLELISM, + hists->parallelism_filter); + else + hists__filter_by_type(hists, HIST_FILTER__PARALLELISM, + hists__filter_entry_by_parallelism); +} + void events_stats__inc(struct events_stats *stats, u32 type) { ++stats->nr_events[0]; @@ -2759,6 +2903,12 @@ u64 hists__total_period(struct hists *hists) hists->stats.total_period; } +u64 hists__total_latency(struct hists *hists) +{ + return symbol_conf.filter_relative ? hists->stats.total_non_filtered_latency : + hists->stats.total_latency; +} + int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq) { char unit; @@ -2870,6 +3020,7 @@ int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list) hists->entries = RB_ROOT_CACHED; mutex_init(&hists->lock); hists->socket_filter = -1; + hists->parallelism_filter = symbol_conf.parallelism_filter; hists->hpp_list = hpp_list; INIT_LIST_HEAD(&hists->hpp_formats); return 0; @@ -2904,6 +3055,8 @@ static void hists_evsel__exit(struct evsel *evsel) struct perf_hpp_list_node *node, *tmp; hists__delete_all_entries(hists); + zfree(&hists->mem_stat_types); + zfree(&hists->mem_stat_total); list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) { perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 46c8373e3146..d97a4efb9250 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -9,6 +9,7 @@ #include "events_stats.h" #include "evsel.h" #include "map_symbol.h" +#include "mem-events.h" #include "mutex.h" #include "sample.h" #include "spark.h" @@ -31,17 +32,23 @@ enum hist_filter { HIST_FILTER__HOST, HIST_FILTER__SOCKET, HIST_FILTER__C2C, + HIST_FILTER__PARALLELISM, }; +typedef u16 filter_mask_t; + enum hist_column { HISTC_SYMBOL, HISTC_TIME, HISTC_DSO, HISTC_THREAD, + HISTC_TGID, HISTC_COMM, + HISTC_COMM_NODIGIT, HISTC_CGROUP_ID, HISTC_CGROUP, HISTC_PARENT, + HISTC_PARALLELISM, HISTC_CPU, HISTC_SOCKET, HISTC_SRCLINE, @@ -96,6 +103,13 @@ enum hist_column { struct thread; struct dso; +#define MEM_STAT_LEN 8 + +struct he_mem_stat { + /* meaning of entries depends on enum mem_stat_type */ + u64 entries[MEM_STAT_LEN]; +}; + struct hists { struct rb_root_cached entries_in_array[2]; struct rb_root_cached *entries_in; @@ -105,10 +119,13 @@ struct hists { u64 nr_non_filtered_entries; u64 callchain_period; u64 callchain_non_filtered_period; + u64 callchain_latency; + u64 callchain_non_filtered_latency; struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; const char *symbol_filter_str; + unsigned long *parallelism_filter; struct mutex lock; struct hists_stats stats; u64 event_stream; @@ -118,6 +135,9 @@ struct hists { struct perf_hpp_list *hpp_list; struct list_head hpp_formats; int nr_hpp_node; + int nr_mem_stats; + enum mem_stat_type *mem_stat_types; + struct he_mem_stat *mem_stat_total; }; #define hists__has(__h, __f) (__h)->hpp_list->__f @@ -165,6 +185,12 @@ struct res_sample { struct he_stat { u64 period; + /* + * Period re-scaled from CPU time to wall-clock time (divided by the + * parallelism at the time of the sample). This represents effect of + * the event on latency rather than CPU consumption. + */ + u64 latency; u64 period_sys; u64 period_us; u64 period_guest_sys; @@ -219,6 +245,7 @@ struct hist_entry { } pairs; struct he_stat stat; struct he_stat *stat_acc; + struct he_mem_stat *mem_stat; struct map_symbol ms; struct thread *thread; struct comm *comm; @@ -226,15 +253,17 @@ struct hist_entry { u64 cgroup; u64 ip; u64 transaction; - s32 socket; - s32 cpu; u64 code_page_size; u64 weight; u64 ins_lat; - u64 p_stage_cyc; + /** @weight3: On x86 holds retire_lat, on powerpc holds p_stage_cyc. */ + u64 weight3; + s32 socket; + s32 cpu; + int parallelism; + int mem_type_off; u8 cpumode; u8 depth; - int mem_type_off; struct simd_flags simd_flags; /* We are added by hists__add_dummy_entry. */ @@ -242,7 +271,7 @@ struct hist_entry { bool leaf; char level; - u8 filtered; + filter_mask_t filtered; u16 callchain_size; union { @@ -368,6 +397,7 @@ void hists__output_recalc_col_len(struct hists *hists, int max_rows); struct hist_entry *hists__get_entry(struct hists *hists, int idx); u64 hists__total_period(struct hists *hists); +u64 hists__total_latency(struct hists *hists); void hists__reset_stats(struct hists *hists); void hists__inc_stats(struct hists *hists, struct hist_entry *h); void hists__inc_nr_events(struct hists *hists); @@ -384,11 +414,13 @@ void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); void hists__filter_by_symbol(struct hists *hists); void hists__filter_by_socket(struct hists *hists); +void hists__filter_by_parallelism(struct hists *hists); static inline bool hists__has_filter(struct hists *hists) { return hists->thread_filter || hists->dso_filter || - hists->symbol_filter_str || (hists->socket_filter > -1); + hists->symbol_filter_str || (hists->socket_filter > -1) || + hists->parallelism_filter; } u16 hists__col_len(struct hists *hists, enum hist_column col); @@ -491,6 +523,7 @@ struct perf_hpp_list { int socket; int thread; int comm; + int comm_nodigit; }; extern struct perf_hpp_list perf_hpp_list; @@ -547,27 +580,37 @@ extern struct perf_hpp_fmt perf_hpp__format[]; enum { /* Matches perf_hpp__format array. */ PERF_HPP__OVERHEAD, + PERF_HPP__LATENCY, PERF_HPP__OVERHEAD_SYS, PERF_HPP__OVERHEAD_US, PERF_HPP__OVERHEAD_GUEST_SYS, PERF_HPP__OVERHEAD_GUEST_US, PERF_HPP__OVERHEAD_ACC, + PERF_HPP__LATENCY_ACC, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, PERF_HPP__WEIGHT1, PERF_HPP__WEIGHT2, PERF_HPP__WEIGHT3, + PERF_HPP__MEM_STAT_OP, + PERF_HPP__MEM_STAT_CACHE, + PERF_HPP__MEM_STAT_MEMORY, + PERF_HPP__MEM_STAT_SNOOP, + PERF_HPP__MEM_STAT_DTLB, PERF_HPP__MAX_INDEX }; void perf_hpp__init(void); -void perf_hpp__cancel_cumulate(void); +void perf_hpp__cancel_cumulate(struct evlist *evlist); +void perf_hpp__cancel_latency(struct evlist *evlist); void perf_hpp__setup_output_field(struct perf_hpp_list *list); void perf_hpp__reset_output_field(struct perf_hpp_list *list); void perf_hpp__append_sort_keys(struct perf_hpp_list *list); int perf_hpp__setup_hists_formats(struct perf_hpp_list *list, struct evlist *evlist); +int perf_hpp__alloc_mem_stats(struct perf_hpp_list *list, + struct evlist *evlist); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); @@ -580,6 +623,7 @@ bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_parallelism_entry(struct perf_hpp_fmt *fmt); struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt); @@ -606,6 +650,7 @@ void hists__reset_column_width(struct hists *hists); enum perf_hpp_fmt_type { PERF_HPP_FMT_TYPE__RAW, PERF_HPP_FMT_TYPE__PERCENT, + PERF_HPP_FMT_TYPE__LATENCY, PERF_HPP_FMT_TYPE__AVERAGE, }; @@ -621,6 +666,9 @@ int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he, hpp_field_fn get_field, const char *fmtstr, hpp_snprint_fn print_fn, enum perf_hpp_fmt_type fmtype); +int hpp__fmt_mem_stat(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he, enum mem_stat_type mst, + const char *fmtstr, hpp_snprint_fn print_fn); static inline void advance_hpp(struct perf_hpp *hpp, int inc) { @@ -663,15 +711,18 @@ struct block_hist { struct hist_entry he; }; +#define NO_ADDR 0 + #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" void attr_to_script(char *buf, struct perf_event_attr *attr); -int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, - struct hist_browser_timer *hbt); +int __hist_entry__tui_annotate(struct hist_entry *he, struct map_symbol *ms, + struct evsel *evsel, + struct hist_browser_timer *hbt, u64 al_addr); int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, - struct hist_browser_timer *hbt); + struct hist_browser_timer *hbt, u64 al_addr); int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, bool warn_lost_event); @@ -696,16 +747,19 @@ int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, { return 0; } -static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, - struct evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) +static inline int __hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, + struct map_symbol *ms __maybe_unused, + struct evsel *evsel __maybe_unused, + struct hist_browser_timer *hbt __maybe_unused, + u64 al_addr __maybe_unused) { return 0; } static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, struct evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + u64 al_addr __maybe_unused) { return 0; } diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c index 4acb9bb19b84..fb3ffa8d32ad 100644 --- a/tools/perf/util/hwmon_pmu.c +++ b/tools/perf/util/hwmon_pmu.c @@ -11,13 +11,13 @@ #include <sys/types.h> #include <assert.h> #include <ctype.h> -#include <dirent.h> #include <fcntl.h> #include <stddef.h> #include <stdlib.h> #include <string.h> #include <api/fs/fs.h> #include <api/io.h> +#include <api/io_dir.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/zalloc.h> @@ -104,21 +104,7 @@ static const char *const hwmon_units[HWMON_TYPE_MAX] = { struct hwmon_pmu { struct perf_pmu pmu; struct hashmap events; - int hwmon_dir_fd; -}; - -/** - * union hwmon_pmu_event_key: Key for hwmon_pmu->events as such each key - * represents an event. - * - * Related hwmon files start <type><number> that this key represents. - */ -union hwmon_pmu_event_key { - long type_and_num; - struct { - int num :16; - enum hwmon_type type :8; - }; + char *hwmon_dir; }; /** @@ -175,7 +161,7 @@ bool parse_hwmon_filename(const char *filename, bool *alarm) { char fn_type[24]; - const char **elem; + const char * const *elem; const char *fn_item = NULL; size_t fn_item_len; @@ -249,31 +235,22 @@ static void fix_name(char *p) static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) { - DIR *dir; - struct dirent *ent; - int dup_fd, err = 0; + int err = 0; struct hashmap_entry *cur, *tmp; size_t bkt; + struct io_dirent64 *ent; + struct io_dir dir; if (pmu->pmu.sysfs_aliases_loaded) return 0; - /* - * Use a dup-ed fd as closedir will close it. Use openat so that the - * directory contents are refreshed. - */ - dup_fd = openat(pmu->hwmon_dir_fd, ".", O_DIRECTORY); - - if (dup_fd == -1) - return -ENOMEM; + /* Use openat so that the directory contents are refreshed. */ + io_dir__init(&dir, open(pmu->hwmon_dir, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); - dir = fdopendir(dup_fd); - if (!dir) { - close(dup_fd); - return -ENOMEM; - } + if (dir.dirfd < 0) + return -ENOENT; - while ((ent = readdir(dir)) != NULL) { + while ((ent = io_dir__readdir(&dir)) != NULL) { enum hwmon_type type; int number; enum hwmon_item item; @@ -306,7 +283,7 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) __set_bit(item, alarm ? value->alarm_items : value->items); if (item == HWMON_ITEM_LABEL) { char buf[128]; - int fd = openat(pmu->hwmon_dir_fd, ent->d_name, O_RDONLY); + int fd = openat(dir.dirfd, ent->d_name, O_RDONLY); ssize_t read_len; if (fd < 0) @@ -361,50 +338,56 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) pmu->pmu.sysfs_aliases_loaded = true; err_out: - closedir(dir); + close(dir.dirfd); return err; } -struct perf_pmu *hwmon_pmu__new(struct list_head *pmus, int hwmon_dir, const char *sysfs_name, const char *name) +struct perf_pmu *hwmon_pmu__new(struct list_head *pmus, const char *hwmon_dir, + const char *sysfs_name, const char *name) { - char buf[32]; + char buf[64]; struct hwmon_pmu *hwm; + __u32 type = PERF_PMU_TYPE_HWMON_START + strtoul(sysfs_name + 5, NULL, 10); + + if (type > PERF_PMU_TYPE_HWMON_END) { + pr_err("Unable to encode hwmon type from %s in valid PMU type\n", sysfs_name); + return NULL; + } + + snprintf(buf, sizeof(buf), "hwmon_%s", name); + fix_name(buf + 6); hwm = zalloc(sizeof(*hwm)); if (!hwm) return NULL; - hwm->hwmon_dir_fd = hwmon_dir; - hwm->pmu.type = PERF_PMU_TYPE_HWMON_START + strtoul(sysfs_name + 5, NULL, 10); - if (hwm->pmu.type > PERF_PMU_TYPE_HWMON_END) { - pr_err("Unable to encode hwmon type from %s in valid PMU type\n", sysfs_name); - goto err_out; + if (perf_pmu__init(&hwm->pmu, type, buf) != 0) { + perf_pmu__delete(&hwm->pmu); + return NULL; + } + + hwm->hwmon_dir = strdup(hwmon_dir); + if (!hwm->hwmon_dir) { + perf_pmu__delete(&hwm->pmu); + return NULL; } - snprintf(buf, sizeof(buf), "hwmon_%s", name); - fix_name(buf + 6); - hwm->pmu.name = strdup(buf); - if (!hwm->pmu.name) - goto err_out; hwm->pmu.alias_name = strdup(sysfs_name); - if (!hwm->pmu.alias_name) - goto err_out; - hwm->pmu.cpus = perf_cpu_map__new("0"); - if (!hwm->pmu.cpus) - goto err_out; + if (!hwm->pmu.alias_name) { + perf_pmu__delete(&hwm->pmu); + return NULL; + } + hwm->pmu.cpus = perf_cpu_map__new_int(0); + if (!hwm->pmu.cpus) { + perf_pmu__delete(&hwm->pmu); + return NULL; + } INIT_LIST_HEAD(&hwm->pmu.format); - INIT_LIST_HEAD(&hwm->pmu.aliases); INIT_LIST_HEAD(&hwm->pmu.caps); hashmap__init(&hwm->events, hwmon_pmu__event_hashmap_hash, hwmon_pmu__event_hashmap_equal, /*ctx=*/NULL); list_add_tail(&hwm->pmu.list, pmus); return &hwm->pmu; -err_out: - free((char *)hwm->pmu.name); - free(hwm->pmu.alias_name); - free(hwm); - close(hwmon_dir); - return NULL; } void hwmon_pmu__exit(struct perf_pmu *pmu) @@ -421,7 +404,7 @@ void hwmon_pmu__exit(struct perf_pmu *pmu) free(value); } hashmap__clear(&hwm->events); - close(hwm->hwmon_dir_fd); + zfree(&hwm->hwmon_dir); } static size_t hwmon_pmu__describe_items(struct hwmon_pmu *hwm, char *out_buf, size_t out_buf_len, @@ -431,6 +414,10 @@ static size_t hwmon_pmu__describe_items(struct hwmon_pmu *hwm, char *out_buf, si size_t bit; char buf[64]; size_t len = 0; + int dir = open(hwm->hwmon_dir, O_CLOEXEC | O_DIRECTORY | O_RDONLY); + + if (dir < 0) + return 0; for_each_set_bit(bit, items, HWMON_ITEM__MAX) { int fd; @@ -443,7 +430,7 @@ static size_t hwmon_pmu__describe_items(struct hwmon_pmu *hwm, char *out_buf, si key.num, hwmon_item_strs[bit], is_alarm ? "_alarm" : ""); - fd = openat(hwm->hwmon_dir_fd, buf, O_RDONLY); + fd = openat(dir, buf, O_RDONLY); if (fd > 0) { ssize_t read_len = read(fd, buf, sizeof(buf)); @@ -465,6 +452,7 @@ static size_t hwmon_pmu__describe_items(struct hwmon_pmu *hwm, char *out_buf, si close(fd); } } + close(dir); return len; } @@ -716,8 +704,8 @@ int hwmon_pmu__check_alias(struct parse_events_terms *terms, struct perf_pmu_inf int perf_pmus__read_hwmon_pmus(struct list_head *pmus) { char *line = NULL; - DIR *class_hwmon_dir; - struct dirent *class_hwmon_ent; + struct io_dirent64 *class_hwmon_ent; + struct io_dir class_hwmon_dir; char buf[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -725,14 +713,16 @@ int perf_pmus__read_hwmon_pmus(struct list_head *pmus) return 0; scnprintf(buf, sizeof(buf), "%s/class/hwmon/", sysfs); - class_hwmon_dir = opendir(buf); - if (!class_hwmon_dir) + io_dir__init(&class_hwmon_dir, open(buf, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + + if (class_hwmon_dir.dirfd < 0) return 0; - while ((class_hwmon_ent = readdir(class_hwmon_dir)) != NULL) { + while ((class_hwmon_ent = io_dir__readdir(&class_hwmon_dir)) != NULL) { size_t line_len; int hwmon_dir, name_fd; struct io io; + char buf2[128]; if (class_hwmon_ent->d_type != DT_LNK) continue; @@ -751,15 +741,15 @@ int perf_pmus__read_hwmon_pmus(struct list_head *pmus) close(hwmon_dir); continue; } - io__init(&io, name_fd, buf, sizeof(buf)); - io__getline(&io, &line, &line_len); - if (line_len > 0 && line[line_len - 1] == '\n') + io__init(&io, name_fd, buf2, sizeof(buf2)); + if (io__getline(&io, &line, &line_len) > 0 && line[line_len - 1] == '\n') line[line_len - 1] = '\0'; - hwmon_pmu__new(pmus, hwmon_dir, class_hwmon_ent->d_name, line); + hwmon_pmu__new(pmus, buf, class_hwmon_ent->d_name, line); close(name_fd); + close(hwmon_dir); } free(line); - closedir(class_hwmon_dir); + close(class_hwmon_dir.dirfd); return 0; } @@ -774,6 +764,10 @@ int evsel__hwmon_pmu_open(struct evsel *evsel, .type_and_num = evsel->core.attr.config, }; int idx = 0, thread = 0, nthreads, err = 0; + int dir = open(hwm->hwmon_dir, O_CLOEXEC | O_DIRECTORY | O_RDONLY); + + if (dir < 0) + return -errno; nthreads = perf_thread_map__nr(threads); for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { @@ -784,7 +778,7 @@ int evsel__hwmon_pmu_open(struct evsel *evsel, snprintf(buf, sizeof(buf), "%s%d_input", hwmon_type_strs[key.type], key.num); - fd = openat(hwm->hwmon_dir_fd, buf, O_RDONLY); + fd = openat(dir, buf, O_RDONLY); FD(evsel, idx, thread) = fd; if (fd < 0) { err = -errno; @@ -792,6 +786,7 @@ int evsel__hwmon_pmu_open(struct evsel *evsel, } } } + close(dir); return 0; out_close: if (err) @@ -805,6 +800,7 @@ out_close: } thread = nthreads; } while (--idx >= 0); + close(dir); return err; } diff --git a/tools/perf/util/hwmon_pmu.h b/tools/perf/util/hwmon_pmu.h index 882566846df4..d1e403c8b70b 100644 --- a/tools/perf/util/hwmon_pmu.h +++ b/tools/perf/util/hwmon_pmu.h @@ -37,7 +37,7 @@ enum hwmon_type { /** * enum hwmon_item: * - * Similar to enum hwmon_type but describes the item part of a a sysfs filename. + * Similar to enum hwmon_type but describes the item part of a sysfs filename. * * This enum is exposed for testing. */ @@ -91,6 +91,22 @@ enum hwmon_item { HWMON_ITEM__MAX, }; +/** + * union hwmon_pmu_event_key: Key for hwmon_pmu->events as such each key + * represents an event. + * union is exposed for testing to ensure problems are avoided on big + * endian machines. + * + * Related hwmon files start <type><number> that this key represents. + */ +union hwmon_pmu_event_key { + long type_and_num; + struct { + int num :16; + enum hwmon_type type :8; + }; +}; + bool perf_pmu__is_hwmon(const struct perf_pmu *pmu); bool evsel__is_hwmon(const struct evsel *evsel); @@ -119,14 +135,14 @@ bool parse_hwmon_filename(const char *filename, * hwmon_pmu__new() - Allocate and construct a hwmon PMU. * * @pmus: The list of PMUs to be added to. - * @hwmon_dir: An O_DIRECTORY file descriptor for a hwmon directory. + * @hwmon_dir: The path to a hwmon directory. * @sysfs_name: Name of the hwmon sysfs directory like hwmon0. * @name: The contents of the "name" file in the hwmon directory. * * Exposed for testing. Regular construction should happen via * perf_pmus__read_hwmon_pmus. */ -struct perf_pmu *hwmon_pmu__new(struct list_head *pmus, int hwmon_dir, +struct perf_pmu *hwmon_pmu__new(struct list_head *pmus, const char *hwmon_dir, const char *sysfs_name, const char *name); void hwmon_pmu__exit(struct perf_pmu *pmu); diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h index 6f1b9f6b2466..46a764cf322f 100644 --- a/tools/perf/util/include/dwarf-regs.h +++ b/tools/perf/util/include/dwarf-regs.h @@ -89,8 +89,6 @@ #define DWARF_REG_FB 0xd3affb /* random number */ #ifdef HAVE_LIBDW_SUPPORT -const char *get_csky_regstr(unsigned int n, unsigned int flags); - /** * get_dwarf_regstr() - Returns ftrace register string from DWARF regnum. * @n: DWARF register number. @@ -99,11 +97,23 @@ const char *get_csky_regstr(unsigned int n, unsigned int flags); */ const char *get_dwarf_regstr(unsigned int n, unsigned int machine, unsigned int flags); -int get_x86_regnum(const char *name); +const char *__get_csky_regstr(unsigned int n, unsigned int flags); +int __get_csky_regnum(const char *name, unsigned int flags); -#if !defined(__x86_64__) && !defined(__i386__) -int get_arch_regnum(const char *name); -#endif +int __get_dwarf_regnum_i386(const char *name); +int __get_dwarf_regnum_x86_64(const char *name); +int __get_dwarf_regnum_for_perf_regnum_i386(int perf_regnum); +int __get_dwarf_regnum_for_perf_regnum_x86_64(int perf_regnum); + +int __get_dwarf_regnum_for_perf_regnum_arm(int perf_regnum); +int __get_dwarf_regnum_for_perf_regnum_arm64(int perf_regnum); + +int __get_dwarf_regnum_for_perf_regnum_csky(int perf_regnum, unsigned int flags); +int __get_dwarf_regnum_for_perf_regnum_loongarch(int perf_regnum); +int __get_dwarf_regnum_for_perf_regnum_powerpc(int perf_regnum); +int __get_dwarf_regnum_for_perf_regnum_riscv(int perf_regnum); +int __get_dwarf_regnum_for_perf_regnum_s390(int perf_regnum); +int __get_dwarf_regnum_for_perf_regnum_mips(int perf_regnum); /* * get_dwarf_regnum - Returns DWARF regnum from register name @@ -112,6 +122,12 @@ int get_arch_regnum(const char *name); */ int get_dwarf_regnum(const char *name, unsigned int machine, unsigned int flags); +/* + * get_dwarf_regnum - Returns DWARF regnum from perf register number. + */ +int get_dwarf_regnum_for_perf_regnum(int perf_regnum, unsigned int machine, unsigned int flags, + bool only_libdw_supported); + void get_powerpc_regs(u32 raw_insn, int is_source, struct annotated_op_loc *op_loc); #else /* HAVE_LIBDW_SUPPORT */ diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index 178b00205fe6..34e2fdfe7300 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -120,7 +120,7 @@ #endif // In the kernel sources (include/linux/cfi_types.h), this has a different -// definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang +// definition when CONFIG_CFI is used, for tools/ just use the !cfi // definition: #ifndef SYM_TYPED_START #define SYM_TYPED_START(name, linkage, align...) \ @@ -132,4 +132,8 @@ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #endif +#ifndef SYM_PIC_ALIAS +#define SYM_PIC_ALIAS(sym) SYM_ALIAS(__pi_ ## sym, sym, SYM_T_FUNC, SYM_L_GLOBAL) +#endif + #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index a7c589fecb98..382255393fb3 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -275,12 +275,13 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, int ret; struct intel_bts *bts = btsq->bts; union perf_event event; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; if (bts->synth_opts.initial_skip && bts->num_events++ <= bts->synth_opts.initial_skip) return 0; + perf_sample__init(&sample, /*all=*/true); sample.ip = le64_to_cpu(branch->from); sample.cpumode = intel_bts_cpumode(bts, sample.ip); sample.pid = btsq->pid; @@ -312,6 +313,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, pr_err("Intel BTS: failed to deliver branch event, error %d\n", ret); + perf_sample__exit(&sample); return ret; } @@ -775,9 +777,7 @@ static int intel_bts_synth_events(struct intel_bts *bts, attr.sample_id_all = evsel->core.attr.sample_id_all; attr.read_format = evsel->core.attr.read_format; - id = evsel->core.id[0] + 1000000000; - if (!id) - id = 1; + id = auxtrace_synth_id_range_start(evsel); if (bts->synth_opts.branches) { attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 5b8f0149167d..8fd7e4330044 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -1,4 +1,4 @@ -perf-util-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o +perf-util-y += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o inat_tables_script = $(srctree)/tools/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/tools/arch/x86/lib/x86-opcode-map.txt @@ -7,11 +7,7 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table $(call rule_mkdir) @$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@ -ifeq ($(SRCARCH),x86) - perf-util-y += inat.o insn.o -else - perf-util-$(CONFIG_AUXTRACE) += inat.o insn.o -endif +perf-util-y += inat.o insn.o $(OUTPUT)util/intel-pt-decoder/inat.o: $(srctree)/tools/arch/x86/lib/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(call rule_mkdir) 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 8fabddc1c0da..72c7a4e15d61 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 @@ -32,7 +32,7 @@ static void intel_pt_insn_decoder(struct insn *insn, intel_pt_insn->rel = 0; intel_pt_insn->emulated_ptwrite = false; - if (insn_is_avx(insn)) { + if (insn_is_avx_or_xop(insn)) { intel_pt_insn->op = INTEL_PT_OP_OTHER; intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH; intel_pt_insn->length = insn->length; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 30be6dfe09eb..fc9eec8b54b8 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -127,6 +127,7 @@ struct intel_pt { bool single_pebs; bool sample_pebs; + int pebs_data_src_fmt; struct evsel *pebs_evsel; u64 evt_sample_type; @@ -175,6 +176,7 @@ enum switch_state { struct intel_pt_pebs_event { struct evsel *evsel; u64 id; + int data_src_fmt; }; struct intel_pt_queue { @@ -1764,12 +1766,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct dummy_branch_stack { u64 nr; u64 hw_idx; struct branch_entry entries; } dummy_bs; + int ret; if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; @@ -1777,6 +1780,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_b_sample(pt, ptq, event, &sample); sample.id = ptq->pt->branches_id; @@ -1806,8 +1810,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt; } - return intel_pt_deliver_synth_event(pt, event, &sample, + perf_sample__exit(&sample); + ret = intel_pt_deliver_synth_event(pt, event, &sample, pt->branches_sample_type); + return ret; } static void intel_pt_prep_sample(struct intel_pt *pt, @@ -1835,11 +1841,13 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_sample(pt, ptq, event, &sample); sample.id = ptq->pt->instructions_id; @@ -1859,16 +1867,19 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) ptq->last_insn_cnt = ptq->state->tot_insn_cnt; - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->instructions_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->instructions_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; u64 period = 0; + int ret; if (ptq->sample_ipc) period = ptq->ipc_cyc_cnt - ptq->last_cy_cyc_cnt; @@ -1876,6 +1887,7 @@ static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq) if (!period || intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_sample(pt, ptq, event, &sample); sample.id = ptq->pt->cycles_id; @@ -1887,25 +1899,31 @@ static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq) ptq->last_cy_insn_cnt = ptq->ipc_insn_cnt; ptq->last_cy_cyc_cnt = ptq->ipc_cyc_cnt; - return intel_pt_deliver_synth_event(pt, event, &sample, pt->cycles_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, pt->cycles_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_sample(pt, ptq, event, &sample); sample.id = ptq->pt->transactions_id; sample.stream_id = ptq->pt->transactions_id; - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->transactions_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->transactions_sample_type); + perf_sample__exit(&sample); + return ret; } static void intel_pt_prep_p_sample(struct intel_pt *pt, @@ -1953,15 +1971,17 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_cbr raw; u32 flags; + int ret; if (intel_pt_skip_cbr_event(pt)) return 0; ptq->cbr_seen = ptq->state->cbr; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->cbr_id; @@ -1975,20 +1995,24 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_psb_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_psb raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->psb_id; @@ -2001,20 +2025,24 @@ static int intel_pt_synth_psb_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_mwait raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->mwait_id; @@ -2026,20 +2054,24 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_pwre raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->pwre_id; @@ -2051,20 +2083,24 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_exstop raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->exstop_id; @@ -2076,20 +2112,24 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_pwrx raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->pwrx_id; @@ -2101,8 +2141,10 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } /* @@ -2232,19 +2274,160 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack, } } -static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id) +#define P(a, b) PERF_MEM_S(a, b) +#define OP_LH (P(OP, LOAD) | P(LVL, HIT)) +#define LEVEL(x) P(LVLNUM, x) +#define REM P(REMOTE, REMOTE) +#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) + +#define PERF_PEBS_DATA_SOURCE_GRT_MAX 0x10 +#define PERF_PEBS_DATA_SOURCE_GRT_MASK (PERF_PEBS_DATA_SOURCE_GRT_MAX - 1) + +/* Based on kernel __intel_pmu_pebs_data_source_grt() and pebs_data_source */ +static const u64 pebs_data_source_grt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = { + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP Hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP Fwd */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* RAM hit|SNP Hit */ + OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* Remote L3 hit|SNP Hit */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* RAM hit|SNP None or Miss */ + OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* Remote RAM hit|SNP None or Miss */ + OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */ + OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */ +}; + +/* Based on kernel __intel_pmu_pebs_data_source_cmt() and pebs_data_source */ +static const u64 pebs_data_source_cmt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = { + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* L3 hit|SNP Hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP Fwd */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* RAM hit|SNP Hit */ + OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE), /* Remote L3 hit|SNP Hit */ + OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD), /* RAM hit|SNP None or Miss */ + OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM), /* Remote RAM hit|SNP None or Miss */ + OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */ + OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */ +}; + +/* Based on kernel pebs_set_tlb_lock() */ +static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock) +{ + /* + * TLB access + * 0 = did not miss 2nd level TLB + * 1 = missed 2nd level TLB + */ + if (tlb) + *val |= P(TLB, MISS) | P(TLB, L2); + else + *val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + /* locked prefix */ + if (lock) + *val |= P(LOCK, LOCKED); +} + +/* Based on kernel __grt_latency_data() */ +static u64 intel_pt_grt_latency_data(u8 dse, bool tlb, bool lock, bool blk, + const u64 *pebs_data_source) +{ + u64 val; + + dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK; + val = pebs_data_source[dse]; + + pebs_set_tlb_lock(&val, tlb, lock); + + if (blk) + val |= P(BLK, DATA); + else + val |= P(BLK, NA); + + return val; +} + +/* Default value for data source */ +#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ + PERF_MEM_S(LVL, NA) |\ + PERF_MEM_S(SNOOP, NA) |\ + PERF_MEM_S(LOCK, NA) |\ + PERF_MEM_S(TLB, NA) |\ + PERF_MEM_S(LVLNUM, NA)) + +enum DATA_SRC_FORMAT { + DATA_SRC_FORMAT_ERR = -1, + DATA_SRC_FORMAT_NA = 0, + DATA_SRC_FORMAT_GRT = 1, + DATA_SRC_FORMAT_CMT = 2, +}; + +/* Based on kernel grt_latency_data() and cmt_latency_data */ +static u64 intel_pt_get_data_src(u64 mem_aux_info, int data_src_fmt) +{ + switch (data_src_fmt) { + case DATA_SRC_FORMAT_GRT: { + union { + u64 val; + struct { + unsigned int dse:4; + unsigned int locked:1; + unsigned int stlb_miss:1; + unsigned int fwd_blk:1; + unsigned int reserved:25; + }; + } x = {.val = mem_aux_info}; + return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk, + pebs_data_source_grt); + } + case DATA_SRC_FORMAT_CMT: { + union { + u64 val; + struct { + unsigned int dse:5; + unsigned int locked:1; + unsigned int stlb_miss:1; + unsigned int fwd_blk:1; + unsigned int reserved:24; + }; + } x = {.val = mem_aux_info}; + return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk, + pebs_data_source_cmt); + } + default: + return PERF_MEM_NA; + } +} + +static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, + u64 id, int data_src_fmt) { const struct intel_pt_blk_items *items = &ptq->state->items; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; union perf_event *event = ptq->event_buf; struct intel_pt *pt = ptq->pt; u64 sample_type = evsel->core.attr.sample_type; u8 cpumode; - u64 regs[8 * sizeof(sample.intr_regs.mask)]; + u64 regs[8 * sizeof(sample.intr_regs->mask)]; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_a_sample(ptq, event, &sample); sample.id = id; @@ -2291,15 +2474,16 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse items->mask[INTEL_PT_XMM_POS])) { u64 regs_mask = evsel->core.attr.sample_regs_intr; u64 *pos; + struct regs_dump *intr_regs = perf_sample__intr_regs(&sample); - sample.intr_regs.abi = items->is_32_bit ? + intr_regs->abi = items->is_32_bit ? PERF_SAMPLE_REGS_ABI_32 : PERF_SAMPLE_REGS_ABI_64; - sample.intr_regs.regs = regs; + intr_regs->regs = regs; - pos = intel_pt_add_gp_regs(&sample.intr_regs, regs, items, regs_mask); + pos = intel_pt_add_gp_regs(intr_regs, regs, items, regs_mask); - intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask); + intel_pt_add_xmm(intr_regs, pos, items, regs_mask); } if (sample_type & PERF_SAMPLE_BRANCH_STACK) { @@ -2350,6 +2534,18 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse } } + if (sample_type & PERF_SAMPLE_DATA_SRC) { + if (items->has_mem_aux_info && data_src_fmt) { + if (data_src_fmt < 0) { + pr_err("Intel PT missing data_src info\n"); + return -1; + } + sample.data_src = intel_pt_get_data_src(items->mem_aux_info, data_src_fmt); + } else { + sample.data_src = PERF_MEM_NA; + } + } + if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) { u64 ax = items->has_rax ? items->rax : 0; /* Refer kernel's intel_hsw_transaction() */ @@ -2361,16 +2557,19 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse sample.transaction = txn; } - return intel_pt_deliver_synth_event(pt, event, &sample, sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; struct evsel *evsel = pt->pebs_evsel; + int data_src_fmt = pt->pebs_data_src_fmt; u64 id = evsel->core.id[0]; - return intel_pt_do_synth_pebs_sample(ptq, evsel, id); + return intel_pt_do_synth_pebs_sample(ptq, evsel, id, data_src_fmt); } static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) @@ -2395,7 +2594,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) hw_id); return intel_pt_synth_single_pebs_sample(ptq); } - err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id); + err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id, pe->data_src_fmt); if (err) return err; } @@ -2407,16 +2606,17 @@ static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct { struct perf_synth_intel_evt cfe; struct perf_synth_intel_evd evd[INTEL_PT_MAX_EVDS]; } raw; - int i; + int i, ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->evt_id; @@ -2438,20 +2638,24 @@ static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq) ptq->state->evd_cnt * sizeof(struct perf_synth_intel_evd); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->evt_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->evt_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_iflag_chg raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->iflag_chg_id; @@ -2471,8 +2675,10 @@ static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->iflag_chg_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->iflag_chg_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, @@ -3355,6 +3561,49 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt, event->itrace_start.tid); } +/* + * Events with data_src are identified by L1_Hit_Indication + * refer https://github.com/intel/perfmon + */ +static int intel_pt_data_src_fmt(struct intel_pt *pt, struct evsel *evsel) +{ + struct perf_env *env = pt->machine->env; + int fmt = DATA_SRC_FORMAT_NA; + + if (!env->cpuid) + return DATA_SRC_FORMAT_ERR; + + /* + * PEBS-via-PT is only supported on E-core non-hybrid. Of those only + * Gracemont and Crestmont have data_src. Check for: + * Alderlake N (Gracemont) + * Sierra Forest (Crestmont) + * Grand Ridge (Crestmont) + */ + + if (!strncmp(env->cpuid, "GenuineIntel,6,190,", 19)) + fmt = DATA_SRC_FORMAT_GRT; + + if (!strncmp(env->cpuid, "GenuineIntel,6,175,", 19) || + !strncmp(env->cpuid, "GenuineIntel,6,182,", 19)) + fmt = DATA_SRC_FORMAT_CMT; + + if (fmt == DATA_SRC_FORMAT_NA) + return fmt; + + /* + * Only data_src events are: + * mem-loads event=0xd0,umask=0x5 + * mem-stores event=0xd0,umask=0x6 + */ + if (evsel->core.attr.type == PERF_TYPE_RAW && + ((evsel->core.attr.config & 0xffff) == 0x5d0 || + (evsel->core.attr.config & 0xffff) == 0x6d0)) + return fmt; + + return DATA_SRC_FORMAT_NA; +} + static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt, union perf_event *event, struct perf_sample *sample) @@ -3375,6 +3624,7 @@ static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt, ptq->pebs[hw_id].evsel = evsel; ptq->pebs[hw_id].id = sample->id; + ptq->pebs[hw_id].data_src_fmt = intel_pt_data_src_fmt(pt, evsel); return 0; } @@ -3737,9 +3987,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, attr.sample_id_all = evsel->core.attr.sample_id_all; attr.read_format = evsel->core.attr.read_format; - id = evsel->core.id[0] + 1000000000; - if (!id) - id = 1; + id = auxtrace_synth_id_range_start(evsel); if (pt->synth_opts.branches) { attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; @@ -3924,6 +4172,7 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt) } pt->single_pebs = true; pt->sample_pebs = true; + pt->pebs_data_src_fmt = intel_pt_data_src_fmt(pt, evsel); pt->pebs_evsel = evsel; } } diff --git a/tools/perf/util/intel-tpebs.c b/tools/perf/util/intel-tpebs.c index 50a3c3e07160..8b615dc94e9e 100644 --- a/tools/perf/util/intel-tpebs.c +++ b/tools/perf/util/intel-tpebs.c @@ -3,7 +3,7 @@ * intel_tpebs.c: Intel TPEBS support */ - +#include <api/fs/fs.h> #include <sys/param.h> #include <subcmd/run-command.h> #include <thread.h> @@ -12,110 +12,174 @@ #include <linux/zalloc.h> #include <linux/err.h> #include "sample.h" +#include "counts.h" #include "debug.h" #include "evlist.h" #include "evsel.h" +#include "mutex.h" #include "session.h" +#include "stat.h" #include "tool.h" #include "cpumap.h" #include "metricgroup.h" #include <sys/stat.h> #include <sys/file.h> +#include <errno.h> #include <poll.h> #include <math.h> #define PERF_DATA "-" bool tpebs_recording; -static pid_t tpebs_pid = -1; -static size_t tpebs_event_size; +enum tpebs_mode tpebs_mode; static LIST_HEAD(tpebs_results); static pthread_t tpebs_reader_thread; -static struct child_process *tpebs_cmd; +static struct child_process tpebs_cmd; +static int control_fd[2], ack_fd[2]; +static struct mutex tpebs_mtx; struct tpebs_retire_lat { struct list_head nd; - /* Event name */ - const char *name; - /* Event name with the TPEBS modifier R */ - const char *tpebs_name; - /* Count of retire_latency values found in sample data */ - size_t count; - /* Sum of all the retire_latency values in sample data */ - int sum; - /* Average of retire_latency, val = sum / count */ - double val; + /** @evsel: The evsel that opened the retire_lat event. */ + struct evsel *evsel; + /** @event: Event passed to perf record. */ + char *event; + /** @stats: Recorded retirement latency stats. */ + struct stats stats; + /** @last: Last retirement latency read. */ + uint64_t last; + /* Has the event been sent to perf record? */ + bool started; }; -static int get_perf_record_args(const char **record_argv, char buf[], - const char *cpumap_buf) +static void tpebs_mtx_init(void) +{ + mutex_init(&tpebs_mtx); +} + +static struct mutex *tpebs_mtx_get(void) { - struct tpebs_retire_lat *e; - int i = 0; + static pthread_once_t tpebs_mtx_once = PTHREAD_ONCE_INIT; + + pthread_once(&tpebs_mtx_once, tpebs_mtx_init); + return &tpebs_mtx; +} - pr_debug("tpebs: Prepare perf record for retire_latency\n"); +static struct tpebs_retire_lat *tpebs_retire_lat__find(struct evsel *evsel) + EXCLUSIVE_LOCKS_REQUIRED(tpebs_mtx_get()); + +static int evsel__tpebs_start_perf_record(struct evsel *evsel) +{ + const char **record_argv; + int tpebs_event_size = 0, i = 0, ret; + char control_fd_buf[32]; + char cpumap_buf[50]; + struct tpebs_retire_lat *t; + + list_for_each_entry(t, &tpebs_results, nd) + tpebs_event_size++; + + record_argv = malloc((10 + 2 * tpebs_event_size) * sizeof(*record_argv)); + if (!record_argv) + return -ENOMEM; record_argv[i++] = "perf"; record_argv[i++] = "record"; record_argv[i++] = "-W"; record_argv[i++] = "--synth=no"; - record_argv[i++] = buf; - if (!cpumap_buf) { - pr_err("tpebs: Require cpumap list to run sampling\n"); - return -ECANCELED; - } - /* Use -C when cpumap_buf is not "-1" */ - if (strcmp(cpumap_buf, "-1")) { + scnprintf(control_fd_buf, sizeof(control_fd_buf), "--control=fd:%d,%d", + control_fd[0], ack_fd[1]); + record_argv[i++] = control_fd_buf; + + record_argv[i++] = "-o"; + record_argv[i++] = PERF_DATA; + + if (!perf_cpu_map__is_any_cpu_or_is_empty(evsel->evlist->core.user_requested_cpus)) { + cpu_map__snprint(evsel->evlist->core.user_requested_cpus, cpumap_buf, + sizeof(cpumap_buf)); record_argv[i++] = "-C"; record_argv[i++] = cpumap_buf; } - list_for_each_entry(e, &tpebs_results, nd) { + list_for_each_entry(t, &tpebs_results, nd) { record_argv[i++] = "-e"; - record_argv[i++] = e->name; + record_argv[i++] = t->event; } + record_argv[i++] = NULL; + assert(i == 10 + 2 * tpebs_event_size || i == 8 + 2 * tpebs_event_size); + /* Note, no workload given so system wide is implied. */ + + assert(tpebs_cmd.pid == 0); + tpebs_cmd.argv = record_argv; + tpebs_cmd.out = -1; + ret = start_command(&tpebs_cmd); + zfree(&tpebs_cmd.argv); + list_for_each_entry(t, &tpebs_results, nd) + t->started = true; - record_argv[i++] = "-o"; - record_argv[i++] = PERF_DATA; - - return 0; + return ret; } -static int prepare_run_command(const char **argv) +static bool is_child_pid(pid_t parent, pid_t child) { - tpebs_cmd = zalloc(sizeof(struct child_process)); - if (!tpebs_cmd) - return -ENOMEM; - tpebs_cmd->argv = argv; - tpebs_cmd->out = -1; - return 0; + if (parent < 0 || child < 0) + return false; + + while (true) { + char path[PATH_MAX]; + char line[256]; + FILE *fp; + +new_child: + if (parent == child) + return true; + + if (child <= 0) + return false; + + scnprintf(path, sizeof(path), "%s/%d/status", procfs__mountpoint(), child); + fp = fopen(path, "r"); + if (!fp) { + /* Presumably the process went away. Assume not a child. */ + return false; + } + while (fgets(line, sizeof(line), fp) != NULL) { + if (strncmp(line, "PPid:", 5) == 0) { + fclose(fp); + if (sscanf(line + 5, "%d", &child) != 1) { + /* Unexpected error parsing. */ + return false; + } + goto new_child; + } + } + /* Unexpected EOF. */ + fclose(fp); + return false; + } } -static int start_perf_record(int control_fd[], int ack_fd[], - const char *cpumap_buf) +static bool should_ignore_sample(const struct perf_sample *sample, const struct tpebs_retire_lat *t) { - const char **record_argv; - int ret; - char buf[32]; + pid_t workload_pid, sample_pid = sample->pid; - scnprintf(buf, sizeof(buf), "--control=fd:%d,%d", control_fd[0], ack_fd[1]); + /* + * During evlist__purge the evlist will be removed prior to the + * evsel__exit calling evsel__tpebs_close and taking the + * tpebs_mtx. Avoid a segfault by ignoring samples in this case. + */ + if (t->evsel->evlist == NULL) + return true; - record_argv = calloc(12 + 2 * tpebs_event_size, sizeof(char *)); - if (!record_argv) - return -ENOMEM; + workload_pid = t->evsel->evlist->workload.pid; + if (workload_pid < 0 || workload_pid == sample_pid) + return false; - ret = get_perf_record_args(record_argv, buf, cpumap_buf); - if (ret) - goto out; + if (!t->evsel->core.attr.inherit) + return true; - ret = prepare_run_command(record_argv); - if (ret) - goto out; - ret = start_command(tpebs_cmd); -out: - free(record_argv); - return ret; + return !is_child_pid(workload_pid, sample_pid); } static int process_sample_event(const struct perf_tool *tool __maybe_unused, @@ -124,51 +188,47 @@ static int process_sample_event(const struct perf_tool *tool __maybe_unused, struct evsel *evsel, struct machine *machine __maybe_unused) { - int ret = 0; - const char *evname; struct tpebs_retire_lat *t; - evname = evsel__name(evsel); - + mutex_lock(tpebs_mtx_get()); + if (tpebs_cmd.pid == 0) { + /* Record has terminated. */ + mutex_unlock(tpebs_mtx_get()); + return 0; + } + t = tpebs_retire_lat__find(evsel); + if (!t) { + mutex_unlock(tpebs_mtx_get()); + return -EINVAL; + } + if (should_ignore_sample(sample, t)) { + mutex_unlock(tpebs_mtx_get()); + return 0; + } /* * Need to handle per core results? We are assuming average retire * latency value will be used. Save the number of samples and the sum of * retire latency value for each event. */ - list_for_each_entry(t, &tpebs_results, nd) { - if (!strcmp(evname, t->name)) { - t->count += 1; - t->sum += sample->retire_lat; - t->val = (double) t->sum / t->count; - break; - } - } - - return ret; -} - -static int process_feature_event(struct perf_session *session, - union perf_event *event) -{ - if (event->feat.feat_id < HEADER_LAST_FEATURE) - return perf_event__process_feature(session, event); + t->last = sample->weight3; + update_stats(&t->stats, sample->weight3); + mutex_unlock(tpebs_mtx_get()); return 0; } -static void *__sample_reader(void *arg) +static void *__sample_reader(void *arg __maybe_unused) { - struct child_process *child = arg; struct perf_session *session; struct perf_data data = { .mode = PERF_DATA_MODE_READ, .path = PERF_DATA, - .file.fd = child->out, + .file.fd = tpebs_cmd.out, }; struct perf_tool tool; perf_tool__init(&tool, /*ordered_events=*/false); tool.sample = process_sample_event; - tool.feature = process_feature_event; + tool.feature = perf_event__process_feature; tool.attr = perf_event__process_attr; session = perf_session__new(&data, &tool); @@ -180,94 +240,277 @@ static void *__sample_reader(void *arg) return NULL; } +static int tpebs_send_record_cmd(const char *msg) EXCLUSIVE_LOCKS_REQUIRED(tpebs_mtx_get()) +{ + struct pollfd pollfd = { .events = POLLIN, }; + int ret, len, retries = 0; + char ack_buf[8]; + + /* Check if the command exited before the send, done with the lock held. */ + if (tpebs_cmd.pid == 0) + return 0; + + /* + * Let go of the lock while sending/receiving as blocking can starve the + * sample reading thread. + */ + mutex_unlock(tpebs_mtx_get()); + + /* Send perf record command.*/ + len = strlen(msg); + ret = write(control_fd[1], msg, len); + if (ret != len) { + pr_err("perf record control write control message '%s' failed\n", msg); + ret = -EPIPE; + goto out; + } + + if (!strcmp(msg, EVLIST_CTL_CMD_STOP_TAG)) { + ret = 0; + goto out; + } + + /* Wait for an ack. */ + pollfd.fd = ack_fd[0]; + + /* + * We need this poll to ensure the ack_fd PIPE will not hang + * when perf record failed for any reason. The timeout value + * 3000ms is an empirical selection. + */ +again: + if (!poll(&pollfd, 1, 500)) { + if (check_if_command_finished(&tpebs_cmd)) { + ret = 0; + goto out; + } + + if (retries++ < 6) + goto again; + pr_err("tpebs failed: perf record ack timeout for '%s'\n", msg); + ret = -ETIMEDOUT; + goto out; + } + + if (!(pollfd.revents & POLLIN)) { + if (check_if_command_finished(&tpebs_cmd)) { + ret = 0; + goto out; + } + + pr_err("tpebs failed: did not received an ack for '%s'\n", msg); + ret = -EPIPE; + goto out; + } + + ret = read(ack_fd[0], ack_buf, sizeof(ack_buf)); + if (ret > 0) + ret = strcmp(ack_buf, EVLIST_CTL_CMD_ACK_TAG); + else + pr_err("tpebs: perf record control ack failed\n"); +out: + /* Re-take lock as expected by caller. */ + mutex_lock(tpebs_mtx_get()); + return ret; +} + /* * tpebs_stop - stop the sample data read thread and the perf record process. */ -static int tpebs_stop(void) +static int tpebs_stop(void) EXCLUSIVE_LOCKS_REQUIRED(tpebs_mtx_get()) { int ret = 0; /* Like tpebs_start, we should only run tpebs_end once. */ - if (tpebs_pid != -1) { - kill(tpebs_cmd->pid, SIGTERM); - tpebs_pid = -1; + if (tpebs_cmd.pid != 0) { + tpebs_send_record_cmd(EVLIST_CTL_CMD_STOP_TAG); + tpebs_cmd.pid = 0; + mutex_unlock(tpebs_mtx_get()); pthread_join(tpebs_reader_thread, NULL); - close(tpebs_cmd->out); - ret = finish_command(tpebs_cmd); + mutex_lock(tpebs_mtx_get()); + close(control_fd[0]); + close(control_fd[1]); + close(ack_fd[0]); + close(ack_fd[1]); + close(tpebs_cmd.out); + ret = finish_command(&tpebs_cmd); + tpebs_cmd.pid = 0; if (ret == -ERR_RUN_COMMAND_WAITPID_SIGNAL) ret = 0; } return ret; } -/* - * tpebs_start - start tpebs execution. - * @evsel_list: retire_latency evsels in this list will be selected and sampled - * to get the average retire_latency value. - * - * This function will be called from evlist level later when evlist__open() is - * called consistently. +/** + * evsel__tpebs_event() - Create string event encoding to pass to `perf record`. */ -int tpebs_start(struct evlist *evsel_list) +static int evsel__tpebs_event(struct evsel *evsel, char **event) { - int ret = 0; - struct evsel *evsel; - char cpumap_buf[50]; + char *name, *modifier; + int ret; + + name = strdup(evsel->name); + if (!name) + return -ENOMEM; + + modifier = strrchr(name, 'R'); + if (!modifier) { + ret = -EINVAL; + goto out; + } + *modifier = 'p'; + modifier = strchr(name, ':'); + if (!modifier) + modifier = strrchr(name, '/'); + if (!modifier) { + ret = -EINVAL; + goto out; + } + *modifier = '\0'; + if (asprintf(event, "%s/name=tpebs_event_%p/%s", name, evsel, modifier + 1) > 0) + ret = 0; + else + ret = -ENOMEM; +out: + if (ret) + pr_err("Tpebs event modifier broken '%s'\n", evsel->name); + free(name); + return ret; +} + +static struct tpebs_retire_lat *tpebs_retire_lat__new(struct evsel *evsel) +{ + struct tpebs_retire_lat *result = zalloc(sizeof(*result)); + int ret; + + if (!result) + return NULL; + + ret = evsel__tpebs_event(evsel, &result->event); + if (ret) { + free(result); + return NULL; + } + result->evsel = evsel; + return result; +} + +static void tpebs_retire_lat__delete(struct tpebs_retire_lat *r) +{ + zfree(&r->event); + free(r); +} + +static struct tpebs_retire_lat *tpebs_retire_lat__find(struct evsel *evsel) +{ + struct tpebs_retire_lat *t; + unsigned long num; + const char *evsel_name; /* - * We should only run tpebs_start when tpebs_recording is enabled. - * And we should only run it once with all the required events. + * Evsels will match for evlist with the retirement latency event. The + * name with "tpebs_event_" prefix will be present on events being read + * from `perf record`. */ - if (tpebs_pid != -1 || !tpebs_recording) + if (evsel__is_retire_lat(evsel)) { + list_for_each_entry(t, &tpebs_results, nd) { + if (t->evsel == evsel) + return t; + } + return NULL; + } + evsel_name = strstr(evsel->name, "tpebs_event_"); + if (!evsel_name) { + /* Unexpected that the perf record should have other events. */ + return NULL; + } + errno = 0; + num = strtoull(evsel_name + 12, NULL, 16); + if (errno) { + pr_err("Bad evsel for tpebs find '%s'\n", evsel->name); + return NULL; + } + list_for_each_entry(t, &tpebs_results, nd) { + if ((unsigned long)t->evsel == num) + return t; + } + return NULL; +} + +/** + * evsel__tpebs_prepare - create tpebs data structures ready for opening. + * @evsel: retire_latency evsel, all evsels on its list will be prepared. + */ +static int evsel__tpebs_prepare(struct evsel *evsel) +{ + struct evsel *pos; + struct tpebs_retire_lat *tpebs_event; + + mutex_lock(tpebs_mtx_get()); + tpebs_event = tpebs_retire_lat__find(evsel); + if (tpebs_event) { + /* evsel, or an identically named one, was already prepared. */ + mutex_unlock(tpebs_mtx_get()); return 0; + } + tpebs_event = tpebs_retire_lat__new(evsel); + if (!tpebs_event) { + mutex_unlock(tpebs_mtx_get()); + return -ENOMEM; + } + list_add_tail(&tpebs_event->nd, &tpebs_results); + mutex_unlock(tpebs_mtx_get()); - cpu_map__snprint(evsel_list->core.user_requested_cpus, cpumap_buf, sizeof(cpumap_buf)); /* - * Prepare perf record for sampling event retire_latency before fork and - * prepare workload + * Eagerly prepare all other evsels on the list to try to ensure that by + * open they are all known. */ - evlist__for_each_entry(evsel_list, evsel) { - int i; - char *name; - struct tpebs_retire_lat *new; + evlist__for_each_entry(evsel->evlist, pos) { + int ret; - if (!evsel->retire_lat) + if (pos == evsel || !pos->retire_lat) continue; - pr_debug("tpebs: Retire_latency of event %s is required\n", evsel->name); - for (i = strlen(evsel->name) - 1; i > 0; i--) { - if (evsel->name[i] == 'R') - break; - } - if (i <= 0 || evsel->name[i] != 'R') { - ret = -1; - goto err; - } + ret = evsel__tpebs_prepare(pos); + if (ret) + return ret; + } + return 0; +} - name = strdup(evsel->name); - if (!name) { - ret = -ENOMEM; - goto err; - } - name[i] = 'p'; +/** + * evsel__tpebs_open - starts tpebs execution. + * @evsel: retire_latency evsel, all evsels on its list will be selected. Each + * evsel is sampled to get the average retire_latency value. + */ +int evsel__tpebs_open(struct evsel *evsel) +{ + int ret; + bool tpebs_empty; - new = zalloc(sizeof(*new)); - if (!new) { - ret = -1; - zfree(name); - goto err; - } - new->name = name; - new->tpebs_name = evsel->name; - list_add_tail(&new->nd, &tpebs_results); - tpebs_event_size += 1; + /* We should only run tpebs_start when tpebs_recording is enabled. */ + if (!tpebs_recording) + return 0; + /* Only start the events once. */ + if (tpebs_cmd.pid != 0) { + struct tpebs_retire_lat *t; + bool valid; + + mutex_lock(tpebs_mtx_get()); + t = tpebs_retire_lat__find(evsel); + valid = t && t->started; + mutex_unlock(tpebs_mtx_get()); + /* May fail as the event wasn't started. */ + return valid ? 0 : -EBUSY; } - if (tpebs_event_size > 0) { - struct pollfd pollfd = { .events = POLLIN, }; - int control_fd[2], ack_fd[2], len; - char ack_buf[8]; + ret = evsel__tpebs_prepare(evsel); + if (ret) + return ret; + mutex_lock(tpebs_mtx_get()); + tpebs_empty = list_empty(&tpebs_results); + if (!tpebs_empty) { /*Create control and ack fd for --control*/ if (pipe(control_fd) < 0) { pr_err("tpebs: Failed to create control fifo"); @@ -280,153 +523,131 @@ int tpebs_start(struct evlist *evsel_list) goto out; } - ret = start_perf_record(control_fd, ack_fd, cpumap_buf); + ret = evsel__tpebs_start_perf_record(evsel); if (ret) goto out; - tpebs_pid = tpebs_cmd->pid; - if (pthread_create(&tpebs_reader_thread, NULL, __sample_reader, tpebs_cmd)) { - kill(tpebs_cmd->pid, SIGTERM); - close(tpebs_cmd->out); - pr_err("Could not create thread to process sample data.\n"); - ret = -1; - goto out; - } - /* Wait for perf record initialization.*/ - len = strlen(EVLIST_CTL_CMD_ENABLE_TAG); - ret = write(control_fd[1], EVLIST_CTL_CMD_ENABLE_TAG, len); - if (ret != len) { - pr_err("perf record control write control message failed\n"); - goto out; - } - /* wait for an ack */ - pollfd.fd = ack_fd[0]; - - /* - * We need this poll to ensure the ack_fd PIPE will not hang - * when perf record failed for any reason. The timeout value - * 3000ms is an empirical selection. - */ - if (!poll(&pollfd, 1, 3000)) { - pr_err("tpebs failed: perf record ack timeout\n"); - ret = -1; - goto out; - } - - if (!(pollfd.revents & POLLIN)) { - pr_err("tpebs failed: did not received an ack\n"); + if (pthread_create(&tpebs_reader_thread, /*attr=*/NULL, __sample_reader, + /*arg=*/NULL)) { + kill(tpebs_cmd.pid, SIGTERM); + close(tpebs_cmd.out); + pr_err("Could not create thread to process sample data.\n"); ret = -1; goto out; } - - ret = read(ack_fd[0], ack_buf, sizeof(ack_buf)); - if (ret > 0) - ret = strcmp(ack_buf, EVLIST_CTL_CMD_ACK_TAG); - else { - pr_err("tpebs: perf record control ack failed\n"); - goto out; - } + ret = tpebs_send_record_cmd(EVLIST_CTL_CMD_ENABLE_TAG); + } out: - close(control_fd[0]); - close(control_fd[1]); - close(ack_fd[0]); - close(ack_fd[1]); + if (ret) { + struct tpebs_retire_lat *t = tpebs_retire_lat__find(evsel); + + list_del_init(&t->nd); + tpebs_retire_lat__delete(t); } -err: - if (ret) - tpebs_delete(); + mutex_unlock(tpebs_mtx_get()); return ret; } - -int tpebs_set_evsel(struct evsel *evsel, int cpu_map_idx, int thread) +int evsel__tpebs_read(struct evsel *evsel, int cpu_map_idx, int thread) { - __u64 val; - bool found = false; + struct perf_counts_values *count, *old_count = NULL; struct tpebs_retire_lat *t; - struct perf_counts_values *count; + uint64_t val; + int ret; - /* Non reitre_latency evsel should never enter this function. */ - if (!evsel__is_retire_lat(evsel)) - return -1; + /* Only set retire_latency value to the first CPU and thread. */ + if (cpu_map_idx != 0 || thread != 0) + return 0; + + if (evsel->prev_raw_counts) + old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); - /* - * Need to stop the forked record to ensure get sampled data from the - * PIPE to process and get non-zero retire_lat value for hybrid. - */ - tpebs_stop(); count = perf_counts(evsel->counts, cpu_map_idx, thread); - list_for_each_entry(t, &tpebs_results, nd) { - if (t->tpebs_name == evsel->name || - (evsel->metric_id && !strcmp(t->tpebs_name, evsel->metric_id))) { - found = true; + mutex_lock(tpebs_mtx_get()); + t = tpebs_retire_lat__find(evsel); + /* + * If reading the first tpebs result, send a ping to the record + * process. Allow the sample reader a chance to read by releasing and + * reacquiring the lock. + */ + if (t && &t->nd == tpebs_results.next) { + ret = tpebs_send_record_cmd(EVLIST_CTL_CMD_PING_TAG); + mutex_unlock(tpebs_mtx_get()); + if (ret) + return ret; + mutex_lock(tpebs_mtx_get()); + } + if (t == NULL || t->stats.n == 0) { + /* No sample data, use default. */ + if (tpebs_recording) { + pr_warning_once( + "Using precomputed retirement latency data as no samples\n"); + } + val = 0; + switch (tpebs_mode) { + case TPEBS_MODE__MIN: + val = rint(evsel->retirement_latency.min); + break; + case TPEBS_MODE__MAX: + val = rint(evsel->retirement_latency.max); + break; + default: + case TPEBS_MODE__LAST: + case TPEBS_MODE__MEAN: + val = rint(evsel->retirement_latency.mean); + break; + } + } else { + switch (tpebs_mode) { + case TPEBS_MODE__MIN: + val = t->stats.min; + break; + case TPEBS_MODE__MAX: + val = t->stats.max; + break; + case TPEBS_MODE__LAST: + val = t->last; + break; + default: + case TPEBS_MODE__MEAN: + val = rint(t->stats.mean); break; } } - - /* Set ena and run to non-zero */ - count->ena = count->run = 1; - count->lost = 0; - - if (!found) { - /* - * Set default value or 0 when retire_latency for this event is - * not found from sampling data (record_tpebs not set or 0 - * sample recorded). - */ - count->val = 0; - return 0; + mutex_unlock(tpebs_mtx_get()); + + if (old_count) { + count->val = old_count->val + val; + count->run = old_count->run + 1; + count->ena = old_count->ena + 1; + } else { + count->val = val; + count->run++; + count->ena++; } - - /* - * Only set retire_latency value to the first CPU and thread. - */ - if (cpu_map_idx == 0 && thread == 0) - val = rint(t->val); - else - val = 0; - - count->val = val; return 0; } -static void tpebs_retire_lat__delete(struct tpebs_retire_lat *r) -{ - zfree(&r->name); - free(r); -} - - -/* - * tpebs_delete - delete tpebs related data and stop the created thread and - * process by calling tpebs_stop(). +/** + * evsel__tpebs_close() - delete tpebs related data. If the last event, stop the + * created thread and process by calling tpebs_stop(). * - * This function is called from evlist_delete() and also from builtin-stat - * stat_handle_error(). If tpebs_start() is called from places other then perf - * stat, need to ensure tpebs_delete() is also called to safely free mem and - * close the data read thread and the forked perf record process. - * - * This function is also called in evsel__close() to be symmetric with - * tpebs_start() being called in evsel__open(). We will update this call site - * when move tpebs_start() to evlist level. + * This function is called in evsel__close() to be symmetric with + * evsel__tpebs_open() being called in evsel__open(). */ -void tpebs_delete(void) +void evsel__tpebs_close(struct evsel *evsel) { - struct tpebs_retire_lat *r, *rtmp; - - if (tpebs_pid == -1) - return; - - tpebs_stop(); + struct tpebs_retire_lat *t; - list_for_each_entry_safe(r, rtmp, &tpebs_results, nd) { - list_del_init(&r->nd); - tpebs_retire_lat__delete(r); - } + mutex_lock(tpebs_mtx_get()); + t = tpebs_retire_lat__find(evsel); + if (t) { + list_del_init(&t->nd); + tpebs_retire_lat__delete(t); - if (tpebs_cmd) { - free(tpebs_cmd); - tpebs_cmd = NULL; + if (list_empty(&tpebs_results)) + tpebs_stop(); } + mutex_unlock(tpebs_mtx_get()); } diff --git a/tools/perf/util/intel-tpebs.h b/tools/perf/util/intel-tpebs.h index 766b3fbd79f1..9475e2e6ea74 100644 --- a/tools/perf/util/intel-tpebs.h +++ b/tools/perf/util/intel-tpebs.h @@ -2,34 +2,24 @@ /* * intel_tpebs.h: Intel TEPBS support */ -#ifndef INCLUDE__PERF_INTEL_TPEBS_H__ -#define INCLUDE__PERF_INTEL_TPEBS_H__ +#ifndef __INTEL_TPEBS_H +#define __INTEL_TPEBS_H -#include "stat.h" -#include "evsel.h" +struct evlist; +struct evsel; -#ifdef HAVE_ARCH_X86_64_SUPPORT +enum tpebs_mode { + TPEBS_MODE__MEAN, + TPEBS_MODE__MIN, + TPEBS_MODE__MAX, + TPEBS_MODE__LAST, +}; extern bool tpebs_recording; -int tpebs_start(struct evlist *evsel_list); -void tpebs_delete(void); -int tpebs_set_evsel(struct evsel *evsel, int cpu_map_idx, int thread); +extern enum tpebs_mode tpebs_mode; -#else +int evsel__tpebs_open(struct evsel *evsel); +void evsel__tpebs_close(struct evsel *evsel); +int evsel__tpebs_read(struct evsel *evsel, int cpu_map_idx, int thread); -static inline int tpebs_start(struct evlist *evsel_list __maybe_unused) -{ - return 0; -} - -static inline void tpebs_delete(void) {}; - -static inline int tpebs_set_evsel(struct evsel *evsel __maybe_unused, - int cpu_map_idx __maybe_unused, - int thread __maybe_unused) -{ - return 0; -} - -#endif -#endif +#endif /* __INTEL_TPEBS_H */ diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index f23e21502bf8..e0ce8b904729 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -14,9 +14,9 @@ #include <sys/mman.h> #include <linux/stringify.h> -#include "build-id.h" #include "event.h" #include "debug.h" +#include "dso.h" #include "evlist.h" #include "namespaces.h" #include "symbol.h" @@ -90,7 +90,8 @@ jit_emit_elf(struct jit_buf_desc *jd, saved_errno = errno; nsinfo__mountns_exit(&nsc); if (fd == -1) { - pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(saved_errno)); + errno = saved_errno; + pr_warning("cannot create jit ELF %s: %m\n", filename); return -1; } @@ -233,7 +234,8 @@ jit_open(struct jit_buf_desc *jd, const char *name) /* * keep dirname for generating files and mmap records */ - strcpy(jd->dir, name); + strncpy(jd->dir, name, PATH_MAX); + jd->dir[PATH_MAX - 1] = '\0'; dirname(jd->dir); free(buf); @@ -516,7 +518,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) * create pseudo sample to induce dso hit increment * use first address as sample address */ - memset(&sample, 0, sizeof(sample)); + perf_sample__init(&sample, /*all=*/true); sample.cpumode = PERF_RECORD_MISC_USER; sample.pid = pid; sample.tid = tid; @@ -531,10 +533,26 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) /* * mark dso as use to generate buildid in the header */ - if (!ret) - build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine); - + if (!ret) { + struct dso_id dso_id = { + { + .maj = event->mmap2.maj, + .min = event->mmap2.min, + .ino = event->mmap2.ino, + .ino_generation = event->mmap2.ino_generation, + }, + .mmap2_valid = true, + .mmap2_ino_generation_valid = true, + }; + struct dso *dso = machine__findnew_dso_id(jd->machine, filename, &dso_id); + + if (dso) + dso__set_hit(dso); + + dso__put(dso); + } out: + perf_sample__exit(&sample); free(event); return ret; } @@ -611,7 +629,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) * create pseudo sample to induce dso hit increment * use first address as sample address */ - memset(&sample, 0, sizeof(sample)); + perf_sample__init(&sample, /*all=*/true); sample.cpumode = PERF_RECORD_MISC_USER; sample.pid = pid; sample.tid = tid; @@ -620,12 +638,13 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) ret = perf_event__process_mmap2(tool, event, &sample, jd->machine); if (ret) - return ret; + goto out; ret = jit_inject_event(jd, event); if (!ret) build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine); - +out: + perf_sample__exit(&sample); return ret; } @@ -739,7 +758,7 @@ jit_inject(struct jit_buf_desc *jd, const char *path) static int jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi, bool *in_pidns) { - char *p; + const char *p; char *end = NULL; pid_t pid2; diff --git a/tools/perf/util/kvm-stat-arch/Build b/tools/perf/util/kvm-stat-arch/Build new file mode 100644 index 000000000000..d84e55656e7a --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/Build @@ -0,0 +1,6 @@ +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat-arm64.o +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat-loongarch.o +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat-powerpc.o +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat-riscv.o +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat-s390.o +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat-x86.o diff --git a/tools/perf/util/kvm-stat-arch/arm64_exception_types.h b/tools/perf/util/kvm-stat-arch/arm64_exception_types.h new file mode 100644 index 000000000000..bf827f19ace0 --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/arm64_exception_types.h @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef ARCH_PERF_ARM64_EXCEPTION_TYPES_H +#define ARCH_PERF_ARM64_EXCEPTION_TYPES_H + +/* Per asm/virt.h */ +#define HVC_STUB_ERR 0xbadca11 + +/* Per asm/kvm_asm.h */ +#define ARM_EXCEPTION_IRQ 0 +#define ARM_EXCEPTION_EL1_SERROR 1 +#define ARM_EXCEPTION_TRAP 2 +#define ARM_EXCEPTION_IL 3 +/* The hyp-stub will return this for any kvm_call_hyp() call */ +#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR + +#define kvm_arm_exception_type \ + {ARM_EXCEPTION_IRQ, "IRQ" }, \ + {ARM_EXCEPTION_EL1_SERROR, "SERROR" }, \ + {ARM_EXCEPTION_TRAP, "TRAP" }, \ + {ARM_EXCEPTION_IL, "ILLEGAL" }, \ + {ARM_EXCEPTION_HYP_GONE, "HYP_GONE" } + +/* Per asm/esr.h */ +#define ESR_ELx_EC_UNKNOWN (0x00) +#define ESR_ELx_EC_WFx (0x01) +/* Unallocated EC: 0x02 */ +#define ESR_ELx_EC_CP15_32 (0x03) +#define ESR_ELx_EC_CP15_64 (0x04) +#define ESR_ELx_EC_CP14_MR (0x05) +#define ESR_ELx_EC_CP14_LS (0x06) +#define ESR_ELx_EC_FP_ASIMD (0x07) +#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +#define ESR_ELx_EC_OTHER (0x0A) +/* Unallocated EC: 0x0B */ +#define ESR_ELx_EC_CP14_64 (0x0C) +#define ESR_ELx_EC_BTI (0x0D) +#define ESR_ELx_EC_ILL (0x0E) +/* Unallocated EC: 0x0F - 0x10 */ +#define ESR_ELx_EC_SVC32 (0x11) +#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ +/* Unallocated EC: 0x14 */ +#define ESR_ELx_EC_SVC64 (0x15) +#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ +#define ESR_ELx_EC_SYS64 (0x18) +#define ESR_ELx_EC_SVE (0x19) +#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +/* Unallocated EC: 0x1B */ +#define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ +#define ESR_ELx_EC_SME (0x1D) +/* Unallocated EC: 0x1E */ +#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ +#define ESR_ELx_EC_IABT_LOW (0x20) +#define ESR_ELx_EC_IABT_CUR (0x21) +#define ESR_ELx_EC_PC_ALIGN (0x22) +/* Unallocated EC: 0x23 */ +#define ESR_ELx_EC_DABT_LOW (0x24) +#define ESR_ELx_EC_DABT_CUR (0x25) +#define ESR_ELx_EC_SP_ALIGN (0x26) +#define ESR_ELx_EC_MOPS (0x27) +#define ESR_ELx_EC_FP_EXC32 (0x28) +/* Unallocated EC: 0x29 - 0x2B */ +#define ESR_ELx_EC_FP_EXC64 (0x2C) +#define ESR_ELx_EC_GCS (0x2D) +/* Unallocated EC: 0x2E */ +#define ESR_ELx_EC_SERROR (0x2F) +#define ESR_ELx_EC_BREAKPT_LOW (0x30) +#define ESR_ELx_EC_BREAKPT_CUR (0x31) +#define ESR_ELx_EC_SOFTSTP_LOW (0x32) +#define ESR_ELx_EC_SOFTSTP_CUR (0x33) +#define ESR_ELx_EC_WATCHPT_LOW (0x34) +#define ESR_ELx_EC_WATCHPT_CUR (0x35) +/* Unallocated EC: 0x36 - 0x37 */ +#define ESR_ELx_EC_BKPT32 (0x38) +/* Unallocated EC: 0x39 */ +#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ +/* Unallocated EC: 0x3B */ +#define ESR_ELx_EC_BRK64 (0x3C) +/* Unallocated EC: 0x3D - 0x3F */ +#define ESR_ELx_EC_MAX (0x3F) + +#define ECN(x) { ESR_ELx_EC_##x, #x } + +#define kvm_arm_exception_class \ + ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \ + ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \ + ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \ + ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \ + ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ + ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ + ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ + ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ + ECN(BKPT32), ECN(VECTOR32), ECN(BRK64) + +#endif /* ARCH_PERF_ARM64_EXCEPTION_TYPES_H */ diff --git a/tools/perf/util/kvm-stat-arch/book3s_hcalls.h b/tools/perf/util/kvm-stat-arch/book3s_hcalls.h new file mode 100644 index 000000000000..488f4339b83c --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/book3s_hcalls.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H +#define ARCH_PERF_BOOK3S_HV_HCALLS_H + +/* + * PowerPC HCALL codes : hcall code to name mapping + */ +#define kvm_trace_symbol_hcall \ + {0x4, "H_REMOVE"}, \ + {0x8, "H_ENTER"}, \ + {0xc, "H_READ"}, \ + {0x10, "H_CLEAR_MOD"}, \ + {0x14, "H_CLEAR_REF"}, \ + {0x18, "H_PROTECT"}, \ + {0x1c, "H_GET_TCE"}, \ + {0x20, "H_PUT_TCE"}, \ + {0x24, "H_SET_SPRG0"}, \ + {0x28, "H_SET_DABR"}, \ + {0x2c, "H_PAGE_INIT"}, \ + {0x30, "H_SET_ASR"}, \ + {0x34, "H_ASR_ON"}, \ + {0x38, "H_ASR_OFF"}, \ + {0x3c, "H_LOGICAL_CI_LOAD"}, \ + {0x40, "H_LOGICAL_CI_STORE"}, \ + {0x44, "H_LOGICAL_CACHE_LOAD"}, \ + {0x48, "H_LOGICAL_CACHE_STORE"}, \ + {0x4c, "H_LOGICAL_ICBI"}, \ + {0x50, "H_LOGICAL_DCBF"}, \ + {0x54, "H_GET_TERM_CHAR"}, \ + {0x58, "H_PUT_TERM_CHAR"}, \ + {0x5c, "H_REAL_TO_LOGICAL"}, \ + {0x60, "H_HYPERVISOR_DATA"}, \ + {0x64, "H_EOI"}, \ + {0x68, "H_CPPR"}, \ + {0x6c, "H_IPI"}, \ + {0x70, "H_IPOLL"}, \ + {0x74, "H_XIRR"}, \ + {0x78, "H_MIGRATE_DMA"}, \ + {0x7c, "H_PERFMON"}, \ + {0xdc, "H_REGISTER_VPA"}, \ + {0xe0, "H_CEDE"}, \ + {0xe4, "H_CONFER"}, \ + {0xe8, "H_PROD"}, \ + {0xec, "H_GET_PPP"}, \ + {0xf0, "H_SET_PPP"}, \ + {0xf4, "H_PURR"}, \ + {0xf8, "H_PIC"}, \ + {0xfc, "H_REG_CRQ"}, \ + {0x100, "H_FREE_CRQ"}, \ + {0x104, "H_VIO_SIGNAL"}, \ + {0x108, "H_SEND_CRQ"}, \ + {0x110, "H_COPY_RDMA"}, \ + {0x114, "H_REGISTER_LOGICAL_LAN"}, \ + {0x118, "H_FREE_LOGICAL_LAN"}, \ + {0x11c, "H_ADD_LOGICAL_LAN_BUFFER"}, \ + {0x120, "H_SEND_LOGICAL_LAN"}, \ + {0x124, "H_BULK_REMOVE"}, \ + {0x130, "H_MULTICAST_CTRL"}, \ + {0x134, "H_SET_XDABR"}, \ + {0x138, "H_STUFF_TCE"}, \ + {0x13c, "H_PUT_TCE_INDIRECT"}, \ + {0x14c, "H_CHANGE_LOGICAL_LAN_MAC"}, \ + {0x150, "H_VTERM_PARTNER_INFO"}, \ + {0x154, "H_REGISTER_VTERM"}, \ + {0x158, "H_FREE_VTERM"}, \ + {0x15c, "H_RESET_EVENTS"}, \ + {0x160, "H_ALLOC_RESOURCE"}, \ + {0x164, "H_FREE_RESOURCE"}, \ + {0x168, "H_MODIFY_QP"}, \ + {0x16c, "H_QUERY_QP"}, \ + {0x170, "H_REREGISTER_PMR"}, \ + {0x174, "H_REGISTER_SMR"}, \ + {0x178, "H_QUERY_MR"}, \ + {0x17c, "H_QUERY_MW"}, \ + {0x180, "H_QUERY_HCA"}, \ + {0x184, "H_QUERY_PORT"}, \ + {0x188, "H_MODIFY_PORT"}, \ + {0x18c, "H_DEFINE_AQP1"}, \ + {0x190, "H_GET_TRACE_BUFFER"}, \ + {0x194, "H_DEFINE_AQP0"}, \ + {0x198, "H_RESIZE_MR"}, \ + {0x19c, "H_ATTACH_MCQP"}, \ + {0x1a0, "H_DETACH_MCQP"}, \ + {0x1a4, "H_CREATE_RPT"}, \ + {0x1a8, "H_REMOVE_RPT"}, \ + {0x1ac, "H_REGISTER_RPAGES"}, \ + {0x1b0, "H_DISABLE_AND_GET"}, \ + {0x1b4, "H_ERROR_DATA"}, \ + {0x1b8, "H_GET_HCA_INFO"}, \ + {0x1bc, "H_GET_PERF_COUNT"}, \ + {0x1c0, "H_MANAGE_TRACE"}, \ + {0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"}, \ + {0x1d8, "H_POLL_PENDING"}, \ + {0x1e4, "H_QUERY_INT_STATE"}, \ + {0x244, "H_ILLAN_ATTRIBUTES"}, \ + {0x250, "H_MODIFY_HEA_QP"}, \ + {0x254, "H_QUERY_HEA_QP"}, \ + {0x258, "H_QUERY_HEA"}, \ + {0x25c, "H_QUERY_HEA_PORT"}, \ + {0x260, "H_MODIFY_HEA_PORT"}, \ + {0x264, "H_REG_BCMC"}, \ + {0x268, "H_DEREG_BCMC"}, \ + {0x26c, "H_REGISTER_HEA_RPAGES"}, \ + {0x270, "H_DISABLE_AND_GET_HEA"}, \ + {0x274, "H_GET_HEA_INFO"}, \ + {0x278, "H_ALLOC_HEA_RESOURCE"}, \ + {0x284, "H_ADD_CONN"}, \ + {0x288, "H_DEL_CONN"}, \ + {0x298, "H_JOIN"}, \ + {0x2a4, "H_VASI_STATE"}, \ + {0x2b0, "H_ENABLE_CRQ"}, \ + {0x2b8, "H_GET_EM_PARMS"}, \ + {0x2d0, "H_SET_MPP"}, \ + {0x2d4, "H_GET_MPP"}, \ + {0x2ec, "H_HOME_NODE_ASSOCIATIVITY"}, \ + {0x2f4, "H_BEST_ENERGY"}, \ + {0x2fc, "H_XIRR_X"}, \ + {0x300, "H_RANDOM"}, \ + {0x304, "H_COP"}, \ + {0x314, "H_GET_MPP_X"}, \ + {0x31c, "H_SET_MODE"}, \ + {0xf000, "H_RTAS"} \ + +#endif diff --git a/tools/perf/util/kvm-stat-arch/book3s_hv_exits.h b/tools/perf/util/kvm-stat-arch/book3s_hv_exits.h new file mode 100644 index 000000000000..2011376c7ab5 --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/book3s_hv_exits.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H +#define ARCH_PERF_BOOK3S_HV_EXITS_H + +/* + * PowerPC Interrupt vectors : exit code to name mapping + */ + +#define kvm_trace_symbol_exit \ + {0x0, "RETURN_TO_HOST"}, \ + {0x100, "SYSTEM_RESET"}, \ + {0x200, "MACHINE_CHECK"}, \ + {0x300, "DATA_STORAGE"}, \ + {0x380, "DATA_SEGMENT"}, \ + {0x400, "INST_STORAGE"}, \ + {0x480, "INST_SEGMENT"}, \ + {0x500, "EXTERNAL"}, \ + {0x502, "EXTERNAL_HV"}, \ + {0x600, "ALIGNMENT"}, \ + {0x700, "PROGRAM"}, \ + {0x800, "FP_UNAVAIL"}, \ + {0x900, "DECREMENTER"}, \ + {0x980, "HV_DECREMENTER"}, \ + {0xc00, "SYSCALL"}, \ + {0xd00, "TRACE"}, \ + {0xe00, "H_DATA_STORAGE"}, \ + {0xe20, "H_INST_STORAGE"}, \ + {0xe40, "H_EMUL_ASSIST"}, \ + {0xf00, "PERFMON"}, \ + {0xf20, "ALTIVEC"}, \ + {0xf40, "VSX"} + +#endif diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-arm64.c b/tools/perf/util/kvm-stat-arch/kvm-stat-arm64.c new file mode 100644 index 000000000000..c640dcd8af7c --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/kvm-stat-arm64.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <memory.h> +#include "../debug.h" +#include "../evsel.h" +#include "../kvm-stat.h" +#include "arm64_exception_types.h" + +define_exit_reasons_table(arm64_exit_reasons, kvm_arm_exception_type); +define_exit_reasons_table(arm64_trap_exit_reasons, kvm_arm_exception_class); + +static const char *kvm_trap_exit_reason = "esr_ec"; + +static const char * const __kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + NULL, +}; + +static void event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = evsel__intval(evsel, sample, kvm_exit_reason(EM_AARCH64)); + key->exit_reasons = arm64_exit_reasons; + + /* + * TRAP exceptions carry exception class info in esr_ec field + * and, hence, we need to use a different exit_reasons table to + * properly decode event's est_ec. + */ + if (key->key == ARM_EXCEPTION_TRAP) { + key->key = evsel__intval(evsel, sample, kvm_trap_exit_reason); + key->exit_reasons = arm64_trap_exit_reasons; + } +} + +static bool event_begin(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return evsel__name_is(evsel, kvm_entry_trace(EM_AARCH64)); +} + +static bool event_end(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (evsel__name_is(evsel, kvm_exit_trace(EM_AARCH64))) { + event_get_key(evsel, sample, key); + return true; + } + return false; +} + +static const struct kvm_events_ops exit_events = { + .is_begin_event = event_begin, + .is_end_event = event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +static const struct kvm_reg_events_ops __kvm_reg_events_ops[] = { + { + .name = "vmexit", + .ops = &exit_events, + }, + { NULL, NULL }, +}; + +static const char * const __kvm_skip_events[] = { + NULL, +}; + +int __cpu_isa_init_arm64(struct perf_kvm_stat *kvm) +{ + kvm->exit_reasons_isa = "arm64"; + return 0; +} + +const char * const *__kvm_events_tp_arm64(void) +{ + return __kvm_events_tp; +} + +const struct kvm_reg_events_ops *__kvm_reg_events_ops_arm64(void) +{ + return __kvm_reg_events_ops; +} + +const char * const *__kvm_skip_events_arm64(void) +{ + return __kvm_skip_events; +} diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-loongarch.c b/tools/perf/util/kvm-stat-arch/kvm-stat-loongarch.c new file mode 100644 index 000000000000..b802e516b138 --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/kvm-stat-loongarch.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <memory.h> +#include <dwarf-regs.h> +#include "../kvm-stat.h" +#include "../parse-events.h" +#include "../debug.h" +#include "../evsel.h" +#include "../evlist.h" +#include "../pmus.h" + +#define LOONGARCH_EXCEPTION_INT 0 +#define LOONGARCH_EXCEPTION_PIL 1 +#define LOONGARCH_EXCEPTION_PIS 2 +#define LOONGARCH_EXCEPTION_PIF 3 +#define LOONGARCH_EXCEPTION_PME 4 +#define LOONGARCH_EXCEPTION_FPD 15 +#define LOONGARCH_EXCEPTION_SXD 16 +#define LOONGARCH_EXCEPTION_ASXD 17 +#define LOONGARCH_EXCEPTION_GSPR 22 +#define LOONGARCH_EXCEPTION_CPUCFG 100 +#define LOONGARCH_EXCEPTION_CSR 101 +#define LOONGARCH_EXCEPTION_IOCSR 102 +#define LOONGARCH_EXCEPTION_IDLE 103 +#define LOONGARCH_EXCEPTION_OTHERS 104 +#define LOONGARCH_EXCEPTION_HVC 23 + +#define loongarch_exception_type \ + {LOONGARCH_EXCEPTION_INT, "Interrupt" }, \ + {LOONGARCH_EXCEPTION_PIL, "Mem Read" }, \ + {LOONGARCH_EXCEPTION_PIS, "Mem Store" }, \ + {LOONGARCH_EXCEPTION_PIF, "Inst Fetch" }, \ + {LOONGARCH_EXCEPTION_PME, "Mem Modify" }, \ + {LOONGARCH_EXCEPTION_FPD, "FPU" }, \ + {LOONGARCH_EXCEPTION_SXD, "LSX" }, \ + {LOONGARCH_EXCEPTION_ASXD, "LASX" }, \ + {LOONGARCH_EXCEPTION_GSPR, "Privilege Error" }, \ + {LOONGARCH_EXCEPTION_HVC, "Hypercall" }, \ + {LOONGARCH_EXCEPTION_CPUCFG, "CPUCFG" }, \ + {LOONGARCH_EXCEPTION_CSR, "CSR" }, \ + {LOONGARCH_EXCEPTION_IOCSR, "IOCSR" }, \ + {LOONGARCH_EXCEPTION_IDLE, "Idle" }, \ + {LOONGARCH_EXCEPTION_OTHERS, "Others" } + +define_exit_reasons_table(loongarch_exit_reasons, loongarch_exception_type); + +static const char *kvm_reenter_trace = "kvm:kvm_reenter"; +static const char * const __kvm_events_tp[] = { + "kvm:kvm_enter", + "kvm:kvm_reenter", + "kvm:kvm_exit", + "kvm:kvm_exit_gspr", + NULL, +}; + +static bool event_begin(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + return exit_event_begin(evsel, sample, key); +} + +static bool event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + /* + * LoongArch kvm is different with other architectures + * + * There is kvm:kvm_reenter or kvm:kvm_enter event adjacent with + * kvm:kvm_exit event. + * kvm:kvm_enter means returning to vmm and then to guest + * kvm:kvm_reenter means returning to guest immediately + */ + return evsel__name_is(evsel, kvm_entry_trace(EM_LOONGARCH)) || + evsel__name_is(evsel, kvm_reenter_trace); +} + +static void event_gspr_get_key(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + unsigned int insn; + + key->key = LOONGARCH_EXCEPTION_OTHERS; + insn = evsel__intval(evsel, sample, "inst_word"); + + switch (insn >> 24) { + case 0: + /* CPUCFG inst trap */ + if ((insn >> 10) == 0x1b) + key->key = LOONGARCH_EXCEPTION_CPUCFG; + break; + case 4: + /* CSR inst trap */ + key->key = LOONGARCH_EXCEPTION_CSR; + break; + case 6: + /* IOCSR inst trap */ + if ((insn >> 15) == 0xc90) + key->key = LOONGARCH_EXCEPTION_IOCSR; + else if ((insn >> 15) == 0xc91) + /* Idle inst trap */ + key->key = LOONGARCH_EXCEPTION_IDLE; + break; + default: + key->key = LOONGARCH_EXCEPTION_OTHERS; + break; + } +} + +static const struct child_event_ops child_events[] = { + { .name = "kvm:kvm_exit_gspr", .get_key = event_gspr_get_key }, + { NULL, NULL }, +}; + +static const struct kvm_events_ops exit_events = { + .is_begin_event = event_begin, + .is_end_event = event_end, + .child_ops = child_events, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +static const struct kvm_reg_events_ops __kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events, }, + { NULL, NULL }, +}; + +static const char * const __kvm_skip_events[] = { + NULL, +}; + +int __cpu_isa_init_loongarch(struct perf_kvm_stat *kvm) +{ + kvm->exit_reasons_isa = "loongarch64"; + kvm->exit_reasons = loongarch_exit_reasons; + return 0; +} + +const char * const *__kvm_events_tp_loongarch(void) +{ + return __kvm_events_tp; +} + +const struct kvm_reg_events_ops *__kvm_reg_events_ops_loongarch(void) +{ + return __kvm_reg_events_ops; +} + +const char * const *__kvm_skip_events_loongarch(void) +{ + return __kvm_skip_events; +} diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-powerpc.c b/tools/perf/util/kvm-stat-arch/kvm-stat-powerpc.c new file mode 100644 index 000000000000..42182d70beb6 --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/kvm-stat-powerpc.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include "../kvm-stat.h" +#include "../parse-events.h" +#include "../debug.h" +#include "../evsel.h" +#include "../evlist.h" +#include "../pmus.h" + +#include "book3s_hv_exits.h" +#include "book3s_hcalls.h" +#include <subcmd/parse-options.h> + +#define NR_TPS 4 + +define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit); +define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall); + +/* Tracepoints specific to ppc_book3s_hv */ +static const char * const ppc_book3s_hv_kvm_tp[] = { + "kvm_hv:kvm_guest_enter", + "kvm_hv:kvm_guest_exit", + "kvm_hv:kvm_hcall_enter", + "kvm_hv:kvm_hcall_exit", + NULL, +}; + +/* 1 extra placeholder for NULL */ +static const char *__kvm_events_tp[NR_TPS + 1]; + +static void hcall_event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = evsel__intval(evsel, sample, "req"); +} + +static const char *get_hcall_exit_reason(u64 exit_code) +{ + struct exit_reasons_table *tbl = hcall_reasons; + + while (tbl->reason != NULL) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; + } + + pr_debug("Unknown hcall code: %lld\n", + (unsigned long long)exit_code); + return "UNKNOWN"; +} + +static bool hcall_event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return evsel__name_is(evsel, __kvm_events_tp[3]); +} + +static bool hcall_event_begin(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (evsel__name_is(evsel, __kvm_events_tp[2])) { + hcall_event_get_key(evsel, sample, key); + return true; + } + + return false; +} +static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + const char *hcall_reason = get_hcall_exit_reason(key->key); + + scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", hcall_reason); +} + +static const struct kvm_events_ops hcall_events = { + .is_begin_event = hcall_event_begin, + .is_end_event = hcall_event_end, + .decode_key = hcall_event_decode_key, + .name = "HCALL-EVENT", +}; + +static const struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +static const struct kvm_reg_events_ops __kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { .name = "hcall", .ops = &hcall_events }, + { NULL, NULL }, +}; + +static const char * const __kvm_skip_events[] = { + NULL, +}; + + +static int is_tracepoint_available(const char *str, struct evlist *evlist) +{ + struct parse_events_error err; + int ret; + + parse_events_error__init(&err); + ret = parse_events(evlist, str, &err); + if (ret) + parse_events_error__print(&err, "tracepoint"); + parse_events_error__exit(&err); + return ret; +} + +static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm, + struct evlist *evlist) +{ + const char * const *events_ptr; + int i, nr_tp = 0, err = -1; + + /* Check for book3s_hv tracepoints */ + for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) { + err = is_tracepoint_available(*events_ptr, evlist); + if (err) + return -1; + nr_tp++; + } + + for (i = 0; i < nr_tp; i++) + __kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i]; + + __kvm_events_tp[i] = NULL; + kvm->exit_reasons = hv_exit_reasons; + kvm->exit_reasons_isa = "HV"; + + return 0; +} + +/* Wrapper to setup kvm tracepoints */ +static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm) +{ + struct evlist *evlist = evlist__new(); + + if (evlist == NULL) + return -ENOMEM; + + /* Right now, only supported on book3s_hv */ + return ppc__setup_book3s_hv(kvm, evlist); +} + +int __setup_kvm_events_tp_powerpc(struct perf_kvm_stat *kvm) +{ + return ppc__setup_kvm_tp(kvm); +} + +int __cpu_isa_init_powerpc(struct perf_kvm_stat *kvm) +{ + int ret; + + ret = ppc__setup_kvm_tp(kvm); + if (ret) { + kvm->exit_reasons = NULL; + kvm->exit_reasons_isa = NULL; + } + + return ret; +} + +/* + * In case of powerpc architecture, pmu registers are programmable + * by guest kernel. So monitoring guest via host may not provide + * valid samples with default 'cycles' event. It is better to use + * 'trace_imc/trace_cycles' event for guest profiling, since it + * can track the guest instruction pointer in the trace-record. + * + * Function to parse the arguments and return appropriate values. + */ +int __kvm_add_default_arch_event_powerpc(int *argc, const char **argv) +{ + const char **tmp; + bool event = false; + int i, j = *argc; + + const struct option event_options[] = { + OPT_BOOLEAN('e', "event", &event, NULL), + OPT_END() + }; + + tmp = calloc(j + 1, sizeof(char *)); + if (!tmp) + return -EINVAL; + + for (i = 0; i < j; i++) + tmp[i] = argv[i]; + + parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN); + if (!event) { + if (perf_pmus__have_event("trace_imc", "trace_cycles")) { + argv[j++] = strdup("-e"); + argv[j++] = strdup("trace_imc/trace_cycles/"); + *argc += 2; + } else { + free(tmp); + return -EINVAL; + } + } + + free(tmp); + return 0; +} + +const char * const *__kvm_events_tp_powerpc(void) +{ + return __kvm_events_tp; +} + +const struct kvm_reg_events_ops *__kvm_reg_events_ops_powerpc(void) +{ + return __kvm_reg_events_ops; +} + +const char * const *__kvm_skip_events_powerpc(void) +{ + return __kvm_skip_events; +} diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-riscv.c b/tools/perf/util/kvm-stat-arch/kvm-stat-riscv.c new file mode 100644 index 000000000000..8d4d5d6ce720 --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/kvm-stat-riscv.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Arch specific functions for perf kvm stat. + * + * Copyright 2024 Beijing ESWIN Computing Technology Co., Ltd. + * + */ +#include <errno.h> +#include <memory.h> +#include "../evsel.h" +#include "../kvm-stat.h" +#include "riscv_trap_types.h" +#include "debug.h" + +define_exit_reasons_table(riscv_exit_reasons, kvm_riscv_trap_class); + +static const char * const __kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + NULL, +}; + +static void event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + int xlen = 64; // TODO: 32-bit support. + + key->info = 0; + key->key = evsel__intval(evsel, sample, kvm_exit_reason(EM_RISCV)) & ~CAUSE_IRQ_FLAG(xlen); + key->exit_reasons = riscv_exit_reasons; +} + +static bool event_begin(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return evsel__name_is(evsel, kvm_entry_trace(EM_RISCV)); +} + +static bool event_end(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (evsel__name_is(evsel, kvm_exit_trace(EM_RISCV))) { + event_get_key(evsel, sample, key); + return true; + } + return false; +} + +static const struct kvm_events_ops exit_events = { + .is_begin_event = event_begin, + .is_end_event = event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +static const struct kvm_reg_events_ops __kvm_reg_events_ops[] = { + { + .name = "vmexit", + .ops = &exit_events, + }, + { NULL, NULL }, +}; + +static const char * const __kvm_skip_events[] = { + NULL, +}; + +int __cpu_isa_init_riscv(struct perf_kvm_stat *kvm) +{ + kvm->exit_reasons_isa = "riscv64"; + return 0; +} + +const char * const *__kvm_events_tp_riscv(void) +{ + return __kvm_events_tp; +} + +const struct kvm_reg_events_ops *__kvm_reg_events_ops_riscv(void) +{ + return __kvm_reg_events_ops; +} + +const char * const *__kvm_skip_events_riscv(void) +{ + return __kvm_skip_events; +} diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-s390.c b/tools/perf/util/kvm-stat-arch/kvm-stat-s390.c new file mode 100644 index 000000000000..7e29169f5bb0 --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/kvm-stat-s390.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Arch specific functions for perf kvm stat. + * + * Copyright 2014 IBM Corp. + * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com> + */ + +#include <errno.h> +#include <string.h> +#include "../kvm-stat.h" +#include "../evsel.h" +#include "../../../arch/s390/include/uapi/asm/sie.h" + +define_exit_reasons_table(sie_exit_reasons, sie_intercept_code); +define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes); +define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes); +define_exit_reasons_table(sie_diagnose_codes, diagnose_codes); +define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes); + +static void event_icpt_insn_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + u64 insn; + + insn = evsel__intval(evsel, sample, "instruction"); + key->key = icpt_insn_decoder(insn); + key->exit_reasons = sie_icpt_insn_codes; +} + +static void event_sigp_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = evsel__intval(evsel, sample, "order_code"); + key->exit_reasons = sie_sigp_order_codes; +} + +static void event_diag_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = evsel__intval(evsel, sample, "code"); + key->exit_reasons = sie_diagnose_codes; +} + +static void event_icpt_prog_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = evsel__intval(evsel, sample, "code"); + key->exit_reasons = sie_icpt_prog_codes; +} + +static const struct child_event_ops child_events[] = { + { .name = "kvm:kvm_s390_intercept_instruction", + .get_key = event_icpt_insn_get_key }, + { .name = "kvm:kvm_s390_handle_sigp", + .get_key = event_sigp_get_key }, + { .name = "kvm:kvm_s390_handle_diag", + .get_key = event_diag_get_key }, + { .name = "kvm:kvm_s390_intercept_prog", + .get_key = event_icpt_prog_get_key }, + { NULL, NULL }, +}; + +static const struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .child_ops = child_events, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +static const char * const __kvm_events_tp[] = { + "kvm:kvm_s390_sie_enter", + "kvm:kvm_s390_sie_exit", + "kvm:kvm_s390_intercept_instruction", + "kvm:kvm_s390_handle_sigp", + "kvm:kvm_s390_handle_diag", + "kvm:kvm_s390_intercept_prog", + NULL, +}; + +static const struct kvm_reg_events_ops __kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { NULL, NULL }, +}; + +static const char * const __kvm_skip_events[] = { + "Wait state", + NULL, +}; + +int __cpu_isa_init_s390(struct perf_kvm_stat *kvm, const char *cpuid) +{ + if (strstr(cpuid, "IBM")) { + kvm->exit_reasons = sie_exit_reasons; + kvm->exit_reasons_isa = "SIE"; + } else + return -ENOTSUP; + + return 0; +} + +const char * const *__kvm_events_tp_s390(void) +{ + return __kvm_events_tp; +} + +const struct kvm_reg_events_ops *__kvm_reg_events_ops_s390(void) +{ + return __kvm_reg_events_ops; +} + +const char * const *__kvm_skip_events_s390(void) +{ + return __kvm_skip_events; +} diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c b/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c new file mode 100644 index 000000000000..0f626db3a439 --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <string.h> +#include "../kvm-stat.h" +#include "../evsel.h" +#include "../env.h" +#include "../../../arch/x86/include/uapi/asm/svm.h" +#include "../../../arch/x86/include/uapi/asm/vmx.h" +#include "../../../arch/x86/include/uapi/asm/kvm.h" +#include <subcmd/parse-options.h> + +define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); +define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS); + +static const struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +/* + * For the mmio events, we treat: + * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry + * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). + */ +static void mmio_event_get_key(struct evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + key->key = evsel__intval(evsel, sample, "gpa"); + key->info = evsel__intval(evsel, sample, "type"); +} + +#define KVM_TRACE_MMIO_READ_UNSATISFIED 0 +#define KVM_TRACE_MMIO_READ 1 +#define KVM_TRACE_MMIO_WRITE 2 + +static bool mmio_event_begin(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + /* MMIO read begin event in kernel. */ + if (kvm_exit_event(evsel)) + return true; + + /* MMIO write begin event in kernel. */ + if (evsel__name_is(evsel, "kvm:kvm_mmio") && + evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample, + struct event_key *key) +{ + /* MMIO write end event in kernel. */ + if (kvm_entry_event(evsel)) + return true; + + /* MMIO read end event in kernel.*/ + if (evsel__name_is(evsel, "kvm:kvm_mmio") && + evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { + mmio_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + scnprintf(decode, KVM_EVENT_NAME_LEN, "%#lx:%s", + (unsigned long)key->key, + key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); +} + +static const struct kvm_events_ops mmio_events = { + .is_begin_event = mmio_event_begin, + .is_end_event = mmio_event_end, + .decode_key = mmio_event_decode_key, + .name = "MMIO Access" +}; + + /* The time of emulation pio access is from kvm_pio to kvm_entry. */ +static void ioport_event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = evsel__intval(evsel, sample, "port"); + key->info = evsel__intval(evsel, sample, "rw"); +} + +static bool ioport_event_begin(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (evsel__name_is(evsel, "kvm:kvm_pio")) { + ioport_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool ioport_event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + scnprintf(decode, KVM_EVENT_NAME_LEN, "%#llx:%s", + (unsigned long long)key->key, + key->info ? "POUT" : "PIN"); +} + +static const struct kvm_events_ops ioport_events = { + .is_begin_event = ioport_event_begin, + .is_end_event = ioport_event_end, + .decode_key = ioport_event_decode_key, + .name = "IO Port Access" +}; + + /* The time of emulation msr is from kvm_msr to kvm_entry. */ +static void msr_event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->key = evsel__intval(evsel, sample, "ecx"); + key->info = evsel__intval(evsel, sample, "write"); +} + +static bool msr_event_begin(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (evsel__name_is(evsel, "kvm:kvm_msr")) { + msr_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +static bool msr_event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +static void msr_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + scnprintf(decode, KVM_EVENT_NAME_LEN, "%#llx:%s", + (unsigned long long)key->key, + key->info ? "W" : "R"); +} + +static const struct kvm_events_ops msr_events = { + .is_begin_event = msr_event_begin, + .is_end_event = msr_event_end, + .decode_key = msr_event_decode_key, + .name = "MSR Access" +}; + +static const char * const __kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + "kvm:kvm_mmio", + "kvm:kvm_pio", + "kvm:kvm_msr", + NULL, +}; + +static const struct kvm_reg_events_ops __kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { .name = "mmio", .ops = &mmio_events }, + { .name = "ioport", .ops = &ioport_events }, + { .name = "msr", .ops = &msr_events }, + { NULL, NULL }, +}; + +static const char * const __kvm_skip_events[] = { + "HLT", + NULL, +}; + +int __cpu_isa_init_x86(struct perf_kvm_stat *kvm, const char *cpuid) +{ + if (strstr(cpuid, "Intel")) { + kvm->exit_reasons = vmx_exit_reasons; + kvm->exit_reasons_isa = "VMX"; + } else if (strstr(cpuid, "AMD") || strstr(cpuid, "Hygon")) { + kvm->exit_reasons = svm_exit_reasons; + kvm->exit_reasons_isa = "SVM"; + } else + return -ENOTSUP; + + return 0; +} + +/* + * After KVM supports PEBS for guest on Intel platforms + * (https://lore.kernel.org/all/20220411101946.20262-1-likexu@tencent.com/), + * host loses the capability to sample guest with PEBS since all PEBS related + * MSRs are switched to guest value after vm-entry, like IA32_DS_AREA MSR is + * switched to guest GVA at vm-entry. This would lead to "perf kvm record" + * fails to sample guest on Intel platforms since "cycles:P" event is used to + * sample guest by default. + * + * So, to avoid this issue explicitly use "cycles" instead of "cycles:P" event + * by default to sample guest on Intel platforms. + */ +int __kvm_add_default_arch_event_x86(int *argc, const char **argv) +{ + const char **tmp; + bool event = false; + int ret = 0, i, j = *argc; + + const struct option event_options[] = { + OPT_BOOLEAN('e', "event", &event, NULL), + OPT_BOOLEAN(0, "pfm-events", &event, NULL), + OPT_END() + }; + + if (!x86__is_intel_cpu()) + return 0; + + tmp = calloc(j + 1, sizeof(char *)); + if (!tmp) + return -ENOMEM; + + for (i = 0; i < j; i++) + tmp[i] = argv[i]; + + parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN); + if (!event) { + argv[j++] = STRDUP_FAIL_EXIT("-e"); + argv[j++] = STRDUP_FAIL_EXIT("cycles"); + *argc += 2; + } + + free(tmp); + return 0; + +EXIT: + free(tmp); + return ret; +} + +const char * const *__kvm_events_tp_x86(void) +{ + return __kvm_events_tp; +} + +const struct kvm_reg_events_ops *__kvm_reg_events_ops_x86(void) +{ + return __kvm_reg_events_ops; +} + +const char * const *__kvm_skip_events_x86(void) +{ + return __kvm_skip_events; +} diff --git a/tools/perf/util/kvm-stat-arch/riscv_trap_types.h b/tools/perf/util/kvm-stat-arch/riscv_trap_types.h new file mode 100644 index 000000000000..aa5d24fab4ee --- /dev/null +++ b/tools/perf/util/kvm-stat-arch/riscv_trap_types.h @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef ARCH_PERF_RISCV_TRAP_TYPES_H +#define ARCH_PERF_RISCV_TRAP_TYPES_H + +/* Exception cause high bit - is an interrupt if set */ +#define CAUSE_IRQ_FLAG(xlen) (_AC(1, UL) << (xlen - 1)) + +/* Interrupt causes (minus the high bit) */ +#define IRQ_S_SOFT 1 +#define IRQ_VS_SOFT 2 +#define IRQ_M_SOFT 3 +#define IRQ_S_TIMER 5 +#define IRQ_VS_TIMER 6 +#define IRQ_M_TIMER 7 +#define IRQ_S_EXT 9 +#define IRQ_VS_EXT 10 +#define IRQ_M_EXT 11 +#define IRQ_S_GEXT 12 +#define IRQ_PMU_OVF 13 + +/* Exception causes */ +#define EXC_INST_MISALIGNED 0 +#define EXC_INST_ACCESS 1 +#define EXC_INST_ILLEGAL 2 +#define EXC_BREAKPOINT 3 +#define EXC_LOAD_MISALIGNED 4 +#define EXC_LOAD_ACCESS 5 +#define EXC_STORE_MISALIGNED 6 +#define EXC_STORE_ACCESS 7 +#define EXC_SYSCALL 8 +#define EXC_HYPERVISOR_SYSCALL 9 +#define EXC_SUPERVISOR_SYSCALL 10 +#define EXC_INST_PAGE_FAULT 12 +#define EXC_LOAD_PAGE_FAULT 13 +#define EXC_STORE_PAGE_FAULT 15 +#define EXC_INST_GUEST_PAGE_FAULT 20 +#define EXC_LOAD_GUEST_PAGE_FAULT 21 +#define EXC_VIRTUAL_INST_FAULT 22 +#define EXC_STORE_GUEST_PAGE_FAULT 23 + +#define TRAP(x) { x, #x } + +#define kvm_riscv_trap_class \ + TRAP(IRQ_S_SOFT), TRAP(IRQ_VS_SOFT), TRAP(IRQ_M_SOFT), \ + TRAP(IRQ_S_TIMER), TRAP(IRQ_VS_TIMER), TRAP(IRQ_M_TIMER), \ + TRAP(IRQ_S_EXT), TRAP(IRQ_VS_EXT), TRAP(IRQ_M_EXT), \ + TRAP(IRQ_S_GEXT), TRAP(IRQ_PMU_OVF), \ + TRAP(EXC_INST_MISALIGNED), TRAP(EXC_INST_ACCESS), TRAP(EXC_INST_ILLEGAL), \ + TRAP(EXC_BREAKPOINT), TRAP(EXC_LOAD_MISALIGNED), TRAP(EXC_LOAD_ACCESS), \ + TRAP(EXC_STORE_MISALIGNED), TRAP(EXC_STORE_ACCESS), TRAP(EXC_SYSCALL), \ + TRAP(EXC_HYPERVISOR_SYSCALL), TRAP(EXC_SUPERVISOR_SYSCALL), \ + TRAP(EXC_INST_PAGE_FAULT), TRAP(EXC_LOAD_PAGE_FAULT), \ + TRAP(EXC_STORE_PAGE_FAULT), TRAP(EXC_INST_GUEST_PAGE_FAULT), \ + TRAP(EXC_LOAD_GUEST_PAGE_FAULT), TRAP(EXC_VIRTUAL_INST_FAULT), \ + TRAP(EXC_STORE_GUEST_PAGE_FAULT) + +#endif /* ARCH_PERF_RISCV_TRAP_TYPES_H */ diff --git a/tools/perf/util/kvm-stat.c b/tools/perf/util/kvm-stat.c index 38ace736db5c..27f16810498c 100644 --- a/tools/perf/util/kvm-stat.c +++ b/tools/perf/util/kvm-stat.c @@ -2,20 +2,23 @@ #include "debug.h" #include "evsel.h" #include "kvm-stat.h" - -#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) +#include <dwarf-regs.h> bool kvm_exit_event(struct evsel *evsel) { - return evsel__name_is(evsel, kvm_exit_trace); + uint16_t e_machine = evsel__e_machine(evsel, /*e_flags=*/NULL); + + return evsel__name_is(evsel, kvm_exit_trace(e_machine)); } void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { + uint16_t e_machine = evsel__e_machine(evsel, /*e_flags=*/NULL); + key->info = 0; - key->key = evsel__intval(evsel, sample, kvm_exit_reason); + key->key = evsel__intval(evsel, sample, kvm_exit_reason(e_machine)); } @@ -32,7 +35,9 @@ bool exit_event_begin(struct evsel *evsel, bool kvm_entry_event(struct evsel *evsel) { - return evsel__name_is(evsel, kvm_entry_trace); + uint16_t e_machine = evsel__e_machine(evsel, /*e_flags=*/NULL); + + return evsel__name_is(evsel, kvm_entry_trace(e_machine)); } bool exit_event_end(struct evsel *evsel, @@ -67,4 +72,202 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm, scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", exit_reason); } -#endif +int setup_kvm_events_tp(struct perf_kvm_stat *kvm, uint16_t e_machine) +{ + switch (e_machine) { + case EM_PPC: + case EM_PPC64: + return __setup_kvm_events_tp_powerpc(kvm); + default: + return 0; + } +} + +int cpu_isa_init(struct perf_kvm_stat *kvm, uint16_t e_machine, const char *cpuid) +{ + switch (e_machine) { + case EM_AARCH64: + return __cpu_isa_init_arm64(kvm); + case EM_LOONGARCH: + return __cpu_isa_init_loongarch(kvm); + case EM_PPC: + case EM_PPC64: + return __cpu_isa_init_powerpc(kvm); + case EM_RISCV: + return __cpu_isa_init_riscv(kvm); + case EM_S390: + return __cpu_isa_init_s390(kvm, cpuid); + case EM_X86_64: + case EM_386: + return __cpu_isa_init_x86(kvm, cpuid); + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return -1; + } +} + +const char *vcpu_id_str(uint16_t e_machine) +{ + switch (e_machine) { + case EM_AARCH64: + case EM_RISCV: + case EM_S390: + return "id"; + case EM_LOONGARCH: + case EM_PPC: + case EM_PPC64: + case EM_X86_64: + case EM_386: + return "vcpu_id"; + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return NULL; + } +} + +const char *kvm_exit_reason(uint16_t e_machine) +{ + switch (e_machine) { + case EM_AARCH64: + return "ret"; + case EM_LOONGARCH: + return "reason"; + case EM_PPC: + case EM_PPC64: + return "trap"; + case EM_RISCV: + return "scause"; + case EM_S390: + return "icptcode"; + case EM_X86_64: + case EM_386: + return "exit_reason"; + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return NULL; + } +} + +const char *kvm_entry_trace(uint16_t e_machine) +{ + switch (e_machine) { + case EM_AARCH64: + case EM_RISCV: + case EM_X86_64: + case EM_386: + return "kvm:kvm_entry"; + case EM_LOONGARCH: + return "kvm:kvm_enter"; + case EM_PPC: + case EM_PPC64: + return "kvm_hv:kvm_guest_enter"; + case EM_S390: + return "kvm:kvm_s390_sie_enter"; + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return NULL; + } +} + +const char *kvm_exit_trace(uint16_t e_machine) +{ + switch (e_machine) { + case EM_AARCH64: + case EM_LOONGARCH: + case EM_RISCV: + case EM_X86_64: + case EM_386: + return "kvm:kvm_exit"; + case EM_PPC: + case EM_PPC64: + return "kvm_hv:kvm_guest_exit"; + case EM_S390: + return "kvm:kvm_s390_sie_exit"; + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return NULL; + } +} + +const char * const *kvm_events_tp(uint16_t e_machine) +{ + switch (e_machine) { + case EM_AARCH64: + return __kvm_events_tp_arm64(); + case EM_LOONGARCH: + return __kvm_events_tp_loongarch(); + case EM_PPC: + case EM_PPC64: + return __kvm_events_tp_powerpc(); + case EM_RISCV: + return __kvm_events_tp_riscv(); + case EM_S390: + return __kvm_events_tp_s390(); + case EM_X86_64: + case EM_386: + return __kvm_events_tp_x86(); + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return NULL; + } +} + +const struct kvm_reg_events_ops *kvm_reg_events_ops(uint16_t e_machine) +{ + switch (e_machine) { + case EM_AARCH64: + return __kvm_reg_events_ops_arm64(); + case EM_LOONGARCH: + return __kvm_reg_events_ops_loongarch(); + case EM_PPC: + case EM_PPC64: + return __kvm_reg_events_ops_powerpc(); + case EM_RISCV: + return __kvm_reg_events_ops_riscv(); + case EM_S390: + return __kvm_reg_events_ops_s390(); + case EM_X86_64: + case EM_386: + return __kvm_reg_events_ops_x86(); + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return NULL; + } +} + +const char * const *kvm_skip_events(uint16_t e_machine) +{ + switch (e_machine) { + case EM_AARCH64: + return __kvm_skip_events_arm64(); + case EM_LOONGARCH: + return __kvm_skip_events_loongarch(); + case EM_PPC: + case EM_PPC64: + return __kvm_skip_events_powerpc(); + case EM_RISCV: + return __kvm_skip_events_riscv(); + case EM_S390: + return __kvm_skip_events_s390(); + case EM_X86_64: + case EM_386: + return __kvm_skip_events_x86(); + default: + pr_err("Unsupported kvm-stat host %d\n", e_machine); + return NULL; + } +} + +int kvm_add_default_arch_event(uint16_t e_machine, int *argc, const char **argv) +{ + switch (e_machine) { + case EM_PPC: + case EM_PPC64: + return __kvm_add_default_arch_event_powerpc(argc, argv); + case EM_X86_64: + case EM_386: + return __kvm_add_default_arch_event_x86(argc, argv); + default: + return 0; + } +} diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 4249542544bb..4a998aaece5d 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -2,14 +2,13 @@ #ifndef __PERF_KVM_STAT_H #define __PERF_KVM_STAT_H -#ifdef HAVE_KVM_STAT_SUPPORT - #include "tool.h" #include "sort.h" #include "stat.h" #include "symbol.h" #include "record.h" +#include <errno.h> #include <stdlib.h> #include <linux/zalloc.h> @@ -66,7 +65,7 @@ struct kvm_events_ops { struct event_key *key); bool (*is_end_event)(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); - struct child_event_ops *child_ops; + const struct child_event_ops *child_ops; void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key, char *decode); const char *name; @@ -94,7 +93,7 @@ struct perf_kvm_stat { struct exit_reasons_table *exit_reasons; const char *exit_reasons_isa; - struct kvm_events_ops *events_ops; + const struct kvm_events_ops *events_ops; u64 total_time; u64 total_count; @@ -112,10 +111,10 @@ struct perf_kvm_stat { struct kvm_reg_events_ops { const char *name; - struct kvm_events_ops *ops; + const struct kvm_events_ops *ops; }; -#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) +#ifdef HAVE_LIBTRACEEVENT void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, @@ -129,11 +128,9 @@ bool exit_event_end(struct evsel *evsel, void exit_event_decode_key(struct perf_kvm_stat *kvm, struct event_key *key, char *decode); -#endif bool kvm_exit_event(struct evsel *evsel); bool kvm_entry_event(struct evsel *evsel); -int setup_kvm_events_tp(struct perf_kvm_stat *kvm); #define define_exit_reasons_table(name, symbols) \ static struct exit_reasons_table name[] = { \ @@ -143,15 +140,60 @@ int setup_kvm_events_tp(struct perf_kvm_stat *kvm); /* * arch specific callbacks and data structures */ -int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid); +int setup_kvm_events_tp(struct perf_kvm_stat *kvm, uint16_t e_machine); +int __setup_kvm_events_tp_powerpc(struct perf_kvm_stat *kvm); + +int cpu_isa_init(struct perf_kvm_stat *kvm, uint16_t e_machine, const char *cpuid); +int __cpu_isa_init_arm64(struct perf_kvm_stat *kvm); +int __cpu_isa_init_loongarch(struct perf_kvm_stat *kvm); +int __cpu_isa_init_powerpc(struct perf_kvm_stat *kvm); +int __cpu_isa_init_riscv(struct perf_kvm_stat *kvm); +int __cpu_isa_init_s390(struct perf_kvm_stat *kvm, const char *cpuid); +int __cpu_isa_init_x86(struct perf_kvm_stat *kvm, const char *cpuid); + +const char *vcpu_id_str(uint16_t e_machine); +const char *kvm_exit_reason(uint16_t e_machine); +const char *kvm_entry_trace(uint16_t e_machine); +const char *kvm_exit_trace(uint16_t e_machine); + +const char * const *kvm_events_tp(uint16_t e_machine); +const char * const *__kvm_events_tp_arm64(void); +const char * const *__kvm_events_tp_loongarch(void); +const char * const *__kvm_events_tp_powerpc(void); +const char * const *__kvm_events_tp_riscv(void); +const char * const *__kvm_events_tp_s390(void); +const char * const *__kvm_events_tp_x86(void); + +const struct kvm_reg_events_ops *kvm_reg_events_ops(uint16_t e_machine); +const struct kvm_reg_events_ops *__kvm_reg_events_ops_arm64(void); +const struct kvm_reg_events_ops *__kvm_reg_events_ops_loongarch(void); +const struct kvm_reg_events_ops *__kvm_reg_events_ops_powerpc(void); +const struct kvm_reg_events_ops *__kvm_reg_events_ops_riscv(void); +const struct kvm_reg_events_ops *__kvm_reg_events_ops_s390(void); +const struct kvm_reg_events_ops *__kvm_reg_events_ops_x86(void); + +const char * const *kvm_skip_events(uint16_t e_machine); +const char * const *__kvm_skip_events_arm64(void); +const char * const *__kvm_skip_events_loongarch(void); +const char * const *__kvm_skip_events_powerpc(void); +const char * const *__kvm_skip_events_riscv(void); +const char * const *__kvm_skip_events_s390(void); +const char * const *__kvm_skip_events_x86(void); + +int kvm_add_default_arch_event(uint16_t e_machine, int *argc, const char **argv); +int __kvm_add_default_arch_event_powerpc(int *argc, const char **argv); +int __kvm_add_default_arch_event_x86(int *argc, const char **argv); + +#else /* !HAVE_LIBTRACEEVENT */ + +static inline int kvm_add_default_arch_event(uint16_t e_machine __maybe_unused, + int *argc __maybe_unused, + const char **argv __maybe_unused) +{ + return 0; +} -extern const char *kvm_events_tp[]; -extern struct kvm_reg_events_ops kvm_reg_events_ops[]; -extern const char * const kvm_skip_events[]; -extern const char *vcpu_id_str; -extern const char *kvm_exit_reason; -extern const char *kvm_entry_trace; -extern const char *kvm_exit_trace; +#endif /* HAVE_LIBTRACEEVENT */ static inline struct kvm_info *kvm_info__get(struct kvm_info *ki) { @@ -185,10 +227,14 @@ static inline struct kvm_info *kvm_info__new(void) return ki; } -#else /* HAVE_KVM_STAT_SUPPORT */ -// We use this unconditionally in hists__findnew_entry() and hist_entry__delete() -#define kvm_info__zput(ki) do { } while (0) -#endif /* HAVE_KVM_STAT_SUPPORT */ +#define STRDUP_FAIL_EXIT(s) \ + ({ char *_p; \ + _p = strdup(s); \ + if (!