diff options
Diffstat (limited to 'tools/perf/arch')
103 files changed, 2335 insertions, 5288 deletions
diff --git a/tools/perf/arch/arc/annotate/instructions.c b/tools/perf/arch/arc/annotate/instructions.c deleted file mode 100644 index e5619770a1af..000000000000 --- a/tools/perf/arch/arc/annotate/instructions.c +++ /dev/null @@ -1,11 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/compiler.h> - -static int arc__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - arch->initialized = true; - arch->objdump.comment_char = ';'; - arch->e_machine = EM_ARC; - arch->e_flags = 0; - return 0; -} diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c deleted file mode 100644 index cf91a43362b0..000000000000 --- a/tools/perf/arch/arm/annotate/instructions.c +++ /dev/null @@ -1,65 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/compiler.h> -#include <linux/zalloc.h> -#include <sys/types.h> -#include <regex.h> -#include <stdlib.h> - -struct arm_annotate { - regex_t call_insn, - jump_insn; -}; - -static struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const char *name) -{ - struct arm_annotate *arm = arch->priv; - 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; -} - -static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - struct arm_annotate *arm; - int err; - - if (arch->initialized) - return 0; - - arm = zalloc(sizeof(*arm)); - if (!arm) - return ENOMEM; - -#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 - - arch->initialized = true; - arch->priv = arm; - arch->associate_instruction_ops = arm__associate_instruction_ops; - arch->objdump.comment_char = ';'; - arch->objdump.skip_functions_char = '+'; - arch->e_machine = EM_ARM; - arch->e_flags = 0; - return 0; - -out_free_call: - regfree(&arm->call_insn); -out_free_arm: - free(arm); - return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP; -} diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl index 49eeb2ad8dbd..94351e22bfcf 100644 --- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl @@ -481,3 +481,8 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index 75ce1c370114..20c54766e3a0 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -4,7 +4,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/arm/include/uapi/asm/perf_regs.h" void perf_regs_load(u64 *regs); diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build index f7a8b37d1c68..b94bf3c5279a 100644 --- a/tools/perf/arch/arm/util/Build +++ b/tools/perf/arch/arm/util/Build @@ -1,6 +1,3 @@ -perf-util-y += perf_regs.o - perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o -perf-util-$(CONFIG_AUXTRACE) += pmu.o auxtrace.o cs-etm.o +perf-util-y += pmu.o auxtrace.o cs-etm.o diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 3b8eca0ffb17..eb6404267f17 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -5,6 +5,7 @@ */ #include <dirent.h> +#include <errno.h> #include <stdbool.h> #include <linux/coresight-pmu.h> #include <linux/zalloc.h> diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index ea891d12f8f4..4418d21708d6 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -89,13 +89,14 @@ static int cs_etm_validate_context_id(struct perf_pmu *cs_etm_pmu, struct evsel struct perf_cpu cpu) { int err; - __u64 val; - u64 contextid = evsel->core.attr.config & - (perf_pmu__format_bits(cs_etm_pmu, "contextid") | - perf_pmu__format_bits(cs_etm_pmu, "contextid1") | - perf_pmu__format_bits(cs_etm_pmu, "contextid2")); + u64 ctxt, ctxt1, ctxt2; + __u64 trcidr2; - if (!contextid) + evsel__get_config_val(evsel, "contextid", &ctxt); + evsel__get_config_val(evsel, "contextid1", &ctxt1); + evsel__get_config_val(evsel, "contextid2", &ctxt2); + + if (!ctxt && !ctxt1 && !ctxt2) return 0; /* Not supported in etmv3 */ @@ -106,12 +107,11 @@ static int cs_etm_validate_context_id(struct