_p) { \ + ret = -ENOMEM; \ + goto EXIT; \ + } \ + _p; \ + }) -extern int kvm_add_default_arch_event(int *argc, const char **argv); #endif /* __PERF_KVM_STAT_H */ diff --git a/tools/perf/util/libbfd.c b/tools/perf/util/libbfd.c new file mode 100644 index 000000000000..c1c12308cc12 --- /dev/null +++ b/tools/perf/util/libbfd.c @@ -0,0 +1,645 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "libbfd.h" +#include "annotate.h" +#include "bpf-event.h" +#include "bpf-utils.h" +#include "debug.h" +#include "dso.h" +#include "env.h" +#include "map.h" +#include "srcline.h" +#include "symbol.h" +#include "symbol_conf.h" +#include "util.h" +#include <tools/dis-asm-compat.h> +#ifdef HAVE_LIBBPF_SUPPORT +#include <bpf/bpf.h> +#include <bpf/btf.h> +#endif +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#define PACKAGE "perf" +#include <bfd.h> + +/* + * Implement addr2line using libbfd. + */ +struct a2l_data { + const char *input; + u64 addr; + + bool found; + const char *filename; + const char *funcname; + unsigned int line; + + bfd *abfd; + asymbol **syms; +}; + +static bool perf_bfd_lock(void *bfd_mutex) +{ + mutex_lock(bfd_mutex); + return true; +} + +static bool perf_bfd_unlock(void *bfd_mutex) +{ + mutex_unlock(bfd_mutex); + return true; +} + +static void perf_bfd_init(void) +{ + static struct mutex bfd_mutex; + + mutex_init_recursive(&bfd_mutex); + + if (bfd_init() != BFD_INIT_MAGIC) { + pr_err("Error initializing libbfd\n"); + return; + } + if (!bfd_thread_init(perf_bfd_lock, perf_bfd_unlock, &bfd_mutex)) + pr_err("Error initializing libbfd threading\n"); +} + +static void ensure_bfd_init(void) +{ + static pthread_once_t bfd_init_once = PTHREAD_ONCE_INIT; + + pthread_once(&bfd_init_once, perf_bfd_init); +} + +static int bfd_error(const char *string) +{ + const char *errmsg; + + errmsg = bfd_errmsg(bfd_get_error()); + fflush(stdout); + + if (string) + pr_debug("%s: %s\n", string, errmsg); + else + pr_debug("%s\n", errmsg); + + return -1; +} + +static int slurp_symtab(bfd *abfd, struct a2l_data *a2l) +{ + long storage; + long symcount; + asymbol **syms; + bfd_boolean dynamic = FALSE; + + if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0) + return bfd_error(bfd_get_filename(abfd)); + + storage = bfd_get_symtab_upper_bound(abfd); + if (storage == 0L) { + storage = bfd_get_dynamic_symtab_upper_bound(abfd); + dynamic = TRUE; + } + if (storage < 0L) + return bfd_error(bfd_get_filename(abfd)); + + syms = malloc(storage); + if (dynamic) + symcount = bfd_canonicalize_dynamic_symtab(abfd, syms); + else + symcount = bfd_canonicalize_symtab(abfd, syms); + + if (symcount < 0) { + free(syms); + return bfd_error(bfd_get_filename(abfd)); + } + + a2l->syms = syms; + return 0; +} + +static void find_address_in_section(bfd *abfd, asection *section, void *data) +{ + bfd_vma pc, vma; + bfd_size_type size; + struct a2l_data *a2l = data; + flagword flags; + + if (a2l->found) + return; + +#ifdef bfd_get_section_flags + flags = bfd_get_section_flags(abfd, section); +#else + flags = bfd_section_flags(section); +#endif + if ((flags & SEC_ALLOC) == 0) + return; + + pc = a2l->addr; +#ifdef bfd_get_section_vma + vma = bfd_get_section_vma(abfd, section); +#else + vma = bfd_section_vma(section); +#endif +#ifdef bfd_get_section_size + size = bfd_get_section_size(section); +#else + size = bfd_section_size(section); +#endif + + if (pc < vma || pc >= vma + size) + return; + + a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma, + &a2l->filename, &a2l->funcname, + &a2l->line); + + if (a2l->filename && !strlen(a2l->filename)) + a2l->filename = NULL; +} + +static struct a2l_data *addr2line_init(const char *path) +{ + bfd *abfd; + struct a2l_data *a2l = NULL; + + ensure_bfd_init(); + abfd = bfd_openr(path, NULL); + if (abfd == NULL) + return NULL; + + if (!bfd_check_format(abfd, bfd_object)) + goto out; + + a2l = zalloc(sizeof(*a2l)); + if (a2l == NULL) + goto out; + + a2l->abfd = abfd; + a2l->input = strdup(path); + if (a2l->input == NULL) + goto out; + + if (slurp_symtab(abfd, a2l)) + goto out; + + return a2l; + +out: + if (a2l) { + zfree((char **)&a2l->input); + free(a2l); + } + bfd_close(abfd); + return NULL; +} + +static void addr2line_cleanup(struct a2l_data *a2l) +{ + if (a2l->abfd) + bfd_close(a2l->abfd); + zfree((char **)&a2l->input); + zfree(&a2l->syms); + free(a2l); +} + +static int inline_list__append_dso_a2l(struct dso *dso, + struct inline_node *node, + struct symbol *sym) +{ + struct a2l_data *a2l = dso__a2l(dso); + struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname); + char *srcline = NULL; + + if (a2l->filename) + srcline = srcline_from_fileline(a2l->filename, a2l->line); + + return inline_list__append(inline_sym, srcline, node); +} + +int libbfd__addr2line(const char *dso_name, u64 addr, + char **file, unsigned int *line, struct dso *dso, + bool unwind_inlines, struct inline_node *node, + struct symbol *sym) +{ + int ret = 0; + struct a2l_data *a2l = dso__a2l(dso); + + if (!a2l) { + a2l = addr2line_init(dso_name); + dso__set_a2l(dso, a2l); + } + + if (a2l == NULL) { + if (!symbol_conf.addr2line_disable_warn) + pr_warning("addr2line_init failed for %s\n", dso_name); + return 0; + } + + a2l->addr = addr; + a2l->found = false; + + bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l); + + if (!a2l->found) + return 0; + + if (unwind_inlines) { + int cnt = 0; + + if (node && inline_list__append_dso_a2l(dso, node, sym)) + return 0; + + while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, + &a2l->funcname, &a2l->line) && + cnt++ < MAX_INLINE_NEST) { + + if (a2l->filename && !strlen(a2l->filename)) + a2l->filename = NULL; + + if (node != NULL) { + if (inline_list__append_dso_a2l(dso, node, sym)) + return 0; + // found at least one inline frame + ret = 1; + } + } + } + + if (file) { + *file = a2l->filename ? strdup(a2l->filename) : NULL; + ret = *file ? 1 : 0; + } + + if (line) + *line = a2l->line; + + return ret; +} + +void dso__free_a2l_libbfd(struct dso *dso) +{ + struct a2l_data *a2l = dso__a2l(dso); + + if (!a2l) + return; + + addr2line_cleanup(a2l); + + dso__set_a2l(dso, NULL); +} + +static int bfd_symbols__cmpvalue(const void *a, const void *b) +{ + const asymbol *as = *(const asymbol **)a, *bs = *(const asymbol **)b; + + if (bfd_asymbol_value(as) != bfd_asymbol_value(bs)) + return bfd_asymbol_value(as) - bfd_asymbol_value(bs); + + return bfd_asymbol_name(as)[0] - bfd_asymbol_name(bs)[0]; +} + +static int bfd2elf_binding(asymbol *symbol) +{ + if (symbol->flags & BSF_WEAK) + return STB_WEAK; + if (symbol->flags & BSF_GLOBAL) + return STB_GLOBAL; + if (symbol->flags & BSF_LOCAL) + return STB_LOCAL; + return -1; +} + +int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) +{ + int err = -1; + long symbols_size, symbols_count, i; + asection *section; + asymbol **symbols, *sym; + struct symbol *symbol; + bfd *abfd; + u64 start, len; + + ensure_bfd_init(); + abfd = bfd_openr(debugfile, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, + dso__long_name(dso)); + goto out_close; + } + + if (bfd_get_flavour(abfd) == bfd_target_elf_flavour) + goto out_close; + + symbols_size = bfd_get_symtab_upper_bound(abfd); + if (symbols_size == 0) { + bfd_close(abfd); + return 0; + } + + if (symbols_size < 0) + goto out_close; + + symbols = malloc(symbols_size); + if (!symbols) + goto out_close; + + symbols_count = bfd_canonicalize_symtab(abfd, symbols); + if (symbols_count < 0) + goto out_free; + + section = bfd_get_section_by_name(abfd, ".text"); + if (section) { + for (i = 0; i < symbols_count; ++i) { + if (!strcmp(bfd_asymbol_name(symbols[i]), "__ImageBase") || + !strcmp(bfd_asymbol_name(symbols[i]), "__image_base__")) + break; + } + if (i < symbols_count) { + /* PE symbols can only have 4 bytes, so use .text high bits */ + u64 text_offset = (section->vma - (u32)section->vma) + + (u32)bfd_asymbol_value(symbols[i]); + dso__set_text_offset(dso, text_offset); + dso__set_text_end(dso, (section->vma - text_offset) + section->size); + } else { + dso__set_text_offset(dso, section->vma - section->filepos); + dso__set_text_end(dso, section->filepos + section->size); + } + } + + qsort(symbols, symbols_count, sizeof(asymbol *), bfd_symbols__cmpvalue); + +#ifdef bfd_get_section +#define bfd_asymbol_section bfd_get_section +#endif + for (i = 0; i < symbols_count; ++i) { + sym = symbols[i]; + section = bfd_asymbol_section(sym); + if (bfd2elf_binding(sym) < 0) + continue; + + while (i + 1 < symbols_count && + bfd_asymbol_section(symbols[i + 1]) == section && + bfd2elf_binding(symbols[i + 1]) < 0) + i++; + + if (i + 1 < symbols_count && + bfd_asymbol_section(symbols[i + 1]) == section) + len = symbols[i + 1]->value - sym->value; + else + len = section->size - sym->value; + + start = bfd_asymbol_value(sym) - dso__text_offset(dso); + symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC, + bfd_asymbol_name(sym)); + if (!symbol) + goto out_free; + + symbols__insert(dso__symbols(dso), symbol); + } +#ifdef bfd_get_section +#undef bfd_asymbol_section +#endif + + symbols__fixup_end(dso__symbols(dso), false); + symbols__fixup_duplicate(dso__symbols(dso)); + dso__set_adjust_symbols(dso, true); + + err = 0; +out_free: + free(symbols); +out_close: + bfd_close(abfd); + return err; +} + +int libbfd__read_build_id(const char *filename, struct build_id *bid) +{ + size_t size = sizeof(bid->data); + int err = -1, fd; + bfd *abfd; + + if (!filename) + return -EFAULT; + + errno = 0; + if (!is_regular_file(filename)) + return errno == 0 ? -EWOULDBLOCK : -errno; + + fd = open(filename, O_RDONLY); + if (fd < 0) + return -1; + + ensure_bfd_init(); + abfd = bfd_fdopenr(filename, /*target=*/NULL, fd); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); + goto out_close; + } + + if (!abfd->build_id || abfd->build_id->size > size) + goto out_close; + + memcpy(bid->data, abfd->build_id->data, abfd->build_id->size); + memset(bid->data + abfd->build_id->size, 0, size - abfd->build_id->size); + err = bid->size = abfd->build_id->size; + +out_close: + bfd_close(abfd); + return err; +} + +int libbfd_filename__read_debuglink(const char *filename, char *debuglink, + size_t size) +{ + int err = -1; + asection *section; + bfd *abfd; + + ensure_bfd_init(); + abfd = bfd_openr(filename, NULL); + if (!abfd) + return -1; + + if (!bfd_check_format(abfd, bfd_object)) { + pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); + goto out_close; + } + + section = bfd_get_section_by_name(abfd, ".gnu_debuglink"); + if (!section) + goto out_close; + + if (section->size > size) + goto out_close; + + if (!bfd_get_section_contents(abfd, section, debuglink, 0, + section->size)) + goto out_close; + + err = 0; + +out_close: + bfd_close(abfd); + return err; +} + +int symbol__disassemble_bpf_libbfd(struct symbol *sym __maybe_unused, + struct annotate_args *args __maybe_unused) +{ +#ifdef HAVE_LIBBPF_SUPPORT + struct annotation *notes = symbol__annotation(sym); + struct bpf_prog_linfo *prog_linfo = NULL; + struct bpf_prog_info_node *info_node; + int len = sym->end - sym->start; + disassembler_ftype disassemble; + struct map *map = args->ms->map; + struct perf_bpil *info_linear; + struct disassemble_info info; + struct dso *dso = map__dso(map); + int pc = 0, count, sub_id; + struct btf *btf = NULL; + char tpath[PATH_MAX]; + size_t buf_size; + int nr_skip = 0; + char *buf; + bfd *bfdf; + int ret; + FILE *s; + + if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO) + return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE; + + pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__, + sym->name, sym->start, sym->end - sym->start); + + memset(tpath, 0, sizeof(tpath)); + perf_exe(tpath, sizeof(tpath)); + + ensure_bfd_init(); + bfdf = bfd_openr(tpath, NULL); + if (bfdf == NULL) + abort(); + + if (!bfd_check_format(bfdf, bfd_object)) + abort(); + + s = open_memstream(&buf, &buf_size); + if (!s) { + ret = errno; + goto out; + } + init_disassemble_info_compat(&info, s, + (fprintf_ftype) fprintf, + fprintf_styled); + info.arch = bfd_get_arch(bfdf); + info.mach = bfd_get_mach(bfdf); + + info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env, + dso__bpf_prog(dso)->id); + if (!info_node) { + ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF; + goto out; + } + info_linear = info_node->info_linear; + sub_id = dso__bpf_prog(dso)->sub_id; + + info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns); + info.buffer_length = info_linear->info.jited_prog_len; + + if (info_linear->info.nr_line_info) + prog_linfo = bpf_prog_linfo__new(&info_linear->info); + + if (info_linear->info.btf_id) { + struct btf_node *node; + + node = perf_env__find_btf(dso__bpf_prog(dso)->env, + info_linear->info.btf_id); + if (node) + btf = btf__new((__u8 *)(node->data), + node->data_size); + } + + disassemble_init_for_target(&info); + +#ifdef DISASM_FOUR_ARGS_SIGNATURE + disassemble = disassembler(info.arch, + bfd_big_endian(bfdf), + info.mach, + bfdf); +#else + disassemble = disassembler(bfdf); +#endif + if (disassemble == NULL) + abort(); + + fflush(s); + do { + const struct bpf_line_info *linfo = NULL; + struct disasm_line *dl; + size_t prev_buf_size; + const char *srcline; + u64 addr; + + addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id]; + count = disassemble(pc, &info); + + if (prog_linfo) + linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, + addr, sub_id, + nr_skip); + + if (linfo && btf) { + srcline = btf__name_by_offset(btf, linfo->line_off); + nr_skip++; + } else + srcline = NULL; + + fprintf(s, "\n"); + prev_buf_size = buf_size; + fflush(s); + + if (!annotate_opts.hide_src_code && srcline) { + args->offset = -1; + args->line = strdup(srcline); + args->line_nr = 0; + args->fileloc = NULL; + args->ms->sym = sym; + dl = disasm_line__new(args); + if (dl) { + annotation_line__add(&dl->al, + ¬es->src->source); + } + } + + args->offset = pc; + args->line = buf + prev_buf_size; + args->line_nr = 0; + args->fileloc = NULL; + args->ms->sym = sym; + dl = disasm_line__new(args); + if (dl) + annotation_line__add(&dl->al, ¬es->src->source); + + pc += count; + } while (count > 0 && pc < len); + + ret = 0; +out: + free(prog_linfo); + btf__free(btf); + fclose(s); + bfd_close(bfdf); + return ret; +#else + return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF; +#endif +} diff --git a/tools/perf/util/libbfd.h b/tools/perf/util/libbfd.h new file mode 100644 index 000000000000..953886f3d62f --- /dev/null +++ b/tools/perf/util/libbfd.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_LIBBFD_H +#define __PERF_LIBBFD_H + +#include <linux/compiler.h> +#include <linux/types.h> +#include <stdbool.h> +#include <stddef.h> + +struct annotate_args; +struct build_id; +struct dso; +struct inline_node; +struct symbol; + +#ifdef HAVE_LIBBFD_SUPPORT +int libbfd__addr2line(const char *dso_name, u64 addr, + char **file, unsigned int *line, struct dso *dso, + bool unwind_inlines, struct inline_node *node, + struct symbol *sym); + + +void dso__free_a2l_libbfd(struct dso *dso); + +int symbol__disassemble_libbfd(const char *filename, struct symbol *sym, + struct annotate_args *args); + +int libbfd__read_build_id(const char *filename, struct build_id *bid); + +int libbfd_filename__read_debuglink(const char *filename, char *debuglink, size_t size); + +int symbol__disassemble_bpf_libbfd(struct symbol *sym, struct annotate_args *args); + +#else // !defined(HAVE_LIBBFD_SUPPORT) +#include "annotate.h" + +static inline int libbfd__addr2line(const char *dso_name __always_unused, + u64 addr __always_unused, + char **file __always_unused, + unsigned int *line __always_unused, + struct dso *dso __always_unused, + bool unwind_inlines __always_unused, + struct inline_node *node __always_unused, + struct symbol *sym __always_unused) +{ + return -1; +} + + +static inline void dso__free_a2l_libbfd(struct dso *dso __always_unused) +{ +} + +static inline int symbol__disassemble_libbfd(const char *filename __always_unused, + struct symbol *sym __always_unused, + struct annotate_args *args __always_unused) +{ + return -1; +} + +static inline int libbfd__read_build_id(const char *filename __always_unused, + struct build_id *bid __always_unused) +{ + return -1; +} + +static inline int libbfd_filename__read_debuglink(const char *filename __always_unused, + char *debuglink __always_unused, + size_t size __always_unused) +{ + return -1; +} + +static inline int symbol__disassemble_bpf_libbfd(struct symbol *sym __always_unused, + struct annotate_args *args __always_unused) +{ + return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF; +} + +#endif // defined(HAVE_LIBBFD_SUPPORT) + +#endif /* __PERF_LIBBFD_H */ diff --git a/tools/perf/util/libdw.c b/tools/perf/util/libdw.c new file mode 100644 index 000000000000..216977884103 --- /dev/null +++ b/tools/perf/util/libdw.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "dso.h" +#include "libdw.h" +#include "srcline.h" +#include "symbol.h" +#include "dwarf-aux.h" +#include <fcntl.h> +#include <unistd.h> +#include <elfutils/libdwfl.h> + +static const Dwfl_Callbacks offline_callbacks = { + .find_debuginfo = dwfl_standard_find_debuginfo, + .section_address = dwfl_offline_section_address, + .find_elf = dwfl_build_id_find_elf, +}; + +void dso__free_libdw(struct dso *dso) +{ + Dwfl *dwfl = dso__libdw(dso); + + if (dwfl) { + dwfl_end(dwfl); + dso__set_libdw(dso, NULL); + } +} + +struct Dwfl *dso__libdw_dwfl(struct dso *dso) +{ + Dwfl *dwfl = dso__libdw(dso); + const char *dso_name; + Dwfl_Module *mod; + int fd; + + if (dwfl) + return dwfl; + + dso_name = dso__long_name(dso); + /* + * Initialize Dwfl session. + * We need to open the DSO file to report it to libdw. + */ + fd = open(dso_name, O_RDONLY); + if (fd < 0) + return NULL; + + dwfl = dwfl_begin(&offline_callbacks); + if (!dwfl) { + close(fd); + return NULL; + } + + /* + * If the report is successful, the file descriptor fd is consumed + * and closed by the Dwfl. If not, it is not closed. + */ + mod = dwfl_report_offline(dwfl, dso_name, dso_name, fd); + if (!mod) { + dwfl_end(dwfl); + close(fd); + return NULL; + } + + dwfl_report_end(dwfl, /*removed=*/NULL, /*arg=*/NULL); + dso__set_libdw(dso, dwfl); + + return dwfl; +} + +struct libdw_a2l_cb_args { + struct dso *dso; + struct symbol *sym; + struct inline_node *node; + char *leaf_srcline; + bool leaf_srcline_used; +}; + +static int libdw_a2l_cb(Dwarf_Die *die, void *_args) +{ + struct libdw_a2l_cb_args *args = _args; + struct symbol *inline_sym = new_inline_sym(args->dso, args->sym, dwarf_diename(die)); + const char *call_fname = die_get_call_file(die); + char *call_srcline = srcline__unknown; + struct inline_list *ilist; + + if (!inline_sym) + return -ENOMEM; + + /* Assign caller information to the parent. */ + if (call_fname) + call_srcline = srcline_from_fileline(call_fname, die_get_call_lineno(die)); + + list_for_each_entry(ilist, &args->node->val, list) { + if (args->leaf_srcline == ilist->srcline) + args->leaf_srcline_used = false; + else if (ilist->srcline != srcline__unknown) + free(ilist->srcline); + ilist->srcline = call_srcline; + call_srcline = NULL; + break; + } + if (call_srcline && call_srcline != srcline__unknown) + free(call_srcline); + + /* Add this symbol to the chain as the leaf. */ + if (!args->leaf_srcline_used) { + inline_list__append_tail(inline_sym, args->leaf_srcline, args->node); + args->leaf_srcline_used = true; + } else { + inline_list__append_tail(inline_sym, strdup(args->leaf_srcline), args->node); + } + return 0; +} + +int libdw__addr2line(u64 addr, char **file, unsigned int *line_nr, + struct dso *dso, bool unwind_inlines, + struct inline_node *node, struct symbol *sym) +{ + Dwfl *dwfl = dso__libdw_dwfl(dso); + Dwfl_Module *mod; + Dwfl_Line *dwline; + Dwarf_Addr bias; + const char *src; + int lineno = 0; + + if (!dwfl) + return 0; + + mod = dwfl_addrmodule(dwfl, addr); + if (!mod) + return 0; + + /* + * Get/ignore the dwarf information. Determine the bias, difference + * between the regular ELF addr2line addresses and those to use with + * libdw. + */ + if (!dwfl_module_getdwarf(mod, &bias)) + return 0; + + /* Find source line information for the address. */ + dwline = dwfl_module_getsrc(mod, addr + bias); + if (!dwline) + return 0; + + /* Get line information. */ + src = dwfl_lineinfo(dwline, /*addr=*/NULL, &lineno, /*col=*/NULL, /*mtime=*/NULL, + /*length=*/NULL); + + if (file) + *file = src ? strdup(src) : NULL; + if (line_nr) + *line_nr = lineno; + + /* Optionally unwind inline function call chain. */ + if (unwind_inlines && node) { + Dwarf_Addr unused_bias; + Dwarf_Die *cudie = dwfl_module_addrdie(mod, addr + bias, &unused_bias); + struct libdw_a2l_cb_args args = { + .dso = dso, + .sym = sym, + .node = node, + .leaf_srcline = srcline_from_fileline(src ?: "<unknown>", lineno), + }; + + /* Walk from the parent down to the leaf. */ + cu_walk_functions_at(cudie, addr, libdw_a2l_cb, &args); + + if (!args.leaf_srcline_used) + free(args.leaf_srcline); + } + return 1; +} diff --git a/tools/perf/util/libdw.h b/tools/perf/util/libdw.h new file mode 100644 index 000000000000..b12094737415 --- /dev/null +++ b/tools/perf/util/libdw.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef PERF_LIBDW_H +#define PERF_LIBDW_H + +#include <linux/types.h> + +struct dso; +struct inline_node; +struct symbol; + +#ifdef HAVE_LIBDW_SUPPORT +/* + * libdw__addr2line - Convert address to source location using libdw + * @addr: Address to resolve + * @file: Pointer to return filename (caller must free) + * @line_nr: Pointer to return line number + * @dso: The dso struct + * @unwind_inlines: Whether to unwind inline function calls + * @node: Inline node list to append to + * @sym: The symbol associated with the address + * + * This function initializes a Dwfl context for the DSO if not already present, + * finds the source line information for the given address, and optionally + * resolves inline function call chains. + * + * Returns 1 on success (found), 0 on failure (not found). + */ +int libdw__addr2line(u64 addr, char **file, + unsigned int *line_nr, struct dso *dso, + bool unwind_inlines, struct inline_node *node, + struct symbol *sym); + +/* + * dso__free_libdw - Free libdw resources associated with the DSO + * @dso: The dso to free resources for + * + * This function cleans up the Dwfl context used for addr2line lookups. + */ +void dso__free_libdw(struct dso *dso); + +#else /* HAVE_LIBDW_SUPPORT */ + +static inline int libdw__addr2line(u64 addr __maybe_unused, char **file __maybe_unused, + unsigned int *line_nr __maybe_unused, + struct dso *dso __maybe_unused, + bool unwind_inlines __maybe_unused, + struct inline_node *node __maybe_unused, + struct symbol *sym __maybe_unused) +{ + return 0; +} + +static inline void dso__free_libdw(struct dso *dso __maybe_unused) +{ +} +#endif /* HAVE_LIBDW_SUPPORT */ + +#endif /* PERF_LIBDW_H */ diff --git a/tools/perf/util/llvm.c b/tools/perf/util/llvm.c new file mode 100644 index 000000000000..a0deb742a733 --- /dev/null +++ b/tools/perf/util/llvm.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "llvm.h" +#include "annotate.h" +#include "debug.h" +#include "dso.h" +#include "map.h" +#include "namespaces.h" +#include "srcline.h" +#include "symbol.h" +#include <errno.h> +#include <fcntl.h> +#include <unistd.h> +#include <linux/zalloc.h> + +#ifdef HAVE_LIBLLVM_SUPPORT +#include "llvm-c-helpers.h" +#include <llvm-c/Disassembler.h> +#include <llvm-c/Target.h> +#endif + +#ifdef HAVE_LIBLLVM_SUPPORT +static void free_llvm_inline_frames(struct llvm_a2l_frame *inline_frames, + int num_frames) +{ + if (inline_frames != NULL) { + for (int i = 0; i < num_frames; ++i) { + zfree(&inline_frames[i].filename); + zfree(&inline_frames[i].funcname); + } + zfree(&inline_frames); + } +} +#endif + +int llvm__addr2line(const char *dso_name __maybe_unused, u64 addr __maybe_unused, + char **file __maybe_unused, unsigned int *line __maybe_unused, + struct dso *dso __maybe_unused, bool unwind_inlines __maybe_unused, + struct inline_node *node __maybe_unused, struct symbol *sym __maybe_unused) +{ +#ifdef HAVE_LIBLLVM_SUPPORT + struct llvm_a2l_frame *inline_frames = NULL; + int num_frames = llvm_addr2line(dso_name, addr, file, line, + node && unwind_inlines, &inline_frames); + + if (num_frames == 0 || !inline_frames) { + /* Error, or we didn't want inlines. */ + return num_frames; + } + + for (int i = 0; i < num_frames; ++i) { + struct symbol *inline_sym = + new_inline_sym(dso, sym, inline_frames[i].funcname); + char *srcline = NULL; + + if (inline_frames[i].filename) { + srcline = + srcline_from_fileline(inline_frames[i].filename, + inline_frames[i].line); + } + if (inline_list__append(inline_sym, srcline, node) != 0) { + free_llvm_inline_frames(inline_frames, num_frames); + return 0; + } + } + free_llvm_inline_frames(inline_frames, num_frames); + + return num_frames; +#else + return -1; +#endif +} + +#ifdef HAVE_LIBLLVM_SUPPORT +static void init_llvm(void) +{ + static bool init; + + if (!init) { + LLVMInitializeAllTargetInfos(); + LLVMInitializeAllTargetMCs(); + LLVMInitializeAllDisassemblers(); + init = true; + } +} + +/* + * Whenever LLVM wants to resolve an address into a symbol, it calls this + * callback. We don't ever actually _return_ anything (in particular, because + * it puts quotation marks around what we return), but we use this as a hint + * that there is a branch or PC-relative address in the expression that we + * should add some textual annotation for after the instruction. The caller + * will use this information to add the actual annotation. + */ +struct symbol_lookup_storage { + u64 branch_addr; + u64 pcrel_load_addr; +}; + +static const char * +symbol_lookup_callback(void *disinfo, uint64_t value, + uint64_t *ref_type, + uint64_t address __maybe_unused, + const char **ref __maybe_unused) +{ + struct symbol_lookup_storage *storage = disinfo; + + if (*ref_type == LLVMDisassembler_ReferenceType_In_Branch) + storage->branch_addr = value; + else if (*ref_type == LLVMDisassembler_ReferenceType_In_PCrel_Load) + storage->pcrel_load_addr = value; + *ref_type = LLVMDisassembler_ReferenceType_InOut_None; + return NULL; +} +#endif + +int symbol__disassemble_llvm(const char *filename, struct symbol *sym, + struct annotate_args *args __maybe_unused) +{ +#ifdef HAVE_LIBLLVM_SUPPORT + struct annotation *notes = symbol__annotation(sym); + struct map *map = args->ms->map; + struct dso *dso = map__dso(map); + u64 start = map__rip_2objdump(map, sym->start); + /* Malloc-ed buffer containing instructions read from disk. */ + u8 *code_buf = NULL; + /* Pointer to code to be disassembled. */ + const u8 *buf; + u64 buf_len; + u64 pc; + bool is_64bit; + char disasm_buf[2048]; + size_t disasm_len; + struct disasm_line *dl; + LLVMDisasmContextRef disasm = NULL; + struct symbol_lookup_storage storage; + char *line_storage = NULL; + size_t line_storage_len = 0; + int ret = -1; + + if (args->options->objdump_path) + return -1; + + buf = dso__read_symbol(dso, filename, map, sym, + &code_buf, &buf_len, &is_64bit); + if (buf == NULL) + return errno; + + init_llvm(); + if (arch__is_x86(args->arch)) { + const char *triplet = is_64bit ? "x86_64-pc-linux" : "i686-pc-linux"; + + disasm = LLVMCreateDisasm(triplet, &storage, /*tag_type=*/0, + /*get_op_info=*/NULL, symbol_lookup_callback); + } else { + char triplet[64]; + const char *features = NULL; + + scnprintf(triplet, sizeof(triplet), "%s-linux-gnu", + args->arch->name); + if (args->arch->id.e_machine == EM_AARCH64) + features = "+all"; + disasm = LLVMCreateDisasmCPUFeatures(triplet, /*cpu=*/"", + features, &storage, + /*tag_type=*/0, + /*get_op_info=*/NULL, + symbol_lookup_callback); + } + + if (disasm == NULL) + goto err; + + if (args->options->disassembler_style && + !strcmp(args->options->disassembler_style, "intel")) + LLVMSetDisasmOptions(disasm, + LLVMDisassembler_Option_AsmPrinterVariant); + + /* + * This needs to be set after AsmPrinterVariant, due to a bug in LLVM; + * setting AsmPrinterVariant makes a new instruction printer, making it + * forget about the PrintImmHex flag (which is applied before if both + * are given to the same call). + */ + LLVMSetDisasmOptions(disasm, LLVMDisassembler_Option_PrintImmHex); + + /* add the function address and name */ + scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:", + start, sym->name); + + args->offset = -1; + args->line = disasm_buf; + args->line_nr = 0; + args->fileloc = NULL; + args->ms->sym = sym; + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + pc = start; + for (u64 offset = 0; offset < buf_len; ) { + unsigned int ins_len; + + storage.branch_addr = 0; + storage.pcrel_load_addr = 0; + + /* + * LLVM's API has the code be disassembled as non-const, cast + * here as we may be disassembling from mapped read-only memory. + */ + ins_len = LLVMDisasmInstruction(disasm, (u8 *)(buf + offset), + buf_len - offset, pc, + disasm_buf, sizeof(disasm_buf)); + if (ins_len == 0) + goto err; + disasm_len = strlen(disasm_buf); + + if (storage.branch_addr != 0) { + char *name = llvm_name_for_code(dso, filename, + storage.branch_addr); + if (name != NULL) { + disasm_len += scnprintf(disasm_buf + disasm_len, + sizeof(disasm_buf) - + disasm_len, + " <%s>", name); + free(name); + } + } + if (storage.pcrel_load_addr != 0) { + char *name = llvm_name_for_data(dso, filename, + storage.pcrel_load_addr); + disasm_len += scnprintf(disasm_buf + disasm_len, + sizeof(disasm_buf) - disasm_len, + " # %#"PRIx64, + storage.pcrel_load_addr); + if (name) { + disasm_len += scnprintf(disasm_buf + disasm_len, + sizeof(disasm_buf) - + disasm_len, + " <%s>", name); + free(name); + } + } + + args->offset = offset; + args->line = expand_tabs(disasm_buf, &line_storage, + &line_storage_len); + args->line_nr = 0; + args->fileloc = NULL; + args->ms->sym = sym; + + llvm_addr2line(filename, pc, &args->fileloc, + (unsigned int *)&args->line_nr, false, NULL); + + dl = disasm_line__new(args); + if (dl == NULL) + goto err; + + annotation_line__add(&dl->al, ¬es->src->source); + + free(args->fileloc); + pc += ins_len; + offset += ins_len; + } + + ret = 0; + +err: + LLVMDisasmDispose(disasm); + free(code_buf); + free(line_storage); + return ret; +#else // HAVE_LIBLLVM_SUPPORT + pr_debug("The LLVM disassembler isn't linked in for %s in %s\n", + sym->name, filename); + return -1; +#endif +} diff --git a/tools/perf/util/llvm.h b/tools/perf/util/llvm.h new file mode 100644 index 000000000000..57f6bafb24bb --- /dev/null +++ b/tools/perf/util/llvm.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_LLVM_H +#define __PERF_LLVM_H + +#include <stdbool.h> +#include <linux/types.h> + +struct annotate_args; +struct dso; +struct inline_node; +struct symbol; + +int llvm__addr2line(const char *dso_name, u64 addr, + char **file, unsigned int *line, struct dso *dso, + bool unwind_inlines, struct inline_node *node, + struct symbol *sym); + +int symbol__disassemble_llvm(const char *filename, struct symbol *sym, + struct annotate_args *args); + +#endif /* __PERF_LLVM_H */ diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index a09f7fe877df..59c94190b092 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -18,6 +18,12 @@ struct lock_filter { char **slabs; }; +struct lock_delay { + char *sym; + unsigned long addr; + unsigned long time; +}; + struct lock_stat { struct hlist_node hash_entry; struct rb_node rb; /* used for sorting */ @@ -140,14 +146,17 @@ struct lock_contention { struct machine *machine; struct hlist_head *result; struct lock_filter *filters; + struct lock_delay *delays; struct lock_contention_fails fails; struct rb_root cgroups; + void *btf; unsigned long map_nr_entries; int max_stack; int stack_skip; int aggr_mode; int owner; int nr_filtered; + int nr_delays; bool save_callstack; }; @@ -168,6 +177,8 @@ int lock_contention_stop(void); int lock_contention_read(struct lock_contention *con); int lock_contention_finish(struct lock_contention *con); +struct lock_stat *pop_owner_stack_trace(struct lock_contention *con); + #else /* !HAVE_BPF_SKEL */ static inline int lock_contention_prepare(struct lock_contention *con __maybe_unused) @@ -187,6 +198,11 @@ static inline int lock_contention_read(struct lock_contention *con __maybe_unuse return 0; } +static inline struct lock_stat *pop_owner_stack_trace(struct lock_contention *con __maybe_unused) +{ + return NULL; +} + #endif /* HAVE_BPF_SKEL */ #endif /* PERF_LOCK_CONTENTION_H */ diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index af9a97612f9d..91b9b5171d1f 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -32,7 +32,7 @@ static const char *lzma_strerror(lzma_ret ret) } } -int lzma_decompress_to_file(const char *input, int output_fd) +int lzma_decompress_stream_to_file(FILE *infile, int output_fd) { lzma_action action = LZMA_RUN; lzma_stream strm = LZMA_STREAM_INIT; @@ -41,18 +41,11 @@ int lzma_decompress_to_file(const char *input, int output_fd) u8 buf_in[BUFSIZE]; u8 buf_out[BUFSIZE]; - FILE *infile; - - infile = fopen(input, "rb"); - if (!infile) { - pr_debug("lzma: fopen failed on %s: '%s'\n", input, strerror(errno)); - return -1; - } ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED); if (ret != LZMA_OK) { pr_debug("lzma: lzma_stream_decoder failed %s (%d)\n", lzma_strerror(ret), ret); - goto err_fclose; + return err; } strm.next_in = NULL; @@ -66,7 +59,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) strm.avail_in = fread(buf_in, 1, sizeof(buf_in), infile); if (ferror(infile)) { - pr_debug("lzma: read error: %s\n", strerror(errno)); + pr_debug("lzma: read error: %m\n"); goto err_lzma_end; } @@ -80,7 +73,7 @@ int lzma_decompress_to_file(const char *input, int output_fd) ssize_t write_size = sizeof(buf_out) - strm.avail_out; if (writen(output_fd, buf_out, write_size) != write_size) { - pr_debug("lzma: write error: %s\n", strerror(errno)); + pr_debug("lzma: write error: %m\n"); goto err_lzma_end; } @@ -100,11 +93,25 @@ int lzma_decompress_to_file(const char *input, int output_fd) err = 0; err_lzma_end: lzma_end(&strm); -err_fclose: - fclose(infile); return err; } +int lzma_decompress_to_file(const char *input, int output_fd) +{ + FILE *infile; + int ret; + + infile = fopen(input, "rb"); + if (!infile) { + pr_debug("lzma: fopen failed on %s: '%m'\n", input); + return -1; + } + + ret = lzma_decompress_stream_to_file(infile, output_fd); + fclose(infile); + return ret; +} + bool lzma_is_compressed(const char *input) { int fd = open(input, O_RDONLY); @@ -113,7 +120,7 @@ bool lzma_is_compressed(const char *input) ssize_t rc; if (fd < 0) - return -1; + return false; rc = read(fd, buf, sizeof(buf)); close(fd); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2d51badfbf2e..e76f8c86e62a 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -20,6 +20,7 @@ #include "path.h" #include "srcline.h" #include "symbol.h" +#include "synthetic-events.h" #include "sort.h" #include "strlist.h" #include "target.h" @@ -37,6 +38,7 @@ #include <internal/lib.h> // page_size #include "cgroup.h" #include "arm64-frame-pointer-unwind-support.h" +#include <api/io_dir.h> #include <linux/ctype.h> #include <symbol/kallsyms.h> @@ -94,6 +96,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->comm_exec = false; machine->kernel_start = 0; machine->vmlinux_map = NULL; + /* There is no initial context switch in, so we start at 1. */ + machine->parallelism = 1; machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) @@ -125,28 +129,62 @@ out: return 0; } -struct machine *machine__new_host(void) +static struct machine *__machine__new_host(struct perf_env *host_env, bool kernel_maps) { struct machine *machine = malloc(sizeof(*machine)); - if (machine != NULL) { - machine__init(machine, "", HOST_KERNEL_ID); + if (!machine) + return NULL; - if (machine__create_kernel_maps(machine) < 0) - goto out_delete; + machine__init(machine, "", HOST_KERNEL_ID); - machine->env = &perf_env; + if (kernel_maps && machine__create_kernel_maps(machine) < 0) { + free(machine); + return NULL; } + machine->env = host_env; + return machine; +} + +struct machine *machine__new_host(struct perf_env *host_env) +{ + return __machine__new_host(host_env, /*kernel_maps=*/true); +} + +static int mmap_handler(const struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_mmap2_event(machine, event, sample); +} + +static int machine__init_live(struct machine *machine, pid_t pid) +{ + union perf_event event; + + memset(&event, 0, sizeof(event)); + return perf_event__synthesize_mmap_events(NULL, &event, pid, pid, + mmap_handler, machine, true); +} + +struct machine *machine__new_live(struct perf_env *host_env, bool kernel_maps, pid_t pid) +{ + struct machine *machine = __machine__new_host(host_env, kernel_maps); + if (!machine) + return NULL; + + if (machine__init_live(machine, pid)) { + machine__delete(machine); + return NULL; + } return machine; -out_delete: - free(machine); - return NULL; } -struct machine *machine__new_kallsyms(void) +struct machine *machine__new_kallsyms(struct perf_env *host_env) { - struct machine *machine = machine__new_host(); + struct machine *machine = machine__new_host(host_env); /* * FIXME: * 1) We should switch to machine__load_kallsyms(), i.e. not explicitly @@ -677,8 +715,11 @@ int machine__process_aux_output_hw_id_event(struct machine *machine __maybe_unus int machine__process_switch_event(struct machine *machine __maybe_unused, union perf_event *event) { + bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT; + if (dump_trace) perf_event__fprintf_switch(event, stdout); + machine->parallelism += out ? -1 : 1; return 0; } @@ -712,7 +753,7 @@ static int machine__process_ksymbol_register(struct machine *machine, map__set_start(map, event->ksymbol.addr); map__set_end(map, map__start(map) + event->ksymbol.len); - err = maps__insert(machine__kernel_maps(machine), map); + err = maps__fixup_overlap_and_insert(machine__kernel_maps(machine), map); if (err) { err = -ENOMEM; goto out; @@ -773,6 +814,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused, if (dump_trace) perf_event__fprintf_ksymbol(event, stdout); + /* no need to process non-JIT BPF as it cannot get samples */ + if (event->ksymbol.len == 0) + return 0; + if (event->ksymbol.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER) return machine__process_ksymbol_unregister(machine, event, sample); @@ -886,26 +931,6 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, return ret; } -size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) -{ - int i; - size_t printed = 0; - struct dso *kdso = machine__kernel_dso(machine); - - if (dso__has_build_id(kdso)) { - char filename[PATH_MAX]; - - if (dso__build_id_filename(kdso, filename, sizeof(filename), false)) - printed += fprintf(fp, "[0] %s\n", filename); - } - - for (i = 0; i < vmlinux_path__nr_entries; ++i) { - printed += fprintf(fp, "[%d] %s\n", i + dso__has_build_id(kdso), - vmlinux_path[i]); - } - return printed; -} - struct machine_fprintf_cb_args { FILE *fp; size_t printed; @@ -1352,27 +1377,24 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo return 0; } -static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, int depth) +static int maps__set_modules_path_dir(struct maps *maps, char *path, size_t path_size, int depth) { - struct dirent *dent; - DIR *dir = opendir(dir_name); + struct io_dirent64 *dent; + struct io_dir iod; + size_t root_len = strlen(path); int ret = 0; - if (!dir) { - pr_debug("%s: cannot open %s dir\n", __func__, dir_name); + io_dir__init(&iod, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (iod.dirfd < 0) { + pr_debug("%s: cannot open %s dir\n", __func__, path); return -1; } - - while ((dent = readdir(dir)) != NULL) { - char path[PATH_MAX]; - struct stat st; - - /*sshfs might return bad dent->d_type, so we have to stat*/ - path__join(path, sizeof(path), dir_name, dent->d_name); - if (stat(path, &st)) - continue; - - if (S_ISDIR(st.st_mode)) { + /* Bounds check, should never happen. */ + if (root_len >= path_size) + return -1; + path[root_len++] = '/'; + while ((dent = io_dir__readdir(&iod)) != NULL) { + if (io_dir__is_dir(&iod, dent)) { if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) continue; @@ -1384,7 +1406,12 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i continue; } - ret = maps__set_modules_path_dir(maps, path, depth + 1); + /* Bounds check, should never happen. */ + if (root_len + strlen(dent->d_name) >= path_size) + continue; + + strcpy(path + root_len, dent->d_name); + ret = maps__set_modules_path_dir(maps, path, path_size, depth + 1); if (ret < 0) goto out; } else { @@ -1394,9 +1421,14 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i if (ret) goto out; - if (m.kmod) - ret = maps__set_module_path(maps, path, &m); + if (m.kmod) { + /* Bounds check, should never happen. */ + if (root_len + strlen(dent->d_name) < path_size) { + strcpy(path + root_len, dent->d_name); + ret = maps__set_module_path(maps, path, &m); + } + } zfree(&m.name); if (ret) @@ -1405,7 +1437,7 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i } out: - closedir(dir); + close(iod.dirfd); return ret; } @@ -1422,7 +1454,8 @@ static int machine__set_modules_path(struct machine *machine) machine->root_dir, version); free(version); - return maps__set_modules_path_dir(machine__kernel_maps(machine), modules_path, 0); + return maps__set_modules_path_dir(machine__kernel_maps(machine), + modules_path, sizeof(modules_path), 0); } int __weak arch__fix_module_text_start(u64 *start __maybe_unused, u64 *size __maybe_unused, @@ -1468,8 +1501,6 @@ static int machine__create_modules(struct machine *machine) if (modules__parse(modules, machine, machine__create_module)) return -1; - maps__fixup_end(machine__kernel_maps(machine)); - if (!machine__set_modules_path(machine)) return 0; @@ -1563,6 +1594,8 @@ int machine__create_kernel_maps(struct machine *machine) } } + maps__fixup_end(machine__kernel_maps(machine)); + out_put: dso__put(kernel); return ret; @@ -1698,21 +1731,21 @@ int machine__process_mmap2_event(struct machine *machine, { struct thread *thread; struct map *map; - struct dso_id dso_id = { - .maj = event->mmap2.maj, - .min = event->mmap2.min, - .ino = event->mmap2.ino, - .ino_generation = event->mmap2.ino_generation, - }; - struct build_id __bid, *bid = NULL; + struct dso_id dso_id = dso_id_empty; int ret = 0; if (dump_trace) perf_event__fprintf_mmap2(event, stdout); if (event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID) { - bid = &__bid; - build_id__init(bid, event->mmap2.build_id, event->mmap2.build_id_size); + build_id__init(&dso_id.build_id, event->mmap2.build_id, event->mmap2.build_id_size); + } else { + dso_id.maj = event->mmap2.maj; + dso_id.min = event->mmap2.min; + dso_id.ino = event->mmap2.ino; + dso_id.ino_generation = event->mmap2.ino_generation; + dso_id.mmap2_valid = true; + dso_id.mmap2_ino_generation_valid = true; } if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL || @@ -1724,7 +1757,7 @@ int machine__process_mmap2_event(struct machine *machine, }; strlcpy(xm.name, event->mmap2.filename, KMAP_NAME_LEN); - ret = machine__process_kernel_mmap_event(machine, &xm, bid); + ret = machine__process_kernel_mmap_event(machine, &xm, &dso_id.build_id); if (ret < 0) goto out_problem; return 0; @@ -1738,7 +1771,7 @@ int machine__process_mmap2_event(struct machine *machine, map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, &dso_id, event->mmap2.prot, - event->mmap2.flags, bid, + event->mmap2.flags, event->mmap2.filename, thread); if (map == NULL) @@ -1796,8 +1829,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event prot = PROT_EXEC; map = map__new(machine, event->mmap.start, - event->mmap.len, event->mmap.pgoff, - NULL, prot, 0, NULL, event->mmap.filename, thread); + event->mmap.len, event->mmap.pgoff, + &dso_id_empty, prot, /*flags=*/0, event->mmap.filename, thread); if (map == NULL) goto out_problem_map; @@ -1900,6 +1933,8 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event if (dump_trace) perf_event__fprintf_task(event, stdout); + /* There is no context switch out before exit, so we decrement here. */ + machine->parallelism--; if (thread != NULL) { if (symbol_conf.keep_exited_threads) thread__set_exited(thread, /*exited=*/true); @@ -1976,12 +2011,12 @@ static void ip__resolve_ams(struct thread *thread, * Thus, we have to try consecutively until we find a match * or else, the symbol is unknown */ - thread__find_cpumode_addr_location(thread, ip, &al); + thread__find_cpumode_addr_location(thread, ip, /*symbols=*/true, &al); ams->addr = ip; ams->al_addr = al.addr; ams->al_level = al.level; - ams->ms.maps = maps__get(al.maps); + ams->ms.thread = thread__get(al.thread); ams->ms.sym = al.sym; ams->ms.map = map__get(al.map); ams->phys_addr = 0; @@ -2002,7 +2037,7 @@ static void ip__resolve_data(struct thread *thread, ams->addr = addr; ams->al_addr = al.addr; ams->al_level = al.level; - ams->ms.maps = maps__get(al.maps); + ams->ms.thread = thread__get(al.thread); ams->ms.sym = al.sym; ams->ms.map = map__get(al.map); ams->phys_addr = phys_addr; @@ -2055,6 +2090,59 @@ struct iterations { u64 cycles; }; +static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip, + bool branch, struct branch_flags *flags, int nr_loop_iter, + u64 iter_cycles, u64 branch_from) +{ + struct symbol *sym = ms->sym; + struct map *map = ms->map; + struct inline_node *inline_node; + struct inline_list *ilist; + struct dso *dso; + u64 addr; + int ret = 1; + struct map_symbol ilist_ms; + bool first = true; + + if (!symbol_conf.inline_name || !map || !sym) + return ret; + + addr = map__dso_map_ip(map, ip); + addr = map__rip_2objdump(map, addr); + dso = map__dso(map); + + inline_node = inlines__tree_find(dso__inlined_nodes(dso), addr); + if (!inline_node) { + inline_node = dso__parse_addr_inlines(dso, addr, sym); + if (!inline_node) + return ret; + inlines__tree_insert(dso__inlined_nodes(dso), inline_node); + } + + ilist_ms = (struct map_symbol) { + .thread = thread__get(ms->thread), + .map = map__get(map), + }; + list_for_each_entry(ilist, &inline_node->val, list) { + ilist_ms.sym = ilist->symbol; + if (first) { + ret = callchain_cursor_append(cursor, ip, &ilist_ms, + branch, flags, nr_loop_iter, + iter_cycles, branch_from, ilist->srcline); + } else { + ret = callchain_cursor_append(cursor, ip, &ilist_ms, false, + NULL, 0, 0, 0, ilist->srcline); + } + first = false; + + if (ret != 0) + return ret; + } + map_symbol__exit(&ilist_ms); + + return ret; +} + static int add_callchain_ip(struct thread *thread, struct callchain_cursor *cursor, struct symbol **parent, @@ -2078,7 +2166,7 @@ static int add_callchain_ip(struct thread *thread, al.sym = NULL; al.srcline = NULL; if (!cpumode) { - thread__find_cpumode_addr_location(thread, ip, &al); + thread__find_cpumode_addr_location(thread, ip, symbols, &al); } else { if (ip >= PERF_CONTEXT_MAX) { switch (ip) { @@ -2089,6 +2177,7 @@ static int add_callchain_ip(struct thread *thread, *cpumode = PERF_RECORD_MISC_KERNEL; break; case PERF_CONTEXT_USER: + case PERF_CONTEXT_USER_DEFERRED: *cpumode = PERF_RECORD_MISC_USER; break; default: @@ -2106,6 +2195,8 @@ static int add_callchain_ip(struct thread *thread, } if (symbols) thread__find_symbol(thread, *cpumode, ip, &al); + else + thread__find_map(thread, *cpumode, ip, &al); } if (al.sym != NULL) { @@ -2129,9 +2220,14 @@ static int add_callchain_ip(struct thread *thread, iter_cycles = iter->cycles; } - ms.maps = maps__get(al.maps); + ms.thread = thread__get(al.thread); ms.map = map__get(al.map); ms.sym = al.sym; + + if (append_inlines(cursor, &ms, ip, branch, flags, nr_loop_iter, + iter_cycles, branch_from) == 0) + goto out; + srcline = callchain_srcline(&ms, al.addr); err = callchain_cursor_append(cursor, ip, &ms, branch, flags, nr_loop_iter, @@ -2287,7 +2383,7 @@ static void save_lbr_cursor_node(struct thread *thread, map_symbol__exit(&lbr_stitch->prev_lbr_cursor[idx].ms); memcpy(&lbr_stitch->prev_lbr_cursor[idx], cursor->curr, sizeof(struct callchain_cursor_node)); - lbr_stitch->prev_lbr_cursor[idx].ms.maps = maps__get(cursor->curr->ms.maps); + lbr_stitch->prev_lbr_cursor[idx].ms.thread = thread__get(cursor->curr->ms.thread); lbr_stitch->prev_lbr_cursor[idx].ms.map = map__get(cursor->curr->ms.map); lbr_stitch->prev_lbr_cursor[idx].valid = true; @@ -2327,8 +2423,14 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread, } if (callee) { - /* Add LBR ip from first entries.to */ - ip = entries[0].to; + /* + * Set the (first) leaf function's IP to sample->ip (the + * location of the sample) but if not recorded use entries.to + */ + if (sample->ip) + ip = sample->ip; + else + ip = entries[0].to; flags = &entries[0].flags; *branch_from = entries[0].from; err = add_callchain_ip(thread, cursor, parent, @@ -2381,8 +2483,14 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread, } if (lbr_nr > 0) { - /* Add LBR ip from first entries.to */ - ip = entries[0].to; + /* + * Set the (first) leaf function's IP to sample->ip (the + * location of the sample) but if not recorded use entries.to + */ + if (sample->ip) + ip = sample->ip; + else + ip = entries[0].to; flags = &entries[0].flags; *branch_from = entries[0].from; err = add_callchain_ip(thread, cursor, parent, @@ -2500,7 +2608,8 @@ static bool has_stitched_lbr(struct thread *thread, memcpy(&stitch_node->cursor, &lbr_stitch->prev_lbr_cursor[i], sizeof(struct callchain_cursor_node)); - stitch_node->cursor.ms.maps = maps__get(lbr_stitch->prev_lbr_cursor[i].ms.maps); + stitch_node->cursor.ms.thread = + thread__get(lbr_stitch->prev_lbr_cursor[i].ms.thread); stitch_node->cursor.ms.map = map__get(lbr_stitch->prev_lbr_cursor[i].ms.map); if (callee) @@ -2850,49 +2959,6 @@ check_calls: return 0; } -static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip) -{ - struct symbol *sym = ms->sym; - struct map *map = ms->map; - struct inline_node *inline_node; - struct inline_list *ilist; - struct dso *dso; - u64 addr; - int ret = 1; - struct map_symbol ilist_ms; - - if (!symbol_conf.inline_name || !map || !sym) - return ret; - - addr = map__dso_map_ip(map, ip); - addr = map__rip_2objdump(map, addr); - dso = map__dso(map); - - inline_node = inlines__tree_find(dso__inlined_nodes(dso), addr); - if (!inline_node) { - inline_node = dso__parse_addr_inlines(dso, addr, sym); - if (!inline_node) - return ret; - inlines__tree_insert(dso__inlined_nodes(dso), inline_node); - } - - ilist_ms = (struct map_symbol) { - .maps = maps__get(ms->maps), - .map = map__get(map), - }; - list_for_each_entry(ilist, &inline_node->val, list) { - ilist_ms.sym = ilist->symbol; - ret = callchain_cursor_append(cursor, ip, &ilist_ms, false, - NULL, 0, 0, 0, ilist->srcline); - - if (ret != 0) - return ret; - } - map_symbol__exit(&ilist_ms); - - return ret; -} - static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; @@ -2902,7 +2968,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) if (symbol_conf.hide_unresolved && entry->ms.sym == NULL) return 0; - if (append_inlines(cursor, &entry->ms, entry->ip) == 0) + if (append_inlines(cursor, &entry->ms, entry->ip, /*branch=*/false, /*branch_flags=*/NULL, + /*nr_loop_iter=*/0, /*iter_cycles=*/0, /*branch_from=*/0) == 0) return 0; /* @@ -2929,8 +2996,8 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; /* Bail out if nothing was captured. */ - if ((!sample->user_regs.regs) || - (!sample->user_stack.size)) + if (!sample->user_regs || !sample->user_regs->regs || + !sample->user_stack.size) return 0; if (!symbols) @@ -3155,7 +3222,7 @@ struct dso *machine__findnew_dso_id(struct machine *machine, const char *filenam struct dso *machine__findnew_dso(struct machine *machine, const char *filename) { - return machine__findnew_dso_id(machine, filename, NULL); + return machine__findnew_dso_id(machine, filename, &dso_id_empty); } char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp) diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 2e5a4cb342d8..22a42c5825fa 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -50,6 +50,12 @@ struct machine { u64 text_start; u64 text_end; } sched, lock, traceiter, trace; + /* + * The current parallelism level (number of threads that run on CPUs). + * This value can be less than 1, or larger than the total number + * of CPUs, if events are poorly ordered. + */ + int parallelism; pid_t *current_tid; size_t current_tid_sz; union { /* Tool specific area */ @@ -163,8 +169,9 @@ struct thread *machine__findnew_guest_code(struct machine *machine, pid_t pid); void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size); void machines__set_comm_exec(struct machines *machines, bool comm_exec); -struct machine *machine__new_host(void); -struct machine *machine__new_kallsyms(void); +struct machine *machine__new_host(struct perf_env *host_env); +struct machine *machine__new_kallsyms(struct perf_env *host_env); +struct machine *machine__new_live(struct perf_env *host_env, bool kernel_maps, pid_t pid); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); void machine__delete_threads(struct machine *machine); @@ -266,8 +273,6 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid); int machines__create_guest_kernel_maps(struct machines *machines); void machines__destroy_kernel_maps(struct machines *machines); -size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); - typedef int (*machine__dso_t)(struct dso *dso, struct machine *machine, void *priv); int machine__for_each_dso(struct machine *machine, machine__dso_t fn, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index d729438b7d65..41cdddc987ee 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -120,8 +120,8 @@ static void map__init(struct map *map, u64 start, u64 end, u64 pgoff, } struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, struct dso_id *id, - u32 prot, u32 flags, struct build_id *bid, + u64 pgoff, const struct dso_id *id, + u32 prot, u32 flags, char *filename, struct thread *thread) { struct map *result; @@ -132,7 +132,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, map = zalloc(sizeof(*map)); if (ADD_RC_CHK(result, map)) { char newfilename[PATH_MAX]; - struct dso *dso, *header_bid_dso; + struct dso *dso; int anon, no_dso, vdso, android; android = is_android_lib(filename); @@ -189,16 +189,15 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, dso__set_nsinfo(dso, nsi); mutex_unlock(dso__lock(dso)); - if (build_id__is_defined(bid)) { - dso__set_build_id(dso, bid); - } else { + if (!build_id__is_defined(&id->build_id)) { /* * If the mmap event had no build ID, search for an existing dso from the * build ID header by name. Otherwise only the dso loaded at the time of * reading the header will have the build ID set and all future mmaps will * have it missing. */ - header_bid_dso = dsos__find(&machine->dsos, filename, false); + struct dso *header_bid_dso = dsos__find(&machine->dsos, filename, false); + if (header_bid_dso && dso__header_build_id(header_bid_dso)) { dso__set_build_id(dso, dso__bid(header_bid_dso)); dso__set_header_build_id(dso, 1); @@ -354,7 +353,7 @@ int map__load(struct map *map) if (dso__has_build_id(dso)) { char sbuild_id[SBUILD_ID_SIZE]; - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); pr_debug("%s with build id %s not found", name, sbuild_id); } else pr_debug("Failed to open %s", name); @@ -514,6 +513,8 @@ void srccode_state_free(struct srccode_state *state) state->line = 0; } +static const struct kmap *__map__const_kmap(const struct map *map); + /** * map__rip_2objdump - convert symbol start address to objdump address. * @map: memory map @@ -525,9 +526,9 @@ void srccode_state_free(struct srccode_state *state) * * Return: Address suitable for passing to "objdump --start-address=" */ -u64 map__rip_2objdump(struct map *map, u64 rip) +u64 map__rip_2objdump(const struct map *map, u64 rip) { - struct kmap *kmap = __map__kmap(map); + const struct kmap *kmap = __map__const_kmap(map); const struct dso *dso = map__dso(map); /* @@ -570,7 +571,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip) * * Return: Memory address. */ -u64 map__objdump_2mem(struct map *map, u64 ip) +u64 map__objdump_2mem(const struct map *map, u64 ip) { const struct dso *dso = map__dso(map); @@ -587,7 +588,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip) } /* convert objdump address to relative address. (To be removed) */ -u64 map__objdump_2rip(struct map *map, u64 ip) +u64 map__objdump_2rip(const struct map *map, u64 ip) { const struct dso *dso = map__dso(map); @@ -619,6 +620,15 @@ struct kmap *__map__kmap(struct map *map) return (struct kmap *)(&RC_CHK_ACCESS(map)[1]); } +static const struct kmap *__map__const_kmap(const struct map *map) +{ + const struct dso *dso = map__dso(map); + + if (!dso || !dso__kernel(dso)) + return NULL; + return (struct kmap *)(&RC_CHK_ACCESS(map)[1]); +} + struct kmap *map__kmap(struct map *map) { struct kmap *kmap = __map__kmap(map); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 4262f5a143be..979b3e11b9bc 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -133,13 +133,13 @@ static inline u64 map__unmap_ip(const struct map *map, u64 ip_or_rip) } /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ -u64 map__rip_2objdump(struct map *map, u64 rip); +u64 map__rip_2objdump(const struct map *map, u64 rip); /* objdump address -> memory address */ -u64 map__objdump_2mem(struct map *map, u64 ip); +u64 map__objdump_2mem(const struct map *map, u64 ip); /* objdump address -> rip */ -u64 map__objdump_2rip(struct map *map, u64 ip); +u64 map__objdump_2rip(const struct map *map, u64 ip); struct symbol; struct thread; @@ -173,11 +173,10 @@ struct thread; __map__for_each_symbol_by_name(map, sym_name, (pos), idx) struct dso_id; -struct build_id; struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, struct dso_id *id, u32 prot, u32 flags, - struct build_id *bid, char *filename, struct thread *thread); + u64 pgoff, const struct dso_id *id, u32 prot, u32 flags, + char *filename, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso); void map__delete(struct map *map); struct map *map__clone(struct map *map); diff --git a/tools/perf/util/map_symbol.c b/tools/perf/util/map_symbol.c index 6ad2960bc289..11bc0a7f704c 100644 --- a/tools/perf/util/map_symbol.c +++ b/tools/perf/util/map_symbol.c @@ -2,10 +2,11 @@ #include "map_symbol.h" #include "maps.h" #include "map.h" +#include "thread.h" void map_symbol__exit(struct map_symbol *ms) { - maps__zput(ms->maps); + thread__zput(ms->thread); map__zput(ms->map); } @@ -16,7 +17,7 @@ void addr_map_symbol__exit(struct addr_map_symbol *ams) void map_symbol__copy(struct map_symbol *dst, struct map_symbol *src) { - dst->maps = maps__get(src->maps); + dst->thread = thread__get(src->thread); dst->map = map__get(src->map); dst->sym = src->sym; } diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index e370bb32ed47..7437e319f4a3 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -4,12 +4,13 @@ #include <linux/types.h> +struct thread; struct maps; struct map; struct symbol; struct map_symbol { - struct maps *maps; + struct thread *thread; struct map *map; struct symbol *sym; }; diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 09c9cc326c08..81a97ac34077 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -10,6 +10,7 @@ #include "thread.h" #include "ui/ui.h" #include "unwind.h" +#include "unwind-libdw.h" #include <internal/rc_check.h> /* @@ -40,6 +41,9 @@ DECLARE_RC_STRUCT(maps) { void *addr_space; const struct unwind_libunwind_ops *unwind_libunwind_ops; #endif +#ifdef HAVE_LIBDW_SUPPORT + void *libdw_addr_space_dwfl; +#endif refcount_t refcnt; /** * @nr_maps: number of maps_by_address, and possibly maps_by_name, @@ -203,6 +207,17 @@ void maps__set_unwind_libunwind_ops(struct maps *maps, const struct unwind_libun RC_CHK_ACCESS(maps)->unwind_libunwind_ops = ops; } #endif +#ifdef HAVE_LIBDW_SUPPORT +void *maps__libdw_addr_space_dwfl(const struct maps *maps) +{ + return RC_CHK_ACCESS(maps)->libdw_addr_space_dwfl; +} + +void maps__set_libdw_addr_space_dwfl(struct maps *maps, void *dwfl) +{ + RC_CHK_ACCESS(maps)->libdw_addr_space_dwfl = dwfl; +} +#endif static struct rw_semaphore *maps__lock(struct maps *maps) { @@ -219,6 +234,9 @@ static void maps__init(struct maps *maps, struct machine *machine) RC_CHK_ACCESS(maps)->addr_space = NULL; RC_CHK_ACCESS(maps)->unwind_libunwind_ops = NULL; #endif +#ifdef HAVE_LIBDW_SUPPORT + RC_CHK_ACCESS(maps)->libdw_addr_space_dwfl = NULL; +#endif refcount_set(maps__refcnt(maps), 1); RC_CHK_ACCESS(maps)->nr_maps = 0; RC_CHK_ACCESS(maps)->nr_maps_allocated = 0; @@ -240,6 +258,9 @@ static void maps__exit(struct maps *maps) zfree(&maps_by_address); zfree(&maps_by_name); unwind__finish_access(maps); +#ifdef HAVE_LIBDW_SUPPORT + libdw__invalidate_dwfl(maps, maps__libdw_addr_space_dwfl(maps)); +#endif } struct maps *maps__new(struct machine *machine) @@ -428,11 +449,29 @@ static unsigned int maps__by_name_index(const struct maps *maps, const struct ma return -1; } +static void map__set_kmap_maps(struct map *map, struct maps *maps) +{ + struct dso *dso; + + if (map == NULL) + return; + + dso = map__dso(map); + + if (dso && dso__kernel(dso)) { + struct kmap *kmap = map__kmap(map); + + if (kmap) + kmap->kmaps = maps; + else + pr_err("Internal error: kernel dso with non kernel map\n"); + } +} + static int __maps__insert(struct maps *maps, struct map *new) { struct map **maps_by_address = maps__maps_by_address(maps); struct map **maps_by_name = maps__maps_by_name(maps); - const struct dso *dso = map__dso(new); unsigned int nr_maps = maps__nr_maps(maps); unsigned int nr_allocate = RC_CHK_ACCESS(maps)->nr_maps_allocated; @@ -459,6 +498,7 @@ static int __maps__insert(struct maps *maps, struct map *new) } /* Insert the value at the end. */ maps_by_address[nr_maps] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) maps_by_name[nr_maps] = map__get(new); @@ -483,14 +523,7 @@ static int __maps__insert(struct maps *maps, struct map *new) } if (map__end(new) < map__start(new)) RC_CHK_ACCESS(maps)->ends_broken = true; - if (dso && dso__kernel(dso)) { - struct kmap *kmap = map__kmap(new); - if (kmap) - kmap->kmaps = maps; - else - pr_err("Internal error: kernel dso with non kernel map\n"); - } return 0; } @@ -537,6 +570,9 @@ void maps__remove(struct maps *maps, struct map *map) __maps__remove(maps, map); check_invariants(maps); up_write(maps__lock(maps)); +#ifdef HAVE_LIBDW_SUPPORT + libdw__invalidate_dwfl(maps, maps__libdw_addr_space_dwfl(maps)); +#endif } bool maps__empty(struct maps *maps) @@ -592,18 +628,26 @@ int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data) void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data) { struct map **maps_by_address; + bool removed = false; down_write(maps__lock(maps)); maps_by_address = maps__maps_by_address(maps); for (unsigned int i = 0; i < maps__nr_maps(maps);) { - if (cb(maps_by_address[i], data)) + if (cb(maps_by_address[i], data)) { __maps__remove(maps, maps_by_address[i]); - else + removed = true; + } else { i++; + } } check_invariants(maps); up_write(maps__lock(maps)); + if (removed) { +#ifdef HAVE_LIBDW_SUPPORT + libdw__invalidate_dwfl(maps, maps__libdw_addr_space_dwfl(maps)); +#endif + } } struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) @@ -664,6 +708,7 @@ int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) if (ams->addr < map__start(ams->ms.map) || ams->addr >= map__end(ams->ms.map)) { if (maps == NULL) return -1; + map__put(ams->ms.map); ams->ms.map = maps__find(maps, ams->addr); if (ams->ms.map == NULL) return -1; @@ -785,6 +830,9 @@ static int __maps__insert_sorted(struct maps *maps, unsigned int first_after_ind } RC_CHK_ACCESS(maps)->nr_maps = nr_maps + to_add; maps__set_maps_by_name_sorted(maps, false); + map__set_kmap_maps(new1, maps); + map__set_kmap_maps(new2, maps); + check_invariants(maps); return 0; } @@ -796,8 +844,7 @@ static int __maps__insert_sorted(struct maps *maps, unsigned int first_after_ind static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) { int err = 0; - FILE *fp = debug_file(); - unsigned int i; + unsigned int i, ni = INT_MAX; // Some gcc complain, but depends on maps_by_name... if (!maps__maps_by_address_sorted(maps)) __maps__sort_by_address(maps); @@ -808,6 +855,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ for (i = first_ending_after(maps, new); i < maps__nr_maps(maps); ) { struct map **maps_by_address = maps__maps_by_address(maps); + struct map **maps_by_name = maps__maps_by_name(maps); struct map *pos = maps_by_address[i]; struct map *before = NULL, *after = NULL; @@ -823,10 +871,13 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) dso__name(map__dso(new))); } else if (verbose >= 2) { pr_debug("overlapping maps:\n"); - map__fprintf(new, fp); - map__fprintf(pos, fp); + map__fprintf(new, debug_file()); + map__fprintf(pos, debug_file()); } + if (maps_by_name) + ni = maps__by_name_index(maps, pos); + /* * Now check if we need to create new maps for areas not * overlapped by the new map: @@ -842,7 +893,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) map__set_end(before, map__start(new)); if (verbose >= 2 && !use_browser) - map__fprintf(before, fp); + map__fprintf(before, debug_file()); } if (map__end(new) < map__end(pos)) { /* The new map isn't as long as the existing map. */ @@ -860,7 +911,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) map__map_ip(after, map__end(new))); if (verbose >= 2 && !use_browser) - map__fprintf(after, fp); + map__fprintf(after, debug_file()); } /* * If adding one entry, for `before` or `after`, we can replace @@ -871,6 +922,13 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) if (before) { map__put(maps_by_address[i]); maps_by_address[i] = before; + map__set_kmap_maps(before, maps); + + if (maps_by_name) { + map__put(maps_by_name[ni]); + maps_by_name[ni] = map__get(before); + } + /* Maps are still ordered, go to next one. */ i++; if (after) { @@ -892,14 +950,23 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); + + if (maps_by_name) { + map__put(maps_by_name[ni]); + maps_by_name[ni] = map__get(new); + maps__set_maps_by_name_sorted(maps, false); + } + err = __maps__insert_sorted(maps, i + 1, after, NULL); map__put(after); check_invariants(maps); return err; } else { struct map *next = NULL; + unsigned int nr_maps = maps__nr_maps(maps); - if (i + 1 < maps__nr_maps(maps)) + if (i + 1 < nr_maps) next = maps_by_address[i + 1]; if (!next || map__start(next) >= map__end(new)) { @@ -910,10 +977,35 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); + + if (maps_by_name) { + map__put(maps_by_name[ni]); + maps_by_name[ni] = map__get(new); + maps__set_maps_by_name_sorted(maps, false); + } + check_invariants(maps); return err; } - __maps__remove(maps, pos); + /* + * pos fully covers the previous mapping so remove + * it. The following is an inlined version of + * maps__remove that reuses the already computed + * indices. + */ + map__put(maps_by_address[i]); + memmove(&maps_by_address[i], + &maps_by_address[i + 1], + (nr_maps - i - 1) * sizeof(*maps_by_address)); + + if (maps_by_name) { + map__put(maps_by_name[ni]); + memmove(&maps_by_name[ni], + &maps_by_name[ni + 1], + (nr_maps - ni - 1) * sizeof(*maps_by_name)); + } + --RC_CHK_ACCESS(maps)->nr_maps; check_invariants(maps); /* * Maps are ordered but no need to increase `i` as the @@ -979,6 +1071,7 @@ int maps__copy_from(struct maps *dest, struct maps *parent) err = unwind__prepare_access(dest, new, NULL); if (!err) { dest_maps_by_address[i] = new; + map__set_kmap_maps(new, dest); if (dest_maps_by_name) dest_maps_by_name[i] = map__get(new); RC_CHK_ACCESS(dest)->nr_maps = i + 1; @@ -988,16 +1081,9 @@ int maps__copy_from(struct maps *dest, struct maps *parent) map__put(new); } maps__set_maps_by_address_sorted(dest, maps__maps_by_address_sorted(parent)); - if (!err) { - RC_CHK_ACCESS(dest)->last_search_by_name_idx = - RC_CHK_ACCESS(parent)->last_search_by_name_idx; - maps__set_maps_by_name_sorted(dest, - dest_maps_by_name && - maps__maps_by_name_sorted(parent)); - } else { - RC_CHK_ACCESS(dest)->last_search_by_name_idx = 0; - maps__set_maps_by_name_sorted(dest, false); - } + RC_CHK_ACCESS(dest)->last_search_by_name_idx = 0; + /* Values were copied into the name array in address order. */ + maps__set_maps_by_name_sorted(dest, false); } else { /* Unexpected copying to a maps containing entries. */ for (unsigned int i = 0; !err && i < n; i++) { @@ -1042,10 +1128,13 @@ struct map *maps__find(struct maps *maps, u64 ip) while (!done) { down_read(maps__lock(maps)); if (maps__maps_by_address_sorted(maps)) { - struct map **mapp = - bsearch(&ip, maps__maps_by_address(maps), maps__nr_maps(maps), - sizeof(*mapp), map__addr_cmp); + struct map **mapp = NULL; + struct map **maps_by_address = maps__maps_by_address(maps); + unsigned int nr_maps = maps__nr_maps(maps); + if (maps_by_address && nr_maps) + mapp = bsearch(&ip, maps_by_address, nr_maps, sizeof(*mapp), + map__addr_cmp); if (mapp) result = map__get(*mapp); done = true; diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h index d9aa62ed968a..20c52084ba9e 100644 --- a/tools/perf/util/maps.h +++ b/tools/perf/util/maps.h @@ -52,6 +52,10 @@ void maps__set_addr_space(struct maps *maps, void *addr_space); const struct unwind_libunwind_ops *maps__unwind_libunwind_ops(const struct maps *maps); void maps__set_unwind_libunwind_ops(struct maps *maps, const struct unwind_libunwind_ops *ops); #endif +#ifdef HAVE_LIBDW_SUPPORT +void *maps__libdw_addr_space_dwfl(const struct maps *maps); +void maps__set_libdw_addr_space_dwfl(struct maps *maps, void *dwfl); +#endif size_t maps__fprintf(struct maps *maps, FILE *fp); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 3692e988c86e..0b49fce251fc 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -31,9 +31,6 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { bool perf_mem_record[PERF_MEM_EVENTS__MAX] = { 0 }; -static char mem_loads_name[100]; -static char mem_stores_name[100]; - struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i) { if (i >= PERF_MEM_EVENTS__MAX || !pmu) @@ -81,7 +78,8 @@ int perf_pmu__mem_events_num_mem_pmus(struct perf_pmu *pmu) return num; } -static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu) +static const char *perf_pmu__mem_events_name(struct perf_pmu *pmu, int i, + char *buf, size_t buf_size) { struct perf_mem_event *e; @@ -96,31 +94,31 @@ static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu) if (e->ldlat) { if (!e->aux_event) { /* ARM and Most of Intel */ - scnprintf(mem_loads_name, sizeof(mem_loads_name), + scnprintf(buf, buf_size, e->name, pmu->name, perf_mem_events__loads_ldlat); } else { /* Intel with mem-loads-aux event */ - scnprintf(mem_loads_name, sizeof(mem_loads_name), + scnprintf(buf, buf_size, e->name, pmu->name, pmu->name, perf_mem_events__loads_ldlat); } } else { if (!e->aux_event) { /* AMD and POWER */ - scnprintf(mem_loads_name, sizeof(mem_loads_name), + scnprintf(buf, buf_size, e->name, pmu->name); - } else + } else { return NULL; + } } - - return mem_loads_name; + return buf; } if (i == PERF_MEM_EVENTS__STORE) { - scnprintf(mem_stores_name, sizeof(mem_stores_name), + scnprintf(buf, buf_size, e->name, pmu->name); - return mem_stores_name; + return buf; } return NULL; @@ -189,7 +187,7 @@ static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu if (!e->event_name) return true; - scnprintf(path, PATH_MAX, "%s/devices/%s/events/%s", mnt, pmu->name, e->event_name); + scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/%s", mnt, pmu->name, e->event_name); return !stat(path, &st); } @@ -238,69 +236,87 @@ void perf_pmu__mem_events_list(struct perf_pmu *pmu) int j; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { + char buf[128]; struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j); fprintf(stderr, "%-*s%-*s%s", e->tag ? 13 : 0, e->tag ? : "", e->tag && verbose > 0 ? 25 : 0, - e->tag && verbose > 0 ? perf_pmu__mem_events_name(j, pmu) : "", + e->tag && verbose > 0 + ? perf_pmu__mem_events_name(pmu, j, buf, sizeof(buf)) + : "", e->supported ? ": available\n" : ""); } } -int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) +int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, char **event_name_storage_out) { const char *mnt = sysfs__mount(); struct perf_pmu *pmu = NULL; - struct perf_mem_event *e; int i = *argv_nr; - const char *s; - char *copy; struct perf_cpu_map *cpu_map = NULL; - int ret; + size_t event_name_storage_size = + perf_pmu__mem_events_num_mem_pmus(NULL) * PERF_MEM_EVENTS__MAX * 128; + size_t event_name_storage_remaining = event_name_storage_size; + char *event_name_storage = malloc(event_name_storage_size); + char *event_name_storage_ptr = event_name_storage; + if (!event_name_storage) + return -ENOMEM; + + *event_name_storage_out = NULL; while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) { for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - e = perf_pmu__mem_events_ptr(pmu, j); + const char *s; + struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j); + int ret; if (!perf_mem_record[j]) continue; if (!e->supported) { + char buf[128]; + pr_err("failed: event '%s' not supported\n", - perf_pmu__mem_events_name(j, pmu)); + perf_pmu__mem_events_name(pmu, j, buf, sizeof(buf))); + free(event_name_storage); return -1; } - s = perf_pmu__mem_events_name(j, pmu); + s = perf_pmu__mem_events_name(pmu, j, event_name_storage_ptr, + event_name_storage_remaining); if (!s || !perf_pmu__mem_events_supported(mnt, pmu, e)) continue; - copy = strdup(s); - if (!copy) - return -1; - rec_argv[i++] = "-e"; - rec_argv[i++] = copy; + rec_argv[i++] = event_name_storage_ptr; + event_name_storage_remaining -= strlen(event_name_storage_ptr) + 1; + event_name_storage_ptr += strlen(event_name_storage_ptr) + 1; ret = perf_cpu_map__merge(&cpu_map, pmu->cpus); - if (ret < 0) + if (ret < 0) { + free(event_name_storage); return ret; + } } } if (cpu_map) { - if (!perf_cpu_map__equal(cpu_map, cpu_map__online())) { + struct perf_cpu_map *online = cpu_map__online(); + + if (!perf_cpu_map__equal(cpu_map, online)) { char buf[200]; cpu_map__snprint(cpu_map, buf, sizeof(buf)); pr_warning("Memory events are enabled on a subset of CPUs: %s\n", buf); } + perf_cpu_map__put(online); perf_cpu_map__put(cpu_map); } *argv_nr = i; + *event_name_storage_out = event_name_storage; return 0; } @@ -664,7 +680,10 @@ do { \ 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 (snoop & P(SNOOP, HITM)) + HITM_INC(lcl_hitm); + else + stats->ld_l2hit++; if (snoopx & P(SNOOPX, PEER)) PEER_INC(lcl_peer); @@ -783,3 +802,181 @@ void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add) stats->nomap += add->nomap; stats->noparse += add->noparse; } + +/* + * It returns an index in hist_entry->mem_stat array for the given val which + * represents a data-src based on the mem_stat_type. + */ +int mem_stat_index(const enum mem_stat_type mst, const u64 val) +{ + union perf_mem_data_src src = { + .val = val, + }; + + switch (mst) { + case PERF_MEM_STAT_OP: + switch (src.mem_op) { + case PERF_MEM_OP_LOAD: + return MEM_STAT_OP_LOAD; + case PERF_MEM_OP_STORE: + return MEM_STAT_OP_STORE; + case PERF_MEM_OP_LOAD | PERF_MEM_OP_STORE: + return MEM_STAT_OP_LDST; + default: + if (src.mem_op & PERF_MEM_OP_PFETCH) + return MEM_STAT_OP_PFETCH; + if (src.mem_op & PERF_MEM_OP_EXEC) + return MEM_STAT_OP_EXEC; + return MEM_STAT_OP_OTHER; + } + case PERF_MEM_STAT_CACHE: + switch (src.mem_lvl_num) { + case PERF_MEM_LVLNUM_L1: + return MEM_STAT_CACHE_L1; + case PERF_MEM_LVLNUM_L2: + return MEM_STAT_CACHE_L2; + case PERF_MEM_LVLNUM_L3: + return MEM_STAT_CACHE_L3; + case PERF_MEM_LVLNUM_L4: + return MEM_STAT_CACHE_L4; + case PERF_MEM_LVLNUM_LFB: + return MEM_STAT_CACHE_L1_BUF; + case PERF_MEM_LVLNUM_L2_MHB: + return MEM_STAT_CACHE_L2_BUF; + default: + return MEM_STAT_CACHE_OTHER; + } + case PERF_MEM_STAT_MEMORY: + switch (src.mem_lvl_num) { + case PERF_MEM_LVLNUM_MSC: + return MEM_STAT_MEMORY_MSC; + case PERF_MEM_LVLNUM_RAM: + return MEM_STAT_MEMORY_RAM; + case PERF_MEM_LVLNUM_UNC: + return MEM_STAT_MEMORY_UNC; + case PERF_MEM_LVLNUM_CXL: + return MEM_STAT_MEMORY_CXL; + case PERF_MEM_LVLNUM_IO: + return MEM_STAT_MEMORY_IO; + case PERF_MEM_LVLNUM_PMEM: + return MEM_STAT_MEMORY_PMEM; + default: + return MEM_STAT_MEMORY_OTHER; + } + case PERF_MEM_STAT_SNOOP: + switch (src.mem_snoop) { + case PERF_MEM_SNOOP_HIT: + return MEM_STAT_SNOOP_HIT; + case PERF_MEM_SNOOP_HITM: + return MEM_STAT_SNOOP_HITM; + case PERF_MEM_SNOOP_MISS: + return MEM_STAT_SNOOP_MISS; + default: + return MEM_STAT_SNOOP_OTHER; + } + case PERF_MEM_STAT_DTLB: + switch (src.mem_dtlb) { + case PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT: + return MEM_STAT_DTLB_L1_HIT; + case PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT: + return MEM_STAT_DTLB_L2_HIT; + case PERF_MEM_TLB_L1 | PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT: + return MEM_STAT_DTLB_ANY_HIT; + default: + if (src.mem_dtlb & PERF_MEM_TLB_MISS) + return MEM_STAT_DTLB_MISS; + return MEM_STAT_DTLB_OTHER; + } + default: + break; + } + return -1; +} + +/* To align output, returned string should be shorter than MEM_STAT_PRINT_LEN */ +const char *mem_stat_name(const enum mem_stat_type mst, const int idx) +{ + switch (mst) { + case PERF_MEM_STAT_OP: + switch (idx) { + case MEM_STAT_OP_LOAD: + return "Load"; + case MEM_STAT_OP_STORE: + return "Store"; + case MEM_STAT_OP_LDST: + return "Ld+St"; + case MEM_STAT_OP_PFETCH: + return "Pfetch"; + case MEM_STAT_OP_EXEC: + return "Exec"; + case MEM_STAT_OP_OTHER: + default: + return "Other"; + } + case PERF_MEM_STAT_CACHE: + switch (idx) { + case MEM_STAT_CACHE_L1: + return "L1"; + case MEM_STAT_CACHE_L2: + return "L2"; + case MEM_STAT_CACHE_L3: + return "L3"; + case MEM_STAT_CACHE_L4: + return "L4"; + case MEM_STAT_CACHE_L1_BUF: + return "L1-buf"; + case MEM_STAT_CACHE_L2_BUF: + return "L2-buf"; + case MEM_STAT_CACHE_OTHER: + default: + return "Other"; + } + case PERF_MEM_STAT_MEMORY: + switch (idx) { + case MEM_STAT_MEMORY_RAM: + return "RAM"; + case MEM_STAT_MEMORY_MSC: + return "MSC"; + case MEM_STAT_MEMORY_UNC: + return "Uncach"; + case MEM_STAT_MEMORY_CXL: + return "CXL"; + case MEM_STAT_MEMORY_IO: + return "IO"; + case MEM_STAT_MEMORY_PMEM: + return "PMEM"; + case MEM_STAT_MEMORY_OTHER: + default: + return "Other"; + } + case PERF_MEM_STAT_SNOOP: + switch (idx) { + case MEM_STAT_SNOOP_HIT: + return "Hit"; + case MEM_STAT_SNOOP_HITM: + return "HitM"; + case MEM_STAT_SNOOP_MISS: + return "Miss"; + case MEM_STAT_SNOOP_OTHER: + default: + return "Other"; + } + case PERF_MEM_STAT_DTLB: + switch (idx) { + case MEM_STAT_DTLB_L1_HIT: + return "L1-Hit"; + case MEM_STAT_DTLB_L2_HIT: + return "L2-Hit"; + case MEM_STAT_DTLB_ANY_HIT: + return "L?-Hit"; + case MEM_STAT_DTLB_MISS: + return "Miss"; + case MEM_STAT_DTLB_OTHER: + default: + return "Other"; + } + default: + break; + } + return "N/A"; +} diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 8dc27db9fd52..5b98076904b0 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -38,7 +38,8 @@ int perf_pmu__mem_events_num_mem_pmus(struct perf_pmu *pmu); bool is_mem_loads_aux_event(struct evsel *leader); void perf_pmu__mem_events_list(struct perf_pmu *pmu); -int perf_mem_events__record_args(const char **rec_argv, int *argv_nr); +int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, + char **event_name_storage_out); int perf_mem__tlb_scnprintf(char *out, size_t sz, const struct mem_info *mem_info); int perf_mem__lvl_scnprintf(char *out, size_t sz, const struct mem_info *mem_info); @@ -88,4 +89,61 @@ 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); +enum mem_stat_type { + PERF_MEM_STAT_OP, + PERF_MEM_STAT_CACHE, + PERF_MEM_STAT_MEMORY, + PERF_MEM_STAT_SNOOP, + PERF_MEM_STAT_DTLB, +}; + +#define MEM_STAT_PRINT_LEN 7 /* 1 space + 5 digits + 1 percent sign */ + +enum mem_stat_op { + MEM_STAT_OP_LOAD, + MEM_STAT_OP_STORE, + MEM_STAT_OP_LDST, + MEM_STAT_OP_PFETCH, + MEM_STAT_OP_EXEC, + MEM_STAT_OP_OTHER, +}; + +enum mem_stat_cache { + MEM_STAT_CACHE_L1, + MEM_STAT_CACHE_L2, + MEM_STAT_CACHE_L3, + MEM_STAT_CACHE_L4, + MEM_STAT_CACHE_L1_BUF, + MEM_STAT_CACHE_L2_BUF, + MEM_STAT_CACHE_OTHER, +}; + +enum mem_stat_memory { + MEM_STAT_MEMORY_RAM, + MEM_STAT_MEMORY_MSC, + MEM_STAT_MEMORY_UNC, + MEM_STAT_MEMORY_CXL, + MEM_STAT_MEMORY_IO, + MEM_STAT_MEMORY_PMEM, + MEM_STAT_MEMORY_OTHER, +}; + +enum mem_stat_snoop { + MEM_STAT_SNOOP_HIT, + MEM_STAT_SNOOP_HITM, + MEM_STAT_SNOOP_MISS, + MEM_STAT_SNOOP_OTHER, +}; + +enum mem_stat_dtlb { + MEM_STAT_DTLB_L1_HIT, + MEM_STAT_DTLB_L2_HIT, + MEM_STAT_DTLB_ANY_HIT, + MEM_STAT_DTLB_MISS, + MEM_STAT_DTLB_OTHER, +}; + +int mem_stat_index(const enum mem_stat_type mst, const u64 data_src); +const char *mem_stat_name(const enum mem_stat_type mst, const int idx); + #endif /* __PERF_MEM_EVENTS_H */ diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c index 03a7d7b27737..51a2292cbf7e 100644 --- a/tools/perf/util/mem2node.c +++ b/tools/perf/util/mem2node.c @@ -59,7 +59,7 @@ int mem2node__init(struct mem2node *map, struct perf_env *env) max += bitmap_weight(n->set, n->size); } - entries = zalloc(sizeof(*entries) * max); + entries = calloc(max, sizeof(*entries)); if (!entries) return -ENOMEM; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 46920ebadfd1..4db9578efd81 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -103,7 +103,7 @@ static void metric_event_delete(struct rblist *rblist __maybe_unused, free(me); } -static void metricgroup__rblist_init(struct rblist *metric_events) +void metricgroup__rblist_init(struct rblist *metric_events) { rblist__init(metric_events); metric_events->node_cmp = metric_event_cmp; @@ -152,6 +152,8 @@ struct metric { * Should events of the metric be grouped? */ bool group_events; + /** Show events even if in the Default metric group. */ + bool default_show_events; /** * Parsed events for the metric. Optional as events may be taken from a * different metric whose group contains all the IDs necessary for this @@ -179,7 +181,7 @@ static void metric__watchdog_constraint_hint(const char *name, bool foot) " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); } -static bool metric__group_events(const struct pmu_metric *pm) +static bool metric__group_events(const struct pmu_metric *pm, bool metric_no_threshold) { switch (pm->event_grouping) { case MetricNoGroupEvents: @@ -191,6 +193,13 @@ static bool metric__group_events(const struct pmu_metric *pm) return false; case MetricNoGroupEventsSmt: return !smt_on(); + case MetricNoGroupEventsThresholdAndNmi: + if (metric_no_threshold) + return true; + if (!sysctl__nmi_watchdog_enabled()) + return true; + metric__watchdog_constraint_hint(pm->metric_name, /*foot=*/false); + return false; case MetricGroupEvents: default: return true; @@ -212,6 +221,7 @@ static void metric__free(struct metric *m) static struct metric *metric__new(const struct pmu_metric *pm, const char *modifier, bool metric_no_group, + bool metric_no_threshold, int runtime, const char *user_requested_cpu_list, bool system_wide) @@ -246,7 +256,8 @@ static struct metric *metric__new(const struct pmu_metric *pm, } m->pctx->sctx.runtime = runtime; m->pctx->sctx.system_wide = system_wide; - m->group_events = !metric_no_group && metric__group_events(pm); + m->group_events = !metric_no_group && metric__group_events(pm, metric_no_threshold); + m->default_show_events = pm->default_show_events; m->metric_refs = NULL; m->evlist = NULL; @@ -353,10 +364,10 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids, return 0; } -static bool match_metric(const char *metric_or_groups, const char *sought) +static bool match_metric_or_groups(const char *metric_or_groups, const char *sought) { int len; - char *m; + const char *m; if (!sought) return false; @@ -369,117 +380,24 @@ static bool match_metric(const char *metric_or_groups, const char *sought) (metric_or_groups[len] == 0 || metric_or_groups[len] == ';')) return true; m = strchr(metric_or_groups, ';'); - return m && match_metric(m + 1, sought); + return m && match_metric_or_groups(m + 1, sought); } -static bool match_pm_metric(const struct pmu_metric *pm, const char *pmu, const char *metric) +static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *pmu, + const char *metric_or_groups) { const char *pm_pmu = pm->pmu ?: "cpu"; + struct perf_pmu *perf_pmu = NULL; - if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu)) - return false; - - return match_metric(pm->metric_group, metric) || - match_metric(pm->metric_name, metric); -} - -/** struct mep - RB-tree node for building printing information. */ -struct mep { - /** nd - RB-tree element. */ - struct rb_node nd; - /** @metric_group: Owned metric group name, separated others with ';'. */ - char *metric_group; - const char *metric_name; - const char *metric_desc; - const char *metric_long_desc; - const char *metric_expr; - const char *metric_threshold; - const char *metric_unit; -}; - -static int mep_cmp(struct rb_node *rb_node, const void *entry) -{ - struct mep *a = container_of(rb_node, struct mep, nd); - struct mep *b = (struct mep *)entry; - int ret; - - ret = strcmp(a->metric_group, b->metric_group); - if (ret) - return ret; - - return strcmp(a->metric_name, b->metric_name); -} - -static struct rb_node *mep_new(struct rblist *rl __maybe_unused, const void *entry) -{ - struct mep *me = malloc(sizeof(struct mep)); - - if (!me) - return NULL; - - memcpy(me, entry, sizeof(struct mep)); - return &me->nd; -} - -static void mep_delete(struct rblist *rl __maybe_unused, - struct rb_node *nd) -{ - struct mep *me = container_of(nd, struct mep, nd); - - zfree(&me->metric_group); - free(me); -} - -static struct mep *mep_lookup(struct rblist *groups, const char *metric_group, - const char *metric_name) -{ - struct rb_node *nd; - struct mep me = { - .metric_group = strdup(metric_group), - .metric_name = metric_name, - }; - nd = rblist__find(groups, &me); - if (nd) { - free(me.metric_group); - return container_of(nd, struct mep, nd); - } - rblist__add_node(groups, &me); - nd = rblist__find(groups, &me); - if (nd) - return container_of(nd, struct mep, nd); - return NULL; -} - -static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm, - struct rblist *groups) -{ - const char *g; - char *omg, *mg; - - mg = strdup(pm->metric_group ?: pm->metric_name); - if (!mg) - return -ENOMEM; - omg = mg; - while ((g = strsep(&mg, ";")) != NULL) { - struct mep *me; + if (pm->pmu) + perf_pmu = perf_pmus__find(pm->pmu); - g = skip_spaces(g); - if (strlen(g)) - me = mep_lookup(groups, g, pm->metric_name); - else - me = mep_lookup(groups, pm->metric_name, pm->metric_name); - - if (me) { - me->metric_desc = pm->desc; - me->metric_long_desc = pm->long_desc; - me->metric_expr = pm->metric_expr; - me->metric_threshold = pm->metric_threshold; - me->metric_unit = pm->unit; - } - } - free(omg); + if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) && + (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu))) + return false; - return 0; + return match_metric_or_groups(pm->metric_group, metric_or_groups) || + match_metric_or_groups(pm->metric_name, metric_or_groups); } struct metricgroup_iter_data { @@ -507,64 +425,40 @@ static int metricgroup__sys_event_iter(const struct pmu_metric *pm, return 0; } -static int metricgroup__add_to_mep_groups_callback(const struct pmu_metric *pm, - const struct pmu_metrics_table *table __maybe_unused, - void *vdata) +int metricgroup__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, + void *data) { - struct rblist *groups = vdata; + struct metricgroup_iter_data sys_data = { + .fn = fn, + .data = data, + }; + const struct pmu_metrics_table *tables[2] = { + table, + pmu_metrics_table__default(), + }; - return metricgroup__add_to_mep_groups(pm, groups); -} + for (size_t i = 0; i < ARRAY_SIZE(tables); i++) { + int ret; -void metricgroup__print(const struct print_callbacks *print_cb, void *print_state) -{ - struct rblist groups; - const struct pmu_metrics_table *table; - struct rb_node *node, *next; - - rblist__init(&groups); - groups.node_new = mep_new; - groups.node_cmp = mep_cmp; - groups.node_delete = mep_delete; - table = pmu_metrics_table__find(); - if (table) { - pmu_metrics_table__for_each_metric(table, - metricgroup__add_to_mep_groups_callback, - &groups); - } - { - struct metricgroup_iter_data data = { - .fn = metricgroup__add_to_mep_groups_callback, - .data = &groups, - }; - pmu_for_each_sys_metric(metricgroup__sys_event_iter, &data); - } + if (!tables[i]) + continue; - for (node = rb_first_cached(&groups.entries); node; node = next) { - struct mep *me = container_of(node, struct mep, nd); - - print_cb->print_metric(print_state, - me->metric_group, - me->metric_name, - me->metric_desc, - me->metric_long_desc, - me->metric_expr, - me->metric_threshold, - me->metric_unit); - next = rb_next(node); - rblist__remove_node(&groups, node); + ret = pmu_metrics_table__for_each_metric(tables[i], fn, data); + if (ret) + return ret; } + + return pmu_for_each_sys_metric(metricgroup__sys_event_iter, &sys_data); } static const char *code_characters = ",-=@"; static int encode_metric_id(struct strbuf *sb, const char *x) { - char *c; int ret = 0; for (; *x; x++) { - c = strchr(code_characters, *x); + const char *c = strchr(code_characters, *x); if (c) { ret = strbuf_addch(sb, '!'); if (ret) @@ -802,11 +696,6 @@ struct metricgroup_add_iter_data { const struct pmu_metrics_table *table; }; -static bool metricgroup__find_metric(const char *pmu, - const char *metric, - const struct pmu_metrics_table *table, - struct pmu_metric *pm); - static int add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, @@ -818,6 +707,16 @@ static int add_metric(struct list_head *metric_list, const struct visited_metric *visited, const struct pmu_metrics_table *table); +static int metricgroup__find_metric_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *vdata) +{ + struct pmu_metric *copied_pm = vdata; + + memcpy(copied_pm, pm, sizeof(*pm)); + return 0; +} + /** * resolve_metric - Locate metrics within the root metric and recursively add * references to them. @@ -838,7 +737,7 @@ static int add_metric(struct list_head *metric_list, * architecture perf is running upon. */ static int resolve_metric(struct list_head *metric_list, - const char *pmu, + struct perf_pmu *pmu, const char *modifier, bool metric_no_group, bool metric_no_threshold, @@ -868,7 +767,9 @@ static int resolve_metric(struct list_head *metric_list, hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) { struct pmu_metric pm; - if (metricgroup__find_metric(pmu, cur->pkey, table, &pm)) { + if (pmu_metrics_table__find_metric(table, pmu, cur->pkey, + metricgroup__find_metric_callback, + &pm) != PMU_METRICS__NOT_FOUND) { pending = realloc(pending, (pending_cnt + 1) * sizeof(struct to_resolve)); if (!pending) @@ -953,8 +854,8 @@ static int __add_metric(struct list_head *metric_list, * This metric is the root of a tree and may reference other * metrics that are added recursively. */ - root_metric = metric__new(pm, modifier, metric_no_group, runtime, - user_requested_cpu_list, system_wide); + root_metric = metric__new(pm, modifier, metric_no_group, metric_no_threshold, + runtime, user_requested_cpu_list, system_wide); if (!root_metric) return -ENOMEM; @@ -1013,13 +914,17 @@ static int __add_metric(struct list_head *metric_list, expr = metric_no_threshold ? pm->metric_name : pm->metric_threshold; visited_node.name = "__threshold__"; } - if (expr__find_ids(expr, NULL, root_metric->pctx) < 0) { - /* Broken metric. */ - ret = -EINVAL; - } + + ret = expr__find_ids(expr, NULL, root_metric->pctx); + if (!ret) { /* Resolve referenced metrics. */ - const char *pmu = pm->pmu ?: "cpu"; + struct perf_pmu *pmu; + + if (pm->pmu && pm->pmu[0] != '\0') + pmu = perf_pmus__find(pm->pmu); + else + pmu = perf_pmus__scan_core(/*pmu=*/ NULL); ret = resolve_metric(metric_list, pmu, modifier, metric_no_group, metric_no_threshold, user_requested_cpu_list, @@ -1036,44 +941,6 @@ static int __add_metric(struct list_head *metric_list, return ret; } -struct metricgroup__find_metric_data { - const char *pmu; - const char *metric; - struct pmu_metric *pm; -}; - -static int metricgroup__find_metric_callback(const struct pmu_metric *pm, - const struct pmu_metrics_table *table __maybe_unused, - void *vdata) -{ - struct metricgroup__find_metric_data *data = vdata; - const char *pm_pmu = pm->pmu ?: "cpu"; - - if (strcmp(data->pmu, "all") && strcmp(pm_pmu, data->pmu)) - return 0; - - if (!match_metric(pm->metric_name, data->metric)) - return 0; - - memcpy(data->pm, pm, sizeof(*pm)); - return 1; -} - -static bool metricgroup__find_metric(const char *pmu, - const char *metric, - const struct pmu_metrics_table *table, - struct pmu_metric *pm) -{ - struct metricgroup__find_metric_data data = { - .pmu = pmu, - .metric = metric, - .pm = pm, - }; - - return pmu_metrics_table__for_each_metric(table, metricgroup__find_metric_callback, &data) - ? true : false; -} - static int add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, @@ -1112,29 +979,6 @@ static int add_metric(struct list_head *metric_list, return ret; } -static int metricgroup__add_metric_sys_event_iter(const struct pmu_metric *pm, - const struct pmu_metrics_table *table __maybe_unused, - void *data) -{ - struct metricgroup_add_iter_data *d = data; - int ret; - - if (!match_pm_metric(pm, d->pmu, d->metric_name)) - return 0; - - ret = add_metric(d->metric_list, pm, d->modifier, d->metric_no_group, - d->metric_no_threshold, d->user_requested_cpu_list, - d->system_wide, d->root_metric, d->visited, d->table); - if (ret) - goto out; - - *(d->has_match) = true; - -out: - *(d->ret) = ret; - return ret; -} - /** * metric_list_cmp - list_sort comparator that sorts metrics with more events to * the front. tool events are excluded from the count. @@ -1200,9 +1044,9 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && match_pm_metric(pm, data->pmu, data->metric_name)) { + if (pm->metric_expr && match_pm_metric_or_groups(pm, data->pmu, data->metric_name)) { bool metric_no_group = data->metric_no_group || - match_metric(pm->metricgroup_no_group, data->metric_name); + match_metric_or_groups(pm->metricgroup_no_group, data->metric_name); data->has_match = true; ret = add_metric(data->list, pm, data->modifier, metric_no_group, @@ -1238,55 +1082,26 @@ static int metricgroup__add_metric(const char *pmu, const char *metric_name, con { LIST_HEAD(list); int ret; - bool has_match = false; - - { - struct metricgroup__add_metric_data data = { - .list = &list, - .pmu = pmu, - .metric_name = metric_name, - .modifier = modifier, - .metric_no_group = metric_no_group, - .metric_no_threshold = metric_no_threshold, - .user_requested_cpu_list = user_requested_cpu_list, - .system_wide = system_wide, - .has_match = false, - }; - /* - * Iterate over all metrics seeing if metric matches either the - * name or group. When it does add the metric to the list. - */ - ret = pmu_metrics_table__for_each_metric(table, metricgroup__add_metric_callback, - &data); - if (ret) - goto out; + struct metricgroup__add_metric_data data = { + .list = &list, + .pmu = pmu, + .metric_name = metric_name, + .modifier = modifier, + .metric_no_group = metric_no_group, + .metric_no_threshold = metric_no_threshold, + .user_requested_cpu_list = user_requested_cpu_list, + .system_wide = system_wide, + .has_match = false, + }; - has_match = data.has_match; - } - { - struct metricgroup_iter_data data = { - .fn = metricgroup__add_metric_sys_event_iter, - .data = (void *) &(struct metricgroup_add_iter_data) { - .metric_list = &list, - .pmu = pmu, - .metric_name = metric_name, - .modifier = modifier, - .metric_no_group = metric_no_group, - .user_requested_cpu_list = user_requested_cpu_list, - .system_wide = system_wide, - .has_match = &has_match, - .ret = &ret, - .table = table, - }, - }; - - pmu_for_each_sys_metric(metricgroup__sys_event_iter, &data); - } - /* End of pmu events. */ - if (!has_match) - ret = -EINVAL; + /* + * Iterate over all metrics seeing if metric matches either the + * name or group. When it does add the metric to the list. + */ + ret = metricgroup__for_each_metric(table, metricgroup__add_metric_callback, &data); + if (!ret && !data.has_match) + ret = -ENOENT; -out: /* * add to metric_list so that they can be released * even if it's failed @@ -1336,6 +1151,8 @@ static int metricgroup__add_metric_list(const char *pmu, const char *list, user_requested_cpu_list, system_wide, metric_list, table); if (ret == -EINVAL) + pr_err("Fail to parse metric or group `%s'\n", metric_name); + else if (ret == -ENOENT) pr_err("Cannot find metric or group `%s'\n", metric_name); if (ret) @@ -1448,7 +1265,8 @@ err_out: static int parse_ids(bool metric_no_merge, bool fake_pmu, struct expr_parse_ctx *ids, const char *modifier, bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX], - struct evlist **out_evlist) + struct evlist **out_evlist, + const char *filter_pmu) { struct parse_events_error parse_error; struct evlist *parsed_evlist; @@ -1502,7 +1320,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu, } pr_debug("Parsing metric events '%s'\n", events.buf); parse_events_error__init(&parse_error); - ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL, + ret = __parse_events(parsed_evlist, events.buf, filter_pmu, &parse_error, fake_pmu, /*warn_if_reordered=*/false, /*fake_tp=*/false); if (ret) { @@ -1522,6 +1340,51 @@ err_out: return ret; } +/* How many times will a given evsel be used in a set of metrics? */ +static int count_uses(struct list_head *metric_list, struct evsel *evsel) +{ + const char *metric_id = evsel__metric_id(evsel); + struct metric *m; + int uses = 0; + + list_for_each_entry(m, metric_list, nd) { + if (hashmap__find(m->pctx->ids, metric_id, NULL)) + uses++; + } + return uses; +} + +/* + * Select the evsel that stat-display will use to trigger shadow/metric + * printing. Pick the least shared non-tool evsel, encouraging metrics to be + * with a hardware counter that is specific to them. + */ +static struct evsel *pick_display_evsel(struct list_head *metric_list, + struct evsel **metric_events) +{ + struct evsel *selected = metric_events[0]; + size_t selected_uses; + bool selected_is_tool; + + if (!selected) + return NULL; + + selected_uses = count_uses(metric_list, selected); + selected_is_tool = evsel__is_tool(selected); + for (int i = 1; metric_events[i]; i++) { + struct evsel *candidate = metric_events[i]; + size_t candidate_uses = count_uses(metric_list, candidate); + + if ((selected_is_tool && !evsel__is_tool(candidate)) || + (candidate_uses < selected_uses)) { + selected = candidate; + selected_uses = candidate_uses; + selected_is_tool = evsel__is_tool(selected); + } + } + return selected; +} + static int parse_groups(struct evlist *perf_evlist, const char *pmu, const char *str, bool metric_no_group, @@ -1530,7 +1393,6 @@ static int parse_groups(struct evlist *perf_evlist, const char *user_requested_cpu_list, bool system_wide, bool fake_pmu, - struct rblist *metric_events_list, const struct pmu_metrics_table *table) { struct evlist *combined_evlist = NULL; @@ -1540,8 +1402,6 @@ static int parse_groups(struct evlist *perf_evlist, bool is_default = !strcmp(str, "Default"); int ret; - if (metric_events_list->nr_entries == 0) - metricgroup__rblist_init(metric_events_list); ret = metricgroup__add_metric_list(pmu, str, metric_no_group, metric_no_threshold, user_requested_cpu_list, system_wide, &metric_list, table); @@ -1563,7 +1423,8 @@ static int parse_groups(struct evlist *perf_evlist, /*modifier=*/NULL, /*group_events=*/false, tool_events, - &combined_evlist); + &combined_evlist, + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu); } if (combined) expr__ctx_free(combined); @@ -1618,7 +1479,8 @@ static int parse_groups(struct evlist *perf_evlist, } if (!metric_evlist) { ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier, - m->group_events, tool_events, &m->evlist); + m->group_events, tool_events, &m->evlist, + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu); if (ret) goto out; @@ -1632,7 +1494,9 @@ static int parse_groups(struct evlist *perf_evlist, goto out; } - me = metricgroup__lookup(metric_events_list, metric_events[0], true); + me = metricgroup__lookup(&perf_evlist->metric_events, + pick_display_evsel(&metric_list, metric_events), + /*create=*/true); expr = malloc(sizeof(struct metric_expr)); if (!expr) { @@ -1656,9 +1520,20 @@ static int parse_groups(struct evlist *perf_evlist, if (!expr->metric_name) { ret = -ENOMEM; + free(expr); free(metric_events); goto out; } + if (m->default_show_events) { + struct evsel *pos; + + for (int i = 0; metric_events[i]; i++) + metric_events[i]->default_show_events = true; + evlist__for_each_entry(metric_evlist, pos) { + if (pos->metric_leader && pos->metric_leader->default_show_events) + pos->default_show_events = true; + } + } expr->metric_threshold = m->metric_threshold; expr->metric_unit = m->metric_unit; expr->metric_events = metric_events; @@ -1692,25 +1567,21 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, - bool hardware_aware_grouping, - struct rblist *metric_events) + bool hardware_aware_grouping) { const struct pmu_metrics_table *table = pmu_metrics_table__find(); - if (!table) - return -EINVAL; if (hardware_aware_grouping) pr_debug("Use hardware aware grouping instead of traditional metric grouping method\n"); return parse_groups(perf_evlist, pmu, str, metric_no_group, metric_no_merge, metric_no_threshold, user_requested_cpu_list, system_wide, - /*fake_pmu=*/false, metric_events, table); + /*fake_pmu=*/false, table); } int metricgroup__parse_groups_test(struct evlist *evlist, const struct pmu_metrics_table *table, - const char *str, - struct rblist *metric_events) + const char *str) { return parse_groups(evlist, "all", str, /*metric_no_group=*/false, @@ -1718,34 +1589,34 @@ int metricgroup__parse_groups_test(struct evlist *evlist, /*metric_no_threshold=*/false, /*user_requested_cpu_list=*/NULL, /*system_wide=*/false, - /*fake_pmu=*/true, metric_events, table); + /*fake_pmu=*/true, table); } struct metricgroup__has_metric_data { const char *pmu; - const char *metric; + const char *metric_or_groups; }; -static int metricgroup__has_metric_callback(const struct pmu_metric *pm, - const struct pmu_metrics_table *table __maybe_unused, - void *vdata) +static int metricgroup__has_metric_or_groups_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table + __maybe_unused, + void *vdata) { struct metricgroup__has_metric_data *data = vdata; - return match_pm_metric(pm, data->pmu, data->metric) ? 1 : 0; + return match_pm_metric_or_groups(pm, data->pmu, data->metric_or_groups) ? 1 : 0; } -bool metricgroup__has_metric(const char *pmu, const char *metric) +bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_groups) { const struct pmu_metrics_table *table = pmu_metrics_table__find(); struct metricgroup__has_metric_data data = { .pmu = pmu, - .metric = metric, + .metric_or_groups = metric_or_groups, }; - if (!table) - return false; - - return pmu_metrics_table__for_each_metric(table, metricgroup__has_metric_callback, &data) + return metricgroup__for_each_metric(table, + metricgroup__has_metric_or_groups_callback, + &data) ? true : false; } @@ -1800,13 +1671,14 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, evsel = evlist__find_evsel(evlist, old_me->evsel->core.idx); if (!evsel) return -EINVAL; - new_me = metricgroup__lookup(new_metric_events, evsel, true); + new_me = metricgroup__lookup(new_metric_events, evsel, /*create=*/true); if (!new_me) return -ENOMEM; pr_debug("copying metric event for cgroup '%s': %s (idx=%d)\n", cgrp ? cgrp->name : "root", evsel->name, evsel->core.idx); + new_me->is_default = old_me->is_default; list_for_each_entry(old_expr, &old_me->head, nd) { new_expr = malloc(sizeof(*new_expr)); if (!new_expr) @@ -1820,6 +1692,7 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, new_expr->metric_unit = old_expr->metric_unit; new_expr->runtime = old_expr->runtime; + new_expr->default_metricgroup_name = old_expr->default_metricgroup_name; if (old_expr->metric_refs) { /* calculate number of metric_events */ diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 779f6ede1b51..4be6bfc13c46 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -16,7 +16,7 @@ struct cgroup; /** * A node in a rblist keyed by the evsel. The global rblist of metric events - * generally exists in perf_stat_config. The evsel is looked up in the rblist + * generally exists in evlist. The evsel is looked up in the rblist * yielding a list of metric_expr. */ struct metric_event { @@ -77,17 +77,17 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, - bool hardware_aware_grouping, - struct rblist *metric_events); + bool hardware_aware_grouping); int metricgroup__parse_groups_test(struct evlist *evlist, const struct pmu_metrics_table *table, - const char *str, - struct rblist *metric_events); + const char *str); -void metricgroup__print(const struct print_callbacks *print_cb, void *print_state); -bool metricgroup__has_metric(const char *pmu, const char *metric); +int metricgroup__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn, + void *data); +bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_groups); unsigned int metricgroups__topdown_max_level(void); int arch_get_runtimeparam(const struct pmu_metric *pm); +void metricgroup__rblist_init(struct rblist *metric_events); void metricgroup__rblist_exit(struct rblist *metric_events); int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 43b02293f1d2..b69f926d314b 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -7,6 +7,7 @@ */ #include <sys/mman.h> +#include <errno.h> #include <inttypes.h> #include <asm/bug.h> #include <linux/zalloc.h> @@ -244,9 +245,8 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask) { int idx, nr_cpus; struct perf_cpu cpu; - const struct perf_cpu_map *cpu_map = NULL; + struct perf_cpu_map *cpu_map = cpu_map__online(); - cpu_map = cpu_map__online(); if (!cpu_map) return; @@ -256,6 +256,7 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask) if (cpu__get_node(cpu) == node) __set_bit(cpu.cpu, mask->bits); } + perf_cpu_map__put(cpu_map); } static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) @@ -356,14 +357,3 @@ int perf_mmap__push(struct mmap *md, void *to, out: return rc; } - -int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, struct mmap_cpu_mask *clone) -{ - clone->nbits = original->nbits; - clone->bits = bitmap_zalloc(original->nbits); - if (!clone->bits) - return -ENOMEM; - - memcpy(clone->bits, original->bits, MMAP_CPU_MASK_BYTES(original)); - return 0; -} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 0df6e1621c7e..4d72c5fa5084 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -61,7 +61,4 @@ size_t mmap__mmap_len(struct mmap *map); void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag); -int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, - struct mmap_cpu_mask *clone); - #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/mutex.c b/tools/perf/util/mutex.c index bca7f0717f35..7aa1f3f55a7d 100644 --- a/tools/perf/util/mutex.c +++ b/tools/perf/util/mutex.c @@ -17,7 +17,7 @@ static void check_err(const char *fn, int err) #define CHECK_ERR(err) check_err(__func__, err) -static void __mutex_init(struct mutex *mtx, bool pshared) +static void __mutex_init(struct mutex *mtx, bool pshared, bool recursive) { pthread_mutexattr_t attr; @@ -27,21 +27,27 @@ static void __mutex_init(struct mutex *mtx, bool pshared) /* In normal builds enable error checking, such as recursive usage. */ CHECK_ERR(pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_ERRORCHECK)); #endif + if (recursive) + CHECK_ERR(pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)); if (pshared) CHECK_ERR(pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED)); - CHECK_ERR(pthread_mutex_init(&mtx->lock, &attr)); CHECK_ERR(pthread_mutexattr_destroy(&attr)); } void mutex_init(struct mutex *mtx) { - __mutex_init(mtx, /*pshared=*/false); + __mutex_init(mtx, /*pshared=*/false, /*recursive=*/false); } void mutex_init_pshared(struct mutex *mtx) { - __mutex_init(mtx, /*pshared=*/true); + __mutex_init(mtx, /*pshared=*/true, /*recursive=*/false); +} + +void mutex_init_recursive(struct mutex *mtx) +{ + __mutex_init(mtx, /*pshared=*/false, /*recursive=*/true); } void mutex_destroy(struct mutex *mtx) diff --git a/tools/perf/util/mutex.h b/tools/perf/util/mutex.h index 40661120cacc..70232d8d094f 100644 --- a/tools/perf/util/mutex.h +++ b/tools/perf/util/mutex.h @@ -33,10 +33,22 @@ /* Documents if a type is a lockable type. */ #define LOCKABLE __attribute__((lockable)) +/* Documents a function that expects a lock not to be held prior to entry. */ +#define LOCKS_EXCLUDED(...) __attribute__((locks_excluded(__VA_ARGS__))) + +/* Documents a function that returns a lock. */ +#define LOCK_RETURNED(x) __attribute__((lock_returned(x))) + /* Documents functions that acquire a lock in the body of a function, and do not release it. */ #define EXCLUSIVE_LOCK_FUNCTION(...) __attribute__((exclusive_lock_function(__VA_ARGS__))) /* + * Documents functions that acquire a shared (reader) lock in the body of a + * function, and do not release it. + */ +#define SHARED_LOCK_FUNCTION(...) __attribute__((shared_lock_function(__VA_ARGS__))) + +/* * Documents functions that expect a lock to be held on entry to the function, * and release it in the body of the function. */ @@ -49,6 +61,9 @@ /* Documents a function that expects a mutex to be held prior to entry. */ #define EXCLUSIVE_LOCKS_REQUIRED(...) __attribute__((exclusive_locks_required(__VA_ARGS__))) +/* Documents a function that expects a shared (reader) lock to be held prior to entry. */ +#define SHARED_LOCKS_REQUIRED(...) __attribute__((shared_locks_required(__VA_ARGS__))) + /* Turns off thread safety checking within the body of a particular function. */ #define NO_THREAD_SAFETY_ANALYSIS __attribute__((no_thread_safety_analysis)) @@ -57,10 +72,14 @@ #define GUARDED_BY(x) #define PT_GUARDED_BY(x) #define LOCKABLE +#define LOCKS_EXCLUDED(...) +#define LOCK_RETURNED(x) #define EXCLUSIVE_LOCK_FUNCTION(...) +#define SHARED_LOCK_FUNCTION(...) #define UNLOCK_FUNCTION(...) #define EXCLUSIVE_TRYLOCK_FUNCTION(...) #define EXCLUSIVE_LOCKS_REQUIRED(...) +#define SHARED_LOCKS_REQUIRED(...) #define NO_THREAD_SAFETY_ANALYSIS #endif @@ -85,6 +104,8 @@ void mutex_init(struct mutex *mtx); * process-private attribute. */ void mutex_init_pshared(struct mutex *mtx); +/* Initializes a mutex that may be recursively held on the same thread. */ +void mutex_init_recursive(struct mutex *mtx); void mutex_destroy(struct mutex *mtx); void mutex_lock(struct mutex *mtx) EXCLUSIVE_LOCK_FUNCTION(*mtx); diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 68f5de2d79c7..01502570b32d 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -6,7 +6,6 @@ #include "namespaces.h" #include "event.h" -#include "get_current_dir_name.h" #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> @@ -293,14 +292,14 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, if (!nsi || !nsinfo__need_setns(nsi)) return; - if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) + if (!getcwd(curpath, sizeof(curpath))) return; - oldcwd = get_current_dir_name(); + oldcwd = strdup(curpath); if (!oldcwd) return; - oldns = open(curpath, O_RDONLY); + oldns = open("/proc/self/ns/mnt", O_RDONLY); if (oldns < 0) goto errout; diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h index 2dd67c60f211..64bf763ddf50 100644 --- a/tools/perf/util/off_cpu.h +++ b/tools/perf/util/off_cpu.h @@ -13,9 +13,10 @@ struct record_opts; #define OFFCPU_SAMPLE_TYPES (PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_IP | \ PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | \ - PERF_SAMPLE_PERIOD | PERF_SAMPLE_CALLCHAIN | \ + PERF_SAMPLE_PERIOD | PERF_SAMPLE_RAW | \ PERF_SAMPLE_CGROUP) +#define OFFCPU_THRESH 500000000ULL #ifdef HAVE_BPF_SKEL int off_cpu_prepare(struct evlist *evlist, struct target *target, diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index 8c62611f10aa..a5857f9f5af2 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -243,7 +243,7 @@ static int do_flush(struct ordered_events *oe, bool show_progress) if (iter->timestamp > limit) break; ret = oe->deliver(oe, iter); - if (ret) + if (ret < 0) return ret; ordered_events__delete(oe, iter); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 1e23faa364b1..1497e1f2a08c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -7,6 +7,7 @@ #include <errno.h> #include <sys/ioctl.h> #include <sys/param.h> +#include "cpumap.h" #include "term.h" #include "env.h" #include "evlist.h" @@ -16,19 +17,22 @@ #include "string2.h" #include "strbuf.h" #include "debug.h" -#include <api/fs/tracing_path.h> #include <perf/cpumap.h> #include <util/parse-events-bison.h> #include <util/parse-events-flex.h> #include "pmu.h" #include "pmus.h" +#include "tp_pmu.h" #include "asm/bug.h" +#include "ui/ui.h" #include "util/parse-branch-options.h" #include "util/evsel_config.h" #include "util/event.h" #include "util/bpf-filter.h" +#include "util/stat.h" #include "util/util.h" #include "tracepoint.h" +#include <api/fs/tracing_path.h> #define MAX_NAME_LEN 100 @@ -36,121 +40,23 @@ static int get_config_terms(const struct parse_events_terms *head_config, struct list_head *head_terms); static int parse_events_terms__copy(const struct parse_events_terms *src, struct parse_events_terms *dest); - -const struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { - [PERF_COUNT_HW_CPU_CYCLES] = { - .symbol = "cpu-cycles", - .alias = "cycles", - }, - [PERF_COUNT_HW_INSTRUCTIONS] = { - .symbol = "instructions", - .alias = "", - }, - [PERF_COUNT_HW_CACHE_REFERENCES] = { - .symbol = "cache-references", - .alias = "", - }, - [PERF_COUNT_HW_CACHE_MISSES] = { - .symbol = "cache-misses", - .alias = "", - }, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { - .symbol = "branch-instructions", - .alias = "branches", - }, - [PERF_COUNT_HW_BRANCH_MISSES] = { - .symbol = "branch-misses", - .alias = "", - }, - [PERF_COUNT_HW_BUS_CYCLES] = { - .symbol = "bus-cycles", - .alias = "", - }, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = { - .symbol = "stalled-cycles-frontend", - .alias = "idle-cycles-frontend", - }, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = { - .symbol = "stalled-cycles-backend", - .alias = "idle-cycles-backend", - }, - [PERF_COUNT_HW_REF_CPU_CYCLES] = { - .symbol = "ref-cycles", - .alias = "", - }, +static int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb); + +static const char *const event_types[] = { + [PERF_TYPE_HARDWARE] = "hardware", + [PERF_TYPE_SOFTWARE] = "software", + [PERF_TYPE_TRACEPOINT] = "tracepoint", + [PERF_TYPE_HW_CACHE] = "hardware-cache", + [PERF_TYPE_RAW] = "raw", + [PERF_TYPE_BREAKPOINT] = "breakpoint", }; -const struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { - [PERF_COUNT_SW_CPU_CLOCK] = { - .symbol = "cpu-clock", - .alias = "", - }, - [PERF_COUNT_SW_TASK_CLOCK] = { - .symbol = "task-clock", - .alias = "", - }, - [PERF_COUNT_SW_PAGE_FAULTS] = { - .symbol = "page-faults", - .alias = "faults", - }, - [PERF_COUNT_SW_CONTEXT_SWITCHES] = { - .symbol = "context-switches", - .alias = "cs", - }, - [PERF_COUNT_SW_CPU_MIGRATIONS] = { - .symbol = "cpu-migrations", - .alias = "migrations", - }, - [PERF_COUNT_SW_PAGE_FAULTS_MIN] = { - .symbol = "minor-faults", - .alias = "", - }, - [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = { - .symbol = "major-faults", - .alias = "", - }, - [PERF_COUNT_SW_ALIGNMENT_FAULTS] = { - .symbol = "alignment-faults", - .alias = "", - }, - [PERF_COUNT_SW_EMULATION_FAULTS] = { - .symbol = "emulation-faults", - .alias = "", - }, - [PERF_COUNT_SW_DUMMY] = { - .symbol = "dummy", - .alias = "", - }, - [PERF_COUNT_SW_BPF_OUTPUT] = { - .symbol = "bpf-output", - .alias = "", - }, - [PERF_COUNT_SW_CGROUP_SWITCHES] = { - .symbol = "cgroup-switches", - .alias = "", - }, -}; - -const char *event_type(int type) +const char *event_type(size_t type) { - switch (type) { - case PERF_TYPE_HARDWARE: - return "hardware"; + if (type >= PERF_TYPE_MAX) + return "unknown"; - case PERF_TYPE_SOFTWARE: - return "software"; - - case PERF_TYPE_TRACEPOINT: - return "tracepoint"; - - case PERF_TYPE_HW_CACHE: - return "hardware-cache"; - - default: - break; - } - - return "unknown"; + return event_types[type]; } static char *get_config_str(const struct parse_events_terms *head_terms, @@ -178,6 +84,48 @@ static char *get_config_name(const struct parse_events_terms *head_terms) return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME); } +static struct perf_cpu_map *get_config_cpu(const struct parse_events_terms *head_terms, + bool fake_pmu) +{ + struct parse_events_term *term; + struct perf_cpu_map *cpus = NULL; + + if (!head_terms) + return NULL; + + list_for_each_entry(term, &head_terms->terms, list) { + struct perf_cpu_map *term_cpus; + + if (term->type_term != PARSE_EVENTS__TERM_TYPE_CPU) + continue; + + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + term_cpus = perf_cpu_map__new_int(term->val.num); + } else { + struct perf_pmu *pmu = perf_pmus__find(term->val.str); + + if (pmu) { + term_cpus = pmu->is_core && perf_cpu_map__is_empty(pmu->cpus) + ? cpu_map__online() + : perf_cpu_map__get(pmu->cpus); + } else { + term_cpus = perf_cpu_map__new(term->val.str); + if (!term_cpus && fake_pmu) { + /* + * Assume the PMU string makes sense on a different + * machine and fake a value with all online CPUs. + */ + term_cpus = cpu_map__online(); + } + } + } + perf_cpu_map__merge(&cpus, term_cpus); + perf_cpu_map__put(term_cpus); + } + + return cpus; +} + /** * fix_raw - For each raw term see if there is an event (aka alias) in pmu that * matches the raw's string value. If the string value matches an @@ -227,49 +175,104 @@ __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, bool init_attr, const char *name, const char *metric_id, struct perf_pmu *pmu, - struct list_head *config_terms, bool auto_merge_stats, - struct perf_cpu_map *cpu_list, u64 alternate_hw_config) + struct list_head *config_terms, struct evsel *first_wildcard_match, + struct perf_cpu_map *user_cpus, u64 alternate_hw_config) { struct evsel *evsel; - struct perf_cpu_map *cpus = perf_cpu_map__is_empty(cpu_list) && pmu ? pmu->cpus : cpu_list; + bool is_pmu_core; + struct perf_cpu_map *cpus, *pmu_cpus; + bool has_user_cpus = !perf_cpu_map__is_empty(user_cpus); - cpus = perf_cpu_map__get(cpus); - if (pmu) - perf_pmu__warn_invalid_formats(pmu); + /* + * Ensure the first_wildcard_match's PMU matches that of the new event + * being added. Otherwise try to match with another event further down + * the evlist. + */ + if (first_wildcard_match) { + struct evsel *pos = list_prev_entry(first_wildcard_match, core.node); + + first_wildcard_match = NULL; + list_for_each_entry_continue(pos, list, core.node) { + if (perf_pmu__name_no_suffix_match(pos->pmu, pmu->name)) { + first_wildcard_match = pos; + break; + } + if (pos->pmu->is_core && (!pmu || pmu->is_core)) { + first_wildcard_match = pos; + break; + } + } + } - if (pmu && (attr->type == PERF_TYPE_RAW || attr->type >= PERF_TYPE_MAX)) { - perf_pmu__warn_invalid_config(pmu, attr->config, name, - PERF_PMU_FORMAT_VALUE_CONFIG, "config"); - perf_pmu__warn_invalid_config(pmu, attr->config1, name, - PERF_PMU_FORMAT_VALUE_CONFIG1, "config1"); - perf_pmu__warn_invalid_config(pmu, attr->config2, name, - PERF_PMU_FORMAT_VALUE_CONFIG2, "config2"); - perf_pmu__warn_invalid_config(pmu, attr->config3, name, - PERF_PMU_FORMAT_VALUE_CONFIG3, "config3"); + if (pmu) { + perf_pmu__warn_invalid_formats(pmu); + if (attr->type == PERF_TYPE_RAW || attr->type >= PERF_TYPE_MAX) { + perf_pmu__warn_invalid_config(pmu, attr->config, name, + PERF_PMU_FORMAT_VALUE_CONFIG, "config"); + perf_pmu__warn_invalid_config(pmu, attr->config1, name, + PERF_PMU_FORMAT_VALUE_CONFIG1, "config1"); + perf_pmu__warn_invalid_config(pmu, attr->config2, name, + PERF_PMU_FORMAT_VALUE_CONFIG2, "config2"); + perf_pmu__warn_invalid_config(pmu, attr->config3, name, + PERF_PMU_FORMAT_VALUE_CONFIG3, "config3"); + perf_pmu__warn_invalid_config(pmu, attr->config4, name, + PERF_PMU_FORMAT_VALUE_CONFIG4, "config4"); + } } + /* + * If a PMU wasn't given, such as for legacy events, find now that + * warnings won't be generated. + */ + if (!pmu) + pmu = perf_pmus__find_by_attr(attr); + + if (pmu) { + is_pmu_core = pmu->is_core; + pmu_cpus = perf_cpu_map__get(pmu->cpus); + if (perf_cpu_map__is_empty(pmu_cpus)) + pmu_cpus = cpu_map__online(); + } else { + is_pmu_core = (attr->type == PERF_TYPE_HARDWARE || + attr->type == PERF_TYPE_HW_CACHE); + pmu_cpus = is_pmu_core ? cpu_map__online() : NULL; + } + + if (has_user_cpus) + cpus = perf_cpu_map__get(user_cpus); + else + cpus = perf_cpu_map__get(pmu_cpus); + if (init_attr) event_attr_init(attr); evsel = evsel__new_idx(attr, *idx); if (!evsel) { perf_cpu_map__put(cpus); + perf_cpu_map__put(pmu_cpus); return NULL; } + if (name) { + evsel->name = strdup(name); + if (!evsel->name) + goto out_err; + } + + if (metric_id) { + evsel->metric_id = strdup(metric_id); + if (!evsel->metric_id) + goto out_err; + } + (*idx)++; evsel->core.cpus = cpus; - evsel->core.own_cpus = perf_cpu_map__get(cpus); + evsel->core.pmu_cpus = pmu_cpus; evsel->core.requires_cpu = pmu ? pmu->is_uncore : false; - evsel->core.is_pmu_core = pmu ? pmu->is_core : false; - evsel->auto_merge_stats = auto_merge_stats; + evsel->core.is_pmu_core = is_pmu_core; + evsel->core.reads_only_on_cpu_idx0 = perf_pmu__reads_only_on_cpu_idx0(attr); evsel->pmu = pmu; evsel->alternate_hw_config = alternate_hw_config; - - if (name) - evsel->name = strdup(name); - - if (metric_id) - evsel->metric_id = strdup(metric_id); + evsel->first_wildcard_match = first_wildcard_match; if (config_terms) list_splice_init(config_terms, &evsel->config_terms); @@ -277,7 +280,17 @@ __add_event(struct list_head *list, int *idx, if (list) list_add_tail(&evsel->core.node, list); + if (has_user_cpus) + evsel__warn_user_requested_cpus(evsel, user_cpus); + return evsel; +out_err: + perf_cpu_map__put(cpus); + perf_cpu_map__put(pmu_cpus); + zfree(&evsel->name); + zfree(&evsel->metric_id); + free(evsel); + return NULL; } struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, @@ -286,7 +299,7 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, { return __add_event(/*list=*/NULL, &idx, attr, /*init_attr=*/false, name, metric_id, pmu, /*config_terms=*/NULL, - /*auto_merge_stats=*/false, /*cpu_list=*/NULL, + /*first_wildcard_match=*/NULL, /*cpu_list=*/NULL, /*alternate_hw_config=*/PERF_COUNT_HW_MAX); } @@ -297,7 +310,7 @@ static int add_event(struct list_head *list, int *idx, { return __add_event(list, idx, attr, /*init_attr*/true, name, metric_id, /*pmu=*/NULL, config_terms, - /*auto_merge_stats=*/false, /*cpu_list=*/NULL, + /*first_wildcard_match=*/NULL, /*cpu_list=*/NULL, alternate_hw_config) ? 0 : -ENOMEM; } @@ -330,13 +343,13 @@ static int parse_aliases(const char *str, const char *const names[][EVSEL__MAX_A typedef int config_term_func_t(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err); + struct parse_events_state *parse_state); static int config_term_common(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err); + struct parse_events_state *parse_state); static int config_attr(struct perf_event_attr *attr, const struct parse_events_terms *head, - struct parse_events_error *err, + struct parse_events_state *parse_state, config_term_func_t config_term); /** @@ -416,78 +429,13 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state, if (parse_state->pmu_filter == NULL) return false; - return strcmp(parse_state->pmu_filter, pmu->name) != 0; + return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0; } static int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, struct perf_pmu *pmu, const struct parse_events_terms *const_parsed_terms, - bool auto_merge_stats, u64 alternate_hw_config); - -int parse_events_add_cache(struct list_head *list, int *idx, const char *name, - struct parse_events_state *parse_state, - struct parse_events_terms *parsed_terms) -{ - struct perf_pmu *pmu = NULL; - bool found_supported = false; - const char *config_name = get_config_name(parsed_terms); - const char *metric_id = get_config_metric_id(parsed_terms); - - while ((pmu = perf_pmus__scan(pmu)) != NULL) { - LIST_HEAD(config_terms); - struct perf_event_attr attr; - int ret; - - if (parse_events__filter_pmu(parse_state, pmu)) - continue; - - if (perf_pmu__have_event(pmu, name)) { - /* - * The PMU has the event so add as not a legacy cache - * event. - */ - ret = parse_events_add_pmu(parse_state, list, pmu, - parsed_terms, - perf_pmu__auto_merge_stats(pmu), - /*alternate_hw_config=*/PERF_COUNT_HW_MAX); - if (ret) - return ret; - continue; - } - - if (!pmu->is_core) { - /* Legacy cache events are only supported by core PMUs. */ - continue; - } - - memset(&attr, 0, sizeof(attr)); - attr.type = PERF_TYPE_HW_CACHE; - - ret = parse_events__decode_legacy_cache(name, pmu->type, &attr.config); - if (ret) - return ret; - - found_supported = true; - - if (parsed_terms) { - if (config_attr(&attr, parsed_terms, parse_state->error, - config_term_common)) - return -EINVAL; - - if (get_config_terms(parsed_terms, &config_terms)) - return -ENOMEM; - } - - if (__add_event(list, idx, &attr, /*init_attr*/true, config_name ?: name, - metric_id, pmu, &config_terms, /*auto_merge_stats=*/false, - /*cpu_list=*/NULL, - /*alternate_hw_config=*/PERF_COUNT_HW_MAX) == NULL) - return -ENOMEM; - - free_config_terms(&config_terms); - } - return found_supported ? 0 : -EINVAL; -} + struct evsel *first_wildcard_match); static void tracepoint_error(struct parse_events_error *e, int err, const char *sys, const char *name, int column) @@ -547,100 +495,82 @@ static int add_tracepoint(struct parse_events_state *parse_state, return 0; } -static int add_tracepoint_multi_event(struct parse_events_state *parse_state, - struct list_head *list, - const char *sys_name, const char *evt_name, - struct parse_events_error *err, - struct parse_events_terms *head_config, YYLTYPE *loc) -{ - char *evt_path; - struct dirent *evt_ent; - DIR *evt_dir; - int ret = 0, found = 0; - - evt_path = get_events_file(sys_name); - if (!evt_path) { - tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); - return -1; - } - evt_dir = opendir(evt_path); - if (!evt_dir) { - put_events_file(evt_path); - tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); - return -1; - } +struct add_tracepoint_multi_args { + struct parse_events_state *parse_state; + struct list_head *list; + const char *sys_glob; + const char *evt_glob; + struct parse_events_error *err; + struct parse_events_terms *head_config; + YYLTYPE *loc; + int found; +}; - while (!ret && (evt_ent = readdir(evt_dir))) { - if (!strcmp(evt_ent->d_name, ".") - || !strcmp(evt_ent->d_name, "..") - || !strcmp(evt_ent->d_name, "enable") - || !strcmp(evt_ent->d_name, "filter")) - continue; +static int add_tracepoint_multi_event_cb(void *state, const char *sys_name, const char *evt_name) +{ + struct add_tracepoint_multi_args *args = state; + int ret; - if (!strglobmatch(evt_ent->d_name, evt_name)) - continue; + if (!strglobmatch(evt_name, args->evt_glob)) + return 0; - found++; + args->found++; + ret = add_tracepoint(args->parse_state, args->list, sys_name, evt_name, + args->err, args->head_config, args->loc); - ret = add_tracepoint(parse_state, list, sys_name, evt_ent->d_name, - err, head_config, loc); - } + return ret; +} - if (!found) { - tracepoint_error(err, ENOENT, sys_name, evt_name, loc->first_column); - ret = -1; +static int add_tracepoint_multi_event(struct add_tracepoint_multi_args *args, const char *sys_name) +{ + if (strpbrk(args->evt_glob, "*?") == NULL) { + /* Not a glob. */ + args->found++; + return add_tracepoint(args->parse_state, args->list, sys_name, args->evt_glob, + args->err, args->head_config, args->loc); } - put_events_file(evt_path); - closedir(evt_dir); - return ret; + return tp_pmu__for_each_tp_event(sys_name, args, add_tracepoint_multi_event_cb); } -static int add_tracepoint_event(struct parse_events_state *parse_state, - struct list_head *list, - const char *sys_name, const char *evt_name, - struct parse_events_error *err, - struct parse_events_terms *head_config, YYLTYPE *loc) +static int add_tracepoint_multi_sys_cb(void *state, const char *sys_name) { - return strpbrk(evt_name, "*?") ? - add_tracepoint_multi_event(parse_state, list, sys_name, evt_name, - err, head_config, loc) : - add_tracepoint(parse_state, list, sys_name, evt_name, - err, head_config, loc); + struct add_tracepoint_multi_args *args = state; + + if (!strglobmatch(sys_name, args->sys_glob)) + return 0; + + return add_tracepoint_multi_event(args, sys_name); } static int add_tracepoint_multi_sys(struct parse_events_state *parse_state, struct list_head *list, - const char *sys_name, const char *evt_name, + const char *sys_glob, const char *evt_glob, struct parse_events_error *err, struct parse_events_terms *head_config, YYLTYPE *loc) { - struct dirent *events_ent; - DIR *events_dir; - int ret = 0; + struct add_tracepoint_multi_args args = { + .parse_state = parse_state, + .list = list, + .sys_glob = sys_glob, + .evt_glob = evt_glob, + .err = err, + .head_config = head_config, + .loc = loc, + .found = 0, + }; + int ret; - events_dir = tracing_events__opendir(); - if (!events_dir) { - tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); - return -1; + if (strpbrk(sys_glob, "*?") == NULL) { + /* Not a glob. */ + ret = add_tracepoint_multi_event(&args, sys_glob); + } else { + ret = tp_pmu__for_each_tp_sys(&args, add_tracepoint_multi_sys_cb); } - - while (!ret && (events_ent = readdir(events_dir))) { - if (!strcmp(events_ent->d_name, ".") - || !strcmp(events_ent->d_name, "..") - || !strcmp(events_ent->d_name, "enable") - || !strcmp(events_ent->d_name, "header_event") - || !strcmp(events_ent->d_name, "header_page")) - continue; - - if (!strglobmatch(events_ent->d_name, sys_name)) - continue; - - ret = add_tracepoint_event(parse_state, list, events_ent->d_name, - evt_name, err, head_config, loc); + if (args.found == 0) { + tracepoint_error(err, ENOENT, sys_glob, evt_glob, loc->first_column); + return -ENOENT; } - - closedir(events_dir); return ret; } @@ -733,8 +663,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state, attr.sample_period = 1; if (head_config) { - if (config_attr(&attr, head_config, parse_state->error, - config_term_common)) + if (config_attr(&attr, head_config, parse_state, config_term_common)) return -EINVAL; if (get_config_terms(head_config, &config_terms)) @@ -777,6 +706,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type) [PARSE_EVENTS__TERM_TYPE_CONFIG1] = "config1", [PARSE_EVENTS__TERM_TYPE_CONFIG2] = "config2", [PARSE_EVENTS__TERM_TYPE_CONFIG3] = "config3", + [PARSE_EVENTS__TERM_TYPE_CONFIG4] = "config4", [PARSE_EVENTS__TERM_TYPE_NAME] = "name", [PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD] = "period", [PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ] = "freq", @@ -797,8 +727,10 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type) [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", [PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id", [PARSE_EVENTS__TERM_TYPE_RAW] = "raw", - [PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE] = "legacy-cache", - [PARSE_EVENTS__TERM_TYPE_HARDWARE] = "hardware", + [PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG] = "legacy-hardware-config", + [PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG] = "legacy-cache-config", + [PARSE_EVENTS__TERM_TYPE_CPU] = "cpu", + [PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV] = "ratio-to-prev", }; if ((unsigned int)term_type >= __PARSE_EVENTS__TERM_TYPE_NR) return "unknown term"; @@ -824,10 +756,12 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er case PARSE_EVENTS__TERM_TYPE_CONFIG1: case PARSE_EVENTS__TERM_TYPE_CONFIG2: case PARSE_EVENTS__TERM_TYPE_CONFIG3: + case PARSE_EVENTS__TERM_TYPE_CONFIG4: case PARSE_EVENTS__TERM_TYPE_NAME: case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: case PARSE_EVENTS__TERM_TYPE_PERCORE: + case PARSE_EVENTS__TERM_TYPE_CPU: return true; case PARSE_EVENTS__TERM_TYPE_USER: case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: @@ -846,8 +780,9 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: case PARSE_EVENTS__TERM_TYPE_RAW: - case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: - case PARSE_EVENTS__TERM_TYPE_HARDWARE: + case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV: + case PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG: default: if (!err) return false; @@ -867,12 +802,12 @@ void parse_events__shrink_config_terms(void) static int config_term_common(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err) + struct parse_events_state *parse_state) { -#define CHECK_TYPE_VAL(type) \ -do { \ - if (check_type_val(term, err, PARSE_EVENTS__TERM_TYPE_ ## type)) \ - return -EINVAL; \ +#define CHECK_TYPE_VAL(type) \ +do { \ + if (check_type_val(term, parse_state->error, PARSE_EVENTS__TERM_TYPE_ ## type)) \ + return -EINVAL; \ } while (0) switch (term->type_term) { @@ -892,6 +827,10 @@ do { \ CHECK_TYPE_VAL(NUM); attr->config3 = term->val.num; break; + case PARSE_EVENTS__TERM_TYPE_CONFIG4: + CHECK_TYPE_VAL(NUM); + attr->config4 = term->val.num; + break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: CHECK_TYPE_VAL(NUM); break; @@ -903,7 +842,7 @@ do { \ if (strcmp(term->val.str, "no") && parse_branch_str(term->val.str, &attr->branch_sample_type)) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("invalid branch sample type"), NULL); return -EINVAL; @@ -912,7 +851,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_TIME: CHECK_TYPE_VAL(NUM); if (term->val.num > 1) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("expected 0 or 1"), NULL); return -EINVAL; @@ -954,7 +893,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_PERCORE: CHECK_TYPE_VAL(NUM); if ((unsigned int)term->val.num > 1) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("expected 0 or 1"), NULL); return -EINVAL; @@ -969,18 +908,59 @@ do { \ case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: CHECK_TYPE_VAL(NUM); if (term->val.num > UINT_MAX) { - parse_events_error__handle(err, term->err_val, + parse_events_error__handle(parse_state->error, term->err_val, strdup("too big"), NULL); return -EINVAL; } break; + case PARSE_EVENTS__TERM_TYPE_CPU: { + struct perf_cpu_map *map; + + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (term->val.num >= (u64)cpu__max_present_cpu().cpu) { + parse_events_error__handle(parse_state->error, term->err_val, + strdup("too big"), + /*help=*/NULL); + return -EINVAL; + } + break; + } + assert(term->type_val == PARSE_EVENTS__TERM_TYPE_STR); + if (perf_pmus__find(term->val.str) != NULL) + break; + + map = perf_cpu_map__new(term->val.str); + if (!map && !parse_state->fake_pmu) { + parse_events_error__handle(parse_state->error, term->err_val, + strdup("not a valid PMU or CPU number"), + /*help=*/NULL); + return -EINVAL; + } + perf_cpu_map__put(map); + break; + } + case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV: + CHECK_TYPE_VAL(STR); + if (strtod(term->val.str, NULL) <= 0) { + parse_events_error__handle(parse_state->error, term->err_val, + strdup("zero or negative"), + NULL); + return -EINVAL; + } + if (errno == ERANGE) { + parse_events_error__handle(parse_state->error, term->err_val, + strdup("too big"), + NULL); + return -EINVAL; + } + break; case PARSE_EVENTS__TERM_TYPE_DRV_CFG: case PARSE_EVENTS__TERM_TYPE_USER: - case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: - case PARSE_EVENTS__TERM_TYPE_HARDWARE: + case PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG: default: - parse_events_error__handle(err, term->err_term, + parse_events_error__handle(parse_state->error, term->err_term, strdup(parse_events__term_type_str(term->type_term)), parse_events_formats_error_string(NULL)); return -EINVAL; @@ -995,67 +975,72 @@ do { \ * if an invalid config term is provided for legacy events * (for example, instructions/badterm/...), which is confusing. */ - if (!config_term_avail(term->type_term, err)) + if (!config_term_avail(term->type_term, parse_state->error)) return -EINVAL; return 0; #undef CHECK_TYPE_VAL } -static int config_term_pmu(struct perf_event_attr *attr, - struct parse_events_term *term, - struct parse_events_error *err) +static bool check_pmu_is_core(__u32 type, const struct parse_events_term *term, + struct parse_events_error *err) { - if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) { - struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); + struct perf_pmu *pmu = NULL; - if (!pmu) { - char *err_str; + /* Avoid loading all PMUs with perf_pmus__find_by_type, just scan the core ones. */ + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + if (pmu->type == type) + return true; + } + parse_events_error__handle(err, term->err_val, + strdup("needs a core PMU"), + NULL); + return false; +} - if (asprintf(&err_str, "Failed to find PMU for type %d", attr->type) >= 0) - parse_events_error__handle(err, term->err_term, - err_str, /*help=*/NULL); +static int config_term_pmu(struct perf_event_attr *attr, + struct parse_events_term *term, + struct parse_events_state *parse_state) +{ + if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG) { + if (check_type_val(term, parse_state->error, PARSE_EVENTS__TERM_TYPE_NUM)) + return -EINVAL; + if (term->val.num >= PERF_COUNT_HW_MAX) { + parse_events_error__handle(parse_state->error, term->err_val, + strdup("too big"), + NULL); return -EINVAL; } - /* - * Rewrite the PMU event to a legacy cache one unless the PMU - * doesn't support legacy cache events or the event is present - * within the PMU. - */ - if (perf_pmu__supports_legacy_cache(pmu) && - !perf_pmu__have_event(pmu, term->config)) { - attr->type = PERF_TYPE_HW_CACHE; - return parse_events__decode_legacy_cache(term->config, pmu->type, - &attr->config); - } else { - term->type_term = PARSE_EVENTS__TERM_TYPE_USER; - term->no_value = true; - } + if (!check_pmu_is_core(attr->type, term, parse_state->error)) + return -EINVAL; + attr->config = term->val.num; + if (perf_pmus__supports_extended_type()) + attr->config |= (__u64)attr->type << PERF_PMU_TYPE_SHIFT; + attr->type = PERF_TYPE_HARDWARE; + return 0; } - if (term->type_term == PARSE_EVENTS__TERM_TYPE_HARDWARE) { - struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); - - if (!pmu) { - char *err_str; + if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG) { + int cache_type, cache_op, cache_result; - if (asprintf(&err_str, "Failed to find PMU for type %d", attr->type) >= 0) - parse_events_error__handle(err, term->err_term, - err_str, /*help=*/NULL); + if (check_type_val(term, parse_state->error, PARSE_EVENTS__TERM_TYPE_NUM)) + return -EINVAL; + cache_type = term->val.num & 0xFF; + cache_op = (term->val.num >> 8) & 0xFF; + cache_result = (term->val.num >> 16) & 0xFF; + if ((term->val.num & ~0xFFFFFF) || + cache_type >= PERF_COUNT_HW_CACHE_MAX || + cache_op >= PERF_COUNT_HW_CACHE_OP_MAX || + cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) { + parse_events_error__handle(parse_state->error, term->err_val, + strdup("too big"), + NULL); return -EINVAL; } - /* - * If the PMU has a sysfs or json event prefer it over - * legacy. ARM requires this. - */ - if (perf_pmu__have_event(pmu, term->config)) { - term->type_term = PARSE_EVENTS__TERM_TYPE_USER; - term->no_value = true; - term->alternate_hw_config = true; - } else { - attr->type = PERF_TYPE_HARDWARE; - attr->config = term->val.num; - if (perf_pmus__supports_extended_type()) - attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; - } + if (!check_pmu_is_core(attr->type, term, parse_state->error)) + return -EINVAL; + attr->config = term->val.num; + if (perf_pmus__supports_extended_type()) + attr->config |= (__u64)attr->type << PERF_PMU_TYPE_SHIFT; + attr->type = PERF_TYPE_HW_CACHE; return 0; } if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER || @@ -1066,12 +1051,12 @@ static int config_term_pmu(struct perf_event_attr *attr, */ return 0; } - return config_term_common(attr, term, err); + return config_term_common(attr, term, parse_state); } static int config_term_tracepoint(struct perf_event_attr *attr, struct parse_events_term *term, - struct parse_events_error *err) + struct parse_events_state *parse_state) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: @@ -1085,12 +1070,15 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: - return config_term_common(attr, term, err); + return config_term_common(attr, term, parse_state); case PARSE_EVENTS__TERM_TYPE_USER: case PARSE_EVENTS__TERM_TYPE_CONFIG: case PARSE_EVENTS__TERM_TYPE_CONFIG1: case PARSE_EVENTS__TERM_TYPE_CONFIG2: case PARSE_EVENTS__TERM_TYPE_CONFIG3: + case PARSE_EVENTS__TERM_TYPE_CONFIG4: + case PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG: case PARSE_EVENTS__TERM_TYPE_NAME: case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: @@ -1100,15 +1088,13 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_PERCORE: case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_RAW: - case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: - case PARSE_EVENTS__TERM_TYPE_HARDWARE: + case PARSE_EVENTS__TERM_TYPE_CPU: + case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV: default: - if (err) { - parse_events_error__handle(err, term->err_term, + parse_events_error__handle(parse_state->error, term->err_term, strdup(parse_events__term_type_str(term->type_term)), strdup("valid terms: call-graph,stack-size\n") ); - } return -EINVAL; } @@ -1117,191 +1103,281 @@ static int config_term_tracepoint(struct perf_event_attr *attr, static int config_attr(struct perf_event_attr *attr, const struct parse_events_terms *head, - struct parse_events_error *err, + struct parse_events_state *parse_state, config_term_func_t config_term) { struct parse_events_term *term; list_for_each_entry(term, &head->terms, list) - if (config_term(attr, term, err)) + if (config_term(attr, term, parse_state)) return -EINVAL; return 0; } -static int get_config_terms(const struct parse_events_terms *head_config, - struct list_head *head_terms) +static struct evsel_config_term *add_config_term(enum evsel_term_type type, + struct list_head *head_terms, + bool weak, char *str, u64 val) { -#define ADD_CONFIG_TERM(__type, __weak) \ - struct evsel_config_term *__t; \ - \ - __t = zalloc(sizeof(*__t)); \ - if (!__t) \ - return -ENOMEM; \ - \ - INIT_LIST_HEAD(&__t->list); \ - __t->type = EVSEL__CONFIG_TERM_ ## __type; \ - __t->weak = __weak; \ - list_add_tail(&__t->list, head_terms) - -#define ADD_CONFIG_TERM_VAL(__type, __name, __val, __weak) \ -do { \ - ADD_CONFIG_TERM(__type, __weak); \ - __t->val.__name = __val; \ -} while (0) + struct evsel_config_term *t; -#define ADD_CONFIG_TERM_STR(__type, __val, __weak) \ -do { \ - ADD_CONFIG_TERM(__type, __weak); \ - __t->val.str = strdup(__val); \ - if (!__t->val.str) { \ - zfree(&__t); \ - return -ENOMEM; \ - } \ - __t->free_str = true; \ -} while (0) + t = zalloc(sizeof(*t)); + if (!t) + return NULL; + INIT_LIST_HEAD(&t->list); + t->type = type; + t->weak = weak; + + switch (type) { + case EVSEL__CONFIG_TERM_PERIOD: + case EVSEL__CONFIG_TERM_FREQ: + case EVSEL__CONFIG_TERM_STACK_USER: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG1: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG2: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG3: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG4: + t->val.val = val; + break; + case EVSEL__CONFIG_TERM_TIME: + t->val.time = val; + break; + case EVSEL__CONFIG_TERM_INHERIT: + t->val.inherit = val; + break; + case EVSEL__CONFIG_TERM_OVERWRITE: + t->val.overwrite = val; + break; + case EVSEL__CONFIG_TERM_MAX_STACK: + t->val.max_stack = val; + break; + case EVSEL__CONFIG_TERM_MAX_EVENTS: + t->val.max_events = val; + break; + case EVSEL__CONFIG_TERM_PERCORE: + t->val.percore = val; + break; + case EVSEL__CONFIG_TERM_AUX_OUTPUT: + t->val.aux_output = val; + break; + case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: + t->val.aux_sample_size = val; + break; + case EVSEL__CONFIG_TERM_CALLGRAPH: + case EVSEL__CONFIG_TERM_BRANCH: + case EVSEL__CONFIG_TERM_DRV_CFG: + case EVSEL__CONFIG_TERM_RATIO_TO_PREV: + case EVSEL__CONFIG_TERM_AUX_ACTION: + if (str) { + t->val.str = strdup(str); + if (!t->val.str) { + zfree(&t); + return NULL; + } + t->free_str = true; + } + break; + default: + t->val.val = val; + break; + } + + list_add_tail(&t->list, head_terms); + return t; +} + +static int get_config_terms(const struct parse_events_terms *head_config, + struct list_head *head_terms) +{ struct parse_events_term *term; list_for_each_entry(term, &head_config->terms, list) { + struct evsel_config_term *new_term; + enum evsel_term_type new_type; + bool str_type = false; + u64 val = 0; + switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: - ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num, term->weak); + new_type = EVSEL__CONFIG_TERM_PERIOD; + val = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: - ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num, term->weak); + new_type = EVSEL__CONFIG_TERM_FREQ; + val = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_TIME: - ADD_CONFIG_TERM_VAL(TIME, time, term->val.num, term->weak); + new_type = EVSEL__CONFIG_TERM_TIME; + val = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: - ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str, term->weak); + new_type = EVSEL__CONFIG_TERM_CALLGRAPH; + str_type = true; break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: - ADD_CONFIG_TERM_STR(BRANCH, term->val.str, term->weak); + new_type = EVSEL__CONFIG_TERM_BRANCH; + str_type = true; break; case PARSE_EVENTS__TERM_TYPE_STACKSIZE: - ADD_CONFIG_TERM_VAL(STACK_USER, stack_user, - term->val.num, term->weak); + new_type = EVSEL__CONFIG_TERM_STACK_USER; + val = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_INHERIT: - ADD_CONFIG_TERM_VAL(INHERIT, inherit, - term->val.num ? 1 : 0, term->weak); + new_type = EVSEL__CONFIG_TERM_INHERIT; + val = term->val.num ? 1 : 0; break; case PARSE_EVENTS__TERM_TYPE_NOINHERIT: - ADD_CONFIG_TERM_VAL(INHERIT, inherit, - term->val.num ? 0 : 1, term->weak); + new_type = EVSEL__CONFIG_TERM_INHERIT; + val = term->val.num ? 0 : 1; break; case PARSE_EVENTS__TERM_TYPE_MAX_STACK: - ADD_CONFIG_TERM_VAL(MAX_STACK, max_stack, - term->val.num, term->weak); + new_type = EVSEL__CONFIG_TERM_MAX_STACK; + val = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: - ADD_CONFIG_TERM_VAL(MAX_EVENTS, max_events, - term->val.num, term->weak); + new_type = EVSEL__CONFIG_TERM_MAX_EVENTS; + val = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_OVERWRITE: - ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, - term->val.num ? 1 : 0, term->weak); + new_type = EVSEL__CONFIG_TERM_OVERWRITE; + val = term->val.num ? 1 : 0; break; case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: - ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, - term->val.num ? 0 : 1, term->weak); + new_type = EVSEL__CONFIG_TERM_OVERWRITE; + val = term->val.num ? 0 : 1; break; case PARSE_EVENTS__TERM_TYPE_DRV_CFG: - ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str, term->weak); + new_type = EVSEL__CONFIG_TERM_DRV_CFG; + str_type = true; break; case PARSE_EVENTS__TERM_TYPE_PERCORE: - ADD_CONFIG_TERM_VAL(PERCORE, percore, - term->val.num ? true : false, term->weak); + new_type = EVSEL__CONFIG_TERM_PERCORE; + val = term->val.num ? true : false; break; case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: - ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output, - term->val.num ? 1 : 0, term->weak); + new_type = EVSEL__CONFIG_TERM_AUX_OUTPUT; + val = term->val.num ? 1 : 0; break; case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: - ADD_CONFIG_TERM_STR(AUX_ACTION, term->val.str, term->weak); + new_type = EVSEL__CONFIG_TERM_AUX_ACTION; + str_type = true; break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: - ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, - term->val.num, term->weak); + new_type = EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE; + val = term->val.num; + break; + case PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV: + new_type = EVSEL__CONFIG_TERM_RATIO_TO_PREV; + str_type = true; break; case PARSE_EVENTS__TERM_TYPE_USER: case PARSE_EVENTS__TERM_TYPE_CONFIG: case PARSE_EVENTS__TERM_TYPE_CONFIG1: case PARSE_EVENTS__TERM_TYPE_CONFIG2: case PARSE_EVENTS__TERM_TYPE_CONFIG3: + case PARSE_EVENTS__TERM_TYPE_CONFIG4: + case PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG: + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG: case PARSE_EVENTS__TERM_TYPE_NAME: case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_RAW: - case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: - case PARSE_EVENTS__TERM_TYPE_HARDWARE: + case PARSE_EVENTS__TERM_TYPE_CPU: default: - break; + /* Don't add a new term for these ones */ + continue; } + + /* + * Note: Members evsel_config_term::val and + * parse_events_term::val are unions and endianness needs + * to be taken into account when changing such union members. + */ + new_term = add_config_term(new_type, head_terms, term->weak, + str_type ? term->val.str : NULL, val); + if (!new_term) + return -ENOMEM; } return 0; } -/* - * Add EVSEL__CONFIG_TERM_CFG_CHG where cfg_chg will have a bit set for - * each bit of attr->config that the user has changed. - */ -static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head_config, - struct list_head *head_terms) +static int add_cfg_chg(const struct perf_pmu *pmu, + const struct parse_events_terms *head_config, + struct list_head *head_terms, + int format_type, + enum parse_events__term_type term_type, + enum evsel_term_type new_term_type) { struct parse_events_term *term; u64 bits = 0; int type; list_for_each_entry(term, &head_config->terms, list) { - switch (term->type_term) { - case PARSE_EVENTS__TERM_TYPE_USER: + if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER) { type = perf_pmu__format_type(pmu, term->config); - if (type != PERF_PMU_FORMAT_VALUE_CONFIG) + if (type != format_type) continue; bits |= perf_pmu__format_bits(pmu, term->config); - break; - case PARSE_EVENTS__TERM_TYPE_CONFIG: + } else if (term->type_term == term_type) { bits = ~(u64)0; - break; - case PARSE_EVENTS__TERM_TYPE_CONFIG1: - case PARSE_EVENTS__TERM_TYPE_CONFIG2: - case PARSE_EVENTS__TERM_TYPE_CONFIG3: - case PARSE_EVENTS__TERM_TYPE_NAME: - case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: - case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: - case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: - case PARSE_EVENTS__TERM_TYPE_TIME: - case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: - case PARSE_EVENTS__TERM_TYPE_STACKSIZE: - case PARSE_EVENTS__TERM_TYPE_NOINHERIT: - case PARSE_EVENTS__TERM_TYPE_INHERIT: - case PARSE_EVENTS__TERM_TYPE_MAX_STACK: - case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: - case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: - case PARSE_EVENTS__TERM_TYPE_OVERWRITE: - case PARSE_EVENTS__TERM_TYPE_DRV_CFG: - case PARSE_EVENTS__TERM_TYPE_PERCORE: - case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: - case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: - case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: - case PARSE_EVENTS__TERM_TYPE_METRIC_ID: - case PARSE_EVENTS__TERM_TYPE_RAW: - case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: - case PARSE_EVENTS__TERM_TYPE_HARDWARE: - default: - break; } } - if (bits) - ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits, false); + if (bits) { + struct evsel_config_term *new_term; + + new_term = add_config_term(new_term_type, head_terms, false, NULL, bits); + if (!new_term) + return -ENOMEM; + } -#undef ADD_CONFIG_TERM return 0; } +/* + * Add EVSEL__CONFIG_TERM_USR_CFG_CONFIGn where cfg_chg will have a bit set for + * each bit of attr->configN that the user has changed. + */ +static int get_config_chgs(const struct perf_pmu *pmu, + const struct parse_events_terms *head_config, + struct list_head *head_terms) +{ + int ret; + + ret = add_cfg_chg(pmu, head_config, head_terms, + PERF_PMU_FORMAT_VALUE_CONFIG, + PARSE_EVENTS__TERM_TYPE_CONFIG, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG); + if (ret) + return ret; + + ret = add_cfg_chg(pmu, head_config, head_terms, + PERF_PMU_FORMAT_VALUE_CONFIG1, + PARSE_EVENTS__TERM_TYPE_CONFIG1, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG1); + if (ret) + return ret; + + ret = add_cfg_chg(pmu, head_config, head_terms, + PERF_PMU_FORMAT_VALUE_CONFIG2, + PARSE_EVENTS__TERM_TYPE_CONFIG2, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG2); + if (ret) + return ret; + + ret = add_cfg_chg(pmu, head_config, head_terms, + PERF_PMU_FORMAT_VALUE_CONFIG3, + PARSE_EVENTS__TERM_TYPE_CONFIG3, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG3); + if (ret) + return ret; + + return add_cfg_chg(pmu, head_config, head_terms, + PERF_PMU_FORMAT_VALUE_CONFIG4, + PARSE_EVENTS__TERM_TYPE_CONFIG4, + EVSEL__CONFIG_TERM_USR_CHG_CONFIG4); +} + int parse_events_add_tracepoint(struct parse_events_state *parse_state, struct list_head *list, const char *sys, const char *event, @@ -1313,27 +1389,24 @@ int parse_events_add_tracepoint(struct parse_events_state *parse_state, if (head_config) { struct perf_event_attr attr; - if (config_attr(&attr, head_config, err, - config_term_tracepoint)) + if (config_attr(&attr, head_config, parse_state, config_term_tracepoint)) return -EINVAL; } - if (strpbrk(sys, "*?")) - return add_tracepoint_multi_sys(parse_state, list, sys, event, - err, head_config, loc); - else - return add_tracepoint_event(parse_state, list, sys, event, - err, head_config, loc); + return add_tracepoint_multi_sys(parse_state, list, sys, event, + err, head_config, loc); } static int __parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, struct perf_pmu *pmu, u32 type, u32 extended_type, - u64 config, const struct parse_events_terms *head_config) + u64 config, const struct parse_events_terms *head_config, + struct evsel *first_wildcard_match) { struct perf_event_attr attr; LIST_HEAD(config_terms); const char *name, *metric_id; + struct perf_cpu_map *cpus; int ret; memset(&attr, 0, sizeof(attr)); @@ -1345,8 +1418,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state, } if (head_config) { - if (config_attr(&attr, head_config, parse_state->error, - config_term_common)) + if (config_attr(&attr, head_config, parse_state, config_term_common)) return -EINVAL; if (get_config_terms(head_config, &config_terms)) @@ -1355,10 +1427,11 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state, name = get_config_name(head_config); metric_id = get_config_metric_id(head_config); + cpus = get_config_cpu(head_config, parse_state->fake_pmu); ret = __add_event(list, &parse_state->idx, &attr, /*init_attr*/true, name, - metric_id, pmu, &config_terms, /*auto_merge_stats=*/false, - /*cpu_list=*/NULL, /*alternate_hw_config=*/PERF_COUNT_HW_MAX - ) == NULL ? -ENOMEM : 0; + metric_id, pmu, &config_terms, first_wildcard_match, + cpus, /*alternate_hw_config=*/PERF_COUNT_HW_MAX) ? 0 : -ENOMEM; + perf_cpu_map__put(cpus); free_config_terms(&config_terms); return ret; } @@ -1374,6 +1447,7 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, /* Wildcards on numeric values are only supported by core PMUs. */ if (wildcard && perf_pmus__supports_extended_type()) { + struct evsel *first_wildcard_match = NULL; while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { int ret; @@ -1383,15 +1457,20 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, ret = __parse_events_add_numeric(parse_state, list, pmu, type, pmu->type, - config, head_config); + config, head_config, + first_wildcard_match); if (ret) return ret; + if (first_wildcard_match == NULL) + first_wildcard_match = + container_of(list->prev, struct evsel, core.node); } if (found_supported) return 0; } return __parse_events_add_numeric(parse_state, list, perf_pmus__find_by_type(type), - type, /*extended_type=*/0, config, head_config); + type, /*extended_type=*/0, config, head_config, + /*first_wildcard_match=*/NULL); } static bool config_term_percore(struct list_head *config_terms) @@ -1409,8 +1488,9 @@ static bool config_term_percore(struct list_head *config_terms) static int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, struct perf_pmu *pmu, const struct parse_events_terms *const_parsed_terms, - bool auto_merge_stats, u64 alternate_hw_config) + struct evsel *first_wildcard_match) { + u64 alternate_hw_config = PERF_COUNT_HW_MAX; struct perf_event_attr attr; struct perf_pmu_info info; struct evsel *evsel; @@ -1418,6 +1498,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, LIST_HEAD(config_terms); struct parse_events_terms parsed_terms; bool alias_rewrote_terms = false; + struct perf_cpu_map *term_cpu = NULL; if (verbose > 1) { struct strbuf sb; @@ -1445,7 +1526,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true, /*name=*/NULL, /*metric_id=*/NULL, pmu, - /*config_terms=*/NULL, auto_merge_stats, + /*config_terms=*/NULL, first_wildcard_match, /*cpu_list=*/NULL, alternate_hw_config); return evsel ? 0 : -ENOMEM; } @@ -1460,7 +1541,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, fix_raw(&parsed_terms, pmu); /* Configure attr/terms with a known PMU, this will set hardcoded terms. */ - if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { + if (config_attr(&attr, &parsed_terms, parse_state, config_term_pmu)) { parse_events_terms__exit(&parsed_terms); return -EINVAL; } @@ -1484,7 +1565,7 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, /* Configure attr/terms again if an alias was expanded. */ if (alias_rewrote_terms && - config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { + config_attr(&attr, &parsed_terms, parse_state, config_term_pmu)) { parse_events_terms__exit(&parsed_terms); return -EINVAL; } @@ -1494,12 +1575,8 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, return -ENOMEM; } - /* - * When using default config, record which bits of attr->config were - * changed by the user. - */ - if (pmu->perf_event_attr_init_default && - get_config_chgs(pmu, &parsed_terms, &config_terms)) { + /* Record which bits of attr->config were changed by the user. */ + if (get_config_chgs(pmu, &parsed_terms, &config_terms)) { parse_events_terms__exit(&parsed_terms); return -ENOMEM; } @@ -1512,11 +1589,12 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, return -EINVAL; } + term_cpu = get_config_cpu(&parsed_terms, parse_state->fake_pmu); evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true, get_config_name(&parsed_terms), get_config_metric_id(&parsed_terms), pmu, - &config_terms, auto_merge_stats, /*cpu_list=*/NULL, - alternate_hw_config); + &config_terms, first_wildcard_match, term_cpu, alternate_hw_config); + perf_cpu_map__put(term_cpu); if (!evsel) { parse_events_terms__exit(&parsed_terms); return -ENOMEM; @@ -1533,11 +1611,15 @@ static int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->scale = info.scale; evsel->per_pkg = info.per_pkg; evsel->snapshot = info.snapshot; + evsel->retirement_latency.mean = info.retirement_latency_mean; + evsel->retirement_latency.min = info.retirement_latency_min; + evsel->retirement_latency.max = info.retirement_latency_max; + return 0; } int parse_events_multi_pmu_add(struct parse_events_state *parse_state, - const char *event_name, u64 hw_config, + const char *event_name, const struct parse_events_terms *const_parsed_terms, struct list_head **listp, void *loc_) { @@ -1548,6 +1630,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, int ok = 0; const char *config; struct parse_events_terms parsed_terms; + struct evsel *first_wildcard_match = NULL; *listp = NULL; @@ -1579,8 +1662,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, INIT_LIST_HEAD(list); - while ((pmu = perf_pmus__scan(pmu)) != NULL) { - bool auto_merge_stats; + while ((pmu = perf_pmus__scan_for_event(pmu, event_name)) != NULL) { if (parse_events__filter_pmu(parse_state, pmu)) continue; @@ -1588,9 +1670,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, if (!perf_pmu__have_event(pmu, event_name)) continue; - auto_merge_stats = perf_pmu__auto_merge_stats(pmu); if (!parse_events_add_pmu(parse_state, list, pmu, - &parsed_terms, auto_merge_stats, hw_config)) { + &parsed_terms, first_wildcard_match)) { struct strbuf sb; strbuf_init(&sb, /*hint=*/ 0); @@ -1599,11 +1680,13 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, strbuf_release(&sb); ok++; } + if (first_wildcard_match == NULL) + first_wildcard_match = container_of(list->prev, struct evsel, core.node); } if (parse_state->fake_pmu) { if (!parse_events_add_pmu(parse_state, list, perf_pmus__fake_pmu(), &parsed_terms, - /*auto_merge_stats=*/true, hw_config)) { + first_wildcard_match)) { struct strbuf sb; strbuf_init(&sb, /*hint=*/ 0); @@ -1634,6 +1717,7 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state struct perf_pmu *pmu; int ok = 0; char *help; + struct evsel *first_wildcard_match = NULL; *listp = malloc(sizeof(**listp)); if (!*listp) @@ -1644,32 +1728,32 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state /* Attempt to add to list assuming event_or_pmu is a PMU name. */ pmu = perf_pmus__find(event_or_pmu); if (pmu && !parse_events_add_pmu(parse_state, *listp, pmu, const_parsed_terms, - /*auto_merge_stats=*/false, - /*alternate_hw_config=*/PERF_COUNT_HW_MAX)) + first_wildcard_match)) return 0; if (parse_state->fake_pmu) { if (!parse_events_add_pmu(parse_state, *listp, perf_pmus__fake_pmu(), const_parsed_terms, - /*auto_merge_stats=*/false, - /*alternate_hw_config=*/PERF_COUNT_HW_MAX)) + first_wildcard_match)) return 0; } pmu = NULL; /* Failed to add, try wildcard expansion of event_or_pmu as a PMU name. */ - while ((pmu = perf_pmus__scan(pmu)) != NULL) { - if (!parse_events__filter_pmu(parse_state, pmu) && - perf_pmu__match(pmu, event_or_pmu)) { - bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu); - - if (!parse_events_add_pmu(parse_state, *listp, pmu, - const_parsed_terms, - auto_merge_stats, - /*alternate_hw_config=*/PERF_COUNT_HW_MAX)) { - ok++; - parse_state->wild_card_pmus = true; - } + while ((pmu = perf_pmus__scan_matching_wildcard(pmu, event_or_pmu)) != NULL) { + + if (parse_events__filter_pmu(parse_state, pmu)) + continue; + + if (!parse_events_add_pmu(parse_state, *listp, pmu, + const_parsed_terms, + first_wildcard_match)) { + ok++; + parse_state->wild_card_pmus = true; + } + if (first_wildcard_match == NULL) { + first_wildcard_match = + container_of((*listp)->prev, struct evsel, core.node); } } if (ok) @@ -1677,7 +1761,7 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state /* Failure to add, assume event_or_pmu is an event name. */ zfree(listp); - if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, PERF_COUNT_HW_MAX, + if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, const_parsed_terms, listp, loc)) return 0; @@ -1727,13 +1811,11 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state, int eH = group ? evsel->core.attr.exclude_host : 0; int eG = group ? evsel->core.attr.exclude_guest : 0; int exclude = eu | ek | eh; - int exclude_GH = group ? evsel->exclude_GH : 0; + int exclude_GH = eG | eH; if (mod.user) { if (!exclude) exclude = eu = ek = eh = 1; - if (!exclude_GH && !perf_guest && exclude_GH_default) - eG = 1; eu = 0; } if (mod.kernel) { @@ -1756,6 +1838,13 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state, exclude_GH = eG = eH = 1; eH = 0; } + if (!exclude_GH && exclude_GH_default) { + if (perf_host) + eG = 1; + else if (perf_guest) + eH = 1; + } + evsel->core.attr.exclude_user = eu; evsel->core.attr.exclude_kernel = ek; evsel->core.attr.exclude_hv = eh; @@ -1806,6 +1895,8 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state, evsel->bpf_counter = true; if (mod.retire_lat) evsel->retire_lat = true; + if (mod.dont_regroup) + evsel->dont_regroup = true; } return 0; } @@ -1843,7 +1934,6 @@ int parse_events__set_default_name(struct list_head *list, char *name) } static int parse_events__scanner(const char *str, - FILE *input, struct parse_events_state *parse_state) { YY_BUFFER_STATE buffer; @@ -1854,10 +1944,7 @@ static int parse_events__scanner(const char *str, if (ret) return ret; - if (str) - buffer = parse_events__scan_string(str, scanner); - else - parse_events_set_in(input, scanner); + buffer = parse_events__scan_string(str, scanner); #ifdef PARSER_DEBUG parse_events_debug = 1; @@ -1865,10 +1952,8 @@ static int parse_events__scanner(const char *str, #endif ret = parse_events_parse(parse_state, scanner); - if (str) { - parse_events__flush_buffer(buffer, scanner); - parse_events__delete_buffer(buffer, scanner); - } + parse_events__flush_buffer(buffer, scanner); + parse_events__delete_buffer(buffer, scanner); parse_events_lex_destroy(scanner); return ret; } @@ -1876,7 +1961,7 @@ static int parse_events__scanner(const char *str, /* * parse event config string, return a list of event terms. */ -int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input) +int parse_events_terms(struct parse_events_terms *terms, const char *str) { struct parse_events_state parse_state = { .terms = NULL, @@ -1884,7 +1969,7 @@ int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE * }; int ret; - ret = parse_events__scanner(str, input, &parse_state); + ret = parse_events__scanner(str, &parse_state); if (!ret) list_splice(&parse_state.terms->terms, &terms->terms); @@ -1974,59 +2059,82 @@ static int evlist__cmp(void *_fg_idx, const struct list_head *l, const struct li int *force_grouped_idx = _fg_idx; int lhs_sort_idx, rhs_sort_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; - bool lhs_has_group, rhs_has_group; /* - * First sort by grouping/leader. Read the leader idx only if the evsel - * is part of a group, by default ungrouped events will be sorted - * relative to grouped events based on where the first ungrouped event - * occurs. If both events don't have a group we want to fall-through to - * the arch specific sorting, that can reorder and fix things like - * Intel's topdown events. + * Get the indexes of the 2 events to sort. If the events are + * in groups then the leader's index is used otherwise the + * event's index is used. An index may be forced for events that + * must be in the same group, namely Intel topdown events. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { - lhs_has_group = true; - lhs_sort_idx = lhs_core->leader->idx; + if (lhs->dont_regroup) { + lhs_sort_idx = lhs_core->idx; + } else if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs)) { + lhs_sort_idx = *force_grouped_idx; } else { - lhs_has_group = false; - lhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs) - ? *force_grouped_idx - : lhs_core->idx; - } - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { - rhs_has_group = true; - rhs_sort_idx = rhs_core->leader->idx; + bool lhs_has_group = lhs_core->leader != lhs_core || lhs_core->nr_members > 1; + + lhs_sort_idx = lhs_has_group ? lhs_core->leader->idx : lhs_core->idx; + } + if (rhs->dont_regroup) { + rhs_sort_idx = rhs_core->idx; + } else if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs)) { + rhs_sort_idx = *force_grouped_idx; } else { - rhs_has_group = false; - rhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs) - ? *force_grouped_idx - : rhs_core->idx; + bool rhs_has_group = rhs_core->leader != rhs_core || rhs_core->nr_members > 1; + + rhs_sort_idx = rhs_has_group ? rhs_core->leader->idx : rhs_core->idx; } + /* If the indices differ then respect the insertion order. */ if (lhs_sort_idx != rhs_sort_idx) return lhs_sort_idx - rhs_sort_idx; - /* Group by PMU if there is a group. Groups can't span PMUs. */ - if (lhs_has_group && rhs_has_group) { - lhs_pmu_name = lhs->group_pmu_name; - rhs_pmu_name = rhs->group_pmu_name; - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; - } + /* + * Ignoring forcing, lhs_sort_idx == rhs_sort_idx so lhs and rhs should + * be in the same group. Events in the same group need to be ordered by + * their grouping PMU name as the group will be broken to ensure only + * events on the same PMU are programmed together. + * + * With forcing the lhs_sort_idx == rhs_sort_idx shows that one or both + * events are being forced to be at force_group_index. If only one event + * is being forced then the other event is the group leader of the group + * we're trying to force the event into. Ensure for the force grouped + * case that the PMU name ordering is also respected. + */ + lhs_pmu_name = lhs->group_pmu_name; + rhs_pmu_name = rhs->group_pmu_name; + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; - /* Architecture specific sorting. */ + /* + * Architecture specific sorting, by default sort events in the same + * group with the same PMU by their insertion index. On Intel topdown + * constraints must be adhered to - slots first, etc. + */ return arch_evlist__cmp(lhs, rhs); } +int __weak arch_evlist__add_required_events(struct list_head *list __always_unused) +{ + return 0; +} + static int parse_events__sort_events_and_fix_groups(struct list_head *list) { int idx = 0, force_grouped_idx = -1; struct evsel *pos, *cur_leader = NULL; struct perf_evsel *cur_leaders_grp = NULL; - bool idx_changed = false, cur_leader_force_grouped = false; + bool idx_changed = false; int orig_num_leaders = 0, num_leaders = 0; int ret; + struct evsel *force_grouped_leader = NULL; + bool last_event_was_forced_leader = false; + + /* On x86 topdown metrics events require a slots event. */ + ret = arch_evlist__add_required_events(list); + if (ret) + return ret; /* * Compute index to insert ungrouped events at. Place them where the @@ -2049,10 +2157,13 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) */ pos->core.idx = idx++; - /* Remember an index to sort all forced grouped events together to. */ - if (force_grouped_idx == -1 && pos == pos_leader && pos->core.nr_members < 2 && - arch_evsel__must_be_in_group(pos)) - force_grouped_idx = pos->core.idx; + /* + * Remember an index to sort all forced grouped events + * together to. Use the group leader as some events + * must appear first within the group. + */ + if (force_grouped_idx == -1 && arch_evsel__must_be_in_group(pos)) + force_grouped_idx = pos_leader->core.idx; } /* Sort events. */ @@ -2064,10 +2175,10 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) */ idx = 0; list_for_each_entry(pos, list, core.node) { - const struct evsel *pos_leader = evsel__leader(pos); + struct evsel *pos_leader = evsel__leader(pos); const char *pos_pmu_name = pos->group_pmu_name; const char *cur_leader_pmu_name; - bool pos_force_grouped = force_grouped_idx != -1 && + bool pos_force_grouped = force_grouped_idx != -1 && !pos->dont_regroup && arch_evsel__must_be_in_group(pos); /* Reset index and nr_members. */ @@ -2080,31 +2191,65 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) * Set the group leader respecting the given groupings and that * groups can't span PMUs. */ - if (!cur_leader) - cur_leader = pos; - + if (!cur_leader || pos->dont_regroup) { + cur_leader = pos->dont_regroup ? pos_leader : pos; + cur_leaders_grp = &cur_leader->core; + if (pos_force_grouped) + force_grouped_leader = pos; + } cur_leader_pmu_name = cur_leader->group_pmu_name; - if ((cur_leaders_grp != pos->core.leader && - (!pos_force_grouped || !cur_leader_force_grouped)) || - strcmp(cur_leader_pmu_name, pos_pmu_name)) { - /* Event is for a different group/PMU than last. */ + if (strcmp(cur_leader_pmu_name, pos_pmu_name)) { + /* PMU changed so the group/leader must change. */ cur_leader = pos; - /* - * Remember the leader's group before it is overwritten, - * so that later events match as being in the same - * group. - */ cur_leaders_grp = pos->core.leader; + if (pos_force_grouped && force_grouped_leader == NULL) + force_grouped_leader = pos; + } else if (cur_leaders_grp != pos->core.leader) { + bool split_even_if_last_leader_was_forced = true; + /* - * Avoid forcing events into groups with events that - * don't need to be in the group. + * Event is for a different group. If the last event was + * the forced group leader then subsequent group events + * and forced events should be in the same group. If + * there are no other forced group events then the + * forced group leader wasn't really being forced into a + * group, it just set arch_evsel__must_be_in_group, and + * we don't want the group to split here. */ - cur_leader_force_grouped = pos_force_grouped; + if (force_grouped_idx != -1 && last_event_was_forced_leader) { + struct evsel *pos2 = pos; + /* + * Search the whole list as the group leaders + * aren't currently valid. + */ + list_for_each_entry_continue(pos2, list, core.node) { + if (pos->core.leader == pos2->core.leader && + arch_evsel__must_be_in_group(pos2)) { + split_even_if_last_leader_was_forced = false; + break; + } + } + } + if (!last_event_was_forced_leader || split_even_if_last_leader_was_forced) { + if (pos_force_grouped) { + if (force_grouped_leader) { + cur_leader = force_grouped_leader; + cur_leaders_grp = force_grouped_leader->core.leader; + } else { + cur_leader = force_grouped_leader = pos; + cur_leaders_grp = &pos->core; + } + } else { + cur_leader = pos; + cur_leaders_grp = pos->core.leader; + } + } } if (pos_leader != cur_leader) { /* The leader changed so update it. */ evsel__set_leader(pos, cur_leader); } + last_event_was_forced_leader = (force_grouped_leader == pos); } list_for_each_entry(pos, list, core.node) { struct evsel *pos_leader = evsel__leader(pos); @@ -2132,7 +2277,7 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte }; int ret, ret2; - ret = parse_events__scanner(str, /*input=*/ NULL, &parse_state); + ret = parse_events__scanner(str, &parse_state); if (!ret && list_empty(&parse_state.list)) { WARN_ONCE(true, "WARNING: event parser found nothing\n"); @@ -2143,14 +2288,23 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte if (ret2 < 0) return ret; - if (ret2 && warn_if_reordered && !parse_state.wild_card_pmus) - pr_warning("WARNING: events were regrouped to match PMUs\n"); - /* * Add list to the evlist even with errors to allow callers to clean up. */ evlist__splice_list_tail(evlist, &parse_state.list); + if (ret2 && warn_if_reordered && !parse_state.wild_card_pmus) { + evlist__uniquify_evsel_names(evlist, &stat_config); + pr_warning("WARNING: events were regrouped to match PMUs\n"); + + if (verbose > 0) { + struct strbuf sb = STRBUF_INIT; + + evlist__format_evsels(evlist, &sb, 2048); + pr_debug("evlist after sorting/fixing: '%s'\n", sb.buf); + strbuf_release(&sb); + } + } if (!ret) { struct evsel *last; @@ -2175,6 +2329,8 @@ int parse_event(struct evlist *evlist, const char *str) parse_events_error__init(&err); ret = parse_events(evlist, str, &err); + if (ret && verbose > 0) + parse_events_error__print(&err, str); parse_events_error__exit(&err); return ret; } @@ -2403,12 +2559,17 @@ foreach_evsel_in_last_glob(struct evlist *evlist, return 0; } +/* Will a tracepoint filter work for str or should a BPF filter be used? */ +static bool is_possible_tp_filter(const char *str) +{ + return strstr(str, "uid") == NULL; +} + static int set_filter(struct evsel *evsel, const void *arg) { const char *str = arg; - bool found = false; int nr_addr_filters = 0; - struct perf_pmu *pmu = NULL; + struct perf_pmu *pmu; if (evsel == NULL) { fprintf(stderr, @@ -2416,7 +2577,7 @@ static int set_filter(struct evsel *evsel, const void *arg) return -1; } - if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) { + if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT && is_possible_tp_filter(str)) { if (evsel__append_tp_filter(evsel, str) < 0) { fprintf(stderr, "not enough memory to hold filter string\n"); @@ -2426,16 +2587,11 @@ static int set_filter(struct evsel *evsel, const void *arg) return 0; } - while ((pmu = perf_pmus__scan(pmu)) != NULL) - if (pmu->type == evsel->core.attr.type) { - found = true; - break; - } - - if (found) + pmu = evsel__find_pmu(evsel); + if (pmu) { perf_pmu__scan_file(pmu, "nr_addr_filters", "%d", &nr_addr_filters); - + } if (!nr_addr_filters) return perf_bpf_filter__parse(&evsel->bpf_filters, str); @@ -2457,6 +2613,30 @@ int parse_filter(const struct option *opt, const char *str, (const void *)str); } +int parse_uid_filter(struct evlist *evlist, uid_t uid) +{ + struct option opt = { + .value = &evlist, + }; + char buf[128]; + int ret; + + snprintf(buf, sizeof(buf), "uid == %d", uid); + ret = parse_filter(&opt, buf, /*unset=*/0); + if (ret) { + if (use_browser >= 1) { + /* + * Use ui__warning so a pop up appears above the + * underlying BPF error message. + */ + ui__warning("Failed to add UID filtering that uses BPF filtering.\n"); + } else { + fprintf(stderr, "Failed to add UID filtering that uses BPF filtering.\n"); + } + } + return ret; +} + static int add_exclude_perf_filter(struct evsel *evsel, const void *arg __maybe_unused) { @@ -2647,7 +2827,7 @@ void parse_events_terms__delete(struct parse_events_terms *terms) free(terms); } -int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb) +static int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb) { struct parse_events_term *term; bool first = true; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index e176a34ab088..3577ab213730 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -9,8 +9,8 @@ #include <stdbool.h> #include <linux/types.h> #include <linux/perf_event.h> -#include <stdio.h> #include <string.h> +#include <sys/types.h> struct evsel; struct evlist; @@ -20,7 +20,7 @@ struct option; struct perf_pmu; struct strbuf; -const char *event_type(int type); +const char *event_type(size_t type); /* Arguments encoded in opt->value. */ struct parse_events_option_args { @@ -45,6 +45,7 @@ static inline int parse_events(struct evlist *evlist, const char *str, int parse_event(struct evlist *evlist, const char *str); int parse_filter(const struct option *opt, const char *str, int unset); +int parse_uid_filter(struct evlist *evlist, uid_t uid); int exclude_perf(const struct option *opt, const char *arg, int unset); enum parse_events__term_val_type { @@ -58,6 +59,7 @@ enum parse_events__term_type { PARSE_EVENTS__TERM_TYPE_CONFIG1, PARSE_EVENTS__TERM_TYPE_CONFIG2, PARSE_EVENTS__TERM_TYPE_CONFIG3, + PARSE_EVENTS__TERM_TYPE_CONFIG4, PARSE_EVENTS__TERM_TYPE_NAME, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ, @@ -78,9 +80,11 @@ enum parse_events__term_type { PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, PARSE_EVENTS__TERM_TYPE_METRIC_ID, PARSE_EVENTS__TERM_TYPE_RAW, - PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE, - PARSE_EVENTS__TERM_TYPE_HARDWARE, -#define __PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_HARDWARE + 1) + PARSE_EVENTS__TERM_TYPE_CPU, + PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV, + PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG, + PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG, +#define __PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG + 1) }; struct parse_events_term { @@ -128,12 +132,6 @@ struct parse_events_term { * value is assumed to be 1. An event name also has no value. */ bool no_value; - /** - * @alternate_hw_config: config is the event name but num is an - * alternate PERF_TYPE_HARDWARE config value which is often nice for the - * sake of quick matching. - */ - bool alternate_hw_config; }; struct parse_events_error { @@ -195,8 +193,7 @@ void parse_events_term__delete(struct parse_events_term *term); void parse_events_terms__delete(struct parse_events_terms *terms); void parse_events_terms__init(struct parse_events_terms *terms); void parse_events_terms__exit(struct parse_events_terms *terms); -int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input); -int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb); +int parse_events_terms(struct parse_events_terms *terms, const char *str); struct parse_events_modifier { u8 precise; /* Number of repeated 'p' for precision. */ @@ -213,6 +210,7 @@ struct parse_events_modifier { bool guest : 1; /* 'G' */ bool host : 1; /* 'H' */ bool retire_lat : 1; /* 'R' */ + bool dont_regroup : 1; /* 'X' */ }; int parse_events__modifier_event(struct parse_events_state *parse_state, void *loc, @@ -230,9 +228,6 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, u32 type, u64 config, const struct parse_events_terms *head_config, bool wildcard); -int parse_events_add_cache(struct list_head *list, int *idx, const char *name, - struct parse_events_state *parse_state, - struct parse_events_terms *parsed_terms); int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config); int parse_events_add_breakpoint(struct parse_events_state *parse_state, struct list_head *list, @@ -244,7 +239,7 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, struct perf_pmu *pmu); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, - const char *event_name, u64 hw_config, + const char *event_name, const struct parse_events_terms *const_parsed_terms, struct list_head **listp, void *loc); @@ -260,8 +255,6 @@ struct event_symbol { const char *symbol; const char *alias; }; -extern const struct event_symbol event_symbols_hw[]; -extern const struct event_symbol event_symbols_sw[]; char *parse_events_formats_error_string(char *additional_terms); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index bf7f73548605..251ce4321878 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -5,16 +5,14 @@ %option stack %option bison-locations %option yylineno -%option reject +%option noyywrap %{ #include <errno.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <unistd.h> +#include <stdlib.h> +#include <stdio.h> #include "parse-events.h" #include "parse-events-bison.h" -#include "evsel.h" char *parse_events_get_text(yyscan_t yyscanner); YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); @@ -53,27 +51,26 @@ static int str(yyscan_t scanner, int token) YYSTYPE *yylval = parse_events_get_lval(scanner); char *text = parse_events_get_text(scanner); - if (text[0] != '\'') { - yylval->str = strdup(text); - } else { - /* - * If a text tag specified on the command line - * contains opening single quite ' then it is - * expected that the tag ends with single quote - * as well, like this: - * name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\' - * quotes need to be escaped to bypass shell - * processing. - */ - yylval->str = strndup(&text[1], strlen(text) - 2); - } - + yylval->str = strdup(text); return token; } -static int lc_str(yyscan_t scanner, const struct parse_events_state *state) +static int quoted_str(yyscan_t scanner, int token) { - return str(scanner, state->match_legacy_cache_terms ? PE_LEGACY_CACHE : PE_NAME); + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + /* + * If a text tag specified on the command line + * contains opening single quite ' then it is + * expected that the tag ends with single quote + * as well, like this: + * name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\' + * quotes need to be escaped to bypass shell + * processing. + */ + yylval->str = strndup(&text[1], strlen(text) - 2); + return token; } /* @@ -113,14 +110,6 @@ do { \ yyless(0); \ } while (0) -static int sym(yyscan_t scanner, int type, int config) -{ - YYSTYPE *yylval = parse_events_get_lval(scanner); - - yylval->num = (type << 16) + config; - return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW; -} - static int term(yyscan_t scanner, enum parse_events__term_type type) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -129,16 +118,6 @@ static int term(yyscan_t scanner, enum parse_events__term_type type) return PE_TERM; } -static int hw_term(yyscan_t scanner, int config) -{ - YYSTYPE *yylval = parse_events_get_lval(scanner); - char *text = parse_events_get_text(scanner); - - yylval->hardware_term.str = strdup(text); - yylval->hardware_term.num = PERF_TYPE_HARDWARE + config; - return PE_TERM_HW; -} - static void modifiers_error(struct parse_events_state *parse_state, yyscan_t scanner, int pos, char mod_char, const char *mod_name) { @@ -202,6 +181,7 @@ static int modifiers(struct parse_events_state *parse_state, yyscan_t scanner) CASE('e', exclusive); CASE('b', bpf); CASE('R', retire_lat); + CASE('X', dont_regroup); default: return PE_ERROR; } @@ -218,10 +198,6 @@ do { \ yycolumn += yyleng; \ } while (0); -#define USER_REJECT \ - yycolumn -= yyleng; \ - REJECT - %} %x mem @@ -235,18 +211,23 @@ event [^,{}/]+ num_dec [0-9]+ num_hex 0x[a-fA-F0-9]{1,16} num_raw_hex [a-fA-F0-9]{1,16} -name [a-zA-Z0-9_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]* -name_tag [\'][a-zA-Z0-9_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] -name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* +/* Regular pattern to match the token PE_NAME. */ +name_start [a-zA-Z0-9_*?\[\]] +name {name_start}[a-zA-Z0-9_*?.\[\]!\-]* +/* PE_NAME token when inside a config term list, allows ':'. */ +term_name {name_start}[a-zA-Z0-9_*?.\[\]!\-:]* +/* + * PE_NAME token when quoted, allows ':,.='. + * Matches the RHS of terms like: name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'. + */ +quoted_name [\']{name_start}[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(). + * If you add a modifier you need to update modifiers(). * Also, the letters in modifier_event must not be in modifier_bp. */ -modifier_event [ukhpPGHSDIWebR]{1,16} +modifier_event [ukhpPGHSDIWebRX]{1,17} modifier_bp [rwx]{1,3} -lc_type (L1-dcache|l1-d|l1d|L1-data|L1-icache|l1-i|l1i|L1-instruction|LLC|L2|dTLB|d-tlb|Data-TLB|iTLB|i-tlb|Instruction-TLB|branch|branches|bpu|btb|bpc|node) -lc_op_result (load|loads|read|store|stores|write|prefetch|prefetches|speculative-read|speculative-load|refs|Reference|ops|access|misses|miss) digit [0-9] non_digit [^0-9] @@ -306,6 +287,7 @@ config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } config3 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG3); } +config4 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG4); } name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } freq { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ); } @@ -324,24 +306,17 @@ aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } aux-action { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } -cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } -stalled-cycles-frontend|idle-cycles-frontend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } -stalled-cycles-backend|idle-cycles-backend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } -instructions { return hw_term(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); } -cache-references { return hw_term(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); } -cache-misses { return hw_term(yyscanner, PERF_COUNT_HW_CACHE_MISSES); } -branch-instructions|branches { return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } -branch-misses { return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); } -bus-cycles { return hw_term(yyscanner, PERF_COUNT_HW_BUS_CYCLES); } -ref-cycles { return hw_term(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); } +cpu { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CPU); } +ratio-to-prev { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV); } +legacy-hardware-config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG); } +legacy-cache-config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG); } r{num_raw_hex} { return str(yyscanner, PE_RAW); } r0x{num_raw_hex} { return str(yyscanner, PE_RAW); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } -{lc_type} { return lc_str(yyscanner, _parse_state); } -{lc_type}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } -{lc_type}-{lc_op_result}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } -{name_minus} { return str(yyscanner, PE_NAME); } +{num_dec} { return value(_parse_state, yyscanner, 10); } +{num_hex} { return value(_parse_state, yyscanner, 16); } +{term_name} { return str(yyscanner, PE_NAME); } @{drv_cfg_term} { return drv_str(yyscanner, PE_DRV_CFG_TERM); } } @@ -377,32 +352,6 @@ r0x{num_raw_hex} { return str(yyscanner, PE_RAW); } <<EOF>> { BEGIN(INITIAL); } } -cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } -stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } -stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } -instructions { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); } -cache-references { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); } -cache-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); } -branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } -branch-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); } -bus-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); } -ref-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); } -cpu-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); } -task-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); } -page-faults|faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); } -minor-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); } -major-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } -context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); } -cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } -alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } -emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } -dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } -bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } -cgroup-switches { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); } - -{lc_type} { return str(yyscanner, PE_LEGACY_CACHE); } -{lc_type}-{lc_op_result} { return str(yyscanner, PE_LEGACY_CACHE); } -{lc_type}-{lc_op_result}-{lc_op_result} { return str(yyscanner, PE_LEGACY_CACHE); } mem: { BEGIN(mem); return PE_PREFIX_MEM; } r{num_raw_hex} { return str(yyscanner, PE_RAW); } {num_dec} { return value(_parse_state, yyscanner, 10); } @@ -410,7 +359,7 @@ r{num_raw_hex} { return str(yyscanner, PE_RAW); } {modifier_event} { return modifiers(_parse_state, yyscanner); } {name} { return str(yyscanner, PE_NAME); } -{name_tag} { return str(yyscanner, PE_NAME); } +{quoted_name} { return quoted_str(yyscanner, PE_NAME); } "/" { BEGIN(config); return '/'; } , { BEGIN(event); return ','; } : { return ':'; } @@ -421,8 +370,3 @@ r{num_raw_hex} { return str(yyscanner, PE_RAW); } . { } %% - -int parse_events_wrap(void *scanner __maybe_unused) -{ - return 1; -} diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index f888cbb076d6..c194de5ec1ec 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -55,24 +55,18 @@ static void free_list_evsel(struct list_head* list_evsel) %} %token PE_START_EVENTS PE_START_TERMS -%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_TERM +%token PE_VALUE PE_TERM %token PE_EVENT_NAME %token PE_RAW PE_NAME %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH -%token PE_LEGACY_CACHE %token PE_PREFIX_MEM %token PE_ERROR %token PE_DRV_CFG_TERM -%token PE_TERM_HW %type <num> PE_VALUE -%type <num> PE_VALUE_SYM_HW -%type <num> PE_VALUE_SYM_SW %type <mod> PE_MODIFIER_EVENT %type <term_type> PE_TERM -%type <num> value_sym %type <str> PE_RAW %type <str> PE_NAME -%type <str> PE_LEGACY_CACHE %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME %type <str> PE_DRV_CFG_TERM @@ -85,8 +79,6 @@ static void free_list_evsel(struct list_head* list_evsel) %type <list_terms> opt_pmu_config %destructor { parse_events_terms__delete ($$); } <list_terms> %type <list_evsel> event_pmu -%type <list_evsel> event_legacy_symbol -%type <list_evsel> event_legacy_cache %type <list_evsel> event_legacy_mem %type <list_evsel> event_legacy_tracepoint %type <list_evsel> event_legacy_numeric @@ -102,8 +94,6 @@ static void free_list_evsel(struct list_head* list_evsel) %destructor { free_list_evsel ($$); } <list_evsel> %type <tracepoint_name> tracepoint_name %destructor { free ($$.sys); free ($$.event); } <tracepoint_name> -%type <hardware_term> PE_TERM_HW -%destructor { free ($$.str); } <hardware_term> %union { @@ -118,10 +108,6 @@ static void free_list_evsel(struct list_head* list_evsel) char *sys; char *event; } tracepoint_name; - struct hardware_term { - char *str; - u64 num; - } hardware_term; } %% @@ -264,8 +250,6 @@ PE_EVENT_NAME event_def event_def event_def: event_pmu | - event_legacy_symbol | - event_legacy_cache sep_dc | event_legacy_mem sep_dc | event_legacy_tracepoint sep_dc | event_legacy_numeric sep_dc | @@ -290,7 +274,7 @@ PE_NAME sep_dc struct list_head *list; int err; - err = parse_events_multi_pmu_add(_parse_state, $1, PERF_COUNT_HW_MAX, NULL, &list, &@1); + err = parse_events_multi_pmu_add(_parse_state, $1, /*const_parsed_terms*/NULL, &list, &@1); if (err < 0) { struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; @@ -306,71 +290,6 @@ PE_NAME sep_dc $$ = list; } -value_sym: -PE_VALUE_SYM_HW -| -PE_VALUE_SYM_SW - -event_legacy_symbol: -value_sym '/' event_config '/' -{ - struct list_head *list; - int type = $1 >> 16; - int config = $1 & 255; - int err; - bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE); - - list = alloc_list(); - if (!list) - YYNOMEM; - err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard); - parse_events_terms__delete($3); - if (err) { - free_list_evsel(list); - PE_ABORT(err); - } - $$ = list; -} -| -value_sym sep_slash_slash_dc -{ - struct list_head *list; - int type = $1 >> 16; - int config = $1 & 255; - bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE); - int err; - - list = alloc_list(); - if (!list) - YYNOMEM; - err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard); - if (err) - PE_ABORT(err); - $$ = list; -} - -event_legacy_cache: -PE_LEGACY_CACHE opt_event_config -{ - struct parse_events_state *parse_state = _parse_state; - struct list_head *list; - int err; - - list = alloc_list(); - if (!list) - YYNOMEM; - - err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2); - - parse_events_terms__delete($2); - free($1); - if (err) { - free_list_evsel(list); - PE_ABORT(err); - } - $$ = list; -} - event_legacy_mem: PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event_config { @@ -589,12 +508,7 @@ event_term $$ = head; } -name_or_raw: PE_RAW | PE_NAME | PE_LEGACY_CACHE -| -PE_TERM_HW -{ - $$ = $1.str; -} +name_or_raw: PE_RAW | PE_NAME event_term: PE_RAW @@ -636,19 +550,6 @@ name_or_raw '=' PE_VALUE $$ = term; } | -PE_LEGACY_CACHE -{ - struct parse_events_term *term; - int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE, - $1, /*num=*/1, /*novalue=*/true, &@1, /*loc_val=*/NULL); - - if (err) { - free($1); - PE_ABORT(err); - } - $$ = term; -} -| PE_NAME { struct parse_events_term *term; @@ -662,20 +563,6 @@ PE_NAME $$ = term; } | -PE_TERM_HW -{ - struct parse_events_term *term; - int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE, - $1.str, $1.num & 255, /*novalue=*/false, - &@1, /*loc_val=*/NULL); - - if (err) { - free($1.str); - PE_ABORT(err); - } - $$ = term; -} -| PE_TERM '=' name_or_raw { struct parse_events_term *term; @@ -744,8 +631,6 @@ PE_DRV_CFG_TERM sep_dc: ':' | -sep_slash_slash_dc: '/' '/' | ':' | - %% void parse_events_error(YYLTYPE *loc, void *_parse_state, diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index cda1c620968e..c93c2f0c8105 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -5,15 +5,54 @@ #include <string.h> #include <stdio.h> #include "util/debug.h" +#include <dwarf-regs.h> #include <subcmd/parse-options.h> #include "util/perf_regs.h" #include "util/parse-regs-options.h" +static void list_perf_regs(FILE *fp, uint64_t mask) +{ + const char *last_name = NULL; + + fprintf(fp, "available registers: "); + for (int reg = 0; reg < 64; reg++) { + const char *name; + + if (((1ULL << reg) & mask) == 0) + continue; + + name = perf_reg_name(reg, EM_HOST, EF_HOST); + if (name && (!last_name || strcmp(last_name, name))) + fprintf(fp, "%s%s", reg > 0 ? " " : "", name); + last_name = name; + } + fputc('\n', fp); +} + +static uint64_t name_to_perf_reg_mask(const char *to_match, uint64_t mask) +{ + uint64_t reg_mask = 0; + + for (int reg = 0; reg < 64; reg++) { + const char *name; + + if (((1ULL << reg) & mask) == 0) + continue; + + name = perf_reg_name(reg, EM_HOST, EF_HOST); + if (!name) + continue; + + if (!strcasecmp(to_match, name)) + reg_mask |= 1ULL << reg; + } + return reg_mask; +} + static int __parse_regs(const struct option *opt, const char *str, int unset, bool intr) { uint64_t *mode = (uint64_t *)opt->value; - const struct sample_reg *r = NULL; char *s, *os = NULL, *p; int ret = -1; uint64_t mask; @@ -27,56 +66,46 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr) if (*mode) return -1; - if (intr) - mask = arch__intr_reg_mask(); - else - mask = arch__user_reg_mask(); + mask = intr ? perf_intr_reg_mask(EM_HOST) : perf_user_reg_mask(EM_HOST); /* str may be NULL in case no arg is passed to -I */ - if (str) { - /* because str is read-only */ - s = os = strdup(str); - if (!s) - return -1; - - for (;;) { - p = strchr(s, ','); - if (p) - *p = '\0'; - - if (!strcmp(s, "?")) { - fprintf(stderr, "available registers: "); - for (r = arch__sample_reg_masks(); r->name; r++) { - if (r->mask & mask) - fprintf(stderr, "%s ", r->name); - } - fputc('\n', stderr); - /* just printing available regs */ - goto error; - } - for (r = arch__sample_reg_masks(); r->name; r++) { - if ((r->mask & mask) && !strcasecmp(s, r->name)) - break; - } - if (!r || !r->name) { - ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n", - s, intr ? "-I" : "--user-regs="); - goto error; - } - - *mode |= r->mask; - - if (!p) - break; - - s = p + 1; + if (!str) { + *mode = mask; + return 0; + } + + /* because str is read-only */ + s = os = strdup(str); + if (!s) + return -1; + + for (;;) { + uint64_t reg_mask; + + p = strchr(s, ','); + if (p) + *p = '\0'; + + if (!strcmp(s, "?")) { + list_perf_regs(stderr, mask); + goto error; + } + + reg_mask = name_to_perf_reg_mask(s, mask); + if (reg_mask == 0) { + ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n", + s, intr ? "-I" : "--user-regs="); + goto error; } + *mode |= reg_mask; + + if (!p) + break; + + s = p + 1; } ret = 0; - /* default to all possible regs */ - if (*mode == 0) - *mode = mask; error: free(os); return ret; diff --git a/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c index 9dcda80d310f..6833d34dcbfd 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c @@ -1,7 +1,144 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <regex.h> +#include <string.h> +#include <sys/auxv.h> +#include <linux/kernel.h> +#include <linux/zalloc.h> +#include "../debug.h" +#include "../event.h" #include "../perf_regs.h" -#include "../../../arch/arm64/include/uapi/asm/perf_regs.h" +#include "../../perf-sys.h" +#include "../../arch/arm64/include/perf_regs.h" + +#define SMPL_REG_MASK(b) (1ULL << (b)) + +#ifndef HWCAP_SVE +#define HWCAP_SVE (1 << 22) +#endif + +/* %xNUM */ +#define SDT_OP_REGEX1 "^(x[1-2]?[0-9]|3[0-1])$" + +/* [sp], [sp, NUM] */ +#define SDT_OP_REGEX2 "^\\[sp(, )?([0-9]+)?\\]$" + +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + + initialized = 1; + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error.\n"); + return ret; +} + +/* + * SDT marker arguments on Arm64 uses %xREG or [sp, NUM], currently + * support these two formats. + */ +int __perf_sdt_arg_parse_op_arm64(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[5]; + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) { + /* Extract xNUM */ + new_len = 2; /* % NULL */ + new_len += (int)(rm[1].rm_eo - rm[1].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%%%.*s", + (int)(rm[1].rm_eo - rm[1].rm_so), old_op + rm[1].rm_so); + } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) { + /* [sp], [sp, NUM] or [sp,NUM] */ + new_len = 7; /* + ( % s p ) NULL */ + + /* If the argument is [sp], need to fill offset '0' */ + if (rm[2].rm_so == -1) + new_len += 1; + else + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + if (rm[2].rm_so == -1) + scnprintf(*new_op, new_len, "+0(%%sp)"); + else + scnprintf(*new_op, new_len, "+%.*s(%%sp)", + (int)(rm[2].rm_eo - rm[2].rm_so), + old_op + rm[2].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} + +uint64_t __perf_reg_mask_arm64(bool intr) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_REGS_USER, + .disabled = 1, + .exclude_kernel = 1, + .sample_period = 1, + .sample_regs_user = PERF_REGS_MASK + }; + int fd; + + if (intr) + return PERF_REGS_MASK; + + if (getauxval(AT_HWCAP) & HWCAP_SVE) + attr.sample_regs_user |= SMPL_REG_MASK(PERF_REG_ARM64_VG); + + /* + * Check if the pmu supports perf extended regs, before + * returning the register mask to sample. Open the event + * on the perf process to check this. + */ + if (attr.sample_regs_user != PERF_REGS_MASK) { + event_attr_init(&attr); + fd = sys_perf_event_open(&attr, /*pid=*/0, /*cpu=*/-1, + /*group_fd=*/-1, /*flags=*/0); + if (fd != -1) { + close(fd); + return attr.sample_regs_user; + } + } + return PERF_REGS_MASK; +} const char *__perf_reg_name_arm64(int id) { diff --git a/tools/perf/util/perf-regs-arch/perf_regs_arm.c b/tools/perf/util/perf-regs-arch/perf_regs_arm.c index e29d130a587a..184d6e248dfc 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_arm.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_arm.c @@ -1,7 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include "../perf_regs.h" -#include "../../../arch/arm/include/uapi/asm/perf_regs.h" +#include "../../arch/arm/include/perf_regs.h" + +uint64_t __perf_reg_mask_arm(bool intr __maybe_unused) +{ + return PERF_REGS_MASK; +} const char *__perf_reg_name_arm(int id) { diff --git a/tools/perf/util/perf-regs-arch/perf_regs_csky.c b/tools/perf/util/perf-regs-arch/perf_regs_csky.c index 75b461ef2eba..16cbd8303acf 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_csky.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_csky.c @@ -1,10 +1,26 @@ // SPDX-License-Identifier: GPL-2.0 - +#include <elf.h> +#ifndef EF_CSKY_ABIMASK +#define EF_CSKY_ABIMASK 0XF0000000 +#endif +#ifndef EF_CSKY_ABIV2 +#define EF_CSKY_ABIV2 0X20000000 +#endif #include "../perf_regs.h" -#include "../../arch/csky/include/uapi/asm/perf_regs.h" +#undef __CSKYABIV2__ +#define __CSKYABIV2__ 1 // Always want the V2 register definitions. +#include "../../arch/csky/include/perf_regs.h" + +uint64_t __perf_reg_mask_csky(bool intr __maybe_unused) +{ + return PERF_REGS_MASK; +} -const char *__perf_reg_name_csky(int id) +const char *__perf_reg_name_csky(int id, uint32_t e_flags) { + if (id >= PERF_REG_CSKY_EXREGS0 && (e_flags & EF_CSKY_ABIMASK) == EF_CSKY_ABIV2) + return NULL; + switch (id) { case PERF_REG_CSKY_A0: return "a0"; @@ -40,7 +56,6 @@ const char *__perf_reg_name_csky(int id) return "lr"; case PERF_REG_CSKY_PC: return "pc"; -#if defined(__CSKYABIV2__) case PERF_REG_CSKY_EXREGS0: return "exregs0"; case PERF_REG_CSKY_EXREGS1: @@ -77,12 +92,9 @@ const char *__perf_reg_name_csky(int id) return "hi"; case PERF_REG_CSKY_LO: return "lo"; -#endif default: return NULL; } - - return NULL; } uint64_t __perf_reg_ip_csky(void) diff --git a/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c index 043f97f4e3ac..478ee889afa1 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c @@ -1,7 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include "../perf_regs.h" -#include "../../../arch/loongarch/include/uapi/asm/perf_regs.h" +#include "../../arch/loongarch/include/perf_regs.h" + +uint64_t __perf_reg_mask_loongarch(bool intr __maybe_unused) +{ + return PERF_REGS_MASK; +} const char *__perf_reg_name_loongarch(int id) { diff --git a/tools/perf/util/perf-regs-arch/perf_regs_mips.c b/tools/perf/util/perf-regs-arch/perf_regs_mips.c index 793178fc3c78..c5a475f6ec64 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_mips.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_mips.c @@ -1,7 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include "../perf_regs.h" -#include "../../../arch/mips/include/uapi/asm/perf_regs.h" +#include "../../arch/mips/include/perf_regs.h" + +uint64_t __perf_reg_mask_mips(bool intr __maybe_unused) +{ + return PERF_REGS_MASK; +} const char *__perf_reg_name_mips(int id) { diff --git a/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c index 08636bb09a3a..217a001ccd2e 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c @@ -1,7 +1,188 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <string.h> +#include <regex.h> +#include <linux/zalloc.h> + +#include "../debug.h" +#include "../event.h" +#include "../header.h" #include "../perf_regs.h" -#include "../../../arch/powerpc/include/uapi/asm/perf_regs.h" +#include "../../perf-sys.h" +#include "../../arch/powerpc/util/utils_header.h" +#include "../../arch/powerpc/include/perf_regs.h" + +#include <linux/kernel.h> + +#define PVR_POWER9 0x004E +#define PVR_POWER10 0x0080 +#define PVR_POWER11 0x0082 + +/* REG or %rREG */ +#define SDT_OP_REGEX1 "^(%r)?([1-2]?[0-9]|3[0-1])$" + +/* -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) */ +#define SDT_OP_REGEX2 "^(\\-)?([0-9]+)\\((%r)?([1-2]?[0-9]|3[0-1])\\)$" + +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + + initialized = 1; + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error.\n"); + return ret; +} + +/* + * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG). + * Possible variants of OP are: + * Format Example + * ------------------------- + * NUM(REG) 48(18) + * -NUM(REG) -48(18) + * NUM(%rREG) 48(%r18) + * -NUM(%rREG) -48(%r18) + * REG 18 + * %rREG %r18 + * iNUM i0 + * i-NUM i-1 + * + * SDT marker arguments on Powerpc uses %rREG form with -mregnames flag + * and REG form with -mno-regnames. Here REG is general purpose register, + * which is in 0 to 31 range. + */ +int __perf_sdt_arg_parse_op_powerpc(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[5]; + char prefix; + + /* Constant argument. Uprobe does not support it */ + if (old_op[0] == 'i') { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) { + /* REG or %rREG --> %gprREG */ + + new_len = 5; /* % g p r NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%%gpr%.*s", + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so); + } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) { + /* + * -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) --> + * +/-NUM(%gprREG) + */ + prefix = (rm[1].rm_so == -1) ? '+' : '-'; + + new_len = 8; /* +/- ( % g p r ) NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + new_len += (int)(rm[4].rm_eo - rm[4].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%c%.*s(%%gpr%.*s)", prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[4].rm_eo - rm[4].rm_so), old_op + rm[4].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} + +/* + * mfspr is a POWERPC specific instruction, ensure it's only + * built and called on POWERPC by guarding with __powerpc64__ + * or __powerpc__. + */ +#if defined(__powerpc64__) && defined(__powerpc__) +uint64_t __perf_reg_mask_powerpc(bool intr) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_REGS_INTR, + .precise_ip = 1, + .disabled = 1, + .exclude_kernel = 1, + }; + int fd; + u32 version; + u64 extended_mask = 0, mask = PERF_REGS_MASK; + + if (!intr) + return PERF_REGS_MASK; + + /* + * Get the PVR value to set the extended + * mask specific to platform. + */ + version = (((mfspr(SPRN_PVR)) >> 16) & 0xFFFF); + if (version == PVR_POWER9) + extended_mask = PERF_REG_PMU_MASK_300; + else if ((version == PVR_POWER10) || (version == PVR_POWER11)) + extended_mask = PERF_REG_PMU_MASK_31; + else + return mask; + + attr.sample_regs_intr = extended_mask; + attr.sample_period = 1; + event_attr_init(&attr); + + /* + * Check if the pmu supports perf extended regs, before + * returning the register mask to sample. Open the event + * on the perf process to check this. + */ + fd = sys_perf_event_open(&attr, /*pid=*/0, /*cpu=*/-1, + /*group_fd=*/-1, /*flags=*/0); + if (fd != -1) { + close(fd); + mask |= extended_mask; + } + return mask; +} +#else +uint64_t __perf_reg_mask_powerpc(bool intr __maybe_unused) +{ + return PERF_REGS_MASK; +} +#endif const char *__perf_reg_name_powerpc(int id) { diff --git a/tools/perf/util/perf-regs-arch/perf_regs_riscv.c b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c index 337b687c655d..5b5f21fcba8c 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_riscv.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c @@ -1,7 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include "../perf_regs.h" -#include "../../../arch/riscv/include/uapi/asm/perf_regs.h" +#include "../../arch/riscv/include/perf_regs.h" + +uint64_t __perf_reg_mask_riscv(bool intr __maybe_unused) +{ + return PERF_REGS_MASK; +} const char *__perf_reg_name_riscv(int id) { diff --git a/tools/perf/util/perf-regs-arch/perf_regs_s390.c b/tools/perf/util/perf-regs-arch/perf_regs_s390.c index d69bba881080..19f219225183 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_s390.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_s390.c @@ -1,7 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <regex.h> #include "../perf_regs.h" -#include "../../../arch/s390/include/uapi/asm/perf_regs.h" +#include "../../arch/s390/include/perf_regs.h" +#include "debug.h" + +#include <linux/zalloc.h> +#include <linux/kernel.h> + +uint64_t __perf_reg_mask_s390(bool intr __maybe_unused) +{ + return PERF_REGS_MASK; +} const char *__perf_reg_name_s390(int id) { @@ -90,3 +101,75 @@ uint64_t __perf_reg_sp_s390(void) { return PERF_REG_S390_R15; } + +/* %rXX */ +#define SDT_OP_REGEX1 "^(%r([0-9]|1[0-5]))$" +/* +-###(%rXX) */ +#define SDT_OP_REGEX2 "^([+-]?[0-9]+\\(%r([0-9]|1[0-5])\\))$" +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + initialized = 1; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + initialized = 2; + + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error, initialized %d\n", initialized); + initialized = 0; + return ret; +} + +/* + * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG). + * Possible variants of OP are: + * Format Example + * ------------------------- + * NUM(%rREG) 48(%r1) + * -NUM(%rREG) -48(%r1) + * +NUM(%rREG) +48(%r1) + * %rREG %r1 + */ +int __perf_sdt_arg_parse_op_s390(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[6]; + + *new_op = NULL; + ret = sdt_init_op_regex(); + if (ret) + return -EINVAL; + + if (!regexec(&sdt_op_regex1, old_op, ARRAY_SIZE(rm), rm, 0) || + !regexec(&sdt_op_regex2, old_op, ARRAY_SIZE(rm), rm, 0)) { + new_len = 1; /* NULL byte */ + new_len += (int)(rm[1].rm_eo - rm[1].rm_so); + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%.*s", + (int)(rm[1].rm_eo - rm[1].rm_so), old_op + rm[1].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} diff --git a/tools/perf/util/perf-regs-arch/perf_regs_x86.c b/tools/perf/util/perf-regs-arch/perf_regs_x86.c index 708954a9d35d..b6d20522b4e8 100644 --- a/tools/perf/util/perf-regs-arch/perf_regs_x86.c +++ b/tools/perf/util/perf-regs-arch/perf_regs_x86.c @@ -1,7 +1,286 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <string.h> +#include <regex.h> +#include <linux/kernel.h> +#include <linux/zalloc.h> + +#include "../debug.h" +#include "../event.h" +#include "../pmu.h" +#include "../pmus.h" #include "../perf_regs.h" -#include "../../../arch/x86/include/uapi/asm/perf_regs.h" +#include "../../perf-sys.h" +#include "../../arch/x86/include/perf_regs.h" + +struct sdt_name_reg { + const char *sdt_name; + const char *uprobe_name; +}; +#define SDT_NAME_REG(n, m) {.sdt_name = "%" #n, .uprobe_name = "%" #m} +#define SDT_NAME_REG_END {.sdt_name = NULL, .uprobe_name = NULL} + +static const struct sdt_name_reg sdt_reg_tbl[] = { + SDT_NAME_REG(eax, ax), + SDT_NAME_REG(rax, ax), + SDT_NAME_REG(al, ax), + SDT_NAME_REG(ah, ax), + SDT_NAME_REG(ebx, bx), + SDT_NAME_REG(rbx, bx), + SDT_NAME_REG(bl, bx), + SDT_NAME_REG(bh, bx), + SDT_NAME_REG(ecx, cx), + SDT_NAME_REG(rcx, cx), + SDT_NAME_REG(cl, cx), + SDT_NAME_REG(ch, cx), + SDT_NAME_REG(edx, dx), + SDT_NAME_REG(rdx, dx), + SDT_NAME_REG(dl, dx), + SDT_NAME_REG(dh, dx), + SDT_NAME_REG(esi, si), + SDT_NAME_REG(rsi, si), + SDT_NAME_REG(sil, si), + SDT_NAME_REG(edi, di), + SDT_NAME_REG(rdi, di), + SDT_NAME_REG(dil, di), + SDT_NAME_REG(ebp, bp), + SDT_NAME_REG(rbp, bp), + SDT_NAME_REG(bpl, bp), + SDT_NAME_REG(rsp, sp), + SDT_NAME_REG(esp, sp), + SDT_NAME_REG(spl, sp), + + /* rNN registers */ + SDT_NAME_REG(r8b, r8), + SDT_NAME_REG(r8w, r8), + SDT_NAME_REG(r8d, r8), + SDT_NAME_REG(r9b, r9), + SDT_NAME_REG(r9w, r9), + SDT_NAME_REG(r9d, r9), + SDT_NAME_REG(r10b, r10), + SDT_NAME_REG(r10w, r10), + SDT_NAME_REG(r10d, r10), + SDT_NAME_REG(r11b, r11), + SDT_NAME_REG(r11w, r11), + SDT_NAME_REG(r11d, r11), + SDT_NAME_REG(r12b, r12), + SDT_NAME_REG(r12w, r12), + SDT_NAME_REG(r12d, r12), + SDT_NAME_REG(r13b, r13), + SDT_NAME_REG(r13w, r13), + SDT_NAME_REG(r13d, r13), + SDT_NAME_REG(r14b, r14), + SDT_NAME_REG(r14w, r14), + SDT_NAME_REG(r14d, r14), + SDT_NAME_REG(r15b, r15), + SDT_NAME_REG(r15w, r15), + SDT_NAME_REG(r15d, r15), + SDT_NAME_REG_END, +}; + +/* + * Perf only supports OP which is in +/-NUM(REG) form. + * Here plus-minus sign, NUM and parenthesis are optional, + * only REG is mandatory. + * + * SDT events also supports indirect addressing mode with a + * symbol as offset, scaled mode and constants in OP. But + * perf does not support them yet. Below are few examples. + * + * OP with scaled mode: + * (%rax,%rsi,8) + * 10(%ras,%rsi,8) + * + * OP with indirect addressing mode: + * check_action(%rip) + * mp_+52(%rip) + * 44+mp_(%rip) + * + * OP with constant values: + * $0 + * $123 + * $-1 + */ +#define SDT_OP_REGEX "^([+\\-]?)([0-9]*)(\\(?)(%[a-z][a-z0-9]+)(\\)?)$" + +static regex_t sdt_op_regex; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex, SDT_OP_REGEX, REG_EXTENDED); + if (ret < 0) { + pr_debug4("Regex compilation error.\n"); + return ret; + } + + initialized = 1; + return 0; +} + +/* + * Max x86 register name length is 5(ex: %r15d). So, 6th char + * should always contain NULL. This helps to find register name + * length using strlen, instead of maintaining one more variable. + */ +#define SDT_REG_NAME_SIZE 6 + +/* + * The uprobe parser does not support all gas register names; + * so, we have to replace them (ex. for x86_64: %rax -> %ax). + * Note: If register does not require renaming, just copy + * paste as it is, but don't leave it empty. + */ +static void sdt_rename_register(char *sdt_reg, int sdt_len, char *uprobe_reg) +{ + int i = 0; + + for (i = 0; sdt_reg_tbl[i].sdt_name != NULL; i++) { + if (!strncmp(sdt_reg_tbl[i].sdt_name, sdt_reg, sdt_len)) { + strcpy(uprobe_reg, sdt_reg_tbl[i].uprobe_name); + return; + } + } + + strncpy(uprobe_reg, sdt_reg, sdt_len); +} + +int __perf_sdt_arg_parse_op_x86(char *old_op, char **new_op) +{ + char new_reg[SDT_REG_NAME_SIZE] = {0}; + int new_len = 0, ret; + /* + * rm[0]: +/-NUM(REG) + * rm[1]: +/- + * rm[2]: NUM + * rm[3]: ( + * rm[4]: REG + * rm[5]: ) + */ + regmatch_t rm[6]; + /* + * Max prefix length is 2 as it may contains sign(+/-) + * and displacement 0 (Both sign and displacement 0 are + * optional so it may be empty). Use one more character + * to hold last NULL so that strlen can be used to find + * prefix length, instead of maintaining one more variable. + */ + char prefix[3] = {0}; + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + /* + * If unsupported OR does not match with regex OR + * register name too long, skip it. + */ + if (strchr(old_op, ',') || strchr(old_op, '$') || + regexec(&sdt_op_regex, old_op, 6, rm, 0) || + rm[4].rm_eo - rm[4].rm_so > SDT_REG_NAME_SIZE) { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + /* + * Prepare prefix. + * If SDT OP has parenthesis but does not provide + * displacement, add 0 for displacement. + * SDT Uprobe Prefix + * ----------------------------- + * +24(%rdi) +24(%di) + + * 24(%rdi) +24(%di) + + * %rdi %di + * (%rdi) +0(%di) +0 + * -80(%rbx) -80(%bx) - + */ + if (rm[3].rm_so != rm[3].rm_eo) { + if (rm[1].rm_so != rm[1].rm_eo) + prefix[0] = *(old_op + rm[1].rm_so); + else if (rm[2].rm_so != rm[2].rm_eo) + prefix[0] = '+'; + else + scnprintf(prefix, sizeof(prefix), "+0"); + } + + /* Rename register */ + sdt_rename_register(old_op + rm[4].rm_so, rm[4].rm_eo - rm[4].rm_so, + new_reg); + + /* Prepare final OP which should be valid for uprobe_events */ + new_len = strlen(prefix) + + (rm[2].rm_eo - rm[2].rm_so) + + (rm[3].rm_eo - rm[3].rm_so) + + strlen(new_reg) + + (rm[5].rm_eo - rm[5].rm_so) + + 1; /* NULL */ + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%.*s%.*s%.*s%.*s%.*s", + strlen(prefix), prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[3].rm_eo - rm[3].rm_so), old_op + rm[3].rm_so, + strlen(new_reg), new_reg, + (int)(rm[5].rm_eo - rm[5].rm_so), old_op + rm[5].rm_so); + + return SDT_ARG_VALID; +} + +uint64_t __perf_reg_mask_x86(bool intr) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_REGS_INTR, + .sample_regs_intr = PERF_REG_EXTENDED_MASK, + .precise_ip = 1, + .disabled = 1, + .exclude_kernel = 1, + }; + int fd; + + if (!intr) + return PERF_REGS_MASK; + + /* + * In an unnamed union, init it here to build on older gcc versions + */ + attr.sample_period = 1; + + if (perf_pmus__num_core_pmus() > 1) { + struct perf_pmu *pmu = NULL; + __u64 type = PERF_TYPE_RAW; + + /* + * The same register set is supported among different hybrid PMUs. + * Only check the first available one. + */ + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + type = pmu->type; + break; + } + attr.config |= type << PERF_PMU_TYPE_SHIFT; + } + + event_attr_init(&attr); + fd = sys_perf_event_open(&attr, /*pid=*/0, /*cpu=*/-1, + /*group_fd=*/-1, /*flags=*/0); + if (fd != -1) { + close(fd); + return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK); + } + + return PERF_REGS_MASK; +} const char *__perf_reg_name_x86(int id) { diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 1de3b69cdf4a..6ecf38314f01 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -59,10 +59,10 @@ out_delete: static bool perf_probe_api(setup_probe_fn_t fn) { - const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL}; + struct perf_pmu *pmu; struct perf_cpu_map *cpus; struct perf_cpu cpu; - int ret, i = 0; + int ret = 0; cpus = perf_cpu_map__new_online_cpus(); if (!cpus) @@ -70,12 +70,23 @@ static bool perf_probe_api(setup_probe_fn_t fn) cpu = perf_cpu_map__cpu(cpus, 0); perf_cpu_map__put(cpus); - do { - ret = perf_do_probe_api(fn, cpu, try[i++]); - if (!ret) - return true; - } while (ret == -EAGAIN && try[i]); - + ret = perf_do_probe_api(fn, cpu, "software/cpu-clock/u"); + if (!ret) + return true; + + pmu = perf_pmus__scan_core(/*pmu=*/NULL); + if (pmu) { + const char *try[] = {"cycles", "instructions", NULL}; + char buf[256]; + int i = 0; + + while (ret == -EAGAIN && try[i]) { + snprintf(buf, sizeof(buf), "%s/%s/u", pmu->name, try[i++]); + ret = perf_do_probe_api(fn, cpu, buf); + if (!ret) + return true; + } + } return false; } diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index c7f3543b9921..741c3d657a8b 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -79,24 +79,22 @@ static void __p_read_format(char *buf, size_t size, u64 value) #define ENUM_ID_TO_STR_CASE(x) case x: return (#x); static const char *stringify_perf_type_id(struct perf_pmu *pmu, u32 type) { - if (pmu) - return pmu->name; - switch (type) { ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE) ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE) ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT) ENUM_ID_TO_STR_CASE(PERF_TYPE_HW_CACHE) - ENUM_ID_TO_STR_CASE(PERF_TYPE_RAW) ENUM_ID_TO_STR_CASE(PERF_TYPE_BREAKPOINT) + case PERF_TYPE_RAW: + return pmu ? pmu->name : "PERF_TYPE_RAW"; default: - return NULL; + return pmu ? pmu->name : NULL; } } static const char *stringify_perf_hw_id(u64 value) { - switch (value) { + switch (value & PERF_HW_EVENT_MASK) { ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CPU_CYCLES) ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_INSTRUCTIONS) ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_REFERENCES) @@ -169,79 +167,100 @@ static const char *stringify_perf_sw_id(u64 value) } #undef ENUM_ID_TO_STR_CASE -#define PRINT_ID(_s, _f) \ -do { \ - const char *__s = _s; \ - if (__s == NULL) \ - snprintf(buf, size, _f, value); \ - else \ - snprintf(buf, size, _f" (%s)", value, __s); \ -} while (0) -#define print_id_unsigned(_s) PRINT_ID(_s, "%"PRIu64) -#define print_id_hex(_s) PRINT_ID(_s, "%#"PRIx64) +static void print_id_unsigned(char *buf, size_t size, u64 value, const char *s) +{ + if (s == NULL) + snprintf(buf, size, "%"PRIu64, value); + else + snprintf(buf, size, "%"PRIu64" (%s)", value, s); +} + +static void print_id_hex(char *buf, size_t size, u64 value, const char *s) +{ + if (s == NULL) + snprintf(buf, size, "%#"PRIx64, value); + else + snprintf(buf, size, "%#"PRIx64" (%s)", value, s); +} -static void __p_type_id(struct perf_pmu *pmu, char *buf, size_t size, u64 value) +static void __p_type_id(char *buf, size_t size, struct perf_pmu *pmu, u32 type) { - print_id_unsigned(stringify_perf_type_id(pmu, value)); + print_id_unsigned(buf, size, type, stringify_perf_type_id(pmu, type)); } -static void __p_config_hw_id(char *buf, size_t size, u64 value) +static void __p_config_hw_id(char *buf, size_t size, struct perf_pmu *pmu, u64 config) { - print_id_hex(stringify_perf_hw_id(value)); + const char *name = stringify_perf_hw_id(config); + + if (name == NULL) { + if (pmu == NULL) { + snprintf(buf, size, "%#"PRIx64, config); + } else { + snprintf(buf, size, "%#"PRIx64" (%s/config=%#"PRIx64"/)", config, pmu->name, + config); + } + } else { + if (pmu == NULL) + snprintf(buf, size, "%#"PRIx64" (%s)", config, name); + else + snprintf(buf, size, "%#"PRIx64" (%s/%s/)", config, pmu->name, name); + } } -static void __p_config_sw_id(char *buf, size_t size, u64 value) +static void __p_config_sw_id(char *buf, size_t size, u64 id) { - print_id_hex(stringify_perf_sw_id(value)); + print_id_hex(buf, size, id, stringify_perf_sw_id(id)); } -static void __p_config_hw_cache_id(char *buf, size_t size, u64 value) +static void __p_config_hw_cache_id(char *buf, size_t size, struct perf_pmu *pmu, u64 config) { - const char *hw_cache_str = stringify_perf_hw_cache_id(value & 0xff); + const char *hw_cache_str = stringify_perf_hw_cache_id(config & 0xff); const char *hw_cache_op_str = - stringify_perf_hw_cache_op_id((value & 0xff00) >> 8); + stringify_perf_hw_cache_op_id((config & 0xff00) >> 8); const char *hw_cache_op_result_str = - stringify_perf_hw_cache_op_result_id((value & 0xff0000) >> 16); - - if (hw_cache_str == NULL || hw_cache_op_str == NULL || - hw_cache_op_result_str == NULL) { - snprintf(buf, size, "%#"PRIx64, value); + stringify_perf_hw_cache_op_result_id((config & 0xff0000) >> 16); + + if (hw_cache_str == NULL || hw_cache_op_str == NULL || hw_cache_op_result_str == NULL) { + if (pmu == NULL) { + snprintf(buf, size, "%#"PRIx64, config); + } else { + snprintf(buf, size, "%#"PRIx64" (%s/config=%#"PRIx64"/)", config, pmu->name, + config); + } } else { - snprintf(buf, size, "%#"PRIx64" (%s | %s | %s)", value, - hw_cache_op_result_str, hw_cache_op_str, hw_cache_str); + if (pmu == NULL) { + snprintf(buf, size, "%#"PRIx64" (%s | %s | %s)", config, + hw_cache_op_result_str, hw_cache_op_str, hw_cache_str); + } else { + snprintf(buf, size, "%#"PRIx64" (%s/%s | %s | %s/)", config, pmu->name, + hw_cache_op_result_str, hw_cache_op_str, hw_cache_str); + } } } -static void __p_config_tracepoint_id(char *buf, size_t size, u64 value) +static void __p_config_tracepoint_id(char *buf, size_t size, u64 id) { - char *str = tracepoint_id_to_name(value); + char *str = tracepoint_id_to_name(id); - print_id_hex(str); + print_id_hex(buf, size, id, str); free(str); } -static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value) +static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 config) { - const char *name = perf_pmu__name_from_config(pmu, value); - - if (name) { - print_id_hex(name); - return; - } switch (type) { case PERF_TYPE_HARDWARE: - return __p_config_hw_id(buf, size, value); + return __p_config_hw_id(buf, size, pmu, config); case PERF_TYPE_SOFTWARE: - return __p_config_sw_id(buf, size, value); + return __p_config_sw_id(buf, size, config); case PERF_TYPE_HW_CACHE: - return __p_config_hw_cache_id(buf, size, value); + return __p_config_hw_cache_id(buf, size, pmu, config); case PERF_TYPE_TRACEPOINT: - return __p_config_tracepoint_id(buf, size, value); + return __p_config_tracepoint_id(buf, size, config); case PERF_TYPE_RAW: case PERF_TYPE_BREAKPOINT: default: - snprintf(buf, size, "%#"PRIx64, value); - return; + return print_id_hex(buf, size, config, perf_pmu__name_from_config(pmu, config)); } } @@ -253,7 +272,7 @@ static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type #define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) #define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) #define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) -#define p_type_id(val) __p_type_id(pmu, buf, BUF_SIZE, val) +#define p_type_id(val) __p_type_id(buf, BUF_SIZE, pmu, val) #define p_config_id(val) __p_config_id(pmu, buf, BUF_SIZE, attr->type, val) #define PRINT_ATTRn(_n, _f, _p, _a) \ @@ -273,6 +292,13 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, char buf[BUF_SIZE]; int ret = 0; + if (!pmu && (attr->type == PERF_TYPE_HARDWARE || attr->type == PERF_TYPE_HW_CACHE)) { + u32 extended_type = attr->config >> PERF_PMU_TYPE_SHIFT; + + if (extended_type) + pmu = perf_pmus__find_by_type(extended_type); + } + PRINT_ATTRn("type", type, p_type_id, true); PRINT_ATTRf(size, p_unsigned); PRINT_ATTRn("config", config, p_config_id, true); @@ -317,6 +343,8 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(inherit_thread, p_unsigned); PRINT_ATTRf(remove_on_exec, p_unsigned); PRINT_ATTRf(sigtrap, p_unsigned); + PRINT_ATTRf(defer_callchain, p_unsigned); + PRINT_ATTRf(defer_output, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned, false); PRINT_ATTRf(bp_type, p_unsigned); diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 44b90bbf2d07..f52b0e1f7fc7 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -1,59 +1,168 @@ // SPDX-License-Identifier: GPL-2.0 +#include <elf.h> #include <errno.h> #include <string.h> +#include "dwarf-regs.h" #include "perf_regs.h" #include "util/sample.h" #include "debug.h" -int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, - char **new_op __maybe_unused) +int perf_sdt_arg_parse_op(uint16_t e_machine, char *old_op, char **new_op) { - return SDT_ARG_SKIP; -} + int ret = SDT_ARG_SKIP; + + switch (e_machine) { + case EM_AARCH64: + ret = __perf_sdt_arg_parse_op_arm64(old_op, new_op); + break; + case EM_PPC: + case EM_PPC64: + ret = __perf_sdt_arg_parse_op_powerpc(old_op, new_op); + break; + case EM_386: + case EM_X86_64: + ret = __perf_sdt_arg_parse_op_x86(old_op, new_op); + break; + case EM_S390: + ret = __perf_sdt_arg_parse_op_s390(old_op, new_op); + break; + default: + pr_debug("Unknown ELF machine %d, standard arguments parse will be skipped.\n", + e_machine); + break; + } -uint64_t __weak arch__intr_reg_mask(void) -{ - return 0; + return ret; } -uint64_t __weak arch__user_reg_mask(void) +uint64_t perf_intr_reg_mask(uint16_t e_machine) { - return 0; -} + uint64_t mask = 0; + + switch (e_machine) { + case EM_ARM: + mask = __perf_reg_mask_arm(/*intr=*/true); + break; + case EM_AARCH64: + mask = __perf_reg_mask_arm64(/*intr=*/true); + break; + case EM_CSKY: + mask = __perf_reg_mask_csky(/*intr=*/true); + break; + case EM_LOONGARCH: + mask = __perf_reg_mask_loongarch(/*intr=*/true); + break; + case EM_MIPS: + mask = __perf_reg_mask_mips(/*intr=*/true); + break; + case EM_PPC: + case EM_PPC64: + mask = __perf_reg_mask_powerpc(/*intr=*/true); + break; + case EM_RISCV: + mask = __perf_reg_mask_riscv(/*intr=*/true); + break; + case EM_S390: + mask = __perf_reg_mask_s390(/*intr=*/true); + break; + case EM_386: + case EM_X86_64: + mask = __perf_reg_mask_x86(/*intr=*/true); + break; + default: + pr_debug("Unknown ELF machine %d, interrupt sampling register mask will be empty.\n", + e_machine); + break; + } -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG_END -}; + return mask; +} -const struct sample_reg * __weak arch__sample_reg_masks(void) +uint64_t perf_user_reg_mask(uint16_t e_machine) { - return sample_reg_masks; + uint64_t mask = 0; + + switch (e_machine) { + case EM_ARM: + mask = __perf_reg_mask_arm(/*intr=*/false); + break; + case EM_AARCH64: + mask = __perf_reg_mask_arm64(/*intr=*/false); + break; + case EM_CSKY: + mask = __perf_reg_mask_csky(/*intr=*/false); + break; + case EM_LOONGARCH: + mask = __perf_reg_mask_loongarch(/*intr=*/false); + break; + case EM_MIPS: + mask = __perf_reg_mask_mips(/*intr=*/false); + break; + case EM_PPC: + case EM_PPC64: + mask = __perf_reg_mask_powerpc(/*intr=*/false); + break; + case EM_RISCV: + mask = __perf_reg_mask_riscv(/*intr=*/false); + break; + case EM_S390: + mask = __perf_reg_mask_s390(/*intr=*/false); + break; + case EM_386: + case EM_X86_64: + mask = __perf_reg_mask_x86(/*intr=*/false); + break; + default: + pr_debug("Unknown ELF machine %d, user sampling register mask will be empty.\n", + e_machine); + break; + } + + return mask; } -const char *perf_reg_name(int id, const char *arch) +const char *perf_reg_name(int id, uint16_t e_machine, uint32_t e_flags) { const char *reg_name = NULL; - if (!strcmp(arch, "csky")) - reg_name = __perf_reg_name_csky(id); - else if (!strcmp(arch, "loongarch")) + switch (e_machine) { + case EM_ARM: + reg_name = __perf_reg_name_arm(id); + break; + case EM_AARCH64: + reg_name = __perf_reg_name_arm64(id); + break; + case EM_CSKY: + reg_name = __perf_reg_name_csky(id, e_flags); + break; + case EM_LOONGARCH: reg_name = __perf_reg_name_loongarch(id); - else if (!strcmp(arch, "mips")) + break; + case EM_MIPS: reg_name = __perf_reg_name_mips(id); - else if (!strcmp(arch, "powerpc")) + break; + case EM_PPC: + case EM_PPC64: reg_name = __perf_reg_name_powerpc(id); - else if (!strcmp(arch, "riscv")) + break; + case EM_RISCV: reg_name = __perf_reg_name_riscv(id); - else if (!strcmp(arch, "s390")) + break; + case EM_S390: reg_name = __perf_reg_name_s390(id); - else if (!strcmp(arch, "x86")) + break; + case EM_386: + case EM_X86_64: reg_name = __perf_reg_name_x86(id); - else if (!strcmp(arch, "arm")) - reg_name = __perf_reg_name_arm(id); - else if (!strcmp(arch, "arm64")) - reg_name = __perf_reg_name_arm64(id); + break; + default: + break; + } + if (reg_name) + return reg_name; - return reg_name ?: "unknown"; + pr_debug("Failed to find register %d for ELF machine type %u\n", id, e_machine); + return "unknown"; } int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) @@ -83,52 +192,60 @@ out: return 0; } -uint64_t perf_arch_reg_ip(const char *arch) +uint64_t perf_arch_reg_ip(uint16_t e_machine) { - if (!strcmp(arch, "arm")) + switch (e_machine) { + case EM_ARM: return __perf_reg_ip_arm(); - else if (!strcmp(arch, "arm64")) + case EM_AARCH64: return __perf_reg_ip_arm64(); - else if (!strcmp(arch, "csky")) + case EM_CSKY: return __perf_reg_ip_csky(); - else if (!strcmp(arch, "loongarch")) + case EM_LOONGARCH: return __perf_reg_ip_loongarch(); - else if (!strcmp(arch, "mips")) + case EM_MIPS: return __perf_reg_ip_mips(); - else if (!strcmp(arch, "powerpc")) + case EM_PPC: + case EM_PPC64: return __perf_reg_ip_powerpc(); - else if (!strcmp(arch, "riscv")) + case EM_RISCV: return __perf_reg_ip_riscv(); - else if (!strcmp(arch, "s390")) + case EM_S390: return __perf_reg_ip_s390(); - else if (!strcmp(arch, "x86")) + case EM_386: + case EM_X86_64: return __perf_reg_ip_x86(); - - pr_err("Fail to find IP register for arch %s, returns 0\n", arch); - return 0; + default: + pr_err("Failed to find IP register for ELF machine type %u\n", e_machine); + return 0; + } } -uint64_t perf_arch_reg_sp(const char *arch) +uint64_t perf_arch_reg_sp(uint16_t e_machine) { - if (!strcmp(arch, "arm")) + switch (e_machine) { + case EM_ARM: return __perf_reg_sp_arm(); - else if (!strcmp(arch, "arm64")) + case EM_AARCH64: return __perf_reg_sp_arm64(); - else if (!strcmp(arch, "csky")) + case EM_CSKY: return __perf_reg_sp_csky(); - else if (!strcmp(arch, "loongarch")) + case EM_LOONGARCH: return __perf_reg_sp_loongarch(); - else if (!strcmp(arch, "mips")) + case EM_MIPS: return __perf_reg_sp_mips(); - else if (!strcmp(arch, "powerpc")) + case EM_PPC: + case EM_PPC64: return __perf_reg_sp_powerpc(); - else if (!strcmp(arch, "riscv")) + case EM_RISCV: return __perf_reg_sp_riscv(); - else if (!strcmp(arch, "s390")) + case EM_S390: return __perf_reg_sp_s390(); - else if (!strcmp(arch, "x86")) + case EM_386: + case EM_X86_64: return __perf_reg_sp_x86(); - - pr_err("Fail to find SP register for arch %s, returns 0\n", arch); - return 0; + default: + pr_err("Failed to find SP register for ELF machine type %u\n", e_machine); + return 0; + } } diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index f2d0736d65cc..573f0d1dfe04 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -7,62 +7,72 @@ struct regs_dump; -struct sample_reg { - const char *name; - uint64_t mask; -}; - -#define SMPL_REG_MASK(b) (1ULL << (b)) -#define SMPL_REG(n, b) { .name = #n, .mask = SMPL_REG_MASK(b) } -#define SMPL_REG2_MASK(b) (3ULL << (b)) -#define SMPL_REG2(n, b) { .name = #n, .mask = SMPL_REG2_MASK(b) } -#define SMPL_REG_END { .name = NULL } - enum { SDT_ARG_VALID = 0, SDT_ARG_SKIP, }; -int arch_sdt_arg_parse_op(char *old_op, char **new_op); -uint64_t arch__intr_reg_mask(void); -uint64_t arch__user_reg_mask(void); -const struct sample_reg *arch__sample_reg_masks(void); +int perf_sdt_arg_parse_op(uint16_t e_machine, char *old_op, char **new_op); +uint64_t perf_intr_reg_mask(uint16_t e_machine); +uint64_t perf_user_reg_mask(uint16_t e_machine); -const char *perf_reg_name(int id, const char *arch); +const char *perf_reg_name(int id, uint16_t e_machine, uint32_t e_flags); int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); -uint64_t perf_arch_reg_ip(const char *arch); -uint64_t perf_arch_reg_sp(const char *arch); +uint64_t perf_arch_reg_ip(uint16_t e_machine); +uint64_t perf_arch_reg_sp(uint16_t e_machine); + +int __perf_sdt_arg_parse_op_arm64(char *old_op, char **new_op); +uint64_t __perf_reg_mask_arm64(bool intr); const char *__perf_reg_name_arm64(int id); uint64_t __perf_reg_ip_arm64(void); uint64_t __perf_reg_sp_arm64(void); + +uint64_t __perf_reg_mask_arm(bool intr); const char *__perf_reg_name_arm(int id); uint64_t __perf_reg_ip_arm(void); uint64_t __perf_reg_sp_arm(void); -const char *__perf_reg_name_csky(int id); + +uint64_t __perf_reg_mask_csky(bool intr); +const char *__perf_reg_name_csky(int id, uint32_t e_flags); uint64_t __perf_reg_ip_csky(void); uint64_t __perf_reg_sp_csky(void); + +uint64_t __perf_reg_mask_loongarch(bool intr); const char *__perf_reg_name_loongarch(int id); uint64_t __perf_reg_ip_loongarch(void); uint64_t __perf_reg_sp_loongarch(void); + +uint64_t __perf_reg_mask_mips(bool intr); const char *__perf_reg_name_mips(int id); uint64_t __perf_reg_ip_mips(void); uint64_t __perf_reg_sp_mips(void); + +int __perf_sdt_arg_parse_op_powerpc(char *old_op, char **new_op); +uint64_t __perf_reg_mask_powerpc(bool intr); const char *__perf_reg_name_powerpc(int id); uint64_t __perf_reg_ip_powerpc(void); uint64_t __perf_reg_sp_powerpc(void); + +uint64_t __perf_reg_mask_riscv(bool intr); const char *__perf_reg_name_riscv(int id); uint64_t __perf_reg_ip_riscv(void); uint64_t __perf_reg_sp_riscv(void); + +uint64_t __perf_reg_mask_s390(bool intr); const char *__perf_reg_name_s390(int id); uint64_t __perf_reg_ip_s390(void); uint64_t __perf_reg_sp_s390(void); +int __perf_sdt_arg_parse_op_s390(char *old_op, char **new_op); + +int __perf_sdt_arg_parse_op_x86(char *old_op, char **new_op); +uint64_t __perf_reg_mask_x86(bool intr); const char *__perf_reg_name_x86(int id); uint64_t __perf_reg_ip_x86(void); uint64_t __perf_reg_sp_x86(void); -static inline uint64_t DWARF_MINIMAL_REGS(const char *arch) +static inline uint64_t DWARF_MINIMAL_REGS(uint16_t e_machine) { - return (1ULL << perf_arch_reg_ip(arch)) | (1ULL << perf_arch_reg_sp(arch)); + return (1ULL << perf_arch_reg_ip(e_machine)) | (1ULL << perf_arch_reg_sp(e_machine)); } #endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index 0dacc133ed39..d9043f4afbe7 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -15,6 +15,7 @@ #include "util/strbuf.h" #include "util/thread_map.h" +#include <errno.h> #include <string.h> #include <linux/kernel.h> #include <perfmon/pfmlib_perf_event.h> @@ -47,10 +48,6 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, p_orig = p = strdup(str); if (!p) return -1; - /* - * force loading of the PMU list - */ - perf_pmus__scan(NULL); for (q = p; strsep(&p, ",{}"); q = p) { sep = p ? str + (p - p_orig - 1) : ""; @@ -234,6 +231,7 @@ print_libpfm_event(const struct print_callbacks *print_cb, void *print_state, if (is_libpfm_event_supported(name, cpus, threads)) { print_cb->print_event(print_state, topic, pinfo->name, + /*pmu_type=*/PERF_TYPE_RAW, name, info->equiv, /*scale_unit=*/NULL, /*deprecated=*/NULL, "PFM event", @@ -269,6 +267,7 @@ print_libpfm_event(const struct print_callbacks *print_cb, void *print_state, print_cb->print_event(print_state, topic, pinfo->name, + /*pmu_type=*/PERF_TYPE_RAW, name, /*alias=*/NULL, /*scale_unit=*/NULL, /*deprecated=*/NULL, "PFM event", diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 6206c8fe2bf9..23337d2fa281 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -13,19 +13,23 @@ #include <dirent.h> #include <api/fs/fs.h> #include <api/io.h> +#include <api/io_dir.h> #include <locale.h> #include <fnmatch.h> #include <math.h> #include "debug.h" #include "evsel.h" #include "pmu.h" +#include "drm_pmu.h" #include "hwmon_pmu.h" #include "pmus.h" #include "tool_pmu.h" +#include "tp_pmu.h" #include <util/pmu-bison.h> #include <util/pmu-flex.h> #include "parse-events.h" #include "print-events.h" +#include "hashmap.h" #include "header.h" #include "string2.h" #include "strbuf.h" @@ -36,12 +40,12 @@ #define UNIT_MAX_LEN 31 /* max length for event unit name */ enum event_source { - /* An event loaded from /sys/devices/<pmu>/events. */ + /* An event loaded from /sys/bus/event_source/devices/<pmu>/events. */ EVENT_SRC_SYSFS, /* An event loaded from a CPUID matched json file. */ EVENT_SRC_CPU_JSON, /* - * An event loaded from a /sys/devices/<pmu>/identifier matched json + * An event loaded from a /sys/bus/event_source/devices/<pmu>/identifier matched json * file. */ EVENT_SRC_SYS_JSON, @@ -63,10 +67,13 @@ struct perf_pmu_alias { * json events. */ char *topic; - /** @terms: Owned list of the original parsed parameters. */ - struct parse_events_terms terms; - /** @list: List element of struct perf_pmu aliases. */ - struct list_head list; + /** @terms: Owned copy of the event terms. */ + char *terms; + /** + * @legacy_terms: If the event aliases a legacy event, holds a copy + * ofthe legacy event string. + */ + char *legacy_terms; /** * @pmu_name: The name copied from the json struct pmu_event. This can * differ from the PMU name as it won't have suffixes. @@ -76,6 +83,12 @@ struct perf_pmu_alias { char unit[UNIT_MAX_LEN+1]; /** @scale: Value to scale read counter values by. */ double scale; + /** @retirement_latency_mean: Value to be given for unsampled retirement latency mean. */ + double retirement_latency_mean; + /** @retirement_latency_min: Value to be given for unsampled retirement latency min. */ + double retirement_latency_min; + /** @retirement_latency_max: Value to be given for unsampled retirement latency max. */ + double retirement_latency_max; /** * @per_pkg: Does the file * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or @@ -93,37 +106,18 @@ struct perf_pmu_alias { * default. */ bool deprecated; + /** + * @legacy_deprecated_checked: Legacy events may not be supported by the + * PMU need to be checked. If they aren't supported they are marked + * deprecated. + */ + bool legacy_deprecated_checked; /** @from_sysfs: Was the alias from sysfs or a json event? */ bool from_sysfs; /** @info_loaded: Have the scale, unit and other values been read from disk? */ bool info_loaded; }; -/** - * struct perf_pmu_format - Values from a format file read from - * <sysfs>/devices/cpu/format/ held in struct perf_pmu. - * - * For example, the contents of <sysfs>/devices/cpu/format/event may be - * "config:0-7" and will be represented here as name="event", - * value=PERF_PMU_FORMAT_VALUE_CONFIG and bits 0 to 7 will be set. - */ -struct perf_pmu_format { - /** @list: Element on list within struct perf_pmu. */ - struct list_head list; - /** @bits: Which config bits are set by this format value. */ - DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); - /** @name: The modifier/file name. */ - char *name; - /** - * @value : Which config value the format relates to. Supported values - * are from PERF_PMU_FORMAT_VALUE_CONFIG to - * PERF_PMU_FORMAT_VALUE_CONFIG_END. - */ - u16 value; - /** @loaded: Has the contents been loaded/parsed. */ - bool loaded; -}; - static int pmu_aliases_parse(struct perf_pmu *pmu); static struct perf_pmu_format *perf_pmu__new_format(struct list_head *list, char *name) @@ -195,19 +189,17 @@ static void perf_pmu_format__load(const struct perf_pmu *pmu, struct perf_pmu_fo */ static int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load) { - struct dirent *evt_ent; - DIR *format_dir; + struct io_dirent64 *evt_ent; + struct io_dir format_dir; int ret = 0; - format_dir = fdopendir(dirfd); - if (!format_dir) - return -EINVAL; + io_dir__init(&format_dir, dirfd); - while ((evt_ent = readdir(format_dir)) != NULL) { + while ((evt_ent = io_dir__readdir(&format_dir)) != NULL) { struct perf_pmu_format *format; char *name = evt_ent->d_name; - if (!strcmp(name, ".") || !strcmp(name, "..")) + if (io_dir__is_dir(&format_dir, evt_ent)) continue; format = perf_pmu__new_format(&pmu->format, name); @@ -234,7 +226,7 @@ static int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_lo } } - closedir(format_dir); + close(format_dir.dirfd); return ret; } @@ -258,7 +250,7 @@ static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name, bool ea return 0; } -int perf_pmu__convert_scale(const char *scale, char **end, double *sval) +static int parse_double(const char *scale, char **end, double *sval) { char *lc; int ret = 0; @@ -295,6 +287,11 @@ out: return ret; } +int perf_pmu__convert_scale(const char *scale, char **end, double *sval) +{ + return parse_double(scale, end, sval); +} + static int perf_pmu__parse_scale(struct perf_pmu *pmu, struct perf_pmu_alias *alias) { struct stat st; @@ -408,25 +405,34 @@ static void perf_pmu__parse_snapshot(struct perf_pmu *pmu, struct perf_pmu_alias } /* Delete an alias entry. */ -static void perf_pmu_free_alias(struct perf_pmu_alias *newalias) +static void perf_pmu_free_alias(struct perf_pmu_alias *alias) { - zfree(&newalias->name); - zfree(&newalias->desc); - zfree(&newalias->long_desc); - zfree(&newalias->topic); - zfree(&newalias->pmu_name); - parse_events_terms__exit(&newalias->terms); - free(newalias); + if (!alias) + return; + + zfree(&alias->name); + zfree(&alias->desc); + zfree(&alias->long_desc); + zfree(&alias->topic); + zfree(&alias->pmu_name); + zfree(&alias->terms); + zfree(&alias->legacy_terms); + free(alias); } static void perf_pmu__del_aliases(struct perf_pmu *pmu) { - struct perf_pmu_alias *alias, *tmp; + struct hashmap_entry *entry; + size_t bkt; - list_for_each_entry_safe(alias, tmp, &pmu->aliases, list) { - list_del(&alias->list); - perf_pmu_free_alias(alias); - } + if (!pmu->aliases) + return; + + hashmap__for_each_entry(pmu->aliases, entry, bkt) + perf_pmu_free_alias(entry->pvalue); + + hashmap__free(pmu->aliases); + pmu->aliases = NULL; } static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, @@ -434,35 +440,37 @@ static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, bool load) { struct perf_pmu_alias *alias; + bool has_sysfs_event; + char event_file_name[NAME_MAX + 8]; - if (load && !pmu->sysfs_aliases_loaded) { - bool has_sysfs_event; - char event_file_name[FILENAME_MAX + 8]; + if (hashmap__find(pmu->aliases, name, &alias)) + return alias; - /* - * Test if alias/event 'name' exists in the PMU's sysfs/events - * directory. If not skip parsing the sysfs aliases. Sysfs event - * name must be all lower or all upper case. - */ - scnprintf(event_file_name, sizeof(event_file_name), "events/%s", name); - for (size_t i = 7, n = 7 + strlen(name); i < n; i++) - event_file_name[i] = tolower(event_file_name[i]); + if (!load || pmu->sysfs_aliases_loaded) + return NULL; - has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name); - if (!has_sysfs_event) { - for (size_t i = 7, n = 7 + strlen(name); i < n; i++) - event_file_name[i] = toupper(event_file_name[i]); + /* + * Test if alias/event 'name' exists in the PMU's sysfs/events + * directory. If not skip parsing the sysfs aliases. Sysfs event + * name must be all lower or all upper case. + */ + scnprintf(event_file_name, sizeof(event_file_name), "events/%s", name); + for (size_t i = 7, n = 7 + strlen(name); i < n; i++) + event_file_name[i] = tolower(event_file_name[i]); - has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name); - } - if (has_sysfs_event) - pmu_aliases_parse(pmu); + has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name); + if (!has_sysfs_event) { + for (size_t i = 7, n = 7 + strlen(name); i < n; i++) + event_file_name[i] = toupper(event_file_name[i]); + has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name); } - list_for_each_entry(alias, &pmu->aliases, list) { - if (!strcasecmp(alias->name, name)) + if (has_sysfs_event) { + pmu_aliases_parse(pmu); + if (hashmap__find(pmu->aliases, name, &alias)) return alias; } + return NULL; } @@ -501,6 +509,7 @@ static void read_alias_info(struct perf_pmu *pmu, struct perf_pmu_alias *alias) struct update_alias_data { struct perf_pmu *pmu; struct perf_pmu_alias *alias; + bool legacy; }; static int update_alias(const struct pmu_event *pe, @@ -516,8 +525,13 @@ static int update_alias(const struct pmu_event *pe, assign_str(pe->name, "topic", &data->alias->topic, pe->topic); data->alias->per_pkg = pe->perpkg; if (pe->event) { - parse_events_terms__exit(&data->alias->terms); - ret = parse_events_terms(&data->alias->terms, pe->event, /*input=*/NULL); + if (data->legacy) { + zfree(&data->alias->legacy_terms); + data->alias->legacy_terms = strdup(pe->event); + } else { + zfree(&data->alias->terms); + data->alias->terms = strdup(pe->event); + } } if (!ret && pe->unit) { char *unit; @@ -526,15 +540,27 @@ static int update_alias(const struct pmu_event *pe, if (!ret) snprintf(data->alias->unit, sizeof(data->alias->unit), "%s", unit); } + if (!ret && pe->retirement_latency_mean) { + ret = parse_double(pe->retirement_latency_mean, NULL, + &data->alias->retirement_latency_mean); + } + if (!ret && pe->retirement_latency_min) { + ret = parse_double(pe->retirement_latency_min, NULL, + &data->alias->retirement_latency_min); + } + if (!ret && pe->retirement_latency_max) { + ret = parse_double(pe->retirement_latency_max, NULL, + &data->alias->retirement_latency_max); + } return ret; } static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, - const char *desc, const char *val, FILE *val_fd, + const char *desc, const char *val, int val_fd, const struct pmu_event *pe, enum event_source src) { - struct perf_pmu_alias *alias; - int ret; + struct perf_pmu_alias *alias, *old_alias; + int ret = 0; const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL; bool deprecated = false, perpkg = false; @@ -557,24 +583,49 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, if (!alias) return -ENOMEM; - parse_events_terms__init(&alias->terms); alias->scale = 1.0; alias->unit[0] = '\0'; alias->per_pkg = perpkg; alias->snapshot = false; alias->deprecated = deprecated; + alias->retirement_latency_mean = 0.0; + alias->retirement_latency_min = 0.0; + alias->retirement_latency_max = 0.0; - ret = parse_events_terms(&alias->terms, val, val_fd); - if (ret) { - pr_err("Cannot parse alias %s: %d\n", val, ret); - free(alias); - return ret; + if (!ret && pe && pe->retirement_latency_mean) { + ret = parse_double(pe->retirement_latency_mean, NULL, + &alias->retirement_latency_mean); + } + if (!ret && pe && pe->retirement_latency_min) { + ret = parse_double(pe->retirement_latency_min, NULL, + &alias->retirement_latency_min); + } + if (!ret && pe && pe->retirement_latency_max) { + ret = parse_double(pe->retirement_latency_max, NULL, + &alias->retirement_latency_max); } + if (ret) + return ret; + if (val_fd < 0) { + alias->terms = strdup(val); + } else { + char buf[256]; + struct io io; + size_t line_len; + + io__init(&io, val_fd, buf, sizeof(buf)); + ret = io__getline(&io, &alias->terms, &line_len) < 0 ? -errno : 0; + if (ret) { + pr_err("Failed to read alias %s\n", name); + return ret; + } + if (line_len >= 1 && alias->terms[line_len - 1] == '\n') + alias->terms[line_len - 1] = '\0'; + } alias->name = strdup(name); alias->desc = desc ? strdup(desc) : NULL; - alias->long_desc = long_desc ? strdup(long_desc) : - desc ? strdup(desc) : NULL; + alias->long_desc = long_desc ? strdup(long_desc) : NULL; alias->topic = topic ? strdup(topic) : NULL; alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL; if (unit) { @@ -588,15 +639,29 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, default: case EVENT_SRC_SYSFS: alias->from_sysfs = true; - if (pmu->events_table) { + if (pmu->events_table || pmu->is_core) { /* Update an event from sysfs with json data. */ struct update_alias_data data = { .pmu = pmu, .alias = alias, + .legacy = false, }; - if (pmu_events_table__find_event(pmu->events_table, pmu, name, - update_alias, &data) == 0) - pmu->cpu_json_aliases++; + if ((pmu_events_table__find_event(pmu->events_table, pmu, name, + update_alias, &data) == 0)) { + /* + * Override sysfs encodings with json encodings + * specific to the cpuid. + */ + pmu->cpu_common_json_aliases++; + } + if (pmu->is_core) { + /* Add in legacy encodings. */ + data.legacy = true; + if (pmu_events_table__find_event( + perf_pmu__default_core_events_table(), + pmu, name, update_alias, &data) == 0) + pmu->cpu_common_json_aliases++; + } } pmu->sysfs_aliases++; break; @@ -608,7 +673,8 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, break; } - list_add_tail(&alias->list, &pmu->aliases); + hashmap__set(pmu->aliases, alias->name, alias, /*old_key=*/ NULL, &old_alias); + perf_pmu_free_alias(old_alias); return 0; } @@ -635,17 +701,14 @@ static inline bool pmu_alias_info_file(const char *name) */ static int __pmu_aliases_parse(struct perf_pmu *pmu, int events_dir_fd) { - struct dirent *evt_ent; - DIR *event_dir; + struct io_dirent64 *evt_ent; + struct io_dir event_dir; - event_dir = fdopendir(events_dir_fd); - if (!event_dir) - return -EINVAL; + io_dir__init(&event_dir, events_dir_fd); - while ((evt_ent = readdir(event_dir))) { + while ((evt_ent = io_dir__readdir(&event_dir))) { char *name = evt_ent->d_name; int fd; - FILE *file; if (!strcmp(name, ".") || !strcmp(name, "..")) continue; @@ -661,20 +724,14 @@ static int __pmu_aliases_parse(struct perf_pmu *pmu, int events_dir_fd) pr_debug("Cannot open %s\n", name); continue; } - file = fdopen(fd, "r"); - if (!file) { - close(fd); - continue; - } if (perf_pmu__new_alias(pmu, name, /*desc=*/ NULL, - /*val=*/ NULL, file, /*pe=*/ NULL, + /*val=*/ NULL, fd, /*pe=*/ NULL, EVENT_SRC_SYSFS) < 0) pr_debug("Cannot set up %s\n", name); - fclose(file); + close(fd); } - closedir(event_dir); pmu->sysfs_aliases_loaded = true; return 0; } @@ -705,7 +762,7 @@ static int pmu_aliases_parse(struct perf_pmu *pmu) static int pmu_aliases_parse_eager(struct perf_pmu *pmu, int sysfs_fd) { - char path[FILENAME_MAX + 7]; + char path[NAME_MAX + 8]; int ret, events_dir_fd; scnprintf(path, sizeof(path), "%s/events", pmu->name); @@ -719,29 +776,29 @@ static int pmu_aliases_parse_eager(struct perf_pmu *pmu, int sysfs_fd) return ret; } -static int pmu_alias_terms(struct perf_pmu_alias *alias, int err_loc, struct list_head *terms) +static int pmu_alias_terms(struct perf_pmu_alias *alias, struct list_head *terms) { - struct parse_events_term *term, *cloned; - struct parse_events_terms clone_terms; - - parse_events_terms__init(&clone_terms); - list_for_each_entry(term, &alias->terms.terms, list) { - int ret = parse_events_term__clone(&cloned, term); + struct parse_events_terms alias_terms; + struct parse_events_term *term; + int ret; - if (ret) { - parse_events_terms__exit(&clone_terms); - return ret; - } + parse_events_terms__init(&alias_terms); + ret = parse_events_terms(&alias_terms, alias->terms); + if (ret) { + pr_err("Cannot parse '%s' terms '%s': %d\n", + alias->name, alias->terms, ret); + parse_events_terms__exit(&alias_terms); + return ret; + } + list_for_each_entry(term, &alias_terms.terms, list) { /* * Weak terms don't override command line options, * which we don't want for implicit terms in aliases. */ - cloned->weak = true; - cloned->err_term = cloned->err_val = err_loc; - list_add_tail(&cloned->list, &clone_terms.terms); + term->weak = true; } - list_splice_init(&clone_terms.terms, terms); - parse_events_terms__exit(&clone_terms); + list_splice_init(&alias_terms.terms, terms); + parse_events_terms__exit(&alias_terms); return 0; } @@ -783,7 +840,7 @@ static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *pmu_name, bool is } /* Nothing found, for core PMUs assume this means all CPUs. */ - return is_core ? perf_cpu_map__get(cpu_map__online()) : NULL; + return is_core ? cpu_map__online() : NULL; } static bool pmu_is_uncore(int dirfd, const char *name) @@ -847,31 +904,35 @@ static size_t pmu_deduped_name_len(const struct perf_pmu *pmu, const char *name, } /** - * perf_pmu__match_ignoring_suffix - Does the pmu_name match tok ignoring any - * trailing suffix? The Suffix must be in form - * tok_{digits}, or tok{digits}. + * perf_pmu__match_wildcard - Does the pmu_name start with tok and is then only + * followed by nothing or a suffix? tok may contain + * part of a suffix. * @pmu_name: The pmu_name with possible suffix. - * @tok: The possible match to pmu_name without suffix. + * @tok: The wildcard argument to match. */ -static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *tok) +static bool perf_pmu__match_wildcard(const char *pmu_name, const char *tok) { const char *p, *suffix; bool has_hex = false; + bool has_underscore = false; + size_t tok_len = strlen(tok); - if (strncmp(pmu_name, tok, strlen(tok))) + /* Check start of pmu_name for equality. */ + if (strncmp(pmu_name, tok, tok_len)) return false; - suffix = p = pmu_name + strlen(tok); + suffix = p = pmu_name + tok_len; if (*p == 0) return true; - if (*p == '_') { - ++p; - ++suffix; - } - - /* Ensure we end in a number */ + /* Ensure we end in a number or a mix of number and "_". */ while (1) { + if (!has_underscore && (*p == '_')) { + has_underscore = true; + ++p; + ++suffix; + } + if (!isxdigit(*p)) return false; if (!has_hex) @@ -887,60 +948,84 @@ static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *to } /** - * pmu_uncore_alias_match - does name match the PMU name? - * @pmu_name: the json struct pmu_event name. This may lack a suffix (which + * perf_pmu__match_ignoring_suffix_uncore - Does the pmu_name match tok ignoring + * any trailing suffix on pmu_name and + * tok? The Suffix must be in form + * tok_{digits}, or tok{digits}. + * @pmu_name: The pmu_name with possible suffix. + * @tok: The possible match to pmu_name. + */ +static bool perf_pmu__match_ignoring_suffix_uncore(const char *pmu_name, const char *tok) +{ + size_t pmu_name_len, tok_len; + + /* For robustness, check for NULL. */ + if (pmu_name == NULL) + return tok == NULL; + + /* uncore_ prefixes are ignored. */ + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; + if (!strncmp(tok, "uncore_", 7)) + tok += 7; + + pmu_name_len = pmu_name_len_no_suffix(pmu_name); + tok_len = pmu_name_len_no_suffix(tok); + if (pmu_name_len != tok_len) + return false; + + return strncmp(pmu_name, tok, pmu_name_len) == 0; +} + + +/** + * perf_pmu__match_wildcard_uncore - does to_match match the PMU's name? + * @pmu_name: The pmu->name or pmu->alias to match against. + * @to_match: the json struct pmu_event name. This may lack a suffix (which * matches) or be of the form "socket,pmuname" which will match * "socketX_pmunameY". - * @name: a real full PMU name as from sysfs. */ -static bool pmu_uncore_alias_match(const char *pmu_name, const char *name) +static bool perf_pmu__match_wildcard_uncore(const char *pmu_name, const char *to_match) { - char *tmp = NULL, *tok, *str; - bool res; - - if (strchr(pmu_name, ',') == NULL) - return perf_pmu__match_ignoring_suffix(name, pmu_name); + char *mutable_to_match, *tok, *tmp; - str = strdup(pmu_name); - if (!str) + if (!pmu_name) return false; - /* - * uncore alias may be from different PMU with common prefix - */ - tok = strtok_r(str, ",", &tmp); - if (strncmp(pmu_name, tok, strlen(tok))) { - res = false; - goto out; - } + /* uncore_ prefixes are ignored. */ + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; + if (!strncmp(to_match, "uncore_", 7)) + to_match += 7; - /* - * Match more complex aliases where the alias name is a comma-delimited - * list of tokens, orderly contained in the matching PMU name. - * - * Example: For alias "socket,pmuname" and PMU "socketX_pmunameY", we - * match "socket" in "socketX_pmunameY" and then "pmuname" in - * "pmunameY". - */ - while (1) { - char *next_tok = strtok_r(NULL, ",", &tmp); + if (strchr(to_match, ',') == NULL) + return perf_pmu__match_wildcard(pmu_name, to_match); - name = strstr(name, tok); - if (!name || - (!next_tok && !perf_pmu__match_ignoring_suffix(name, tok))) { - res = false; - goto out; + /* Process comma separated list of PMU name components. */ + mutable_to_match = strdup(to_match); + if (!mutable_to_match) + return false; + + tok = strtok_r(mutable_to_match, ",", &tmp); + while (tok) { + size_t tok_len = strlen(tok); + + if (strncmp(pmu_name, tok, tok_len)) { + /* Mismatch between part of pmu_name and tok. */ + free(mutable_to_match); + return false; } - if (!next_tok) - break; - tok = next_tok; - name += strlen(tok); + /* Move pmu_name forward over tok and suffix. */ + pmu_name += tok_len; + while (*pmu_name != '\0' && isdigit(*pmu_name)) + pmu_name++; + if (*pmu_name == '_') + pmu_name++; + + tok = strtok_r(NULL, ",", &tmp); } - - res = true; -out: - free(str); - return res; + free(mutable_to_match); + return *pmu_name == '\0'; } bool pmu_uncore_identifier_match(const char *compat, const char *id) @@ -971,7 +1056,7 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe, { struct perf_pmu *pmu = vdata; - perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, + perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ -1, pe, EVENT_SRC_CPU_JSON); return 0; } @@ -987,13 +1072,16 @@ void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_tab static void pmu_add_cpu_aliases(struct perf_pmu *pmu) { - if (!pmu->events_table) + if (!pmu->events_table && !pmu->is_core) return; if (pmu->cpu_aliases_added) return; pmu_add_cpu_aliases_table(pmu, pmu->events_table); + if (pmu->is_core) + pmu_add_cpu_aliases_table(pmu, perf_pmu__default_core_events_table()); + pmu->cpu_aliases_added = true; } @@ -1003,20 +1091,27 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, { struct perf_pmu *pmu = vdata; - if (!pe->compat || !pe->pmu) + if (!pe->compat || !pe->pmu) { + /* No data to match. */ return 0; + } - if (pmu_uncore_alias_match(pe->pmu, pmu->name) && - pmu_uncore_identifier_match(pe->compat, pmu->id)) { + if (!perf_pmu__match_wildcard_uncore(pmu->name, pe->pmu) && + !perf_pmu__match_wildcard_uncore(pmu->alias_name, pe->pmu)) { + /* PMU name/alias_name don't match. */ + return 0; + } + + if (pmu_uncore_identifier_match(pe->compat, pmu->id)) { + /* Id matched. */ perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, - /*val_fd=*/ NULL, + /*val_fd=*/ -1, pe, EVENT_SRC_SYS_JSON); } - return 0; } @@ -1066,43 +1161,107 @@ perf_pmu__arch_init(struct perf_pmu *pmu) pmu->mem_events = perf_mem_events; } +/* Variant of str_hash that does tolower on each character. */ +static size_t aliases__hash(long key, void *ctx __maybe_unused) +{ + const char *s = (const char *)key; + size_t h = 0; + + while (*s) { + h = h * 31 + tolower(*s); + s++; + } + return h; +} + +static bool aliases__equal(long key1, long key2, void *ctx __maybe_unused) +{ + return strcasecmp((const char *)key1, (const char *)key2) == 0; +} + +int perf_pmu__init(struct perf_pmu *pmu, __u32 type, const char *name) +{ + pmu->type = type; + INIT_LIST_HEAD(&pmu->format); + INIT_LIST_HEAD(&pmu->caps); + + pmu->name = strdup(name); + if (!pmu->name) + return -ENOMEM; + + pmu->aliases = hashmap__new(aliases__hash, aliases__equal, /*ctx=*/ NULL); + if (!pmu->aliases) + return -ENOMEM; + + return 0; +} + +static __u32 wellknown_pmu_type(const char *pmu_name) +{ + struct { + const char *pmu_name; + __u32 type; + } wellknown_pmus[] = { + { + "software", + PERF_TYPE_SOFTWARE + }, + { + "tracepoint", + PERF_TYPE_TRACEPOINT + }, + { + "breakpoint", + PERF_TYPE_BREAKPOINT + }, + }; + for (size_t i = 0; i < ARRAY_SIZE(wellknown_pmus); i++) { + if (!strcmp(wellknown_pmus[i].pmu_name, pmu_name)) + return wellknown_pmus[i].type; + } + return PERF_TYPE_MAX; +} + struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *name, bool eager_load) { struct perf_pmu *pmu; - __u32 type; pmu = zalloc(sizeof(*pmu)); if (!pmu) return NULL; - pmu->name = strdup(name); - if (!pmu->name) - goto err; + if (perf_pmu__init(pmu, PERF_PMU_TYPE_FAKE, name) != 0) { + perf_pmu__delete(pmu); + return NULL; + } /* * Read type early to fail fast if a lookup name isn't a PMU. Ensure * that type value is successfully assigned (return 1). */ - if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1) - goto err; - - INIT_LIST_HEAD(&pmu->format); - INIT_LIST_HEAD(&pmu->aliases); - INIT_LIST_HEAD(&pmu->caps); + if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &pmu->type) != 1) { + /* Double check the PMU's name isn't wellknown. */ + pmu->type = wellknown_pmu_type(name); + if (pmu->type == PERF_TYPE_MAX) { + perf_pmu__delete(pmu); + return NULL; + } + } /* * The pmu data we store & need consists of the pmu * type value and format definitions. Load both right * now. */ - if (pmu_format(pmu, dirfd, name, eager_load)) - goto err; + if (pmu_format(pmu, dirfd, name, eager_load)) { + perf_pmu__delete(pmu); + return NULL; + } pmu->is_core = is_pmu_core(name); pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core); - pmu->type = type; pmu->is_uncore = pmu_is_uncore(dirfd, name); if (pmu->is_uncore) pmu->id = pmu_id(name); @@ -1124,10 +1283,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char pmu_aliases_parse_eager(pmu, dirfd); return pmu; -err: - zfree(&pmu->name); - free(pmu); - return NULL; } /* Creates the PMU when sysfs scanning fails. */ @@ -1149,7 +1304,7 @@ struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pm pmu->cpus = cpu_map__online(); INIT_LIST_HEAD(&pmu->format); - INIT_LIST_HEAD(&pmu->aliases); + pmu->aliases = hashmap__new(aliases__hash, aliases__equal, /*ctx=*/ NULL); INIT_LIST_HEAD(&pmu->caps); list_add_tail(&pmu->list, core_pmus); return pmu; @@ -1184,48 +1339,28 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) } } -bool evsel__is_aux_event(const struct evsel *evsel) -{ - struct perf_pmu *pmu; - - if (evsel->needs_auxtrace_mmap) - return true; - - pmu = evsel__find_pmu(evsel); - return pmu && pmu->auxtrace; -} - /* - * Set @config_name to @val as long as the user hasn't already set or cleared it - * by passing a config term on the command line. - * - * @val is the value to put into the bits specified by @config_name rather than - * the bit pattern. It is shifted into position by this function, so to set - * something to true, pass 1 for val rather than a pre shifted value. + * Unpacks a raw config[n] value using the sparse bitfield that defines a + * format attr. For example "config1:1,6-7,44" defines a 4 bit value across non + * contiguous bits and this function returns those 4 bits as a value. */ -#define field_prep(_mask, _val) (((_val) << (ffsll(_mask) - 1)) & (_mask)) -void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel, - const char *config_name, u64 val) +u64 perf_pmu__format_unpack(unsigned long *format, u64 config_val) { - u64 user_bits = 0, bits; - struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG); - - if (term) - user_bits = term->val.cfg_chg; + int val_bit = 0; + u64 res = 0; + int fmt_bit; - bits = perf_pmu__format_bits(pmu, config_name); + for_each_set_bit(fmt_bit, format, PERF_PMU_FORMAT_BITS) { + if (config_val & (1ULL << fmt_bit)) + res |= BIT_ULL(val_bit); - /* Do nothing if the user changed the value */ - if (bits & user_bits) - return; - - /* Otherwise replace it */ - evsel->core.attr.config &= ~bits; - evsel->core.attr.config |= field_prep(bits, val); + val_bit++; + } + return res; } -static struct perf_pmu_format * -pmu_find_format(const struct list_head *formats, const char *name) +struct perf_pmu_format *pmu_find_format(const struct list_head *formats, + const char *name) { struct perf_pmu_format *format; @@ -1236,7 +1371,7 @@ pmu_find_format(const struct list_head *formats, const char *name) return NULL; } -__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name) +__u64 perf_pmu__format_bits(const struct perf_pmu *pmu, const char *name) { struct perf_pmu_format *format = pmu_find_format(&pmu->format, name); __u64 bits = 0; @@ -1251,7 +1386,7 @@ __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name) return bits; } -int perf_pmu__format_type(struct perf_pmu *pmu, const char *name) +int perf_pmu__format_type(const struct perf_pmu *pmu, const char *name) { struct perf_pmu_format *format = pmu_find_format(&pmu->format, name); @@ -1266,8 +1401,8 @@ int perf_pmu__format_type(struct perf_pmu *pmu, const char *name) * Sets value based on the format definition (format parameter) * and unformatted value (value parameter). */ -static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, - bool zero) +void perf_pmu__format_pack(unsigned long *format, __u64 value, __u64 *v, + bool zero) { unsigned long fbit, vbit; @@ -1384,23 +1519,55 @@ static int pmu_config_term(const struct perf_pmu *pmu, switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_CONFIG: assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); - pmu_format_value(bits, term->val.num, &attr->config, zero); + perf_pmu__format_pack(bits, term->val.num, &attr->config, zero); break; case PARSE_EVENTS__TERM_TYPE_CONFIG1: assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); - pmu_format_value(bits, term->val.num, &attr->config1, zero); + perf_pmu__format_pack(bits, term->val.num, &attr->config1, zero); break; case PARSE_EVENTS__TERM_TYPE_CONFIG2: assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); - pmu_format_value(bits, term->val.num, &attr->config2, zero); + perf_pmu__format_pack(bits, term->val.num, &attr->config2, zero); break; case PARSE_EVENTS__TERM_TYPE_CONFIG3: assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); - pmu_format_value(bits, term->val.num, &attr->config3, zero); + perf_pmu__format_pack(bits, term->val.num, &attr->config3, zero); + break; + case PARSE_EVENTS__TERM_TYPE_CONFIG4: + assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + perf_pmu__format_pack(bits, term->val.num, &attr->config4, zero); + break; + case PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG: + assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + assert(term->val.num < PERF_COUNT_HW_MAX); + assert(pmu->is_core); + attr->config = term->val.num; + if (perf_pmus__supports_extended_type()) + attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + attr->type = PERF_TYPE_HARDWARE; + break; + case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG: { +#ifndef NDEBUG + int cache_type = term->val.num & 0xFF; + int cache_op = (term->val.num >> 8) & 0xFF; + int cache_result = (term->val.num >> 16) & 0xFF; + + assert(cache_type < PERF_COUNT_HW_CACHE_MAX); + assert(cache_op < PERF_COUNT_HW_CACHE_OP_MAX); + assert(cache_result < PERF_COUNT_HW_CACHE_RESULT_MAX); +#endif + assert(term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + assert((term->val.num & ~0xFFFFFF) == 0); + assert(pmu->is_core); + attr->config = term->val.num; + if (perf_pmus__supports_extended_type()) + attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + attr->type = PERF_TYPE_HW_CACHE; break; + } case PARSE_EVENTS__TERM_TYPE_USER: /* Not hardcoded. */ return -EINVAL; - case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_HARDWARE: + case PARSE_EVENTS__TERM_TYPE_NAME ... PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV: /* Skip non-config terms. */ break; default: @@ -1445,6 +1612,9 @@ static int pmu_config_term(const struct perf_pmu *pmu, case PERF_PMU_FORMAT_VALUE_CONFIG3: vp = &attr->config3; break; + case PERF_PMU_FORMAT_VALUE_CONFIG4: + vp = &attr->config4; + break; default: return -EINVAL; } @@ -1503,7 +1673,7 @@ static int pmu_config_term(const struct perf_pmu *pmu, */ } - pmu_format_value(format->bits, val, vp, zero); + perf_pmu__format_pack(format->bits, val, vp, zero); return 0; } @@ -1517,6 +1687,8 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu, if (perf_pmu__is_hwmon(pmu)) return hwmon_pmu__config_terms(pmu, attr, terms, err); + if (perf_pmu__is_drm(pmu)) + return drm_pmu__config_terms(pmu, attr, terms, err); list_for_each_entry(term, &terms->terms, list) { if (pmu_config_term(pmu, attr, term, terms, zero, apply_hardcoded, err)) @@ -1574,10 +1746,14 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, return alias; /* Alias doesn't exist, try to get it from the json events. */ - if (pmu->events_table && - pmu_events_table__find_event(pmu->events_table, pmu, name, - pmu_add_cpu_aliases_map_callback, - pmu) == 0) { + if ((pmu_events_table__find_event(pmu->events_table, pmu, name, + pmu_add_cpu_aliases_map_callback, + pmu) == 0) || + (pmu->is_core && + pmu_events_table__find_event(perf_pmu__default_core_events_table(), + pmu, name, + pmu_add_cpu_aliases_map_callback, + pmu) == 0)) { alias = perf_pmu__find_alias(pmu, name, /*load=*/ false); } return alias; @@ -1627,6 +1803,24 @@ static int check_info_data(struct perf_pmu *pmu, return 0; } +static int perf_pmu__parse_terms_to_attr(struct perf_pmu *pmu, const char *terms_str, + struct perf_event_attr *attr) +{ + struct parse_events_terms terms; + int ret; + + parse_events_terms__init(&terms); + ret = parse_events_terms(&terms, terms_str); + if (ret) { + pr_debug("Failed to parse terms '%s': %d\n", terms_str, ret); + parse_events_terms__exit(&terms); + return ret; + } + ret = perf_pmu__config(pmu, attr, &terms, /*apply_hardcoded=*/true, /*err=*/NULL); + parse_events_terms__exit(&terms); + return ret; +} + /* * Find alias in the terms list and replace it with the terms * defined for the alias @@ -1649,11 +1843,18 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_ info->unit = NULL; info->scale = 0.0; info->snapshot = false; + info->retirement_latency_mean = 0.0; + info->retirement_latency_min = 0.0; + info->retirement_latency_max = 0.0; if (perf_pmu__is_hwmon(pmu)) { ret = hwmon_pmu__check_alias(head_terms, info, err); goto out; } + if (perf_pmu__is_drm(pmu)) { + ret = drm_pmu__check_alias(pmu, head_terms, info, err); + goto out; + } /* Fake PMU doesn't rewrite terms. */ if (perf_pmu__is_fake(pmu)) @@ -1663,10 +1864,10 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_ alias = pmu_find_alias(pmu, term); if (!alias) continue; - ret = pmu_alias_terms(alias, term->err_term, &term->list); + ret = pmu_alias_terms(alias, &term->list); if (ret) { parse_events_error__handle(err, term->err_term, - strdup("Failure to duplicate terms"), + strdup("Failed to parse terms"), NULL); return ret; } @@ -1676,11 +1877,26 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_ if (ret) return ret; + if (alias->legacy_terms) { + struct perf_event_attr attr = {.config = 0,}; + + ret = perf_pmu__parse_terms_to_attr(pmu, alias->legacy_terms, &attr); + if (ret) { + parse_events_error__handle(err, term->err_term, + strdup("Error evaluating legacy terms"), + NULL); + return ret; + } + if (attr.type == PERF_TYPE_HARDWARE) + *alternate_hw_config = attr.config & PERF_HW_EVENT_MASK; + } + if (alias->per_pkg) info->per_pkg = true; - if (term->alternate_hw_config) - *alternate_hw_config = term->val.num; + info->retirement_latency_mean = alias->retirement_latency_mean; + info->retirement_latency_min = alias->retirement_latency_min; + info->retirement_latency_max = alias->retirement_latency_max; list_del_init(&term->list); parse_events_term__delete(term); @@ -1758,6 +1974,9 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call "config1=0..0xffffffffffffffff", "config2=0..0xffffffffffffffff", "config3=0..0xffffffffffffffff", + "config4=0..0xffffffffffffffff", + "legacy-hardware-config=0..9,", + "legacy-cache-config=0..0xffffff,", "name=string", "period=number", "freq=number", @@ -1775,16 +1994,18 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call "aux-output", "aux-action=(pause|resume|start-paused)", "aux-sample-size=number", + "cpu=number", + "ratio-to-prev=string", }; struct perf_pmu_format *format; int ret; /* * max-events and driver-config are missing above as are the internal - * types user, metric-id, raw, legacy cache and hardware. Assert against - * the enum parse_events__term_type so they are kept in sync. + * types user, metric-id, and raw. Assert against the enum + * parse_events__term_type so they are kept in sync. */ - _Static_assert(ARRAY_SIZE(terms) == __PARSE_EVENTS__TERM_TYPE_NR - 6, + _Static_assert(ARRAY_SIZE(terms) == __PARSE_EVENTS__TERM_TYPE_NR - 4, "perf_pmu__for_each_format()'s terms must be kept in sync with enum parse_events__term_type"); list_for_each_entry(format, &pmu->format, list) { perf_pmu_format__load(pmu, format); @@ -1829,31 +2050,49 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name) return false; if (perf_pmu__is_tool(pmu) && tool_pmu__skip_event(name)) return false; + if (perf_pmu__is_tracepoint(pmu)) + return tp_pmu__have_event(pmu, name); if (perf_pmu__is_hwmon(pmu)) return hwmon_pmu__have_event(pmu, name); + if (perf_pmu__is_drm(pmu)) + return drm_pmu__have_event(pmu, name); if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL) return true; - if (pmu->cpu_aliases_added || !pmu->events_table) + if (pmu->cpu_aliases_added || (!pmu->events_table && !pmu->is_core)) return false; - return pmu_events_table__find_event(pmu->events_table, pmu, name, NULL, NULL) == 0; + if (pmu_events_table__find_event(pmu->events_table, pmu, name, NULL, NULL) == 0) + return true; + return pmu->is_core && + pmu_events_table__find_event(perf_pmu__default_core_events_table(), + pmu, name, NULL, NULL) == 0; } size_t perf_pmu__num_events(struct perf_pmu *pmu) { size_t nr; + if (perf_pmu__is_tracepoint(pmu)) + return tp_pmu__num_events(pmu); if (perf_pmu__is_hwmon(pmu)) return hwmon_pmu__num_events(pmu); + if (perf_pmu__is_drm(pmu)) + return drm_pmu__num_events(pmu); pmu_aliases_parse(pmu); nr = pmu->sysfs_aliases + pmu->sys_json_aliases; - if (pmu->cpu_aliases_added) - nr += pmu->cpu_json_aliases; - else if (pmu->events_table) - nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases; - else - assert(pmu->cpu_json_aliases == 0); + if (pmu->cpu_aliases_added) { + nr += pmu->cpu_json_aliases; + } else if (pmu->events_table || pmu->is_core) { + nr += pmu_events_table__num_events(pmu->events_table, pmu); + if (pmu->is_core) { + nr += pmu_events_table__num_events( + perf_pmu__default_core_events_table(), pmu); + } + nr -= pmu->cpu_common_json_aliases; + } else { + assert(pmu->cpu_json_aliases == 0 && pmu->cpu_common_json_aliases == 0); + } if (perf_pmu__is_tool(pmu)) nr -= tool_pmu__num_skip_events(); @@ -1871,18 +2110,37 @@ static int sub_non_neg(int a, int b) static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, const struct perf_pmu_alias *alias, bool skip_duplicate_pmus) { + struct parse_events_terms terms; struct parse_events_term *term; + int ret, used; size_t pmu_name_len = pmu_deduped_name_len(pmu, pmu->name, skip_duplicate_pmus); - int used = snprintf(buf, len, "%.*s/%s", (int)pmu_name_len, pmu->name, alias->name); - list_for_each_entry(term, &alias->terms.terms, list) { + /* Paramemterized events have the parameters shown. */ + if (strstr(alias->terms, "=?")) { + /* No parameters. */ + snprintf(buf, len, "%.*s/%s/", (int)pmu_name_len, pmu->name, alias->name); + return buf; + } + + parse_events_terms__init(&terms); + ret = parse_events_terms(&terms, alias->terms); + if (ret) { + pr_err("Failure to parse '%s' terms '%s': %d\n", + alias->name, alias->terms, ret); + parse_events_terms__exit(&terms); + snprintf(buf, len, "%.*s/%s/", (int)pmu_name_len, pmu->name, alias->name); + return buf; + } + used = snprintf(buf, len, "%.*s/%s", (int)pmu_name_len, pmu->name, alias->name); + + list_for_each_entry(term, &terms.terms, list) { if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) used += snprintf(buf + used, sub_non_neg(len, used), ",%s=%s", term->config, term->val.str); } - + parse_events_terms__exit(&terms); if (sub_non_neg(len, used) > 0) { buf[used] = '/'; used++; @@ -1896,25 +2154,65 @@ static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, return buf; } +static bool perf_pmu_alias__check_deprecated(struct perf_pmu *pmu, struct perf_pmu_alias *alias) +{ + struct perf_event_attr attr = {.config = 0,}; + const char *check_terms; + bool has_legacy_config; + + if (alias->legacy_deprecated_checked) + return alias->deprecated; + + alias->legacy_deprecated_checked = true; + if (alias->deprecated) + return true; + + check_terms = alias->terms; + has_legacy_config = + strstr(check_terms, "legacy-hardware-config=") != NULL || + strstr(check_terms, "legacy-cache-config=") != NULL; + if (!has_legacy_config && alias->legacy_terms) { + check_terms = alias->legacy_terms; + has_legacy_config = + strstr(check_terms, "legacy-hardware-config=") != NULL || + strstr(check_terms, "legacy-cache-config=") != NULL; + } + if (!has_legacy_config) + return false; + + if (perf_pmu__parse_terms_to_attr(pmu, check_terms, &attr) != 0) { + /* Parsing failed, set as deprecated. */ + alias->deprecated = true; + } else if (attr.type < PERF_TYPE_MAX) { + /* Flag unsupported legacy events as deprecated. */ + alias->deprecated = !is_event_supported(attr.type, attr.config); + } + return alias->deprecated; +} + int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, void *state, pmu_event_callback cb) { char buf[1024]; - struct perf_pmu_alias *event; struct pmu_event_info info = { .pmu = pmu, .event_type_desc = "Kernel PMU event", }; int ret = 0; - struct strbuf sb; + struct hashmap_entry *entry; + size_t bkt; + if (perf_pmu__is_tracepoint(pmu)) + return tp_pmu__for_each_event(pmu, state, cb); if (perf_pmu__is_hwmon(pmu)) return hwmon_pmu__for_each_event(pmu, state, cb); + if (perf_pmu__is_drm(pmu)) + return drm_pmu__for_each_event(pmu, state, cb); - strbuf_init(&sb, /*hint=*/ 0); pmu_aliases_parse(pmu); pmu_add_cpu_aliases(pmu); - list_for_each_entry(event, &pmu->aliases, list) { + hashmap__for_each_entry(pmu->aliases, entry, bkt) { + struct perf_pmu_alias *event = entry->pvalue; size_t buf_used, pmu_name_len; if (perf_pmu__is_tool(pmu) && tool_pmu__skip_event(event->name)) @@ -1945,16 +2243,14 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, info.desc = event->desc; info.long_desc = event->long_desc; info.encoding_desc = buf + buf_used; - parse_events_terms__to_strbuf(&event->terms, &sb); buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, - "%.*s/%s/", (int)pmu_name_len, info.pmu_name, sb.buf) + 1; + "%.*s/%s/", (int)pmu_name_len, info.pmu_name, event->terms) + 1; + info.str = event->terms; info.topic = event->topic; - info.str = sb.buf; - info.deprecated = event->deprecated; + info.deprecated = perf_pmu_alias__check_deprecated(pmu, event); ret = cb(state, &info); if (ret) goto out; - strbuf_setlen(&sb, /*len=*/ 0); } if (pmu->selectable) { info.name = buf; @@ -1970,19 +2266,88 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, ret = cb(state, &info); } out: - strbuf_release(&sb); return ret; } -bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name) +static bool perf_pmu___name_match(const struct perf_pmu *pmu, const char *to_match, bool wildcard) { - return !strcmp(pmu->name, pmu_name) || - (pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name)) || + const char *names[2] = { + pmu->name, + pmu->alias_name, + }; + if (pmu->is_core) { + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (!name) + continue; + + if (!strcmp(name, to_match)) { + /* Exact name match. */ + return true; + } + } + if (!strcmp(to_match, "default_core")) { + /* + * jevents and tests use default_core as a marker for any core + * PMU as the PMU name varies across architectures. + */ + return true; + } + return false; + } + if (!pmu->is_uncore) { /* - * jevents and tests use default_core as a marker for any core - * PMU as the PMU name varies across architectures. + * PMU isn't core or uncore, some kind of broken CPU mask + * situation. Only match exact name. */ - (pmu->is_core && !strcmp(pmu_name, "default_core")); + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (!name) + continue; + + if (!strcmp(name, to_match)) { + /* Exact name match. */ + return true; + } + } + return false; + } + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (!name) + continue; + + if (wildcard && perf_pmu__match_wildcard_uncore(name, to_match)) + return true; + if (!wildcard && perf_pmu__match_ignoring_suffix_uncore(name, to_match)) + return true; + } + return false; +} + +/** + * perf_pmu__name_wildcard_match - Called by the jevents generated code to see + * if pmu matches the json to_match string. + * @pmu: The pmu whose name/alias to match. + * @to_match: The possible match to pmu_name. + */ +bool perf_pmu__name_wildcard_match(const struct perf_pmu *pmu, const char *to_match) +{ + return perf_pmu___name_match(pmu, to_match, /*wildcard=*/true); +} + +/** + * perf_pmu__name_no_suffix_match - Does pmu's name match to_match ignoring any + * trailing suffix on the pmu_name and/or tok? + * @pmu: The pmu whose name/alias to match. + * @to_match: The possible match to pmu_name. + */ +bool perf_pmu__name_no_suffix_match(const struct perf_pmu *pmu, const char *to_match) +{ + return perf_pmu___name_match(pmu, to_match, /*wildcard=*/false); } bool perf_pmu__is_software(const struct perf_pmu *pmu) @@ -2012,6 +2377,18 @@ bool perf_pmu__is_software(const struct perf_pmu *pmu) return false; } +bool perf_pmu__benefits_from_affinity(struct perf_pmu *pmu) +{ + if (!pmu) + return true; /* Assume is core. */ + + /* + * All perf event PMUs should benefit from accessing the perf event + * contexts on the local CPU. + */ + return pmu->type <= PERF_PMU_TYPE_PE_END; +} + FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name) { char path[PATH_MAX]; @@ -2114,6 +2491,17 @@ static void perf_pmu__del_caps(struct perf_pmu *pmu) } } +struct perf_pmu_caps *perf_pmu__get_cap(struct perf_pmu *pmu, const char *name) +{ + struct perf_pmu_caps *caps; + + list_for_each_entry(caps, &pmu->caps, list) { + if (!strcmp(caps->name, name)) + return caps; + } + return NULL; +} + /* * Reading/parsing the given pmu capabilities, which should be located at: * /sys/bus/event_source/devices/<dev>/caps as sysfs group attributes. @@ -2121,10 +2509,9 @@ static void perf_pmu__del_caps(struct perf_pmu *pmu) */ int perf_pmu__caps_parse(struct perf_pmu *pmu) { - struct stat st; char caps_path[PATH_MAX]; - DIR *caps_dir; - struct dirent *evt_ent; + struct io_dir caps_dir; + struct io_dirent64 *evt_ent; int caps_fd; if (pmu->caps_initialized) @@ -2135,24 +2522,21 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) if (!perf_pmu__pathname_scnprintf(caps_path, sizeof(caps_path), pmu->name, "caps")) return -1; - if (stat(caps_path, &st) < 0) { + caps_fd = open(caps_path, O_CLOEXEC | O_DIRECTORY | O_RDONLY); + if (caps_fd == -1) { pmu->caps_initialized = true; return 0; /* no error if caps does not exist */ } - caps_dir = opendir(caps_path); - if (!caps_dir) - return -EINVAL; + io_dir__init(&caps_dir, caps_fd); - caps_fd = dirfd(caps_dir); - - while ((evt_ent = readdir(caps_dir)) != NULL) { + while ((evt_ent = io_dir__readdir(&caps_dir)) != NULL) { char *name = evt_ent->d_name; char value[128]; FILE *file; int fd; - if (!strcmp(name, ".") || !strcmp(name, "..")) + if (io_dir__is_dir(&caps_dir, evt_ent)) continue; fd = openat(caps_fd, name, O_RDONLY); @@ -2174,7 +2558,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) fclose(file); } - closedir(caps_dir); + close(caps_fd); pmu->caps_initialized = true; return pmu->nr_caps; @@ -2229,29 +2613,31 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, name ?: "N/A", buf, config_name, config); } -bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok) +bool perf_pmu__wildcard_match(const struct perf_pmu *pmu, const char *wildcard_to_match) { - const char *name = pmu->name; - bool need_fnmatch = strisglob(tok); + const char *names[2] = { + pmu->name, + pmu->alias_name, + }; + bool need_fnmatch = strisglob(wildcard_to_match); - if (!strncmp(tok, "uncore_", 7)) - tok += 7; - if (!strncmp(name, "uncore_", 7)) - name += 7; + if (!strncmp(wildcard_to_match, "uncore_", 7)) + wildcard_to_match += 7; - if (perf_pmu__match_ignoring_suffix(name, tok) || - (need_fnmatch && !fnmatch(tok, name, 0))) - return true; + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *pmu_name = names[i]; - name = pmu->alias_name; - if (!name) - return false; + if (!pmu_name) + continue; - if (!strncmp(name, "uncore_", 7)) - name += 7; + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; - return perf_pmu__match_ignoring_suffix(name, tok) || - (need_fnmatch && !fnmatch(tok, name, 0)); + if (perf_pmu__match_wildcard(pmu_name, wildcard_to_match) || + (need_fnmatch && !fnmatch(wildcard_to_match, pmu_name, 0))) + return true; + } + return false; } int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size) @@ -2306,8 +2692,13 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, void perf_pmu__delete(struct perf_pmu *pmu) { + if (!pmu) + return; + if (perf_pmu__is_hwmon(pmu)) hwmon_pmu__exit(pmu); + else if (perf_pmu__is_drm(pmu)) + drm_pmu__exit(pmu); perf_pmu__del_formats(&pmu->format); perf_pmu__del_aliases(pmu); @@ -2323,21 +2714,32 @@ void perf_pmu__delete(struct perf_pmu *pmu) const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config) { - struct perf_pmu_alias *event; + struct hashmap_entry *entry; + size_t bkt; if (!pmu) return NULL; pmu_aliases_parse(pmu); pmu_add_cpu_aliases(pmu); - list_for_each_entry(event, &pmu->aliases, list) { + hashmap__for_each_entry(pmu->aliases, entry, bkt) { + struct perf_pmu_alias *event = entry->pvalue; struct perf_event_attr attr = {.config = 0,}; - - int ret = perf_pmu__config(pmu, &attr, &event->terms, /*apply_hardcoded=*/true, - /*err=*/NULL); + int ret = perf_pmu__parse_terms_to_attr(pmu, event->terms, &attr); if (ret == 0 && config == attr.config) return event->name; } return NULL; } + +bool perf_pmu__reads_only_on_cpu_idx0(const struct perf_event_attr *attr) +{ + enum tool_pmu_event event; + + if (attr->type != PERF_PMU_TYPE_TOOL) + return false; + + event = (enum tool_pmu_event)attr->config; + return event != TOOL_PMU__EVENT_USER_TIME && event != TOOL_PMU__EVENT_SYSTEM_TIME; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index dbed6c243a5e..0d9f3c57e8e8 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -14,6 +14,7 @@ #include "mem-events.h" struct evsel_config_term; +struct hashmap; struct perf_cpu_map; struct print_callbacks; @@ -22,6 +23,7 @@ enum { PERF_PMU_FORMAT_VALUE_CONFIG1, PERF_PMU_FORMAT_VALUE_CONFIG2, PERF_PMU_FORMAT_VALUE_CONFIG3, + PERF_PMU_FORMAT_VALUE_CONFIG4, PERF_PMU_FORMAT_VALUE_CONFIG_END, }; @@ -36,7 +38,24 @@ struct perf_pmu_caps { struct list_head list; }; +enum pmu_kind { + /* A perf event syscall PMU. */ + PERF_PMU_KIND_PE, + /* A perf tool provided DRM PMU. */ + PERF_PMU_KIND_DRM, + /* A perf tool provided HWMON PMU. */ + PERF_PMU_KIND_HWMON, + /* Perf tool provided PMU for tool events like time. */ + PERF_PMU_KIND_TOOL, + /* A testing PMU kind. */ + PERF_PMU_KIND_FAKE +}; + enum { + PERF_PMU_TYPE_PE_START = 0, + PERF_PMU_TYPE_PE_END = 0xFFFDFFFF, + PERF_PMU_TYPE_DRM_START = 0xFFFE0000, + PERF_PMU_TYPE_DRM_END = 0xFFFEFFFF, PERF_PMU_TYPE_HWMON_START = 0xFFFF0000, PERF_PMU_TYPE_HWMON_END = 0xFFFFFFFD, PERF_PMU_TYPE_TOOL = 0xFFFFFFFE, @@ -123,7 +142,7 @@ struct perf_pmu { * event read from <sysfs>/bus/event_source/devices/<name>/events/ or * from json events in pmu-events.c. */ - struct list_head aliases; + struct hashmap *aliases; /** * @events_table: The events table for json events in pmu-events.c. */ @@ -134,6 +153,11 @@ struct perf_pmu { uint32_t cpu_json_aliases; /** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */ uint32_t sys_json_aliases; + /** + * @cpu_common_json_aliases: Number of json events that overlapped with sysfs when + * loading all sysfs events. + */ + uint32_t cpu_common_json_aliases; /** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */ bool sysfs_aliases_loaded; /** @@ -187,6 +211,9 @@ struct perf_pmu { struct perf_pmu_info { const char *unit; double scale; + double retirement_latency_mean; + double retirement_latency_min; + double retirement_latency_max; bool per_pkg; bool snapshot; }; @@ -206,6 +233,31 @@ struct pmu_event_info { bool deprecated; }; +/** + * struct perf_pmu_format - Values from a format file read from + * <sysfs>/devices/cpu/format/ held in struct perf_pmu. + * + * For example, the contents of <sysfs>/devices/cpu/format/event may be + * "config:0-7" and will be represented here as name="event", + * value=PERF_PMU_FORMAT_VALUE_CONFIG and bits 0 to 7 will be set. + */ +struct perf_pmu_format { + /** @list: Element on list within struct perf_pmu. */ + struct list_head list; + /** @bits: Which config bits are set by this format value. */ + DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); + /** @name: The modifier/file name. */ + char *name; + /** + * @value : Which config value the format relates to. Supported values + * are from PERF_PMU_FORMAT_VALUE_CONFIG to + * PERF_PMU_FORMAT_VALUE_CONFIG_END. + */ + u16 value; + /** @loaded: Has the contents been loaded/parsed. */ + bool loaded; +}; + typedef int (*pmu_event_callback)(void *state, struct pmu_event_info *info); typedef int (*pmu_format_callback)(void *state, const char *name, int config, const unsigned long *bits); @@ -220,16 +272,21 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu, struct parse_events_terms *terms, bool zero, bool apply_hardcoded, struct parse_events_error *error); -__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name); -int perf_pmu__format_type(struct perf_pmu *pmu, const char *name); +__u64 perf_pmu__format_bits(const struct perf_pmu *pmu, const char *name); +int perf_pmu__format_type(const struct perf_pmu *pmu, const char *name); int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms, struct perf_pmu_info *info, bool *rewrote_terms, u64 *alternate_hw_config, struct parse_events_error *err); int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb); +void perf_pmu__format_pack(unsigned long *format, __u64 value, __u64 *v, + bool zero); +struct perf_pmu_format *pmu_find_format(const struct list_head *formats, + const char *name); void perf_pmu_format__set_value(void *format, int config, unsigned long *bits); bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name); int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_callback cb); +u64 perf_pmu__format_unpack(unsigned long *format, u64 config_val); bool is_pmu_core(const char *name); bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu); @@ -238,13 +295,15 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name); size_t perf_pmu__num_events(struct perf_pmu *pmu); int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, void *state, pmu_event_callback cb); -bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name); +bool perf_pmu__name_wildcard_match(const struct perf_pmu *pmu, const char *to_match); +bool perf_pmu__name_no_suffix_match(const struct perf_pmu *pmu, const char *to_match); /** * perf_pmu_is_software - is the PMU a software PMU as in it uses the * perf_sw_context in the kernel? */ bool perf_pmu__is_software(const struct perf_pmu *pmu); +bool perf_pmu__benefits_from_affinity(struct perf_pmu *pmu); FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name); FILE *perf_pmu__open_file_at(const struct perf_pmu *pmu, int dirfd, const char *name); @@ -266,6 +325,8 @@ bool pmu_uncore_identifier_match(const char *compat, const char *id); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); +struct perf_pmu_caps *perf_pmu__get_cap(struct perf_pmu *pmu, const char *name); + int perf_pmu__caps_parse(struct perf_pmu *pmu); void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, @@ -273,7 +334,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, const char *config_name); void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); -bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok); +bool perf_pmu__wildcard_match(const struct perf_pmu *pmu, const char *wildcard_to_match); int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size); int perf_pmu__pathname_scnprintf(char *buf, size_t size, @@ -281,13 +342,34 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size, int perf_pmu__event_source_devices_fd(void); int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags); +int perf_pmu__init(struct perf_pmu *pmu, __u32 type, const char *name); struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name, bool eager_load); struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus); void perf_pmu__delete(struct perf_pmu *pmu); -struct perf_pmu *perf_pmus__find_core_pmu(void); const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config); bool perf_pmu__is_fake(const struct perf_pmu *pmu); +bool perf_pmu__reads_only_on_cpu_idx0(const struct perf_event_attr *attr); + +static inline enum pmu_kind perf_pmu__kind(const struct perf_pmu *pmu) +{ + __u32 type; + + if (!pmu) + return PERF_PMU_KIND_PE; + + type = pmu->type; + if (type <= PERF_PMU_TYPE_PE_END) + return PERF_PMU_KIND_PE; + if (type <= PERF_PMU_TYPE_DRM_END) + return PERF_PMU_KIND_DRM; + if (type <= PERF_PMU_TYPE_HWMON_END) + return PERF_PMU_KIND_HWMON; + if (type == PERF_PMU_TYPE_TOOL) + return PERF_PMU_KIND_TOOL; + return PERF_PMU_KIND_FAKE; +} + #endif /* __PMU_H */ diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index b493da0d22ef..9a2023ceeefd 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -3,15 +3,16 @@ #include <linux/list_sort.h> #include <linux/string.h> #include <linux/zalloc.h> +#include <api/io_dir.h> #include <subcmd/pager.h> #include <sys/types.h> #include <ctype.h> -#include <dirent.h> #include <pthread.h> #include <string.h> #include <unistd.h> #include "cpumap.h" #include "debug.h" +#include "drm_pmu.h" #include "evsel.h" #include "pmus.h" #include "pmu.h" @@ -19,6 +20,7 @@ #include "tool_pmu.h" #include "print-events.h" #include "strbuf.h" +#include "string2.h" /* * core_pmus: A PMU belongs to core_pmus if it's name is "cpu" or it's sysfs @@ -37,10 +39,28 @@ */ static LIST_HEAD(core_pmus); static LIST_HEAD(other_pmus); -static bool read_sysfs_core_pmus; -static bool read_sysfs_all_pmus; +enum perf_tool_pmu_type { + PERF_TOOL_PMU_TYPE_PE_CORE, + PERF_TOOL_PMU_TYPE_PE_OTHER, + PERF_TOOL_PMU_TYPE_TOOL, + PERF_TOOL_PMU_TYPE_HWMON, + PERF_TOOL_PMU_TYPE_DRM, + +#define PERF_TOOL_PMU_TYPE_PE_CORE_MASK (1 << PERF_TOOL_PMU_TYPE_PE_CORE) +#define PERF_TOOL_PMU_TYPE_PE_OTHER_MASK (1 << PERF_TOOL_PMU_TYPE_PE_OTHER) +#define PERF_TOOL_PMU_TYPE_TOOL_MASK (1 << PERF_TOOL_PMU_TYPE_TOOL) +#define PERF_TOOL_PMU_TYPE_HWMON_MASK (1 << PERF_TOOL_PMU_TYPE_HWMON) +#define PERF_TOOL_PMU_TYPE_DRM_MASK (1 << PERF_TOOL_PMU_TYPE_DRM) + +#define PERF_TOOL_PMU_TYPE_ALL_MASK (PERF_TOOL_PMU_TYPE_PE_CORE_MASK | \ + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK | \ + PERF_TOOL_PMU_TYPE_TOOL_MASK | \ + PERF_TOOL_PMU_TYPE_HWMON_MASK | \ + PERF_TOOL_PMU_TYPE_DRM_MASK) +}; +static unsigned int read_pmu_types; -static void pmu_read_sysfs(bool core_only); +static void pmu_read_sysfs(unsigned int to_read_pmus); size_t pmu_name_len_no_suffix(const char *str) { @@ -102,8 +122,7 @@ void perf_pmus__destroy(void) perf_pmu__delete(pmu); } - read_sysfs_core_pmus = false; - read_sysfs_all_pmus = false; + read_pmu_types = 0; } static struct perf_pmu *pmu_find(const char *name) @@ -129,6 +148,7 @@ struct perf_pmu *perf_pmus__find(const char *name) struct perf_pmu *pmu; int dirfd; bool core_pmu; + unsigned int to_read_pmus = 0; /* * Once PMU is loaded it stays in the list, @@ -139,11 +159,11 @@ struct perf_pmu *perf_pmus__find(const char *name) if (pmu) return pmu; - if (read_sysfs_all_pmus) + if (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK) return NULL; core_pmu = is_pmu_core(name); - if (core_pmu && read_sysfs_core_pmus) + if (core_pmu && (read_pmu_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK)) return NULL; dirfd = perf_pmu__event_source_devices_fd(); @@ -151,15 +171,29 @@ struct perf_pmu *perf_pmus__find(const char *name) /*eager_load=*/false); close(dirfd); - if (!pmu) { - /* - * Looking up an inidividual PMU failed. This may mean name is - * an alias, so read the PMUs from sysfs and try to find again. - */ - pmu_read_sysfs(core_pmu); + if (pmu) + return pmu; + + /* Looking up an individual perf event PMU failed, check if a tool PMU should be read. */ + if (!strncmp(name, "hwmon_", 6)) + to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK; + else if (!strncmp(name, "drm_", 4)) + to_read_pmus |= PERF_TOOL_PMU_TYPE_DRM_MASK; + else if (!strcmp(name, "tool")) + to_read_pmus |= PERF_TOOL_PMU_TYPE_TOOL_MASK; + + if (to_read_pmus) { + pmu_read_sysfs(to_read_pmus); pmu = pmu_find(name); + if (pmu) + return pmu; } - return pmu; + /* Read all necessary PMUs from sysfs and see if the PMU is found. */ + to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK; + if (!core_pmu) + to_read_pmus |= PERF_TOOL_PMU_TYPE_PE_OTHER_MASK; + pmu_read_sysfs(to_read_pmus); + return pmu_find(name); } static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) @@ -176,11 +210,11 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) if (pmu) return pmu; - if (read_sysfs_all_pmus) + if (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK) return NULL; core_pmu = is_pmu_core(name); - if (core_pmu && read_sysfs_core_pmus) + if (core_pmu && (read_pmu_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK)) return NULL; return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name, @@ -197,52 +231,61 @@ static int pmus_cmp(void *priv __maybe_unused, } /* Add all pmus in sysfs to pmu list: */ -static void pmu_read_sysfs(bool core_only) +static void pmu_read_sysfs(unsigned int to_read_types) { - int fd; - DIR *dir; - struct dirent *dent; struct perf_pmu *tool_pmu; - if (read_sysfs_all_pmus || (core_only && read_sysfs_core_pmus)) + if ((read_pmu_types & to_read_types) == to_read_types) { + /* All requested PMU types have been read. */ return; + } - fd = perf_pmu__event_source_devices_fd(); - if (fd < 0) - return; + if (to_read_types & (PERF_TOOL_PMU_TYPE_PE_CORE_MASK | PERF_TOOL_PMU_TYPE_PE_OTHER_MASK)) { + int fd = perf_pmu__event_source_devices_fd(); + struct io_dir dir; + struct io_dirent64 *dent; + bool core_only = (to_read_types & PERF_TOOL_PMU_TYPE_PE_OTHER_MASK) == 0; - dir = fdopendir(fd); - if (!dir) { - close(fd); - return; - } + if (fd < 0) + goto skip_pe_pmus; - while ((dent = readdir(dir))) { - if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) - continue; - if (core_only && !is_pmu_core(dent->d_name)) - continue; - /* add to static LIST_HEAD(core_pmus) or LIST_HEAD(other_pmus): */ - perf_pmu__find2(fd, dent->d_name); - } + io_dir__init(&dir, fd); - closedir(dir); - if (list_empty(&core_pmus)) { + while ((dent = io_dir__readdir(&dir)) != NULL) { + if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) + continue; + if (core_only && !is_pmu_core(dent->d_name)) + continue; + /* add to static LIST_HEAD(core_pmus) or LIST_HEAD(other_pmus): */ + perf_pmu__find2(fd, dent->d_name); + } + + close(fd); + } +skip_pe_pmus: + if ((to_read_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK) && list_empty(&core_pmus)) { if (!perf_pmu__create_placeholder_core_pmu(&core_pmus)) pr_err("Failure to set up any core PMUs\n"); } list_sort(NULL, &core_pmus, pmus_cmp); - if (!core_only) { - tool_pmu = perf_pmus__tool_pmu(); - list_add_tail(&tool_pmu->list, &other_pmus); - perf_pmus__read_hwmon_pmus(&other_pmus); + + if ((to_read_types & PERF_TOOL_PMU_TYPE_TOOL_MASK) != 0 && + (read_pmu_types & PERF_TOOL_PMU_TYPE_TOOL_MASK) == 0) { + tool_pmu = tool_pmu__new(); + if (tool_pmu) + list_add_tail(&tool_pmu->list, &other_pmus); } + if ((to_read_types & PERF_TOOL_PMU_TYPE_HWMON_MASK) != 0 && + (read_pmu_types & PERF_TOOL_PMU_TYPE_HWMON_MASK) == 0) + perf_pmus__read_hwmon_pmus(&other_pmus); + + if ((to_read_types & PERF_TOOL_PMU_TYPE_DRM_MASK) != 0 && + (read_pmu_types & PERF_TOOL_PMU_TYPE_DRM_MASK) == 0) + perf_pmus__read_drm_pmus(&other_pmus); + list_sort(NULL, &other_pmus, pmus_cmp); - if (!list_empty(&core_pmus)) { - read_sysfs_core_pmus = true; - if (!core_only) - read_sysfs_all_pmus = true; - } + + read_pmu_types |= to_read_types; } static struct perf_pmu *__perf_pmus__find_by_type(unsigned int type) @@ -263,12 +306,23 @@ static struct perf_pmu *__perf_pmus__find_by_type(unsigned int type) struct perf_pmu *perf_pmus__find_by_type(unsigned int type) { + unsigned int to_read_pmus; struct perf_pmu *pmu = __perf_pmus__find_by_type(type); - if (pmu || read_sysfs_all_pmus) + if (pmu || (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK)) return pmu; - pmu_read_sysfs(/*core_only=*/false); + if (type >= PERF_PMU_TYPE_PE_START && type <= PERF_PMU_TYPE_PE_END) { + to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK | + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK; + } else if (type >= PERF_PMU_TYPE_DRM_START && type <= PERF_PMU_TYPE_DRM_END) { + to_read_pmus = PERF_TOOL_PMU_TYPE_DRM_MASK; + } else if (type >= PERF_PMU_TYPE_HWMON_START && type <= PERF_PMU_TYPE_HWMON_END) { + to_read_pmus = PERF_TOOL_PMU_TYPE_HWMON_MASK; + } else { + to_read_pmus = PERF_TOOL_PMU_TYPE_TOOL_MASK; + } + pmu_read_sysfs(to_read_pmus); pmu = __perf_pmus__find_by_type(type); return pmu; } @@ -282,7 +336,7 @@ struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu) bool use_core_pmus = !pmu || pmu->is_core; if (!pmu) { - pmu_read_sysfs(/*core_only=*/false); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_ALL_MASK); pmu = list_prepare_entry(pmu, &core_pmus, list); } if (use_core_pmus) { @@ -300,7 +354,7 @@ struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu) struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu) { if (!pmu) { - pmu_read_sysfs(/*core_only=*/true); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_PE_CORE_MASK); return list_first_entry_or_null(&core_pmus, typeof(*pmu), list); } list_for_each_entry_continue(pmu, &core_pmus, list) @@ -309,6 +363,92 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu) return NULL; } +struct perf_pmu *perf_pmus__scan_for_event(struct perf_pmu *pmu, const char *event) +{ + bool use_core_pmus = !pmu || pmu->is_core; + + if (!pmu) { + /* Hwmon filename values that aren't used. */ + enum hwmon_type type; + int number; + /* + * Core PMUs, other sysfs PMUs and tool PMU can take all event + * types or aren't wother optimizing for. + */ + unsigned int to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK | + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK | + PERF_TOOL_PMU_TYPE_TOOL_MASK; + + /* Could the event be a hwmon event? */ + if (parse_hwmon_filename(event, &type, &number, /*item=*/NULL, /*alarm=*/NULL)) + to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK; + + /* Could the event be a DRM event? */ + if (strlen(event) > 4 && strncmp("drm-", event, 4) == 0) + to_read_pmus |= PERF_TOOL_PMU_TYPE_DRM_MASK; + + pmu_read_sysfs(to_read_pmus); + pmu = list_prepare_entry(pmu, &core_pmus, list); + } + if (use_core_pmus) { + list_for_each_entry_continue(pmu, &core_pmus, list) + return pmu; + + pmu = NULL; + pmu = list_prepare_entry(pmu, &other_pmus, list); + } + list_for_each_entry_continue(pmu, &other_pmus, list) + return pmu; + return NULL; +} + +struct perf_pmu *perf_pmus__scan_matching_wildcard(struct perf_pmu *pmu, const char *wildcard) +{ + bool use_core_pmus = !pmu || pmu->is_core; + + if (!pmu) { + /* + * Core PMUs, other sysfs PMUs and tool PMU can have any name or + * aren't wother optimizing for. + */ + unsigned int to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK | + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK | + PERF_TOOL_PMU_TYPE_TOOL_MASK; + + /* + * Hwmon PMUs have an alias from a sysfs name like hwmon0, + * hwmon1, etc. or have a name of hwmon_<name>. They therefore + * can only have a wildcard match if the wildcard begins with + * "hwmon". Similarly drm PMUs must start "drm_", avoid reading + * such events unless the PMU could match. + */ + if (strisglob(wildcard)) { + to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK | + PERF_TOOL_PMU_TYPE_DRM_MASK; + } else if (strlen(wildcard) >= 4 && strncmp("drm_", wildcard, 4) == 0) { + to_read_pmus |= PERF_TOOL_PMU_TYPE_DRM_MASK; + } else if (strlen(wildcard) >= 5 && strncmp("hwmon", wildcard, 5) == 0) { + to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK; + } + + pmu_read_sysfs(to_read_pmus); + pmu = list_prepare_entry(pmu, &core_pmus, list); + } + if (use_core_pmus) { + list_for_each_entry_continue(pmu, &core_pmus, list) { + if (perf_pmu__wildcard_match(pmu, wildcard)) + return pmu; + } + pmu = NULL; + pmu = list_prepare_entry(pmu, &other_pmus, list); + } + list_for_each_entry_continue(pmu, &other_pmus, list) { + if (perf_pmu__wildcard_match(pmu, wildcard)) + return pmu; + } + return NULL; +} + static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu) { bool use_core_pmus = !pmu || pmu->is_core; @@ -316,7 +456,7 @@ static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu) const char *last_pmu_name = (pmu && pmu->name) ? pmu->name : ""; if (!pmu) { - pmu_read_sysfs(/*core_only=*/false); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_ALL_MASK); pmu = list_prepare_entry(pmu, &core_pmus, list); } else last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: ""); @@ -481,7 +621,7 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p while ((pmu = scan_fn(pmu)) != NULL) len += perf_pmu__num_events(pmu); - aliases = zalloc(sizeof(struct sevent) * len); + aliases = calloc(len, sizeof(struct sevent)); if (!aliases) { pr_err("FATAL: not enough memory to print PMU events\n"); return; @@ -505,6 +645,7 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p print_cb->print_event(print_state, aliases[j].topic, aliases[j].pmu_name, + aliases[j].pmu->type, aliases[j].name, aliases[j].alias, aliases[j].scale_unit, @@ -609,6 +750,7 @@ void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, voi print_cb->print_event(print_state, /*topic=*/NULL, /*pmu_name=*/NULL, + pmu->type, format_args.short_string.buf, /*event_alias=*/NULL, /*scale_unit=*/NULL, @@ -674,47 +816,40 @@ bool perf_pmus__supports_extended_type(void) return perf_pmus__do_support_extended_type; } -char *perf_pmus__default_pmu_name(void) +struct perf_pmu *perf_pmus__find_by_attr(const struct perf_event_attr *attr) { - int fd; - DIR *dir; - struct dirent *dent; - char *result = NULL; - - if (!list_empty(&core_pmus)) - return strdup(list_first_entry(&core_pmus, struct perf_pmu, list)->name); + struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); + u32 type = attr->type; + bool legacy_core_type = type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE; - fd = perf_pmu__event_source_devices_fd(); - if (fd < 0) - return strdup("cpu"); + if (!pmu && legacy_core_type && perf_pmus__supports_extended_type()) { + type = attr->config >> PERF_PMU_TYPE_SHIFT; - dir = fdopendir(fd); - if (!dir) { - close(fd); - return strdup("cpu"); + pmu = perf_pmus__find_by_type(type); } - - while ((dent = readdir(dir))) { - if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) - continue; - if (is_pmu_core(dent->d_name)) { - result = strdup(dent->d_name); - break; - } + if (!pmu && (legacy_core_type || type == PERF_TYPE_RAW)) { + /* + * For legacy events, if there was no extended type info then + * assume the PMU is the first core PMU. + * + * On architectures like ARM there is no sysfs PMU with type + * PERF_TYPE_RAW, assume the RAW events are going to be handled + * by the first core PMU. + */ + pmu = perf_pmus__find_core_pmu(); } - - closedir(dir); - return result ?: strdup("cpu"); + return pmu; } struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) { struct perf_pmu *pmu = evsel->pmu; - if (!pmu) { - pmu = perf_pmus__find_by_type(evsel->core.attr.type); - ((struct evsel *)evsel)->pmu = pmu; - } + if (pmu) + return pmu; + + pmu = perf_pmus__find_by_attr(&evsel->core.attr); + ((struct evsel *)evsel)->pmu = pmu; return pmu; } @@ -733,7 +868,7 @@ struct perf_pmu *perf_pmus__add_test_pmu(int test_sysfs_dirfd, const char *name) return perf_pmu__lookup(&other_pmus, test_sysfs_dirfd, name, /*eager_load=*/true); } -struct perf_pmu *perf_pmus__add_test_hwmon_pmu(int hwmon_dir, +struct perf_pmu *perf_pmus__add_test_hwmon_pmu(const char *hwmon_dir, const char *sysfs_name, const char *name) { diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h index a0cb0eb2ff97..7cb36863711a 100644 --- a/tools/perf/util/pmus.h +++ b/tools/perf/util/pmus.h @@ -5,6 +5,7 @@ #include <stdbool.h> #include <stddef.h> +struct perf_event_attr; struct perf_pmu; struct print_callbacks; @@ -16,9 +17,12 @@ void perf_pmus__destroy(void); struct perf_pmu *perf_pmus__find(const char *name); struct perf_pmu *perf_pmus__find_by_type(unsigned int type); +struct perf_pmu *perf_pmus__find_by_attr(const struct perf_event_attr *attr); struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu); struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu); +struct perf_pmu *perf_pmus__scan_for_event(struct perf_pmu *pmu, const char *event); +struct perf_pmu *perf_pmus__scan_matching_wildcard(struct perf_pmu *pmu, const char *wildcard); const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str); @@ -27,12 +31,12 @@ void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, voi bool perf_pmus__have_event(const char *pname, const char *name); int perf_pmus__num_core_pmus(void); bool perf_pmus__supports_extended_type(void); -char *perf_pmus__default_pmu_name(void); struct perf_pmu *perf_pmus__add_test_pmu(int test_sysfs_dirfd, const char *name); -struct perf_pmu *perf_pmus__add_test_hwmon_pmu(int hwmon_dir, +struct perf_pmu *perf_pmus__add_test_hwmon_pmu(const char *hwmon_dir, const char *sysfs_name, const char *name); struct perf_pmu *perf_pmus__fake_pmu(void); +struct perf_pmu *perf_pmus__find_core_pmu(void); #endif /* __PMUS_H */ diff --git a/tools/perf/util/powerpc-vpadtl.c b/tools/perf/util/powerpc-vpadtl.c new file mode 100644 index 000000000000..710f3093f3f9 --- /dev/null +++ b/tools/perf/util/powerpc-vpadtl.c @@ -0,0 +1,736 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * VPA DTL PMU support + */ + +#include <linux/string.h> +#include <linux/zalloc.h> +#include <errno.h> +#include <inttypes.h> +#include "color.h" +#include "evlist.h" +#include "session.h" +#include "auxtrace.h" +#include "data.h" +#include "machine.h" +#include "debug.h" +#include "powerpc-vpadtl.h" +#include "sample.h" +#include "tool.h" + +/* + * Structure to save the auxtrace queue + */ +struct powerpc_vpadtl { + struct auxtrace auxtrace; + struct auxtrace_queues queues; + struct auxtrace_heap heap; + u32 auxtrace_type; + struct perf_session *session; + struct machine *machine; + u32 pmu_type; + u64 sample_id; +}; + +struct boottb_freq { + u64 boot_tb; + u64 tb_freq; + u64 timebase; + u64 padded[3]; +}; + +struct powerpc_vpadtl_queue { + struct powerpc_vpadtl *vpa; + unsigned int queue_nr; + struct auxtrace_buffer *buffer; + struct thread *thread; + bool on_heap; + struct powerpc_vpadtl_entry *dtl; + u64 timestamp; + unsigned long pkt_len; + unsigned long buf_len; + u64 boot_tb; + u64 tb_freq; + unsigned int tb_buffer; + unsigned int size; + bool done; + pid_t pid; + pid_t tid; + int cpu; +}; + +const char *dispatch_reasons[11] = { + "external_interrupt", + "firmware_internal_event", + "H_PROD", + "decrementer_interrupt", + "system_reset", + "firmware_internal_event", + "conferred_cycles", + "time_slice", + "virtual_memory_page_fault", + "expropriated_adjunct", + "priv_doorbell"}; + +const char *preempt_reasons[10] = { + "unused", + "firmware_internal_event", + "H_CEDE", + "H_CONFER", + "time_slice", + "migration_hibernation_page_fault", + "virtual_memory_page_fault", + "H_CONFER_ADJUNCT", + "hcall_adjunct", + "HDEC_adjunct"}; + +#define dtl_entry_size sizeof(struct powerpc_vpadtl_entry) + +/* + * Function to dump the dispatch trace data when perf report + * is invoked with -D + */ +static void powerpc_vpadtl_dump(struct powerpc_vpadtl *vpa __maybe_unused, + unsigned char *buf, size_t len) +{ + struct powerpc_vpadtl_entry *dtl; + int pkt_len, pos = 0; + const char *color = PERF_COLOR_BLUE; + + color_fprintf(stdout, color, + ". ... VPA DTL PMU data: size %zu bytes, entries is %zu\n", + len, len/dtl_entry_size); + + if (len % dtl_entry_size) + len = len - (len % dtl_entry_size); + + while (len) { + pkt_len = dtl_entry_size; + printf("."); + color_fprintf(stdout, color, " %08x: ", pos); + dtl = (struct powerpc_vpadtl_entry *)buf; + if (dtl->timebase != 0) { + printf("dispatch_reason:%s, preempt_reason:%s, " + "enqueue_to_dispatch_time:%d, ready_to_enqueue_time:%d, " + "waiting_to_ready_time:%d\n", + dispatch_reasons[dtl->dispatch_reason], + preempt_reasons[dtl->preempt_reason], + be32_to_cpu(dtl->enqueue_to_dispatch_time), + be32_to_cpu(dtl->ready_to_enqueue_time), + be32_to_cpu(dtl->waiting_to_ready_time)); + } else { + struct boottb_freq *boot_tb = (struct boottb_freq *)buf; + + printf("boot_tb: %" PRIu64 ", tb_freq: %" PRIu64 "\n", + boot_tb->boot_tb, boot_tb->tb_freq); + } + + pos += pkt_len; + buf += pkt_len; + len -= pkt_len; + } +} + +static unsigned long long powerpc_vpadtl_timestamp(struct powerpc_vpadtl_queue *vpaq) +{ + struct powerpc_vpadtl_entry *record = vpaq->dtl; + unsigned long long timestamp = 0; + unsigned long long boot_tb; + unsigned long long diff; + double result, div; + double boot_freq; + /* + * Formula used to get timestamp that can be co-related with + * other perf events: + * ((timbase from DTL entry - boot time) / frequency) * 1000000000 + */ + if (record->timebase) { + boot_tb = vpaq->boot_tb; + boot_freq = vpaq->tb_freq; + diff = be64_to_cpu(record->timebase) - boot_tb; + div = diff / boot_freq; + result = div; + result = result * 1000000000; + timestamp = result; + } + + return timestamp; +} + +static struct powerpc_vpadtl *session_to_vpa(struct perf_session *session) +{ + return container_of(session->auxtrace, struct powerpc_vpadtl, auxtrace); +} + +static void powerpc_vpadtl_dump_event(struct powerpc_vpadtl *vpa, unsigned char *buf, + size_t len) +{ + printf(".\n"); + powerpc_vpadtl_dump(vpa, buf, len); +} + +/* + * Generate perf sample for each entry in the dispatch trace log. + * - sample ip is picked from srr0 field of powerpc_vpadtl_entry + * - sample cpu is logical cpu. + * - cpumode is set to PERF_RECORD_MISC_KERNEL + * - Additionally save the details in raw_data of sample. This + * is to print the relevant fields in perf_sample__fprintf_synth() + * when called from builtin-script + */ +static int powerpc_vpadtl_sample(struct powerpc_vpadtl_entry *record, + struct powerpc_vpadtl *vpa, u64 save, int cpu) +{ + struct perf_sample sample; + union perf_event event; + int ret; + + perf_sample__init(&sample, /*all=*/true); + sample.ip = be64_to_cpu(record->srr0); + sample.period = 1; + sample.cpu = cpu; + sample.id = vpa->sample_id; + sample.callchain = NULL; + sample.branch_stack = NULL; + memset(&event, 0, sizeof(event)); + sample.cpumode = PERF_RECORD_MISC_KERNEL; + sample.time = save; + sample.raw_data = record; + sample.raw_size = sizeof(record); + event.sample.header.type = PERF_RECORD_SAMPLE; + event.sample.header.misc = sample.cpumode; + event.sample.header.size = sizeof(struct perf_event_header); + + ret = perf_session__deliver_synth_event(vpa->session, &event, &sample); + if (ret) + pr_debug("Failed to create sample for dtl entry\n"); + + perf_sample__exit(&sample); + return ret; +} + +static int powerpc_vpadtl_get_buffer(struct powerpc_vpadtl_queue *vpaq) +{ + struct auxtrace_buffer *buffer = vpaq->buffer; + struct auxtrace_queues *queues = &vpaq->vpa->queues; + struct auxtrace_queue *queue; + + queue = &queues->queue_array[vpaq->queue_nr]; + buffer = auxtrace_buffer__next(queue, buffer); + + if (!buffer) + return 0; + + vpaq->buffer = buffer; + vpaq->size = buffer->size; + + /* If the aux_buffer doesn't have data associated, try to load it */ + if (!buffer->data) { + /* get the file desc associated with the perf data file */ + int fd = perf_data__fd(vpaq->vpa->session->data); + + buffer->data = auxtrace_buffer__get_data(buffer, fd); + if (!buffer->data) + return -ENOMEM; + } + + vpaq->buf_len = buffer->size; + + if (buffer->size % dtl_entry_size) + vpaq->buf_len = buffer->size - (buffer->size % dtl_entry_size); + + if (vpaq->tb_buffer != buffer->buffer_nr) { + vpaq->pkt_len = 0; + vpaq->tb_buffer = 0; + } + + return 1; +} + +/* + * The first entry in the queue for VPA DTL PMU has the boot timebase, + * frequency details which are needed to get timestamp which is required to + * correlate with other events. Save the boot_tb and tb_freq as part of + * powerpc_vpadtl_queue. The very next entry is the actual trace data to + * be returned. + */ +static int powerpc_vpadtl_decode(struct powerpc_vpadtl_queue *vpaq) +{ + int ret; + char *buf; + struct boottb_freq *boottb; + + ret = powerpc_vpadtl_get_buffer(vpaq); + if (ret <= 0) + return ret; + + boottb = (struct boottb_freq *)vpaq->buffer->data; + if (boottb->timebase == 0) { + vpaq->boot_tb = boottb->boot_tb; + vpaq->tb_freq = boottb->tb_freq; + vpaq->pkt_len += dtl_entry_size; + } + + buf = vpaq->buffer->data; + buf += vpaq->pkt_len; + vpaq->dtl = (struct powerpc_vpadtl_entry *)buf; + + vpaq->tb_buffer = vpaq->buffer->buffer_nr; + vpaq->buffer = NULL; + vpaq->buf_len = 0; + + return 1; +} + +static int powerpc_vpadtl_decode_all(struct powerpc_vpadtl_queue *vpaq) +{ + int ret; + unsigned char *buf; + + if (!vpaq->buf_len || vpaq->pkt_len == vpaq->size) { + ret = powerpc_vpadtl_get_buffer(vpaq); + if (ret <= 0) + return ret; + } + + if (vpaq->buffer) { + buf = vpaq->buffer->data; + buf += vpaq->pkt_len; + vpaq->dtl = (struct powerpc_vpadtl_entry *)buf; + if ((long long)be64_to_cpu(vpaq->dtl->timebase) <= 0) { + if (vpaq->pkt_len != dtl_entry_size && vpaq->buf_len) { + vpaq->pkt_len += dtl_entry_size; + vpaq->buf_len -= dtl_entry_size; + } + return -1; + } + vpaq->pkt_len += dtl_entry_size; + vpaq->buf_len -= dtl_entry_size; + } else { + return 0; + } + + return 1; +} + +static int powerpc_vpadtl_run_decoder(struct powerpc_vpadtl_queue *vpaq, u64 *timestamp) +{ + struct powerpc_vpadtl *vpa = vpaq->vpa; + struct powerpc_vpadtl_entry *record; + int ret; + unsigned long long vpaq_timestamp; + + while (1) { + ret = powerpc_vpadtl_decode_all(vpaq); + if (!ret) { + pr_debug("All data in the queue has been processed.\n"); + return 1; + } + + /* + * Error is detected when decoding VPA PMU trace. Continue to + * the next trace data and find out more dtl entries. + */ + if (ret < 0) + continue; + + record = vpaq->dtl; + + vpaq_timestamp = powerpc_vpadtl_timestamp(vpaq); + + /* Update timestamp for the last record */ + if (vpaq_timestamp > vpaq->timestamp) + vpaq->timestamp = vpaq_timestamp; + + /* + * If the timestamp of the queue is later than timestamp of the + * coming perf event, bail out so can allow the perf event to + * be processed ahead. + */ + if (vpaq->timestamp >= *timestamp) { + *timestamp = vpaq->timestamp; + vpaq->pkt_len -= dtl_entry_size; + vpaq->buf_len += dtl_entry_size; + return 0; + } + + ret = powerpc_vpadtl_sample(record, vpa, vpaq_timestamp, vpaq->cpu); + if (ret) + continue; + } + return 0; +} + +/* + * For each of the PERF_RECORD_XX record, compare the timestamp + * of perf record with timestamp of top element in the auxtrace heap. + * Process the auxtrace queue if the timestamp of element from heap is + * lower than timestamp from entry in perf record. + * + * Update the timestamp of the auxtrace heap with the timestamp + * of last processed entry from the auxtrace buffer. + */ +static int powerpc_vpadtl_process_queues(struct powerpc_vpadtl *vpa, u64 timestamp) +{ + unsigned int queue_nr; + u64 ts; + int ret; + + while (1) { + struct auxtrace_queue *queue; + struct powerpc_vpadtl_queue *vpaq; + + if (!vpa->heap.heap_cnt) + return 0; + + if (vpa->heap.heap_array[0].ordinal >= timestamp) + return 0; + + queue_nr = vpa->heap.heap_array[0].queue_nr; + queue = &vpa->queues.queue_array[queue_nr]; + vpaq = queue->priv; + + auxtrace_heap__pop(&vpa->heap); + + if (vpa->heap.heap_cnt) { + ts = vpa->heap.heap_array[0].ordinal + 1; + if (ts > timestamp) + ts = timestamp; + } else { + ts = timestamp; + } + + ret = powerpc_vpadtl_run_decoder(vpaq, &ts); + if (ret < 0) { + auxtrace_heap__add(&vpa->heap, queue_nr, ts); + return ret; + } + + if (!ret) { + ret = auxtrace_heap__add(&vpa->heap, queue_nr, ts); + if (ret < 0) + return ret; + } else { + vpaq->on_heap = false; + } + } + return 0; +} + +static struct powerpc_vpadtl_queue *powerpc_vpadtl__alloc_queue(struct powerpc_vpadtl *vpa, + unsigned int queue_nr) +{ + struct powerpc_vpadtl_queue *vpaq; + + vpaq = zalloc(sizeof(*vpaq)); + if (!vpaq) + return NULL; + + vpaq->vpa = vpa; + vpaq->queue_nr = queue_nr; + + return vpaq; +} + +/* + * When the Dispatch Trace Log data is collected along with other events + * like sched tracepoint events, it needs to be correlated and present + * interleaved along with these events. Perf events can be collected + * parallely across the CPUs. + * + * An auxtrace_queue is created for each CPU. Data within each queue is in + * increasing order of timestamp. Allocate and setup auxtrace queues here. + * All auxtrace queues is maintained in auxtrace heap in the increasing order + * of timestamp. So always the lowest timestamp (entries to be processed first) + * is on top of the heap. + * + * To add to auxtrace heap, fetch the timestamp from first DTL entry + * for each of the queue. + */ +static int powerpc_vpadtl__setup_queue(struct powerpc_vpadtl *vpa, + struct auxtrace_queue *queue, + unsigned int queue_nr) +{ + struct powerpc_vpadtl_queue *vpaq = queue->priv; + + if (list_empty(&queue->head) || vpaq) + return 0; + + vpaq = powerpc_vpadtl__alloc_queue(vpa, queue_nr); + if (!vpaq) + return -ENOMEM; + + queue->priv = vpaq; + + if (queue->cpu != -1) + vpaq->cpu = queue->cpu; + + if (!vpaq->on_heap) { + int ret; +retry: + ret = powerpc_vpadtl_decode(vpaq); + if (!ret) + return 0; + + if (ret < 0) + goto retry; + + vpaq->timestamp = powerpc_vpadtl_timestamp(vpaq); + + ret = auxtrace_heap__add(&vpa->heap, queue_nr, vpaq->timestamp); + if (ret) + return ret; + vpaq->on_heap = true; + } + + return 0; +} + +static int powerpc_vpadtl__setup_queues(struct powerpc_vpadtl *vpa) +{ + unsigned int i; + int ret; + + for (i = 0; i < vpa->queues.nr_queues; i++) { + ret = powerpc_vpadtl__setup_queue(vpa, &vpa->queues.queue_array[i], i); + if (ret) + return ret; + } + + return 0; +} + +static int powerpc_vpadtl__update_queues(struct powerpc_vpadtl *vpa) +{ + if (vpa->queues.new_data) { + vpa->queues.new_data = false; + return powerpc_vpadtl__setup_queues(vpa); + } + + return 0; +} + +static int powerpc_vpadtl_process_event(struct perf_session *session, + union perf_event *event __maybe_unused, + struct perf_sample *sample, + const struct perf_tool *tool) +{ + struct powerpc_vpadtl *vpa = session_to_vpa(session); + int err = 0; + + if (dump_trace) + return 0; + + if (!tool->ordered_events) { + pr_err("VPA requires ordered events\n"); + return -EINVAL; + } + + if (sample->time) { + err = powerpc_vpadtl__update_queues(vpa); + if (err) + return err; + + err = powerpc_vpadtl_process_queues(vpa, sample->time); + } + + return err; +} + +/* + * Process PERF_RECORD_AUXTRACE records + */ +static int powerpc_vpadtl_process_auxtrace_event(struct perf_session *session, + union perf_event *event, + const struct perf_tool *tool __maybe_unused) +{ + struct powerpc_vpadtl *vpa = session_to_vpa(session); + struct auxtrace_buffer *buffer; + int fd = perf_data__fd(session->data); + off_t data_offset; + int err; + + if (!dump_trace) + return 0; + + if (perf_data__is_pipe(session->data)) { + data_offset = 0; + } else { + data_offset = lseek(fd, 0, SEEK_CUR); + if (data_offset == -1) + return -errno; + } + + err = auxtrace_queues__add_event(&vpa->queues, session, event, + data_offset, &buffer); + + if (err) + return err; + + /* Dump here now we have copied a piped trace out of the pipe */ + if (auxtrace_buffer__get_data(buffer, fd)) { + powerpc_vpadtl_dump_event(vpa, buffer->data, buffer->size); + auxtrace_buffer__put_data(buffer); + } + + return 0; +} + +static int powerpc_vpadtl_flush(struct perf_session *session __maybe_unused, + const struct perf_tool *tool __maybe_unused) +{ + return 0; +} + +static void powerpc_vpadtl_free_events(struct perf_session *session) +{ + struct powerpc_vpadtl *vpa = session_to_vpa(session); + struct auxtrace_queues *queues = &vpa->queues; + + for (unsigned int i = 0; i < queues->nr_queues; i++) + zfree(&queues->queue_array[i].priv); + + auxtrace_queues__free(queues); +} + +static void powerpc_vpadtl_free(struct perf_session *session) +{ + struct powerpc_vpadtl *vpa = session_to_vpa(session); + + auxtrace_heap__free(&vpa->heap); + powerpc_vpadtl_free_events(session); + session->auxtrace = NULL; + free(vpa); +} + +static const char * const powerpc_vpadtl_info_fmts[] = { + [POWERPC_VPADTL_TYPE] = " PMU Type %"PRId64"\n", +}; + +static void powerpc_vpadtl_print_info(__u64 *arr) +{ + if (!dump_trace) + return; + + fprintf(stdout, powerpc_vpadtl_info_fmts[POWERPC_VPADTL_TYPE], arr[POWERPC_VPADTL_TYPE]); +} + +static void set_event_name(struct evlist *evlist, u64 id, + const char *name) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.id && evsel->core.id[0] == id) { + if (evsel->name) + zfree(&evsel->name); + evsel->name = strdup(name); + break; + } + } +} + +static int +powerpc_vpadtl_synth_events(struct powerpc_vpadtl *vpa, struct perf_session *session) +{ + struct evlist *evlist = session->evlist; + struct evsel *evsel; + struct perf_event_attr attr; + bool found = false; + u64 id; + int err; + + evlist__for_each_entry(evlist, evsel) { + if (strstarts(evsel->name, "vpa_dtl")) { + found = true; + break; + } + } + + if (!found) { + pr_debug("No selected events with VPA trace data\n"); + return 0; + } + + memset(&attr, 0, sizeof(struct perf_event_attr)); + attr.size = sizeof(struct perf_event_attr); + attr.sample_type = evsel->core.attr.sample_type; + attr.sample_id_all = evsel->core.attr.sample_id_all; + attr.type = PERF_TYPE_SYNTH; + attr.config = PERF_SYNTH_POWERPC_VPA_DTL; + + /* create new id val to be a fixed offset from evsel id */ + id = auxtrace_synth_id_range_start(evsel); + + err = perf_session__deliver_synth_attr_event(session, &attr, id); + if (err) + return err; + + vpa->sample_id = id; + set_event_name(evlist, id, "vpa-dtl"); + + return 0; +} + +/* + * Process the PERF_RECORD_AUXTRACE_INFO records and setup + * the infrastructure to process auxtrace events. PERF_RECORD_AUXTRACE_INFO + * is processed first since it is of type perf_user_event_type. + * Initialise the aux buffer queues using auxtrace_queues__init(). + * auxtrace_queue is created for each CPU. + */ +int powerpc_vpadtl_process_auxtrace_info(union perf_event *event, + struct perf_session *session) +{ + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; + size_t min_sz = sizeof(u64) * POWERPC_VPADTL_TYPE; + struct powerpc_vpadtl *vpa; + int err; + + if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) + + min_sz) + return -EINVAL; + + vpa = zalloc(sizeof(struct powerpc_vpadtl)); + if (!vpa) + return -ENOMEM; + + err = auxtrace_queues__init(&vpa->queues); + if (err) + goto err_free; + + vpa->session = session; + vpa->machine = &session->machines.host; /* No kvm support */ + vpa->auxtrace_type = auxtrace_info->type; + vpa->pmu_type = auxtrace_info->priv[POWERPC_VPADTL_TYPE]; + + vpa->auxtrace.process_event = powerpc_vpadtl_process_event; + vpa->auxtrace.process_auxtrace_event = powerpc_vpadtl_process_auxtrace_event; + vpa->auxtrace.flush_events = powerpc_vpadtl_flush; + vpa->auxtrace.free_events = powerpc_vpadtl_free_events; + vpa->auxtrace.free = powerpc_vpadtl_free; + session->auxtrace = &vpa->auxtrace; + + powerpc_vpadtl_print_info(&auxtrace_info->priv[0]); + + if (dump_trace) + return 0; + + err = powerpc_vpadtl_synth_events(vpa, session); + if (err) + goto err_free_queues; + + err = auxtrace_queues__process_index(&vpa->queues, session); + if (err) + goto err_free_queues; + + return 0; + +err_free_queues: + auxtrace_queues__free(&vpa->queues); + session->auxtrace = NULL; + +err_free: + free(vpa); + return err; +} diff --git a/tools/perf/util/powerpc-vpadtl.h b/tools/perf/util/powerpc-vpadtl.h new file mode 100644 index 000000000000..ca809660b9bb --- /dev/null +++ b/tools/perf/util/powerpc-vpadtl.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * VPA DTL PMU Support + */ + +#ifndef INCLUDE__PERF_POWERPC_VPADTL_H__ +#define INCLUDE__PERF_POWERPC_VPADTL_H__ + +enum { + POWERPC_VPADTL_TYPE, + VPADTL_AUXTRACE_PRIV_MAX, +}; + +#define VPADTL_AUXTRACE_PRIV_SIZE (VPADTL_AUXTRACE_PRIV_MAX * sizeof(u64)) + +union perf_event; +struct perf_session; +struct perf_pmu; + +int powerpc_vpadtl_process_auxtrace_info(union perf_event *event, + struct perf_session *session); + +#endif diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index a786cbfb0ff5..cb27e2898aa0 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -44,97 +44,6 @@ static const char * const event_type_descriptors[] = { "Hardware breakpoint", }; -/* - * Print the events from <debugfs_mount_point>/tracing/events - */ -void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unused, void *print_state __maybe_unused) -{ - char *events_path = get_tracing_file("events"); - int events_fd = open(events_path, O_PATH); - struct dirent **sys_namelist = NULL; - int sys_items; - - if (events_fd < 0) { - pr_err("Error: failed to open tracing events directory\n"); - pr_err("%s: %s\n", events_path, strerror(errno)); - return; - } - put_tracing_file(events_path); - - sys_items = tracing_events__scandir_alphasort(&sys_namelist); - - for (int i = 0; i < sys_items; i++) { - struct dirent *sys_dirent = sys_namelist[i]; - struct dirent **evt_namelist = NULL; - int dir_fd; - int evt_items; - - if (sys_dirent->d_type != DT_DIR || - !strcmp(sys_dirent->d_name, ".") || - !strcmp(sys_dirent->d_name, "..")) - goto next_sys; - - dir_fd = openat(events_fd, sys_dirent->d_name, O_PATH); - if (dir_fd < 0) - goto next_sys; - - evt_items = scandirat(events_fd, sys_dirent->d_name, &evt_namelist, NULL, alphasort); - for (int j = 0; j < evt_items; j++) { - /* - * Buffer sized at twice the max filename length + 1 - * separator + 1 \0 terminator. - */ - char buf[NAME_MAX * 2 + 2]; - /* 16 possible hex digits and 22 other characters and \0. */ - char encoding[16 + 22]; - struct dirent *evt_dirent = evt_namelist[j]; - struct io id; - __u64 config; - - if (evt_dirent->d_type != DT_DIR || - !strcmp(evt_dirent->d_name, ".") || - !strcmp(evt_dirent->d_name, "..")) - goto next_evt; - - snprintf(buf, sizeof(buf), "%s/id", evt_dirent->d_name); - io__init(&id, openat(dir_fd, buf, O_RDONLY), buf, sizeof(buf)); - - if (id.fd < 0) - goto next_evt; - - if (io__get_dec(&id, &config) < 0) { - close(id.fd); - goto next_evt; - } - close(id.fd); - - snprintf(buf, sizeof(buf), "%s:%s", - sys_dirent->d_name, evt_dirent->d_name); - snprintf(encoding, sizeof(encoding), "tracepoint/config=0x%llx/", config); - print_cb->print_event(print_state, - /*topic=*/NULL, - /*pmu_name=*/NULL, /* really "tracepoint" */ - /*event_name=*/buf, - /*event_alias=*/NULL, - /*scale_unit=*/NULL, - /*deprecated=*/false, - "Tracepoint event", - /*desc=*/NULL, - /*long_desc=*/NULL, - encoding); -next_evt: - free(evt_namelist[j]); - } - close(dir_fd); - free(evt_namelist); -next_sys: - free(sys_namelist[i]); - } - - free(sys_namelist); - close(events_fd); -} - void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) { struct strlist *bidlist, *sdtlist; @@ -177,7 +86,7 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) strlist__for_each_entry(sdt_name, sdtlist) { bool show_detail = false; - char *bid = strchr(sdt_name->s, '@'); + char *bid = (char *)strchr(sdt_name->s, '@'); char *evt_name = NULL; if (bid) @@ -188,14 +97,9 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) } else { next_sdt_name = strlist__next(sdt_name); if (next_sdt_name) { - char *bid2 = strchr(next_sdt_name->s, '@'); - - if (bid2) - *bid2 = '\0'; - if (strcmp(sdt_name->s, next_sdt_name->s) == 0) - show_detail = true; - if (bid2) - *bid2 = '@'; + const char *bid2 = strchrnul(next_sdt_name->s, '@'); + + show_detail = strncmp(sdt_name->s, next_sdt_name->s, bid2 - next_sdt_name->s) == 0; } } last_sdt_name = sdt_name->s; @@ -212,6 +116,7 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) print_cb->print_event(print_state, /*topic=*/NULL, /*pmu_name=*/NULL, + PERF_TYPE_TRACEPOINT, evt_name ?: sdt_name->s, /*event_alias=*/NULL, /*deprecated=*/false, @@ -268,6 +173,7 @@ bool is_event_supported(u8 type, u64 config) ret = evsel__open(evsel, NULL, tmap) >= 0; } + evsel__close(evsel); evsel__delete(evsel); } @@ -275,109 +181,137 @@ bool is_event_supported(u8 type, u64 config) return ret; } -int print_hwcache_events(const struct print_callbacks *print_cb, void *print_state) +/** struct mep - RB-tree node for building printing information. */ +struct mep { + /** nd - RB-tree element. */ + struct rb_node nd; + /** @metric_group: Owned metric group name, separated others with ';'. */ + char *metric_group; + const char *metric_name; + const char *metric_desc; + const char *metric_long_desc; + const char *metric_expr; + const char *metric_threshold; + const char *metric_unit; + const char *pmu_name; +}; + +static int mep_cmp(struct rb_node *rb_node, const void *entry) { - struct perf_pmu *pmu = NULL; - const char *event_type_descriptor = event_type_descriptors[PERF_TYPE_HW_CACHE]; + struct mep *a = container_of(rb_node, struct mep, nd); + struct mep *b = (struct mep *)entry; + int ret; - /* - * Only print core PMUs, skipping uncore for performance and - * PERF_TYPE_SOFTWARE that can succeed in opening legacy cache evenst. - */ - while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { - if (pmu->is_uncore || pmu->type == PERF_TYPE_SOFTWARE) - continue; + ret = strcmp(a->metric_group, b->metric_group); + if (ret) + return ret; - for (int type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { - for (int op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { - /* skip invalid cache type */ - if (!evsel__is_cache_op_valid(type, op)) - continue; - - for (int res = 0; res < PERF_COUNT_HW_CACHE_RESULT_MAX; res++) { - char name[64]; - char alias_name[128]; - __u64 config; - int ret; - - __evsel__hw_cache_type_op_res_name(type, op, res, - name, sizeof(name)); - - ret = parse_events__decode_legacy_cache(name, pmu->type, - &config); - if (ret || !is_event_supported(PERF_TYPE_HW_CACHE, config)) - continue; - snprintf(alias_name, sizeof(alias_name), "%s/%s/", - pmu->name, name); - print_cb->print_event(print_state, - "cache", - pmu->name, - name, - alias_name, - /*scale_unit=*/NULL, - /*deprecated=*/false, - event_type_descriptor, - /*desc=*/NULL, - /*long_desc=*/NULL, - /*encoding_desc=*/NULL); - } - } - } - } - return 0; + return strcmp(a->metric_name, b->metric_name); } -void print_symbol_events(const struct print_callbacks *print_cb, void *print_state, - unsigned int type, const struct event_symbol *syms, - unsigned int max) +static struct rb_node *mep_new(struct rblist *rl __maybe_unused, const void *entry) { - struct strlist *evt_name_list = strlist__new(NULL, NULL); - struct str_node *nd; + struct mep *me = malloc(sizeof(struct mep)); - if (!evt_name_list) { - pr_debug("Failed to allocate new strlist for symbol events\n"); - return; - } - for (unsigned int i = 0; i < max; i++) { - /* - * New attr.config still not supported here, the latest - * example was PERF_COUNT_SW_CGROUP_SWITCHES - */ - if (syms[i].symbol == NULL) - continue; + if (!me) + return NULL; - if (!is_event_supported(type, i)) - continue; + memcpy(me, entry, sizeof(struct mep)); + return &me->nd; +} - if (strlen(syms[i].alias)) { - char name[MAX_NAME_LEN]; +static void mep_delete(struct rblist *rl __maybe_unused, + struct rb_node *nd) +{ + struct mep *me = container_of(nd, struct mep, nd); - snprintf(name, MAX_NAME_LEN, "%s OR %s", syms[i].symbol, syms[i].alias); - strlist__add(evt_name_list, name); - } else - strlist__add(evt_name_list, syms[i].symbol); - } + zfree(&me->metric_group); + free(me); +} - strlist__for_each_entry(nd, evt_name_list) { - char *alias = strstr(nd->s, " OR "); +static struct mep *mep_lookup(struct rblist *groups, const char *metric_group, + const char *metric_name) +{ + struct rb_node *nd; + struct mep me = { + .metric_group = strdup(metric_group), + .metric_name = metric_name, + }; + nd = rblist__find(groups, &me); + if (nd) { + free(me.metric_group); + return container_of(nd, struct mep, nd); + } + rblist__add_node(groups, &me); + nd = rblist__find(groups, &me); + if (nd) + return container_of(nd, struct mep, nd); + return NULL; +} - if (alias) { - *alias = '\0'; - alias += 4; +static int metricgroup__add_to_mep_groups_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *vdata) +{ + struct rblist *groups = vdata; + const char *g; + char *omg, *mg; + + mg = strdup(pm->metric_group ?: pm->metric_name); + if (!mg) + return -ENOMEM; + omg = mg; + while ((g = strsep(&mg, ";")) != NULL) { + struct mep *me; + + g = skip_spaces(g); + if (strlen(g)) + me = mep_lookup(groups, g, pm->metric_name); + else + me = mep_lookup(groups, pm->metric_name, pm->metric_name); + + if (me) { + me->metric_desc = pm->desc; + me->metric_long_desc = pm->long_desc; + me->metric_expr = pm->metric_expr; + me->metric_threshold = pm->metric_threshold; + me->metric_unit = pm->unit; + me->pmu_name = pm->pmu; } - print_cb->print_event(print_state, - /*topic=*/NULL, - /*pmu_name=*/NULL, - nd->s, - alias, - /*scale_unit=*/NULL, - /*deprecated=*/false, - event_type_descriptors[type], - /*desc=*/NULL, - /*long_desc=*/NULL, - /*encoding_desc=*/NULL); } - strlist__delete(evt_name_list); + free(omg); + + return 0; +} + +void metricgroup__print(const struct print_callbacks *print_cb, void *print_state) +{ + struct rblist groups; + struct rb_node *node, *next; + const struct pmu_metrics_table *table = pmu_metrics_table__find(); + + rblist__init(&groups); + groups.node_new = mep_new; + groups.node_cmp = mep_cmp; + groups.node_delete = mep_delete; + + metricgroup__for_each_metric(table, metricgroup__add_to_mep_groups_callback, &groups); + + for (node = rb_first_cached(&groups.entries); node; node = next) { + struct mep *me = container_of(node, struct mep, nd); + + print_cb->print_metric(print_state, + me->metric_group, + me->metric_name, + me->metric_desc, + me->metric_long_desc, + me->metric_expr, + me->metric_threshold, + me->metric_unit, + me->pmu_name); + next = rb_next(node); + rblist__remove_node(&groups, node); + } } /* @@ -385,18 +319,12 @@ void print_symbol_events(const struct print_callbacks *print_cb, void *print_sta */ void print_events(const struct print_callbacks *print_cb, void *print_state) { - print_symbol_events(print_cb, print_state, PERF_TYPE_HARDWARE, - event_symbols_hw, PERF_COUNT_HW_MAX); - print_symbol_events(print_cb, print_state, PERF_TYPE_SOFTWARE, - event_symbols_sw, PERF_COUNT_SW_MAX); - - print_hwcache_events(print_cb, print_state); - perf_pmus__print_pmu_events(print_cb, print_state); print_cb->print_event(print_state, /*topic=*/NULL, /*pmu_name=*/NULL, + PERF_TYPE_RAW, "rNNN", /*event_alias=*/NULL, /*scale_unit=*/NULL, @@ -411,6 +339,7 @@ void print_events(const struct print_callbacks *print_cb, void *print_state) print_cb->print_event(print_state, /*topic=*/NULL, /*pmu_name=*/NULL, + PERF_TYPE_BREAKPOINT, "mem:<addr>[/len][:access]", /*scale_unit=*/NULL, /*event_alias=*/NULL, @@ -420,8 +349,6 @@ void print_events(const struct print_callbacks *print_cb, void *print_state) /*long_desc=*/NULL, /*encoding_desc=*/NULL); - print_tracepoint_events(print_cb, print_state); - print_sdt_events(print_cb, print_state); metricgroup__print(print_cb, print_state); diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h index 445efa1636c1..eabba5d4a1fd 100644 --- a/tools/perf/util/print-events.h +++ b/tools/perf/util/print-events.h @@ -12,7 +12,7 @@ struct print_callbacks { void (*print_start)(void *print_state); void (*print_end)(void *print_state); void (*print_event)(void *print_state, const char *topic, - const char *pmu_name, + const char *pmu_name, u32 pmu_type, const char *event_name, const char *event_alias, const char *scale_unit, bool deprecated, const char *event_type_desc, @@ -25,18 +25,15 @@ struct print_callbacks { const char *long_desc, const char *expr, const char *threshold, - const char *unit); + const char *unit, + const char *pmu_name); bool (*skip_duplicate_pmus)(void *print_state); }; /** Print all events, the default when no options are specified. */ void print_events(const struct print_callbacks *print_cb, void *print_state); -int print_hwcache_events(const struct print_callbacks *print_cb, void *print_state); void print_sdt_events(const struct print_callbacks *print_cb, void *print_state); -void print_symbol_events(const struct print_callbacks *print_cb, void *print_state, - unsigned int type, const struct event_symbol *syms, - unsigned int max); -void print_tracepoint_events(const struct print_callbacks *print_cb, void *print_state); +void metricgroup__print(const struct print_callbacks *print_cb, void *print_state); bool is_event_supported(u8 type, u64 config); #endif /* __PERF_PRINT_EVENTS_H */ diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c index a33a7726422d..02e6fbb8ca04 100644 --- a/tools/perf/util/print_insn.c +++ b/tools/perf/util/print_insn.c @@ -7,6 +7,7 @@ #include <inttypes.h> #include <string.h> #include <stdbool.h> +#include "capstone.h" #include "debug.h" #include "sample.h" #include "symbol.h" @@ -29,84 +30,6 @@ size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp) return printed; } -#ifdef HAVE_LIBCAPSTONE_SUPPORT -#include <capstone/capstone.h> - -int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style); - -int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style) -{ - cs_arch arch; - cs_mode mode; - - if (machine__is(machine, "x86_64") && is64) { - arch = CS_ARCH_X86; - mode = CS_MODE_64; - } else if (machine__normalized_is(machine, "x86")) { - arch = CS_ARCH_X86; - mode = CS_MODE_32; - } else if (machine__normalized_is(machine, "arm64")) { - arch = CS_ARCH_ARM64; - mode = CS_MODE_ARM; - } else if (machine__normalized_is(machine, "arm")) { - arch = CS_ARCH_ARM; - mode = CS_MODE_ARM + CS_MODE_V8; - } else if (machine__normalized_is(machine, "s390")) { - arch = CS_ARCH_SYSZ; - mode = CS_MODE_BIG_ENDIAN; - } else { - return -1; - } - - if (cs_open(arch, mode, cs_handle) != CS_ERR_OK) { - pr_warning_once("cs_open failed\n"); - return -1; - } - - if (machine__normalized_is(machine, "x86")) { - /* - * In case of using capstone_init while symbol__disassemble - * setting CS_OPT_SYNTAX_ATT depends if disassembler_style opts - * is set via annotation args - */ - if (disassembler_style) - cs_option(*cs_handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT); - /* - * Resolving address operands to symbols is implemented - * on x86 by investigating instruction details. - */ - cs_option(*cs_handle, CS_OPT_DETAIL, CS_OPT_ON); - } - - return 0; -} - -static size_t print_insn_x86(struct thread *thread, u8 cpumode, cs_insn *insn, - int print_opts, FILE *fp) -{ - struct addr_location al; - size_t printed = 0; - - if (insn->detail && insn->detail->x86.op_count == 1) { - cs_x86_op *op = &insn->detail->x86.operands[0]; - - addr_location__init(&al); - if (op->type == X86_OP_IMM && - thread__find_symbol(thread, cpumode, op->imm, &al)) { - printed += fprintf(fp, "%s ", insn[0].mnemonic); - printed += symbol__fprintf_symname_offs(al.sym, &al, fp); - if (print_opts & PRINT_INSN_IMM_HEX) - printed += fprintf(fp, " [%#" PRIx64 "]", op->imm); - addr_location__exit(&al); - return printed; - } - addr_location__exit(&al); - } - - printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str); - return printed; -} - static bool is64bitip(struct machine *machine, struct addr_location *al) { const struct dso *dso = al->map ? map__dso(al->map) : NULL; @@ -123,32 +46,8 @@ ssize_t fprintf_insn_asm(struct machine *machine, struct thread *thread, u8 cpum bool is64bit, const uint8_t *code, size_t code_size, uint64_t ip, int *lenp, int print_opts, FILE *fp) { - size_t printed; - cs_insn *insn; - csh cs_handle; - size_t count; - int ret; - - /* TODO: Try to initiate capstone only once but need a proper place. */ - ret = capstone_init(machine, &cs_handle, is64bit, true); - if (ret < 0) - return ret; - - count = cs_disasm(cs_handle, code, code_size, ip, 1, &insn); - if (count > 0) { - if (machine__normalized_is(machine, "x86")) - printed = print_insn_x86(thread, cpumode, &insn[0], print_opts, fp); - else - printed = fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str); - if (lenp) - *lenp = insn->size; - cs_free(insn, count); - } else { - printed = -1; - } - - cs_close(&cs_handle); - return printed; + return capstone__fprintf_insn_asm(machine, thread, cpumode, is64bit, code, code_size, + ip, lenp, print_opts, fp); } size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread, @@ -166,13 +65,3 @@ size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *threa return printed; } -#else -size_t sample__fprintf_insn_asm(struct perf_sample *sample __maybe_unused, - struct thread *thread __maybe_unused, - struct machine *machine __maybe_unused, - FILE *fp __maybe_unused, - struct addr_location *al __maybe_unused) -{ - return 0; -} -#endif diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 307ad6242a4e..34b4badd2c14 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -11,7 +11,6 @@ #include <sys/stat.h> #include <fcntl.h> #include <errno.h> -#include <libgen.h> #include <stdio.h> #include <unistd.h> #include <stdlib.h> @@ -75,12 +74,14 @@ int e_snprintf(char *str, size_t size, const char *format, ...) } static struct machine *host_machine; +static struct perf_env host_env; /* Initialize symbol maps and path of vmlinux/modules */ int init_probe_symbol_maps(bool user_only) { int ret; + perf_env__init(&host_env); symbol_conf.allow_aliases = true; ret = symbol__init(NULL); if (ret < 0) { @@ -94,7 +95,7 @@ int init_probe_symbol_maps(bool user_only) if (symbol_conf.vmlinux_name) pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name); - host_machine = machine__new_host(); + host_machine = machine__new_host(&host_env); if (!host_machine) { pr_debug("machine__new_host() failed.\n"); symbol__exit(); @@ -111,6 +112,7 @@ void exit_probe_symbol_maps(void) machine__delete(host_machine); host_machine = NULL; symbol__exit(); + perf_env__exit(&host_env); } static struct ref_reloc_sym *kernel_get_ref_reloc_sym(struct map **pmap) @@ -226,7 +228,7 @@ static int convert_exec_to_group(const char *exec, char **result) if (!exec_copy) return -ENOMEM; - ptr1 = basename(exec_copy); + ptr1 = (char *)perf_basename(exec_copy); if (!ptr1) { ret = -EINVAL; goto out; @@ -502,7 +504,7 @@ static struct debuginfo *open_from_debuginfod(struct dso *dso, struct nsinfo *ns if (!c) return NULL; - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); fd = debuginfod_find_debuginfo(c, (const unsigned char *)sbuild_id, 0, &path); if (fd >= 0) @@ -1063,7 +1065,6 @@ static int sprint_line_description(char *sbuf, size_t size, struct line_range *l static int __show_line_range(struct line_range *lr, const char *module, bool user) { - struct build_id bid; int l = 1; struct int_node *ln; struct debuginfo *dinfo; @@ -1088,8 +1089,10 @@ static int __show_line_range(struct line_range *lr, const char *module, ret = -ENOENT; } if (dinfo->build_id) { + struct build_id bid; + build_id__init(&bid, dinfo->build_id, BUILD_ID_SIZE); - build_id__sprintf(&bid, sbuild_id); + build_id__snprintf(&bid, sbuild_id, sizeof(sbuild_id)); } debuginfo__delete(dinfo); if (ret == 0 || ret == -ENOENT) { @@ -1846,7 +1849,7 @@ int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev) /* Copy arguments and ensure return probe has no C argument */ pev->nargs = argc - 1; - pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs); + pev->args = calloc(pev->nargs, sizeof(struct perf_probe_arg)); if (pev->args == NULL) { ret = -ENOMEM; goto out; @@ -1996,7 +1999,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) } tev->nargs = argc - 2; - tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); + tev->args = calloc(tev->nargs, sizeof(struct probe_trace_arg)); if (tev->args == NULL) { ret = -ENOMEM; goto out; @@ -2369,7 +2372,7 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev, /* Convert trace_arg to probe_arg */ pev->nargs = tev->nargs; - pev->args = zalloc(sizeof(struct perf_probe_arg) * pev->nargs); + pev->args = calloc(pev->nargs, sizeof(struct perf_probe_arg)); if (pev->args == NULL) return -ENOMEM; for (i = 0; i < tev->nargs && ret >= 0; i++) { @@ -2415,6 +2418,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev) } pev->nargs = 0; zfree(&pev->args); + nsinfo__zput(pev->nsi); } #define strdup_or_goto(str, label) \ @@ -2475,7 +2479,7 @@ int perf_probe_event__copy(struct perf_probe_event *dst, if (perf_probe_point__copy(&dst->point, &src->point) < 0) goto out_err; - dst->args = zalloc(sizeof(struct perf_probe_arg) * src->nargs); + dst->args = calloc(src->nargs, sizeof(struct perf_probe_arg)); if (!dst->args) goto out_err; dst->nargs = src->nargs; @@ -3174,7 +3178,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } /* Setup result trace-probe-events */ - *tevs = zalloc(sizeof(*tev) * num_matched_functions); + *tevs = calloc(num_matched_functions, sizeof(*tev)); if (!*tevs) { ret = -ENOMEM; goto out; @@ -3246,8 +3250,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, tev->uprobes = pev->uprobes; tev->nargs = pev->nargs; if (tev->nargs) { - tev->args = zalloc(sizeof(struct probe_trace_arg) * - tev->nargs); + tev->args = calloc(tev->nargs, sizeof(struct probe_trace_arg)); if (tev->args == NULL) goto nomem_out; } @@ -3358,7 +3361,7 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, } tev->nargs = pev->nargs; - tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); + tev->args = calloc(tev->nargs, sizeof(struct probe_trace_arg)); if (!tev->args) goto errout; @@ -3544,7 +3547,7 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev, goto out; } - *tevs = zalloc(ret * sizeof(*tev)); + *tevs = calloc(ret, sizeof(*tev)); if (!*tevs) { ret = -ENOMEM; goto out; @@ -3763,12 +3766,11 @@ void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs) /* Loop 3: cleanup and free trace events */ for (i = 0; i < npevs; i++) { pev = &pevs[i]; - for (j = 0; j < pevs[i].ntevs; j++) - clear_probe_trace_event(&pevs[i].tevs[j]); - zfree(&pevs[i].tevs); - pevs[i].ntevs = 0; - nsinfo__zput(pev->nsi); - clear_perf_probe_event(&pevs[i]); + for (j = 0; j < pev->ntevs; j++) + clear_probe_trace_event(&pev->tevs[j]); + zfree(&pev->tevs); + pev->ntevs = 0; + clear_perf_probe_event(pev); } } diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index ec8ac242fedb..4032572cbf55 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -28,6 +28,7 @@ #include "session.h" #include "perf_regs.h" #include "string2.h" +#include "dwarf-regs.h" /* 4096 - 2 ('\n' + '\0') */ #define MAX_CMDLEN 4094 @@ -413,7 +414,7 @@ int probe_cache_entry__get_event(struct probe_cache_entry *entry, if (ret > probe_conf.max_probes) return -E2BIG; - *tevs = zalloc(ret * sizeof(*tev)); + *tevs = calloc(ret, sizeof(*tev)); if (!*tevs) return -ENOMEM; @@ -448,10 +449,10 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target, if (!target || !strcmp(target, DSO__NAME_KALLSYMS)) { target = DSO__NAME_KALLSYMS; is_kallsyms = true; - ret = sysfs__sprintf_build_id("/", sbuildid); + ret = sysfs__snprintf_build_id("/", sbuildid, sizeof(sbuildid)); } else { nsinfo__mountns_enter(nsi, &nsc); - ret = filename__sprintf_build_id(target, sbuildid); + ret = filename__snprintf_build_id(target, sbuildid, sizeof(sbuildid)); nsinfo__mountns_exit(&nsc); } @@ -784,7 +785,7 @@ static int synthesize_sdt_probe_arg(struct strbuf *buf, int i, const char *arg) op = desc; } - ret = arch_sdt_arg_parse_op(op, &new_op); + ret = perf_sdt_arg_parse_op(EM_HOST, op, &new_op); if (ret < 0) goto error; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1e769b68da37..64328abeef8b 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -848,7 +848,6 @@ static int probe_point_lazy_walker(const char *fname, int lineno, /* Find probe points from lazy pattern */ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) { - struct build_id bid; char sbuild_id[SBUILD_ID_SIZE] = ""; int ret = 0; char *fpath; @@ -858,8 +857,10 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) comp_dir = cu_get_comp_dir(&pf->cu_die); if (pf->dbg->build_id) { + struct build_id bid; + build_id__init(&bid, pf->dbg->build_id, BUILD_ID_SIZE); - build_id__sprintf(&bid, sbuild_id); + build_id__snprintf(&bid, sbuild_id, sizeof(sbuild_id)); } ret = find_source_path(pf->fname, sbuild_id, comp_dir, &fpath); if (ret < 0) { @@ -973,6 +974,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) pr_debug("Matched function: %s [%lx]\n", dwarf_diename(sp_die), (unsigned long)dwarf_dieoffset(sp_die)); pf->fname = fname; + pf->abstrace_dieoffset = dwarf_dieoffset(sp_die); if (pp->line) { /* Function relative line */ dwarf_decl_line(sp_die, &pf->lno); pf->lno += pp->line; @@ -1179,6 +1181,8 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data) struct local_vars_finder *vf = data; struct probe_finder *pf = vf->pf; int tag; + Dwarf_Attribute attr; + Dwarf_Die var_die; tag = dwarf_tag(die_mem); if (tag == DW_TAG_formal_parameter || @@ -1196,10 +1200,22 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data) } } - if (dwarf_haspc(die_mem, vf->pf->addr)) + if (dwarf_haspc(die_mem, vf->pf->addr)) { + /* + * when DW_AT_entry_pc contains instruction address, + * also check if the DW_AT_abstract_origin of die_mem + * points to correct die. + */ + if (dwarf_attr(die_mem, DW_AT_abstract_origin, &attr)) { + dwarf_formref_die(&attr, &var_die); + if (pf->abstrace_dieoffset != dwarf_dieoffset(&var_die)) + goto out; + } return DIE_FIND_CB_CONTINUE; - else - return DIE_FIND_CB_SIBLING; + } + +out: + return DIE_FIND_CB_SIBLING; } static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf, @@ -1289,7 +1305,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) tev->point.offset); /* Expand special probe argument if exist */ - args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS); + args = calloc(MAX_PROBE_ARGS, sizeof(struct perf_probe_arg)); if (args == NULL) { ret = -ENOMEM; goto end; @@ -1300,7 +1316,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) goto end; tev->nargs = ret; - tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); + tev->args = calloc(tev->nargs, sizeof(struct probe_trace_arg)); if (tev->args == NULL) { ret = -ENOMEM; goto end; @@ -1377,7 +1393,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, int ret, i; /* Allocate result tevs array */ - *tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs); + *tevs = calloc(tf.max_tevs, sizeof(struct probe_trace_event)); if (*tevs == NULL) return -ENOMEM; @@ -1550,7 +1566,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg, int ret; /* Allocate result vls array */ - *vls = zalloc(sizeof(struct variable_list) * af.max_vls); + *vls = calloc(af.max_vls, sizeof(struct variable_list)); if (*vls == NULL) return -ENOMEM; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index dcf6cc1e1cbe..ecd6d937c592 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -63,6 +63,7 @@ struct probe_finder { const char *fname; /* Real file name */ Dwarf_Die cu_die; /* Current CU */ Dwarf_Die sp_die; + Dwarf_Off abstrace_dieoffset; struct intlist *lcache; /* Line cache for lazy match */ /* For variable searching */ diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index a1d1e4ef6257..141ffa129c69 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -63,20 +63,6 @@ void pstack__push(struct pstack *pstack, void *key) pstack->entries[pstack->top++] = key; } -void *pstack__pop(struct pstack *pstack) -{ - void *ret; - - if (pstack->top == 0) { - pr_err("%s: underflow!\n", __func__); - return NULL; - } - - ret = pstack->entries[--pstack->top]; - pstack->entries[pstack->top] = NULL; - return ret; -} - void *pstack__peek(struct pstack *pstack) { if (pstack->top == 0) diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h index 8729b8be061d..712051b8130f 100644 --- a/tools/perf/util/pstack.h +++ b/tools/perf/util/pstack.h @@ -10,7 +10,6 @@ void pstack__delete(struct pstack *pstack); bool pstack__empty(const struct pstack *pstack); void pstack__remove(struct pstack *pstack, void *key); void pstack__push(struct pstack *pstack, void *key); -void *pstack__pop(struct pstack *pstack); void *pstack__peek(struct pstack *pstack); #endif /* _PERF_PSTACK_ */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index b4bc57859f73..cc1019d29a5d 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -9,24 +9,23 @@ #include <event-parse.h> #endif #include <perf/mmap.h> +#include "callchain.h" +#include "counts.h" #include "evlist.h" #include "evsel.h" #include "event.h" +#include "expr.h" #include "print_binary.h" +#include "record.h" #include "strbuf.h" #include "thread_map.h" +#include "tp_pmu.h" #include "trace-event.h" +#include "metricgroup.h" #include "mmap.h" #include "util/sample.h" #include <internal/lib.h> -#define _PyUnicode_FromString(arg) \ - PyUnicode_FromString(arg) -#define _PyUnicode_FromFormat(...) \ - PyUnicode_FromFormat(__VA_ARGS__) -#define _PyLong_FromLong(arg) \ - PyLong_FromLong(arg) - PyMODINIT_FUNC PyInit_perf(void); #define member_def(type, member, ptype, help) \ @@ -47,7 +46,7 @@ struct pyrf_event { }; #define sample_members \ - sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \ + sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"), \ sample_member_def(sample_pid, pid, T_INT, "event pid"), \ sample_member_def(sample_tid, tid, T_INT, "event tid"), \ sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \ @@ -270,6 +269,12 @@ static PyMemberDef pyrf_sample_event__members[] = { { .name = NULL, }, }; +static void pyrf_sample_event__delete(struct pyrf_event *pevent) +{ + perf_sample__exit(&pevent->sample); + Py_TYPE(pevent)->tp_free((PyObject*)pevent); +} + static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent) { PyObject *ret; @@ -334,25 +339,26 @@ tracepoint_field(const struct pyrf_event *pe, struct tep_format_field *field) static PyObject* get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) { - const char *str = _PyUnicode_AsString(PyObject_Str(attr_name)); struct evsel *evsel = pevent->evsel; + struct tep_event *tp_format = evsel__tp_format(evsel); struct tep_format_field *field; - if (!evsel->tp_format) { - struct tep_event *tp_format; - - tp_format = trace_event__tp_format_id(evsel->core.attr.config); - if (IS_ERR_OR_NULL(tp_format)) - return NULL; + if (IS_ERR_OR_NULL(tp_format)) + return NULL; - evsel->tp_format = tp_format; - } + PyObject *obj = PyObject_Str(attr_name); + if (obj == NULL) + return NULL; - field = tep_find_any_field(evsel->tp_format, str); - if (!field) + const char *str = PyUnicode_AsUTF8(obj); + if (str == NULL) { + Py_DECREF(obj); return NULL; + } - return tracepoint_field(pevent, field); + field = tep_find_any_field(tp_format, str); + Py_DECREF(obj); + return field ? tracepoint_field(pevent, field) : NULL; } #endif /* HAVE_LIBTRACEEVENT */ @@ -428,6 +434,9 @@ static int pyrf_event__setup_types(void) pyrf_sample_event__type.tp_new = pyrf_context_switch_event__type.tp_new = pyrf_throttle_event__type.tp_new = PyType_GenericNew; + + pyrf_sample_event__type.tp_dealloc = (destructor)pyrf_sample_event__delete, + err = PyType_Ready(&pyrf_mmap_event__type); if (err < 0) goto out; @@ -478,8 +487,19 @@ static PyObject *pyrf_event__new(const union perf_event *event) if ((event->header.type < PERF_RECORD_MMAP || event->header.type > PERF_RECORD_SAMPLE) && !(event->header.type == PERF_RECORD_SWITCH || - event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)) + event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)) { + PyErr_Format(PyExc_TypeError, "Unexpected header type %u", + event->header.type); return NULL; + } + + // FIXME this better be dynamic or we need to parse everything + // before calling perf_mmap__consume(), including tracepoint fields. + if (sizeof(pevent->event) < event->header.size) { + PyErr_Format(PyExc_TypeError, "Unexpected event size: %zd < %u", + sizeof(pevent->event), event->header.size); + return NULL; + } ptype = pyrf_event__type[event->header.type]; pevent = PyObject_New(struct pyrf_event, ptype); @@ -527,8 +547,10 @@ static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i) { struct pyrf_cpu_map *pcpus = (void *)obj; - if (i >= perf_cpu_map__nr(pcpus->cpus)) + if (i >= perf_cpu_map__nr(pcpus->cpus)) { + PyErr_SetString(PyExc_IndexError, "Index out of range"); return NULL; + } return Py_BuildValue("i", perf_cpu_map__cpu(pcpus->cpus, i).cpu); } @@ -566,14 +588,14 @@ struct pyrf_thread_map { static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, PyObject *args, PyObject *kwargs) { - static char *kwlist[] = { "pid", "tid", "uid", NULL }; - int pid = -1, tid = -1, uid = UINT_MAX; + static char *kwlist[] = { "pid", "tid", NULL }; + int pid = -1, tid = -1; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iii", - kwlist, &pid, &tid, &uid)) + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", + kwlist, &pid, &tid)) return -1; - pthreads->threads = thread_map__new(pid, tid, uid); + pthreads->threads = thread_map__new(pid, tid); if (pthreads->threads == NULL) return -1; return 0; @@ -596,8 +618,10 @@ static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i) { struct pyrf_thread_map *pthreads = (void *)obj; - if (i >= perf_thread_map__nr(pthreads->threads)) + if (i >= perf_thread_map__nr(pthreads->threads)) { + PyErr_SetString(PyExc_IndexError, "Index out of range"); return NULL; + } return Py_BuildValue("i", perf_thread_map__pid(pthreads->threads, i)); } @@ -626,6 +650,295 @@ static int pyrf_thread_map__setup_types(void) return PyType_Ready(&pyrf_thread_map__type); } +/** + * A python wrapper for perf_pmus that are globally owned by the pmus.c code. + */ +struct pyrf_pmu { + PyObject_HEAD + + struct perf_pmu *pmu; +}; + +static void pyrf_pmu__delete(struct pyrf_pmu *ppmu) +{ + Py_TYPE(ppmu)->tp_free((PyObject *)ppmu); +} + +static PyObject *pyrf_pmu__name(PyObject *self) +{ + struct pyrf_pmu *ppmu = (void *)self; + + return PyUnicode_FromString(ppmu->pmu->name); +} + +static bool add_to_dict(PyObject *dict, const char *key, const char *value) +{ + PyObject *pkey, *pvalue; + bool ret; + + if (value == NULL) + return true; + + pkey = PyUnicode_FromString(key); + pvalue = PyUnicode_FromString(value); + + ret = pkey && pvalue && PyDict_SetItem(dict, pkey, pvalue) == 0; + Py_XDECREF(pkey); + Py_XDECREF(pvalue); + return ret; +} + +static int pyrf_pmu__events_cb(void *state, struct pmu_event_info *info) +{ + PyObject *py_list = state; + PyObject *dict = PyDict_New(); + + if (!dict) + return -ENOMEM; + + if (!add_to_dict(dict, "name", info->name) || + !add_to_dict(dict, "alias", info->alias) || + !add_to_dict(dict, "scale_unit", info->scale_unit) || + !add_to_dict(dict, "desc", info->desc) || + !add_to_dict(dict, "long_desc", info->long_desc) || + !add_to_dict(dict, "encoding_desc", info->encoding_desc) || + !add_to_dict(dict, "topic", info->topic) || + !add_to_dict(dict, "event_type_desc", info->event_type_desc) || + !add_to_dict(dict, "str", info->str) || + !add_to_dict(dict, "deprecated", info->deprecated ? "deprecated" : NULL) || + PyList_Append(py_list, dict) != 0) { + Py_DECREF(dict); + return -ENOMEM; + } + Py_DECREF(dict); + return 0; +} + +static PyObject *pyrf_pmu__events(PyObject *self) +{ + struct pyrf_pmu *ppmu = (void *)self; + PyObject *py_list = PyList_New(0); + int ret; + + if (!py_list) + return NULL; + + ret = perf_pmu__for_each_event(ppmu->pmu, + /*skip_duplicate_pmus=*/false, + py_list, + pyrf_pmu__events_cb); + if (ret) { + Py_DECREF(py_list); + errno = -ret; + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + return py_list; +} + +static PyObject *pyrf_pmu__repr(PyObject *self) +{ + struct pyrf_pmu *ppmu = (void *)self; + + return PyUnicode_FromFormat("pmu(%s)", ppmu->pmu->name); +} + +static const char pyrf_pmu__doc[] = PyDoc_STR("perf Performance Monitoring Unit (PMU) object."); + +static PyMethodDef pyrf_pmu__methods[] = { + { + .ml_name = "events", + .ml_meth = (PyCFunction)pyrf_pmu__events, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Returns a sequence of events encoded as a dictionaries.") + }, + { + .ml_name = "name", + .ml_meth = (PyCFunction)pyrf_pmu__name, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Name of the PMU including suffixes.") + }, + { .ml_name = NULL, } +}; + +/** The python type for a perf.pmu. */ +static PyTypeObject pyrf_pmu__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.pmu", + .tp_basicsize = sizeof(struct pyrf_pmu), + .tp_dealloc = (destructor)pyrf_pmu__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_pmu__doc, + .tp_methods = pyrf_pmu__methods, + .tp_str = pyrf_pmu__name, + .tp_repr = pyrf_pmu__repr, +}; + +static int pyrf_pmu__setup_types(void) +{ + pyrf_pmu__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_pmu__type); +} + + +/** A python iterator for pmus that has no equivalent in the C code. */ +struct pyrf_pmu_iterator { + PyObject_HEAD + struct perf_pmu *pmu; +}; + +static void pyrf_pmu_iterator__dealloc(struct pyrf_pmu_iterator *self) +{ + Py_TYPE(self)->tp_free((PyObject *) self); +} + +static PyObject *pyrf_pmu_iterator__new(PyTypeObject *type, PyObject *args __maybe_unused, + PyObject *kwds __maybe_unused) +{ + struct pyrf_pmu_iterator *itr = (void *)type->tp_alloc(type, 0); + + if (itr != NULL) + itr->pmu = perf_pmus__scan(/*pmu=*/NULL); + + return (PyObject *) itr; +} + +static PyObject *pyrf_pmu_iterator__iter(PyObject *self) +{ + Py_INCREF(self); + return self; +} + +static PyObject *pyrf_pmu_iterator__iternext(PyObject *self) +{ + struct pyrf_pmu_iterator *itr = (void *)self; + struct pyrf_pmu *ppmu; + + if (itr->pmu == NULL) { + PyErr_SetNone(PyExc_StopIteration); + return NULL; + } + // Create object to return. + ppmu = PyObject_New(struct pyrf_pmu, &pyrf_pmu__type); + if (ppmu) { + ppmu->pmu = itr->pmu; + // Advance iterator. + itr->pmu = perf_pmus__scan(itr->pmu); + } + return (PyObject *)ppmu; +} + +/** The python type for the PMU iterator. */ +static PyTypeObject pyrf_pmu_iterator__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "pmus.iterator", + .tp_doc = "Iterator for the pmus string sequence.", + .tp_basicsize = sizeof(struct pyrf_pmu_iterator), + .tp_itemsize = 0, + .tp_flags = Py_TPFLAGS_DEFAULT, + .tp_new = pyrf_pmu_iterator__new, + .tp_dealloc = (destructor) pyrf_pmu_iterator__dealloc, + .tp_iter = pyrf_pmu_iterator__iter, + .tp_iternext = pyrf_pmu_iterator__iternext, +}; + +static int pyrf_pmu_iterator__setup_types(void) +{ + return PyType_Ready(&pyrf_pmu_iterator__type); +} + +static PyObject *pyrf__pmus(PyObject *self, PyObject *args) +{ + // Calling the class creates an instance of the iterator. + return PyObject_CallObject((PyObject *) &pyrf_pmu_iterator__type, /*args=*/NULL); +} + +struct pyrf_counts_values { + PyObject_HEAD + + struct perf_counts_values values; +}; + +static const char pyrf_counts_values__doc[] = PyDoc_STR("perf counts values object."); + +static void pyrf_counts_values__delete(struct pyrf_counts_values *pcounts_values) +{ + Py_TYPE(pcounts_values)->tp_free((PyObject *)pcounts_values); +} + +#define counts_values_member_def(member, ptype, help) \ + { #member, ptype, \ + offsetof(struct pyrf_counts_values, values.member), \ + 0, help } + +static PyMemberDef pyrf_counts_values_members[] = { + counts_values_member_def(val, T_ULONG, "Value of event"), + counts_values_member_def(ena, T_ULONG, "Time for which enabled"), + counts_values_member_def(run, T_ULONG, "Time for which running"), + counts_values_member_def(id, T_ULONG, "Unique ID for an event"), + counts_values_member_def(lost, T_ULONG, "Num of lost samples"), + { .name = NULL, }, +}; + +static PyObject *pyrf_counts_values_get_values(struct pyrf_counts_values *self, void *closure) +{ + PyObject *vals = PyList_New(5); + + if (!vals) + return NULL; + for (int i = 0; i < 5; i++) + PyList_SetItem(vals, i, PyLong_FromLong(self->values.values[i])); + + return vals; +} + +static int pyrf_counts_values_set_values(struct pyrf_counts_values *self, PyObject *list, + void *closure) +{ + Py_ssize_t size; + PyObject *item = NULL; + + if (!PyList_Check(list)) { + PyErr_SetString(PyExc_TypeError, "Value assigned must be a list"); + return -1; + } + + size = PyList_Size(list); + for (Py_ssize_t i = 0; i < size; i++) { + item = PyList_GetItem(list, i); + if (!PyLong_Check(item)) { + PyErr_SetString(PyExc_TypeError, "List members should be numbers"); + return -1; + } + self->values.values[i] = PyLong_AsLong(item); + } + + return 0; +} + +static PyGetSetDef pyrf_counts_values_getset[] = { + {"values", (getter)pyrf_counts_values_get_values, (setter)pyrf_counts_values_set_values, + "Name field", NULL}, + { .name = NULL, }, +}; + +static PyTypeObject pyrf_counts_values__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.counts_values", + .tp_basicsize = sizeof(struct pyrf_counts_values), + .tp_dealloc = (destructor)pyrf_counts_values__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_counts_values__doc, + .tp_members = pyrf_counts_values_members, + .tp_getset = pyrf_counts_values_getset, +}; + +static int pyrf_counts_values__setup_types(void) +{ + pyrf_counts_values__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_counts_values__type); +} + struct pyrf_evsel { PyObject_HEAD @@ -781,15 +1094,104 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, return Py_None; } +static PyObject *pyrf_evsel__cpus(struct pyrf_evsel *pevsel) +{ + struct pyrf_cpu_map *pcpu_map = PyObject_New(struct pyrf_cpu_map, &pyrf_cpu_map__type); + + if (pcpu_map) + pcpu_map->cpus = perf_cpu_map__get(pevsel->evsel.core.cpus); + + return (PyObject *)pcpu_map; +} + +static PyObject *pyrf_evsel__threads(struct pyrf_evsel *pevsel) +{ + struct pyrf_thread_map *pthread_map = + PyObject_New(struct pyrf_thread_map, &pyrf_thread_map__type); + + if (pthread_map) + pthread_map->threads = perf_thread_map__get(pevsel->evsel.core.threads); + + return (PyObject *)pthread_map; +} + +/* + * Ensure evsel's counts and prev_raw_counts are allocated, the latter + * used by tool PMUs to compute the cumulative count as expected by + * stat's process_counter_values. + */ +static int evsel__ensure_counts(struct evsel *evsel) +{ + int nthreads, ncpus; + + if (evsel->counts != NULL) + return 0; + + nthreads = perf_thread_map__nr(evsel->core.threads); + ncpus = perf_cpu_map__nr(evsel->core.cpus); + + evsel->counts = perf_counts__new(ncpus, nthreads); + if (evsel->counts == NULL) + return -ENOMEM; + + evsel->prev_raw_counts = perf_counts__new(ncpus, nthreads); + if (evsel->prev_raw_counts == NULL) + return -ENOMEM; + + return 0; +} + +static PyObject *pyrf_evsel__read(struct pyrf_evsel *pevsel, + PyObject *args, PyObject *kwargs) +{ + struct evsel *evsel = &pevsel->evsel; + int cpu = 0, cpu_idx, thread = 0, thread_idx; + struct perf_counts_values *old_count, *new_count; + struct pyrf_counts_values *count_values = PyObject_New(struct pyrf_counts_values, + &pyrf_counts_values__type); + + if (!count_values) + return NULL; + + if (!PyArg_ParseTuple(args, "ii", &cpu, &thread)) + return NULL; + + cpu_idx = perf_cpu_map__idx(evsel->core.cpus, (struct perf_cpu){.cpu = cpu}); + if (cpu_idx < 0) { + PyErr_Format(PyExc_TypeError, "CPU %d is not part of evsel's CPUs", cpu); + return NULL; + } + thread_idx = perf_thread_map__idx(evsel->core.threads, thread); + if (thread_idx < 0) { + PyErr_Format(PyExc_TypeError, "Thread %d is not part of evsel's threads", + thread); + return NULL; + } + + if (evsel__ensure_counts(evsel)) + return PyErr_NoMemory(); + + /* Set up pointers to the old and newly read counter values. */ + old_count = perf_counts(evsel->prev_raw_counts, cpu_idx, thread_idx); + new_count = perf_counts(evsel->counts, cpu_idx, thread_idx); + /* Update the value in evsel->counts. */ + evsel__read_counter(evsel, cpu_idx, thread_idx); + /* Copy the value and turn it into the delta from old_count. */ + count_values->values = *new_count; + count_values->values.val -= old_count->val; + count_values->values.ena -= old_count->ena; + count_values->values.run -= old_count->run; + /* Save the new count over the old_count for the next read. */ + *old_count = *new_count; + return (PyObject *)count_values; +} + static PyObject *pyrf_evsel__str(PyObject *self) { struct pyrf_evsel *pevsel = (void *)self; struct evsel *evsel = &pevsel->evsel; - if (!evsel->pmu) - return PyUnicode_FromFormat("evsel(%s)", evsel__name(evsel)); - - return PyUnicode_FromFormat("evsel(%s/%s/)", evsel->pmu->name, evsel__name(evsel)); + return PyUnicode_FromFormat("evsel(%s/%s/)", evsel__pmu_name(evsel), evsel__name(evsel)); } static PyMethodDef pyrf_evsel__methods[] = { @@ -799,9 +1201,49 @@ static PyMethodDef pyrf_evsel__methods[] = { .ml_flags = METH_VARARGS | METH_KEYWORDS, .ml_doc = PyDoc_STR("open the event selector file descriptor table.") }, + { + .ml_name = "cpus", + .ml_meth = (PyCFunction)pyrf_evsel__cpus, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("CPUs the event is to be used with.") + }, + { + .ml_name = "threads", + .ml_meth = (PyCFunction)pyrf_evsel__threads, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("threads the event is to be used with.") + }, + { + .ml_name = "read", + .ml_meth = (PyCFunction)pyrf_evsel__read, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("read counters") + }, { .ml_name = NULL, } }; +#define evsel_member_def(member, ptype, help) \ + { #member, ptype, \ + offsetof(struct pyrf_evsel, evsel.member), \ + 0, help } + +#define evsel_attr_member_def(member, ptype, help) \ + { #member, ptype, \ + offsetof(struct pyrf_evsel, evsel.core.attr.member), \ + 0, help } + +static PyMemberDef pyrf_evsel__members[] = { + evsel_member_def(tracking, T_BOOL, "tracking event."), + evsel_attr_member_def(type, T_UINT, "attribute type."), + evsel_attr_member_def(size, T_UINT, "attribute size."), + evsel_attr_member_def(config, T_ULONGLONG, "attribute config."), + evsel_attr_member_def(sample_period, T_ULONGLONG, "attribute sample_period."), + evsel_attr_member_def(sample_type, T_ULONGLONG, "attribute sample_type."), + evsel_attr_member_def(read_format, T_ULONGLONG, "attribute read_format."), + evsel_attr_member_def(wakeup_events, T_UINT, "attribute wakeup_events."), + { .name = NULL, }, +}; + static const char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); static PyTypeObject pyrf_evsel__type = { @@ -811,6 +1253,7 @@ static PyTypeObject pyrf_evsel__type = { .tp_dealloc = (destructor)pyrf_evsel__delete, .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, .tp_doc = pyrf_evsel__doc, + .tp_members = pyrf_evsel__members, .tp_methods = pyrf_evsel__methods, .tp_init = (initproc)pyrf_evsel__init, .tp_str = pyrf_evsel__str, @@ -851,6 +1294,188 @@ static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) Py_TYPE(pevlist)->tp_free((PyObject*)pevlist); } +static PyObject *pyrf_evlist__all_cpus(struct pyrf_evlist *pevlist) +{ + struct pyrf_cpu_map *pcpu_map = PyObject_New(struct pyrf_cpu_map, &pyrf_cpu_map__type); + + if (pcpu_map) + pcpu_map->cpus = perf_cpu_map__get(pevlist->evlist.core.all_cpus); + + return (PyObject *)pcpu_map; +} + +static PyObject *pyrf_evlist__metrics(struct pyrf_evlist *pevlist) +{ + PyObject *list = PyList_New(/*len=*/0); + struct rb_node *node; + + if (!list) + return NULL; + + for (node = rb_first_cached(&pevlist->evlist.metric_events.entries); node; + node = rb_next(node)) { + struct metric_event *me = container_of(node, struct metric_event, nd); + struct list_head *pos; + + list_for_each(pos, &me->head) { + struct metric_expr *expr = container_of(pos, struct metric_expr, nd); + PyObject *str = PyUnicode_FromString(expr->metric_name); + + if (!str || PyList_Append(list, str) != 0) { + Py_DECREF(list); + return NULL; + } + Py_DECREF(str); + } + } + return list; +} + +static int prepare_metric(const struct metric_expr *mexp, + const struct evsel *evsel, + struct expr_parse_ctx *pctx, + int cpu_idx, int thread_idx) +{ + struct evsel * const *metric_events = mexp->metric_events; + struct metric_ref *metric_refs = mexp->metric_refs; + + for (int i = 0; metric_events[i]; i++) { + struct evsel *cur = metric_events[i]; + double val, ena, run; + int ret, source_count = 0; + struct perf_counts_values *old_count, *new_count; + char *n = strdup(evsel__metric_id(cur)); + + if (!n) + return -ENOMEM; + + /* + * If there are multiple uncore PMUs and we're not reading the + * leader's stats, determine the stats for the appropriate + * uncore PMU. + */ + if (evsel && evsel->metric_leader && + evsel->pmu != evsel->metric_leader->pmu && + cur->pmu == evsel->metric_leader->pmu) { + struct evsel *pos; + + evlist__for_each_entry(evsel->evlist, pos) { + if (pos->pmu != evsel->pmu) + continue; + if (pos->metric_leader != cur) + continue; + cur = pos; + source_count = 1; + break; + } + } + + if (source_count == 0) + source_count = evsel__source_count(cur); + + ret = evsel__ensure_counts(cur); + if (ret) + return ret; + + /* Set up pointers to the old and newly read counter values. */ + old_count = perf_counts(cur->prev_raw_counts, cpu_idx, thread_idx); + new_count = perf_counts(cur->counts, cpu_idx, thread_idx); + /* Update the value in cur->counts. */ + evsel__read_counter(cur, cpu_idx, thread_idx); + + val = new_count->val - old_count->val; + ena = new_count->ena - old_count->ena; + run = new_count->run - old_count->run; + + if (ena != run && run != 0) + val = val * ena / run; + ret = expr__add_id_val_source_count(pctx, n, val, source_count); + if (ret) + return ret; + } + + for (int i = 0; metric_refs && metric_refs[i].metric_name; i++) { + int ret = expr__add_ref(pctx, &metric_refs[i]); + + if (ret) + return ret; + } + + return 0; +} + +static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + int ret, cpu = 0, cpu_idx = 0, thread = 0, thread_idx = 0; + const char *metric; + struct rb_node *node; + struct metric_expr *mexp = NULL; + struct expr_parse_ctx *pctx; + double result = 0; + struct evsel *metric_evsel = NULL; + + if (!PyArg_ParseTuple(args, "sii", &metric, &cpu, &thread)) + return NULL; + + for (node = rb_first_cached(&pevlist->evlist.metric_events.entries); + mexp == NULL && node; + node = rb_next(node)) { + struct metric_event *me = container_of(node, struct metric_event, nd); + struct list_head *pos; + + list_for_each(pos, &me->head) { + struct metric_expr *e = container_of(pos, struct metric_expr, nd); + struct evsel *pos2; + + if (strcmp(e->metric_name, metric)) + continue; + + if (e->metric_events[0] == NULL) + continue; + + evlist__for_each_entry(&pevlist->evlist, pos2) { + if (pos2->metric_leader != e->metric_events[0]) + continue; + cpu_idx = perf_cpu_map__idx(pos2->core.cpus, + (struct perf_cpu){.cpu = cpu}); + if (cpu_idx < 0) + continue; + + thread_idx = perf_thread_map__idx(pos2->core.threads, thread); + if (thread_idx < 0) + continue; + metric_evsel = pos2; + mexp = e; + goto done; + } + } + } +done: + if (!mexp) { + PyErr_Format(PyExc_TypeError, "Unknown metric '%s' for CPU '%d' and thread '%d'", + metric, cpu, thread); + return NULL; + } + + pctx = expr__ctx_new(); + if (!pctx) + return PyErr_NoMemory(); + + ret = prepare_metric(mexp, metric_evsel, pctx, cpu_idx, thread_idx); + if (ret) { + expr__ctx_free(pctx); + errno = -ret; + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + if (expr__parse(&result, pctx, mexp->metric_expr)) + result = 0.0; + + expr__ctx_free(pctx); + return PyFloat_FromDouble(result); +} + static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { @@ -967,8 +1592,10 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, return NULL; md = get_md(evlist, cpu); - if (!md) + if (!md) { + PyErr_Format(PyExc_TypeError, "Unknown CPU '%d'", cpu); return NULL; + } if (perf_mmap__read_init(&md->core) < 0) goto end; @@ -984,20 +1611,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, evsel = evlist__event2evsel(evlist, event); if (!evsel) { + Py_DECREF(pyevent); Py_INCREF(Py_None); return Py_None; } pevent->evsel = evsel; - err = evsel__parse_sample(evsel, event, &pevent->sample); - - /* Consume the even only after we parsed it out. */ perf_mmap__consume(&md->core); - if (err) + err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample); + if (err) { + Py_DECREF(pyevent); return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); + } + return pyevent; } end: @@ -1019,8 +1648,75 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, return Py_None; } +static PyObject *pyrf_evlist__close(struct pyrf_evlist *pevlist) +{ + struct evlist *evlist = &pevlist->evlist; + + evlist__close(evlist); + + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__config(struct pyrf_evlist *pevlist) +{ + struct record_opts opts = { + .sample_time = true, + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, + .target = { + .uses_mmap = true, + .default_per_cpu = true, + }, + .nr_threads_synthesize = 1, + .ctl_fd = -1, + .ctl_fd_ack = -1, + .no_buffering = true, + .no_inherit = true, + }; + struct evlist *evlist = &pevlist->evlist; + + evlist__config(evlist, &opts, &callchain_param); + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__disable(struct pyrf_evlist *pevlist) +{ + evlist__disable(&pevlist->evlist); + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__enable(struct pyrf_evlist *pevlist) +{ + evlist__enable(&pevlist->evlist); + Py_INCREF(Py_None); + return Py_None; +} + static PyMethodDef pyrf_evlist__methods[] = { { + .ml_name = "all_cpus", + .ml_meth = (PyCFunction)pyrf_evlist__all_cpus, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("CPU map union of all evsel CPU maps.") + }, + { + .ml_name = "metrics", + .ml_meth = (PyCFunction)pyrf_evlist__metrics, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("List of metric names within the evlist.") + }, + { + .ml_name = "compute_metric", + .ml_meth = (PyCFunction)pyrf_evlist__compute_metric, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("compute metric for given name, cpu and thread") + }, + { .ml_name = "mmap", .ml_meth = (PyCFunction)pyrf_evlist__mmap, .ml_flags = METH_VARARGS | METH_KEYWORDS, @@ -1033,6 +1729,12 @@ static PyMethodDef pyrf_evlist__methods[] = { .ml_doc = PyDoc_STR("open the file descriptors.") }, { + .ml_name = "close", + .ml_meth = (PyCFunction)pyrf_evlist__close, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("close the file descriptors.") + }, + { .ml_name = "poll", .ml_meth = (PyCFunction)pyrf_evlist__poll, .ml_flags = METH_VARARGS | METH_KEYWORDS, @@ -1056,6 +1758,24 @@ static PyMethodDef pyrf_evlist__methods[] = { .ml_flags = METH_VARARGS | METH_KEYWORDS, .ml_doc = PyDoc_STR("reads an event.") }, + { + .ml_name = "config", + .ml_meth = (PyCFunction)pyrf_evlist__config, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Apply default record options to the evlist.") + }, + { + .ml_name = "disable", + .ml_meth = (PyCFunction)pyrf_evlist__disable, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Disable the evsels in the evlist.") + }, + { + .ml_name = "enable", + .ml_meth = (PyCFunction)pyrf_evlist__enable, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Enable the evsels in the evlist.") + }, { .ml_name = NULL, } }; @@ -1223,10 +1943,6 @@ static const struct perf_constant perf__constants[] = { static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel, PyObject *args, PyObject *kwargs) { -#ifndef HAVE_LIBTRACEEVENT - return NULL; -#else - struct tep_event *tp_format; static char *kwlist[] = { "sys", "name", NULL }; char *sys = NULL; char *name = NULL; @@ -1235,12 +1951,7 @@ static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel, &sys, &name)) return NULL; - tp_format = trace_event__tp_format(sys, name); - if (IS_ERR(tp_format)) - return PyLong_FromLong(-1); - - return PyLong_FromLong(tp_format->id); -#endif // HAVE_LIBTRACEEVENT + return PyLong_FromLong(tp_pmu__id(sys, name)); } static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel) @@ -1254,13 +1965,42 @@ static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel) evsel__init(&pevsel->evsel, &evsel->core.attr, evsel->core.idx); evsel__clone(&pevsel->evsel, evsel); + if (evsel__is_group_leader(evsel)) + evsel__set_leader(&pevsel->evsel, &pevsel->evsel); return (PyObject *)pevsel; } +static int evlist__pos(struct evlist *evlist, struct evsel *evsel) +{ + struct evsel *pos; + int idx = 0; + + evlist__for_each_entry(evlist, pos) { + if (evsel == pos) + return idx; + idx++; + } + return -1; +} + +static struct evsel *evlist__at(struct evlist *evlist, int idx) +{ + struct evsel *pos; + int idx2 = 0; + + evlist__for_each_entry(evlist, pos) { + if (idx == idx2) + return pos; + idx2++; + } + return NULL; +} + static PyObject *pyrf_evlist__from_evlist(struct evlist *evlist) { struct pyrf_evlist *pevlist = PyObject_New(struct pyrf_evlist, &pyrf_evlist__type); struct evsel *pos; + struct rb_node *node; if (!pevlist) return NULL; @@ -1272,6 +2012,50 @@ static PyObject *pyrf_evlist__from_evlist(struct evlist *evlist) evlist__add(&pevlist->evlist, &pevsel->evsel); } + evlist__for_each_entry(&pevlist->evlist, pos) { + struct evsel *leader = evsel__leader(pos); + + if (pos != leader) { + int idx = evlist__pos(evlist, leader); + + if (idx >= 0) + evsel__set_leader(pos, evlist__at(&pevlist->evlist, idx)); + else if (leader == NULL) + evsel__set_leader(pos, pos); + } + + leader = pos->metric_leader; + + if (pos != leader) { + int idx = evlist__pos(evlist, leader); + + if (idx >= 0) + pos->metric_leader = evlist__at(&pevlist->evlist, idx); + else if (leader == NULL) + pos->metric_leader = pos; + } + } + metricgroup__copy_metric_events(&pevlist->evlist, /*cgrp=*/NULL, + &pevlist->evlist.metric_events, + &evlist->metric_events); + for (node = rb_first_cached(&pevlist->evlist.metric_events.entries); node; + node = rb_next(node)) { + struct metric_event *me = container_of(node, struct metric_event, nd); + struct list_head *mpos; + int idx = evlist__pos(evlist, me->evsel); + + if (idx >= 0) + me->evsel = evlist__at(&pevlist->evlist, idx); + list_for_each(mpos, &me->head) { + struct metric_expr *e = container_of(mpos, struct metric_expr, nd); + + for (int j = 0; e->metric_events[j]; j++) { + idx = evlist__pos(evlist, e->metric_events[j]); + if (idx >= 0) + e->metric_events[j] = evlist__at(&pevlist->evlist, idx); + } + } + } return (PyObject *)pevlist; } @@ -1281,12 +2065,18 @@ static PyObject *pyrf__parse_events(PyObject *self, PyObject *args) struct evlist evlist = {}; struct parse_events_error err; PyObject *result; + PyObject *pcpus = NULL, *pthreads = NULL; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; - if (!PyArg_ParseTuple(args, "s", &input)) + if (!PyArg_ParseTuple(args, "s|OO", &input, &pcpus, &pthreads)) return NULL; + threads = pthreads ? ((struct pyrf_thread_map *)pthreads)->threads : NULL; + cpus = pcpus ? ((struct pyrf_cpu_map *)pcpus)->cpus : NULL; + parse_events_error__init(&err); - evlist__init(&evlist, NULL, NULL); + evlist__init(&evlist, cpus, threads); if (parse_events(&evlist, input, &err)) { parse_events_error__print(&err, input); PyErr_SetFromErrno(PyExc_OSError); @@ -1297,8 +2087,128 @@ static PyObject *pyrf__parse_events(PyObject *self, PyObject *args) return result; } +static PyObject *pyrf__parse_metrics(PyObject *self, PyObject *args) +{ + const char *input, *pmu = NULL; + struct evlist evlist = {}; + PyObject *result; + PyObject *pcpus = NULL, *pthreads = NULL; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; + int ret; + + if (!PyArg_ParseTuple(args, "s|sOO", &input, &pmu, &pcpus, &pthreads)) + return NULL; + + threads = pthreads ? ((struct pyrf_thread_map *)pthreads)->threads : NULL; + cpus = pcpus ? ((struct pyrf_cpu_map *)pcpus)->cpus : NULL; + + evlist__init(&evlist, cpus, threads); + ret = metricgroup__parse_groups(&evlist, pmu ?: "all", input, + /*metric_no_group=*/ false, + /*metric_no_merge=*/ false, + /*metric_no_threshold=*/ true, + /*user_requested_cpu_list=*/ NULL, + /*system_wide=*/true, + /*hardware_aware_grouping=*/ false); + if (ret) { + errno = -ret; + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + result = pyrf_evlist__from_evlist(&evlist); + evlist__exit(&evlist); + return result; +} + +static PyObject *pyrf__metrics_groups(const struct pmu_metric *pm) +{ + PyObject *groups = PyList_New(/*len=*/0); + const char *mg = pm->metric_group; + + if (!groups) + return NULL; + + while (mg) { + PyObject *val = NULL; + const char *sep = strchr(mg, ';'); + size_t len = sep ? (size_t)(sep - mg) : strlen(mg); + + if (len > 0) { + val = PyUnicode_FromStringAndSize(mg, len); + if (val) + PyList_Append(groups, val); + + Py_XDECREF(val); + } + mg = sep ? sep + 1 : NULL; + } + return groups; +} + +static int pyrf__metrics_cb(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *vdata) +{ + PyObject *py_list = vdata; + PyObject *dict = PyDict_New(); + PyObject *key = dict ? PyUnicode_FromString("MetricGroup") : NULL; + PyObject *value = key ? pyrf__metrics_groups(pm) : NULL; + + if (!value || PyDict_SetItem(dict, key, value) != 0) { + Py_XDECREF(key); + Py_XDECREF(value); + Py_XDECREF(dict); + return -ENOMEM; + } + + if (!add_to_dict(dict, "MetricName", pm->metric_name) || + !add_to_dict(dict, "PMU", pm->pmu) || + !add_to_dict(dict, "MetricExpr", pm->metric_expr) || + !add_to_dict(dict, "MetricThreshold", pm->metric_threshold) || + !add_to_dict(dict, "ScaleUnit", pm->unit) || + !add_to_dict(dict, "Compat", pm->compat) || + !add_to_dict(dict, "BriefDescription", pm->desc) || + !add_to_dict(dict, "PublicDescription", pm->long_desc) || + PyList_Append(py_list, dict) != 0) { + Py_DECREF(dict); + return -ENOMEM; + } + Py_DECREF(dict); + return 0; +} + +static PyObject *pyrf__metrics(PyObject *self, PyObject *args) +{ + const struct pmu_metrics_table *table = pmu_metrics_table__find(); + PyObject *list = PyList_New(/*len=*/0); + int ret; + + if (!list) + return NULL; + + ret = pmu_metrics_table__for_each_metric(table, pyrf__metrics_cb, list); + if (!ret) + ret = pmu_for_each_sys_metric(pyrf__metrics_cb, list); + + if (ret) { + Py_DECREF(list); + errno = -ret; + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + return list; +} + static PyMethodDef perf__methods[] = { { + .ml_name = "metrics", + .ml_meth = (PyCFunction) pyrf__metrics, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR( + "Returns a list of metrics represented as string values in dictionaries.") + }, + { .ml_name = "tracepoint", .ml_meth = (PyCFunction) pyrf__tracepoint, .ml_flags = METH_VARARGS | METH_KEYWORDS, @@ -1310,6 +2220,19 @@ static PyMethodDef perf__methods[] = { .ml_flags = METH_VARARGS, .ml_doc = PyDoc_STR("Parse a string of events and return an evlist.") }, + { + .ml_name = "parse_metrics", + .ml_meth = (PyCFunction) pyrf__parse_metrics, + .ml_flags = METH_VARARGS, + .ml_doc = PyDoc_STR( + "Parse a string of metrics or metric groups and return an evlist.") + }, + { + .ml_name = "pmus", + .ml_meth = (PyCFunction) pyrf__pmus, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Returns a sequence of pmus.") + }, { .ml_name = NULL, } }; @@ -1336,7 +2259,10 @@ PyMODINIT_FUNC PyInit_perf(void) pyrf_evlist__setup_types() < 0 || pyrf_evsel__setup_types() < 0 || pyrf_thread_map__setup_types() < 0 || - pyrf_cpu_map__setup_types() < 0) + pyrf_cpu_map__setup_types() < 0 || + pyrf_pmu_iterator__setup_types() < 0 || + pyrf_pmu__setup_types() < 0 || + pyrf_counts_values__setup_types() < 0) return module; /* The page_size is placed in util object. */ @@ -1381,6 +2307,9 @@ PyMODINIT_FUNC PyInit_perf(void) Py_INCREF(&pyrf_cpu_map__type); PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type); + Py_INCREF(&pyrf_counts_values__type); + PyModule_AddObject(module, "counts_values", (PyObject *)&pyrf_counts_values__type); + dict = PyModule_GetDict(module); if (dict == NULL) goto error; diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h deleted file mode 100644 index d927a0d25052..000000000000 --- a/tools/perf/util/rb_resort.h +++ /dev/null @@ -1,146 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _PERF_RESORT_RB_H_ -#define _PERF_RESORT_RB_H_ -/* - * Template for creating a class to resort an existing rb_tree according to - * a new sort criteria, that must be present in the entries of the source - * rb_tree. - * - * (c) 2016 Arnaldo Carvalho de Melo <acme@redhat.com> - * - * Quick example, resorting threads by its shortname: - * - * First define the prefix (threads) to be used for the functions and data - * structures created, and provide an expression for the sorting, then the - * fields to be present in each of the entries in the new, sorted, rb_tree. - * - * The body of the init function should collect the fields, maybe - * pre-calculating them from multiple entries in the original 'entry' from - * the rb_tree used as a source for the entries to be sorted: - -DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname, - b->thread->shortname) < 0, - struct thread *thread; -) -{ - entry->thread = rb_entry(nd, struct thread, rb_node); -} - - * After this it is just a matter of instantiating it and iterating it, - * for a few data structures with existing rb_trees, such as 'struct machine', - * helpers are available to get the rb_root and the nr_entries: - - DECLARE_RESORT_RB_MACHINE_THREADS(threads, machine_ptr); - - * This will instantiate the new rb_tree and a cursor for it, that can be used as: - - struct rb_node *nd; - - resort_rb__for_each_entry(nd, threads) { - struct thread *t = threads_entry; - printf("%s: %d\n", t->shortname, t->tid); - } - - * Then delete it: - - resort_rb__delete(threads); - - * The name of the data structures and functions will have a _sorted suffix - * right before the method names, i.e. will look like: - * - * struct threads_sorted_entry {} - * threads_sorted__insert() - */ - -#define DEFINE_RESORT_RB(__name, __comp, ...) \ -struct __name##_sorted_entry { \ - struct rb_node rb_node; \ - __VA_ARGS__ \ -}; \ -static void __name##_sorted__init_entry(struct rb_node *nd, \ - struct __name##_sorted_entry *entry); \ - \ -static int __name##_sorted__cmp(struct rb_node *nda, struct rb_node *ndb) \ -{ \ - struct __name##_sorted_entry *a, *b; \ - a = rb_entry(nda, struct __name##_sorted_entry, rb_node); \ - b = rb_entry(ndb, struct __name##_sorted_entry, rb_node); \ - return __comp; \ -} \ - \ -struct __name##_sorted { \ - struct rb_root entries; \ - struct __name##_sorted_entry nd[0]; \ -}; \ - \ -static void __name##_sorted__insert(struct __name##_sorted *sorted, \ - struct rb_node *sorted_nd) \ -{ \ - struct rb_node **p = &sorted->entries.rb_node, *parent = NULL; \ - while (*p != NULL) { \ - parent = *p; \ - if (__name##_sorted__cmp(sorted_nd, parent)) \ - p = &(*p)->rb_left; \ - else \ - p = &(*p)->rb_right; \ - } \ - rb_link_node(sorted_nd, parent, p); \ - rb_insert_color(sorted_nd, &sorted->entries); \ -} \ - \ -static void __name##_sorted__sort(struct __name##_sorted *sorted, \ - struct rb_root *entries) \ -{ \ - struct rb_node *nd; \ - unsigned int i = 0; \ - for (nd = rb_first(entries); nd; nd = rb_next(nd)) { \ - struct __name##_sorted_entry *snd = &sorted->nd[i++]; \ - __name##_sorted__init_entry(nd, snd); \ - __name##_sorted__insert(sorted, &snd->rb_node); \ - } \ -} \ - \ -static struct __name##_sorted *__name##_sorted__new(struct rb_root *entries, \ - int nr_entries) \ -{ \ - struct __name##_sorted *sorted; \ - sorted = malloc(sizeof(*sorted) + sizeof(sorted->nd[0]) * nr_entries); \ - if (sorted) { \ - sorted->entries = RB_ROOT; \ - __name##_sorted__sort(sorted, entries); \ - } \ - return sorted; \ -} \ - \ -static void __name##_sorted__delete(struct __name##_sorted *sorted) \ -{ \ - free(sorted); \ -} \ - \ -static void __name##_sorted__init_entry(struct rb_node *nd, \ - struct __name##_sorted_entry *entry) - -#define DECLARE_RESORT_RB(__name) \ -struct __name##_sorted_entry *__name##_entry; \ -struct __name##_sorted *__name = __name##_sorted__new - -#define resort_rb__for_each_entry(__nd, __name) \ - for (__nd = rb_first(&__name->entries); \ - __name##_entry = rb_entry(__nd, struct __name##_sorted_entry, \ - rb_node), __nd; \ - __nd = rb_next(__nd)) - -#define resort_rb__delete(__name) \ - __name##_sorted__delete(__name), __name = NULL - -/* - * Helpers for other classes that contains both an rbtree and the - * number of entries in it: - */ - -/* For 'struct intlist' */ -#define DECLARE_RESORT_RB_INTLIST(__name, __ilist) \ - DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries.rb_root, \ - __ilist->rblist.nr_entries) - -#endif /* _PERF_RESORT_RB_H_ */ diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index a6566134e09e..93627c9a7338 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -28,6 +28,7 @@ struct record_opts { bool sample_time_set; bool sample_cpu; bool sample_identifier; + bool sample_data_src; bool period; bool period_set; bool running_time; @@ -39,6 +40,8 @@ struct record_opts { bool record_cgroup; bool record_switch_events; bool record_switch_events_set; + bool record_data_mmap; + bool record_data_mmap_set; bool all_kernel; bool all_user; bool kernel_callchains; @@ -79,6 +82,7 @@ struct record_opts { int synth; int threads_spec; const char *threads_user_spec; + u64 off_cpu_thresh_ns; }; extern const char * const *record_usage; diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c index 5109167f27f7..9d26832398db 100644 --- a/tools/perf/util/rwsem.c +++ b/tools/perf/util/rwsem.c @@ -27,6 +27,7 @@ int exit_rwsem(struct rw_semaphore *sem) } int down_read(struct rw_semaphore *sem) + NO_THREAD_SAFETY_ANALYSIS { #if RWS_ERRORCHECK mutex_lock(&sem->mtx); @@ -37,6 +38,7 @@ int down_read(struct rw_semaphore *sem) } int up_read(struct rw_semaphore *sem) + NO_THREAD_SAFETY_ANALYSIS { #if RWS_ERRORCHECK mutex_unlock(&sem->mtx); @@ -47,6 +49,7 @@ int up_read(struct rw_semaphore *sem) } int down_write(struct rw_semaphore *sem) + NO_THREAD_SAFETY_ANALYSIS { #if RWS_ERRORCHECK mutex_lock(&sem->mtx); @@ -57,6 +60,7 @@ int down_write(struct rw_semaphore *sem) } int up_write(struct rw_semaphore *sem) + NO_THREAD_SAFETY_ANALYSIS { #if RWS_ERRORCHECK mutex_unlock(&sem->mtx); diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h index ef5cbc31d967..b102d8143181 100644 --- a/tools/perf/util/rwsem.h +++ b/tools/perf/util/rwsem.h @@ -10,7 +10,7 @@ */ #define RWS_ERRORCHECK 0 -struct rw_semaphore { +struct LOCKABLE rw_semaphore { #if RWS_ERRORCHECK struct mutex mtx; #else @@ -21,10 +21,10 @@ struct rw_semaphore { int init_rwsem(struct rw_semaphore *sem); int exit_rwsem(struct rw_semaphore *sem); -int down_read(struct rw_semaphore *sem); -int up_read(struct rw_semaphore *sem); +int down_read(struct rw_semaphore *sem) SHARED_LOCK_FUNCTION(sem); +int up_read(struct rw_semaphore *sem) UNLOCK_FUNCTION(sem); -int down_write(struct rw_semaphore *sem); -int up_write(struct rw_semaphore *sem); +int down_write(struct rw_semaphore *sem) EXCLUSIVE_LOCK_FUNCTION(sem); +int up_write(struct rw_semaphore *sem) UNLOCK_FUNCTION(sem); #endif /* _PERF_RWSEM_H */ diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 30638653ad2d..c17dbe232c54 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -513,6 +513,7 @@ static bool s390_cpumsf_make_event(size_t pos, .period = 1 }; union perf_event event; + int ret; memset(&event, 0, sizeof(event)); if (basic->CL == 1) /* Native LPAR mode */ @@ -536,8 +537,9 @@ static bool s390_cpumsf_make_event(size_t pos, pr_debug4("%s pos:%#zx ip:%#" PRIx64 " P:%d CL:%d pid:%d.%d cpumode:%d cpu:%d\n", __func__, pos, sample.ip, basic->P, basic->CL, sample.pid, sample.tid, sample.cpumode, sample.cpu); - if (perf_session__deliver_synth_event(sfq->sf->session, &event, - &sample)) { + ret = perf_session__deliver_synth_event(sfq->sf->session, &event, &sample); + perf_sample__exit(&sample); + if (ret) { pr_err("s390 Auxiliary Trace: failed to deliver event\n"); return false; } @@ -1140,7 +1142,7 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event, sf->machine = &session->machines.host; /* No kvm support */ sf->auxtrace_type = auxtrace_info->type; sf->pmu_type = PERF_TYPE_RAW; - sf->machine_type = s390_cpumsf_get_type(session->evlist->env->cpuid); + sf->machine_type = s390_cpumsf_get_type(perf_session__env(session)->cpuid); sf->auxtrace.process_event = s390_cpumsf_process_event; sf->auxtrace.process_auxtrace_event = s390_cpumsf_process_auxtrace_event; diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 335217bb532b..c6ae0ae8d86a 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -19,12 +19,14 @@ #include <sys/stat.h> #include <linux/compiler.h> +#include <linux/err.h> #include <asm/byteorder.h> #include "debug.h" #include "session.h" #include "evlist.h" #include "color.h" +#include "hashmap.h" #include "sample-raw.h" #include "s390-cpumcf-kernel.h" #include "util/pmu.h" @@ -132,8 +134,8 @@ static int get_counterset_start(int setnr) } struct get_counter_name_data { - int wanted; - char *result; + long wanted; + const char *result; }; static int get_counter_name_callback(void *vdata, struct pmu_event_info *info) @@ -151,12 +153,22 @@ static int get_counter_name_callback(void *vdata, struct pmu_event_info *info) rc = sscanf(event_str, "event=%x", &event_nr); if (rc == 1 && event_nr == data->wanted) { - data->result = strdup(info->name); + data->result = info->name; return 1; /* Terminate the search. */ } return 0; } +static size_t get_counter_name_hash_fn(long key, void *ctx __maybe_unused) +{ + return key; +} + +static bool get_counter_name_hashmap_equal_fn(long key1, long key2, void *ctx __maybe_unused) +{ + return key1 == key2; +} + /* Scan the PMU and extract the logical name of a counter from the event. Input * is the counter set and counter number with in the set. Construct the event * number and use this as key. If they match return the name of this counter. @@ -164,17 +176,50 @@ static int get_counter_name_callback(void *vdata, struct pmu_event_info *info) */ static char *get_counter_name(int set, int nr, struct perf_pmu *pmu) { + static struct hashmap *cache; + static struct perf_pmu *cache_pmu; + long cache_key = get_counterset_start(set) + nr; struct get_counter_name_data data = { - .wanted = get_counterset_start(set) + nr, + .wanted = cache_key, .result = NULL, }; + char *result = NULL; if (!pmu) return NULL; + if (cache_pmu == pmu && hashmap__find(cache, cache_key, &result)) + return strdup(result); + perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/ true, &data, get_counter_name_callback); - return data.result; + + result = strdup(data.result ?: "<unknown>"); + + if (cache_pmu == NULL) { + struct hashmap *tmp = hashmap__new(get_counter_name_hash_fn, + get_counter_name_hashmap_equal_fn, + /*ctx=*/NULL); + + if (!IS_ERR(tmp)) { + cache = tmp; + cache_pmu = pmu; + } + } + + if (cache_pmu == pmu && result) { + char *old_value = NULL, *new_value = strdup(result); + + if (new_value) { + hashmap__set(cache, cache_key, new_value, /*old_key=*/NULL, &old_value); + /* + * Free in case of a race, but resizing would be broken + * in that case. + */ + free(old_value); + } + } + return result; } static void s390_cpumcfdg_dump(struct perf_pmu *pmu, struct perf_sample *sample) diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c index f3f6bd9d290e..bcf442574d6e 100644 --- a/tools/perf/util/sample-raw.c +++ b/tools/perf/util/sample-raw.c @@ -6,15 +6,16 @@ #include "env.h" #include "header.h" #include "sample-raw.h" +#include "session.h" /* * Check platform the perf data file was created on and perform platform * specific interpretation. */ -void evlist__init_trace_event_sample_raw(struct evlist *evlist) +void evlist__init_trace_event_sample_raw(struct evlist *evlist, struct perf_env *env) { - const char *arch_pf = perf_env__arch(evlist->env); - const char *cpuid = perf_env__cpuid(evlist->env); + const char *arch_pf = perf_env__arch(env); + const char *cpuid = perf_env__cpuid(env); if (arch_pf && !strcmp("s390", arch_pf)) evlist->trace_event_sample_raw = evlist__s390_sample_raw; diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h index ea01c5811503..896e9a87e373 100644 --- a/tools/perf/util/sample-raw.h +++ b/tools/perf/util/sample-raw.h @@ -11,5 +11,5 @@ void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, bool evlist__has_amd_ibs(struct evlist *evlist); void evlist__amd_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); -void evlist__init_trace_event_sample_raw(struct evlist *evlist); +void evlist__init_trace_event_sample_raw(struct evlist *evlist, struct perf_env *env); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/sample.c b/tools/perf/util/sample.c new file mode 100644 index 000000000000..cf73329326d7 --- /dev/null +++ b/tools/perf/util/sample.c @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include "sample.h" +#include "debug.h" +#include "thread.h" +#include <elf.h> +#ifndef EM_CSKY +#define EM_CSKY 252 +#endif +#ifndef EM_LOONGARCH +#define EM_LOONGARCH 258 +#endif +#include <linux/zalloc.h> +#include <stdlib.h> +#include <string.h> +#include "../../arch/x86/include/asm/insn.h" + +void perf_sample__init(struct perf_sample *sample, bool all) +{ + if (all) { + memset(sample, 0, sizeof(*sample)); + } else { + sample->evsel = NULL; + sample->user_regs = NULL; + sample->intr_regs = NULL; + sample->merged_callchain = false; + sample->callchain = NULL; + } +} + +void perf_sample__exit(struct perf_sample *sample) +{ + zfree(&sample->user_regs); + zfree(&sample->intr_regs); + if (sample->merged_callchain) { + zfree(&sample->callchain); + sample->merged_callchain = false; + } +} + +struct regs_dump *perf_sample__user_regs(struct perf_sample *sample) +{ + if (!sample->user_regs) { + sample->user_regs = zalloc(sizeof(*sample->user_regs)); + if (!sample->user_regs) + pr_err("Failure to allocate sample user_regs"); + } + return sample->user_regs; +} + + +struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample) +{ + if (!sample->intr_regs) { + sample->intr_regs = zalloc(sizeof(*sample->intr_regs)); + if (!sample->intr_regs) + pr_err("Failure to allocate sample intr_regs"); + } + return sample->intr_regs; +} + +static int elf_machine_max_instruction_length(uint16_t e_machine) +{ + switch (e_machine) { + /* Fixed 4-byte (32-bit) architectures */ + case EM_AARCH64: + case EM_PPC: + case EM_PPC64: + case EM_MIPS: + case EM_SPARC: + case EM_SPARCV9: + case EM_ALPHA: + case EM_LOONGARCH: + case EM_PARISC: + case EM_SH: + return 4; + + /* Variable length or mixed-mode architectures */ + case EM_ARM: /* Variable due to Thumb/Thumb-2 */ + case EM_RISCV: /* Variable due to Compressed (C) extension */ + case EM_CSKY: /* Variable (16 or 32 bit) */ + case EM_ARC: /* Variable (ARCompact) */ + return 4; + case EM_S390: /* Variable (2, 4, or 6 bytes) */ + return 6; + case EM_68K: + return 10; + case EM_386: + case EM_X86_64: + return 15; + case EM_XTENSA: /* Variable (FLIX) */ + return 16; + default: + return MAX_INSN; + } +} + +void perf_sample__fetch_insn(struct perf_sample *sample, + struct thread *thread, + struct machine *machine) +{ + int ret, len; + bool is64bit = false; + uint16_t e_machine; + + if (!sample->ip || sample->insn_len != 0) + return; + + e_machine = thread__e_machine(thread, machine, /*e_flags=*/NULL); + len = elf_machine_max_instruction_length(e_machine); + len = thread__memcpy(thread, machine, sample->insn, + sample->ip, len, + &is64bit); + if (len <= 0) + return; + + sample->insn_len = len; + + if (e_machine == EM_386 || e_machine == EM_X86_64) { + /* Refine the x86 instruction length with the decoder. */ + struct insn insn; + + ret = insn_decode(&insn, sample->insn, len, + is64bit ? INSN_MODE_64 : INSN_MODE_32); + if (ret >= 0 && insn.length <= len) + sample->insn_len = insn.length; + } +} diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h index 70b2c3135555..e556c9b656ea 100644 --- a/tools/perf/util/sample.h +++ b/tools/perf/util/sample.h @@ -5,6 +5,10 @@ #include <linux/perf_event.h> #include <linux/types.h> +struct evsel; +struct machine; +struct thread; + /* number of register is bound by the number of bits in regs_dump::mask (64) */ #define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64)) @@ -67,61 +71,189 @@ struct aux_sample { }; struct simd_flags { - u64 arch:1, /* architecture (isa) */ - pred:2; /* predication */ + u8 arch: 2, /* architecture (isa) */ + pred: 3, /* predication */ + resv: 3; /* reserved */ }; /* simd architecture flags */ -#define SIMD_OP_FLAGS_ARCH_SVE 0x01 /* ARM SVE */ +enum simd_op_flags { + SIMD_OP_FLAGS_ARCH_NONE = 0x0, /* No SIMD operation */ + SIMD_OP_FLAGS_ARCH_SVE, /* Arm SVE */ + SIMD_OP_FLAGS_ARCH_SME, /* Arm SME */ + SIMD_OP_FLAGS_ARCH_ASE, /* Arm Advanced SIMD */ +}; /* simd predicate flags */ -#define SIMD_OP_FLAGS_PRED_PARTIAL 0x01 /* partial predicate */ -#define SIMD_OP_FLAGS_PRED_EMPTY 0x02 /* empty predicate */ +enum simd_pred_flags { + SIMD_OP_FLAGS_PRED_NONE = 0x0, /* Not available */ + SIMD_OP_FLAGS_PRED_PARTIAL, /* partial predicate */ + SIMD_OP_FLAGS_PRED_EMPTY, /* empty predicate */ + SIMD_OP_FLAGS_PRED_FULL, /* full predicate */ + SIMD_OP_FLAGS_PRED_DISABLED, /* disabled predicate */ +}; +/** + * struct perf_sample + * + * A sample is generally filled in by evlist__parse_sample/evsel__parse_sample + * which fills in the variables from a "union perf_event *event" which is data + * from a perf ring buffer or perf.data file. The "event" sample is variable in + * length as determined by the perf_event_attr (in the evsel) and details within + * the sample event itself. A struct perf_sample avoids needing to care about + * the variable length nature of the original event. + * + * To avoid being excessively large parts of the struct perf_sample are pointers + * into the original sample event. In general the lifetime of a struct + * perf_sample needs to be less than the "union perf_event *event" it was + * derived from. + * + * The struct regs_dump user_regs and intr_regs are lazily allocated again for + * size reasons, due to them holding a cache of looked up registers. The + * function pair of perf_sample__init and perf_sample__exit correctly initialize + * and clean up these values. + */ struct perf_sample { + /** @evsel: Backward reference to the evsel used when constructing the sample. */ + struct evsel *evsel; + /** @ip: The sample event PERF_SAMPLE_IP value. */ u64 ip; - u32 pid, tid; + /** @pid: The sample event PERF_SAMPLE_TID pid value. */ + u32 pid; + /** @tid: The sample event PERF_SAMPLE_TID tid value. */ + u32 tid; + /** @time: The sample event PERF_SAMPLE_TIME value. */ u64 time; + /** @addr: The sample event PERF_SAMPLE_ADDR value. */ u64 addr; + /** @id: The sample event PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER value. */ u64 id; + /** @stream_id: The sample event PERF_SAMPLE_STREAM_ID value. */ u64 stream_id; + /** @period: The sample event PERF_SAMPLE_PERIOD value. */ u64 period; + /** @weight: Data determined by PERF_SAMPLE_WEIGHT or PERF_SAMPLE_WEIGHT_STRUCT. */ u64 weight; + /** @transaction: The sample event PERF_SAMPLE_TRANSACTION value. */ u64 transaction; + /** @insn_cnt: Filled in and used by intel-pt. */ u64 insn_cnt; + /** @cyc_cnt: Filled in and used by intel-pt. */ u64 cyc_cnt; + /** @cpu: The sample event PERF_SAMPLE_CPU value. */ u32 cpu; + /** + * @raw_size: The size in bytes of raw data from PERF_SAMPLE_RAW. For + * alignment reasons this should always be sizeof(u32) + * followed by a multiple of sizeof(u64). + */ u32 raw_size; + /** @data_src: The sample event PERF_SAMPLE_DATA_SRC value. */ u64 data_src; + /** @phys_addr: The sample event PERF_SAMPLE_PHYS_ADDR value. */ u64 phys_addr; + /** @data_page_size: The sample event PERF_SAMPLE_DATA_PAGE_SIZE value. */ u64 data_page_size; + /** @code_page_size: The sample event PERF_SAMPLE_CODE_PAGE_SIZE value. */ u64 code_page_size; + /** @cgroup: The sample event PERF_SAMPLE_CGROUP value. */ u64 cgroup; + /** @flags: Extra flag data from auxiliary events like intel-pt. */ u32 flags; + /** @machine_pid: The guest machine pid derived from the sample id. */ u32 machine_pid; + /** @vcpu: The guest machine vcpu derived from the sample id. */ u32 vcpu; + /** + * @insn_len: Instruction length from auxiliary events like + * intel-pt. The instruction itself is held in insn. + */ u16 insn_len; - u8 cpumode; + /** @misc: The entire struct perf_event_header misc variable. */ u16 misc; + /** + * @ins_lat: Instruction latency information from weight2 in + * PERF_SAMPLE_WEIGHT_STRUCT or auxiliary events like + * intel-pt. + */ u16 ins_lat; - union { - u16 p_stage_cyc; - u16 retire_lat; - }; - bool no_hw_idx; /* No hw_idx collected in branch_stack */ + /** + * @weight3: From PERF_SAMPLE_WEIGHT_STRUCT. On x86 holds retire_lat, on + * powerpc holds p_stage_cyc. + */ + u16 weight3; + /** + * @cpumode: The cpumode from struct perf_event_header misc variable + * masked with CPUMODE_MASK. Gives user, kernel and hypervisor + * information. + */ + u8 cpumode; + /** + * @no_hw_idx: For PERF_SAMPLE_BRANCH_STACK, true when + * PERF_SAMPLE_BRANCH_HW_INDEX isn't set. + */ + bool no_hw_idx; + /** + * @deferred_callchain: When processing PERF_SAMPLE_CALLCHAIN a deferred + * user callchain marker was encountered. + */ + bool deferred_callchain; + /** + * @merged_callchain: A synthesized merged callchain that is allocated + * and needs freeing. + */ + bool merged_callchain; + /** + * @deferred_cookie: Identifier of the deferred callchain in the later + * PERF_RECORD_CALLCHAIN_DEFERRED event. + */ + u64 deferred_cookie; + /** @insn: A copy of the sampled instruction filled in by perf_sample__fetch_insn. */ char insn[MAX_INSN]; + /** @raw_data: Pointer into the original event for PERF_SAMPLE_RAW data. */ void *raw_data; + /** + * @callchain: Pointer into the original event for PERF_SAMPLE_CALLCHAIN + * data. For deferred callchains this may be a copy that + * needs freeing, see sample__merge_deferred_callchain. + */ struct ip_callchain *callchain; + /** @branch_stack: Pointer into the original event for PERF_SAMPLE_BRANCH_STACK data. */ struct branch_stack *branch_stack; + /** + * @branch_stack_cntr: Pointer into the original event for + * PERF_SAMPLE_BRANCH_COUNTERS data. + */ u64 *branch_stack_cntr; - struct regs_dump user_regs; - struct regs_dump intr_regs; + /** @user_regs: Values and pointers into the sample for PERF_SAMPLE_REGS_USER. */ + struct regs_dump *user_regs; + /** @intr_regs: Values and pointers into the sample for PERF_SAMPLE_REGS_INTR. */ + struct regs_dump *intr_regs; + /** @user_stack: Size and pointer into the sample for PERF_SAMPLE_STACK_USER. */ struct stack_dump user_stack; + /** + * @read: The sample event PERF_SAMPLE_READ counter values. The valid + * values depend on the attr.read_format PERF_FORMAT_ values. + */ struct sample_read read; + /** + * @aux_sample: Similar to raw data but with a 64-bit size and + * alignment, PERF_SAMPLE_AUX data. + */ struct aux_sample aux_sample; + /** @simd_flags: SIMD flag information from ARM SPE auxiliary events. */ struct simd_flags simd_flags; }; +void perf_sample__init(struct perf_sample *sample, bool all); +void perf_sample__exit(struct perf_sample *sample); +struct regs_dump *perf_sample__user_regs(struct perf_sample *sample); +struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample); + +void perf_sample__fetch_insn(struct perf_sample *sample, + struct thread *thread, + struct machine *machine); + /* * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get * 8-byte alignment. diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index 2282fe3772f3..24f087b0cd11 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -3,7 +3,7 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y) endif perf-util-$(CONFIG_LIBPYTHON) += trace-event-python.o -CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum +CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum -Wno-thread-safety-analysis # -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance) CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations -Wno-switch-enum -Wno-declaration-after-statement diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index b1b5e94537e4..5a30caaec73e 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -50,6 +50,7 @@ #include "../thread-stack.h" #include "../trace-event.h" #include "../call-path.h" +#include "dwarf-regs.h" #include "map.h" #include "symbol.h" #include "thread_map.h" @@ -713,7 +714,8 @@ static void set_sample_datasrc_in_dict(PyObject *dict, _PyUnicode_FromString(decode)); } -static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, char *bf, int size) +static void regs_map(struct regs_dump *regs, uint64_t mask, uint16_t e_machine, uint32_t e_flags, + char *bf, int size) { unsigned int i = 0, r; int printed = 0; @@ -731,7 +733,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch printed += scnprintf(bf + printed, size - printed, "%5s:0x%" PRIx64 " ", - perf_reg_name(r, arch), val); + perf_reg_name(r, e_machine, e_flags), val); } } @@ -739,25 +741,37 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch static int set_regs_in_dict(PyObject *dict, struct perf_sample *sample, - struct evsel *evsel) + struct evsel *evsel, + uint16_t e_machine, + uint32_t e_flags) { struct perf_event_attr *attr = &evsel->core.attr; - const char *arch = perf_env__arch(evsel__env(evsel)); int size = (__sw_hweight64(attr->sample_regs_intr) * MAX_REG_SIZE) + 1; - char *bf = malloc(size); - if (!bf) - return -1; + char *bf = NULL; - regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size); + if (sample->intr_regs) { + bf = malloc(size); + if (!bf) + return -1; - pydict_set_item_string_decref(dict, "iregs", - _PyUnicode_FromString(bf)); + regs_map(sample->intr_regs, attr->sample_regs_intr, e_machine, e_flags, bf, size); - regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, size); + pydict_set_item_string_decref(dict, "iregs", + _PyUnicode_FromString(bf)); + } + + if (sample->user_regs) { + if (!bf) { + bf = malloc(size); + if (!bf) + return -1; + } + regs_map(sample->user_regs, attr->sample_regs_user, e_machine, e_flags, bf, size); - pydict_set_item_string_decref(dict, "uregs", - _PyUnicode_FromString(bf)); + pydict_set_item_string_decref(dict, "uregs", + _PyUnicode_FromString(bf)); + } free(bf); return 0; @@ -769,14 +783,13 @@ static void set_sym_in_dict(PyObject *dict, struct addr_location *al, const char *sym_field, const char *symoff_field, const char *map_pgoff) { - char sbuild_id[SBUILD_ID_SIZE]; - if (al->map) { + char sbuild_id[SBUILD_ID_SIZE]; struct dso *dso = map__dso(al->map); pydict_set_item_string_decref(dict, dso_field, _PyUnicode_FromString(dso__name(dso))); - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); pydict_set_item_string_decref(dict, dso_bid_field, _PyUnicode_FromString(sbuild_id)); pydict_set_item_string_decref(dict, dso_map_start, @@ -824,6 +837,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, PyObject *callchain) { PyObject *dict, *dict_sample, *brstack, *brstacksym; + uint16_t e_machine = EM_HOST; + uint32_t e_flags = EF_HOST; dict = PyDict_New(); if (!dict) @@ -910,7 +925,10 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, PyLong_FromUnsignedLongLong(sample->cyc_cnt)); } - if (set_regs_in_dict(dict, sample, evsel)) + if (al->thread) + e_machine = thread__e_machine(al->thread, /*machine=*/NULL, &e_flags); + + if (set_regs_in_dict(dict, sample, evsel, e_machine, e_flags)) Py_FatalError("Failed to setting regs in dict"); return dict; @@ -1227,7 +1245,7 @@ static int python_export_dso(struct db_export *dbe, struct dso *dso, char sbuild_id[SBUILD_ID_SIZE]; PyObject *t; - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); t = tuple_new(5); @@ -1295,7 +1313,7 @@ static void python_export_sample_table(struct db_export *dbe, tuple_set_d64(t, 0, es->db_id); tuple_set_d64(t, 1, es->evsel->db_id); - tuple_set_d64(t, 2, maps__machine(es->al->maps)->db_id); + tuple_set_d64(t, 2, maps__machine(thread__maps(es->al->thread))->db_id); tuple_set_d64(t, 3, thread__db_id(es->al->thread)); tuple_set_d64(t, 4, es->comm_db_id); tuple_set_d64(t, 5, es->dso_db_id); @@ -1683,7 +1701,7 @@ static void python_process_stat(struct perf_stat_config *config, struct perf_cpu_map *cpus = counter->core.cpus; for (int thread = 0; thread < perf_thread_map__nr(threads); thread++) { - int idx; + unsigned int idx; struct perf_cpu cpu; perf_cpu_map__for_each_cpu(cpu, idx, cpus) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c06e3020a976..fe0de2a0277f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -12,10 +12,12 @@ #include <sys/types.h> #include <sys/mman.h> #include <perf/cpumap.h> +#include <perf/event.h> #include "map_symbol.h" #include "branch.h" #include "debug.h" +#include "dwarf-regs.h" #include "env.h" #include "evlist.h" #include "evsel.h" @@ -129,15 +131,23 @@ static int ordered_events__deliver_event(struct ordered_events *oe, { struct perf_session *session = container_of(oe, struct perf_session, ordered_events); + int ret = perf_session__deliver_event(session, event->event, + session->tool, event->file_offset, + event->file_path); - return perf_session__deliver_event(session, event->event, - session->tool, event->file_offset, - event->file_path); + if (ret) { + pr_err("%#" PRIx64 " [%#x]: ordered event processing failed (%d) for event of type: %s (%d)\n", + event->file_offset, event->event->header.size, ret, + perf_event__name(event->event->header.type), + event->event->header.type); + } + return ret; } struct perf_session *__perf_session__new(struct perf_data *data, struct perf_tool *tool, - bool trace_event_repipe) + bool trace_event_repipe, + struct perf_env *host_env) { int ret = -ENOMEM; struct perf_session *session = zalloc(sizeof(*session)); @@ -176,7 +186,7 @@ struct perf_session *__perf_session__new(struct perf_data *data, perf_session__set_comm_exec(session); } - evlist__init_trace_event_sample_raw(session->evlist); + evlist__init_trace_event_sample_raw(session->evlist, &session->header.env); /* Open the directory data. */ if (data->is_dir) { @@ -190,8 +200,11 @@ struct perf_session *__perf_session__new(struct perf_data *data, symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); } } else { - session->machines.host.env = &perf_env; + assert(host_env != NULL); + session->machines.host.env = host_env; } + if (session->evlist) + session->evlist->session = session; session->machines.host.single_address_space = perf_env__single_address_space(session->machines.host.env); @@ -692,6 +705,20 @@ static void perf_event__time_conv_swap(union perf_event *event, } } +static void +perf_event__schedstat_cpu_swap(union perf_event *event __maybe_unused, + bool sample_id_all __maybe_unused) +{ + /* FIXME */ +} + +static void +perf_event__schedstat_domain_swap(union perf_event *event __maybe_unused, + bool sample_id_all __maybe_unused) +{ + /* FIXME */ +} + typedef void (*perf_event__swap_op)(union perf_event *event, bool sample_id_all); @@ -715,6 +742,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_CGROUP] = perf_event__cgroup_swap, [PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap, [PERF_RECORD_AUX_OUTPUT_HW_ID] = perf_event__all64_swap, + [PERF_RECORD_CALLCHAIN_DEFERRED] = perf_event__all64_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, @@ -730,6 +758,8 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_STAT_ROUND] = perf_event__stat_round_swap, [PERF_RECORD_EVENT_UPDATE] = perf_event__event_update_swap, [PERF_RECORD_TIME_CONV] = perf_event__time_conv_swap, + [PERF_RECORD_SCHEDSTAT_CPU] = perf_event__schedstat_cpu_swap, + [PERF_RECORD_SCHEDSTAT_DOMAIN] = perf_event__schedstat_domain_swap, [PERF_RECORD_HEADER_MAX] = NULL, }; @@ -835,6 +865,28 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample) } } +static const char *callchain_context_str(u64 ip) +{ + switch (ip) { + case PERF_CONTEXT_HV: + return " (PERF_CONTEXT_HV)"; + case PERF_CONTEXT_KERNEL: + return " (PERF_CONTEXT_KERNEL)"; + case PERF_CONTEXT_USER: + return " (PERF_CONTEXT_USER)"; + case PERF_CONTEXT_GUEST: + return " (PERF_CONTEXT_GUEST)"; + case PERF_CONTEXT_GUEST_KERNEL: + return " (PERF_CONTEXT_GUEST_KERNEL)"; + case PERF_CONTEXT_GUEST_USER: + return " (PERF_CONTEXT_GUEST_USER)"; + case PERF_CONTEXT_USER_DEFERRED: + return " (PERF_CONTEXT_USER_DEFERRED)"; + default: + return ""; + } +} + static void callchain__printf(struct evsel *evsel, struct perf_sample *sample) { @@ -847,8 +899,12 @@ static void callchain__printf(struct evsel *evsel, printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr); for (i = 0; i < callchain->nr; i++) - printf("..... %2d: %016" PRIx64 "\n", - i, callchain->ips[i]); + printf("..... %2d: %016" PRIx64 "%s\n", + i, callchain->ips[i], + callchain_context_str(callchain->ips[i])); + + if (sample->deferred_callchain) + printf("...... (deferred)\n"); } static void branch_stack__printf(struct perf_sample *sample, @@ -910,7 +966,7 @@ static void branch_stack__printf(struct perf_sample *sample, } } -static void regs_dump__printf(u64 mask, u64 *regs, const char *arch) +static void regs_dump__printf(u64 mask, u64 *regs, uint16_t e_machine, uint32_t e_flags) { unsigned rid, i = 0; @@ -918,7 +974,7 @@ static void regs_dump__printf(u64 mask, u64 *regs, const char *arch) u64 val = regs[i++]; printf(".... %-5s 0x%016" PRIx64 "\n", - perf_reg_name(rid, arch), val); + perf_reg_name(rid, e_machine, e_flags), val); } } @@ -936,7 +992,8 @@ static inline const char *regs_dump_abi(struct regs_dump *d) return regs_abi[d->abi]; } -static void regs__printf(const char *type, struct regs_dump *regs, const char *arch) +static void regs__printf(const char *type, struct regs_dump *regs, + uint16_t e_machine, uint32_t e_flags) { u64 mask = regs->mask; @@ -945,23 +1002,33 @@ static void regs__printf(const char *type, struct regs_dump *regs, const char *a mask, regs_dump_abi(regs)); - regs_dump__printf(mask, regs->regs, arch); + regs_dump__printf(mask, regs->regs, e_machine, e_flags); } -static void regs_user__printf(struct perf_sample *sample, const char *arch) +static void regs_user__printf(struct perf_sample *sample, uint16_t e_machine, uint32_t e_flags) { - struct regs_dump *user_regs = &sample->user_regs; + struct regs_dump *user_regs; + + if (!sample->user_regs) + return; + + user_regs = perf_sample__user_regs(sample); if (user_regs->regs) - regs__printf("user", user_regs, arch); + regs__printf("user", user_regs, e_machine, e_flags); } -static void regs_intr__printf(struct perf_sample *sample, const char *arch) +static void regs_intr__printf(struct perf_sample *sample, uint16_t e_machine, uint32_t e_flags) { - struct regs_dump *intr_regs = &sample->intr_regs; + struct regs_dump *intr_regs; + + if (!sample->intr_regs) + return; + + intr_regs = perf_sample__intr_regs(sample); if (intr_regs->regs) - regs__printf("intr", intr_regs, arch); + regs__printf("intr", intr_regs, e_machine, e_flags); } static void stack_user__printf(struct stack_dump *dump) @@ -1050,21 +1117,29 @@ char *get_page_size_name(u64 size, char *str) return str; } -static void dump_sample(struct evsel *evsel, union perf_event *event, - struct perf_sample *sample, const char *arch) +static void dump_sample(struct machine *machine, struct evsel *evsel, union perf_event *event, + struct perf_sample *sample) { u64 sample_type; char str[PAGE_SIZE_NAME_LEN]; + uint16_t e_machine = EM_NONE; + uint32_t e_flags = 0; if (!dump_trace) return; + sample_type = evsel->core.attr.sample_type; + + if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR)) { + struct thread *thread = machine__find_thread(machine, sample->pid, sample->pid); + + e_machine = thread__e_machine(thread, machine, &e_flags); + } + printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", event->header.misc, sample->pid, sample->tid, sample->ip, sample->period, sample->addr); - sample_type = evsel->core.attr.sample_type; - if (evsel__has_callchain(evsel)) callchain__printf(evsel, sample); @@ -1072,10 +1147,10 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, branch_stack__printf(sample, evsel); if (sample_type & PERF_SAMPLE_REGS_USER) - regs_user__printf(sample, arch); + regs_user__printf(sample, e_machine, e_flags); if (sample_type & PERF_SAMPLE_REGS_INTR) - regs_intr__printf(sample, arch); + regs_intr__printf(sample, e_machine, e_flags); if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); @@ -1084,7 +1159,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, printf("... weight: %" PRIu64 "", sample->weight); if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { printf(",0x%"PRIx16"", sample->ins_lat); - printf(",0x%"PRIx16"", sample->p_stage_cyc); + printf(",0x%"PRIx16"", sample->weight3); } printf("\n"); } @@ -1108,6 +1183,19 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, sample_read__printf(sample, evsel->core.attr.read_format); } +static void dump_deferred_callchain(struct evsel *evsel, union perf_event *event, + struct perf_sample *sample) +{ + if (!dump_trace) + return; + + printf("(IP, 0x%x): %d/%d: %#" PRIx64 "\n", + event->header.misc, sample->pid, sample->tid, sample->deferred_cookie); + + if (evsel__has_callchain(evsel)) + callchain__printf(evsel, sample); +} + static void dump_read(struct evsel *evsel, union perf_event *event) { struct perf_record_read *read_event = &event->read; @@ -1176,8 +1264,9 @@ static int deliver_sample_value(struct evlist *evlist, bool per_thread) { struct perf_sample_id *sid = evlist__id2sid(evlist, v->id); - struct evsel *evsel; + struct evsel *saved_evsel = sample->evsel; u64 *storage = NULL; + int ret; if (sid) { storage = perf_sample_id__get_period_storage(sid, sample->tid, per_thread); @@ -1201,8 +1290,10 @@ static int deliver_sample_value(struct evlist *evlist, if (!sample->period) return 0; - evsel = container_of(sid->evsel, struct evsel, core); - return tool->sample(tool, event, sample, evsel, machine); + sample->evsel = container_of(sid->evsel, struct evsel, core); + ret = tool->sample(tool, event, sample, sample->evsel, machine); + sample->evsel = saved_evsel; + return ret; } static int deliver_sample_group(struct evlist *evlist, @@ -1253,6 +1344,113 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool per_thread); } +/* + * Samples with deferred callchains should wait for the next matching + * PERF_RECORD_CALLCHAIN_RECORD entries. Keep the events in a list and + * deliver them once it finds the callchains. + */ +struct deferred_event { + struct list_head list; + union perf_event *event; +}; + +/* + * This is called when a deferred callchain record comes up. Find all matching + * samples, merge the callchains and process them. + */ +static int evlist__deliver_deferred_callchain(struct evlist *evlist, + const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct deferred_event *de, *tmp; + int ret = 0; + + if (!tool->merge_deferred_callchains) { + struct evsel *saved_evsel = sample->evsel; + + sample->evsel = evlist__id2evsel(evlist, sample->id); + ret = tool->callchain_deferred(tool, event, sample, + sample->evsel, machine); + sample->evsel = saved_evsel; + return ret; + } + + list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) { + struct perf_sample orig_sample; + + perf_sample__init(&orig_sample, /*all=*/false); + ret = evlist__parse_sample(evlist, de->event, &orig_sample); + if (ret < 0) { + pr_err("failed to parse original sample\n"); + perf_sample__exit(&orig_sample); + break; + } + + if (sample->tid != orig_sample.tid) { + perf_sample__exit(&orig_sample); + continue; + } + + if (event->callchain_deferred.cookie == orig_sample.deferred_cookie) + sample__merge_deferred_callchain(&orig_sample, sample); + else + orig_sample.deferred_callchain = false; + + orig_sample.evsel = evlist__id2evsel(evlist, orig_sample.id); + ret = evlist__deliver_sample(evlist, tool, de->event, + &orig_sample, orig_sample.evsel, machine); + + perf_sample__exit(&orig_sample); + list_del(&de->list); + free(de->event); + free(de); + + if (ret) + break; + } + return ret; +} + +/* + * This is called at the end of the data processing for the session. Flush the + * remaining samples as there's no hope for matching deferred callchains. + */ +static int session__flush_deferred_samples(struct perf_session *session, + const struct perf_tool *tool) +{ + struct evlist *evlist = session->evlist; + struct machine *machine = &session->machines.host; + struct deferred_event *de, *tmp; + int ret = 0; + + list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) { + struct perf_sample sample; + + perf_sample__init(&sample, /*all=*/false); + ret = evlist__parse_sample(evlist, de->event, &sample); + if (ret < 0) { + pr_err("failed to parse original sample\n"); + perf_sample__exit(&sample); + break; + } + + sample.evsel = evlist__id2evsel(evlist, sample.id); + ret = evlist__deliver_sample(evlist, tool, de->event, + &sample, sample.evsel, machine); + + perf_sample__exit(&sample); + list_del(&de->list); + free(de->event); + free(de); + + if (ret) + break; + } + return ret; +} + static int machines__deliver_event(struct machines *machines, struct evlist *evlist, union perf_event *event, @@ -1265,8 +1463,12 @@ static int machines__deliver_event(struct machines *machines, dump_event(evlist, event, file_offset, sample, file_path); - evsel = evlist__id2evsel(evlist, sample->id); + if (!sample->evsel) + sample->evsel = evlist__id2evsel(evlist, sample->id); + else + assert(sample->evsel == evlist__id2evsel(evlist, sample->id)); + evsel = sample->evsel; machine = machines__find_for_cpumode(machines, event, sample); switch (event->header.type) { @@ -1277,10 +1479,26 @@ static int machines__deliver_event(struct machines *machines, } if (machine == NULL) { ++evlist->stats.nr_unprocessable_samples; - dump_sample(evsel, event, sample, perf_env__arch(NULL)); + dump_sample(machine, evsel, event, sample); + return 0; + } + dump_sample(machine, evsel, event, sample); + if (sample->deferred_callchain && tool->merge_deferred_callchains) { + struct deferred_event *de = malloc(sizeof(*de)); + size_t sz = event->header.size; + + if (de == NULL) + return -ENOMEM; + + de->event = malloc(sz); + if (de->event == NULL) { + free(de); + return -ENOMEM; + } + memcpy(de->event, event, sz); + list_add_tail(&de->list, &evlist->deferred_samples); return 0; } - dump_sample(evsel, event, sample, perf_env__arch(machine->env)); return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); @@ -1338,6 +1556,10 @@ static int machines__deliver_event(struct machines *machines, return tool->text_poke(tool, event, sample, machine); case PERF_RECORD_AUX_OUTPUT_HW_ID: return tool->aux_output_hw_id(tool, event, sample, machine); + case PERF_RECORD_CALLCHAIN_DEFERRED: + dump_deferred_callchain(evsel, event, sample); + return evlist__deliver_deferred_callchain(evlist, tool, event, + sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; @@ -1351,25 +1573,30 @@ static int perf_session__deliver_event(struct perf_session *session, const char *file_path) { struct perf_sample sample; - int ret = evlist__parse_sample(session->evlist, event, &sample); + int ret; + perf_sample__init(&sample, /*all=*/false); + ret = evlist__parse_sample(session->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); - return ret; + goto out; } ret = auxtrace__process_event(session, event, &sample, tool); if (ret < 0) - return ret; - if (ret > 0) - return 0; + goto out; + if (ret > 0) { + ret = 0; + goto out; + } ret = machines__deliver_event(&session->machines, session->evlist, event, &sample, tool, file_offset, file_path); if (dump_trace && sample.aux_sample.size) auxtrace__dump_auxtrace_sample(session, &sample); - +out: + perf_sample__exit(&sample); return ret; } @@ -1380,11 +1607,14 @@ static s64 perf_session__process_user_event(struct perf_session *session, { struct ordered_events *oe = &session->ordered_events; const struct perf_tool *tool = session->tool; - struct perf_sample sample = { .time = 0, }; + struct perf_sample sample; int fd = perf_data__fd(session->data); - int err; + s64 err; - if (event->header.type != PERF_RECORD_COMPRESSED || perf_tool__compressed_is_stub(tool)) + perf_sample__init(&sample, /*all=*/true); + if ((event->header.type != PERF_RECORD_COMPRESSED && + event->header.type != PERF_RECORD_COMPRESSED2) || + perf_tool__compressed_is_stub(tool)) dump_event(session->evlist, event, file_offset, &sample, file_path); /* These events are processed right away */ @@ -1395,15 +1625,17 @@ static s64 perf_session__process_user_event(struct perf_session *session, perf_session__set_id_hdr_size(session); perf_session__set_comm_exec(session); } - return err; + break; case PERF_RECORD_EVENT_UPDATE: - return tool->event_update(tool, event, &session->evlist); + err = tool->event_update(tool, event, &session->evlist); + break; case PERF_RECORD_HEADER_EVENT_TYPE: /* * Deprecated, but we need to handle it for sake * of old data files create in pipe mode. */ - return 0; + err = 0; + break; case PERF_RECORD_HEADER_TRACING_DATA: /* * Setup for reading amidst mmap, but only when we @@ -1412,15 +1644,20 @@ static s64 perf_session__process_user_event(struct perf_session *session, */ if (!perf_data__is_pipe(session->data)) lseek(fd, file_offset, SEEK_SET); - return tool->tracing_data(session, event); + err = tool->tracing_data(tool, session, event); + break; case PERF_RECORD_HEADER_BUILD_ID: - return tool->build_id(session, event); + err = tool->build_id(tool, session, event); + break; case PERF_RECORD_FINISHED_ROUND: - return tool->finished_round(tool, event, oe); + err = tool->finished_round(tool, event, oe); + break; case PERF_RECORD_ID_INDEX: - return tool->id_index(session, event); + err = tool->id_index(tool, session, event); + break; case PERF_RECORD_AUXTRACE_INFO: - return tool->auxtrace_info(session, event); + err = tool->auxtrace_info(tool, session, event); + break; case PERF_RECORD_AUXTRACE: /* * Setup for reading amidst mmap, but only when we @@ -1429,35 +1666,58 @@ static s64 perf_session__process_user_event(struct perf_session *session, */ if (!perf_data__is_pipe(session->data)) lseek(fd, file_offset + event->header.size, SEEK_SET); - return tool->auxtrace(session, event); + err = tool->auxtrace(tool, session, event); + break; case PERF_RECORD_AUXTRACE_ERROR: perf_session__auxtrace_error_inc(session, event); - return tool->auxtrace_error(session, event); + err = tool->auxtrace_error(tool, session, event); + break; case PERF_RECORD_THREAD_MAP: - return tool->thread_map(session, event); + err = tool->thread_map(tool, session, event); + break; case PERF_RECORD_CPU_MAP: - return tool->cpu_map(session, event); + err = tool->cpu_map(tool, session, event); + break; case PERF_RECORD_STAT_CONFIG: - return tool->stat_config(session, event); + err = tool->stat_config(tool, session, event); + break; case PERF_RECORD_STAT: - return tool->stat(session, event); + err = tool->stat(tool, session, event); + break; case PERF_RECORD_STAT_ROUND: - return tool->stat_round(session, event); + err = tool->stat_round(tool, session, event); + break; case PERF_RECORD_TIME_CONV: session->time_conv = event->time_conv; - return tool->time_conv(session, event); + err = tool->time_conv(tool, session, event); + break; case PERF_RECORD_HEADER_FEATURE: - return tool->feature(session, event); + err = tool->feature(tool, session, event); + break; case PERF_RECORD_COMPRESSED: - err = tool->compressed(session, event, file_offset, file_path); + case PERF_RECORD_COMPRESSED2: + err = tool->compressed(tool, session, event, file_offset, file_path); if (err) dump_event(session->evlist, event, file_offset, &sample, file_path); - return err; + break; case PERF_RECORD_FINISHED_INIT: - return tool->finished_init(session, event); + err = tool->finished_init(tool, session, event); + break; + case PERF_RECORD_BPF_METADATA: + err = tool->bpf_metadata(tool, session, event); + break; + case PERF_RECORD_SCHEDSTAT_CPU: + err = tool->schedstat_cpu(tool, session, event); + break; + case PERF_RECORD_SCHEDSTAT_DOMAIN: + err = tool->schedstat_domain(tool, session, event); + break; default: - return -EINVAL; + err = -EINVAL; + break; } + perf_sample__exit(&sample); + return err; } int perf_session__deliver_synth_event(struct perf_session *session, @@ -1603,8 +1863,17 @@ static s64 perf_session__process_event(struct perf_session *session, if (session->header.needs_swap) event_swap(event, evlist__sample_id_all(evlist)); - if (event->header.type >= PERF_RECORD_HEADER_MAX) - return -EINVAL; + if (event->header.type >= PERF_RECORD_HEADER_MAX) { + /* perf should not support unaligned event, stop here. */ + if (event->header.size % sizeof(u64)) + return -EINVAL; + + /* This perf is outdated and does not support the latest event type. */ + ui__warning("Unsupported header type %u, please consider updating perf.\n", + event->header.type); + /* Skip unsupported event by returning its size. */ + return event->header.size; + } events_stats__inc(&evlist->stats, event->header.type); @@ -1862,8 +2131,10 @@ more: } if ((skip = perf_session__process_event(session, event, head, "pipe")) < 0) { - pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", - head, event->header.size, event->header.type); + pr_err("%#" PRIx64 " [%#x]: piped event processing failed for event of type: %s (%d)\n", + head, event->header.size, + perf_event__name(event->header.type), + event->header.type); err = -EINVAL; goto out_err; } @@ -1887,6 +2158,9 @@ done: err = ordered_events__flush(oe, OE_FLUSH__FINAL); if (err) goto out_err; + err = session__flush_deferred_samples(session, tool); + if (err) + goto out_err; err = auxtrace__flush_events(session, tool); if (err) goto out_err; @@ -1974,8 +2248,10 @@ static int __perf_session__process_decomp_events(struct perf_session *session) if (size < sizeof(struct perf_event_header) || (skip = perf_session__process_event(session, event, decomp->file_pos, decomp->file_path)) < 0) { - pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", - decomp->file_pos + decomp->head, event->header.size, event->header.type); + pr_err("%#" PRIx64 " [%#x]: decompress event processing failed for event of type: %s (%d)\n", + decomp->file_pos + decomp->head, event->header.size, + perf_event__name(event->header.type), + event->header.type); return -EINVAL; } @@ -2130,9 +2406,11 @@ reader__read_event(struct reader *rd, struct perf_session *session, if (size < sizeof(struct perf_event_header) || (skip = rd->process(session, event, rd->file_pos, rd->path)) < 0) { - pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n", + errno = -skip; + pr_err("%#" PRIx64 " [%#x]: processing failed for event of type: %s (%d) [%m]\n", rd->file_offset + rd->head, event->header.size, - event->header.type, strerror(-skip)); + perf_event__name(event->header.type), + event->header.type); err = skip; goto out; } @@ -2233,6 +2511,9 @@ static int __perf_session__process_events(struct perf_session *session) err = auxtrace__flush_events(session, tool); if (err) goto out_err; + err = session__flush_deferred_samples(session, tool); + if (err) + goto out_err; err = perf_session__flush_thread_stacks(session); out_err: ui_progress__finish(); @@ -2278,7 +2559,7 @@ static int __perf_session__process_dir_events(struct perf_session *session) nr_readers++; } - rd = zalloc(nr_readers * sizeof(struct reader)); + rd = calloc(nr_readers, sizeof(struct reader)); if (!rd) return -ENOMEM; @@ -2302,7 +2583,7 @@ static int __perf_session__process_dir_events(struct perf_session *session) if (!data->dir.files[i].size) continue; rd[readers] = (struct reader) { - .fd = data->dir.files[i].fd, + .fd = perf_data_file__fd(&data->dir.files[i]), .path = data->dir.files[i].path, .data_size = data->dir.files[i].size, .data_offset = 0, @@ -2353,6 +2634,10 @@ static int __perf_session__process_dir_events(struct perf_session *session) if (ret) goto out_err; + ret = session__flush_deferred_samples(session, tool); + if (ret) + goto out_err; + ret = perf_session__flush_thread_stacks(session); out_err: ui_progress__finish(); @@ -2403,9 +2688,21 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg) return false; } +bool perf_session__has_switch_events(struct perf_session *session) +{ + struct evsel *evsel; + + evlist__for_each_entry(session->evlist, evsel) { + if (evsel->core.attr.context_switch) + return true; + } + + return false; +} + int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr) { - char *bracket; + char *bracket, *name; struct ref_reloc_sym *ref; struct kmap *kmap; @@ -2413,13 +2710,13 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u6 if (ref == NULL) return -ENOMEM; - ref->name = strdup(symbol_name); + ref->name = name = strdup(symbol_name); if (ref->name == NULL) { free(ref); return -ENOMEM; } - bracket = strchr(ref->name, ']'); + bracket = strchr(name, ']'); if (bracket) *bracket = '\0'; @@ -2459,11 +2756,14 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) size_t perf_session__fprintf(struct perf_session *session, FILE *fp) { - /* - * FIXME: Here we have to actually print all the machines in this - * session, not just the host... - */ - return machine__fprintf(&session->machines.host, fp); + size_t ret = machine__fprintf(&session->machines.host, fp); + + for (struct rb_node *nd = rb_first_cached(&session->machines.guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + + ret += machine__fprintf(pos, fp); + } + return ret; } void perf_session__dump_kmaps(struct perf_session *session) @@ -2492,9 +2792,10 @@ struct evsel *perf_session__find_first_evtype(struct perf_session *session, int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap) { - int i, err = -1; + unsigned int i; + int err = -1; struct perf_cpu_map *map; - int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS); + int nr_cpus = min(perf_session__env(session)->nr_cpus_avail, MAX_NR_CPUS); struct perf_cpu cpu; for (i = 0; i < PERF_TYPE_MAX; ++i) { @@ -2579,7 +2880,8 @@ static int perf_session__set_guest_cpu(struct perf_session *session, pid_t pid, return 0; } -int perf_event__process_id_index(struct perf_session *session, +int perf_event__process_id_index(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { struct evlist *evlist = session->evlist; @@ -2683,3 +2985,73 @@ int perf_session__dsos_hit_all(struct perf_session *session) return 0; } + +struct perf_env *perf_session__env(struct perf_session *session) +{ + return &session->header.env; +} + +struct perf_session__e_machine_cb_args { + uint32_t e_flags; + uint16_t e_machine; +}; + +static int perf_session__e_machine_cb(struct thread *thread, void *_args) +{ + struct perf_session__e_machine_cb_args *args = _args; + + args->e_machine = thread__e_machine(thread, /*machine=*/NULL, &args->e_flags); + return args->e_machine != EM_NONE ? 1 : 0; +} + +/* + * Note, a machine may have mixed 32-bit and 64-bit processes and so mixed + * e_machines. Use thread__e_machine when this matters. + */ +uint16_t perf_session__e_machine(struct perf_session *session, uint32_t *e_flags) +{ + struct perf_session__e_machine_cb_args args = { + .e_machine = EM_NONE, + }; + struct perf_env *env; + + if (!session) { + /* Default to assuming a host machine. */ + if (e_flags) + *e_flags = EF_HOST; + + return EM_HOST; + } + + env = perf_session__env(session); + if (env && env->e_machine != EM_NONE) { + if (e_flags) + *e_flags = env->e_flags; + + return env->e_machine; + } + + machines__for_each_thread(&session->machines, + perf_session__e_machine_cb, + &args); + + if (args.e_machine != EM_NONE) { + if (env) { + env->e_machine = args.e_machine; + env->e_flags = args.e_flags; + } + if (e_flags) + *e_flags = args.e_flags; + + return args.e_machine; + } + + /* + * Couldn't determine from the perf_env or current set of + * threads. Default to the host. + */ + if (e_flags) + *e_flags = EF_HOST; + + return EM_HOST; +} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index bcf1bcf06959..f05f0d4a6c23 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -107,12 +107,13 @@ struct perf_tool; struct perf_session *__perf_session__new(struct perf_data *data, struct perf_tool *tool, - bool trace_event_repipe); + bool trace_event_repipe, + struct perf_env *host_env); static inline struct perf_session *perf_session__new(struct perf_data *data, struct perf_tool *tool) { - return __perf_session__new(data, tool, /*trace_event_repipe=*/false); + return __perf_session__new(data, tool, /*trace_event_repipe=*/false, /*host_env=*/NULL); } void perf_session__delete(struct perf_session *session); @@ -141,6 +142,7 @@ int perf_session__resolve_callchain(struct perf_session *session, struct symbol **parent); bool perf_session__has_traces(struct perf_session *session, const char *msg); +bool perf_session__has_switch_events(struct perf_session *session); void perf_event__attr_swap(struct perf_event_attr *attr); @@ -200,11 +202,15 @@ int perf_session__deliver_synth_attr_event(struct perf_session *session, int perf_session__dsos_hit_all(struct perf_session *session); -int perf_event__process_id_index(struct perf_session *session, +int perf_event__process_id_index(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); int perf_event__process_finished_round(const struct perf_tool *tool, union perf_event *event, struct ordered_events *oe); +struct perf_env *perf_session__env(struct perf_session *session); +uint16_t perf_session__e_machine(struct perf_session *session, uint32_t *e_flags); + #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 649550e9b7aa..b65b1792ca05 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,8 +1,10 @@ from os import getenv, path from subprocess import Popen, PIPE from re import sub +import shlex cc = getenv("CC") +assert cc, "Environment variable CC not set" # Check if CC has options, as is the case in yocto, where it uses CC="cc --sysroot..." cc_tokens = cc.split() @@ -12,12 +14,26 @@ if len(cc_tokens) > 1: else: cc_options = "" +# ignore optional stderr could be None as it is set to PIPE to avoid that. +# mypy: disable-error-code="union-attr" cc_is_clang = b"clang version" in Popen([cc, "-v"], stderr=PIPE).stderr.readline() -src_feature_tests = getenv('srctree') + '/tools/build/feature' + +srctree = getenv('srctree') +assert srctree, "Environment variable srctree, for the Linux sources, not set" +src_feature_tests = f'{srctree}/tools/build/feature' def clang_has_option(option): - cc_output = Popen([cc, cc_options + option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() - return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o) or (b"unknown warning option" in o))] == [ ] + error_substrings = ( + b"unknown argument", + b"is not supported", + b"unknown warning option" + ) + cmd = shlex.split(f"{cc} {cc_options} {option}") + [ + "-o", "/dev/null", + path.join(src_feature_tests, "test-hello.c") + ] + cc_output = Popen(cmd, stderr=PIPE).stderr.readlines() + return not any(any(error in line for error in error_substrings) for line in cc_output) if cc_is_clang: from sysconfig import get_config_vars @@ -71,7 +87,7 @@ else: # The python headers have mixed code with declarations (decls after asserts, for instance) cflags += [ "-Wno-declaration-after-statement" ] -src_perf = getenv('srctree') + '/tools/perf' +src_perf = f'{srctree}/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 3dd33721823f..0020089cb13c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <ctype.h> #include <errno.h> #include <inttypes.h> #include <regex.h> @@ -30,6 +31,7 @@ #include "time-utils.h" #include "cgroup.h" #include "machine.h" +#include "session.h" #include "trace-event.h" #include <linux/kernel.h> #include <linux/string.h> @@ -42,11 +44,11 @@ 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_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles"; +static 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,blocked,local_ins_lat,local_p_stage_cyc"; -const char default_top_sort_order[] = "dso,symbol"; -const char default_diff_sort_order[] = "dso,symbol"; -const char default_tracepoint_sort_order[] = "trace"; +static const char default_top_sort_order[] = "dso,symbol"; +static const char default_diff_sort_order[] = "dso,symbol"; +static const char default_tracepoint_sort_order[] = "trace"; const char *sort_order; const char *field_order; regex_t ignore_callees_regex; @@ -141,6 +143,43 @@ struct sort_entry sort_thread = { .se_width_idx = HISTC_THREAD, }; +/* --sort tgid */ + +static int64_t +sort__tgid_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return thread__pid(right->thread) - thread__pid(left->thread); +} + +static int hist_entry__tgid_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + int tgid = thread__pid(he->thread); + const char *comm = NULL; + + /* display comm of the thread-group leader */ + if (thread__pid(he->thread) == thread__tid(he->thread)) { + comm = thread__comm_str(he->thread); + } else { + struct maps *maps = thread__maps(he->thread); + struct thread *leader = machine__find_thread(maps__machine(maps), + tgid, tgid); + if (leader) { + comm = thread__comm_str(leader); + thread__put(leader); + } + } + width = max(7U, width) - 8; + return repsep_snprintf(bf, size, "%7d:%-*.*s", tgid, width, width, comm ?: ""); +} + +static struct sort_entry sort_tgid = { + .se_header = " Tgid:Command", + .se_cmp = sort__tgid_cmp, + .se_snprintf = hist_entry__tgid_snprintf, + .se_width_idx = HISTC_TGID, +}; + /* --sort simd */ static int64_t @@ -156,8 +195,12 @@ static const char *hist_entry__get_simd_name(struct simd_flags *simd_flags) { u64 arch = simd_flags->arch; - if (arch & SIMD_OP_FLAGS_ARCH_SVE) + if (arch == SIMD_OP_FLAGS_ARCH_SVE) return "SVE"; + else if (arch == SIMD_OP_FLAGS_ARCH_SME) + return "SME"; + else if (arch == SIMD_OP_FLAGS_ARCH_ASE) + return "ASE"; else return "n/a"; } @@ -166,21 +209,26 @@ static int hist_entry__simd_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width __maybe_unused) { const char *name; + const char *pred_str = "."; if (!he->simd_flags.arch) return repsep_snprintf(bf, size, ""); name = hist_entry__get_simd_name(&he->simd_flags); - if (he->simd_flags.pred & SIMD_OP_FLAGS_PRED_EMPTY) - return repsep_snprintf(bf, size, "[e] %s", name); - else if (he->simd_flags.pred & SIMD_OP_FLAGS_PRED_PARTIAL) - return repsep_snprintf(bf, size, "[p] %s", name); + if (he->simd_flags.pred == SIMD_OP_FLAGS_PRED_EMPTY) + pred_str = "e"; + else if (he->simd_flags.pred == SIMD_OP_FLAGS_PRED_PARTIAL) + pred_str = "p"; + else if (he->simd_flags.pred == SIMD_OP_FLAGS_PRED_DISABLED) + pred_str = "d"; + else if (he->simd_flags.pred == SIMD_OP_FLAGS_PRED_FULL) + pred_str = "f"; - return repsep_snprintf(bf, size, "[.] %s", name); + return repsep_snprintf(bf, size, "[%s] %s", pred_str, name); } -struct sort_entry sort_simd = { +static struct sort_entry sort_simd = { .se_header = "Simd ", .se_cmp = sort__simd_cmp, .se_snprintf = hist_entry__simd_snprintf, @@ -228,6 +276,115 @@ struct sort_entry sort_comm = { .se_width_idx = HISTC_COMM, }; +/* --sort comm_nodigit */ + +size_t sort__comm_nodigit_len(struct hist_entry *entry) +{ + const char *comm = comm__str(entry->comm); + size_t index, len_nodigit = 0; + bool in_number = false; + + if (!comm) + return 0; + + for (index = 0; comm[index]; index++) { + if (!isdigit((unsigned char)comm[index])) { + in_number = false; + len_nodigit++; + } else if (!in_number) { + in_number = true; + len_nodigit += 3; /* <N> */ + } + } + + return len_nodigit; +} + +static int64_t strcmp_nodigit(const char *left, const char *right) +{ + for (;;) { + while (*left && isdigit((unsigned char)*left)) + left++; + while (*right && isdigit((unsigned char)*right)) + right++; + if (*left == *right && !*left) { + return 0; + } else if (*left == *right) { + left++; + right++; + } else { + return (int64_t)((unsigned char)*left - (unsigned char)*right); + } + } +} + +static int64_t +sort__comm_nodigit_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return strcmp_nodigit(comm__str(right->comm), comm__str(left->comm)); +} + +static int64_t +sort__comm_nodigit_collapse(struct hist_entry *left, struct hist_entry *right) +{ + return strcmp_nodigit(comm__str(right->comm), comm__str(left->comm)); +} + +static int64_t +sort__comm_nodigit_sort(struct hist_entry *left, struct hist_entry *right) +{ + return strcmp_nodigit(comm__str(right->comm), comm__str(left->comm)); +} + +static int hist_entry__comm_nodigit_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + int ret = 0; + unsigned int print_len, printed = 0, start = 0, end = 0; + bool in_digit; + const char *comm = comm__str(he->comm), *print; + + while (printed < width && printed < size && comm[start]) { + in_digit = !!isdigit((unsigned char)comm[start]); + end = start + 1; + while (comm[end] && !!isdigit((unsigned char)comm[end]) == in_digit) + end++; + if (in_digit) { + print_len = 3; /* <N> */ + print = "<N>"; + } else { + print_len = end - start; + print = &comm[start]; + } + print_len = min(print_len, width - printed); + ret = repsep_snprintf(bf + printed, size - printed, "%-.*s", + print_len, print); + if (ret < 0) + return ret; + start = end; + printed += ret; + } + /* Pad to width if necessary */ + if (printed < width && printed < size) { + ret = repsep_snprintf(bf + printed, size - printed, "%-*.*s", + width - printed, width - printed, ""); + if (ret < 0) + return ret; + printed += ret; + } + return printed; +} + +struct sort_entry sort_comm_nodigit = { + .se_header = "CommandNoDigit", + .se_cmp = sort__comm_nodigit_cmp, + .se_collapse = sort__comm_nodigit_collapse, + .se_sort = sort__comm_nodigit_sort, + .se_snprintf = hist_entry__comm_nodigit_snprintf, + .se_filter = hist_entry__thread_filter, + .se_width_idx = HISTC_COMM_NODIGIT, +}; + /* --sort dso */ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) @@ -457,7 +614,7 @@ hist_entry__symoff_snprintf(struct hist_entry *he, char *bf, size_t size, unsign return repsep_snprintf(bf, size, "[%c] %s+0x%llx", he->level, sym->name, he->ip - sym->start); } -struct sort_entry sort_sym_offset = { +static struct sort_entry sort_sym_offset = { .se_header = "Symbol Offset", .se_cmp = sort__symoff_cmp, .se_sort = sort__symoff_sort, @@ -568,7 +725,7 @@ static int hist_entry__srcline_from_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_from); } -struct sort_entry sort_srcline_from = { +static struct sort_entry sort_srcline_from = { .se_header = "From Source:Line", .se_cmp = sort__srcline_from_cmp, .se_collapse = sort__srcline_from_collapse, @@ -616,7 +773,7 @@ static int hist_entry__srcline_to_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*.*s", width, width, he->branch_info->srcline_to); } -struct sort_entry sort_srcline_to = { +static struct sort_entry sort_srcline_to = { .se_header = "To Source:Line", .se_cmp = sort__srcline_to_cmp, .se_collapse = sort__srcline_to_collapse, @@ -652,7 +809,7 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, tmp); } -struct sort_entry sort_sym_ipc = { +static struct sort_entry sort_sym_ipc = { .se_header = "IPC [IPC Coverage]", .se_cmp = sort__sym_cmp, .se_snprintf = hist_entry__sym_ipc_snprintf, @@ -670,7 +827,7 @@ static int hist_entry__sym_ipc_null_snprintf(struct hist_entry *he return repsep_snprintf(bf, size, "%-*s", width, tmp); } -struct sort_entry sort_sym_ipc_null = { +static struct sort_entry sort_sym_ipc_null = { .se_header = "IPC [IPC Coverage]", .se_cmp = sort__sym_cmp, .se_snprintf = hist_entry__sym_ipc_null_snprintf, @@ -703,7 +860,7 @@ static int hist_entry__callchain_branch_predicted_snprintf( return repsep_snprintf(bf, size, "%-*.*s", width, width, str); } -struct sort_entry sort_callchain_branch_predicted = { +static struct sort_entry sort_callchain_branch_predicted = { .se_header = "Predicted", .se_cmp = sort__callchain_branch_predicted_cmp, .se_snprintf = hist_entry__callchain_branch_predicted_snprintf, @@ -733,7 +890,7 @@ static int hist_entry__callchain_branch_abort_snprintf(struct hist_entry *he, return repsep_snprintf(bf, size, "%-*.*s", width, width, str); } -struct sort_entry sort_callchain_branch_abort = { +static struct sort_entry sort_callchain_branch_abort = { .se_header = "Abort", .se_cmp = sort__callchain_branch_abort_cmp, .se_snprintf = hist_entry__callchain_branch_abort_snprintf, @@ -766,7 +923,7 @@ static int hist_entry__callchain_branch_cycles_snprintf(struct hist_entry *he, return repsep_snprintf(bf, size, "%-*.*s", width, width, str); } -struct sort_entry sort_callchain_branch_cycles = { +static struct sort_entry sort_callchain_branch_cycles = { .se_header = "Cycles", .se_cmp = sort__callchain_branch_cycles_cmp, .se_snprintf = hist_entry__callchain_branch_cycles_snprintf, @@ -833,7 +990,7 @@ static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-.*s", width, he->srcfile); } -struct sort_entry sort_srcfile = { +static struct sort_entry sort_srcfile = { .se_header = "Source File", .se_cmp = sort__srcfile_cmp, .se_collapse = sort__srcfile_collapse, @@ -885,13 +1042,45 @@ static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu); } -struct sort_entry sort_cpu = { +static struct sort_entry sort_cpu = { .se_header = "CPU", .se_cmp = sort__cpu_cmp, .se_snprintf = hist_entry__cpu_snprintf, .se_width_idx = HISTC_CPU, }; +/* --sort parallelism */ + +static int64_t +sort__parallelism_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->parallelism - left->parallelism; +} + +static int hist_entry__parallelism_filter(struct hist_entry *he, int type, const void *arg) +{ + const unsigned long *parallelism_filter = arg; + + if (type != HIST_FILTER__PARALLELISM) + return -1; + + return test_bit(he->parallelism, parallelism_filter); +} + +static int hist_entry__parallelism_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%*d", width, he->parallelism); +} + +static struct sort_entry sort_parallelism = { + .se_header = "Parallelism", + .se_cmp = sort__parallelism_cmp, + .se_filter = hist_entry__parallelism_filter, + .se_snprintf = hist_entry__parallelism_snprintf, + .se_width_idx = HISTC_PARALLELISM, +}; + /* --sort cgroup_id */ static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev) @@ -925,7 +1114,7 @@ static int hist_entry__cgroup_id_snprintf(struct hist_entry *he, he->cgroup_id.ino); } -struct sort_entry sort_cgroup_id = { +static struct sort_entry sort_cgroup_id = { .se_header = "cgroup id (dev/inode)", .se_cmp = sort__cgroup_id_cmp, .se_snprintf = hist_entry__cgroup_id_snprintf, @@ -947,7 +1136,7 @@ static int hist_entry__cgroup_snprintf(struct hist_entry *he, const char *cgrp_name = "N/A"; if (he->cgroup) { - struct cgroup *cgrp = cgroup__find(maps__machine(he->ms.maps)->env, + struct cgroup *cgrp = cgroup__find(maps__machine(thread__maps(he->ms.thread))->env, he->cgroup); if (cgrp != NULL) cgrp_name = cgrp->name; @@ -958,7 +1147,7 @@ static int hist_entry__cgroup_snprintf(struct hist_entry *he, return repsep_snprintf(bf, size, "%s", cgrp_name); } -struct sort_entry sort_cgroup = { +static struct sort_entry sort_cgroup = { .se_header = "Cgroup", .se_cmp = sort__cgroup_cmp, .se_snprintf = hist_entry__cgroup_snprintf, @@ -989,7 +1178,7 @@ static int hist_entry__socket_filter(struct hist_entry *he, int type, const void return sk >= 0 && he->socket != sk; } -struct sort_entry sort_socket = { +static struct sort_entry sort_socket = { .se_header = "Socket", .se_cmp = sort__socket_cmp, .se_snprintf = hist_entry__socket_snprintf, @@ -1020,7 +1209,7 @@ static int hist_entry__time_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-.*s", width, he_time); } -struct sort_entry sort_time = { +static struct sort_entry sort_time = { .se_header = "Time", .se_cmp = sort__time_cmp, .se_snprintf = hist_entry__time_snprintf, @@ -1089,7 +1278,7 @@ static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-.*s", width, he->trace_output); } -struct sort_entry sort_trace = { +static struct sort_entry sort_trace = { .se_header = "Trace output", .se_cmp = sort__trace_cmp, .se_snprintf = hist_entry__trace_snprintf, @@ -1384,7 +1573,7 @@ sort__addr_to_cmp(struct hist_entry *left, struct hist_entry *right) return _sort__addr_cmp(to_l->addr, to_r->addr); } -struct sort_entry sort_addr_from = { +static struct sort_entry sort_addr_from = { .se_header = "Source Address", .se_cmp = sort__addr_from_cmp, .se_snprintf = hist_entry__addr_from_snprintf, @@ -1392,7 +1581,7 @@ struct sort_entry sort_addr_from = { .se_width_idx = HISTC_ADDR_FROM, }; -struct sort_entry sort_addr_to = { +static struct sort_entry sort_addr_to = { .se_header = "Target Address", .se_cmp = sort__addr_to_cmp, .se_snprintf = hist_entry__addr_to_snprintf, @@ -1449,7 +1638,7 @@ static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf, he->branch_info->flags.cycles); } -struct sort_entry sort_cycles = { +static struct sort_entry sort_cycles = { .se_header = "Basic Block Cycles", .se_cmp = sort__cycles_cmp, .se_snprintf = hist_entry__cycles_snprintf, @@ -1677,22 +1866,27 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if (rc) return rc; /* - * Addresses with no major/minor numbers are assumed to be + * Addresses with no major/minor numbers or build ID are assumed to be * anonymous in userspace. Sort those on pid then address. * * The kernel and non-zero major/minor mapped areas are * assumed to be unity mapped. Sort those on address. */ + if (left->cpumode != PERF_RECORD_MISC_KERNEL && (map__flags(l_map) & MAP_SHARED) == 0) { + const struct dso_id *dso_id = dso__id_const(l_dso); - if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && - (!(map__flags(l_map) & MAP_SHARED)) && !dso__id(l_dso)->maj && !dso__id(l_dso)->min && - !dso__id(l_dso)->ino && !dso__id(l_dso)->ino_generation) { - /* userspace anonymous */ + if (!dso_id->mmap2_valid) + dso_id = dso__id_const(r_dso); - if (thread__pid(left->thread) > thread__pid(right->thread)) - return -1; - if (thread__pid(left->thread) < thread__pid(right->thread)) - return 1; + if (!build_id__is_defined(&dso_id->build_id) && + (!dso_id->mmap2_valid || (dso_id->maj == 0 && dso_id->min == 0))) { + /* userspace anonymous */ + + if (thread__pid(left->thread) > thread__pid(right->thread)) + return -1; + if (thread__pid(left->thread) < thread__pid(right->thread)) + return 1; + } } addr: @@ -1717,6 +1911,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, if (he->mem_info) { struct map *map = mem_info__daddr(he->mem_info)->ms.map; struct dso *dso = map ? map__dso(map) : NULL; + const struct dso_id *dso_id = dso ? dso__id_const(dso) : &dso_id_empty; addr = cl_address(mem_info__daddr(he->mem_info)->al_addr, chk_double_cl); ms = &mem_info__daddr(he->mem_info)->ms; @@ -1725,8 +1920,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && map && !(map__prot(map) & PROT_EXEC) && (map__flags(map) & MAP_SHARED) && - (dso__id(dso)->maj || dso__id(dso)->min || dso__id(dso)->ino || - dso__id(dso)->ino_generation)) + (!dso_id->mmap2_valid || (dso_id->maj == 0 && dso_id->min == 0))) level = 's'; else if (!map) level = 'X'; @@ -1734,7 +1928,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, return _hist_entry__sym_snprintf(ms, addr, level, bf, size, width); } -struct sort_entry sort_mispredict = { +static struct sort_entry sort_mispredict = { .se_header = "Branch Mispredicted", .se_cmp = sort__mispredict_cmp, .se_snprintf = hist_entry__mispredict_snprintf, @@ -1753,7 +1947,7 @@ static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*llu", width, he->weight); } -struct sort_entry sort_local_weight = { +static struct sort_entry sort_local_weight = { .se_header = "Local Weight", .se_cmp = sort__weight_cmp, .se_snprintf = hist_entry__local_weight_snprintf, @@ -1767,7 +1961,7 @@ static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf, he->weight * he->stat.nr_events); } -struct sort_entry sort_global_weight = { +static struct sort_entry sort_global_weight = { .se_header = "Weight", .se_cmp = sort__weight_cmp, .se_snprintf = hist_entry__global_weight_snprintf, @@ -1786,7 +1980,7 @@ static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*u", width, he->ins_lat); } -struct sort_entry sort_local_ins_lat = { +static struct sort_entry sort_local_ins_lat = { .se_header = "Local INSTR Latency", .se_cmp = sort__ins_lat_cmp, .se_snprintf = hist_entry__local_ins_lat_snprintf, @@ -1800,7 +1994,7 @@ static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf, he->ins_lat * he->stat.nr_events); } -struct sort_entry sort_global_ins_lat = { +static struct sort_entry sort_global_ins_lat = { .se_header = "INSTR Latency", .se_cmp = sort__ins_lat_cmp, .se_snprintf = hist_entry__global_ins_lat_snprintf, @@ -1810,87 +2004,86 @@ struct sort_entry sort_global_ins_lat = { static int64_t sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right) { - return left->p_stage_cyc - right->p_stage_cyc; + return left->weight3 - right->weight3; } static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, - he->p_stage_cyc * he->stat.nr_events); + return repsep_snprintf(bf, size, "%-*u", width, he->weight3 * he->stat.nr_events); } static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc); + return repsep_snprintf(bf, size, "%-*u", width, he->weight3); } -struct sort_entry sort_local_p_stage_cyc = { +static struct sort_entry sort_local_p_stage_cyc = { .se_header = "Local Pipeline Stage Cycle", .se_cmp = sort__p_stage_cyc_cmp, .se_snprintf = hist_entry__p_stage_cyc_snprintf, .se_width_idx = HISTC_LOCAL_P_STAGE_CYC, }; -struct sort_entry sort_global_p_stage_cyc = { +static struct sort_entry sort_global_p_stage_cyc = { .se_header = "Pipeline Stage Cycle", .se_cmp = sort__p_stage_cyc_cmp, .se_snprintf = hist_entry__global_p_stage_cyc_snprintf, .se_width_idx = HISTC_GLOBAL_P_STAGE_CYC, }; -struct sort_entry sort_mem_daddr_sym = { +static struct sort_entry sort_mem_daddr_sym = { .se_header = "Data Symbol", .se_cmp = sort__daddr_cmp, .se_snprintf = hist_entry__daddr_snprintf, .se_width_idx = HISTC_MEM_DADDR_SYMBOL, }; -struct sort_entry sort_mem_iaddr_sym = { +static struct sort_entry sort_mem_iaddr_sym = { .se_header = "Code Symbol", .se_cmp = sort__iaddr_cmp, .se_snprintf = hist_entry__iaddr_snprintf, .se_width_idx = HISTC_MEM_IADDR_SYMBOL, }; -struct sort_entry sort_mem_daddr_dso = { +static struct sort_entry sort_mem_daddr_dso = { .se_header = "Data Object", .se_cmp = sort__dso_daddr_cmp, .se_snprintf = hist_entry__dso_daddr_snprintf, .se_width_idx = HISTC_MEM_DADDR_DSO, }; -struct sort_entry sort_mem_locked = { +static struct sort_entry sort_mem_locked = { .se_header = "Locked", .se_cmp = sort__locked_cmp, .se_snprintf = hist_entry__locked_snprintf, .se_width_idx = HISTC_MEM_LOCKED, }; -struct sort_entry sort_mem_tlb = { +static struct sort_entry sort_mem_tlb = { .se_header = "TLB access", .se_cmp = sort__tlb_cmp, .se_snprintf = hist_entry__tlb_snprintf, .se_width_idx = HISTC_MEM_TLB, }; -struct sort_entry sort_mem_lvl = { +static struct sort_entry sort_mem_lvl = { .se_header = "Memory access", .se_cmp = sort__lvl_cmp, .se_snprintf = hist_entry__lvl_snprintf, .se_width_idx = HISTC_MEM_LVL, }; -struct sort_entry sort_mem_snoop = { +static struct sort_entry sort_mem_snoop = { .se_header = "Snoop", .se_cmp = sort__snoop_cmp, .se_snprintf = hist_entry__snoop_snprintf, .se_width_idx = HISTC_MEM_SNOOP, }; -struct sort_entry sort_mem_dcacheline = { +static struct sort_entry sort_mem_dcacheline = { .se_header = "Data Cacheline", .se_cmp = sort__dcacheline_cmp, .se_snprintf = hist_entry__dcacheline_snprintf, @@ -1925,7 +2118,7 @@ static int hist_entry__blocked_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%.*s", width, out); } -struct sort_entry sort_mem_blocked = { +static struct sort_entry sort_mem_blocked = { .se_header = "Blocked", .se_cmp = sort__blocked_cmp, .se_snprintf = hist_entry__blocked_snprintf, @@ -1966,7 +2159,7 @@ static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf, return width; } -struct sort_entry sort_mem_phys_daddr = { +static struct sort_entry sort_mem_phys_daddr = { .se_header = "Data Physical Address", .se_cmp = sort__phys_daddr_cmp, .se_snprintf = hist_entry__phys_daddr_snprintf, @@ -1995,7 +2188,7 @@ static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf, get_page_size_name(mem_info__daddr(he->mem_info)->data_page_size, str)); } -struct sort_entry sort_mem_data_page_size = { +static struct sort_entry sort_mem_data_page_size = { .se_header = "Data Page Size", .se_cmp = sort__data_page_size_cmp, .se_snprintf = hist_entry__data_page_size_snprintf, @@ -2020,7 +2213,7 @@ static int hist_entry__code_page_size_snprintf(struct hist_entry *he, char *bf, get_page_size_name(he->code_page_size, str)); } -struct sort_entry sort_code_page_size = { +static struct sort_entry sort_code_page_size = { .se_header = "Code Page Size", .se_cmp = sort__code_page_size_cmp, .se_snprintf = hist_entry__code_page_size_snprintf, @@ -2052,7 +2245,7 @@ static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, out); } -struct sort_entry sort_abort = { +static struct sort_entry sort_abort = { .se_header = "Transaction abort", .se_cmp = sort__abort_cmp, .se_snprintf = hist_entry__abort_snprintf, @@ -2084,7 +2277,7 @@ static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, out); } -struct sort_entry sort_in_tx = { +static struct sort_entry sort_in_tx = { .se_header = "Branch in transaction", .se_cmp = sort__in_tx_cmp, .se_snprintf = hist_entry__in_tx_snprintf, @@ -2156,7 +2349,7 @@ static int hist_entry__transaction_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-*s", width, buf); } -struct sort_entry sort_transaction = { +static struct sort_entry sort_transaction = { .se_header = "Transaction ", .se_cmp = sort__transaction_cmp, .se_snprintf = hist_entry__transaction_snprintf, @@ -2195,7 +2388,7 @@ static int hist_entry__sym_size_snprintf(struct hist_entry *he, char *bf, return _hist_entry__sym_size_snprintf(he->ms.sym, bf, size, width); } -struct sort_entry sort_sym_size = { +static struct sort_entry sort_sym_size = { .se_header = "Symbol size", .se_cmp = sort__sym_size_cmp, .se_snprintf = hist_entry__sym_size_snprintf, @@ -2234,7 +2427,7 @@ static int hist_entry__dso_size_snprintf(struct hist_entry *he, char *bf, return _hist_entry__dso_size_snprintf(he->ms.map, bf, size, width); } -struct sort_entry sort_dso_size = { +static struct sort_entry sort_dso_size = { .se_header = "DSO size", .se_cmp = sort__dso_size_cmp, .se_snprintf = hist_entry__dso_size_snprintf, @@ -2271,7 +2464,7 @@ static int hist_entry__addr_snprintf(struct hist_entry *he, char *bf, return repsep_snprintf(bf, size, "%-#*llx", width, ip); } -struct sort_entry sort_addr = { +static struct sort_entry sort_addr = { .se_header = "Address", .se_cmp = sort__addr_cmp, .se_snprintf = hist_entry__addr_snprintf, @@ -2371,50 +2564,25 @@ sort__typeoff_sort(struct hist_entry *left, struct hist_entry *right) return left->mem_type_off - right->mem_type_off; } -static void fill_member_name(char *buf, size_t sz, struct annotated_member *m, - int offset, bool first) -{ - struct annotated_member *child; - - if (list_empty(&m->children)) - return; - - list_for_each_entry(child, &m->children, node) { - if (child->offset <= offset && offset < child->offset + child->size) { - int len = 0; - - /* It can have anonymous struct/union members */ - if (child->var_name) { - len = scnprintf(buf, sz, "%s%s", - first ? "" : ".", child->var_name); - first = false; - } - - fill_member_name(buf + len, sz - len, child, offset, first); - return; - } - } -} - static int hist_entry__typeoff_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width __maybe_unused) { struct annotated_data_type *he_type = he->mem_type; char buf[4096]; - buf[0] = '\0'; - if (list_empty(&he_type->self.children)) - snprintf(buf, sizeof(buf), "no field"); - else - fill_member_name(buf, sizeof(buf), &he_type->self, - he->mem_type_off, true); - buf[4095] = '\0'; + if (he_type == &unknown_type || he_type == &stackop_type || + he_type == &canary_type) + return repsep_snprintf(bf, size, "%s", he_type->self.type_name); + + if (!annotated_data_type__get_member_name(he_type, buf, sizeof(buf), + he->mem_type_off)) + scnprintf(buf, sizeof(buf), "no field"); return repsep_snprintf(bf, size, "%s +%#x (%s)", he_type->self.type_name, he->mem_type_off, buf); } -struct sort_entry sort_type_offset = { +static struct sort_entry sort_type_offset = { .se_header = "Data Type Offset", .se_cmp = sort__type_cmp, .se_collapse = sort__typeoff_sort, @@ -2426,8 +2594,26 @@ struct sort_entry sort_type_offset = { /* --sort typecln */ -/* TODO: use actual value in the system */ -#define TYPE_CACHELINE_SIZE 64 +static int +hist_entry__cln_size(struct hist_entry *he) +{ + int ret = 0; + + if (he && he->hists) { + struct evsel *evsel = hists_to_evsel(he->hists); + + if (evsel) { + struct perf_session *session = evsel__session(evsel); + + ret = session->header.env.cln_size; + } + } + + if (ret < 1) + ret = DEFAULT_CACHELINE_SIZE; // avoid div/0 later + + return ret; +} static int64_t sort__typecln_sort(struct hist_entry *left, struct hist_entry *right) @@ -2435,6 +2621,8 @@ sort__typecln_sort(struct hist_entry *left, struct hist_entry *right) struct annotated_data_type *left_type = left->mem_type; struct annotated_data_type *right_type = right->mem_type; int64_t left_cln, right_cln; + int64_t cln_size_left = hist_entry__cln_size(left); + int64_t cln_size_right = hist_entry__cln_size(right); int64_t ret; if (!left_type) { @@ -2451,8 +2639,8 @@ sort__typecln_sort(struct hist_entry *left, struct hist_entry *right) if (ret) return ret; - left_cln = left->mem_type_off / TYPE_CACHELINE_SIZE; - right_cln = right->mem_type_off / TYPE_CACHELINE_SIZE; + left_cln = left->mem_type_off / cln_size_left; + right_cln = right->mem_type_off / cln_size_right; return left_cln - right_cln; } @@ -2460,12 +2648,13 @@ static int hist_entry__typecln_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width __maybe_unused) { struct annotated_data_type *he_type = he->mem_type; + int cln_size = hist_entry__cln_size(he); return repsep_snprintf(bf, size, "%s: cache-line %d", he_type->self.type_name, - he->mem_type_off / TYPE_CACHELINE_SIZE); + he->mem_type_off / cln_size); } -struct sort_entry sort_type_cacheline = { +static struct sort_entry sort_type_cacheline = { .se_header = "Data Type Cacheline", .se_cmp = sort__type_cmp, .se_collapse = sort__typecln_sort, @@ -2482,26 +2671,53 @@ struct sort_dimension { int taken; }; -int __weak arch_support_sort_key(const char *sort_key __maybe_unused) +static int arch_support_sort_key(const char *sort_key, struct perf_env *env) { + const char *arch = perf_env__arch(env); + + if (!strcmp("x86", arch) || !strcmp("powerpc", arch)) { + if (!strcmp(sort_key, "p_stage_cyc")) + return 1; + if (!strcmp(sort_key, "local_p_stage_cyc")) + return 1; + } return 0; } -const char * __weak arch_perf_header_entry(const char *se_header) -{ +static const char *arch_perf_header_entry(const char *se_header, struct perf_env *env) +{ + const char *arch = perf_env__arch(env); + + if (!strcmp("x86", arch)) { + if (!strcmp(se_header, "Local Pipeline Stage Cycle")) + return "Local Retire Latency"; + else if (!strcmp(se_header, "Pipeline Stage Cycle")) + return "Retire Latency"; + } else if (!strcmp("powerpc", arch)) { + if (!strcmp(se_header, "Local INSTR Latency")) + return "Finish Cyc"; + else if (!strcmp(se_header, "INSTR Latency")) + return "Global Finish_cyc"; + else if (!strcmp(se_header, "Local Pipeline Stage Cycle")) + return "Dispatch Cyc"; + else if (!strcmp(se_header, "Pipeline Stage Cycle")) + return "Global Dispatch_cyc"; + } return se_header; } -static void sort_dimension_add_dynamic_header(struct sort_dimension *sd) +static void sort_dimension_add_dynamic_header(struct sort_dimension *sd, struct perf_env *env) { - sd->entry->se_header = arch_perf_header_entry(sd->entry->se_header); + sd->entry->se_header = arch_perf_header_entry(sd->entry->se_header, env); } #define DIM(d, n, func) [d] = { .name = n, .entry = &(func) } static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PID, "pid", sort_thread), + DIM(SORT_TGID, "tgid", sort_tgid), DIM(SORT_COMM, "comm", sort_comm), + DIM(SORT_COMM_NODIGIT, "comm_nodigit", sort_comm_nodigit), DIM(SORT_DSO, "dso", sort_dso), DIM(SORT_SYM, "symbol", sort_sym), DIM(SORT_PARENT, "parent", sort_parent), @@ -2534,6 +2750,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_ANNOTATE_DATA_TYPE_OFFSET, "typeoff", sort_type_offset), DIM(SORT_SYM_OFFSET, "symoff", sort_sym_offset), DIM(SORT_ANNOTATE_DATA_TYPE_CACHELINE, "typecln", sort_type_cacheline), + DIM(SORT_PARALLELISM, "parallelism", sort_parallelism), }; #undef DIM @@ -2589,17 +2806,22 @@ struct hpp_dimension { const char *name; struct perf_hpp_fmt *fmt; int taken; + int was_taken; + int mem_mode; }; #define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], } +#define DIM_MEM(d, n) { .name = n, .fmt = &perf_hpp__format[d], .mem_mode = 1, } static struct hpp_dimension hpp_sort_dimensions[] = { DIM(PERF_HPP__OVERHEAD, "overhead"), + DIM(PERF_HPP__LATENCY, "latency"), DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"), DIM(PERF_HPP__OVERHEAD_US, "overhead_us"), DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"), DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"), DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"), + DIM(PERF_HPP__LATENCY_ACC, "latency_children"), DIM(PERF_HPP__SAMPLES, "sample"), DIM(PERF_HPP__PERIOD, "period"), DIM(PERF_HPP__WEIGHT1, "weight1"), @@ -2609,8 +2831,15 @@ static struct hpp_dimension hpp_sort_dimensions[] = { DIM(PERF_HPP__WEIGHT2, "ins_lat"), DIM(PERF_HPP__WEIGHT3, "retire_lat"), DIM(PERF_HPP__WEIGHT3, "p_stage_cyc"), + /* used for output only when SORT_MODE__MEM */ + DIM_MEM(PERF_HPP__MEM_STAT_OP, "op"), + DIM_MEM(PERF_HPP__MEM_STAT_CACHE, "cache"), + DIM_MEM(PERF_HPP__MEM_STAT_MEMORY, "memory"), + DIM_MEM(PERF_HPP__MEM_STAT_SNOOP, "snoop"), + DIM_MEM(PERF_HPP__MEM_STAT_DTLB, "dtlb"), }; +#undef DIM_MEM #undef DIM struct hpp_sort_entry { @@ -2630,18 +2859,22 @@ 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, int line __maybe_unused, + struct hists *hists, int line, int *span __maybe_unused) { struct hpp_sort_entry *hse; size_t len = fmt->user_len; + const char *hdr = ""; + + if (line == hists->hpp_list->nr_header_lines - 1) + hdr = fmt->name; hse = container_of(fmt, struct hpp_sort_entry, hpp); if (!len) len = hists__col_len(hists, hse->se->se_width_idx); - return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name); + return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, hdr); } static int __sort__hpp_width(struct perf_hpp_fmt *fmt, @@ -2735,6 +2968,7 @@ MK_SORT_ENTRY_CHK(thread) MK_SORT_ENTRY_CHK(comm) MK_SORT_ENTRY_CHK(dso) MK_SORT_ENTRY_CHK(sym) +MK_SORT_ENTRY_CHK(parallelism) static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) @@ -2872,9 +3106,10 @@ static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd, } static int __sort_dimension__add_hpp_output(struct sort_dimension *sd, - struct perf_hpp_list *list) + struct perf_hpp_list *list, + int level) { - struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0); + struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level); if (hse == NULL) return -1; @@ -3445,6 +3680,58 @@ out: return ret; } +static int __sort_dimension__update(struct sort_dimension *sd, + struct perf_hpp_list *list) +{ + if (sd->entry == &sort_parent && parent_pattern) { + int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); + if (ret) { + char err[BUFSIZ]; + + regerror(ret, &parent_regex, err, sizeof(err)); + pr_err("Invalid regex: %s\n%s", parent_pattern, err); + return -EINVAL; + } + list->parent = 1; + } else if (sd->entry == &sort_sym) { + list->sym = 1; + /* + * perf diff displays the performance difference amongst + * two or more perf.data files. Those files could come + * from different binaries. So we should not compare + * their ips, but the name of symbol. + */ + if (sort__mode == SORT_MODE__DIFF) + sd->entry->se_collapse = sort__sym_sort; + + } else if (sd->entry == &sort_sym_offset) { + list->sym = 1; + } else if (sd->entry == &sort_dso) { + list->dso = 1; + } else if (sd->entry == &sort_socket) { + list->socket = 1; + } else if (sd->entry == &sort_thread) { + list->thread = 1; + } else if (sd->entry == &sort_comm) { + list->comm = 1; + } else if (sd->entry == &sort_comm_nodigit) { + list->comm_nodigit = list->comm = 1; + } else if (sd->entry == &sort_type_offset) { + symbol_conf.annotate_data_member = true; + } else if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) { + list->sym = 1; + } else if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0) { + return -EINVAL; + } else if (sd->entry == &sort_mem_daddr_sym) { + list->sym = 1; + } + + if (sd->entry->se_collapse) + list->need_collapse = 1; + + return 0; +} + static int __sort_dimension__add(struct sort_dimension *sd, struct perf_hpp_list *list, int level) @@ -3455,8 +3742,8 @@ static int __sort_dimension__add(struct sort_dimension *sd, if (__sort_dimension__add_hpp_sort(sd, list, level) < 0) return -1; - if (sd->entry->se_collapse) - list->need_collapse = 1; + if (__sort_dimension__update(sd, list) < 0) + return -1; sd->taken = 1; @@ -3477,17 +3764,22 @@ static int __hpp_dimension__add(struct hpp_dimension *hd, return -1; hd->taken = 1; + hd->was_taken = 1; perf_hpp_list__register_sort_field(list, fmt); return 0; } static int __sort_dimension__add_output(struct perf_hpp_list *list, - struct sort_dimension *sd) + struct sort_dimension *sd, + int level) { if (sd->taken) return 0; - if (__sort_dimension__add_hpp_output(sd, list) < 0) + if (__sort_dimension__add_hpp_output(sd, list, level) < 0) + return -1; + + if (__sort_dimension__update(sd, list) < 0) return -1; sd->taken = 1; @@ -3495,14 +3787,15 @@ static int __sort_dimension__add_output(struct perf_hpp_list *list, } static int __hpp_dimension__add_output(struct perf_hpp_list *list, - struct hpp_dimension *hd) + struct hpp_dimension *hd, + int level) { struct perf_hpp_fmt *fmt; if (hd->taken) return 0; - fmt = __hpp_dimension__alloc_hpp(hd, 0); + fmt = __hpp_dimension__alloc_hpp(hd, level); if (!fmt) return -1; @@ -3511,14 +3804,19 @@ static int __hpp_dimension__add_output(struct perf_hpp_list *list, return 0; } -int hpp_dimension__add_output(unsigned col) +int hpp_dimension__add_output(unsigned col, bool implicit) { + struct hpp_dimension *hd; + BUG_ON(col >= PERF_HPP__MAX_INDEX); - return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]); + hd = &hpp_sort_dimensions[col]; + if (implicit && !hd->was_taken) + return 0; + return __hpp_dimension__add_output(&perf_hpp_list, hd, /*level=*/0); } int sort_dimension__add(struct perf_hpp_list *list, const char *tok, - struct evlist *evlist, + struct evlist *evlist, struct perf_env *env, int level) { unsigned int i, j; @@ -3531,7 +3829,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, */ for (j = 0; j < ARRAY_SIZE(arch_specific_sort_keys); j++) { if (!strcmp(arch_specific_sort_keys[j], tok) && - !arch_support_sort_key(tok)) { + !arch_support_sort_key(tok, env)) { return 0; } } @@ -3544,54 +3842,12 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, for (j = 0; j < ARRAY_SIZE(dynamic_headers); j++) { if (sd->name && !strcmp(dynamic_headers[j], sd->name)) - sort_dimension_add_dynamic_header(sd); - } - - if (sd->entry == &sort_parent && parent_pattern) { - int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); - if (ret) { - char err[BUFSIZ]; - - regerror(ret, &parent_regex, err, sizeof(err)); - pr_err("Invalid regex: %s\n%s", parent_pattern, err); - return -EINVAL; - } - list->parent = 1; - } else if (sd->entry == &sort_sym) { - list->sym = 1; - /* - * perf diff displays the performance difference amongst - * two or more perf.data files. Those files could come - * from different binaries. So we should not compare - * their ips, but the name of symbol. - */ - if (sort__mode == SORT_MODE__DIFF) - sd->entry->se_collapse = sort__sym_sort; - - } else if (sd->entry == &sort_dso) { - list->dso = 1; - } else if (sd->entry == &sort_socket) { - list->socket = 1; - } else if (sd->entry == &sort_thread) { - list->thread = 1; - } else if (sd->entry == &sort_comm) { - list->comm = 1; - } else if (sd->entry == &sort_type_offset) { - symbol_conf.annotate_data_member = true; + sort_dimension_add_dynamic_header(sd, env); } return __sort_dimension__add(sd, list, level); } - for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { - struct hpp_dimension *hd = &hpp_sort_dimensions[i]; - - if (strncasecmp(tok, hd->name, strlen(tok))) - continue; - - return __hpp_dimension__add(hd, list, level); - } - for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { struct sort_dimension *sd = &bstack_sort_dimensions[i]; @@ -3607,9 +3863,6 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, strlen(tok))) return -EINVAL; - if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) - list->sym = 1; - __sort_dimension__add(sd, list, level); return 0; } @@ -3623,30 +3876,63 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, if (sort__mode != SORT_MODE__MEMORY) return -EINVAL; - if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0) - return -EINVAL; - - if (sd->entry == &sort_mem_daddr_sym) - list->sym = 1; - __sort_dimension__add(sd, list, level); return 0; } + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (strncasecmp(tok, hd->name, strlen(tok))) + continue; + + return __hpp_dimension__add(hd, list, level); + } + if (!add_dynamic_entry(evlist, tok, level)) return 0; return -ESRCH; } +/* This should match with sort_dimension__add() above */ +static bool is_hpp_sort_key(const char *key, struct perf_env *env) +{ + unsigned i; + + for (i = 0; i < ARRAY_SIZE(arch_specific_sort_keys); i++) { + if (!strcmp(arch_specific_sort_keys[i], key) && + !arch_support_sort_key(key, env)) { + return false; + } + } + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; + + if (sd->name && !strncasecmp(key, sd->name, strlen(key))) + return false; + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (!strncasecmp(key, hd->name, strlen(key))) + return true; + } + return false; +} + static int setup_sort_list(struct perf_hpp_list *list, char *str, - struct evlist *evlist) + struct evlist *evlist, struct perf_env *env) { char *tmp, *tok; int ret = 0; int level = 0; int next_level = 1; + int prev_level = 0; bool in_group = false; + bool prev_was_hpp = false; do { tok = str; @@ -3667,7 +3953,20 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, } if (*tok) { - ret = sort_dimension__add(list, tok, evlist, level); + if (is_hpp_sort_key(tok, env)) { + /* keep output (hpp) sort keys in the same level */ + if (prev_was_hpp) { + bool next_same = (level == next_level); + + level = prev_level; + next_level = next_same ? level : level+1; + } + prev_was_hpp = true; + } else { + prev_was_hpp = false; + } + + ret = sort_dimension__add(list, tok, evlist, env, level); if (ret == -EINVAL) { if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok))) ui__error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); @@ -3678,6 +3977,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ui__error("Unknown --sort key: `%s'", tok); break; } + prev_level = level; } level = next_level; @@ -3773,15 +4073,29 @@ static char *setup_overhead(char *keys) if (sort__mode == SORT_MODE__DIFF) return keys; - keys = prefix_if_not_in("overhead", keys); - - if (symbol_conf.cumulate_callchain) - keys = prefix_if_not_in("overhead_children", keys); + if (symbol_conf.prefer_latency) { + keys = prefix_if_not_in("overhead", keys); + keys = prefix_if_not_in("latency", keys); + if (symbol_conf.cumulate_callchain) { + keys = prefix_if_not_in("overhead_children", keys); + keys = prefix_if_not_in("latency_children", keys); + } + } else if (!keys || (!strstr(keys, "overhead") && + !strstr(keys, "latency"))) { + if (symbol_conf.enable_latency) + keys = prefix_if_not_in("latency", keys); + keys = prefix_if_not_in("overhead", keys); + if (symbol_conf.cumulate_callchain) { + if (symbol_conf.enable_latency) + keys = prefix_if_not_in("latency_children", keys); + keys = prefix_if_not_in("overhead_children", keys); + } + } return keys; } -static int __setup_sorting(struct evlist *evlist) +static int __setup_sorting(struct evlist *evlist, struct perf_env *env) { char *str; const char *sort_keys; @@ -3821,7 +4135,7 @@ static int __setup_sorting(struct evlist *evlist) } } - ret = setup_sort_list(&perf_hpp_list, str, evlist); + ret = setup_sort_list(&perf_hpp_list, str, evlist, env); free(str); return ret; @@ -3863,6 +4177,7 @@ static bool get_elide(int idx, FILE *output) case HISTC_DSO: return __get_elide(symbol_conf.dso_list, "dso", output); case HISTC_COMM: + case HISTC_COMM_NODIGIT: return __get_elide(symbol_conf.comm_list, "comm", output); default: break; @@ -3924,7 +4239,7 @@ void sort__setup_elide(FILE *output) } } -int output_field_add(struct perf_hpp_list *list, const char *tok) +int output_field_add(struct perf_hpp_list *list, const char *tok, int *level) { unsigned int i; @@ -3937,16 +4252,25 @@ int output_field_add(struct perf_hpp_list *list, const char *tok) if (!strcasecmp(tok, "weight")) ui__warning("--fields weight shows the average value unlike in the --sort key.\n"); - return __hpp_dimension__add_output(list, hd); + if (hd->mem_mode && sort__mode != SORT_MODE__MEMORY) + continue; + + return __hpp_dimension__add_output(list, hd, *level); } + /* + * A non-output field will increase level so that it can be in a + * different hierarchy. + */ + (*level)++; + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { struct sort_dimension *sd = &common_sort_dimensions[i]; if (!sd->name || strncasecmp(tok, sd->name, strlen(tok))) continue; - return __sort_dimension__add_output(list, sd); + return __sort_dimension__add_output(list, sd, *level); } for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { @@ -3958,7 +4282,7 @@ int output_field_add(struct perf_hpp_list *list, const char *tok) if (sort__mode != SORT_MODE__BRANCH) return -EINVAL; - return __sort_dimension__add_output(list, sd); + return __sort_dimension__add_output(list, sd, *level); } for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) { @@ -3970,7 +4294,7 @@ int output_field_add(struct perf_hpp_list *list, const char *tok) if (sort__mode != SORT_MODE__MEMORY) return -EINVAL; - return __sort_dimension__add_output(list, sd); + return __sort_dimension__add_output(list, sd, *level); } return -ESRCH; @@ -3980,10 +4304,11 @@ static int setup_output_list(struct perf_hpp_list *list, char *str) { char *tmp, *tok; int ret = 0; + int level = 0; for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - ret = output_field_add(list, tok); + ret = output_field_add(list, tok, &level); if (ret == -EINVAL) { ui__error("Invalid --fields key: `%s'", tok); break; @@ -4047,16 +4372,16 @@ out: return ret; } -int setup_sorting(struct evlist *evlist) +int setup_sorting(struct evlist *evlist, struct perf_env *env) { int err; - err = __setup_sorting(evlist); + err = __setup_sorting(evlist, env); if (err < 0) return err; if (parent_pattern != default_parent_pattern) { - err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1); + err = sort_dimension__add(&perf_hpp_list, "parent", evlist, env, -1); if (err < 0) return err; } @@ -4073,6 +4398,10 @@ int setup_sorting(struct evlist *evlist) if (err < 0) return err; + err = perf_hpp__alloc_mem_stats(&perf_hpp_list, evlist); + if (err < 0) + return err; + /* copy sort keys to output fields */ perf_hpp__setup_output_field(&perf_hpp_list); /* and then copy output fields to sort keys */ diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index a8572574e168..c962e77e4b93 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -6,6 +6,7 @@ #include "hist.h" struct option; +struct perf_env; extern regex_t parent_regex; extern const char *sort_order; @@ -42,6 +43,7 @@ enum sort_type { /* common sort keys */ SORT_PID, SORT_COMM, + SORT_COMM_NODIGIT, SORT_DSO, SORT_SYM, SORT_PARENT, @@ -72,6 +74,8 @@ enum sort_type { SORT_ANNOTATE_DATA_TYPE_OFFSET, SORT_SYM_OFFSET, SORT_ANNOTATE_DATA_TYPE_CACHELINE, + SORT_PARALLELISM, + SORT_TGID, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, @@ -128,7 +132,7 @@ extern struct sort_entry sort_thread; struct evlist; struct tep_handle; -int setup_sorting(struct evlist *evlist); +int setup_sorting(struct evlist *evlist, struct perf_env *env); int setup_output_field(void); void reset_output_field(void); void sort__setup_elide(FILE *fp); @@ -140,12 +144,12 @@ 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); +int hpp_dimension__add_output(unsigned col, bool implicit); void reset_dimensions(void); int sort_dimension__add(struct perf_hpp_list *list, const char *tok, - struct evlist *evlist, + struct evlist *evlist, struct perf_env *env, int level); -int output_field_add(struct perf_hpp_list *list, const char *tok); +int output_field_add(struct perf_hpp_list *list, const char *tok, int *level); int64_t sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right); int64_t @@ -155,4 +159,5 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right); int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r); char *hist_entry__srcline(struct hist_entry *he); +size_t sort__comm_nodigit_len(struct hist_entry *entry); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/spark.c b/tools/perf/util/spark.c index 70272a8b81a6..65ca253cc22e 100644 --- a/tools/perf/util/spark.c +++ b/tools/perf/util/spark.c @@ -1,9 +1,7 @@ -#include <stdio.h> -#include <limits.h> -#include <string.h> -#include <stdlib.h> +// SPDX-License-Identifier: GPL-2.0 #include "spark.h" -#include "stat.h" +#include <limits.h> +#include <linux/kernel.h> #define SPARK_SHIFT 8 diff --git a/tools/perf/util/spark.h b/tools/perf/util/spark.h index 25402d7d7a64..78597c38ef35 100644 --- a/tools/perf/util/spark.h +++ b/tools/perf/util/spark.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef SPARK_H #define SPARK_H 1 diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c index 476e99896d5e..0f4907843ac1 100644 --- a/tools/perf/util/srccode.c +++ b/tools/perf/util/srccode.c @@ -16,7 +16,7 @@ #include "srccode.h" #include "debug.h" #include <internal/lib.h> // page_size -#include "fncache.h" +#include "hashmap.h" #define MAXSRCCACHE (32*1024*1024) #define MAXSRCFILES 64 @@ -92,7 +92,7 @@ static struct srcfile *find_srcfile(char *fn) struct srcfile *h; int fd; unsigned long sz; - unsigned hval = shash((unsigned char *)fn) % SRC_HTAB_SZ; + size_t hval = str_hash(fn) % SRC_HTAB_SZ; hlist_for_each_entry (h, &srcfile_htab[hval], hash_nd) { if (!strcmp(fn, h->fn)) { diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index f32d0d4f4bc9..db164d258163 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -1,32 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 +#include "srcline.h" +#include "addr2line.h" +#include "dso.h" +#include "callchain.h" +#include "libbfd.h" +#include "llvm.h" +#include "symbol.h" +#include "libdw.h" +#include "debug.h" +#include "util.h" + #include <inttypes.h> -#include <signal.h> -#include <stdio.h> -#include <stdlib.h> #include <string.h> -#include <sys/types.h> - -#include <linux/compiler.h> -#include <linux/kernel.h> #include <linux/string.h> #include <linux/zalloc.h> -#include <api/io.h> - -#include "util/dso.h" -#include "util/debug.h" -#include "util/callchain.h" -#include "util/symbol_conf.h" -#ifdef HAVE_LIBLLVM_SUPPORT -#include "util/llvm-c-helpers.h" -#endif -#include "srcline.h" -#include "string2.h" -#include "symbol.h" -#include "subcmd/run-command.h" - -/* If addr2line doesn't return data for 1 second then timeout. */ -int addr2line_timeout_ms = 1 * 1000; bool srcline_full_filename; char *srcline__unknown = (char *)"??:0"; @@ -49,8 +37,7 @@ static const char *srcline_dso_name(struct dso *dso) return dso_name; } -static int inline_list__append(struct symbol *symbol, char *srcline, - struct inline_node *node) +int inline_list__append(struct symbol *symbol, char *srcline, struct inline_node *node) { struct inline_list *ilist; @@ -69,15 +56,26 @@ static int inline_list__append(struct symbol *symbol, char *srcline, return 0; } -/* basename version that takes a const input string */ -static const char *gnu_basename(const char *path) +int inline_list__append_tail(struct symbol *symbol, char *srcline, struct inline_node *node) { - const char *base = strrchr(path, '/'); + struct inline_list *ilist; + + ilist = zalloc(sizeof(*ilist)); + if (ilist == NULL) + return -1; - return base ? base + 1 : path; + ilist->symbol = symbol; + ilist->srcline = srcline; + + if (callchain_param.order == ORDER_CALLEE) + list_add(&ilist->list, &node->val); + else + list_add_tail(&ilist->list, &node->val); + + return 0; } -static char *srcline_from_fileline(const char *file, unsigned int line) +char *srcline_from_fileline(const char *file, unsigned int line) { char *srcline; @@ -85,7 +83,7 @@ static char *srcline_from_fileline(const char *file, unsigned int line) return NULL; if (!srcline_full_filename) - file = gnu_basename(file); + file = perf_basename(file); if (asprintf(&srcline, "%s:%u", file, line) < 0) return NULL; @@ -93,9 +91,9 @@ static char *srcline_from_fileline(const char *file, unsigned int line) return srcline; } -static struct symbol *new_inline_sym(struct dso *dso, - struct symbol *base_sym, - const char *funcname) +struct symbol *new_inline_sym(struct dso *dso, + struct symbol *base_sym, + const char *funcname) { struct symbol *inline_sym; char *demangled = NULL; @@ -132,722 +130,101 @@ static struct symbol *new_inline_sym(struct dso *dso, return inline_sym; } -#define MAX_INLINE_NEST 1024 - -#ifdef HAVE_LIBLLVM_SUPPORT - -static void free_llvm_inline_frames(struct llvm_a2l_frame *inline_frames, - int num_frames) -{ - if (inline_frames != NULL) { - for (int i = 0; i < num_frames; ++i) { - zfree(&inline_frames[i].filename); - zfree(&inline_frames[i].funcname); - } - zfree(&inline_frames); - } -} - -static int addr2line(const char *dso_name, u64 addr, - char **file, unsigned int *line, struct dso *dso, - bool unwind_inlines, struct inline_node *node, +static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line_nr, + struct dso *dso, bool unwind_inlines, struct inline_node *node, struct symbol *sym) { - struct llvm_a2l_frame *inline_frames = NULL; - int num_frames = llvm_addr2line(dso_name, addr, file, line, - node && unwind_inlines, &inline_frames); - - if (num_frames == 0 || !inline_frames) { - /* Error, or we didn't want inlines. */ - return num_frames; - } - - for (int i = 0; i < num_frames; ++i) { - struct symbol *inline_sym = - new_inline_sym(dso, sym, inline_frames[i].funcname); - char *srcline = NULL; - - if (inline_frames[i].filename) { - srcline = - srcline_from_fileline(inline_frames[i].filename, - inline_frames[i].line); - } - if (inline_list__append(inline_sym, srcline, node) != 0) { - free_llvm_inline_frames(inline_frames, num_frames); - return 0; - } - } - free_llvm_inline_frames(inline_frames, num_frames); - - return num_frames; -} - -void dso__free_a2l(struct dso *dso __maybe_unused) -{ - /* Nothing to free. */ -} - -#elif defined(HAVE_LIBBFD_SUPPORT) - -/* - * Implement addr2line using libbfd. - */ -#define PACKAGE "perf" -#include <bfd.h> - -struct a2l_data { - const char *input; - u64 addr; - - bool found; - const char *filename; - const char *funcname; - unsigned line; - - bfd *abfd; - asymbol **syms; -}; - -static int bfd_error(const char *string) -{ - const char *errmsg; - - errmsg = bfd_errmsg(bfd_get_error()); - fflush(stdout); - - if (string) - pr_debug("%s: %s\n", string, errmsg); - else - pr_debug("%s\n", errmsg); - - return -1; -} - -static int slurp_symtab(bfd *abfd, struct a2l_data *a2l) -{ - long storage; - long symcount; - asymbol **syms; - bfd_boolean dynamic = FALSE; - - if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0) - return bfd_error(bfd_get_filename(abfd)); - - storage = bfd_get_symtab_upper_bound(abfd); - if (storage == 0L) { - storage = bfd_get_dynamic_symtab_upper_bound(abfd); - dynamic = TRUE; - } - if (storage < 0L) - return bfd_error(bfd_get_filename(abfd)); - - syms = malloc(storage); - if (dynamic) - symcount = bfd_canonicalize_dynamic_symtab(abfd, syms); - else - symcount = bfd_canonicalize_symtab(abfd, syms); - - if (symcount < 0) { - free(syms); - return bfd_error(bfd_get_filename(abfd)); - } - - a2l->syms = syms; - return 0; -} - -static void find_address_in_section(bfd *abfd, asection *section, void *data) -{ - bfd_vma pc, vma; - bfd_size_type size; - struct a2l_data *a2l = data; - flagword flags; + int ret = 0; - if (a2l->found) - return; + if (symbol_conf.addr2line_style[0] == A2L_STYLE_UNKNOWN) { + int i = 0; -#ifdef bfd_get_section_flags - flags = bfd_get_section_flags(abfd, section); -#else - flags = bfd_section_flags(section); + /* Default addr2line fallback order. */ +#ifdef HAVE_LIBDW_SUPPORT + symbol_conf.addr2line_style[i++] = A2L_STYLE_LIBDW; #endif - if ((flags & SEC_ALLOC) == 0) - return; - - pc = a2l->addr; -#ifdef bfd_get_section_vma - vma = bfd_get_section_vma(abfd, section); -#else - vma = bfd_section_vma(section); +#ifdef HAVE_LIBLLVM_SUPPORT + symbol_conf.addr2line_style[i++] = A2L_STYLE_LLVM; #endif -#ifdef bfd_get_section_size - size = bfd_get_section_size(section); -#else - size = bfd_section_size(section); +#ifdef HAVE_LIBBFD_SUPPORT + symbol_conf.addr2line_style[i++] = A2L_STYLE_LIBBFD; #endif - - if (pc < vma || pc >= vma + size) - return; - - a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma, - &a2l->filename, &a2l->funcname, - &a2l->line); - - if (a2l->filename && !strlen(a2l->filename)) - a2l->filename = NULL; -} - -static struct a2l_data *addr2line_init(const char *path) -{ - bfd *abfd; - struct a2l_data *a2l = NULL; - - abfd = bfd_openr(path, NULL); - if (abfd == NULL) - return NULL; - - if (!bfd_check_format(abfd, bfd_object)) - goto out; - - a2l = zalloc(sizeof(*a2l)); - if (a2l == NULL) - goto out; - - a2l->abfd = abfd; - a2l->input = strdup(path); - if (a2l->input == NULL) - goto out; - - if (slurp_symtab(abfd, a2l)) - goto out; - - return a2l; - -out: - if (a2l) { - zfree((char **)&a2l->input); - free(a2l); - } - bfd_close(abfd); - return NULL; -} - -static void addr2line_cleanup(struct a2l_data *a2l) -{ - if (a2l->abfd) - bfd_close(a2l->abfd); - zfree((char **)&a2l->input); - zfree(&a2l->syms); - free(a2l); -} - -static int inline_list__append_dso_a2l(struct dso *dso, - struct inline_node *node, - struct symbol *sym) -{ - struct a2l_data *a2l = dso__a2l(dso); - struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname); - char *srcline = NULL; - - if (a2l->filename) - srcline = srcline_from_fileline(a2l->filename, a2l->line); - - return inline_list__append(inline_sym, srcline, node); -} - -static int addr2line(const char *dso_name, u64 addr, - char **file, unsigned int *line, struct dso *dso, - bool unwind_inlines, struct inline_node *node, - struct symbol *sym) -{ - int ret = 0; - struct a2l_data *a2l = dso__a2l(dso); - - if (!a2l) { - a2l = addr2line_init(dso_name); - dso__set_a2l(dso, a2l); - } - - if (a2l == NULL) { - if (!symbol_conf.disable_add2line_warn) - pr_warning("addr2line_init failed for %s\n", dso_name); - return 0; + symbol_conf.addr2line_style[i++] = A2L_STYLE_CMD; } - a2l->addr = addr; - a2l->found = false; - - bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l); - - if (!a2l->found) - return 0; - - if (unwind_inlines) { - int cnt = 0; - - if (node && inline_list__append_dso_a2l(dso, node, sym)) - return 0; - - while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, - &a2l->funcname, &a2l->line) && - cnt++ < MAX_INLINE_NEST) { - - if (a2l->filename && !strlen(a2l->filename)) - a2l->filename = NULL; - - if (node != NULL) { - if (inline_list__append_dso_a2l(dso, node, sym)) - return 0; - // found at least one inline frame - ret = 1; - } + for (size_t i = 0; i < ARRAY_SIZE(symbol_conf.addr2line_style); i++) { + switch (symbol_conf.addr2line_style[i]) { + case A2L_STYLE_LIBDW: + ret = libdw__addr2line(addr, file, line_nr, dso, unwind_inlines, + node, sym); + break; + case A2L_STYLE_LLVM: + ret = llvm__addr2line(dso_name, addr, file, line_nr, dso, unwind_inlines, + node, sym); + break; + case A2L_STYLE_LIBBFD: + ret = libbfd__addr2line(dso_name, addr, file, line_nr, dso, unwind_inlines, + node, sym); + break; + case A2L_STYLE_CMD: + ret = cmd__addr2line(dso_name, addr, file, line_nr, dso, unwind_inlines, + node, sym); + break; + case A2L_STYLE_UNKNOWN: + default: + break; } + if (ret > 0) + return ret; } - if (file) { - *file = a2l->filename ? strdup(a2l->filename) : NULL; - ret = *file ? 1 : 0; - } - - if (line) - *line = a2l->line; - - return ret; -} - -void dso__free_a2l(struct dso *dso) -{ - struct a2l_data *a2l = dso__a2l(dso); - - if (!a2l) - return; - - addr2line_cleanup(a2l); - - dso__set_a2l(dso, NULL); -} - -#else /* HAVE_LIBBFD_SUPPORT */ - -static int filename_split(char *filename, unsigned int *line_nr) -{ - char *sep; - - sep = strchr(filename, '\n'); - if (sep) - *sep = '\0'; - - if (!strcmp(filename, "??:0")) - return 0; - - sep = strchr(filename, ':'); - if (sep) { - *sep++ = '\0'; - *line_nr = strtoul(sep, NULL, 0); - return 1; - } - pr_debug("addr2line missing ':' in filename split\n"); return 0; } -static void addr2line_subprocess_cleanup(struct child_process *a2l) +int addr2line_configure(const char *var, const char *value, void *cb __maybe_unused) { - if (a2l->pid != -1) { - kill(a2l->pid, SIGKILL); - finish_command(a2l); /* ignore result, we don't care */ - a2l->pid = -1; - close(a2l->in); - close(a2l->out); - } - - free(a2l); -} - -static struct child_process *addr2line_subprocess_init(const char *addr2line_path, - const char *binary_path) -{ - const char *argv[] = { - addr2line_path ?: "addr2line", - "-e", binary_path, - "-a", "-i", "-f", NULL + static const char * const a2l_style_names[] = { + [A2L_STYLE_LIBDW] = "libdw", + [A2L_STYLE_LLVM] = "llvm", + [A2L_STYLE_LIBBFD] = "libbfd", + [A2L_STYLE_CMD] = "addr2line", + NULL }; - struct child_process *a2l = zalloc(sizeof(*a2l)); - int start_command_status = 0; - - if (a2l == NULL) { - pr_err("Failed to allocate memory for addr2line"); - return NULL; - } - - a2l->pid = -1; - a2l->in = -1; - a2l->out = -1; - a2l->no_stderr = 1; - - a2l->argv = argv; - start_command_status = start_command(a2l); - a2l->argv = NULL; /* it's not used after start_command; avoid dangling pointers */ - - if (start_command_status != 0) { - pr_warning("could not start addr2line (%s) for %s: start_command return code %d\n", - addr2line_path, binary_path, start_command_status); - addr2line_subprocess_cleanup(a2l); - return NULL; - } - - return a2l; -} -enum a2l_style { - BROKEN, - GNU_BINUTILS, - LLVM, -}; + char *s, *p, *saveptr; + size_t i = 0; -static enum a2l_style addr2line_configure(struct child_process *a2l, const char *dso_name) -{ - static bool cached; - static enum a2l_style style; - - if (!cached) { - char buf[128]; - struct io io; - int ch; - int lines; - - if (write(a2l->in, ",\n", 2) != 2) - return BROKEN; - - io__init(&io, a2l->out, buf, sizeof(buf)); - ch = io__get_char(&io); - if (ch == ',') { - style = LLVM; - cached = true; - lines = 1; - pr_debug("Detected LLVM addr2line style\n"); - } else if (ch == '0') { - style = GNU_BINUTILS; - cached = true; - lines = 3; - pr_debug("Detected binutils addr2line style\n"); - } else { - if (!symbol_conf.disable_add2line_warn) { - char *output = NULL; - size_t output_len; - - io__getline(&io, &output, &output_len); - pr_warning("%s %s: addr2line configuration failed\n", - __func__, dso_name); - pr_warning("\t%c%s", ch, output); - } - pr_debug("Unknown/broken addr2line style\n"); - return BROKEN; - } - while (lines) { - ch = io__get_char(&io); - if (ch <= 0) - break; - if (ch == '\n') - lines--; - } - /* Ignore SIGPIPE in the event addr2line exits. */ - signal(SIGPIPE, SIG_IGN); - } - return style; -} - -static int read_addr2line_record(struct io *io, - enum a2l_style style, - const char *dso_name, - u64 addr, - bool first, - char **function, - char **filename, - unsigned int *line_nr) -{ - /* - * Returns: - * -1 ==> error - * 0 ==> sentinel (or other ill-formed) record read - * 1 ==> a genuine record read - */ - char *line = NULL; - size_t line_len = 0; - unsigned int dummy_line_nr = 0; - int ret = -1; - - if (function != NULL) - zfree(function); - - if (filename != NULL) - zfree(filename); - - if (line_nr != NULL) - *line_nr = 0; - - /* - * Read the first line. Without an error this will be: - * - for the first line an address like 0x1234, - * - the binutils sentinel 0x0000000000000000, - * - the llvm-addr2line the sentinel ',' character, - * - the function name line for an inlined function. - */ - if (io__getline(io, &line, &line_len) < 0 || !line_len) - goto error; - - pr_debug("%s %s: addr2line read address for sentinel: %s", __func__, dso_name, line); - if (style == LLVM && line_len == 2 && line[0] == ',') { - /* Found the llvm-addr2line sentinel character. */ - zfree(&line); + if (strcmp(var, "addr2line.style")) return 0; - } else if (style == GNU_BINUTILS && (!first || addr != 0)) { - int zero_count = 0, non_zero_count = 0; - /* - * Check for binutils sentinel ignoring it for the case the - * requested address is 0. - */ - - /* A given address should always start 0x. */ - if (line_len >= 2 || line[0] != '0' || line[1] != 'x') { - for (size_t i = 2; i < line_len; i++) { - if (line[i] == '0') - zero_count++; - else if (line[i] != '\n') - non_zero_count++; - } - if (!non_zero_count) { - int ch; - - if (first && !zero_count) { - /* Line was erroneous just '0x'. */ - goto error; - } - /* - * Line was 0x0..0, the sentinel for binutils. Remove - * the function and filename lines. - */ - zfree(&line); - do { - ch = io__get_char(io); - } while (ch > 0 && ch != '\n'); - do { - ch = io__get_char(io); - } while (ch > 0 && ch != '\n'); - return 0; - } - } - } - /* Read the second function name line (if inline data then this is the first line). */ - if (first && (io__getline(io, &line, &line_len) < 0 || !line_len)) - goto error; - - pr_debug("%s %s: addr2line read line: %s", __func__, dso_name, line); - if (function != NULL) - *function = strdup(strim(line)); - - zfree(&line); - line_len = 0; - - /* Read the third filename and line number line. */ - if (io__getline(io, &line, &line_len) < 0 || !line_len) - goto error; - - pr_debug("%s %s: addr2line filename:number : %s", __func__, dso_name, line); - if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0 && - style == GNU_BINUTILS) { - ret = 0; - goto error; - } - - if (filename != NULL) - *filename = strdup(line); - - zfree(&line); - line_len = 0; - - return 1; -error: - free(line); - if (function != NULL) - zfree(function); - if (filename != NULL) - zfree(filename); - return ret; -} - -static int inline_list__append_record(struct dso *dso, - struct inline_node *node, - struct symbol *sym, - const char *function, - const char *filename, - unsigned int line_nr) -{ - struct symbol *inline_sym = new_inline_sym(dso, sym, function); - - return inline_list__append(inline_sym, srcline_from_fileline(filename, line_nr), node); -} - -static int addr2line(const char *dso_name, u64 addr, - char **file, unsigned int *line_nr, - struct dso *dso, - bool unwind_inlines, - struct inline_node *node, - struct symbol *sym __maybe_unused) -{ - struct child_process *a2l = dso__a2l(dso); - char *record_function = NULL; - char *record_filename = NULL; - unsigned int record_line_nr = 0; - int record_status = -1; - int ret = 0; - size_t inline_count = 0; - int len; - char buf[128]; - ssize_t written; - struct io io = { .eof = false }; - enum a2l_style a2l_style; - - if (!a2l) { - if (!filename__has_section(dso_name, ".debug_line")) - goto out; - - dso__set_a2l(dso, - addr2line_subprocess_init(symbol_conf.addr2line_path, dso_name)); - a2l = dso__a2l(dso); - } - - if (a2l == NULL) { - if (!symbol_conf.disable_add2line_warn) - pr_warning("%s %s: addr2line_subprocess_init failed\n", __func__, dso_name); - goto out; - } - a2l_style = addr2line_configure(a2l, dso_name); - if (a2l_style == BROKEN) - goto out; + if (!value) + return -1; - /* - * Send our request and then *deliberately* send something that can't be - * interpreted as a valid address to ask addr2line about (namely, - * ","). This causes addr2line to first write out the answer to our - * request, in an unbounded/unknown number of records, and then to write - * out the lines "0x0...0", "??" and "??:0", for GNU binutils, or "," - * for llvm-addr2line, so that we can detect when it has finished giving - * us anything useful. - */ - len = snprintf(buf, sizeof(buf), "%016"PRIx64"\n,\n", addr); - written = len > 0 ? write(a2l->in, buf, len) : -1; - if (written != len) { - if (!symbol_conf.disable_add2line_warn) - pr_warning("%s %s: could not send request\n", __func__, dso_name); - goto out; - } - io__init(&io, a2l->out, buf, sizeof(buf)); - io.timeout_ms = addr2line_timeout_ms; - switch (read_addr2line_record(&io, a2l_style, dso_name, addr, /*first=*/true, - &record_function, &record_filename, &record_line_nr)) { - case -1: - if (!symbol_conf.disable_add2line_warn) - pr_warning("%s %s: could not read first record\n", __func__, dso_name); - goto out; - case 0: - /* - * The first record was invalid, so return failure, but first - * read another record, since we sent a sentinel ',' for the - * sake of detected the last inlined function. Treat this as the - * first of a record as the ',' generates a new start with GNU - * binutils, also force a non-zero address as we're no longer - * reading that record. - */ - switch (read_addr2line_record(&io, a2l_style, dso_name, - /*addr=*/1, /*first=*/true, - NULL, NULL, NULL)) { - case -1: - if (!symbol_conf.disable_add2line_warn) - pr_warning("%s %s: could not read sentinel record\n", - __func__, dso_name); - break; - case 0: - /* The sentinel as expected. */ - break; - default: - if (!symbol_conf.disable_add2line_warn) - pr_warning("%s %s: unexpected record instead of sentinel", - __func__, dso_name); - break; - } - goto out; - default: - /* First record as expected. */ - break; - } + s = strdup(value); + if (!s) + return -1; - if (file) { - *file = strdup(record_filename); - ret = 1; - } - if (line_nr) - *line_nr = record_line_nr; - - if (unwind_inlines) { - if (node && inline_list__append_record(dso, node, sym, - record_function, - record_filename, - record_line_nr)) { - ret = 0; - goto out; - } - } + p = strtok_r(s, ",", &saveptr); + while (p && i < ARRAY_SIZE(symbol_conf.addr2line_style)) { + bool found = false; + char *q = strim(p); - /* - * We have to read the records even if we don't care about the inline - * info. This isn't the first record and force the address to non-zero - * as we're reading records beyond the first. - */ - while ((record_status = read_addr2line_record(&io, - a2l_style, - dso_name, - /*addr=*/1, - /*first=*/false, - &record_function, - &record_filename, - &record_line_nr)) == 1) { - if (unwind_inlines && node && inline_count++ < MAX_INLINE_NEST) { - if (inline_list__append_record(dso, node, sym, - record_function, - record_filename, - record_line_nr)) { - ret = 0; - goto out; + for (size_t j = A2L_STYLE_LIBDW; j < MAX_A2L_STYLE; j++) { + if (!strcasecmp(q, a2l_style_names[j])) { + symbol_conf.addr2line_style[i++] = j; + found = true; + break; } - ret = 1; /* found at least one inline frame */ } + if (!found) + pr_warning("Unknown addr2line style: %s\n", q); + p = strtok_r(NULL, ",", &saveptr); } -out: - free(record_function); - free(record_filename); - if (io.eof) { - dso__set_a2l(dso, NULL); - addr2line_subprocess_cleanup(a2l); - } - return ret; -} - -void dso__free_a2l(struct dso *dso) -{ - struct child_process *a2l = dso__a2l(dso); - - if (!a2l) - return; - - addr2line_subprocess_cleanup(a2l); - - dso__set_a2l(dso, NULL); + free(s); + return 0; } -#endif /* HAVE_LIBBFD_SUPPORT */ - static struct inline_node *addr2inlines(const char *dso_name, u64 addr, struct dso *dso, struct symbol *sym) { @@ -862,7 +239,9 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr, INIT_LIST_HEAD(&node->val); node->addr = addr; - addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym); + addr2line(dso_name, addr, /*file=*/NULL, /*line_nr=*/NULL, dso, + /*unwind_inlines=*/true, node, sym); + return node; } @@ -889,7 +268,7 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, goto out_err; if (!addr2line(dso_name, addr, &file, &line, dso, - unwind_inlines, NULL, sym)) + unwind_inlines, /*node=*/NULL, sym)) goto out_err; srcline = srcline_from_fileline(file, line); @@ -935,7 +314,8 @@ char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line) if (dso_name == NULL) goto out_err; - if (!addr2line(dso_name, addr, &file, line, dso, true, NULL, NULL)) + if (!addr2line(dso_name, addr, &file, line, dso, /*unwind_inlines=*/true, + /*node=*/NULL, /*sym=*/NULL)) goto out_err; dso__set_a2l_fails(dso, 0); diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h index 75010d39ea28..7c37b3bf9ce7 100644 --- a/tools/perf/util/srcline.h +++ b/tools/perf/util/srcline.h @@ -9,7 +9,6 @@ struct dso; struct symbol; -extern int addr2line_timeout_ms; extern bool srcline_full_filename; char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, bool show_sym, bool show_addr, u64 ip); @@ -29,6 +28,8 @@ void srcline__tree_delete(struct rb_root_cached *tree); extern char *srcline__unknown; #define SRCLINE_UNKNOWN srcline__unknown +#define MAX_INLINE_NEST 1024 + struct inline_list { struct symbol *symbol; char *srcline; @@ -55,4 +56,13 @@ struct inline_node *inlines__tree_find(struct rb_root_cached *tree, u64 addr); /* delete all nodes within the tree of inline_node s */ void inlines__tree_delete(struct rb_root_cached *tree); +int inline_list__append(struct symbol *symbol, char *srcline, struct inline_node *node); +int inline_list__append_tail(struct symbol *symbol, char *srcline, struct inline_node *node); +char *srcline_from_fileline(const char *file, unsigned int line); +struct symbol *new_inline_sym(struct dso *dso, + struct symbol *base_sym, + const char *funcname); + +int addr2line_configure(const char *var, const char *value, void *cb); + #endif /* PERF_SRCLINE_H */ diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index ba79f73e1cf5..993f4c4b8f44 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -50,15 +50,15 @@ static int aggr_header_lens[] = { }; static const char *aggr_header_csv[] = { - [AGGR_CORE] = "core,cpus,", - [AGGR_CACHE] = "cache,cpus,", - [AGGR_CLUSTER] = "cluster,cpus,", - [AGGR_DIE] = "die,cpus,", - [AGGR_SOCKET] = "socket,cpus,", - [AGGR_NONE] = "cpu,", - [AGGR_THREAD] = "comm-pid,", - [AGGR_NODE] = "node,", - [AGGR_GLOBAL] = "" + [AGGR_CORE] = "core,ctrs,", + [AGGR_CACHE] = "cache,ctrs,", + [AGGR_CLUSTER] = "cluster,ctrs,", + [AGGR_DIE] = "die,ctrs,", + [AGGR_SOCKET] = "socket,ctrs,", + [AGGR_NONE] = "cpu,", + [AGGR_THREAD] = "comm-pid,", + [AGGR_NODE] = "node,", + [AGGR_GLOBAL] = "" }; static const char *aggr_header_std[] = { @@ -304,7 +304,7 @@ static void print_aggr_id_std(struct perf_stat_config *config, return; } - fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, 4, aggr_nr); + fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, /*strlen("ctrs")*/ 4, aggr_nr); } static void print_aggr_id_csv(struct perf_stat_config *config, @@ -366,27 +366,27 @@ static void print_aggr_id_json(struct perf_stat_config *config, struct outstate { switch (config->aggr_mode) { case AGGR_CORE: - json_out(os, "\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d", + json_out(os, "\"core\" : \"S%d-D%d-C%d\", \"counters\" : %d", id.socket, id.die, id.core, aggr_nr); break; case AGGR_CACHE: - json_out(os, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d", + json_out(os, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"counters\" : %d", id.socket, id.die, id.cache_lvl, id.cache, aggr_nr); break; case AGGR_CLUSTER: - json_out(os, "\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d", + json_out(os, "\"cluster\" : \"S%d-D%d-CLS%d\", \"counters\" : %d", id.socket, id.die, id.cluster, aggr_nr); break; case AGGR_DIE: - json_out(os, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d", + json_out(os, "\"die\" : \"S%d-D%d\", \"counters\" : %d", id.socket, id.die, aggr_nr); break; case AGGR_SOCKET: - json_out(os, "\"socket\" : \"S%d\", \"aggregate-number\" : %d", + json_out(os, "\"socket\" : \"S%d\", \"counters\" : %d", id.socket, aggr_nr); break; case AGGR_NODE: - json_out(os, "\"node\" : \"N%d\", \"aggregate-number\" : %d", + json_out(os, "\"node\" : \"N%d\", \"counters\" : %d", id.node, aggr_nr); break; case AGGR_NONE: @@ -439,9 +439,9 @@ static inline void __new_line_std_csv(struct perf_stat_config *config, aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); } -static inline void __new_line_std(struct outstate *os) +static inline void __new_line_std(struct perf_stat_config *config, struct outstate *os) { - fprintf(os->fh, " "); + fprintf(os->fh, "%*s", COUNTS_LEN + EVNAME_LEN + config->unit_width + 2, ""); } static void do_new_line_std(struct perf_stat_config *config, @@ -450,7 +450,7 @@ static void do_new_line_std(struct perf_stat_config *config, __new_line_std_csv(config, os); if (config->aggr_mode == AGGR_NONE) fprintf(os->fh, " "); - __new_line_std(os); + __new_line_std(config, os); } static void print_metric_std(struct perf_stat_config *config, @@ -583,36 +583,13 @@ static void print_metricgroup_header_std(struct perf_stat_config *config, int n; if (!metricgroup_name) { - __new_line_std(os); + __new_line_std(config, os); return; } n = fprintf(config->output, " %*s", EVNAME_LEN, metricgroup_name); - fprintf(config->output, "%*s", MGROUP_LEN - n - 1, ""); -} - -/* Filter out some columns that don't work well in metrics only mode */ - -static bool valid_only_metric(const char *unit) -{ - if (!unit) - return false; - if (strstr(unit, "/sec") || - strstr(unit, "CPUs utilized")) - return false; - return true; -} - -static const char *fixunit(char *buf, struct evsel *evsel, - const char *unit) -{ - if (!strncmp(unit, "of all", 6)) { - snprintf(buf, 1024, "%s %s", evsel__name(evsel), - unit); - return buf; - } - return unit; + fprintf(config->output, "%*s", MGROUP_LEN + config->unit_width + 2 - n, ""); } static void print_metric_only(struct perf_stat_config *config, @@ -621,13 +598,12 @@ static void print_metric_only(struct perf_stat_config *config, { struct outstate *os = ctx; FILE *out = os->fh; - char buf[1024], str[1024]; + char str[1024]; unsigned mlen = config->metric_only_len; const char *color = metric_threshold_classify__color(thresh); - if (!valid_only_metric(unit)) - return; - unit = fixunit(buf, os->evsel, unit); + if (!unit) + unit = ""; if (mlen < strlen(unit)) mlen = strlen(unit) + 1; @@ -643,16 +619,15 @@ static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused void *ctx, enum metric_threshold_classify thresh __maybe_unused, const char *fmt, - const char *unit, double val) + const char *unit __maybe_unused, double val) { struct outstate *os = ctx; FILE *out = os->fh; char buf[64], *vals, *ends; - char tbuf[1024]; - if (!valid_only_metric(unit)) + if (!unit) return; - unit = fixunit(tbuf, os->evsel, unit); + snprintf(buf, sizeof(buf), fmt ?: "", val); ends = vals = skip_spaces(buf); while (isdigit(*ends) || *ends == '.') @@ -670,13 +645,9 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse { struct outstate *os = ctx; char buf[64], *ends; - char tbuf[1024]; const char *vals; - if (!valid_only_metric(unit)) - return; - unit = fixunit(tbuf, os->evsel, unit); - if (!unit[0]) + if (!unit || !unit[0]) return; snprintf(buf, sizeof(buf), fmt ?: "", val); vals = ends = skip_spaces(buf); @@ -695,7 +666,6 @@ static void print_metric_header(struct perf_stat_config *config, const char *unit, double val __maybe_unused) { struct outstate *os = ctx; - char tbuf[1024]; /* In case of iostat, print metric header for first root port only */ if (config->iostat_run && @@ -705,9 +675,8 @@ static void print_metric_header(struct perf_stat_config *config, if (os->evsel->cgrp != os->cgrp) return; - if (!valid_only_metric(unit)) + if (!unit) return; - unit = fixunit(tbuf, os->evsel, unit); if (config->json_output) return; @@ -798,40 +767,28 @@ static void abs_printout(struct perf_stat_config *config, print_cgroup(config, os, evsel->cgrp); } -static bool is_mixed_hw_group(struct evsel *counter) -{ - struct evlist *evlist = counter->evlist; - u32 pmu_type = counter->core.attr.type; - struct evsel *pos; - - if (counter->core.nr_members < 2) - return false; - - evlist__for_each_entry(evlist, pos) { - /* software events can be part of any hardware group */ - if (pos->core.attr.type == PERF_TYPE_SOFTWARE) - continue; - if (pmu_type == PERF_TYPE_SOFTWARE) { - pmu_type = pos->core.attr.type; - continue; - } - if (pmu_type != pos->core.attr.type) - return true; - } - - return false; -} - -static bool evlist__has_hybrid(struct evlist *evlist) +static bool evlist__has_hybrid_pmus(struct evlist *evlist) { struct evsel *evsel; + struct perf_pmu *last_core_pmu = NULL; if (perf_pmus__num_core_pmus() == 1) return false; evlist__for_each_entry(evlist, evsel) { - if (evsel->core.is_pmu_core) + if (evsel->core.is_pmu_core) { + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu == last_core_pmu) + continue; + + if (last_core_pmu == NULL) { + last_core_pmu = pmu; + continue; + } + /* A distinct core PMU. */ return true; + } } return false; @@ -863,19 +820,11 @@ static void printout(struct perf_stat_config *config, struct outstate *os, } if (run == 0 || ena == 0 || counter->counts->scaled == -1) { - if (config->metric_only) { - pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, - /*unit=*/NULL, /*val=*/0); - return; - } - ok = false; if (counter->supported) { - if (!evlist__has_hybrid(counter->evlist)) { + if (!evlist__has_hybrid_pmus(counter->evlist)) { config->print_free_counters_hint = 1; - if (is_mixed_hw_group(counter)) - config->print_mixed_hw_group_error = 1; } } } @@ -886,41 +835,39 @@ static void printout(struct perf_stat_config *config, struct outstate *os, out.ctx = os; out.force_header = false; - if (!config->metric_only && !counter->default_metricgroup) { + if (!config->metric_only && (!counter->default_metricgroup || counter->default_show_events)) { abs_printout(config, os, os->id, os->aggr_nr, counter, uval, ok); print_noise(config, os, counter, noise, /*before_metric=*/true); print_running(config, os, run, ena, /*before_metric=*/true); } - if (ok) { - if (!config->metric_only && counter->default_metricgroup) { - void *from = NULL; - - aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); - /* Print out all the metricgroup with the same metric event. */ - do { - int num = 0; - - /* Print out the new line for the next new metricgroup. */ - if (from) { - if (config->json_output) - new_line_json(config, (void *)os); - else - __new_line_std_csv(config, os); - } - - print_noise(config, os, counter, noise, /*before_metric=*/true); - print_running(config, os, run, ena, /*before_metric=*/true); - from = perf_stat__print_shadow_stats_metricgroup(config, counter, aggr_idx, - &num, from, &out, - &config->metric_events); - } while (from != NULL); - } else - perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, - &out, &config->metric_events); + if (!config->metric_only && counter->default_metricgroup && + !counter->default_show_events) { + void *from = NULL; + + aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); + /* Print out all the metricgroup with the same metric event. */ + do { + int num = 0; + + /* Print out the new line for the next new metricgroup. */ + if (from) { + if (config->json_output) + new_line_json(config, (void *)os); + else + __new_line_std_csv(config, os); + } + + print_noise(config, os, counter, noise, + /*before_metric=*/true); + print_running(config, os, run, ena, + /*before_metric=*/true); + from = perf_stat__print_shadow_stats_metricgroup( + config, counter, aggr_idx, &num, from, &out); + } while (from != NULL); } else { - pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, /*unit=*/NULL, /*val=*/0); + perf_stat__print_shadow_stats(config, counter, aggr_idx, &out); } if (!config->metric_only) { @@ -929,81 +876,6 @@ static void printout(struct perf_stat_config *config, struct outstate *os, } } -static void uniquify_event_name(struct evsel *counter) -{ - const char *name, *pmu_name; - char *new_name, *config; - int ret; - - /* The evsel was already uniquified. */ - if (counter->uniquified_name) - return; - - /* Avoid checking to uniquify twice. */ - counter->uniquified_name = true; - - /* The evsel has a "name=" config term or is from libpfm. */ - if (counter->use_config_name || counter->is_libpfm_event) - return; - - /* Legacy no PMU event, don't uniquify. */ - if (!counter->pmu || - (counter->pmu->type < PERF_TYPE_MAX && counter->pmu->type != PERF_TYPE_RAW)) - return; - - /* A sysfs or json event replacing a legacy event, don't uniquify. */ - if (counter->pmu->is_core && counter->alternate_hw_config != PERF_COUNT_HW_MAX) - return; - - name = evsel__name(counter); - pmu_name = counter->pmu->name; - /* Already prefixed by the PMU name. */ - if (!strncmp(name, pmu_name, strlen(pmu_name))) - return; - - config = strchr(name, '/'); - if (config) { - int len = config - name; - - if (config[1] == '/') { - /* case: event// */ - ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2); - } else { - /* case: event/.../ */ - ret = asprintf(&new_name, "%s/%.*s,%s", pmu_name, len, name, config + 1); - } - } else { - config = strchr(name, ':'); - if (config) { - /* case: event:.. */ - int len = config - name; - - ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1); - } else { - /* case: event */ - ret = asprintf(&new_name, "%s/%s/", pmu_name, name); - } - } - if (ret > 0) { - free(counter->name); - counter->name = new_name; - } else { - /* ENOMEM from asprintf. */ - counter->uniquified_name = false; - } -} - -static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config) -{ - return evsel__is_hybrid(evsel) && !config->hybrid_merge; -} - -static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter) -{ - if (config->aggr_mode == AGGR_NONE || hybrid_uniquify(counter, config)) - uniquify_event_name(counter); -} - /** * should_skip_zero_count() - Check if the event should print 0 values. * @config: The perf stat configuration (including aggregation mode). @@ -1025,7 +897,7 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, const struct aggr_cpu_id *id) { struct perf_cpu cpu; - int idx; + unsigned int idx; /* * Skip unsupported default events when not verbose. (default events @@ -1034,6 +906,9 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, if (verbose == 0 && counter->skippable && !counter->supported) return true; + /* Metric only counts won't be displayed but the metric wants to be computed. */ + if (config->metric_only) + return false; /* * Skip value 0 when enabling --per-thread globally, * otherwise it will have too many 0 output. @@ -1042,8 +917,16 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, return true; /* - * Many tool events are only gathered on the first index, skip other - * zero values. + * In per-thread mode the aggr_map and aggr_get_id functions may be + * NULL, assume all 0 values should be output in that case. + */ + if (!config->aggr_map || !config->aggr_get_id) + return false; + + /* + * Tool events may be gathered on all logical CPUs, for example + * system_time, but for many the first index is the only one used, for + * example num_cores. Don't skip for the first index. */ if (evsel__is_tool(counter)) { struct aggr_cpu_id own_id = @@ -1051,15 +934,12 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, return !aggr_cpu_id__equal(id, &own_id); } - /* - * Skip value 0 when it's an uncore event and the given aggr id - * does not belong to the PMU cpumask. + * Skip value 0 when the counter's cpumask doesn't match the given aggr + * id. */ - if (!counter->pmu || !counter->pmu->is_uncore) - return false; - perf_cpu_map__for_each_cpu(cpu, idx, counter->pmu->cpus) { + perf_cpu_map__for_each_cpu(cpu, idx, counter->core.cpus) { struct aggr_cpu_id own_id = config->aggr_get_id(config, cpu); if (aggr_cpu_id__equal(id, &own_id)) @@ -1086,16 +966,21 @@ static void print_counter_aggrdata(struct perf_stat_config *config, os->evsel = counter; /* Skip already merged uncore/hybrid events */ - if (counter->merged_stat) - return; - - uniquify_counter(config, counter); + if (config->aggr_mode != AGGR_NONE) { + if (evsel__is_hybrid(counter)) { + if (config->hybrid_merge && counter->first_wildcard_match != NULL) + return; + } else { + if (counter->first_wildcard_match != NULL) + return; + } + } val = aggr->counts.val; ena = aggr->counts.ena; run = aggr->counts.run; - if (perf_stat__skip_metric_event(counter, &config->metric_events, ena, run)) + if (perf_stat__skip_metric_event(counter)) return; if (val == 0 && should_skip_zero_counter(config, counter, &id)) @@ -1240,7 +1125,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config, struct evlist *evlist, struct outstate *os) { - int all_idx; + unsigned int all_idx; struct perf_cpu cpu; perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.user_requested_cpus) { @@ -1354,10 +1239,7 @@ static void print_metric_headers(struct perf_stat_config *config, os.evsel = counter; - perf_stat__print_shadow_stats(config, counter, 0, - 0, - &out, - &config->metric_events); + perf_stat__print_shadow_stats(config, counter, /*aggr_idx=*/0, &out); } if (!config->json_output) @@ -1396,7 +1278,7 @@ static void print_header_interval_std(struct perf_stat_config *config, case AGGR_CLUSTER: case AGGR_CACHE: case AGGR_CORE: - fprintf(output, "#%*s %-*s cpus", + fprintf(output, "#%*s %-*s ctrs", INTERVAL_LEN - 1, "time", aggr_header_lens[config->aggr_mode], aggr_header_std[config->aggr_mode]); @@ -1508,21 +1390,12 @@ static void print_header(struct perf_stat_config *config, num_print_iv = 0; } -static int get_precision(double num) -{ - if (num > 1) - return 0; - - return lround(ceil(-log10(num))); -} - -static void print_table(struct perf_stat_config *config, - FILE *output, int precision, double avg) +static void print_table(struct perf_stat_config *config, FILE *output, double avg) { char tmp[64]; int idx, indent = 0; - scnprintf(tmp, 64, " %17.*f", precision, avg); + scnprintf(tmp, 64, " %17.9f", avg); while (tmp[indent] == ' ') indent++; @@ -1532,8 +1405,7 @@ static void print_table(struct perf_stat_config *config, double run = (double) config->walltime_run[idx] / NSEC_PER_SEC; int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5); - fprintf(output, " %17.*f (%+.*f) ", - precision, run, precision, run - avg); + fprintf(output, " %17.9f (%+.9f) ", run, run - avg); for (h = 0; h < n; h++) fprintf(output, "#"); @@ -1573,17 +1445,11 @@ static void print_footer(struct perf_stat_config *config) } } else { double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC; - /* - * Display at most 2 more significant - * digits than the stddev inaccuracy. - */ - int precision = get_precision(sd) + 2; if (config->walltime_run_table) - print_table(config, output, precision, avg); + print_table(config, output, avg); - fprintf(output, " %17.*f +- %.*f seconds time elapsed", - precision, avg, precision, sd); + fprintf(output, " %17.9f +- %.9f seconds time elapsed", avg, sd); print_noise_pct(config, NULL, sd, avg, /*before_metric=*/false); } @@ -1595,11 +1461,6 @@ static void print_footer(struct perf_stat_config *config) " echo 0 > /proc/sys/kernel/nmi_watchdog\n" " perf stat ...\n" " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); - - if (config->print_mixed_hw_group_error) - fprintf(output, - "The events in group usually have to be from " - "the same PMU. Try reorganizing the group.\n"); } static void print_percore(struct perf_stat_config *config, @@ -1670,31 +1531,6 @@ static void print_cgroup_counter(struct perf_stat_config *config, struct evlist print_metric_end(config, os); } -static void disable_uniquify(struct evlist *evlist) -{ - struct evsel *counter; - struct perf_pmu *last_pmu = NULL; - bool first = true; - - evlist__for_each_entry(evlist, counter) { - /* If PMUs vary then uniquify can be useful. */ - if (!first && counter->pmu != last_pmu) - return; - first = false; - if (counter->pmu) { - /* Allow uniquify for uncore PMUs. */ - if (!counter->pmu->is_core) - return; - /* Keep hybrid event names uniquified for clarity. */ - if (perf_pmus__num_core_pmus() > 1) - return; - } - } - evlist__for_each_entry_continue(evlist, counter) { - counter->uniquified_name = true; - } -} - void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, int argc, const char **argv) @@ -1706,7 +1542,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf .first = true, }; - disable_uniquify(evlist); + evlist__uniquify_evsel_names(evlist, config); if (config->iostat_run) evlist->selected = evlist__first(evlist); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index fa8b2a1048ff..bc2d44df7baf 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> #include <math.h> #include <stdio.h> #include "evsel.h" @@ -12,365 +13,36 @@ #include "metricgroup.h" #include "cgroup.h" #include "units.h" -#include <linux/zalloc.h> #include "iostat.h" #include "util/hashmap.h" #include "tool_pmu.h" -struct stats walltime_nsecs_stats; -struct rusage_stats ru_stats; - -enum { - CTX_BIT_USER = 1 << 0, - CTX_BIT_KERNEL = 1 << 1, - CTX_BIT_HV = 1 << 2, - CTX_BIT_HOST = 1 << 3, - CTX_BIT_IDLE = 1 << 4, - CTX_BIT_MAX = 1 << 5, -}; - -enum stat_type { - STAT_NONE = 0, - STAT_NSECS, - STAT_CYCLES, - STAT_INSTRUCTIONS, - STAT_STALLED_CYCLES_FRONT, - STAT_STALLED_CYCLES_BACK, - STAT_BRANCHES, - STAT_BRANCH_MISS, - STAT_CACHE_REFS, - STAT_CACHE_MISSES, - STAT_L1_DCACHE, - STAT_L1_ICACHE, - STAT_LL_CACHE, - STAT_ITLB_CACHE, - STAT_DTLB_CACHE, - STAT_L1D_MISS, - STAT_L1I_MISS, - STAT_LL_MISS, - STAT_DTLB_MISS, - STAT_ITLB_MISS, - STAT_MAX -}; - -static int evsel_context(const struct evsel *evsel) +static bool tool_pmu__is_time_event(const struct perf_stat_config *config, + const struct evsel *evsel, int *tool_aggr_idx) { - int ctx = 0; - - if (evsel->core.attr.exclude_kernel) - ctx |= CTX_BIT_KERNEL; - if (evsel->core.attr.exclude_user) - ctx |= CTX_BIT_USER; - if (evsel->core.attr.exclude_hv) - ctx |= CTX_BIT_HV; - if (evsel->core.attr.exclude_host) - ctx |= CTX_BIT_HOST; - if (evsel->core.attr.exclude_idle) - ctx |= CTX_BIT_IDLE; - - return ctx; -} - -void perf_stat__reset_shadow_stats(void) -{ - memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); - memset(&ru_stats, 0, sizeof(ru_stats)); -} - -static enum stat_type evsel__stat_type(struct evsel *evsel) -{ - /* Fake perf_hw_cache_op_id values for use with evsel__match. */ - u64 PERF_COUNT_hw_cache_l1d_miss = PERF_COUNT_HW_CACHE_L1D | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); - u64 PERF_COUNT_hw_cache_l1i_miss = PERF_COUNT_HW_CACHE_L1I | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); - u64 PERF_COUNT_hw_cache_ll_miss = PERF_COUNT_HW_CACHE_LL | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); - u64 PERF_COUNT_hw_cache_dtlb_miss = PERF_COUNT_HW_CACHE_DTLB | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); - u64 PERF_COUNT_hw_cache_itlb_miss = PERF_COUNT_HW_CACHE_ITLB | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); - - if (evsel__is_clock(evsel)) - return STAT_NSECS; - else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) - return STAT_CYCLES; - else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) - return STAT_INSTRUCTIONS; - else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - return STAT_STALLED_CYCLES_FRONT; - else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - return STAT_STALLED_CYCLES_BACK; - else if (evsel__match(evsel, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - return STAT_BRANCHES; - else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) - return STAT_BRANCH_MISS; - else if (evsel__match(evsel, HARDWARE, HW_CACHE_REFERENCES)) - return STAT_CACHE_REFS; - else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) - return STAT_CACHE_MISSES; - else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1D)) - return STAT_L1_DCACHE; - else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1I)) - return STAT_L1_ICACHE; - else if (evsel__match(evsel, HW_CACHE, HW_CACHE_LL)) - return STAT_LL_CACHE; - else if (evsel__match(evsel, HW_CACHE, HW_CACHE_DTLB)) - return STAT_DTLB_CACHE; - else if (evsel__match(evsel, HW_CACHE, HW_CACHE_ITLB)) - return STAT_ITLB_CACHE; - else if (evsel__match(evsel, HW_CACHE, hw_cache_l1d_miss)) - return STAT_L1D_MISS; - else if (evsel__match(evsel, HW_CACHE, hw_cache_l1i_miss)) - return STAT_L1I_MISS; - else if (evsel__match(evsel, HW_CACHE, hw_cache_ll_miss)) - return STAT_LL_MISS; - else if (evsel__match(evsel, HW_CACHE, hw_cache_dtlb_miss)) - return STAT_DTLB_MISS; - else if (evsel__match(evsel, HW_CACHE, hw_cache_itlb_miss)) - return STAT_ITLB_MISS; - return STAT_NONE; -} - -static enum metric_threshold_classify get_ratio_thresh(const double ratios[3], double val) -{ - assert(ratios[0] > ratios[1]); - assert(ratios[1] > ratios[2]); - - return val > ratios[1] - ? (val > ratios[0] ? METRIC_THRESHOLD_BAD : METRIC_THRESHOLD_NEARLY_BAD) - : (val > ratios[2] ? METRIC_THRESHOLD_LESS_GOOD : METRIC_THRESHOLD_GOOD); -} - -static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type type) -{ - struct evsel *cur; - int evsel_ctx = evsel_context(evsel); - - evlist__for_each_entry(evsel->evlist, cur) { - struct perf_stat_aggr *aggr; - - /* Ignore the evsel that is being searched from. */ - if (evsel == cur) - continue; - - /* Ignore evsels that are part of different groups. */ - if (evsel->core.leader->nr_members > 1 && - evsel->core.leader != cur->core.leader) - continue; - /* Ignore evsels with mismatched modifiers. */ - if (evsel_ctx != evsel_context(cur)) - continue; - /* Ignore if not the cgroup we're looking for. */ - if (evsel->cgrp != cur->cgrp) - continue; - /* Ignore if not the stat we're looking for. */ - if (type != evsel__stat_type(cur)) - continue; - - /* - * Except the SW CLOCK events, - * ignore if not the PMU we're looking for. - */ - if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu)) - continue; - - aggr = &cur->stats->aggr[aggr_idx]; - if (type == STAT_NSECS) - return aggr->counts.val; - return aggr->counts.val * cur->scale; - } - return 0.0; -} - -static void print_ratio(struct perf_stat_config *config, - const struct evsel *evsel, int aggr_idx, - double numerator, struct perf_stat_output_ctx *out, - enum stat_type denominator_type, - const double thresh_ratios[3], const char *_unit) -{ - double denominator = find_stat(evsel, aggr_idx, denominator_type); - double ratio = 0; - enum metric_threshold_classify thresh = METRIC_THRESHOLD_UNKNOWN; - const char *fmt = NULL; - const char *unit = NULL; - - if (numerator && denominator) { - ratio = numerator / denominator * 100.0; - thresh = get_ratio_thresh(thresh_ratios, ratio); - fmt = "%7.2f%%"; - unit = _unit; - } - out->print_metric(config, out->ctx, thresh, fmt, unit, ratio); -} - -static void print_stalled_cycles_front(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double stalled, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {50.0, 30.0, 10.0}; - - print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, thresh_ratios, - "frontend cycles idle"); -} - -static void print_stalled_cycles_back(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double stalled, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {75.0, 50.0, 20.0}; - - print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, thresh_ratios, - "backend cycles idle"); -} - -static void print_branch_miss(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {20.0, 10.0, 5.0}; - - print_ratio(config, evsel, aggr_idx, misses, out, STAT_BRANCHES, thresh_ratios, - "of all branches"); -} - -static void print_l1d_miss(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {20.0, 10.0, 5.0}; - - print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_DCACHE, thresh_ratios, - "of all L1-dcache accesses"); -} - -static void print_l1i_miss(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {20.0, 10.0, 5.0}; - - print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_ICACHE, thresh_ratios, - "of all L1-icache accesses"); -} - -static void print_ll_miss(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {20.0, 10.0, 5.0}; - - print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, thresh_ratios, - "of all LL-cache accesses"); -} - -static void print_dtlb_miss(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {20.0, 10.0, 5.0}; - - print_ratio(config, evsel, aggr_idx, misses, out, STAT_DTLB_CACHE, thresh_ratios, - "of all dTLB cache accesses"); -} - -static void print_itlb_miss(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {20.0, 10.0, 5.0}; - - print_ratio(config, evsel, aggr_idx, misses, out, STAT_ITLB_CACHE, thresh_ratios, - "of all iTLB cache accesses"); -} - -static void print_cache_miss(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out) -{ - const double thresh_ratios[3] = {20.0, 10.0, 5.0}; - - print_ratio(config, evsel, aggr_idx, misses, out, STAT_CACHE_REFS, thresh_ratios, - "of all cache refs"); -} + enum tool_pmu_event event = evsel__tool_event(evsel); + int aggr_idx; -static void print_instructions(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double instructions, - struct perf_stat_output_ctx *out) -{ - print_metric_t print_metric = out->print_metric; - void *ctxp = out->ctx; - double cycles = find_stat(evsel, aggr_idx, STAT_CYCLES); - double max_stalled = max(find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_FRONT), - find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_BACK)); - - if (cycles) { - print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%7.2f ", - "insn per cycle", instructions / cycles); - } else { - print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, /*fmt=*/NULL, - "insn per cycle", 0); - } - if (max_stalled && instructions) { - if (out->new_line) - out->new_line(config, ctxp); - print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%7.2f ", - "stalled cycles per insn", max_stalled / instructions); - } -} - -static void print_cycles(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double cycles, - struct perf_stat_output_ctx *out) -{ - double nsecs = find_stat(evsel, aggr_idx, STAT_NSECS); - - if (cycles && nsecs) { - double ratio = cycles / nsecs; - - out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, "%8.3f", - "GHz", ratio); - } else { - out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, /*fmt=*/NULL, - "GHz", 0); - } -} - -static void print_nsecs(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx __maybe_unused, double nsecs, - struct perf_stat_output_ctx *out) -{ - print_metric_t print_metric = out->print_metric; - void *ctxp = out->ctx; - double wall_time = avg_stats(&walltime_nsecs_stats); + if (event != TOOL_PMU__EVENT_DURATION_TIME && + event != TOOL_PMU__EVENT_USER_TIME && + event != TOOL_PMU__EVENT_SYSTEM_TIME) + return false; - if (wall_time) { - print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%8.3f", "CPUs utilized", - nsecs / (wall_time * evsel->scale)); - } else { - print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, /*fmt=*/NULL, - "CPUs utilized", 0); + if (config) { + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + if (config->aggr_map->map[aggr_idx].cpu.cpu == 0) { + *tool_aggr_idx = aggr_idx; + return true; + } + } + pr_debug("Unexpected CPU0 missing in aggregation for tool event.\n"); } + *tool_aggr_idx = 0; /* Assume the first aggregation index works. */ + return true; } -static int prepare_metric(const struct metric_expr *mexp, +static int prepare_metric(struct perf_stat_config *config, + const struct metric_expr *mexp, const struct evsel *evsel, struct expr_parse_ctx *pctx, int aggr_idx) @@ -380,88 +52,56 @@ static int prepare_metric(const struct metric_expr *mexp, int i; for (i = 0; metric_events[i]; i++) { + int source_count = 0, tool_aggr_idx; + bool is_tool_time = + tool_pmu__is_time_event(config, metric_events[i], &tool_aggr_idx); + struct perf_stat_evsel *ps = metric_events[i]->stats; char *n; double val; - int source_count = 0; - if (evsel__is_tool(metric_events[i])) { - struct stats *stats; - double scale; - - switch (evsel__tool_event(metric_events[i])) { - case TOOL_PMU__EVENT_DURATION_TIME: - stats = &walltime_nsecs_stats; - scale = 1e-9; - break; - case TOOL_PMU__EVENT_USER_TIME: - stats = &ru_stats.ru_utime_usec_stat; - scale = 1e-6; - break; - case TOOL_PMU__EVENT_SYSTEM_TIME: - stats = &ru_stats.ru_stime_usec_stat; - scale = 1e-6; + /* + * If there are multiple uncore PMUs and we're not reading the + * leader's stats, determine the stats for the appropriate + * uncore PMU. + */ + if (evsel && evsel->metric_leader && + evsel->pmu != evsel->metric_leader->pmu && + mexp->metric_events[i]->pmu == evsel->metric_leader->pmu) { + struct evsel *pos; + + evlist__for_each_entry(evsel->evlist, pos) { + if (pos->pmu != evsel->pmu) + continue; + if (pos->metric_leader != mexp->metric_events[i]) + continue; + ps = pos->stats; + source_count = 1; break; - case TOOL_PMU__EVENT_NONE: - pr_err("Invalid tool event 'none'"); - abort(); - case TOOL_PMU__EVENT_MAX: - pr_err("Invalid tool event 'max'"); - abort(); - case TOOL_PMU__EVENT_HAS_PMEM: - case TOOL_PMU__EVENT_NUM_CORES: - case TOOL_PMU__EVENT_NUM_CPUS: - case TOOL_PMU__EVENT_NUM_CPUS_ONLINE: - case TOOL_PMU__EVENT_NUM_DIES: - case TOOL_PMU__EVENT_NUM_PACKAGES: - case TOOL_PMU__EVENT_SLOTS: - case TOOL_PMU__EVENT_SMT_ON: - case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ: - default: - pr_err("Unexpected tool event '%s'", evsel__name(metric_events[i])); - abort(); } - val = avg_stats(stats) * scale; - source_count = 1; - } else { - struct perf_stat_evsel *ps = metric_events[i]->stats; - struct perf_stat_aggr *aggr; - + } + /* Time events are always on CPU0, the first aggregation index. */ + if (!ps || !metric_events[i]->supported) { /* - * If there are multiple uncore PMUs and we're not - * reading the leader's stats, determine the stats for - * the appropriate uncore PMU. + * Not supported events will have a count of 0, which + * can be confusing in a metric. Explicitly set the + * value to NAN. Not counted events (enable time of 0) + * are read as 0. */ - if (evsel && evsel->metric_leader && - evsel->pmu != evsel->metric_leader->pmu && - mexp->metric_events[i]->pmu == evsel->metric_leader->pmu) { - struct evsel *pos; - - evlist__for_each_entry(evsel->evlist, pos) { - if (pos->pmu != evsel->pmu) - continue; - if (pos->metric_leader != mexp->metric_events[i]) - continue; - ps = pos->stats; - source_count = 1; - break; - } - } - aggr = &ps->aggr[aggr_idx]; - if (!aggr) - break; + val = NAN; + source_count = 0; + } else { + struct perf_stat_aggr *aggr = + &ps->aggr[is_tool_time ? tool_aggr_idx : aggr_idx]; - if (!metric_events[i]->supported) { - /* - * Not supported events will have a count of 0, - * which can be confusing in a - * metric. Explicitly set the value to NAN. Not - * counted events (enable time of 0) are read as - * 0. - */ + if (aggr->counts.run == 0) { val = NAN; source_count = 0; } else { val = aggr->counts.val; + if (is_tool_time) { + /* Convert time event nanoseconds to seconds. */ + val *= 1e-9; + } if (!source_count) source_count = evsel__source_count(metric_events[i]); } @@ -510,7 +150,7 @@ static void generic_metric(struct perf_stat_config *config, pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list); pctx->sctx.runtime = runtime; pctx->sctx.system_wide = config->system_wide; - i = prepare_metric(mexp, evsel, pctx, aggr_idx); + i = prepare_metric(config, mexp, evsel, pctx, aggr_idx); if (i < 0) { expr__ctx_free(pctx); return; @@ -571,7 +211,7 @@ double test_generic_metric(struct metric_expr *mexp, int aggr_idx) if (!pctx) return NAN; - if (prepare_metric(mexp, /*evsel=*/NULL, pctx, aggr_idx) < 0) + if (prepare_metric(/*config=*/NULL, mexp, /*evsel=*/NULL, pctx, aggr_idx) < 0) goto out; if (expr__parse(&ratio, pctx, mexp->metric_expr)) @@ -600,11 +240,9 @@ static void perf_stat__print_metricgroup_header(struct perf_stat_config *config, * event. Only align with other metics from * different metric events. */ - if (last_name && !strcmp(last_name, name)) { - if (!need_full_name || last_pmu != evsel->pmu) { - out->print_metricgroup_header(config, ctxp, NULL); - return; - } + if (last_name && !strcmp(last_name, name) && last_pmu == evsel->pmu) { + out->print_metricgroup_header(config, ctxp, NULL); + return; } if (need_full_name && evsel->pmu) @@ -634,14 +272,14 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config, int aggr_idx, int *num, void *from, - struct perf_stat_output_ctx *out, - struct rblist *metric_events) + struct perf_stat_output_ctx *out) { struct metric_event *me; struct metric_expr *mexp = from; void *ctxp = out->ctx; bool header_printed = false; const char *name = NULL; + struct rblist *metric_events = &evsel->evlist->metric_events; me = metricgroup__lookup(metric_events, evsel, false); if (me == NULL) @@ -664,7 +302,7 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config, if (strcmp(name, mexp->default_metricgroup_name)) return (void *)mexp; /* Only print the name of the metricgroup once */ - if (!header_printed) { + if (!header_printed && !evsel->default_show_events) { header_printed = true; perf_stat__print_metricgroup_header(config, evsel, ctxp, name, out); @@ -681,60 +319,18 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config, void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int aggr_idx, - struct perf_stat_output_ctx *out, - struct rblist *metric_events) + int aggr_idx, + struct perf_stat_output_ctx *out) { - typedef void (*stat_print_function_t)(struct perf_stat_config *config, - const struct evsel *evsel, - int aggr_idx, double misses, - struct perf_stat_output_ctx *out); - static const stat_print_function_t stat_print_function[STAT_MAX] = { - [STAT_INSTRUCTIONS] = print_instructions, - [STAT_BRANCH_MISS] = print_branch_miss, - [STAT_L1D_MISS] = print_l1d_miss, - [STAT_L1I_MISS] = print_l1i_miss, - [STAT_DTLB_MISS] = print_dtlb_miss, - [STAT_ITLB_MISS] = print_itlb_miss, - [STAT_LL_MISS] = print_ll_miss, - [STAT_CACHE_MISSES] = print_cache_miss, - [STAT_STALLED_CYCLES_FRONT] = print_stalled_cycles_front, - [STAT_STALLED_CYCLES_BACK] = print_stalled_cycles_back, - [STAT_CYCLES] = print_cycles, - [STAT_NSECS] = print_nsecs, - }; print_metric_t print_metric = out->print_metric; void *ctxp = out->ctx; - int num = 1; + int num = 0; - if (config->iostat_run) { + if (config->iostat_run) iostat_print_metric(config, evsel, out); - } else { - stat_print_function_t fn = stat_print_function[evsel__stat_type(evsel)]; - - if (fn) - fn(config, evsel, aggr_idx, avg, out); - else { - double nsecs = find_stat(evsel, aggr_idx, STAT_NSECS); - - if (nsecs) { - char unit = ' '; - char unit_buf[10] = "/sec"; - double ratio = convert_unit_double(1000000000.0 * avg / nsecs, - &unit); - - if (unit != ' ') - snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); - print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%8.3f", - unit_buf, ratio); - } else { - num = 0; - } - } - } perf_stat__print_shadow_stats_metricgroup(config, evsel, aggr_idx, - &num, NULL, out, metric_events); + &num, NULL, out); if (num == 0) { print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, @@ -746,15 +342,10 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, * perf_stat__skip_metric_event - Skip the evsel in the Default metricgroup, * if it's not running or not the metric event. */ -bool perf_stat__skip_metric_event(struct evsel *evsel, - struct rblist *metric_events, - u64 ena, u64 run) +bool perf_stat__skip_metric_event(struct evsel *evsel) { if (!evsel->default_metricgroup) return false; - if (!ena || !run) - return true; - - return !metricgroup__lookup(metric_events, evsel, false); + return !metricgroup__lookup(&evsel->evlist->metric_events, evsel, false); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 7c2ccdcc3fdb..14d169e22e8f 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -246,9 +246,11 @@ void evlist__reset_prev_raw_counts(struct evlist *evlist) static void evsel__copy_prev_raw_counts(struct evsel *evsel) { - int idx, nthreads = perf_thread_map__nr(evsel->core.threads); + int nthreads = perf_thread_map__nr(evsel->core.threads); for (int thread = 0; thread < nthreads; thread++) { + unsigned int idx; + perf_cpu_map__for_each_idx(idx, evsel__cpus(evsel)) { *perf_counts(evsel->counts, idx, thread) = *perf_counts(evsel->prev_raw_counts, idx, thread); @@ -526,7 +528,7 @@ static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias) struct perf_counts_values *aggr_counts_a = &ps_a->aggr[i].counts; struct perf_counts_values *aggr_counts_b = &ps_b->aggr[i].counts; - /* NB: don't increase aggr.nr for aliases */ + ps_a->aggr[i].nr += ps_b->aggr[i].nr; aggr_counts_a->val += aggr_counts_b->val; aggr_counts_a->ena += aggr_counts_b->ena; @@ -535,26 +537,6 @@ static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias) return 0; } -/* events should have the same name, scale, unit, cgroup but on different PMUs */ -static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b) -{ - if (strcmp(evsel__name(evsel_a), evsel__name(evsel_b))) - return false; - - if (evsel_a->scale != evsel_b->scale) - return false; - - if (evsel_a->cgrp != evsel_b->cgrp) - return false; - - if (strcmp(evsel_a->unit, evsel_b->unit)) - return false; - - if (evsel__is_clock(evsel_a) != evsel__is_clock(evsel_b)) - return false; - - return evsel_a->pmu != evsel_b->pmu; -} static void evsel__merge_aliases(struct evsel *evsel) { @@ -563,10 +545,9 @@ static void evsel__merge_aliases(struct evsel *evsel) alias = list_prepare_entry(evsel, &(evlist->core.entries), core.node); list_for_each_entry_continue(alias, &evlist->core.entries, core.node) { - /* Merge the same events on different PMUs. */ - if (evsel__is_alias(evsel, alias)) { + if (alias->first_wildcard_match == evsel) { + /* Merge the same events on different PMUs. */ evsel__merge_aggr_counters(evsel, alias); - alias->merged_stat = true; } } } @@ -579,11 +560,7 @@ static bool evsel__should_merge_hybrid(const struct evsel *evsel, static void evsel__merge_stats(struct evsel *evsel, struct perf_stat_config *config) { - /* this evsel is already merged */ - if (evsel->merged_stat) - return; - - if (evsel->auto_merge_stats || evsel__should_merge_hybrid(evsel, config)) + if (!evsel->pmu || !evsel->pmu->is_core || evsel__should_merge_hybrid(evsel, config)) evsel__merge_aliases(evsel); } @@ -605,7 +582,7 @@ static void evsel__update_percore_stats(struct evsel *evsel, struct aggr_cpu_id struct perf_counts_values counts = { 0, }; struct aggr_cpu_id id; struct perf_cpu cpu; - int idx; + unsigned int idx; /* collect per-core counts */ perf_cpu_map__for_each_cpu(cpu, idx, evsel->core.cpus) { @@ -642,7 +619,7 @@ static void evsel__process_percore(struct evsel *evsel) struct perf_stat_evsel *ps = evsel->stats; struct aggr_cpu_id core_id; struct perf_cpu cpu; - int idx; + unsigned int idx; if (!evsel->percore) return; @@ -670,7 +647,8 @@ void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *e evsel__process_percore(evsel); } -int perf_event__process_stat_event(struct perf_session *session, +int perf_event__process_stat_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { struct perf_counts_values count, *ptr; @@ -741,61 +719,3 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) return ret; } - -int create_perf_stat_counter(struct evsel *evsel, - struct perf_stat_config *config, - struct target *target, - int cpu_map_idx) -{ - struct perf_event_attr *attr = &evsel->core.attr; - struct evsel *leader = evsel__leader(evsel); - - attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | - PERF_FORMAT_TOTAL_TIME_RUNNING; - - /* - * The event is part of non trivial group, let's enable - * the group read (for leader) and ID retrieval for all - * members. - */ - if (leader->core.nr_members > 1) - attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP; - - attr->inherit = !config->no_inherit && list_empty(&evsel->bpf_counter_list); - - /* - * Some events get initialized with sample_(period/type) set, - * like tracepoints. Clear it up for counting. - */ - attr->sample_period = 0; - - if (config->identifier) - attr->sample_type = PERF_SAMPLE_IDENTIFIER; - - if (config->all_user) { - attr->exclude_kernel = 1; - attr->exclude_user = 0; - } - - if (config->all_kernel) { - attr->exclude_kernel = 0; - attr->exclude_user = 1; - } - - /* - * Disabling all counters initially, they will be enabled - * either manually by us or by kernel via enable_on_exec - * set later. - */ - if (evsel__is_group_leader(evsel)) { - attr->disabled = 1; - - if (target__enable_on_exec(target)) - attr->enable_on_exec = 1; - } - - if (target__has_cpu(target) && !target__has_per_thread(target)) - return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx); - - return evsel__open_per_thread(evsel, evsel->core.threads); -} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 2fda9acd7374..4bced233d2fc 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -7,7 +7,6 @@ #include <sys/types.h> #include <sys/resource.h> #include "cpumap.h" -#include "rblist.h" #include "counts.h" struct perf_cpu_map; @@ -57,11 +56,6 @@ enum aggr_mode { AGGR_MAX }; -struct rusage_stats { - struct stats ru_utime_usec_stat; - struct stats ru_stime_usec_stat; -}; - typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu); struct perf_stat_config { @@ -100,16 +94,13 @@ struct perf_stat_config { int times; int run_count; int print_free_counters_hint; - int print_mixed_hw_group_error; const char *csv_sep; struct stats *walltime_nsecs_stats; struct rusage ru_data; - struct rusage_stats *ru_stats; struct cpu_aggr_map *aggr_map; aggr_get_id_t aggr_get_id; struct cpu_aggr_map *cpus_aggr_map; u64 *walltime_run; - struct rblist metric_events; int ctl_fd; int ctl_fd_ack; bool ctl_fd_close; @@ -135,26 +126,9 @@ static inline void init_stats(struct stats *stats) stats->max = 0; } -static inline void init_rusage_stats(struct rusage_stats *ru_stats) { - init_stats(&ru_stats->ru_utime_usec_stat); - init_stats(&ru_stats->ru_stime_usec_stat); -} - -static inline void update_rusage_stats(struct rusage_stats *ru_stats, struct rusage* rusage) { - const u64 us_to_ns = 1000; - const u64 s_to_ns = 1000000000; - update_stats(&ru_stats->ru_utime_usec_stat, - (rusage->ru_utime.tv_usec * us_to_ns + rusage->ru_utime.tv_sec * s_to_ns)); - update_stats(&ru_stats->ru_stime_usec_stat, - (rusage->ru_stime.tv_usec * us_to_ns + rusage->ru_stime.tv_sec * s_to_ns)); -} - struct evsel; struct evlist; -extern struct stats walltime_nsecs_stats; -extern struct rusage_stats ru_stats; - enum metric_threshold_classify { METRIC_THRESHOLD_UNKNOWN, METRIC_THRESHOLD_BAD, @@ -187,19 +161,15 @@ struct perf_stat_output_ctx { void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int aggr_idx, - struct perf_stat_output_ctx *out, - struct rblist *metric_events); -bool perf_stat__skip_metric_event(struct evsel *evsel, - struct rblist *metric_events, - u64 ena, u64 run); + int aggr_idx, + struct perf_stat_output_ctx *out); +bool perf_stat__skip_metric_event(struct evsel *evsel); void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config, struct evsel *evsel, int aggr_idx, int *num, void *from, - struct perf_stat_output_ctx *out, - struct rblist *metric_events); + struct perf_stat_output_ctx *out); int evlist__alloc_stats(struct perf_stat_config *config, struct evlist *evlist, bool alloc_raw); @@ -223,17 +193,14 @@ union perf_event; struct perf_session; struct target; -int perf_event__process_stat_event(struct perf_session *session, +int perf_event__process_stat_event(const struct perf_tool *tool, + struct perf_session *session, union perf_event *event); size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp); size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); -int create_perf_stat_counter(struct evsel *evsel, - struct perf_stat_config *config, - struct target *target, - int cpu_map_idx); void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, int argc, const char **argv); diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index 8a868cbeffae..50add72575e0 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -12,20 +12,16 @@ #include <linux/zalloc.h> static -struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry) +struct rb_node *strlist__node_new(struct rblist *rblist __maybe_unused, const void *entry) { const char *s = entry; struct rb_node *rc = NULL; - struct strlist *strlist = container_of(rblist, struct strlist, rblist); struct str_node *snode = malloc(sizeof(*snode)); if (snode != NULL) { - if (strlist->dupstr) { - s = strdup(s); - if (s == NULL) - goto out_delete; - } - snode->s = s; + snode->s = strdup(s); + if (snode->s == NULL) + goto out_delete; rc = &snode->rb_node; } @@ -36,20 +32,18 @@ out_delete: return NULL; } -static void str_node__delete(struct str_node *snode, bool dupstr) +static void str_node__delete(struct str_node *snode) { - if (dupstr) - zfree((char **)&snode->s); + zfree((char **)&snode->s); free(snode); } static -void strlist__node_delete(struct rblist *rblist, struct rb_node *rb_node) +void strlist__node_delete(struct rblist *rblist __maybe_unused, struct rb_node *rb_node) { - struct strlist *slist = container_of(rblist, struct strlist, rblist); struct str_node *snode = container_of(rb_node, struct str_node, rb_node); - str_node__delete(snode, slist->dupstr); + str_node__delete(snode); } static int strlist__node_cmp(struct rb_node *rb_node, const void *entry) @@ -139,21 +133,25 @@ out: return err; } -static int strlist__parse_list(struct strlist *slist, const char *s, const char *subst_dir) +static int strlist__parse_list(struct strlist *slist, const char *list, const char *subst_dir) { - char *sep; + char *sep, *s = strdup(list), *sdup = s; int err; + if (s == NULL) + return -ENOMEM; + while ((sep = strchr(s, ',')) != NULL) { *sep = '\0'; err = strlist__parse_list_entry(slist, s, subst_dir); - *sep = ','; if (err != 0) return err; s = sep + 1; } - return *s ? strlist__parse_list_entry(slist, s, subst_dir) : 0; + err = *s ? strlist__parse_list_entry(slist, s, subst_dir) : 0; + free(sdup); + return err; } struct strlist *strlist__new(const char *list, const struct strlist_config *config) @@ -161,12 +159,10 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf struct strlist *slist = malloc(sizeof(*slist)); if (slist != NULL) { - bool dupstr = true; bool file_only = false; const char *dirname = NULL; if (config) { - dupstr = !config->dont_dupstr; dirname = config->dirname; file_only = config->file_only; } @@ -176,7 +172,6 @@ struct strlist *strlist__new(const char *list, const struct strlist_config *conf slist->rblist.node_new = strlist__node_new; slist->rblist.node_delete = strlist__node_delete; - slist->dupstr = dupstr; slist->file_only = file_only; if (list && strlist__parse_list(slist, list, dirname) != 0) diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index 7e82c71dcc42..3e9533e66ca9 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -14,7 +14,6 @@ struct str_node { struct strlist { struct rblist rblist; - bool dupstr; bool file_only; }; @@ -24,7 +23,6 @@ struct strlist { * found */ struct strlist_config { - bool dont_dupstr; bool file_only; const char *dirname; }; diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index b1d259f590e9..e360e7736c7b 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -726,7 +726,8 @@ static void scan_core_topology(int *map, struct topology *t, int nr_cpus) static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus) { - int idx, ret = 0; + unsigned int idx; + int ret = 0; struct perf_cpu_map *map; struct perf_cpu cpu; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66fd1249660a..7afa8a117139 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -7,15 +7,13 @@ #include <unistd.h> #include <inttypes.h> +#include "compress.h" #include "dso.h" +#include "libbfd.h" #include "map.h" #include "maps.h" #include "symbol.h" #include "symsrc.h" -#include "demangle-cxx.h" -#include "demangle-ocaml.h" -#include "demangle-java.h" -#include "demangle-rust.h" #include "machine.h" #include "vdso.h" #include "debug.h" @@ -27,18 +25,6 @@ #include <symbol/kallsyms.h> #include <internal/lib.h> -#ifdef HAVE_LIBBFD_SUPPORT -#define PACKAGE 'perf' -#include <bfd.h> -#endif - -#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT) -#ifndef DMGL_PARAMS -#define DMGL_PARAMS (1 << 0) /* Include function args */ -#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ -#endif -#endif - #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ #endif @@ -278,62 +264,6 @@ static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr) return -1; } -static bool want_demangle(bool is_kernel_sym) -{ - return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; -} - -/* - * Demangle C++ function signature, typically replaced by demangle-cxx.cpp - * version. - */ -#ifndef HAVE_CXA_DEMANGLE_SUPPORT -char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, - bool modifiers __maybe_unused) -{ -#ifdef HAVE_LIBBFD_SUPPORT - int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); - - return bfd_demangle(NULL, str, flags); -#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) - int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); - - return cplus_demangle(str, flags); -#else - return NULL; -#endif -} -#endif /* !HAVE_CXA_DEMANGLE_SUPPORT */ - -static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) -{ - 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(dso) || kmodule)) - return demangled; - - demangled = cxx_demangle_sym(elf_name, verbose > 0, verbose > 0); - if (demangled == NULL) { - demangled = ocaml_demangle_sym(elf_name); - 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; -} - struct rel_info { u32 nr_entries; u32 *sorted; @@ -442,10 +372,8 @@ static bool get_plt_sizes(struct dso *dso, GElf_Ehdr *ehdr, GElf_Shdr *shdr_plt, *plt_entry_size = 12; return true; case EM_AARCH64: - *plt_header_size = 32; - *plt_entry_size = 16; - return true; case EM_LOONGARCH: + case EM_RISCV: *plt_header_size = 32; *plt_entry_size = 16; return true; @@ -619,7 +547,7 @@ static bool get_plt_got_name(GElf_Shdr *shdr, size_t i, /* Get the associated symbol */ gelf_getsym(di->dynsym_data, vr->sym_idx, &sym); sym_name = elf_sym__name(&sym, di->dynstr_data); - demangled = demangle_sym(di->dso, 0, sym_name); + demangled = dso__demangle_sym(di->dso, /*kmodule=*/0, sym_name); if (demangled != NULL) sym_name = demangled; @@ -817,7 +745,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss) gelf_getsym(syms, get_rel_symidx(&ri, idx), &sym); elf_name = elf_sym__name(&sym, symstrs); - demangled = demangle_sym(dso, 0, elf_name); + demangled = dso__demangle_sym(dso, /*kmodule=*/0, elf_name); if (demangled) elf_name = demangled; if (*elf_name) @@ -846,11 +774,6 @@ out_elf_end: return 0; } -char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name) -{ - return demangle_sym(dso, kmodule, elf_name); -} - /* * Align offset to 4 bytes as needed for note name and descriptor data. */ @@ -935,43 +858,16 @@ out: return err; } -#ifdef HAVE_LIBBFD_BUILDID_SUPPORT - -static int read_build_id(const char *filename, struct build_id *bid) -{ - size_t size = sizeof(bid->data); - int err = -1; - bfd *abfd; - - abfd = bfd_openr(filename, NULL); - if (!abfd) - return -1; - - if (!bfd_check_format(abfd, bfd_object)) { - pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); - goto out_close; - } - - if (!abfd->build_id || abfd->build_id->size > size) - goto out_close; - - memcpy(bid->data, abfd->build_id->data, abfd->build_id->size); - memset(bid->data + abfd->build_id->size, 0, size - abfd->build_id->size); - err = bid->size = abfd->build_id->size; - -out_close: - bfd_close(abfd); - return err; -} - -#else // HAVE_LIBBFD_BUILDID_SUPPORT - static int read_build_id(const char *filename, struct build_id *bid) { size_t size = sizeof(bid->data); - int fd, err = -1; + int fd, err; Elf *elf; + err = libbfd__read_build_id(filename, bid); + if (err >= 0) + goto out; + if (size < BUILD_ID_SIZE) goto out; @@ -996,8 +892,6 @@ out: return err; } -#endif // HAVE_LIBBFD_BUILDID_SUPPORT - int filename__read_build_id(const char *filename, struct build_id *bid) { struct kmod_path m = { .name = NULL, }; @@ -1007,6 +901,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid) if (!filename) return -EFAULT; + errno = 0; + if (!is_regular_file(filename)) + return errno == 0 ? -EWOULDBLOCK : -errno; + err = kmod_path__parse(&m, filename); if (err) return -1; @@ -1081,44 +979,6 @@ out: return err; } -#ifdef HAVE_LIBBFD_SUPPORT - -int filename__read_debuglink(const char *filename, char *debuglink, - size_t size) -{ - int err = -1; - asection *section; - bfd *abfd; - - abfd = bfd_openr(filename, NULL); - if (!abfd) - return -1; - - if (!bfd_check_format(abfd, bfd_object)) { - pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename); - goto out_close; - } - - section = bfd_get_section_by_name(abfd, ".gnu_debuglink"); - if (!section) - goto out_close; - - if (section->size > size) - goto out_close; - - if (!bfd_get_section_contents(abfd, section, debuglink, 0, - section->size)) - goto out_close; - - err = 0; - -out_close: - bfd_close(abfd); - return err; -} - -#else - int filename__read_debuglink(const char *filename, char *debuglink, size_t size) { @@ -1130,6 +990,10 @@ int filename__read_debuglink(const char *filename, char *debuglink, Elf_Scn *sec; Elf_Kind ek; + err = libbfd_filename__read_debuglink(filename, debuglink, size); + if (err >= 0) + goto out; + fd = open(filename, O_RDONLY); if (fd < 0) goto out; @@ -1171,35 +1035,6 @@ out: return err; } -#endif - -static int dso__swap_init(struct dso *dso, unsigned char eidata) -{ - static unsigned int const endian = 1; - - dso__set_needs_swap(dso, DSO_SWAP__NO); - - switch (eidata) { - case ELFDATA2LSB: - /* We are big endian, DSO is little endian. */ - if (*(unsigned char const *)&endian != 1) - dso__set_needs_swap(dso, DSO_SWAP__YES); - break; - - case ELFDATA2MSB: - /* We are little endian, DSO is big endian. */ - if (*(unsigned char const *)&endian != 0) - dso__set_needs_swap(dso, DSO_SWAP__YES); - break; - - default: - pr_err("unrecognized DSO data encoding %d\n", eidata); - return -EINVAL; - } - - return 0; -} - bool symsrc__possibly_runtime(struct symsrc *ss) { return ss->dynsym || ss->opdsec; @@ -1217,15 +1052,90 @@ void symsrc__destroy(struct symsrc *ss) close(ss->fd); } -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) +static bool elf__needs_adjust_symbols(const GElf_Ehdr *ehdr) { /* * Usually vmlinux is an ELF file with type ET_EXEC for most * architectures; except Arm64 kernel is linked with option * '-share', so need to check type ET_DYN. */ - return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL || - ehdr.e_type == ET_DYN; + return ehdr->e_type == ET_EXEC || ehdr->e_type == ET_REL || + ehdr->e_type == ET_DYN; +} + +static Elf *read_gnu_debugdata(struct dso *dso, Elf *elf, const char *name, int *fd_ret) +{ + Elf *elf_embedded; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Scn *scn; + Elf_Data *scn_data; + FILE *wrapped; + size_t shndx; + char temp_filename[] = "/tmp/perf.gnu_debugdata.elf.XXXXXX"; + int ret, temp_fd; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_debug("%s: cannot read %s ELF file.\n", __func__, name); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + return NULL; + } + + scn = elf_section_by_name(elf, &ehdr, &shdr, ".gnu_debugdata", &shndx); + if (!scn) { + *dso__load_errno(dso) = -ENOENT; + return NULL; + } + + if (shdr.sh_type == SHT_NOBITS) { + pr_debug("%s: .gnu_debugdata of ELF file %s has no data.\n", __func__, name); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + return NULL; + } + + scn_data = elf_rawdata(scn, NULL); + if (!scn_data) { + pr_debug("%s: error reading .gnu_debugdata of %s: %s\n", __func__, + name, elf_errmsg(-1)); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + return NULL; + } + + wrapped = fmemopen(scn_data->d_buf, scn_data->d_size, "r"); + if (!wrapped) { + pr_debug("%s: fmemopen: %m\n", __func__); + *dso__load_errno(dso) = -errno; + return NULL; + } + + temp_fd = mkstemp(temp_filename); + if (temp_fd < 0) { + pr_debug("%s: mkstemp: %m\n", __func__); + *dso__load_errno(dso) = -errno; + fclose(wrapped); + return NULL; + } + unlink(temp_filename); + + ret = lzma_decompress_stream_to_file(wrapped, temp_fd); + fclose(wrapped); + if (ret < 0) { + *dso__load_errno(dso) = -errno; + close(temp_fd); + return NULL; + } + + elf_embedded = elf_begin(temp_fd, PERF_ELF_C_READ_MMAP, NULL); + if (!elf_embedded) { + pr_debug("%s: error reading .gnu_debugdata of %s: %s\n", __func__, + name, elf_errmsg(-1)); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + close(temp_fd); + return NULL; + } + pr_debug("%s: using .gnu_debugdata of %s\n", __func__, name); + *fd_ret = temp_fd; + return elf_embedded; } int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, @@ -1256,6 +1166,19 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, goto out_close; } + if (type == DSO_BINARY_TYPE__GNU_DEBUGDATA) { + int new_fd; + Elf *embedded = read_gnu_debugdata(dso, elf, name, &new_fd); + + if (!embedded) + goto out_elf_end; + + elf_end(elf); + close(fd); + fd = new_fd; + elf = embedded; + } + if (gelf_getehdr(elf, &ehdr) == NULL) { *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; pr_debug("%s: cannot get elf header.\n", __func__); @@ -1310,7 +1233,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, if (dso__kernel(dso) == DSO_SPACE__USER) ss->adjust_symbols = true; else - ss->adjust_symbols = elf__needs_adjust_symbols(ehdr); + ss->adjust_symbols = elf__needs_adjust_symbols(&ehdr); ss->name = strdup(name); if (!ss->name) { @@ -1431,8 +1354,12 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, char dso_name[PATH_MAX]; /* Adjust symbol to map to file offset */ - if (adjust_kernel_syms) - sym->st_value -= shdr->sh_addr - shdr->sh_offset; + if (adjust_kernel_syms) { + if (dso__rel(dso)) + sym->st_value += shdr->sh_offset; + else + sym->st_value -= shdr->sh_addr - shdr->sh_offset; + } if (strcmp(section_name, (dso__short_name(curr_dso) + dso__short_name_len(dso))) == 0) return 0; @@ -1524,8 +1451,11 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY); } dso__set_symtab_type(curr_dso, dso__symtab_type(dso)); - if (maps__insert(kmaps, curr_map)) + if (maps__insert(kmaps, curr_map)) { + dso__put(curr_dso); + map__put(curr_map); return -1; + } dsos__add(&maps__machine(kmaps)->dsos, curr_dso); dso__set_loaded(curr_dso); dso__put(*curr_dsop); @@ -1671,6 +1601,12 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, continue; } + /* Reject RISCV ELF "mapping symbols" */ + if (ehdr.e_machine == EM_RISCV) { + if (elf_name[0] == '$' && strchr("dx", elf_name[1])) + continue; + } + if (runtime_ss->opdsec && sym.st_shndx == runtime_ss->opdidx) { u32 offset = sym.st_value - syms_ss->opdshdr.sh_addr; u64 *opd = opddata->d_buf + offset; @@ -1778,7 +1714,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, } } - demangled = demangle_sym(dso, kmodule, elf_name); + demangled = dso__demangle_sym(dso, kmodule, elf_name); if (demangled != NULL) elf_name = demangled; @@ -1854,10 +1790,23 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, kmodule, 1); if (err < 0) return err; - err += nr; + nr += err; } - return err; + /* + * The .gnu_debugdata is a special situation: it contains a symbol + * table, but the runtime file may also contain dynsym entries which are + * not present there. We need to load both. + */ + if (syms_ss->type == DSO_BINARY_TYPE__GNU_DEBUGDATA && runtime_ss->dynsym) { + err = dso__load_sym_internal(dso, map, runtime_ss, runtime_ss, + kmodule, 1); + if (err < 0) + return err; + nr += err; + } + + return nr; } static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data) diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index c6f369b5d893..8221dc9868f7 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -4,7 +4,6 @@ #include <errno.h> #include <unistd.h> -#include <stdio.h> #include <fcntl.h> #include <string.h> #include <stdlib.h> @@ -43,7 +42,7 @@ static int read_build_id(void *note_data, size_t note_len, struct build_id *bid, void *ptr; ptr = note_data; - while (ptr < (note_data + note_len)) { + while ((ptr + sizeof(*nhdr)) < (note_data + note_len)) { const char *name; size_t namesz, descsz; @@ -88,139 +87,120 @@ int filename__read_debuglink(const char *filename __maybe_unused, */ int filename__read_build_id(const char *filename, struct build_id *bid) { - FILE *fp; - int ret = -1; - bool need_swap = false; - u8 e_ident[EI_NIDENT]; - size_t buf_size; - void *buf; - int i; + int fd, ret = -1; + bool need_swap = false, elf32; + union { + struct { + Elf32_Ehdr ehdr32; + Elf32_Phdr *phdr32; + }; + struct { + Elf64_Ehdr ehdr64; + Elf64_Phdr *phdr64; + }; + } hdrs; + void *phdr, *buf = NULL; + ssize_t phdr_size, ehdr_size, buf_size = 0; + + if (!filename) + return -EFAULT; + + errno = 0; + if (!is_regular_file(filename)) + return errno == 0 ? -EWOULDBLOCK : -errno; - fp = fopen(filename, "r"); - if (fp == NULL) + fd = open(filename, O_RDONLY); + if (fd < 0) return -1; - if (fread(e_ident, sizeof(e_ident), 1, fp) != 1) + if (read(fd, hdrs.ehdr32.e_ident, EI_NIDENT) != EI_NIDENT) goto out; - if (memcmp(e_ident, ELFMAG, SELFMAG) || - e_ident[EI_VERSION] != EV_CURRENT) + if (memcmp(hdrs.ehdr32.e_ident, ELFMAG, SELFMAG) || + hdrs.ehdr32.e_ident[EI_VERSION] != EV_CURRENT) goto out; - need_swap = check_need_swap(e_ident[EI_DATA]); - - /* for simplicity */ - fseek(fp, 0, SEEK_SET); + need_swap = check_need_swap(hdrs.ehdr32.e_ident[EI_DATA]); + elf32 = hdrs.ehdr32.e_ident[EI_CLASS] == ELFCLASS32; + ehdr_size = (elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64)) - EI_NIDENT; - if (e_ident[EI_CLASS] == ELFCLASS32) { - Elf32_Ehdr ehdr; - Elf32_Phdr *phdr; - - if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) - goto out; + if (read(fd, + (elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64) + EI_NIDENT, + ehdr_size) != ehdr_size) + goto out; - if (need_swap) { - ehdr.e_phoff = bswap_32(ehdr.e_phoff); - ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); - ehdr.e_phnum = bswap_16(ehdr.e_phnum); + if (need_swap) { + if (elf32) { + hdrs.ehdr32.e_phoff = bswap_32(hdrs.ehdr32.e_phoff); + hdrs.ehdr32.e_phentsize = bswap_16(hdrs.ehdr32.e_phentsize); + hdrs.ehdr32.e_phnum = bswap_16(hdrs.ehdr32.e_phnum); + } else { + hdrs.ehdr64.e_phoff = bswap_64(hdrs.ehdr64.e_phoff); + hdrs.ehdr64.e_phentsize = bswap_16(hdrs.ehdr64.e_phentsize); + hdrs.ehdr64.e_phnum = bswap_16(hdrs.ehdr64.e_phnum); } + } + if ((elf32 && hdrs.ehdr32.e_phentsize != sizeof(Elf32_Phdr)) || + (!elf32 && hdrs.ehdr64.e_phentsize != sizeof(Elf64_Phdr))) + goto out; - buf_size = ehdr.e_phentsize * ehdr.e_phnum; - buf = malloc(buf_size); - if (buf == NULL) - goto out; - - fseek(fp, ehdr.e_phoff, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; - - for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { - void *tmp; - long offset; - - if (need_swap) { - phdr->p_type = bswap_32(phdr->p_type); - phdr->p_offset = bswap_32(phdr->p_offset); - phdr->p_filesz = bswap_32(phdr->p_filesz); - } - - if (phdr->p_type != PT_NOTE) - continue; - - buf_size = phdr->p_filesz; - offset = phdr->p_offset; - tmp = realloc(buf, buf_size); - if (tmp == NULL) - goto out_free; + phdr_size = elf32 ? sizeof(Elf32_Phdr) * hdrs.ehdr32.e_phnum + : sizeof(Elf64_Phdr) * hdrs.ehdr64.e_phnum; + phdr = malloc(phdr_size); + if (phdr == NULL) + goto out; - buf = tmp; - fseek(fp, offset, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; + lseek(fd, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET); + if (read(fd, phdr, phdr_size) != phdr_size) + goto out_free; - ret = read_build_id(buf, buf_size, bid, need_swap); - if (ret == 0) { - ret = bid->size; - break; - } - } - } else { - Elf64_Ehdr ehdr; - Elf64_Phdr *phdr; + if (elf32) + hdrs.phdr32 = phdr; + else + hdrs.phdr64 = phdr; - if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) - goto out; + for (int i = 0; i < (elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum); i++) { + ssize_t p_filesz; if (need_swap) { - ehdr.e_phoff = bswap_64(ehdr.e_phoff); - ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); - ehdr.e_phnum = bswap_16(ehdr.e_phnum); + if (elf32) { + hdrs.phdr32[i].p_type = bswap_32(hdrs.phdr32[i].p_type); + hdrs.phdr32[i].p_offset = bswap_32(hdrs.phdr32[i].p_offset); + hdrs.phdr32[i].p_filesz = bswap_32(hdrs.phdr32[i].p_offset); + } else { + hdrs.phdr64[i].p_type = bswap_32(hdrs.phdr64[i].p_type); + hdrs.phdr64[i].p_offset = bswap_64(hdrs.phdr64[i].p_offset); + hdrs.phdr64[i].p_filesz = bswap_64(hdrs.phdr64[i].p_filesz); + } } + if ((elf32 ? hdrs.phdr32[i].p_type : hdrs.phdr64[i].p_type) != PT_NOTE) + continue; - buf_size = ehdr.e_phentsize * ehdr.e_phnum; - buf = malloc(buf_size); - if (buf == NULL) - goto out; - - fseek(fp, ehdr.e_phoff, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; - - for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { + p_filesz = elf32 ? hdrs.phdr32[i].p_filesz : hdrs.phdr64[i].p_filesz; + if (p_filesz > buf_size) { void *tmp; - long offset; - if (need_swap) { - phdr->p_type = bswap_32(phdr->p_type); - phdr->p_offset = bswap_64(phdr->p_offset); - phdr->p_filesz = bswap_64(phdr->p_filesz); - } - - if (phdr->p_type != PT_NOTE) - continue; - - buf_size = phdr->p_filesz; - offset = phdr->p_offset; + buf_size = p_filesz; tmp = realloc(buf, buf_size); if (tmp == NULL) goto out_free; - buf = tmp; - fseek(fp, offset, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; + } + lseek(fd, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET); + if (read(fd, buf, p_filesz) != p_filesz) + goto out_free; - ret = read_build_id(buf, buf_size, bid, need_swap); - if (ret == 0) { - ret = bid->size; - break; - } + ret = read_build_id(buf, p_filesz, bid, need_swap); + if (ret == 0) { + ret = bid->size; + break; } } out_free: free(buf); + free(phdr); out: - fclose(fp); + close(fd); return ret; } @@ -343,7 +323,7 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, struct symsrc *runtime_ss __maybe_unused, int kmodule __maybe_unused) { - struct build_id bid; + struct build_id bid = { .size = 0, }; int ret; ret = fd__is_64_bit(ss->fd); @@ -381,13 +361,6 @@ void symbol__elf_init(void) { } -char *dso__demangle_sym(struct dso *dso __maybe_unused, - int kmodule __maybe_unused, - const char *elf_name __maybe_unused) -{ - return NULL; -} - bool filename__has_section(const char *filename __maybe_unused, const char *sec __maybe_unused) { return false; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 49b08adc6ee3..fcaeeddbbb6b 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -18,9 +18,14 @@ #include "annotate.h" #include "build-id.h" #include "cap.h" +#include "cpumap.h" +#include "debug.h" +#include "demangle-cxx.h" +#include "demangle-java.h" +#include "demangle-ocaml.h" +#include "demangle-rust-v0.h" #include "dso.h" #include "util.h" // lsdir() -#include "debug.h" #include "event.h" #include "machine.h" #include "map.h" @@ -35,6 +40,7 @@ #include "header.h" #include "path.h" #include <linux/ctype.h> +#include <linux/log2.h> #include <linux/zalloc.h> #include <elf.h> @@ -59,9 +65,11 @@ struct symbol_conf symbol_conf = { .time_quantum = 100 * NSEC_PER_MSEC, /* 100ms */ .show_hist_headers = true, .symfs = "", + .symfs_layout_flat = false, .event_group = true, .inline_name = true, .res_sample = 0, + .addr2line_timeout_ms = 5 * 1000, }; struct map_list_node { @@ -84,6 +92,7 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__FEDORA_DEBUGINFO, DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__GNU_DEBUGDATA, DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, DSO_BINARY_TYPE__GUEST_KMODULE_COMP, @@ -621,7 +630,7 @@ void dso__sort_by_name(struct dso *dso) { mutex_lock(dso__lock(dso)); if (!dso__sorted_by_name(dso)) { - size_t len; + size_t len = 0; dso__set_symbol_names(dso, symbols__sort_by_name(dso__symbols(dso), &len)); if (dso__symbol_names(dso)) { @@ -936,7 +945,8 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, pos->end -= delta; } - if (count == 0) { + if (map__start(initial_map) <= (pos->start + delta) && + (pos->start + delta) < map__end(initial_map)) { map__zput(curr_map); curr_map = map__get(initial_map); goto add_symbol; @@ -945,11 +955,11 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, if (dso__kernel(dso) == DSO_SPACE__KERNEL_GUEST) snprintf(dso_name, sizeof(dso_name), "[guest.kernel].%d", - kernel_range++); + kernel_range); else snprintf(dso_name, sizeof(dso_name), "[kernel].%d", - kernel_range++); + kernel_range); ndso = dso__new(dso_name); map__zput(curr_map); @@ -957,6 +967,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, return -1; dso__set_kernel(ndso, dso__kernel(dso)); + dso__set_loaded(ndso); curr_map = map__new2(pos->start, ndso); if (curr_map == NULL) { @@ -970,6 +981,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, dso__put(ndso); return -1; } + dso__put(ndso); ++kernel_range; } else if (delta) { /* Kernel was relocated at boot time */ @@ -1412,6 +1424,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, goto out_err; } } + map__zput(new_node->map); free(new_node); } @@ -1573,137 +1586,6 @@ out_failure: return -1; } -#ifdef HAVE_LIBBFD_SUPPORT -#define PACKAGE 'perf' -#include <bfd.h> - -static int bfd_symbols__cmpvalue(const void *a, const void *b) -{ - const asymbol *as = *(const asymbol **)a, *bs = *(const asymbol **)b; - - if (bfd_asymbol_value(as) != bfd_asymbol_value(bs)) - return bfd_asymbol_value(as) - bfd_asymbol_value(bs); - - return bfd_asymbol_name(as)[0] - bfd_asymbol_name(bs)[0]; -} - -static int bfd2elf_binding(asymbol *symbol) -{ - if (symbol->flags & BSF_WEAK) - return STB_WEAK; - if (symbol->flags & BSF_GLOBAL) - return STB_GLOBAL; - if (symbol->flags & BSF_LOCAL) - return STB_LOCAL; - return -1; -} - -int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) -{ - int err = -1; - long symbols_size, symbols_count, i; - asection *section; - asymbol **symbols, *sym; - struct symbol *symbol; - bfd *abfd; - u64 start, len; - - abfd = bfd_openr(debugfile, NULL); - if (!abfd) - return -1; - - if (!bfd_check_format(abfd, bfd_object)) { - pr_debug2("%s: cannot read %s bfd file.\n", __func__, - dso__long_name(dso)); - goto out_close; - } - - if (bfd_get_flavour(abfd) == bfd_target_elf_flavour) - goto out_close; - - symbols_size = bfd_get_symtab_upper_bound(abfd); - if (symbols_size == 0) { - bfd_close(abfd); - return 0; - } - - if (symbols_size < 0) - goto out_close; - - symbols = malloc(symbols_size); - if (!symbols) - goto out_close; - - symbols_count = bfd_canonicalize_symtab(abfd, symbols); - if (symbols_count < 0) - goto out_free; - - section = bfd_get_section_by_name(abfd, ".text"); - if (section) { - for (i = 0; i < symbols_count; ++i) { - if (!strcmp(bfd_asymbol_name(symbols[i]), "__ImageBase") || - !strcmp(bfd_asymbol_name(symbols[i]), "__image_base__")) - break; - } - if (i < symbols_count) { - /* PE symbols can only have 4 bytes, so use .text high bits */ - u64 text_offset = (section->vma - (u32)section->vma) - + (u32)bfd_asymbol_value(symbols[i]); - dso__set_text_offset(dso, text_offset); - dso__set_text_end(dso, (section->vma - text_offset) + section->size); - } else { - dso__set_text_offset(dso, section->vma - section->filepos); - dso__set_text_end(dso, section->filepos + section->size); - } - } - - qsort(symbols, symbols_count, sizeof(asymbol *), bfd_symbols__cmpvalue); - -#ifdef bfd_get_section -#define bfd_asymbol_section bfd_get_section -#endif - for (i = 0; i < symbols_count; ++i) { - sym = symbols[i]; - section = bfd_asymbol_section(sym); - if (bfd2elf_binding(sym) < 0) - continue; - - while (i + 1 < symbols_count && - bfd_asymbol_section(symbols[i + 1]) == section && - bfd2elf_binding(symbols[i + 1]) < 0) - i++; - - if (i + 1 < symbols_count && - bfd_asymbol_section(symbols[i + 1]) == section) - len = symbols[i + 1]->value - sym->value; - else - len = section->size - sym->value; - - start = bfd_asymbol_value(sym) - dso__text_offset(dso); - symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC, - bfd_asymbol_name(sym)); - if (!symbol) - goto out_free; - - symbols__insert(dso__symbols(dso), symbol); - } -#ifdef bfd_get_section -#undef bfd_asymbol_section -#endif - - symbols__fixup_end(dso__symbols(dso), false); - symbols__fixup_duplicate(dso__symbols(dso)); - dso__set_adjust_symbols(dso, true); - - err = 0; -out_free: - free(symbols); -out_close: - bfd_close(abfd); - return err; -} -#endif - static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, enum dso_binary_type type) { @@ -1716,6 +1598,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: return !kmod && dso__kernel(dso) == DSO_SPACE__USER; case DSO_BINARY_TYPE__KALLSYMS: @@ -1801,7 +1684,6 @@ int dso__load(struct dso *dso, struct map *map) struct symsrc *syms_ss = NULL, *runtime_ss = NULL; bool kmod; bool perfmap; - struct build_id bid; struct nscookie nsc; char newmapname[PATH_MAX]; const char *map_path = dso__long_name(dso); @@ -1858,10 +1740,11 @@ int dso__load(struct dso *dso, struct map *map) /* * Read the build id if possible. This is required for - * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work + * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work. */ - if (!dso__has_build_id(dso) && - is_regular_file(dso__long_name(dso))) { + if (!dso__has_build_id(dso)) { + struct build_id bid = { .size = 0, }; + __symbol__join_symfs(name, PATH_MAX, dso__long_name(dso)); if (filename__read_build_id(name, &bid) > 0) dso__set_build_id(dso, &bid); @@ -2110,10 +1993,11 @@ static bool filename__readable(const char *file) static char *dso__find_kallsyms(struct dso *dso, struct map *map) { - struct build_id bid; + struct build_id bid = { .size = 0, }; char sbuild_id[SBUILD_ID_SIZE]; bool is_host = false; char path[PATH_MAX]; + struct maps *kmaps = map__kmaps(map); if (!dso__has_build_id(dso)) { /* @@ -2140,7 +2024,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) goto proc_kallsyms; } - build_id__sprintf(dso__bid(dso), sbuild_id); + build_id__snprintf(dso__bid(dso), sbuild_id, sizeof(sbuild_id)); /* Find kallsyms in build-id cache with kcore */ scnprintf(path, sizeof(path), "%s/%s/%s", @@ -2150,8 +2034,13 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) return strdup(path); /* Use current /proc/kallsyms if possible */ - if (is_host) { proc_kallsyms: + if (kmaps) { + struct machine *machine = maps__machine(kmaps); + + scnprintf(path, sizeof(path), "%s/proc/kallsyms", machine->root_dir); + return strdup(path); + } else if (is_host) { return strdup("/proc/kallsyms"); } @@ -2471,6 +2360,37 @@ int symbol__annotation_init(void) return 0; } +static int setup_parallelism_bitmap(void) +{ + struct perf_cpu_map *map; + struct perf_cpu cpu; + unsigned int i; + int err = -1; + + if (symbol_conf.parallelism_list_str == NULL) + return 0; + + map = perf_cpu_map__new(symbol_conf.parallelism_list_str); + if (map == NULL) { + pr_err("failed to parse parallelism filter list\n"); + return -1; + } + + bitmap_fill(symbol_conf.parallelism_filter, MAX_NR_CPUS + 1); + perf_cpu_map__for_each_cpu(cpu, i, map) { + if (cpu.cpu <= 0 || cpu.cpu > MAX_NR_CPUS) { + pr_err("Requested parallelism level %d is invalid.\n", cpu.cpu); + goto out_delete_map; + } + __clear_bit(cpu.cpu, symbol_conf.parallelism_filter); + } + + err = 0; +out_delete_map: + perf_cpu_map__put(map); + return err; +} + int symbol__init(struct perf_env *env) { const char *symfs; @@ -2490,6 +2410,9 @@ int symbol__init(struct perf_env *env) return -1; } + if (setup_parallelism_bitmap()) + return -1; + if (setup_list(&symbol_conf.dso_list, symbol_conf.dso_list_str, "dso") < 0) return -1; @@ -2570,16 +2493,42 @@ int symbol__config_symfs(const struct option *opt __maybe_unused, const char *dir, int unset __maybe_unused) { char *bf = NULL; + const char *layout_str; + char *dir_copy; int ret; - symbol_conf.symfs = strdup(dir); - if (symbol_conf.symfs == NULL) - return -ENOMEM; + layout_str = strrchr(dir, ','); + if (layout_str) { + size_t dir_len = layout_str - dir; + + dir_copy = strndup(dir, dir_len); + if (dir_copy == NULL) + return -ENOMEM; + + symbol_conf.symfs = dir_copy; + + layout_str++; + if (!strcmp(layout_str, "flat")) + symbol_conf.symfs_layout_flat = true; + else if (!strcmp(layout_str, "hierarchy")) + symbol_conf.symfs_layout_flat = false; + else { + pr_err("Invalid layout: '%s', use 'hierarchy' or 'flat'\n", + layout_str); + free(dir_copy); + return -EINVAL; + } + } else { + symbol_conf.symfs = strdup(dir); + if (symbol_conf.symfs == NULL) + return -ENOMEM; + symbol_conf.symfs_layout_flat = false; + } /* skip the locally configured cache if a symfs is given, and * config buildid dir to symfs/.debug */ - ret = asprintf(&bf, "%s/%s", dir, ".debug"); + ret = asprintf(&bf, "%s/%s", symbol_conf.symfs, ".debug"); if (ret < 0) return -ENOMEM; @@ -2610,3 +2559,79 @@ int symbol__validate_sym_arguments(void) } return 0; } + +static bool want_demangle(bool is_kernel_sym) +{ + return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; +} + +/* + * Demangle C++ function signature, typically replaced by demangle-cxx.cpp + * version. + */ +#ifndef HAVE_CXA_DEMANGLE_SUPPORT +char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) +{ +#ifdef HAVE_LIBBFD_SUPPORT + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return bfd_demangle(NULL, str, flags); +#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return cplus_demangle(str, flags); +#else + return NULL; +#endif +} +#endif /* !HAVE_CXA_DEMANGLE_SUPPORT */ + +char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name) +{ + struct demangle rust_demangle = { + .style = DemangleStyleUnknown, + }; + 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 && dso__kernel(dso)) || kmodule)) + return demangled; + + rust_demangle_demangle(elf_name, &rust_demangle); + if (rust_demangle_is_known(&rust_demangle)) { + /* A rust mangled name. */ + if (rust_demangle.mangled_len == 0) + return demangled; + + for (size_t buf_len = roundup_pow_of_two(rust_demangle.mangled_len * 2); + buf_len < 1024 * 1024; buf_len += 32) { + char *tmp = realloc(demangled, buf_len); + + if (!tmp) { + /* Failure to grow output buffer, return what is there. */ + return demangled; + } + demangled = tmp; + if (rust_demangle_display_demangle(&rust_demangle, demangled, buf_len, + /*alternate=*/true) == OverflowOk) + return demangled; + } + /* Buffer exceeded sensible bounds, return what is there. */ + return demangled; + } + + demangled = cxx_demangle_sym(elf_name, verbose > 0, verbose > 0); + if (demangled) + return demangled; + + demangled = ocaml_demangle_sym(elf_name); + if (demangled) + return demangled; + + return java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET); +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 3fb5d146d9b1..bd6eb90c8668 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -9,10 +9,12 @@ #include <linux/list.h> #include <linux/rbtree.h> #include <stdio.h> +#include <errno.h> #include "addr_location.h" #include "path.h" #include "symbol_conf.h" #include "spark.h" +#include "util.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -96,6 +98,9 @@ struct intlist; static inline int __symbol__join_symfs(char *bf, size_t size, const char *path) { + if (symbol_conf.symfs_layout_flat) + return path__join(bf, size, symbol_conf.symfs, perf_basename(path)); + return path__join(bf, size, symbol_conf.symfs, path); } @@ -169,6 +174,11 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); size_t symbol__fprintf(struct symbol *sym, FILE *fp); bool symbol__restricted_filename(const char *filename, const char *restricted_filename); + +#define SYMFS_HELP "setup root directory which contains debug files:\n" \ + "\t\t\t\t" "directory:\tLook for files with symbols relative to this directory.\n" \ + "\t\t\t\t" "layout: \tLayout of files, 'hierarchy' matches full path (default), 'flat' only matches base name.\n" + int symbol__config_symfs(const struct option *opt __maybe_unused, const char *dir, int unset __maybe_unused); @@ -217,7 +227,6 @@ int setup_intlist(struct intlist **list, const char *list_str, const char *list_name); #ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); #endif diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index a9c51acc722f..6cd454d7c98e 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -3,10 +3,21 @@ #define __PERF_SYMBOL_CONF 1 #include <stdbool.h> +#include <linux/bitmap.h> +#include "perf.h" struct strlist; struct intlist; +enum a2l_style { + A2L_STYLE_UNKNOWN = 0, + A2L_STYLE_LIBDW, + A2L_STYLE_LLVM, + A2L_STYLE_LIBBFD, + A2L_STYLE_CMD, +}; +#define MAX_A2L_STYLE (A2L_STYLE_CMD + 1) + struct symbol_conf { bool nanosecs; unsigned short priv_size; @@ -40,14 +51,16 @@ struct symbol_conf { report_block, report_individual_block, inline_name, - disable_add2line_warn, - buildid_mmap2, + addr2line_disable_warn, + no_buildid_mmap2, guest_code, lazy_load_kernel_maps, keep_exited_threads, annotate_data_member, annotate_data_sample, - skip_empty; + skip_empty, + enable_latency, + prefer_latency; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -62,9 +75,12 @@ struct symbol_conf { *pid_list_str, *tid_list_str, *sym_list_str, + *parallelism_list_str, *col_width_list_str, *bt_stop_list_str; const char *addr2line_path; + enum a2l_style addr2line_style[MAX_A2L_STYLE]; + int addr2line_timeout_ms; unsigned long time_quantum; struct strlist *dso_list, *comm_list, @@ -78,10 +94,12 @@ struct symbol_conf { *tid_list, *addr_list; const char *symfs; + bool symfs_layout_flat; int res_sample; int pad_output_len_dso; int group_sort_idx; int addr_range; + DECLARE_BITMAP(parallelism_filter, MAX_NR_CPUS + 1); }; extern struct symbol_conf symbol_conf; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 6923b0d5efed..85bee747f4cd 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -38,6 +38,7 @@ #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <api/fs/fs.h> #include <api/io.h> +#include <api/io_dir.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> @@ -367,11 +368,11 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event, struct machine *machine, bool is_kernel) { - struct build_id bid; + struct build_id bid = { .size = 0, }; struct nsinfo *nsi; struct nscookie nc; struct dso *dso = NULL; - struct dso_id id; + struct dso_id dso_id = dso_id_empty; int rc; if (is_kernel) { @@ -379,12 +380,18 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event, goto out; } - id.maj = event->maj; - id.min = event->min; - id.ino = event->ino; - id.ino_generation = event->ino_generation; + if (event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID) { + build_id__init(&dso_id.build_id, event->build_id, event->build_id_size); + } else { + dso_id.maj = event->maj; + dso_id.min = event->min; + dso_id.ino = event->ino; + dso_id.ino_generation = event->ino_generation; + dso_id.mmap2_valid = true; + dso_id.mmap2_ino_generation_valid = true; + } - dso = dsos__findnew_id(&machine->dsos, event->filename, &id); + dso = dsos__findnew_id(&machine->dsos, event->filename, &dso_id); if (dso && dso__has_build_id(dso)) { bid = *dso__bid(dso); rc = 0; @@ -525,7 +532,7 @@ out: event->mmap2.pid = tgid; event->mmap2.tid = pid; - if (symbol_conf.buildid_mmap2) + if (!symbol_conf.no_buildid_mmap2) perf_record_mmap2__read_build_id(&event->mmap2, machine, false); if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { @@ -683,7 +690,7 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data) return 0; dso = map__dso(map); - if (symbol_conf.buildid_mmap2) { + if (!symbol_conf.no_buildid_mmap2) { size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64)); event->mmap2.header.type = PERF_RECORD_MMAP2; event->mmap2.header.size = (sizeof(event->mmap2) - @@ -696,6 +703,11 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data) memcpy(event->mmap2.filename, dso__long_name(dso), dso__long_name_len(dso) + 1); + /* Clear stale build ID from previous module iteration */ + event->mmap2.header.misc &= ~PERF_RECORD_MISC_MMAP_BUILD_ID; + memset(event->mmap2.build_id, 0, sizeof(event->mmap2.build_id)); + event->mmap2.build_id_size = 0; + perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false); } else { size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64)); @@ -727,9 +739,9 @@ int perf_event__synthesize_modules(const struct perf_tool *tool, perf_event__han .process = process, .machine = machine, }; - size_t size = symbol_conf.buildid_mmap2 - ? sizeof(args.event->mmap2) - : sizeof(args.event->mmap); + size_t size = symbol_conf.no_buildid_mmap2 + ? sizeof(args.event->mmap) + : sizeof(args.event->mmap2); args.event = zalloc(size + machine->id_hdr_size); if (args.event == NULL) { @@ -767,10 +779,10 @@ static int __event__synthesize_thread(union perf_event *comm_event, bool needs_mmap, bool mmap_data) { char filename[PATH_MAX]; - struct dirent **dirent; + struct io_dir iod; + struct io_dirent64 *dent; pid_t tgid, ppid; int rc = 0; - int i, n; /* special case: only send one comm event using passed in pid */ if (!full) { @@ -802,16 +814,19 @@ static int __event__synthesize_thread(union perf_event *comm_event, snprintf(filename, sizeof(filename), "%s/proc/%d/task", machine->root_dir, pid); - n = scandir(filename, &dirent, filter_task, NULL); - if (n < 0) - return n; + io_dir__init(&iod, open(filename, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (iod.dirfd < 0) + return -1; - for (i = 0; i < n; i++) { + while ((dent = io_dir__readdir(&iod)) != NULL) { char *end; pid_t _pid; bool kernel_thread = false; - _pid = strtol(dirent[i]->d_name, &end, 10); + if (!isdigit(dent->d_name[0])) + continue; + + _pid = strtol(dent->d_name, &end, 10); if (*end) continue; @@ -845,9 +860,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, } } - for (i = 0; i < n; i++) - zfree(&dirent[i]); - free(dirent); + close(iod.dirfd); return rc; } @@ -1116,8 +1129,8 @@ static int __perf_event__synthesize_kernel_mmap(const struct perf_tool *tool, struct machine *machine) { union perf_event *event; - size_t size = symbol_conf.buildid_mmap2 ? - sizeof(event->mmap2) : sizeof(event->mmap); + size_t size = symbol_conf.no_buildid_mmap2 ? + sizeof(event->mmap) : sizeof(event->mmap2); struct map *map = machine__kernel_map(machine); struct kmap *kmap; int err; @@ -1151,7 +1164,7 @@ static int __perf_event__synthesize_kernel_mmap(const struct perf_tool *tool, event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; } - if (symbol_conf.buildid_mmap2) { + if (!symbol_conf.no_buildid_mmap2) { size = snprintf(event->mmap2.filename, sizeof(event->mmap2.filename), "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; size = PERF_ALIGN(size, sizeof(u64)); @@ -1253,7 +1266,7 @@ static void synthesize_cpus(struct synthesize_cpu_map_data *data) static void synthesize_mask(struct synthesize_cpu_map_data *data) { - int idx; + unsigned int idx; struct perf_cpu cpu; /* Due to padding, the 4bytes per entry mask variant is always smaller. */ @@ -1508,9 +1521,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, } if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { + if (sample->user_regs && sample->user_regs->abi) { result += sizeof(u64); - sz = hweight64(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs->mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -1536,9 +1549,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, result += sizeof(u64); if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { + if (sample->intr_regs && sample->intr_regs->abi) { result += sizeof(u64); - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs->mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -1565,10 +1578,16 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, return result; } -void __weak arch_perf_synthesize_sample_weight(const struct perf_sample *data, +static void perf_synthesize_sample_weight(const struct perf_sample *data, __u64 *array, u64 type __maybe_unused) { *array = data->weight; + + if (type & PERF_SAMPLE_WEIGHT_STRUCT) { + *array &= 0xffffffff; + *array |= ((u64)data->ins_lat << 32); + *array |= ((u64)data->weight3 << 48); + } } static __u64 *copy_read_group_values(__u64 *array, __u64 read_format, @@ -1707,10 +1726,10 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo } if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { - *array++ = sample->user_regs.abi; - sz = hweight64(sample->user_regs.mask) * sizeof(u64); - memcpy(array, sample->user_regs.regs, sz); + if (sample->user_regs && sample->user_regs->abi) { + *array++ = sample->user_regs->abi; + sz = hweight64(sample->user_regs->mask) * sizeof(u64); + memcpy(array, sample->user_regs->regs, sz); array = (void *)array + sz; } else { *array++ = 0; @@ -1728,7 +1747,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo } if (type & PERF_SAMPLE_WEIGHT_TYPE) { - arch_perf_synthesize_sample_weight(sample, array, type); + perf_synthesize_sample_weight(sample, array, type); array++; } @@ -1743,10 +1762,10 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo } if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { - *array++ = sample->intr_regs.abi; - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); - memcpy(array, sample->intr_regs.regs, sz); + if (sample->intr_regs && sample->intr_regs->abi) { + *array++ = sample->intr_regs->abi; + sz = hweight64(sample->intr_regs->mask) * sizeof(u64); + memcpy(array, sample->intr_regs->regs, sz); array = (void *)array + sz; } else { *array++ = 0; @@ -2043,7 +2062,7 @@ int perf_event__synthesize_event_update_name(const struct perf_tool *tool, struc int perf_event__synthesize_event_update_cpus(const struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process) { - struct synthesize_cpu_map_data syn_data = { .map = evsel->core.own_cpus }; + struct synthesize_cpu_map_data syn_data = { .map = evsel->core.pmu_cpus }; struct perf_record_event_update *ev; int err; @@ -2124,7 +2143,7 @@ int perf_event__synthesize_extra_attr(const struct perf_tool *tool, struct evlis } } - if (evsel->core.own_cpus) { + if (evsel->core.pmu_cpus) { err = perf_event__synthesize_event_update_cpus(tool, evsel, process); if (err < 0) { pr_err("Couldn't synthesize evsel cpus.\n"); @@ -2246,7 +2265,9 @@ int perf_event__synthesize_build_id(const struct perf_tool *tool, memset(&ev, 0, len); - ev.build_id.size = min(bid->size, sizeof(ev.build_id.build_id)); + ev.build_id.size = bid->size; + if (ev.build_id.size > sizeof(ev.build_id.build_id)) + ev.build_id.size = sizeof(ev.build_id.build_id); memcpy(ev.build_id.build_id, bid->data, ev.build_id.size); ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID; ev.build_id.header.misc = misc | PERF_RECORD_MISC_BUILD_ID_SIZE; @@ -2306,7 +2327,9 @@ int perf_event__synthesize_mmap2_build_id(const struct perf_tool *tool, ev.mmap2.len = len; ev.mmap2.pgoff = pgoff; - ev.mmap2.build_id_size = min(bid->size, sizeof(ev.mmap2.build_id)); + ev.mmap2.build_id_size = bid->size; + if (ev.mmap2.build_id_size > sizeof(ev.mmap2.build_id)) + ev.build_id.size = sizeof(ev.mmap2.build_id); memcpy(ev.mmap2.build_id, bid->data, ev.mmap2.build_id_size); ev.mmap2.prot = prot; @@ -2511,3 +2534,199 @@ int parse_synth_opt(char *synth) return ret; } + +static union perf_event *__synthesize_schedstat_cpu(struct io *io, __u16 version, + __u64 *cpu, __u64 timestamp) +{ + struct perf_record_schedstat_cpu *cs; + union perf_event *event; + size_t size; + char ch; + + size = sizeof(*cs); + size = PERF_ALIGN(size, sizeof(u64)); + event = zalloc(size); + + if (!event) + return NULL; + + cs = &event->schedstat_cpu; + cs->header.type = PERF_RECORD_SCHEDSTAT_CPU; + cs->header.size = size; + cs->timestamp = timestamp; + + if (io__get_char(io) != 'p' || io__get_char(io) != 'u') + goto out_cpu; + + if (io__get_dec(io, (__u64 *)cpu) != ' ') + goto out_cpu; + +#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver) \ + do { \ + __u64 _tmp; \ + ch = io__get_dec(io, &_tmp); \ + if (ch != ' ' && ch != '\n') \ + goto out_cpu; \ + cs->_ver._name = _tmp; \ + } while (0) + + if (version == 15) { +#include <perf/schedstat-v15.h> + } else if (version == 16) { +#include <perf/schedstat-v16.h> + } else if (version == 17) { +#include <perf/schedstat-v17.h> + } +#undef CPU_FIELD + + cs->cpu = *cpu; + cs->version = version; + + return event; +out_cpu: + free(event); + return NULL; +} + +static union perf_event *__synthesize_schedstat_domain(struct io *io, __u16 version, + __u64 cpu, __u64 timestamp) +{ + struct perf_record_schedstat_domain *ds; + union perf_event *event = NULL; + __u64 d_num; + size_t size; + char ch; + + if (io__get_char(io) != 'o' || io__get_char(io) != 'm' || io__get_char(io) != 'a' || + io__get_char(io) != 'i' || io__get_char(io) != 'n') + return NULL; + + ch = io__get_dec(io, &d_num); + if (version >= 17) { + /* Skip domain name as it can be extracted from perf header */ + while (io__get_char(io) != ' ') + continue; + } + + /* Skip cpumask as it can be extracted from perf header */ + while (io__get_char(io) != ' ') + continue; + + size = sizeof(*ds); + size = PERF_ALIGN(size, sizeof(u64)); + event = zalloc(size); + + ds = &event->schedstat_domain; + ds->header.type = PERF_RECORD_SCHEDSTAT_DOMAIN; + ds->header.size = size; + ds->version = version; + ds->timestamp = timestamp; + ds->domain = d_num; + +#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver) \ + do { \ + __u64 _tmp; \ + ch = io__get_dec(io, &_tmp); \ + if (ch != ' ' && ch != '\n') \ + goto out_domain; \ + ds->_ver._name = _tmp; \ + } while (0) + + if (version == 15) { +#include <perf/schedstat-v15.h> + } else if (version == 16) { +#include <perf/schedstat-v16.h> + } else if (version == 17) { +#include <perf/schedstat-v17.h> + } +#undef DOMAIN_FIELD + + ds->cpu = cpu; + goto out; + +out_domain: + free(event); + event = NULL; +out: + return event; +} + +int perf_event__synthesize_schedstat(const struct perf_tool *tool, + perf_event__handler_t process, + struct perf_cpu_map *user_requested_cpus) +{ + char *line = NULL, path[PATH_MAX]; + union perf_event *event = NULL; + size_t line_len = 0; + char bf[BUFSIZ]; + __u64 timestamp; + __u64 cpu = -1; + __u16 version; + struct io io; + int ret = -1; + char ch; + + snprintf(path, PATH_MAX, "%s/schedstat", procfs__mountpoint()); + io.fd = open(path, O_RDONLY, 0); + if (io.fd < 0) { + pr_err("Failed to open %s. Possibly CONFIG_SCHEDSTAT is disabled.\n", path); + return -1; + } + io__init(&io, io.fd, bf, sizeof(bf)); + + if (io__getline(&io, &line, &line_len) < 0 || !line_len) + goto out; + + if (!strcmp(line, "version 15\n")) { + version = 15; + } else if (!strcmp(line, "version 16\n")) { + version = 16; + } else if (!strcmp(line, "version 17\n")) { + version = 17; + } else { + pr_err("Unsupported %s version: %s", path, line + 8); + goto out_free_line; + } + + if (io__getline(&io, &line, &line_len) < 0 || !line_len) + goto out_free_line; + timestamp = atol(line + 10); + + /* + * FIXME: Can be optimized a bit by not synthesizing domain samples + * for filtered out cpus. + */ + for (ch = io__get_char(&io); !io.eof; ch = io__get_char(&io)) { + struct perf_cpu this_cpu; + + if (ch == 'c') { + event = __synthesize_schedstat_cpu(&io, version, + &cpu, timestamp); + } else if (ch == 'd') { + event = __synthesize_schedstat_domain(&io, version, + cpu, timestamp); + } + if (!event) + goto out_free_line; + + this_cpu.cpu = cpu; + + if (user_requested_cpus && !perf_cpu_map__has(user_requested_cpus, this_cpu)) + continue; + + if (process(tool, event, NULL, NULL) < 0) { + free(event); + goto out_free_line; + } + + free(event); + } + + ret = 0; + +out_free_line: + free(line); +out: + close(io.fd); + return ret; +} diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index b9c936b5cfeb..b0edad0c3100 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -92,6 +92,8 @@ int perf_event__synthesize_threads(const struct perf_tool *tool, perf_event__han int perf_event__synthesize_tracing_data(const struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process); int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, const struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); pid_t perf_event__synthesize_comm(const struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine); +void perf_event__synthesize_final_bpf_metadata(struct perf_session *session, + perf_event__handler_t process); int perf_tool__process_synth_event(const struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process); @@ -105,24 +107,9 @@ int machine__synthesize_threads(struct machine *machine, struct target *target, struct perf_thread_map *threads, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); -#ifdef HAVE_AUXTRACE_SUPPORT int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, const struct perf_tool *tool, struct perf_session *session, perf_event__handler_t process); -#else // HAVE_AUXTRACE_SUPPORT - -#include <errno.h> - -static inline int -perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused, - const struct perf_tool *tool __maybe_unused, - struct perf_session *session __maybe_unused, - perf_event__handler_t process __maybe_unused) -{ - return -EINVAL; -} -#endif // HAVE_AUXTRACE_SUPPORT - #ifdef HAVE_LIBBPF_SUPPORT int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process, struct machine *machine, struct record_opts *opts); @@ -141,4 +128,7 @@ int perf_event__synthesize_for_pipe(const struct perf_tool *tool, struct perf_data *data, perf_event__handler_t process); +int perf_event__synthesize_schedstat(const struct perf_tool *tool, + perf_event__handler_t process, + struct perf_cpu_map *user_requested_cpu); #endif // __PERF_SYNTHETIC_EVENTS_H diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 928aca4cd6e9..67a8ec10e9e4 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -7,119 +7,127 @@ #include "syscalltbl.h" #include <stdlib.h> +#include <asm/bitsperlong.h> #include <linux/compiler.h> +#include <linux/kernel.h> #include <linux/zalloc.h> #include <string.h> #include "string2.h" -#include <syscall_table.h> -const int syscalltbl_native_max_id = SYSCALLTBL_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl; +#include "trace/beauty/generated/syscalltbl.c" -struct syscall { - int id; - const char *name; -}; - -static int syscallcmpname(const void *vkey, const void *ventry) -{ - const char *key = vkey; - const struct syscall *entry = ventry; - - return strcmp(key, entry->name); -} - -static int syscallcmp(const void *va, const void *vb) +static const struct syscalltbl *find_table(int e_machine) { - const struct syscall *a = va, *b = vb; + static const struct syscalltbl *last_table; + static int last_table_machine = EM_NONE; - return strcmp(a->name, b->name); -} + /* Tables only exist for EM_SPARC. */ + if (e_machine == EM_SPARCV9) + e_machine = EM_SPARC; -static int syscalltbl__init_native(struct syscalltbl *tbl) -{ - int nr_entries = 0, i, j; - struct syscall *entries; + if (last_table_machine == e_machine && last_table != NULL) + return last_table; - for (i = 0; i <= syscalltbl_native_max_id; ++i) - if (syscalltbl_native[i]) - ++nr_entries; + for (size_t i = 0; i < ARRAY_SIZE(syscalltbls); i++) { + const struct syscalltbl *entry = &syscalltbls[i]; - entries = tbl->syscalls.entries = malloc(sizeof(struct syscall) * nr_entries); - if (tbl->syscalls.entries == NULL) - return -1; + if (entry->e_machine != e_machine && entry->e_machine != EM_NONE) + continue; - for (i = 0, j = 0; i <= syscalltbl_native_max_id; ++i) { - if (syscalltbl_native[i]) { - entries[j].name = syscalltbl_native[i]; - entries[j].id = i; - ++j; - } + last_table = entry; + last_table_machine = e_machine; + return entry; } - - qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp); - tbl->syscalls.nr_entries = nr_entries; - tbl->syscalls.max_id = syscalltbl_native_max_id; - return 0; + return NULL; } -struct syscalltbl *syscalltbl__new(void) +const char *syscalltbl__name(int e_machine, int id) { - struct syscalltbl *tbl = malloc(sizeof(*tbl)); - if (tbl) { - if (syscalltbl__init_native(tbl)) { - free(tbl); - return NULL; - } + const struct syscalltbl *table = find_table(e_machine); + + if (e_machine == EM_MIPS && id > 1000) { + /* + * MIPS may encode the N32/64/O32 type in the high part of + * syscall number. Mask this off if present. See the values of + * __NR_N32_Linux, __NR_64_Linux, __NR_O32_Linux and __NR_Linux. + */ + id = id % 1000; } - return tbl; + if (table && id >= 0 && id < table->num_to_name_len) + return table->num_to_name[id]; + return NULL; } -void syscalltbl__delete(struct syscalltbl *tbl) +struct syscall_cmp_key { + const char *name; + const char *const *tbl; +}; + +static int syscallcmpname(const void *vkey, const void *ventry) { - zfree(&tbl->syscalls.entries); - free(tbl); + const struct syscall_cmp_key *key = vkey; + const uint16_t *entry = ventry; + + return strcmp(key->name, key->tbl[*entry]); } -const char *syscalltbl__name(const struct syscalltbl *tbl __maybe_unused, int id) +int syscalltbl__id(int e_machine, const char *name) { - return id <= syscalltbl_native_max_id ? syscalltbl_native[id]: NULL; + const struct syscalltbl *table = find_table(e_machine); + struct syscall_cmp_key key; + const uint16_t *id; + + if (!table) + return -1; + + key.name = name; + key.tbl = table->num_to_name; + id = bsearch(&key, table->sorted_names, table->sorted_names_len, + sizeof(table->sorted_names[0]), syscallcmpname); + + return id ? *id : -1; } -int syscalltbl__id(struct syscalltbl *tbl, const char *name) +int syscalltbl__num_idx(int e_machine) { - struct syscall *sc = bsearch(name, tbl->syscalls.entries, - tbl->syscalls.nr_entries, sizeof(*sc), - syscallcmpname); + const struct syscalltbl *table = find_table(e_machine); + + if (!table) + return 0; - return sc ? sc->id : -1; + return table->sorted_names_len; } -int syscalltbl__id_at_idx(struct syscalltbl *tbl, int idx) +int syscalltbl__id_at_idx(int e_machine, int idx) { - struct syscall *syscalls = tbl->syscalls.entries; + const struct syscalltbl *table = find_table(e_machine); - return idx < tbl->syscalls.nr_entries ? syscalls[idx].id : -1; + if (!table) + return -1; + + assert(idx >= 0 && idx < table->sorted_names_len); + return table->sorted_names[idx]; } -int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +int syscalltbl__strglobmatch_next(int e_machine, const char *syscall_glob, int *idx) { - int i; - struct syscall *syscalls = tbl->syscalls.entries; + const struct syscalltbl *table = find_table(e_machine); + + for (int i = *idx + 1; table && i < table->sorted_names_len; ++i) { + const char *name = table->num_to_name[table->sorted_names[i]]; - for (i = *idx + 1; i < tbl->syscalls.nr_entries; ++i) { - if (strglobmatch(syscalls[i].name, syscall_glob)) { + if (strglobmatch(name, syscall_glob)) { *idx = i; - return syscalls[i].id; + return table->sorted_names[i]; } } return -1; } -int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +int syscalltbl__strglobmatch_first(int e_machine, const char *syscall_glob, int *idx) { *idx = -1; - return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); + return syscalltbl__strglobmatch_next(e_machine, syscall_glob, idx); } diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index 362411a6d849..2bb628eff367 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -2,22 +2,12 @@ #ifndef __PERF_SYSCALLTBL_H #define __PERF_SYSCALLTBL_H -struct syscalltbl { - struct { - int max_id; - int nr_entries; - void *entries; - } syscalls; -}; +const char *syscalltbl__name(int e_machine, int id); +int syscalltbl__id(int e_machine, const char *name); +int syscalltbl__num_idx(int e_machine); +int syscalltbl__id_at_idx(int e_machine, int idx); -struct syscalltbl *syscalltbl__new(void); -void syscalltbl__delete(struct syscalltbl *tbl); - -const char *syscalltbl__name(const struct syscalltbl *tbl, int id); -int syscalltbl__id(struct syscalltbl *tbl, const char *name); -int syscalltbl__id_at_idx(struct syscalltbl *tbl, int idx); - -int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx); -int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx); +int syscalltbl__strglobmatch_first(int e_machine, const char *syscall_glob, int *idx); +int syscalltbl__strglobmatch_next(int e_machine, const char *syscall_glob, int *idx); #endif /* __PERF_SYSCALLTBL_H */ diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index 0f383418e3df..8cf71bea295a 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -28,20 +28,6 @@ enum target_errno target__validate(struct target *target) ret = TARGET_ERRNO__PID_OVERRIDE_CPU; } - /* UID and PID are mutually exclusive */ - if (target->tid && target->uid_str) { - target->uid_str = NULL; - if (ret == TARGET_ERRNO__SUCCESS) - ret = TARGET_ERRNO__PID_OVERRIDE_UID; - } - - /* UID and CPU are mutually exclusive */ - if (target->uid_str && target->cpu_list) { - target->cpu_list = NULL; - if (ret == TARGET_ERRNO__SUCCESS) - ret = TARGET_ERRNO__UID_OVERRIDE_CPU; - } - /* PID and SYSTEM are mutually exclusive */ if (target->tid && target->system_wide) { target->system_wide = false; @@ -49,13 +35,6 @@ enum target_errno target__validate(struct target *target) ret = TARGET_ERRNO__PID_OVERRIDE_SYSTEM; } - /* UID and SYSTEM are mutually exclusive */ - if (target->uid_str && target->system_wide) { - target->system_wide = false; - if (ret == TARGET_ERRNO__SUCCESS) - ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM; - } - /* BPF and CPU are mutually exclusive */ if (target->bpf_str && target->cpu_list) { target->cpu_list = NULL; @@ -70,13 +49,6 @@ enum target_errno target__validate(struct target *target) ret = TARGET_ERRNO__BPF_OVERRIDE_PID; } - /* BPF and UID are mutually exclusive */ - if (target->bpf_str && target->uid_str) { - target->uid_str = NULL; - if (ret == TARGET_ERRNO__SUCCESS) - ret = TARGET_ERRNO__BPF_OVERRIDE_UID; - } - /* BPF and THREADS are mutually exclusive */ if (target->bpf_str && target->per_thread) { target->per_thread = false; @@ -94,15 +66,13 @@ enum target_errno target__validate(struct target *target) return ret; } -enum target_errno target__parse_uid(struct target *target) +uid_t parse_uid(const char *str) { struct passwd pwd, *result; char buf[1024]; - const char *str = target->uid_str; - target->uid = UINT_MAX; if (str == NULL) - return TARGET_ERRNO__SUCCESS; + return UINT_MAX; /* Try user name first */ getpwnam_r(str, &pwd, buf, sizeof(buf), &result); @@ -115,16 +85,15 @@ enum target_errno target__parse_uid(struct target *target) int uid = strtol(str, &endptr, 10); if (*endptr != '\0') - return TARGET_ERRNO__INVALID_UID; + return UINT_MAX; getpwuid_r(uid, &pwd, buf, sizeof(buf), &result); if (result == NULL) - return TARGET_ERRNO__USER_NOT_FOUND; + return UINT_MAX; } - target->uid = result->pw_uid; - return TARGET_ERRNO__SUCCESS; + return result->pw_uid; } /* @@ -132,20 +101,14 @@ enum target_errno target__parse_uid(struct target *target) */ static const char *target__error_str[] = { "PID/TID switch overriding CPU", - "PID/TID switch overriding UID", - "UID switch overriding CPU", "PID/TID switch overriding SYSTEM", - "UID switch overriding SYSTEM", "SYSTEM/CPU switch overriding PER-THREAD", "BPF switch overriding CPU", "BPF switch overriding PID/TID", - "BPF switch overriding UID", "BPF switch overriding THREAD", - "Invalid User: %s", - "Problems obtaining information for user %s", }; -int target__strerror(struct target *target, int errnum, +int target__strerror(struct target *target __maybe_unused, int errnum, char *buf, size_t buflen) { int idx; @@ -170,11 +133,6 @@ int target__strerror(struct target *target, int errnum, snprintf(buf, buflen, "%s", msg); break; - case TARGET_ERRNO__INVALID_UID: - case TARGET_ERRNO__USER_NOT_FOUND: - snprintf(buf, buflen, msg, target->uid_str); - break; - default: /* cannot reach here */ break; diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h index 2ee2cc30340f..bc2bff9c6842 100644 --- a/tools/perf/util/target.h +++ b/tools/perf/util/target.h @@ -9,9 +9,7 @@ struct target { const char *pid; const char *tid; const char *cpu_list; - const char *uid_str; const char *bpf_str; - uid_t uid; bool system_wide; bool uses_mmap; bool default_per_cpu; @@ -36,44 +34,37 @@ enum target_errno { /* for target__validate() */ TARGET_ERRNO__PID_OVERRIDE_CPU = __TARGET_ERRNO__START, - TARGET_ERRNO__PID_OVERRIDE_UID, - TARGET_ERRNO__UID_OVERRIDE_CPU, TARGET_ERRNO__PID_OVERRIDE_SYSTEM, - TARGET_ERRNO__UID_OVERRIDE_SYSTEM, TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD, TARGET_ERRNO__BPF_OVERRIDE_CPU, TARGET_ERRNO__BPF_OVERRIDE_PID, - TARGET_ERRNO__BPF_OVERRIDE_UID, TARGET_ERRNO__BPF_OVERRIDE_THREAD, - /* for target__parse_uid() */ - TARGET_ERRNO__INVALID_UID, - TARGET_ERRNO__USER_NOT_FOUND, - __TARGET_ERRNO__END, }; enum target_errno target__validate(struct target *target); -enum target_errno target__parse_uid(struct target *target); + +uid_t parse_uid(const char *str); int target__strerror(struct target *target, int errnum, char *buf, size_t buflen); -static inline bool target__has_task(struct target *target) +static inline bool target__has_task(const struct target *target) { - return target->tid || target->pid || target->uid_str; + return target->tid || target->pid; } -static inline bool target__has_cpu(struct target *target) +static inline bool target__has_cpu(const struct target *target) { return target->system_wide || target->cpu_list; } -static inline bool target__none(struct target *target) +static inline bool target__none(const struct target *target) { return !target__has_task(target) && !target__has_cpu(target); } -static inline bool target__enable_on_exec(struct target *target) +static inline bool target__enable_on_exec(const struct target *target) { /* * Normally enable_on_exec should be set if: @@ -84,12 +75,12 @@ static inline bool target__enable_on_exec(struct target *target) return target__none(target) && !target->initial_delay; } -static inline bool target__has_per_thread(struct target *target) +static inline bool target__has_per_thread(const struct target *target) { return target->system_wide && target->per_thread; } -static inline bool target__uses_dummy_map(struct target *target) +static inline bool target__uses_dummy_map(const struct target *target) { bool use_dummy = false; diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index c6a0a27b12c2..c5ce741b0744 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -157,10 +157,10 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread, if (thread__maps(thread) && maps__machine(thread__maps(thread))) { struct machine *machine = maps__machine(thread__maps(thread)); - const char *arch = perf_env__arch(machine->env); + uint16_t e_machine = thread__e_machine(thread, machine, /*e_flags=*/NULL); ts->kernel_start = machine__kernel_start(machine); - if (!strcmp(arch, "x86")) + if (e_machine == EM_X86_64 || e_machine == EM_386) ts->rstate = X86_RETPOLINE_POSSIBLE; } else { ts->kernel_start = 1ULL << 63; diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0ffdd52d86d7..22be77225bb0 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#include <elf.h> #include <errno.h> +#include <fcntl.h> #include <stdlib.h> #include <stdio.h> #include <string.h> @@ -16,6 +18,7 @@ #include "symbol.h" #include "unwind.h" #include "callchain.h" +#include "dwarf-regs.h" #include <api/fs/fs.h> @@ -38,6 +41,7 @@ int thread__init_maps(struct thread *thread, struct machine *machine) } struct thread *thread__new(pid_t pid, pid_t tid) + NO_THREAD_SAFETY_ANALYSIS /* Allocation/creation is inherently single threaded. */ { RC_STRUCT(thread) *_thread = zalloc(sizeof(*_thread)); struct thread *thread; @@ -51,6 +55,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread__set_ppid(thread, -1); thread__set_cpu(thread, -1); thread__set_guest_cpu(thread, -1); + thread__set_e_machine(thread, EM_NONE); thread__set_lbr_stitch_enable(thread, false); INIT_LIST_HEAD(thread__namespaces_list(thread)); INIT_LIST_HEAD(thread__comm_list(thread)); @@ -196,7 +201,8 @@ int thread__set_namespaces(struct thread *thread, u64 timestamp, return ret; } -struct comm *thread__comm(struct thread *thread) +static struct comm *__thread__comm(struct thread *thread) + SHARED_LOCKS_REQUIRED(thread__comm_lock(thread)) { if (list_empty(thread__comm_list(thread))) return NULL; @@ -204,16 +210,30 @@ struct comm *thread__comm(struct thread *thread) return list_first_entry(thread__comm_list(thread), struct comm, list); } +struct comm *thread__comm(struct thread *thread) +{ + struct comm *res = NULL; + + down_read(thread__comm_lock(thread)); + res = __thread__comm(thread); + up_read(thread__comm_lock(thread)); + return res; +} + struct comm *thread__exec_comm(struct thread *thread) { struct comm *comm, *last = NULL, *second_last = NULL; + down_read(thread__comm_lock(thread)); list_for_each_entry(comm, thread__comm_list(thread), list) { - if (comm->exec) + if (comm->exec) { + up_read(thread__comm_lock(thread)); return comm; + } second_last = last; last = comm; } + up_read(thread__comm_lock(thread)); /* * 'last' with no start time might be the parent's comm of a synthesized @@ -229,8 +249,9 @@ struct comm *thread__exec_comm(struct thread *thread) static int ____thread__set_comm(struct thread *thread, const char *str, u64 timestamp, bool exec) + EXCLUSIVE_LOCKS_REQUIRED(thread__comm_lock(thread)) { - struct comm *new, *curr = thread__comm(thread); + struct comm *new, *curr = __thread__comm(thread); /* Override the default :tid entry */ if (!thread__comm_set(thread)) { @@ -281,8 +302,9 @@ int thread__set_comm_from_proc(struct thread *thread) } static const char *__thread__comm_str(struct thread *thread) + SHARED_LOCKS_REQUIRED(thread__comm_lock(thread)) { - const struct comm *comm = thread__comm(thread); + const struct comm *comm = __thread__comm(thread); if (!comm) return NULL; @@ -406,7 +428,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bo } void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, - struct addr_location *al) + bool symbols, struct addr_location *al) { size_t i; const u8 cpumodes[] = { @@ -417,12 +439,118 @@ void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, }; for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { - thread__find_symbol(thread, cpumodes[i], addr, al); + if (symbols) + thread__find_symbol(thread, cpumodes[i], addr, al); + else + thread__find_map(thread, cpumodes[i], addr, al); + if (al->map) break; } } +static uint16_t read_proc_e_machine_for_pid(pid_t pid, uint32_t *e_flags) +{ + char path[6 /* "/proc/" */ + 11 /* max length of pid */ + 5 /* "/exe\0" */]; + int fd; + uint16_t e_machine = EM_NONE; + + snprintf(path, sizeof(path), "/proc/%d/exe", pid); + fd = open(path, O_RDONLY); + if (fd >= 0) { + e_machine = dso__read_e_machine(/*optional_dso=*/NULL, fd, e_flags); + close(fd); + } + return e_machine; +} + +struct thread__e_machine_callback_args { + struct machine *machine; + uint32_t e_flags; + uint16_t e_machine; +}; + +static int thread__e_machine_callback(struct map *map, void *_args) +{ + struct thread__e_machine_callback_args *args = _args; + struct dso *dso = map__dso(map); + + if (!dso) + return 0; // No dso, continue search. + + args->e_machine = dso__e_machine(dso, args->machine, &args->e_flags); + return args->e_machine != EM_NONE ? 1 /* stop search */ : 0 /* continue search */; +} + +uint16_t thread__e_machine(struct thread *thread, struct machine *machine, uint32_t *e_flags) +{ + pid_t tid, pid; + uint16_t e_machine = RC_CHK_ACCESS(thread)->e_machine; + uint32_t local_e_flags = 0; + struct thread__e_machine_callback_args args = { + .machine = machine, + .e_flags = 0, + .e_machine = EM_NONE, + }; + + if (e_machine != EM_NONE) { + if (e_flags) + *e_flags = thread__e_flags(thread); + return e_machine; + } + + if (machine == NULL) { + struct maps *maps = thread__maps(thread); + + machine = maps__machine(maps); + } + tid = thread__tid(thread); + pid = thread__pid(thread); + if (pid != tid) { + struct thread *parent = machine__findnew_thread(machine, pid, pid); + + if (parent) { + e_machine = thread__e_machine(parent, machine, &local_e_flags); + thread__put(parent); + goto out; + } + /* Something went wrong, fallback. */ + } + /* Reading on the PID thread. First try to find from the maps. */ + maps__for_each_map(thread__maps(thread), thread__e_machine_callback, &args); + + if (args.e_machine != EM_NONE) { + e_machine = args.e_machine; + local_e_flags = args.e_flags; + } else { + /* Maps failed, perhaps we're live with map events disabled. */ + bool is_live = machine->machines == NULL; + + if (!is_live) { + /* Check if the session has a data file. */ + struct perf_session *session = container_of(machine->machines, + struct perf_session, + machines); + + is_live = !!session->data; + } + /* Read from /proc/pid/exe if live. */ + if (is_live) + e_machine = read_proc_e_machine_for_pid(pid, &local_e_flags); + } +out: + if (e_machine != EM_NONE) { + thread__set_e_machine(thread, e_machine); + thread__set_e_flags(thread, local_e_flags); + } else { + e_machine = EM_HOST; + local_e_flags = EF_HOST; + } + if (e_flags) + *e_flags = local_e_flags; + return e_machine; +} + struct thread *thread__main_thread(struct machine *machine, struct thread *thread) { if (thread__pid(thread) == thread__tid(thread)) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 6cbf6eb2812e..f5792d3e8a16 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -60,7 +60,15 @@ DECLARE_RC_STRUCT(thread) { struct srccode_state srccode_state; bool filter; int filter_entry_depth; - + /** + * @e_flags: The ELF EF_* associated with the thread. Valid if e_machine != EM_NONE. + */ + uint16_t e_flags; + /** + * @e_machine: The ELF EM_* associated with the thread. EM_NONE if not + * computed. + */ + uint16_t e_machine; /* LBR call stack stitch */ bool lbr_stitch_enable; struct lbr_stitch *lbr_stitch; @@ -122,7 +130,7 @@ struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al); void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, - struct addr_location *al); + bool symbols, struct addr_location *al); int thread__memcpy(struct thread *thread, struct machine *machine, void *buf, u64 ip, int len, bool *is64bit); @@ -232,14 +240,15 @@ static inline struct rw_semaphore *thread__namespaces_lock(struct thread *thread return &RC_CHK_ACCESS(thread)->namespaces_lock; } -static inline struct list_head *thread__comm_list(struct thread *thread) +static inline struct rw_semaphore *thread__comm_lock(struct thread *thread) { - return &RC_CHK_ACCESS(thread)->comm_list; + return &RC_CHK_ACCESS(thread)->comm_lock; } -static inline struct rw_semaphore *thread__comm_lock(struct thread *thread) +static inline struct list_head *thread__comm_list(struct thread *thread) + SHARED_LOCKS_REQUIRED(thread__comm_lock(thread)) { - return &RC_CHK_ACCESS(thread)->comm_lock; + return &RC_CHK_ACCESS(thread)->comm_list; } static inline u64 thread__db_id(const struct thread *thread) @@ -302,6 +311,24 @@ static inline void thread__set_filter_entry_depth(struct thread *thread, int dep RC_CHK_ACCESS(thread)->filter_entry_depth = depth; } +uint16_t thread__e_machine(struct thread *thread, struct machine *machine, uint32_t *e_flags); + +static inline void thread__set_e_machine(struct thread *thread, uint16_t e_machine) +{ + RC_CHK_ACCESS(thread)->e_machine = e_machine; +} + +static inline uint32_t thread__e_flags(const struct thread *thread) +{ + return RC_CHK_ACCESS(thread)->e_flags; +} + +static inline void thread__set_e_flags(struct thread *thread, uint32_t e_flags) +{ + RC_CHK_ACCESS(thread)->e_flags = e_flags; +} + + static inline bool thread__lbr_stitch_enable(const struct thread *thread) { return RC_CHK_ACCESS(thread)->lbr_stitch_enable; diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index b5f12390c355..48c70f149e92 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -72,7 +72,7 @@ struct perf_thread_map *thread_map__new_by_tid(pid_t tid) return threads; } -static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid) +static struct perf_thread_map *thread_map__new_all_cpus(void) { DIR *proc; int max_threads = 32, items, i; @@ -98,15 +98,6 @@ static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid) if (*end) /* only interested in proper numerical dirents */ continue; - snprintf(path, sizeof(path), "/proc/%s", dirent->d_name); - - if (uid != UINT_MAX) { - struct stat st; - - if (stat(path, &st) != 0 || st.st_uid != uid) - continue; - } - snprintf(path, sizeof(path), "/proc/%d/task", pid); items = scandir(path, &namelist, filter, NULL); if (items <= 0) { @@ -157,24 +148,11 @@ out_free_namelist: goto out_closedir; } -struct perf_thread_map *thread_map__new_all_cpus(void) -{ - return __thread_map__new_all_cpus(UINT_MAX); -} - -struct perf_thread_map *thread_map__new_by_uid(uid_t uid) -{ - return __thread_map__new_all_cpus(uid); -} - -struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid) +struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid) { if (pid != -1) return thread_map__new_by_pid(pid); - if (tid == -1 && uid != UINT_MAX) - return thread_map__new_by_uid(uid); - return thread_map__new_by_tid(tid); } @@ -186,19 +164,16 @@ static struct perf_thread_map *thread_map__new_by_pid_str(const char *pid_str) struct dirent **namelist = NULL; int i, j = 0; pid_t pid, prev_pid = INT_MAX; - char *end_ptr; struct str_node *pos; - struct strlist_config slist_config = { .dont_dupstr = true, }; - struct strlist *slist = strlist__new(pid_str, &slist_config); + struct strlist *slist = strlist__new(pid_str, NULL); if (!slist) return NULL; strlist__for_each_entry(pos, slist) { - pid = strtol(pos->s, &end_ptr, 10); + pid = strtol(pos->s, NULL, 10); - if (pid == INT_MIN || pid == INT_MAX || - (*end_ptr != '\0' && *end_ptr != ',')) + if (pid == INT_MIN || pid == INT_MAX) goto out_free_threads; if (pid == prev_pid) @@ -245,24 +220,21 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str) struct perf_thread_map *threads = NULL, *nt; int ntasks = 0; pid_t tid, prev_tid = INT_MAX; - char *end_ptr; struct str_node *pos; - struct strlist_config slist_config = { .dont_dupstr = true, }; struct strlist *slist; /* perf-stat expects threads to be generated even if tid not given */ if (!tid_str) return perf_thread_map__new_dummy(); - slist = strlist__new(tid_str, &slist_config); + slist = strlist__new(tid_str, NULL); if (!slist) return NULL; strlist__for_each_entry(pos, slist) { - tid = strtol(pos->s, &end_ptr, 10); + tid = strtol(pos->s, NULL, 10); - if (tid == INT_MIN || tid == INT_MAX || - (*end_ptr != '\0' && *end_ptr != ',')) + if (tid == INT_MIN || tid == INT_MAX) goto out_free_threads; if (tid == prev_tid) @@ -289,15 +261,11 @@ out_free_threads: goto out; } -struct perf_thread_map *thread_map__new_str(const char *pid, const char *tid, - uid_t uid, bool all_threads) +struct perf_thread_map *thread_map__new_str(const char *pid, const char *tid, bool all_threads) { if (pid) return thread_map__new_by_pid_str(pid); - if (!tid && uid != UINT_MAX) - return thread_map__new_by_uid(uid); - if (all_threads) return thread_map__new_all_cpus(); diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 00ec05fc1656..fc16d87f32fb 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -11,13 +11,11 @@ struct perf_record_thread_map; struct perf_thread_map *thread_map__new_dummy(void); struct perf_thread_map *thread_map__new_by_pid(pid_t pid); struct perf_thread_map *thread_map__new_by_tid(pid_t tid); -struct perf_thread_map *thread_map__new_by_uid(uid_t uid); -struct perf_thread_map *thread_map__new_all_cpus(void); -struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); +struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid); struct perf_thread_map *thread_map__new_event(struct perf_record_thread_map *event); struct perf_thread_map *thread_map__new_str(const char *pid, - const char *tid, uid_t uid, bool all_threads); + const char *tid, bool all_threads); struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str); diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index 1b91ccd4d523..d43c4577d7eb 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -325,7 +325,7 @@ static int percent_comma_split(struct perf_time_interval *ptime_buf, int num, } static int one_percent_convert(struct perf_time_interval *ptime_buf, - const char *ostr, u64 start, u64 end, char *c) + const char *ostr, u64 start, u64 end, const char *c) { char *str; int len = strlen(ostr), ret; @@ -358,7 +358,7 @@ static int one_percent_convert(struct perf_time_interval *ptime_buf, int perf_time__percent_parse_str(struct perf_time_interval *ptime_buf, int num, const char *ostr, u64 start, u64 end) { - char *c; + const char *c; /* * ostr example: diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c index 3b7f390f26eb..013c7839e2cf 100644 --- a/tools/perf/util/tool.c +++ b/tools/perf/util/tool.c @@ -1,23 +1,27 @@ // SPDX-License-Identifier: GPL-2.0 #include "data.h" #include "debug.h" +#include "event.h" #include "header.h" #include "session.h" #include "stat.h" #include "tool.h" #include "tsc.h" +#include <linux/compiler.h> #include <sys/mman.h> +#include <stddef.h> #include <unistd.h> #ifdef HAVE_ZSTD_SUPPORT -static int perf_session__process_compressed_event(struct perf_session *session, +static int perf_session__process_compressed_event(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event, u64 file_offset, const char *file_path) { void *src; size_t decomp_size, src_size; u64 decomp_last_rem = 0; - size_t mmap_len, decomp_len = session->header.env.comp_mmap_len; + size_t mmap_len, decomp_len = perf_session__env(session)->comp_mmap_len; struct decomp *decomp, *decomp_last = session->active_decomp->decomp_last; if (decomp_last) { @@ -43,8 +47,15 @@ static int perf_session__process_compressed_event(struct perf_session *session, decomp->size = decomp_last_rem; } - src = (void *)event + sizeof(struct perf_record_compressed); - src_size = event->pack.header.size - sizeof(struct perf_record_compressed); + if (event->header.type == PERF_RECORD_COMPRESSED) { + src = (void *)event + sizeof(struct perf_record_compressed); + src_size = event->pack.header.size - sizeof(struct perf_record_compressed); + } else if (event->header.type == PERF_RECORD_COMPRESSED2) { + src = (void *)event + sizeof(struct perf_record_compressed2); + src_size = event->pack2.data_size; + } else { + return -1; + } decomp_size = zstd_decompress_stream(session->active_decomp->zstd_decomp, src, src_size, &(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem); @@ -69,10 +80,9 @@ static int perf_session__process_compressed_event(struct perf_session *session, } #endif -static int process_event_synth_tracing_data_stub(struct perf_session *session - __maybe_unused, - union perf_event *event - __maybe_unused) +static int process_event_synth_tracing_data_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -80,8 +90,7 @@ static int process_event_synth_tracing_data_stub(struct perf_session *session static int process_event_synth_attr_stub(const struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct evlist **pevlist - __maybe_unused) + struct evlist **pevlist __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -89,8 +98,7 @@ static int process_event_synth_attr_stub(const struct perf_tool *tool __maybe_un static int process_event_synth_event_update_stub(const struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct evlist **pevlist - __maybe_unused) + struct evlist **pevlist __maybe_unused) { if (dump_trace) perf_event__fprintf_event_update(event, stdout); @@ -141,7 +149,8 @@ static int skipn(int fd, off_t n) return 0; } -static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unused, +static s64 process_event_auxtrace_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event) { dump_printf(": unhandled!\n"); @@ -150,7 +159,8 @@ static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unus return event->auxtrace.size; } -static int process_event_op2_stub(struct perf_session *session __maybe_unused, +static int process_event_op2_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused) { dump_printf(": unhandled!\n"); @@ -159,7 +169,8 @@ static int process_event_op2_stub(struct perf_session *session __maybe_unused, static -int process_event_thread_map_stub(struct perf_session *session __maybe_unused, +int process_event_thread_map_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused) { if (dump_trace) @@ -170,7 +181,8 @@ int process_event_thread_map_stub(struct perf_session *session __maybe_unused, } static -int process_event_cpu_map_stub(struct perf_session *session __maybe_unused, +int process_event_cpu_map_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused) { if (dump_trace) @@ -181,7 +193,8 @@ int process_event_cpu_map_stub(struct perf_session *session __maybe_unused, } static -int process_event_stat_config_stub(struct perf_session *session __maybe_unused, +int process_event_stat_config_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused) { if (dump_trace) @@ -191,7 +204,8 @@ int process_event_stat_config_stub(struct perf_session *session __maybe_unused, return 0; } -static int process_stat_stub(struct perf_session *perf_session __maybe_unused, +static int process_stat_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *perf_session __maybe_unused, union perf_event *event) { if (dump_trace) @@ -201,7 +215,8 @@ static int process_stat_stub(struct perf_session *perf_session __maybe_unused, return 0; } -static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused, +static int process_stat_round_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *perf_session __maybe_unused, union perf_event *event) { if (dump_trace) @@ -211,7 +226,8 @@ static int process_stat_round_stub(struct perf_session *perf_session __maybe_unu return 0; } -static int process_event_time_conv_stub(struct perf_session *perf_session __maybe_unused, +static int process_event_time_conv_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *perf_session __maybe_unused, union perf_event *event) { if (dump_trace) @@ -221,7 +237,8 @@ static int process_event_time_conv_stub(struct perf_session *perf_session __mayb return 0; } -static int perf_session__process_compressed_event_stub(struct perf_session *session __maybe_unused, +static int perf_session__process_compressed_event_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused, u64 file_offset __maybe_unused, const char *file_path __maybe_unused) @@ -230,6 +247,35 @@ static int perf_session__process_compressed_event_stub(struct perf_session *sess return 0; } +static int perf_event__process_bpf_metadata_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *perf_session __maybe_unused, + union perf_event *event) +{ + if (dump_trace) + perf_event__fprintf_bpf_metadata(event, stdout); + dump_printf(": unhandled!\n"); + return 0; +} +static int process_schedstat_cpu_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *perf_session __maybe_unused, + union perf_event *event) +{ + if (dump_trace) + perf_event__fprintf_schedstat_cpu(event, stdout); + dump_printf(": unhandled!\n"); + return 0; +} + +static int process_schedstat_domain_stub(const struct perf_tool *tool __maybe_unused, + struct perf_session *perf_session __maybe_unused, + union perf_event *event) +{ + if (dump_trace) + perf_event__fprintf_schedstat_domain(event, stdout); + dump_printf(": unhandled!\n"); + return 0; +} + void perf_tool__init(struct perf_tool *tool, bool ordered_events) { tool->ordered_events = ordered_events; @@ -238,6 +284,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events) tool->cgroup_events = false; tool->no_warn = false; tool->show_feat_hdr = SHOW_FEAT_NO_HEADER; + tool->merge_deferred_callchains = true; tool->sample = process_event_sample_stub; tool->mmap = process_event_stub; @@ -259,6 +306,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events) tool->read = process_event_sample_stub; tool->throttle = process_event_stub; tool->unthrottle = process_event_stub; + tool->callchain_deferred = process_event_sample_stub; tool->attr = process_event_synth_attr_stub; tool->event_update = process_event_synth_event_update_stub; tool->tracing_data = process_event_synth_tracing_data_stub; @@ -286,9 +334,186 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events) tool->compressed = perf_session__process_compressed_event_stub; #endif tool->finished_init = process_event_op2_stub; + tool->bpf_metadata = perf_event__process_bpf_metadata_stub; + tool->schedstat_cpu = process_schedstat_cpu_stub; + tool->schedstat_domain = process_schedstat_domain_stub; } bool perf_tool__compressed_is_stub(const struct perf_tool *tool) { return tool->compressed == perf_session__process_compressed_event_stub; } + +#define CREATE_DELEGATE_SAMPLE(name) \ + static int delegate_ ## name(const struct perf_tool *tool, \ + union perf_event *event, \ + struct perf_sample *sample, \ + struct evsel *evsel, \ + struct machine *machine) \ + { \ + struct delegate_tool *del_tool = container_of(tool, struct delegate_tool, tool); \ + struct perf_tool *delegate = del_tool->delegate; \ + return delegate->name(delegate, event, sample, evsel, machine); \ + } +CREATE_DELEGATE_SAMPLE(read); +CREATE_DELEGATE_SAMPLE(sample); +CREATE_DELEGATE_SAMPLE(callchain_deferred); + +#define CREATE_DELEGATE_ATTR(name) \ + static int delegate_ ## name(const struct perf_tool *tool, \ + union perf_event *event, \ + struct evlist **pevlist) \ + { \ + struct delegate_tool *del_tool = container_of(tool, struct delegate_tool, tool); \ + struct perf_tool *delegate = del_tool->delegate; \ + return delegate->name(delegate, event, pevlist); \ + } +CREATE_DELEGATE_ATTR(attr); +CREATE_DELEGATE_ATTR(event_update); + +#define CREATE_DELEGATE_OE(name) \ + static int delegate_ ## name(const struct perf_tool *tool, \ + union perf_event *event, \ + struct ordered_events *oe) \ + { \ + struct delegate_tool *del_tool = container_of(tool, struct delegate_tool, tool); \ + struct perf_tool *delegate = del_tool->delegate; \ + return delegate->name(delegate, event, oe); \ + } +CREATE_DELEGATE_OE(finished_round); + +#define CREATE_DELEGATE_OP(name) \ + static int delegate_ ## name(const struct perf_tool *tool, \ + union perf_event *event, \ + struct perf_sample *sample, \ + struct machine *machine) \ + { \ + struct delegate_tool *del_tool = container_of(tool, struct delegate_tool, tool); \ + struct perf_tool *delegate = del_tool->delegate; \ + return delegate->name(delegate, event, sample, machine); \ + } +CREATE_DELEGATE_OP(aux); +CREATE_DELEGATE_OP(aux_output_hw_id); +CREATE_DELEGATE_OP(bpf); +CREATE_DELEGATE_OP(cgroup); +CREATE_DELEGATE_OP(comm); +CREATE_DELEGATE_OP(context_switch); +CREATE_DELEGATE_OP(exit); +CREATE_DELEGATE_OP(fork); +CREATE_DELEGATE_OP(itrace_start); +CREATE_DELEGATE_OP(ksymbol); +CREATE_DELEGATE_OP(lost); +CREATE_DELEGATE_OP(lost_samples); +CREATE_DELEGATE_OP(mmap); +CREATE_DELEGATE_OP(mmap2); +CREATE_DELEGATE_OP(namespaces); +CREATE_DELEGATE_OP(text_poke); +CREATE_DELEGATE_OP(throttle); +CREATE_DELEGATE_OP(unthrottle); + +#define CREATE_DELEGATE_OP2(name) \ + static int delegate_ ## name(const struct perf_tool *tool, \ + struct perf_session *session, \ + union perf_event *event) \ + { \ + struct delegate_tool *del_tool = container_of(tool, struct delegate_tool, tool); \ + struct perf_tool *delegate = del_tool->delegate; \ + return delegate->name(delegate, session, event); \ + } +CREATE_DELEGATE_OP2(auxtrace_error); +CREATE_DELEGATE_OP2(auxtrace_info); +CREATE_DELEGATE_OP2(bpf_metadata); +CREATE_DELEGATE_OP2(build_id); +CREATE_DELEGATE_OP2(cpu_map); +CREATE_DELEGATE_OP2(feature); +CREATE_DELEGATE_OP2(finished_init); +CREATE_DELEGATE_OP2(id_index); +CREATE_DELEGATE_OP2(stat); +CREATE_DELEGATE_OP2(stat_config); +CREATE_DELEGATE_OP2(stat_round); +CREATE_DELEGATE_OP2(thread_map); +CREATE_DELEGATE_OP2(time_conv); +CREATE_DELEGATE_OP2(tracing_data); + +#define CREATE_DELEGATE_OP3(name) \ + static s64 delegate_ ## name(const struct perf_tool *tool, \ + struct perf_session *session, \ + union perf_event *event) \ + { \ + struct delegate_tool *del_tool = container_of(tool, struct delegate_tool, tool); \ + struct perf_tool *delegate = del_tool->delegate; \ + return delegate->name(delegate, session, event); \ + } +CREATE_DELEGATE_OP3(auxtrace); + +#define CREATE_DELEGATE_OP4(name) \ + static int delegate_ ## name(const struct perf_tool *tool, \ + struct perf_session *session, \ + union perf_event *event, \ + u64 data, \ + const char *str) \ + { \ + struct delegate_tool *del_tool = container_of(tool, struct delegate_tool, tool); \ + struct perf_tool *delegate = del_tool->delegate; \ + return delegate->name(delegate, session, event, data, str); \ + } +CREATE_DELEGATE_OP4(compressed); + +void delegate_tool__init(struct delegate_tool *tool, struct perf_tool *delegate) +{ + tool->delegate = delegate; + + tool->tool.ordered_events = delegate->ordered_events; + tool->tool.ordering_requires_timestamps = delegate->ordering_requires_timestamps; + tool->tool.namespace_events = delegate->namespace_events; + tool->tool.cgroup_events = delegate->cgroup_events; + tool->tool.no_warn = delegate->no_warn; + tool->tool.show_feat_hdr = delegate->show_feat_hdr; + tool->tool.merge_deferred_callchains = delegate->merge_deferred_callchains; + + tool->tool.sample = delegate_sample; + tool->tool.read = delegate_read; + + tool->tool.mmap = delegate_mmap; + tool->tool.mmap2 = delegate_mmap2; + tool->tool.comm = delegate_comm; + tool->tool.namespaces = delegate_namespaces; + tool->tool.cgroup = delegate_cgroup; + tool->tool.fork = delegate_fork; + tool->tool.exit = delegate_exit; + tool->tool.lost = delegate_lost; + tool->tool.lost_samples = delegate_lost_samples; + tool->tool.aux = delegate_aux; + tool->tool.itrace_start = delegate_itrace_start; + tool->tool.aux_output_hw_id = delegate_aux_output_hw_id; + tool->tool.context_switch = delegate_context_switch; + tool->tool.throttle = delegate_throttle; + tool->tool.unthrottle = delegate_unthrottle; + tool->tool.ksymbol = delegate_ksymbol; + tool->tool.bpf = delegate_bpf; + tool->tool.text_poke = delegate_text_poke; + tool->tool.callchain_deferred = delegate_callchain_deferred; + + tool->tool.attr = delegate_attr; + tool->tool.event_update = delegate_event_update; + + tool->tool.tracing_data = delegate_tracing_data; + + tool->tool.finished_round = delegate_finished_round; + + tool->tool.build_id = delegate_build_id; + tool->tool.id_index = delegate_id_index; + tool->tool.auxtrace_info = delegate_auxtrace_info; + tool->tool.auxtrace_error = delegate_auxtrace_error; + tool->tool.time_conv = delegate_time_conv; + tool->tool.thread_map = delegate_thread_map; + tool->tool.cpu_map = delegate_cpu_map; + tool->tool.stat_config = delegate_stat_config; + tool->tool.stat = delegate_stat; + tool->tool.stat_round = delegate_stat_round; + tool->tool.feature = delegate_feature; + tool->tool.finished_init = delegate_finished_init; + tool->tool.bpf_metadata = delegate_bpf_metadata; + tool->tool.compressed = delegate_compressed; + tool->tool.auxtrace = delegate_auxtrace; +} diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index db1c7642b0d1..2d9a4b1ca9d0 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -26,10 +26,12 @@ typedef int (*event_attr_op)(const struct perf_tool *tool, union perf_event *event, struct evlist **pevlist); -typedef int (*event_op2)(struct perf_session *session, union perf_event *event); -typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event); -typedef int (*event_op4)(struct perf_session *session, union perf_event *event, u64 data, - const char *str); +typedef int (*event_op2)(const struct perf_tool *tool, struct perf_session *session, + union perf_event *event); +typedef s64 (*event_op3)(const struct perf_tool *tool, struct perf_session *session, + union perf_event *event); +typedef int (*event_op4)(const struct perf_tool *tool, struct perf_session *session, + union perf_event *event, u64 data, const char *str); typedef int (*event_oe)(const struct perf_tool *tool, union perf_event *event, struct ordered_events *oe); @@ -42,7 +44,8 @@ enum show_feature_header { struct perf_tool { event_sample sample, - read; + read, + callchain_deferred; event_op mmap, mmap2, comm, @@ -77,7 +80,10 @@ struct perf_tool { stat, stat_round, feature, - finished_init; + finished_init, + bpf_metadata, + schedstat_cpu, + schedstat_domain; event_op4 compressed; event_op3 auxtrace; bool ordered_events; @@ -86,6 +92,7 @@ struct perf_tool { bool cgroup_events; bool no_warn; bool dont_split_sample_group; + bool merge_deferred_callchains; enum show_feature_header show_feat_hdr; }; @@ -99,4 +106,13 @@ int process_event_sample_stub(const struct perf_tool *tool, struct evsel *evsel, struct machine *machine); +struct delegate_tool { + /** @tool: The actual tool that calls the delegate. */ + struct perf_tool tool; + /** @delegate: The tool that is delegated to. */ + struct perf_tool *delegate; +}; + +void delegate_tool__init(struct delegate_tool *tool, struct perf_tool *delegate); + #endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c index 4fb097578479..6a9df3dc0e07 100644 --- a/tools/perf/util/tool_pmu.c +++ b/tools/perf/util/tool_pmu.c @@ -6,6 +6,7 @@ #include "pmu.h" #include "print-events.h" #include "smt.h" +#include "stat.h" #include "time-utils.h" #include "tool_pmu.h" #include "tsc.h" @@ -30,6 +31,8 @@ static const char *const tool_pmu__event_names[TOOL_PMU__EVENT_MAX] = { "slots", "smt_on", "system_tsc_freq", + "core_wide", + "target_cpu", }; bool tool_pmu__skip_event(const char *name __maybe_unused) @@ -62,7 +65,8 @@ int tool_pmu__num_skip_events(void) const char *tool_pmu__event_to_str(enum tool_pmu_event ev) { - if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) + if ((ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) && + !tool_pmu__skip_event(tool_pmu__event_names[ev])) return tool_pmu__event_names[ev]; return NULL; @@ -238,9 +242,6 @@ int evsel__tool_pmu_open(struct evsel *evsel, nthreads = perf_thread_map__nr(threads); for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { for (thread = 0; thread < nthreads; thread++) { - if (thread >= nthreads) - break; - if (!evsel->cgrp && !evsel->core.system_wide) pid = perf_thread_map__pid(threads, thread); @@ -331,7 +332,11 @@ static bool has_pmem(void) return has_pmem; } -bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) +bool tool_pmu__read_event(enum tool_pmu_event ev, + struct evsel *evsel, + bool system_wide, + const char *user_requested_cpu_list, + u64 *result) { const struct cpu_topology *topology; @@ -346,17 +351,60 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) return true; case TOOL_PMU__EVENT_NUM_CPUS: - *result = cpu__max_present_cpu().cpu; + if (!evsel || perf_cpu_map__is_empty(evsel->core.cpus)) { + /* No evsel to be specific to. */ + *result = cpu__max_present_cpu().cpu; + } else if (!perf_cpu_map__has_any_cpu(evsel->core.cpus)) { + /* Evsel just has specific CPUs. */ + *result = perf_cpu_map__nr(evsel->core.cpus); + } else { + /* + * "Any CPU" event that can be scheduled on any CPU in + * the PMU's cpumask. The PMU cpumask should be saved in + * pmu_cpus. If not present fall back to max. + */ + if (!perf_cpu_map__is_empty(evsel->core.pmu_cpus)) + *result = perf_cpu_map__nr(evsel->core.pmu_cpus); + else + *result = cpu__max_present_cpu().cpu; + } return true; case TOOL_PMU__EVENT_NUM_CPUS_ONLINE: { struct perf_cpu_map *online = cpu_map__online(); - if (online) { + if (!online) + return false; + + if (!evsel || perf_cpu_map__is_empty(evsel->core.cpus)) { + /* No evsel to be specific to. */ *result = perf_cpu_map__nr(online); - return true; + } else if (!perf_cpu_map__has_any_cpu(evsel->core.cpus)) { + /* Evsel just has specific CPUs. */ + struct perf_cpu_map *tmp = + perf_cpu_map__intersect(online, evsel->core.cpus); + + *result = perf_cpu_map__nr(tmp); + perf_cpu_map__put(tmp); + } else { + /* + * "Any CPU" event that can be scheduled on any CPU in + * the PMU's cpumask. The PMU cpumask should be saved in + * pmu_cpus, if not present then just the online cpu + * mask. + */ + if (!perf_cpu_map__is_empty(evsel->core.pmu_cpus)) { + struct perf_cpu_map *tmp = + perf_cpu_map__intersect(online, evsel->core.pmu_cpus); + + *result = perf_cpu_map__nr(tmp); + perf_cpu_map__put(tmp); + } else { + *result = perf_cpu_map__nr(online); + } } - return false; + perf_cpu_map__put(online); + return true; } case TOOL_PMU__EVENT_NUM_DIES: topology = online_topology(); @@ -380,6 +428,14 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) *result = arch_get_tsc_freq(); return true; + case TOOL_PMU__EVENT_CORE_WIDE: + *result = core_wide(system_wide, user_requested_cpu_list) ? 1 : 0; + return true; + + case TOOL_PMU__EVENT_TARGET_CPU: + *result = system_wide || (user_requested_cpu_list != NULL) ? 1 : 0; + return true; + case TOOL_PMU__EVENT_NONE: case TOOL_PMU__EVENT_DURATION_TIME: case TOOL_PMU__EVENT_USER_TIME: @@ -390,16 +446,39 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) } } +static void perf_counts__update(struct perf_counts_values *count, + const struct perf_counts_values *old_count, + bool raw, u64 val) +{ + /* + * The values of enabled and running must make a ratio of 100%. The + * exact values don't matter as long as they are non-zero to avoid + * issues with evsel__count_has_error. + */ + if (old_count) { + count->val = raw ? val : old_count->val + val; + count->run = old_count->run + 1; + count->ena = old_count->ena + 1; + count->lost = old_count->lost; + } else { + count->val = val; + count->run++; + count->ena++; + count->lost = 0; + } +} + int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) { __u64 *start_time, cur_time, delta_start; - u64 val; - int fd, err = 0; + int err = 0; struct perf_counts_values *count, *old_count = NULL; bool adjust = false; enum tool_pmu_event ev = evsel__tool_event(evsel); count = perf_counts(evsel->counts, cpu_map_idx, thread); + if (evsel->prev_raw_counts) + old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); switch (ev) { case TOOL_PMU__EVENT_HAS_PMEM: @@ -410,26 +489,23 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) case TOOL_PMU__EVENT_NUM_PACKAGES: case TOOL_PMU__EVENT_SLOTS: case TOOL_PMU__EVENT_SMT_ON: - case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ: - if (evsel->prev_raw_counts) - old_count = perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); - val = 0; + case TOOL_PMU__EVENT_CORE_WIDE: + case TOOL_PMU__EVENT_TARGET_CPU: + case TOOL_PMU__EVENT_SYSTEM_TSC_FREQ: { + u64 val = 0; + if (cpu_map_idx == 0 && thread == 0) { - if (!tool_pmu__read_event(ev, &val)) { + if (!tool_pmu__read_event(ev, evsel, + stat_config.system_wide, + stat_config.user_requested_cpu_list, + &val)) { count->lost++; val = 0; } } - if (old_count) { - count->val = old_count->val + val; - count->run = old_count->run + 1; - count->ena = old_count->ena + 1; - } else { - count->val = val; - count->run++; - count->ena++; - } + perf_counts__update(count, old_count, /*raw=*/false, val); return 0; + } case TOOL_PMU__EVENT_DURATION_TIME: /* * Pretend duration_time is only on the first CPU and thread, or @@ -445,9 +521,9 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) case TOOL_PMU__EVENT_USER_TIME: case TOOL_PMU__EVENT_SYSTEM_TIME: { bool system = evsel__tool_event(evsel) == TOOL_PMU__EVENT_SYSTEM_TIME; + int fd = FD(evsel, cpu_map_idx, thread); start_time = xyarray__entry(evsel->start_times, cpu_map_idx, thread); - fd = FD(evsel, cpu_map_idx, thread); lseek(fd, SEEK_SET, 0); if (evsel->pid_stat) { /* The event exists solely on 1 CPU. */ @@ -481,25 +557,23 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) if (adjust) { __u64 ticks_per_sec = sysconf(_SC_CLK_TCK); - delta_start *= 1000000000 / ticks_per_sec; + delta_start *= 1e9 / ticks_per_sec; } - count->val = delta_start; - count->ena = count->run = delta_start; - count->lost = 0; + perf_counts__update(count, old_count, /*raw=*/true, delta_start); return 0; } -struct perf_pmu *perf_pmus__tool_pmu(void) +struct perf_pmu *tool_pmu__new(void) { - static struct perf_pmu tool = { - .name = "tool", - .type = PERF_PMU_TYPE_TOOL, - .aliases = LIST_HEAD_INIT(tool.aliases), - .caps = LIST_HEAD_INIT(tool.caps), - .format = LIST_HEAD_INIT(tool.format), - }; - if (!tool.events_table) - tool.events_table = find_core_events_table("common", "common"); - - return &tool; + struct perf_pmu *tool = zalloc(sizeof(struct perf_pmu)); + + if (!tool) + return NULL; + + if (perf_pmu__init(tool, PERF_PMU_TYPE_TOOL, "tool") != 0) { + perf_pmu__delete(tool); + return NULL; + } + tool->events_table = find_core_events_table("common", "common"); + return tool; } diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h index a60184859080..f1714001bc1d 100644 --- a/tools/perf/util/tool_pmu.h +++ b/tools/perf/util/tool_pmu.h @@ -22,6 +22,8 @@ enum tool_pmu_event { TOOL_PMU__EVENT_SLOTS, TOOL_PMU__EVENT_SMT_ON, TOOL_PMU__EVENT_SYSTEM_TSC_FREQ, + TOOL_PMU__EVENT_CORE_WIDE, + TOOL_PMU__EVENT_TARGET_CPU, TOOL_PMU__EVENT_MAX, }; @@ -34,7 +36,12 @@ enum tool_pmu_event tool_pmu__str_to_event(const char *str); bool tool_pmu__skip_event(const char *name); int tool_pmu__num_skip_events(void); -bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result); +bool tool_pmu__read_event(enum tool_pmu_event ev, + struct evsel *evsel, + bool system_wide, + const char *user_requested_cpu_list, + u64 *result); + u64 tool_pmu__cpu_slots_per_cycle(void); @@ -51,6 +58,6 @@ int evsel__tool_pmu_open(struct evsel *evsel, int start_cpu_map_idx, int end_cpu_map_idx); int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread); -struct perf_pmu *perf_pmus__tool_pmu(void); +struct perf_pmu *tool_pmu__new(void); #endif /* __TOOL_PMU_H */ diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 4db3d1bd686c..b06e10a116bb 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -88,9 +88,9 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) else if (target->tid) ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s", target->tid); - else if (target->uid_str != NULL) + else if (top->uid_str != NULL) ret += SNPRINTF(bf + ret, size - ret, " (uid: %s", - target->uid_str); + top->uid_str); else ret += SNPRINTF(bf + ret, size - ret, " (all"); diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 4c5588dbb131..04ff926846be 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -48,6 +48,7 @@ struct perf_top { const char *sym_filter; float min_percent; unsigned int nr_threads_synthesize; + const char *uid_str; struct { struct ordered_events *in; diff --git a/tools/perf/util/tp_pmu.c b/tools/perf/util/tp_pmu.c new file mode 100644 index 000000000000..c2be8c9f9084 --- /dev/null +++ b/tools/perf/util/tp_pmu.c @@ -0,0 +1,208 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#include "tp_pmu.h" +#include "pmus.h" +#include <api/fs/fs.h> +#include <api/fs/tracing_path.h> +#include <api/io_dir.h> +#include <linux/kernel.h> +#include <errno.h> +#include <string.h> + +int tp_pmu__id(const char *sys, const char *name) +{ + char *tp_dir = get_events_file(sys); + char path[PATH_MAX]; + int id, err; + + if (!tp_dir) + return -1; + + scnprintf(path, PATH_MAX, "%s/%s/id", tp_dir, name); + put_events_file(tp_dir); + err = filename__read_int(path, &id); + if (err) + return err; + + return id; +} + + +int tp_pmu__for_each_tp_event(const char *sys, void *state, tp_event_callback cb) +{ + char *evt_path; + struct io_dirent64 *evt_ent; + struct io_dir evt_dir; + int ret = 0; + + evt_path = get_events_file(sys); + if (!evt_path) + return -errno; + + io_dir__init(&evt_dir, open(evt_path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (evt_dir.dirfd < 0) { + ret = -errno; + put_events_file(evt_path); + return ret; + } + put_events_file(evt_path); + + while (!ret && (evt_ent = io_dir__readdir(&evt_dir))) { + if (!strcmp(evt_ent->d_name, ".") + || !strcmp(evt_ent->d_name, "..") + || !strcmp(evt_ent->d_name, "enable") + || !strcmp(evt_ent->d_name, "filter")) + continue; + + ret = cb(state, sys, evt_ent->d_name); + if (ret) + break; + } + close(evt_dir.dirfd); + return ret; +} + +int tp_pmu__for_each_tp_sys(void *state, tp_sys_callback cb) +{ + struct io_dirent64 *events_ent; + struct io_dir events_dir; + int ret = 0; + char *events_dir_path = get_tracing_file("events"); + + if (!events_dir_path) + return -errno; + + io_dir__init(&events_dir, open(events_dir_path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (events_dir.dirfd < 0) { + ret = -errno; + put_events_file(events_dir_path); + return ret; + } + put_events_file(events_dir_path); + + while (!ret && (events_ent = io_dir__readdir(&events_dir))) { + if (!strcmp(events_ent->d_name, ".") || + !strcmp(events_ent->d_name, "..") || + !strcmp(events_ent->d_name, "enable") || + !strcmp(events_ent->d_name, "header_event") || + !strcmp(events_ent->d_name, "header_page")) + continue; + + ret = cb(state, events_ent->d_name); + } + close(events_dir.dirfd); + return ret; +} + +bool perf_pmu__is_tracepoint(const struct perf_pmu *pmu) +{ + return pmu->type == PERF_TYPE_TRACEPOINT; +} + +struct for_each_event_args { + void *state; + pmu_event_callback cb; + const struct perf_pmu *pmu; +}; + +static int for_each_event_cb(void *state, const char *sys_name, const char *evt_name) +{ + struct for_each_event_args *args = state; + char name[2 * FILENAME_MAX + 2]; + /* 16 possible hex digits and 22 other characters and \0. */ + char encoding[16 + 22]; + char *format = NULL; + size_t format_size; + struct pmu_event_info info = { + .pmu = args->pmu, + .pmu_name = args->pmu->name, + .event_type_desc = "Tracepoint event", + }; + char *tp_dir = get_events_file(sys_name); + char path[PATH_MAX]; + int id, err; + + if (!tp_dir) + return -1; + + scnprintf(path, sizeof(path), "%s/%s/id", tp_dir, evt_name); + err = filename__read_int(path, &id); + if (err == 0) { + snprintf(encoding, sizeof(encoding), "tracepoint/config=0x%x/", id); + info.encoding_desc = encoding; + } + + scnprintf(path, sizeof(path), "%s/%s/format", tp_dir, evt_name); + put_events_file(tp_dir); + err = filename__read_str(path, &format, &format_size); + if (err == 0) { + info.long_desc = format; + for (size_t i = 0 ; i < format_size; i++) { + /* Swap tabs to spaces due to some rendering issues. */ + if (format[i] == '\t') + format[i] = ' '; + } + } + snprintf(name, sizeof(name), "%s:%s", sys_name, evt_name); + info.name = name; + err = args->cb(args->state, &info); + free(format); + return err; +} + +static int for_each_event_sys_cb(void *state, const char *sys_name) +{ + return tp_pmu__for_each_tp_event(sys_name, state, for_each_event_cb); +} + +int tp_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb) +{ + struct for_each_event_args args = { + .state = state, + .cb = cb, + .pmu = pmu, + }; + + return tp_pmu__for_each_tp_sys(&args, for_each_event_sys_cb); +} + +static int num_events_cb(void *state, const char *sys_name __maybe_unused, + const char *evt_name __maybe_unused) +{ + size_t *count = state; + + (*count)++; + return 0; +} + +static int num_events_sys_cb(void *state, const char *sys_name) +{ + return tp_pmu__for_each_tp_event(sys_name, state, num_events_cb); +} + +size_t tp_pmu__num_events(struct perf_pmu *pmu __maybe_unused) +{ + size_t count = 0; + + tp_pmu__for_each_tp_sys(&count, num_events_sys_cb); + return count; +} + +bool tp_pmu__have_event(struct perf_pmu *pmu __maybe_unused, const char *name) +{ + char *dup_name, *colon; + int id; + + colon = strchr((char *)name, ':'); + if (colon == NULL) + return false; + + dup_name = strdup(name); + if (!dup_name) + return false; + + colon = dup_name + (colon - name); + *colon = '\0'; + id = tp_pmu__id(dup_name, colon + 1); + free(dup_name); + return id >= 0; +} diff --git a/tools/perf/util/tp_pmu.h b/tools/perf/util/tp_pmu.h new file mode 100644 index 000000000000..30456bd6943d --- /dev/null +++ b/tools/perf/util/tp_pmu.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __TP_PMU_H +#define __TP_PMU_H + +#include "pmu.h" + +typedef int (*tp_sys_callback)(void *state, const char *sys_name); +typedef int (*tp_event_callback)(void *state, const char *sys_name, const char *evt_name); + +int tp_pmu__id(const char *sys, const char *name); +int tp_pmu__for_each_tp_event(const char *sys, void *state, tp_event_callback cb); +int tp_pmu__for_each_tp_sys(void *state, tp_sys_callback cb); + +bool perf_pmu__is_tracepoint(const struct perf_pmu *pmu); +int tp_pmu__for_each_event(struct perf_pmu *pmu, void *state, pmu_event_callback cb); +size_t tp_pmu__num_events(struct perf_pmu *pmu); +bool tp_pmu__have_event(struct perf_pmu *pmu, const char *name); + +#endif /* __TP_PMU_H */ diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index c8755679281e..45774722f249 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -482,7 +482,7 @@ char *tracepoint_id_to_name(u64 config) static struct tracepoint_path *tracepoint_name_to_path(const char *name) { struct tracepoint_path *path = zalloc(sizeof(*path)); - char *str = strchr(name, ':'); + const char *str = strchr(name, ':'); if (path == NULL || str == NULL) { free(path); diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 4e81e02a4f18..fa850e44cb46 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -13,7 +13,6 @@ #include <event-parse.h> #endif -#include "archinsn.h" #include "debug.h" #include "event.h" #include "trace-event.h" @@ -274,21 +273,6 @@ void setup_perl_scripting(void) #endif #endif -#if !defined(__i386__) && !defined(__x86_64__) -void arch_fetch_insn(struct perf_sample *sample __maybe_unused, - struct thread *thread __maybe_unused, - struct machine *machine __maybe_unused) -{ -} -#endif - -void script_fetch_insn(struct perf_sample *sample, struct thread *thread, - struct machine *machine, bool native_arch) -{ - if (sample->insn_len == 0 && native_arch) - arch_fetch_insn(sample, thread, machine); -} - static const struct { u32 flags; const char *name; @@ -309,53 +293,107 @@ static const struct { {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"}, {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_BRANCH_MISS, "br miss"}, {0, NULL} }; -static const char *sample_flags_to_name(u32 flags) +static const struct { + u32 flags; + const char *name; +} branch_events[] = { + {PERF_IP_FLAG_BRANCH_MISS, "miss"}, + {PERF_IP_FLAG_NOT_TAKEN, "not_taken"}, + {0, NULL} +}; + +static int sample_flags_to_name(u32 flags, char *str, size_t size) { int i; + const char *prefix; + int pos = 0, ret, ev_idx = 0; + u32 xf = flags & PERF_ADDITIONAL_STATE_MASK; + u32 types, events; + char xs[16] = { 0 }; + + /* Clear additional state bits */ + flags &= ~PERF_ADDITIONAL_STATE_MASK; + + if (flags & PERF_IP_FLAG_TRACE_BEGIN) + prefix = "tr strt "; + else if (flags & PERF_IP_FLAG_TRACE_END) + prefix = "tr end "; + else + prefix = ""; + + ret = snprintf(str + pos, size - pos, "%s", prefix); + if (ret < 0) + return ret; + pos += ret; + + flags &= ~(PERF_IP_FLAG_TRACE_BEGIN | PERF_IP_FLAG_TRACE_END); + + types = flags & ~PERF_IP_FLAG_BRANCH_EVENT_MASK; + for (i = 0; sample_flags[i].name; i++) { + if (sample_flags[i].flags != types) + continue; + + ret = snprintf(str + pos, size - pos, "%s", sample_flags[i].name); + if (ret < 0) + return ret; + pos += ret; + break; + } - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == flags) - return sample_flags[i].name; + events = flags & PERF_IP_FLAG_BRANCH_EVENT_MASK; + for (i = 0; branch_events[i].name; i++) { + if (!(branch_events[i].flags & events)) + continue; + + ret = snprintf(str + pos, size - pos, !ev_idx ? "/%s" : ",%s", + branch_events[i].name); + if (ret < 0) + return ret; + pos += ret; + ev_idx++; } - return NULL; + /* Add an end character '/' for events */ + if (ev_idx) { + ret = snprintf(str + pos, size - pos, "/"); + if (ret < 0) + return ret; + pos += ret; + } + + if (!xf) + return pos; + + snprintf(xs, sizeof(xs), "(%s%s%s)", + flags & PERF_IP_FLAG_IN_TX ? "x" : "", + flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", + flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); + + /* Right align the string if its length is less than the limit */ + if ((pos + strlen(xs)) < SAMPLE_FLAGS_STR_ALIGNED_SIZE) + ret = snprintf(str + pos, size - pos, "%*s", + (int)(SAMPLE_FLAGS_STR_ALIGNED_SIZE - ret), xs); + else + ret = snprintf(str + pos, size - pos, " %s", xs); + if (ret < 0) + return ret; + + return pos + ret; } int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) { - u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | - PERF_IP_FLAG_INTR_TOGGLE; const char *chars = PERF_IP_FLAG_CHARS; const size_t n = strlen(PERF_IP_FLAG_CHARS); - const char *name = NULL; size_t i, pos = 0; - char xs[16] = {0}; - - if (flags & xf) - snprintf(xs, sizeof(xs), "(%s%s%s)", - flags & PERF_IP_FLAG_IN_TX ? "x" : "", - flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", - flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); - - name = sample_flags_to_name(flags & ~xf); - if (name) - return snprintf(str, sz, "%-15s%6s", name, xs); - - if (flags & PERF_IP_FLAG_TRACE_BEGIN) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); - if (name) - return snprintf(str, sz, "tr strt %-7s%6s", name, xs); - } + int ret; - if (flags & PERF_IP_FLAG_TRACE_END) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); - if (name) - return snprintf(str, sz, "tr end %-7s%6s", name, xs); - } + ret = sample_flags_to_name(flags, str, sz); + if (ret > 0) + return ret; for (i = 0; i < n; i++, flags >>= 1) { if ((flags & 1) && pos < sz) diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index ac9fde2f980c..914d9b69ed62 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -116,9 +116,6 @@ extern unsigned int scripting_max_stack; struct scripting_ops *script_spec__lookup(const char *spec); int script_spec__for_each(int (*cb)(struct scripting_ops *ops, const char *spec)); -void script_fetch_insn(struct perf_sample *sample, struct thread *thread, - struct machine *machine, bool native_arch); - void setup_perl_scripting(void); void setup_python_scripting(void); @@ -145,6 +142,8 @@ int common_flags(struct scripting_context *context); int common_lock_depth(struct scripting_context *context); #define SAMPLE_FLAGS_BUF_SIZE 64 +#define SAMPLE_FLAGS_STR_ALIGNED_SIZE 21 + int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz); #if defined(LIBTRACEEVENT_VERSION) && LIBTRACEEVENT_VERSION >= MAKE_LIBTRACEEVENT_VERSION(1, 5, 0) diff --git a/tools/perf/util/trace.h b/tools/perf/util/trace.h new file mode 100644 index 000000000000..fbbcfe6f44fe --- /dev/null +++ b/tools/perf/util/trace.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef UTIL_TRACE_H +#define UTIL_TRACE_H + +#include <stdio.h> /* for FILE */ + +enum trace_summary_mode { + SUMMARY__NONE = 0, + SUMMARY__BY_TOTAL, + SUMMARY__BY_THREAD, + SUMMARY__BY_CGROUP, +}; + +#ifdef HAVE_BPF_SKEL + +int trace_prepare_bpf_summary(enum trace_summary_mode mode); +void trace_start_bpf_summary(void); +void trace_end_bpf_summary(void); +int trace_print_bpf_summary(FILE *fp, int max_summary); +void trace_cleanup_bpf_summary(void); + +#else /* !HAVE_BPF_SKEL */ + +static inline int trace_prepare_bpf_summary(enum trace_summary_mode mode __maybe_unused) +{ + return -1; +} +static inline void trace_start_bpf_summary(void) {} +static inline void trace_end_bpf_summary(void) {} +static inline int trace_print_bpf_summary(FILE *fp __maybe_unused, int max_summary __maybe_unused) +{ + return 0; +} +static inline void trace_cleanup_bpf_summary(void) {} + +#endif /* HAVE_BPF_SKEL */ + +#endif /* UTIL_TRACE_H */ diff --git a/tools/perf/util/trace_augment.h b/tools/perf/util/trace_augment.h index 57a3e5045937..4f729bc67753 100644 --- a/tools/perf/util/trace_augment.h +++ b/tools/perf/util/trace_augment.h @@ -1,6 +1,66 @@ #ifndef TRACE_AUGMENT_H #define TRACE_AUGMENT_H -#define TRACE_AUG_MAX_BUF 32 /* for buffer augmentation in perf trace */ +#include <linux/compiler.h> + +struct bpf_program; +struct evlist; + +#ifdef HAVE_BPF_SKEL + +int augmented_syscalls__prepare(void); +int augmented_syscalls__create_bpf_output(struct evlist *evlist); +void augmented_syscalls__setup_bpf_output(void); +int augmented_syscalls__set_filter_pids(unsigned int nr, pid_t *pids); +int augmented_syscalls__get_map_fds(int *enter_fd, int *exit_fd, int *beauty_fd); +struct bpf_program *augmented_syscalls__find_by_title(const char *name); +struct bpf_program *augmented_syscalls__unaugmented(void); +void augmented_syscalls__cleanup(void); + +#else /* !HAVE_BPF_SKEL */ + +static inline int augmented_syscalls__prepare(void) +{ + return -1; +} + +static inline int augmented_syscalls__create_bpf_output(struct evlist *evlist __maybe_unused) +{ + return -1; +} + +static inline void augmented_syscalls__setup_bpf_output(void) +{ +} + +static inline int augmented_syscalls__set_filter_pids(unsigned int nr __maybe_unused, + pid_t *pids __maybe_unused) +{ + return 0; +} + +static inline int augmented_syscalls__get_map_fds(int *enter_fd __maybe_unused, + int *exit_fd __maybe_unused, + int *beauty_fd __maybe_unused) +{ + return -1; +} + +static inline struct bpf_program * +augmented_syscalls__find_by_title(const char *name __maybe_unused) +{ + return NULL; +} + +static inline struct bpf_program *augmented_syscalls__unaugmented(void) +{ + return NULL; +} + +static inline void augmented_syscalls__cleanup(void) +{ +} + +#endif /* HAVE_BPF_SKEL */ #endif diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c index 32c39cfe209b..0bbacf5a29aa 100644 --- a/tools/perf/util/units.c +++ b/tools/perf/util/units.c @@ -12,7 +12,7 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags) struct parse_tag *i = tags; while (i->tag) { - char *s = strchr(str, i->tag); + const char *s = strchr(str, i->tag); if (s) { unsigned long int value; @@ -64,7 +64,7 @@ unsigned long convert_unit(unsigned long value, char *unit) int unit_number__scnprintf(char *buf, size_t size, u64 n) { - char unit[4] = "BKMG"; + char unit[] = "BKMG"; int i = 0; while (((n / 1024) > 1) && (i < 3)) { diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index bde216e630d2..05e8e68bd49c 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -6,6 +6,7 @@ #include <errno.h> #include "debug.h" #include "dso.h" +#include <dwarf-regs.h> #include "unwind.h" #include "unwind-libdw.h" #include "machine.h" @@ -19,6 +20,17 @@ #include "callchain.h" #include "util/env.h" +/* + * The dwfl thread argument passed to functions like memory_read. Memory has to + * be allocated to persist of multiple uses of the dwfl. + */ +struct dwfl_ui_thread_info { + /* Back link to the dwfl. */ + Dwfl *dwfl; + /* The current unwind info, only 1 is supported. */ + struct unwind_info *ui; +}; + static char *debuginfo_path; static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata, @@ -34,6 +46,19 @@ static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata, return -1; } +void libdw__invalidate_dwfl(struct maps *maps, void *arg) +{ + struct dwfl_ui_thread_info *dwfl_ui_ti = arg; + + if (!dwfl_ui_ti) + return; + + assert(dwfl_ui_ti->ui == NULL); + maps__set_libdw_addr_space_dwfl(maps, NULL); + dwfl_end(dwfl_ui_ti->dwfl); + free(dwfl_ui_ti); +} + static const Dwfl_Callbacks offline_callbacks = { .find_debuginfo = __find_debuginfo, .debuginfo_path = &debuginfo_path, @@ -84,8 +109,11 @@ static int __report_module(struct addr_location *al, u64 ip, char filename[PATH_MAX]; __symbol__join_symfs(filename, sizeof(filename), dso__long_name(dso)); - mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1, - base, false); + /* Don't hang up on device files like /dev/dri/renderD128. */ + if (is_regular_file(filename)) { + mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1, + base, false); + } } if (!mod) { char filename[PATH_MAX]; @@ -133,8 +161,8 @@ static int entry(u64 ip, struct unwind_info *ui) } e->ip = ip; - e->ms.maps = al.maps; - e->ms.map = al.map; + e->ms.thread = thread__get(al.thread); + e->ms.map = map__get(al.map); e->ms.sym = al.sym; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", @@ -183,15 +211,18 @@ out_fail: static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result, void *arg) { - struct unwind_info *ui = arg; - const char *arch = perf_env__arch(ui->machine->env); + struct dwfl_ui_thread_info *dwfl_ui_ti = arg; + struct unwind_info *ui = dwfl_ui_ti->ui; struct stack_dump *stack = &ui->sample->user_stack; u64 start, end; int offset; int ret; - ret = perf_reg_value(&start, &ui->sample->user_regs, - perf_arch_reg_sp(arch)); + if (!ui->sample->user_regs) + return false; + + ret = perf_reg_value(&start, ui->sample->user_regs, + perf_arch_reg_sp(ui->e_machine)); if (ret) return false; @@ -219,10 +250,64 @@ static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word * return true; } +static bool libdw_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct dwfl_ui_thread_info *dwfl_ui_ti = arg; + struct unwind_info *ui = dwfl_ui_ti->ui; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); + Dwarf_Word *dwarf_regs; + int max_dwarf_reg = 0; + bool ret; + uint16_t e_machine = ui->e_machine; + int e_flags = ui->e_flags; + uint64_t ip_perf_reg = perf_arch_reg_ip(e_machine); + Dwarf_Word val = 0; + + + /* + * For every possible perf register in the bitmap determine the dwarf + * register and use to compute the max. + */ + for (int perf_reg = 0; perf_reg < 64; perf_reg++) { + if (user_regs->mask & (1ULL << perf_reg)) { + int dwarf_reg = + get_dwarf_regnum_for_perf_regnum(perf_reg, e_machine, + e_flags, + /*only_libdw_supported=*/true); + if (dwarf_reg > max_dwarf_reg) + max_dwarf_reg = dwarf_reg; + } + } + + dwarf_regs = calloc(max_dwarf_reg + 1, sizeof(*dwarf_regs)); + if (!dwarf_regs) + return false; + + for (int perf_reg = 0; perf_reg < 64; perf_reg++) { + if (user_regs->mask & (1ULL << perf_reg)) { + int dwarf_reg = + get_dwarf_regnum_for_perf_regnum(perf_reg, e_machine, + e_flags, + /*only_libdw_supported=*/true); + if (dwarf_reg >= 0) { + val = 0; + if (perf_reg_value(&val, user_regs, perf_reg) == 0) + dwarf_regs[dwarf_reg] = val; + } + } + } + if (perf_reg_value(&val, user_regs, ip_perf_reg) == 0) + dwfl_thread_state_register_pc(thread, val); + + ret = dwfl_thread_state_registers(thread, 0, max_dwarf_reg + 1, dwarf_regs); + free(dwarf_regs); + return ret; +} + static const Dwfl_Thread_Callbacks callbacks = { - .next_thread = next_thread, - .memory_read = memory_read, - .set_initial_registers = libdw__arch_set_initial_registers, + .next_thread = next_thread, + .memory_read = memory_read, + .set_initial_registers = libdw_set_initial_registers, }; static int @@ -260,33 +345,54 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, int max_stack, bool best_effort) { - struct unwind_info *ui, ui_buf = { - .sample = data, - .thread = thread, - .machine = maps__machine((thread__maps(thread))), - .cb = cb, - .arg = arg, - .max_stack = max_stack, - .best_effort = best_effort - }; - const char *arch = perf_env__arch(ui_buf.machine->env); + struct maps *maps = thread__maps(thread); + struct machine *machine = maps__machine(maps); + uint32_t e_flags = 0; + uint16_t e_machine = thread__e_machine(thread, machine, &e_flags); + struct dwfl_ui_thread_info *dwfl_ui_ti; + static struct unwind_info *ui; + Dwfl *dwfl; Dwarf_Word ip; int err = -EINVAL, i; - if (!data->user_regs.regs) + if (!data->user_regs || !data->user_regs->regs) return -EINVAL; - ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack); + ui = zalloc(sizeof(*ui) + sizeof(ui->entries[0]) * max_stack); if (!ui) return -ENOMEM; - *ui = ui_buf; + *ui = (struct unwind_info){ + .sample = data, + .thread = thread, + .machine = machine, + .cb = cb, + .arg = arg, + .max_stack = max_stack, + .e_machine = e_machine, + .e_flags = e_flags, + .best_effort = best_effort + }; - ui->dwfl = dwfl_begin(&offline_callbacks); - if (!ui->dwfl) - goto out; + dwfl_ui_ti = maps__libdw_addr_space_dwfl(maps); + if (dwfl_ui_ti) { + dwfl = dwfl_ui_ti->dwfl; + } else { + dwfl_ui_ti = zalloc(sizeof(*dwfl_ui_ti)); + dwfl = dwfl_begin(&offline_callbacks); + if (!dwfl) + goto out; + + dwfl_ui_ti->dwfl = dwfl; + maps__set_libdw_addr_space_dwfl(maps, dwfl_ui_ti); + } + assert(dwfl_ui_ti->ui == NULL); + assert(dwfl_ui_ti->dwfl == dwfl); + assert(dwfl_ui_ti == maps__libdw_addr_space_dwfl(maps)); + dwfl_ui_ti->ui = ui; + ui->dwfl = dwfl; - err = perf_reg_value(&ip, &data->user_regs, perf_arch_reg_ip(arch)); + err = perf_reg_value(&ip, data->user_regs, perf_arch_reg_ip(e_machine)); if (err) goto out; @@ -294,11 +400,12 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (err) goto out; - err = !dwfl_attach_state(ui->dwfl, EM_NONE, thread__tid(thread), &callbacks, ui); - if (err) - goto out; + dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks, + /* Dwfl thread function argument*/dwfl_ui_ti); + // Ignore thread already attached error. - err = dwfl_getthread_frames(ui->dwfl, thread__tid(thread), frame_callback, ui); + err = dwfl_getthread_frames(dwfl, thread__tid(thread), frame_callback, + /* Dwfl frame function argument*/ui); if (err && ui->max_stack != max_stack) err = 0; @@ -319,7 +426,10 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (err) pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1)); - dwfl_end(ui->dwfl); + for (i = 0; i < ui->idx; i++) + map_symbol__exit(&ui->entries[i].ms); + + dwfl_ui_ti->ui = NULL; free(ui); return 0; } diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 8c88bc4f2304..6423bf5a2492 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -2,17 +2,17 @@ #ifndef __PERF_UNWIND_LIBDW_H #define __PERF_UNWIND_LIBDW_H -#include <elfutils/libdwfl.h> +#include <stdint.h> #include "unwind.h" struct machine; struct perf_sample; struct thread; -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg); +#ifdef HAVE_LIBDW_SUPPORT struct unwind_info { - Dwfl *dwfl; + void *dwfl; struct perf_sample *sample; struct machine *machine; struct thread *thread; @@ -20,8 +20,13 @@ struct unwind_info { void *arg; int max_stack; int idx; + uint32_t e_flags; + uint16_t e_machine; bool best_effort; struct unwind_entry entries[]; }; +void libdw__invalidate_dwfl(struct maps *maps, void *dwfl); +#endif + #endif /* __PERF_UNWIND_LIBDW_H */ diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 16c2b03831f3..87d496e9dfa6 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -25,7 +25,6 @@ #include <unistd.h> #include <sys/mman.h> #include <linux/list.h> -#include <linux/zalloc.h> #ifndef REMOTE_UNWIND_LIBUNWIND #include <libunwind.h> #include <libunwind-ptrace.h> @@ -330,8 +329,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, int ret, fd; if (dso__data(dso)->eh_frame_hdr_offset == 0) { - fd = dso__data_get_fd(dso, ui->machine); - if (fd < 0) + if (!dso__data_get_fd(dso, ui->machine, &fd)) return -EINVAL; /* Check the .eh_frame section for unwinding info */ @@ -372,8 +370,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, * has to be pointed by symsrc_filename */ if (ofs == 0) { - fd = dso__data_get_fd(dso, machine); - if (fd >= 0) { + if (dso__data_get_fd(dso, machine, &fd)) { ofs = elf_section_offset(fd, ".debug_frame"); dso__data_put_fd(dso); } @@ -485,14 +482,16 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, /* Check the .debug_frame section for unwinding info */ if (ret < 0 && !read_unwind_spec_debug_frame(dso, ui->machine, &segbase)) { - int fd = dso__data_get_fd(dso, ui->machine); - int is_exec = elf_is_exec(fd, dso__name(dso)); + int fd; u64 start = map__start(map); - unw_word_t base = is_exec ? 0 : start; + unw_word_t base = start; const char *symfile; - if (fd >= 0) + if (dso__data_get_fd(dso, ui->machine, &fd)) { + if (elf_is_exec(fd, dso__name(dso))) + base = 0; dso__data_put_fd(dso); + } symfile = dso__symsrc_filename(dso) ?: dso__name(dso); @@ -572,20 +571,21 @@ static int access_mem(unw_addr_space_t __maybe_unused as, int __write, void *arg) { struct unwind_info *ui = arg; - const char *arch = perf_env__arch(ui->machine->env); struct stack_dump *stack = &ui->sample->user_stack; u64 start, end; int offset; int ret; /* Don't support write, probably not needed. */ - if (__write || !stack || !ui->sample->user_regs.regs) { + if (__write || !stack || !ui->sample->user_regs || !ui->sample->user_regs->regs) { *valp = 0; return 0; } - ret = perf_reg_value(&start, &ui->sample->user_regs, - perf_arch_reg_sp(arch)); + ret = perf_reg_value(&start, perf_sample__user_regs(ui->sample), + perf_arch_reg_sp(thread__e_machine(ui->thread, + ui->machine, + /*e_flags=*/NULL))); if (ret) return ret; @@ -628,7 +628,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as, return 0; } - if (!ui->sample->user_regs.regs) { + if (!ui->sample->user_regs || !ui->sample->user_regs->regs) { *valp = 0; return 0; } @@ -637,7 +637,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as, if (id < 0) return -EINVAL; - ret = perf_reg_value(&val, &ui->sample->user_regs, id); + ret = perf_reg_value(&val, perf_sample__user_regs(ui->sample), id); if (ret) { if (!ui->best_effort) pr_err("unwind: can't read reg %d\n", regnum); @@ -667,7 +667,7 @@ static int entry(u64 ip, struct thread *thread, e.ms.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); e.ip = ip; e.ms.map = al.map; - e.ms.maps = al.maps; + e.ms.thread = thread__get(al.thread); pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", @@ -734,15 +734,15 @@ static void _unwind__finish_access(struct maps *maps) static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, void *arg, int max_stack) { - const char *arch = perf_env__arch(ui->machine->env); + uint16_t e_machine = thread__e_machine(ui->thread, ui->machine, /*e_flags=*/NULL); u64 val; unw_word_t ips[max_stack]; unw_addr_space_t addr_space; unw_cursor_t c; int ret, i = 0; - ret = perf_reg_value(&val, &ui->sample->user_regs, - perf_arch_reg_ip(arch)); + ret = perf_reg_value(&val, perf_sample__user_regs(ui->sample), + perf_arch_reg_ip(e_machine)); if (ret) return ret; @@ -808,7 +808,7 @@ static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, .best_effort = best_effort }; - if (!data->user_regs.regs) + if (!data->user_regs || !data->user_regs->regs) return -EINVAL; if (max_stack <= 0) diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 0f031eb80b4c..25849434f0a4 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include "perf.h" #include "util.h" #include "debug.h" #include "event.h" @@ -76,8 +77,6 @@ bool sysctl__nmi_watchdog_enabled(void) return nmi_watchdog; } -bool test_attr__enabled; - bool exclude_GH_default; bool perf_host = true; @@ -257,6 +256,54 @@ static int rm_rf_kcore_dir(const char *path) return 0; } +void cpumask_to_cpulist(char *cpumask, char *cpulist) +{ + int i, j, bm_size, nbits; + int len = strlen(cpumask); + unsigned long *bm; + char cpus[MAX_NR_CPUS]; + + for (i = 0; i < len; i++) { + if (cpumask[i] == ',') { + for (j = i; j < len; j++) + cpumask[j] = cpumask[j + 1]; + } + } + + len = strlen(cpumask); + bm_size = (len + 15) / 16; + nbits = bm_size * 64; + if (nbits <= 0) + return; + + bm = calloc(bm_size, sizeof(unsigned long)); + if (!bm) + goto free_bm; + + for (i = 0; i < bm_size; i++) { + char blk[17]; + int blklen = len > 16 ? 16 : len; + + strncpy(blk, cpumask + len - blklen, blklen); + blk[blklen] = '\0'; + bm[i] = strtoul(blk, NULL, 16); + cpumask[len - blklen] = '\0'; + len = strlen(cpumask); + } + + bitmap_scnprintf(bm, nbits, cpus, sizeof(cpus)); + strcpy(cpulist, cpus); + +free_bm: + free(bm); +} + +void print_separator2(int pre_dash_cnt, const char *s, int post_dash_cnt) +{ + printf("%.*s%s%.*s\n", pre_dash_cnt, graph_dotted_line, s, post_dash_cnt, + graph_dotted_line); +} + int rm_rf_perf_data(const char *path) { const char *pat[] = { @@ -498,3 +545,11 @@ int scandirat(int dirfd, const char *dirp, return err; } #endif + +/* basename version that takes a const input string */ +const char *perf_basename(const char *path) +{ + const char *base = strrchr(path, '/'); + + return base ? base + 1 : path; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 3423778e39a5..87a0818a8c76 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -11,6 +11,7 @@ #include <stdbool.h> #include <stddef.h> #include <linux/compiler.h> +#include <linux/bitmap.h> #include <sys/types.h> #ifndef __cplusplus #include <internal/cpumap.h> @@ -29,7 +30,6 @@ extern bool perf_guest; /* General helper functions */ void usage(const char *err) __noreturn; -void die(const char *err, ...) __noreturn __printf(1, 2); struct dirent; struct strlist; @@ -48,6 +48,10 @@ bool sysctl__nmi_watchdog_enabled(void); int perf_tip(char **strp, const char *dirpath); +void cpumask_to_cpulist(char *cpumask, char *cpulist); + +void print_separator2(int pre_dash_cnt, const char *s, int post_dash_cnt); + #ifndef HAVE_SCHED_GETCPU_SUPPORT int sched_getcpu(void); #endif @@ -82,6 +86,8 @@ struct perf_debuginfod { }; void perf_debuginfod_setup(struct perf_debuginfod *di); +const char *perf_basename(const char *path); + char *filename_with_chroot(int pid, const char *filename); int do_realloc_array_as_needed(void **arr, size_t *arr_sz, size_t x, diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index ec72d29f3d58..6eaddfcf833e 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -13,9 +13,9 @@ 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 = zalloc(values->threads_max * sizeof(*values->value)); + values->pid = calloc(values->threads_max, sizeof(*values->pid)); + values->tid = calloc(values->threads_max, sizeof(*values->tid)); + values->value = calloc(values->threads_max, sizeof(*values->value)); if (!values->pid || !values->tid || !values->value) { pr_debug("failed to allocate read_values threads arrays"); goto out_free_pid; @@ -96,7 +96,7 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, i = values->threads; - values->value[i] = zalloc(values->counters_max * sizeof(**values->value)); + values->value[i] = calloc(values->counters_max, sizeof(**values->value)); if (!values->value[i]) { pr_debug("failed to allocate read_values counters array"); return -ENOMEM; diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index 78d2297c1b67..1f7c06523059 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -88,7 +88,7 @@ bool gzip_is_compressed(const char *input) ssize_t rc; if (fd < 0) - return -1; + return false; rc = read(fd, buf, sizeof(buf)); close(fd); |