perf_pmu *cs_etm_pmu, struct evsel } /* Get a handle on TRCIDR2 */ - err = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2], &val); + err = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2], &trcidr2); if (err) return err; - if (contextid & - perf_pmu__format_bits(cs_etm_pmu, "contextid1")) { + if (ctxt1) { /* * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID * tracing is supported: @@ -119,15 +119,14 @@ static int cs_etm_validate_context_id(struct perf_pmu *cs_etm_pmu, struct evsel * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - if (BMVAL(val, 5, 9) != 0x4) { + if (BMVAL(trcidr2, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; } } - if (contextid & - perf_pmu__format_bits(cs_etm_pmu, "contextid2")) { + if (ctxt2) { /* * TRCIDR2.VMIDOPT[30:29] != 0 and * TRCIDR2.VMIDSIZE[14:10] == 0b00100 (32bit virtual contextid) @@ -135,7 +134,7 @@ static int cs_etm_validate_context_id(struct perf_pmu *cs_etm_pmu, struct evsel * virtual context id is < 32bit. * Any value of VMIDSIZE >= 4 (i.e, > 32bit) is fine for us. */ - if (!BMVAL(val, 29, 30) || BMVAL(val, 10, 14) < 4) { + if (!BMVAL(trcidr2, 29, 30) || BMVAL(trcidr2, 10, 14) < 4) { pr_err("%s: CONTEXTIDR_EL2 isn't supported, disable with %s/contextid2=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; @@ -149,10 +148,11 @@ static int cs_etm_validate_timestamp(struct perf_pmu *cs_etm_pmu, struct evsel * struct perf_cpu cpu) { int err; - __u64 val; + u64 val; + __u64 trcidr0; - if (!(evsel->core.attr.config & - perf_pmu__format_bits(cs_etm_pmu, "timestamp"))) + evsel__get_config_val(evsel, "timestamp", &val); + if (!val) return 0; if (cs_etm_get_version(cs_etm_pmu, cpu) == CS_ETMV3) { @@ -162,7 +162,7 @@ static int cs_etm_validate_timestamp(struct perf_pmu *cs_etm_pmu, struct evsel * } /* Get a handle on TRCIRD0 */ - err = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0], &val); + err = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0], &trcidr0); if (err) return err; @@ -173,10 +173,9 @@ static int cs_etm_validate_timestamp(struct perf_pmu *cs_etm_pmu, struct evsel * * 0b00110 Implementation supports a maximum timestamp of 48bits. * 0b01000 Implementation supports a maximum timestamp of 64bits. */ - val &= GENMASK(28, 24); - if (!val) { + trcidr0 &= GENMASK(28, 24); + if (!trcidr0) return -EINVAL; - } return 0; } @@ -259,16 +258,19 @@ static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, return 0; } +/* + * If the sink name format "@sink_name" is used, lookup the sink by name to convert to + * "sinkid=sink_hash" format. If the user has already manually provided a hash then + * "sinkid" isn't overwritten. If neither are provided then the driver will pick the best + * sink. + */ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, struct evsel *evsel) { char msg[BUFSIZ], path[PATH_MAX], *sink; struct evsel_config_term *term; - int ret = -EINVAL; u32 hash; - - if (evsel->core.attr.config2 & GENMASK(31, 0)) - return 0; + int ret; list_for_each_entry(term, &evsel->config_terms, list) { if (term->type != EVSEL__CONFIG_TERM_DRV_CFG) @@ -291,17 +293,26 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, return ret; } - evsel->core.attr.config2 |= hash; + evsel__set_config_if_unset(evsel, "sinkid", hash); return 0; } - /* - * No sink was provided on the command line - allow the CoreSight - * system to look for a default - */ return 0; } +static struct evsel *cs_etm_get_evsel(struct evlist *evlist, + struct perf_pmu *cs_etm_pmu) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.type == cs_etm_pmu->type) + return evsel; + } + + return NULL; +} + static int cs_etm_recording_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) @@ -441,10 +452,8 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * when a context switch happened. */ if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) { - evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, - "timestamp", 1); - evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, - "contextid", 1); + evsel__set_config_if_unset(cs_etm_evsel, "timestamp", 1); + evsel__set_config_if_unset(cs_etm_evsel, "contextid", 1); } /* @@ -453,8 +462,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * timestamp tracing. */ if (opts->sample_time_set) - evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, - "timestamp", 1); + evsel__set_config_if_unset(cs_etm_evsel, "timestamp", 1); /* Add dummy event to keep tracking */ err = parse_event(evlist, "dummy:u"); @@ -474,64 +482,64 @@ out: return err; } -static u64 cs_etm_get_config(struct auxtrace_record *itr) +static u64 cs_etm_synth_etmcr(struct auxtrace_record *itr) { - u64 config = 0; struct cs_etm_recording *ptr = - container_of(itr, struct cs_etm_recording, itr); + container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; - struct evlist *evlist = ptr->evlist; - struct evsel *evsel; + struct evsel *evsel = cs_etm_get_evsel(ptr->evlist, cs_etm_pmu); + u64 etmcr = 0; + u64 val; - evlist__for_each_entry(evlist, evsel) { - if (evsel->core.attr.type == cs_etm_pmu->type) { - /* - * Variable perf_event_attr::config is assigned to - * ETMv3/PTM. The bit fields have been made to match - * the ETMv3.5 ETRMCR register specification. See the - * PMU_FORMAT_ATTR() declarations in - * drivers/hwtracing/coresight/coresight-perf.c for - * details. - */ - config = evsel->core.attr.config; - break; - } - } + if (!evsel) + return 0; - return config; + /* + * Synthesize what the kernel programmed into ETMCR based on + * what options the event was opened with. This doesn't have to be + * complete or 100% accurate, not all bits used by OpenCSD anyway. + */ + if (!evsel__get_config_val(evsel, "cycacc", &val) && val) + etmcr |= ETMCR_CYC_ACC; + if (!evsel__get_config_val(evsel, "timestamp", &val) && val) + etmcr |= ETMCR_TIMESTAMP_EN; + if (!evsel__get_config_val(evsel, "retstack", &val) && val) + etmcr |= ETMCR_RETURN_STACK; + + return etmcr; } -#ifndef BIT -#define BIT(N) (1UL << (N)) -#endif - -static u64 cs_etmv4_get_config(struct auxtrace_record *itr) +static u64 cs_etmv4_synth_trcconfigr(struct auxtrace_record *itr) { - u64 config = 0; - u64 config_opts = 0; + u64 trcconfigr = 0; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + struct evsel *evsel = cs_etm_get_evsel(ptr->evlist, cs_etm_pmu); + u64 val; + + if (!evsel) + return 0; /* - * The perf event variable config bits represent both - * the command line options and register programming - * bits in ETMv3/PTM. For ETMv4 we must remap options - * to real bits + * Synthesize what the kernel programmed into TRCCONFIGR based on + * what options the event was opened with. This doesn't have to be + * complete or 100% accurate, not all bits used by OpenCSD anyway. */ - config_opts = cs_etm_get_config(itr); - if (config_opts & BIT(ETM_OPT_CYCACC)) - config |= BIT(ETM4_CFG_BIT_CYCACC); - if (config_opts & BIT(ETM_OPT_CTXTID)) - config |= BIT(ETM4_CFG_BIT_CTXTID); - if (config_opts & BIT(ETM_OPT_TS)) - config |= BIT(ETM4_CFG_BIT_TS); - if (config_opts & BIT(ETM_OPT_RETSTK)) - config |= BIT(ETM4_CFG_BIT_RETSTK); - if (config_opts & BIT(ETM_OPT_CTXTID2)) - config |= BIT(ETM4_CFG_BIT_VMID) | - BIT(ETM4_CFG_BIT_VMID_OPT); - if (config_opts & BIT(ETM_OPT_BRANCH_BROADCAST)) - config |= BIT(ETM4_CFG_BIT_BB); - - return config; + if (!evsel__get_config_val(evsel, "cycacc", &val) && val) + trcconfigr |= TRCCONFIGR_CCI; + if (!evsel__get_config_val(evsel, "contextid1", &val) && val) + trcconfigr |= TRCCONFIGR_CID; + if (!evsel__get_config_val(evsel, "timestamp", &val) && val) + trcconfigr |= TRCCONFIGR_TS; + if (!evsel__get_config_val(evsel, "retstack", &val) && val) + trcconfigr |= TRCCONFIGR_RS; + if (!evsel__get_config_val(evsel, "contextid2", &val) && val) + trcconfigr |= TRCCONFIGR_VMID | TRCCONFIGR_VMIDOPT; + if (!evsel__get_config_val(evsel, "branch_broadcast", &val) && val) + trcconfigr |= TRCCONFIGR_BB; + + return trcconfigr; } static size_t @@ -653,7 +661,7 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr, struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; /* Get trace configuration register */ - data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr); + data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_synth_trcconfigr(itr); /* traceID set to legacy version, in case new perf running on older system */ data[CS_ETMV4_TRCTRACEIDR] = cs_etm_get_legacy_trace_id(cpu); @@ -685,7 +693,7 @@ static void cs_etm_save_ete_header(__u64 data[], struct auxtrace_record *itr, st struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; /* Get trace configuration register */ - data[CS_ETE_TRCCONFIGR] = cs_etmv4_get_config(itr); + data[CS_ETE_TRCCONFIGR] = cs_etmv4_synth_trcconfigr(itr); /* traceID set to legacy version, in case new perf running on older system */ data[CS_ETE_TRCTRACEIDR] = cs_etm_get_legacy_trace_id(cpu); @@ -741,7 +749,7 @@ static void cs_etm_get_metadata(struct perf_cpu cpu, u32 *offset, case CS_ETMV3: magic = __perf_cs_etmv3_magic; /* Get configuration register */ - info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr); + info->priv[*offset + CS_ETM_ETMCR] = cs_etm_synth_etmcr(itr); /* traceID set to legacy value in case new perf running on old system */ info->priv[*offset + CS_ETM_ETMTRACEIDR] = cs_etm_get_legacy_trace_id(cpu); /* Get read-only information from sysFS */ @@ -832,12 +840,11 @@ static int cs_etm_snapshot_start(struct auxtrace_record *itr) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); - struct evsel *evsel; + struct evsel *evsel = cs_etm_get_evsel(ptr->evlist, ptr->cs_etm_pmu); + + if (evsel) + return evsel__disable(evsel); - evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->core.attr.type == ptr->cs_etm_pmu->type) - return evsel__disable(evsel); - } return -EINVAL; } diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c deleted file mode 100644 index f94a0210c7b7..000000000000 --- a/tools/perf/arch/arm/util/perf_regs.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "perf_regs.h" -#include "../../../util/perf_regs.h" - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG_END -}; - -uint64_t arch__intr_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index f70075c89aa0..9be8da5207f5 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -20,7 +20,6 @@ void perf_pmu__arch_init(struct perf_pmu *pmu) { struct perf_cpu_map *intersect, *online = cpu_map__online(); -#ifdef HAVE_AUXTRACE_SUPPORT if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) { /* add ETM default config here */ pmu->auxtrace = true; @@ -39,7 +38,6 @@ void perf_pmu__arch_init(struct perf_pmu *pmu) pmu->selectable = true; #endif } -#endif /* Workaround some ARM PMU's failing to correctly set CPU maps for online processors. */ intersect = perf_cpu_map__intersect(online, pmu->cpus); perf_cpu_map__put(online); diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c deleted file mode 100644 index fbb643f224ec..000000000000 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ /dev/null @@ -1,39 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <elfutils/libdwfl.h> -#include "perf_regs.h" -#include "../../../util/unwind-libdw.h" -#include "../../../util/perf_regs.h" -#include "../../../util/sample.h" - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[PERF_REG_ARM_MAX]; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_ARM_##r); \ - val; \ -}) - - dwarf_regs[0] = REG(R0); - dwarf_regs[1] = REG(R1); - dwarf_regs[2] = REG(R2); - dwarf_regs[3] = REG(R3); - dwarf_regs[4] = REG(R4); - dwarf_regs[5] = REG(R5); - dwarf_regs[6] = REG(R6); - dwarf_regs[7] = REG(R7); - dwarf_regs[8] = REG(R8); - dwarf_regs[9] = REG(R9); - dwarf_regs[10] = REG(R10); - dwarf_regs[11] = REG(FP); - dwarf_regs[12] = REG(IP); - dwarf_regs[13] = REG(SP); - dwarf_regs[14] = REG(LR); - dwarf_regs[15] = REG(PC); - - return dwfl_thread_state_registers(thread, 0, PERF_REG_ARM_MAX, - dwarf_regs); -} diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 087e099fb453..44cc3f023318 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 -HAVE_KVM_STAT_SUPPORT := 1 diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c deleted file mode 100644 index d465d093e7eb..000000000000 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ /dev/null @@ -1,125 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/compiler.h> -#include <sys/types.h> -#include <regex.h> -#include <stdlib.h> - -struct arm64_annotate { - regex_t call_insn, - jump_insn; -}; - -static int arm64_mov__parse(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 int mov__scnprintf(struct ins *ins, char *bf, size_t size, - struct ins_operands *ops, int max_ins_name); - -static struct ins_ops arm64_mov_ops = { - .parse = arm64_mov__parse, - .scnprintf = mov__scnprintf, -}; - -static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name) -{ - struct arm64_annotate *arm = arch->priv; - 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; -} - -static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - struct arm64_annotate *arm; - int err; - - if (arch->initialized) - return 0; - - arm = zalloc(sizeof(*arm)); - if (!arm) - return ENOMEM; - - /* 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?$", - REG_EXTENDED); - if (err) - goto out_free_call; - - arch->initialized = true; - arch->priv = arm; - arch->associate_instruction_ops = arm64__associate_instruction_ops; - arch->objdump.comment_char = '/'; - arch->objdump.skip_functions_char = '+'; - arch->e_machine = EM_AARCH64; - arch->e_flags = 0; - return 0; - -out_free_call: - regfree(&arm->call_insn); -out_free_arm: - free(arm); - return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP; -} diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h index 58639ee9f7ea..372f2565a9dd 100644 --- a/tools/perf/arch/arm64/include/perf_regs.h +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -5,7 +5,7 @@ #include <stdlib.h> #include <linux/types.h> #define perf_event_arm_regs perf_event_arm64_regs -#include <asm/perf_regs.h> +#include "../../../../arch/arm64/include/uapi/asm/perf_regs.h" #undef perf_event_arm_regs void perf_regs_load(u64 *regs); diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index a74521b79eaa..4e06a08d281a 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -1,13 +1,11 @@ +perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o +perf-util-y += ../../arm/util/auxtrace.o +perf-util-y += ../../arm/util/cs-etm.o +perf-util-y += ../../arm/util/pmu.o +perf-util-y += arm-spe.o perf-util-y += header.o +perf-util-y += hisi-ptt.o perf-util-y += machine.o -perf-util-y += perf_regs.o -perf-util-y += tsc.o +perf-util-y += mem-events.o perf-util-y += pmu.o -perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o -perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o - -perf-util-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ - ../../arm/util/auxtrace.o \ - ../../arm/util/cs-etm.o \ - arm-spe.o mem-events.o hisi-ptt.o +perf-util-y += tsc.o diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 4f2833b62ff5..17ced7bbbdda 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -10,6 +10,7 @@ #include <linux/log2.h> #include <linux/string.h> #include <linux/zalloc.h> +#include <errno.h> #include <time.h> #include "../../../util/cpumap.h" @@ -121,12 +122,17 @@ static int arm_spe_save_cpu_header(struct auxtrace_record *itr, /* No Arm SPE PMU is found */ data[ARM_SPE_CPU_PMU_TYPE] = ULLONG_MAX; data[ARM_SPE_CAP_MIN_IVAL] = 0; + data[ARM_SPE_CAP_EVENT_FILTER] = 0; } else { data[ARM_SPE_CPU_PMU_TYPE] = pmu->type; if (perf_pmu__scan_file(pmu, "caps/min_interval", "%lu", &val) != 1) val = 0; data[ARM_SPE_CAP_MIN_IVAL] = val; + + if (perf_pmu__scan_file(pmu, "caps/event_filter", "%lx", &val) != 1) + val = 0; + data[ARM_SPE_CAP_EVENT_FILTER] = val; } free(cpuid); @@ -250,7 +256,7 @@ static __u64 arm_spe_pmu__sample_period(const struct perf_pmu *arm_spe_pmu) static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus) { - u64 bit; + u64 pa_enable_bit; evsel->core.attr.freq = 0; evsel->core.attr.sample_period = arm_spe_pmu__sample_period(evsel->pmu); @@ -268,7 +274,7 @@ static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus) */ if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) { evsel__set_sample_bit(evsel, CPU); - evsel__set_config_if_unset(evsel->pmu, evsel, "ts_enable", 1); + evsel__set_config_if_unset(evsel, "ts_enable", 1); } /* @@ -282,9 +288,10 @@ static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus) * inform that the resulting output's SPE samples contain physical addresses * where applicable. */ - bit = perf_pmu__format_bits(evsel->pmu, "pa_enable"); - if (evsel->core.attr.config & bit) - evsel__set_sample_bit(evsel, PHYS_ADDR); + + if (!evsel__get_config_val(evsel, "pa_enable", &pa_enable_bit)) + if (pa_enable_bit) + evsel__set_sample_bit(evsel, PHYS_ADDR); } static int arm_spe_setup_aux_buffer(struct record_opts *opts) @@ -391,6 +398,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool discard = false; int err; + u64 discard_bit; sper->evlist = evlist; @@ -419,9 +427,8 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, evlist__for_each_entry_safe(evlist, tmp, evsel) { if (evsel__is_aux_event(evsel)) { arm_spe_setup_evsel(evsel, cpus); - if (evsel->core.attr.config & - perf_pmu__format_bits(evsel->pmu, "discard")) - discard = true; + if (!evsel__get_config_val(evsel, "discard", &discard_bit)) + discard = !!discard_bit; } } diff --git a/tools/perf/arch/arm64/util/arm64_exception_types.h b/tools/perf/arch/arm64/util/arm64_exception_types.h deleted file mode 100644 index 27c981ebe401..000000000000 --- a/tools/perf/arch/arm64/util/arm64_exception_types.h +++ /dev/null @@ -1,92 +0,0 @@ -// 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 */ -/* Unallocated EC: 0x0A - 0x0B */ -#define ESR_ELx_EC_CP14_64 (0x0C) -/* Unallocated EC: 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 - 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) -/* Unallocated EC: 0x27 */ -#define ESR_ELx_EC_FP_EXC32 (0x28) -/* Unallocated EC: 0x29 - 0x2B */ -#define ESR_ELx_EC_FP_EXC64 (0x2C) -/* Unallocated EC: 0x2D - 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/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index f445a2dd6293..cbc0ba101636 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -1,4 +1,3 @@ -#include <linux/kernel.h> #include <linux/bits.h> #include <linux/bitfield.h> #include <stdio.h> diff --git a/tools/perf/arch/arm64/util/hisi-ptt.c b/tools/perf/arch/arm64/util/hisi-ptt.c index eac9739c87e6..fe457fd58c9e 100644 --- a/tools/perf/arch/arm64/util/hisi-ptt.c +++ b/tools/perf/arch/arm64/util/hisi-ptt.c @@ -9,6 +9,7 @@ #include <linux/bitops.h> #include <linux/log2.h> #include <linux/zalloc.h> +#include <errno.h> #include <time.h> #include <internal/lib.h> // page_size diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c deleted file mode 100644 index 6611aa21cba9..000000000000 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ /dev/null @@ -1,84 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <memory.h> -#include "../../../util/evsel.h" -#include "../../../util/kvm-stat.h" -#include "arm64_exception_types.h" -#include "debug.h" - -define_exit_reasons_table(arm64_exit_reasons, kvm_arm_exception_type); -define_exit_reasons_table(arm64_trap_exit_reasons, kvm_arm_exception_class); - -const char *kvm_trap_exit_reason = "esr_ec"; -const char *vcpu_id_str = "id"; -const char *kvm_exit_reason = "ret"; -const char *kvm_entry_trace = "kvm:kvm_entry"; -const char *kvm_exit_trace = "kvm:kvm_exit"; - -const char *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); - 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); -} - -static bool event_end(struct evsel *evsel, - struct perf_sample *sample, - struct event_key *key) -{ - if (evsel__name_is(evsel, kvm_exit_trace)) { - event_get_key(evsel, sample, key); - return true; - } - return false; -} - -static 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" -}; - -struct kvm_reg_events_ops kvm_reg_events_ops[] = { - { - .name = "vmexit", - .ops = &exit_events, - }, - { NULL, NULL }, -}; - -const char * const kvm_skip_events[] = { - NULL, -}; - -int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) -{ - kvm->exit_reasons_isa = "arm64"; - return 0; -} diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index aab1cc2bc283..80fb13c958d9 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -1,18 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include <inttypes.h> -#include <stdio.h> -#include <string.h> -#include "debug.h" -#include "symbol.h" -#include "callchain.h" +#include "callchain.h" // prototype of arch__add_leaf_frame_record_opts #include "perf_regs.h" #include "record.h" -#include "util/perf_regs.h" + +#define SMPL_REG_MASK(b) (1ULL << (b)) void arch__add_leaf_frame_record_opts(struct record_opts *opts) { - const struct sample_reg *sample_reg_masks = arch__sample_reg_masks(); - - opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; + opts->sample_user_regs |= SMPL_REG_MASK(PERF_REG_ARM64_LR); } diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c index 9f8da7937255..eaf00e0609c6 100644 --- a/tools/perf/arch/arm64/util/mem-events.c +++ b/tools/perf/arch/arm64/util/mem-events.c @@ -6,7 +6,7 @@ #define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a } struct perf_mem_event perf_mem_events_arm[PERF_MEM_EVENTS__MAX] = { - E("spe-load", "%s/ts_enable=1,pa_enable=1,load_filter=1,store_filter=0,min_latency=%u/", NULL, true, 0), - E("spe-store", "%s/ts_enable=1,pa_enable=1,load_filter=0,store_filter=1/", NULL, false, 0), + E("spe-load", "%s/ts_enable=1,pa_enable=1,load_filter=1,min_latency=%u/", NULL, true, 0), + E("spe-store", "%s/ts_enable=1,pa_enable=1,store_filter=1/", NULL, false, 0), E("spe-ldst", "%s/ts_enable=1,pa_enable=1,load_filter=1,store_filter=1,min_latency=%u/", NULL, true, 0), }; diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c deleted file mode 100644 index 09308665e28a..000000000000 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ /dev/null @@ -1,182 +0,0 @@ -// 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 "perf_regs.h" -#include "../../../perf-sys.h" -#include "../../../util/debug.h" -#include "../../../util/event.h" -#include "../../../util/perf_regs.h" - -#ifndef HWCAP_SVE -#define HWCAP_SVE (1 << 22) -#endif - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG(x0, PERF_REG_ARM64_X0), - SMPL_REG(x1, PERF_REG_ARM64_X1), - SMPL_REG(x2, PERF_REG_ARM64_X2), - SMPL_REG(x3, PERF_REG_ARM64_X3), - SMPL_REG(x4, PERF_REG_ARM64_X4), - SMPL_REG(x5, PERF_REG_ARM64_X5), - SMPL_REG(x6, PERF_REG_ARM64_X6), - SMPL_REG(x7, PERF_REG_ARM64_X7), - SMPL_REG(x8, PERF_REG_ARM64_X8), - SMPL_REG(x9, PERF_REG_ARM64_X9), - SMPL_REG(x10, PERF_REG_ARM64_X10), - SMPL_REG(x11, PERF_REG_ARM64_X11), - SMPL_REG(x12, PERF_REG_ARM64_X12), - SMPL_REG(x13, PERF_REG_ARM64_X13), - SMPL_REG(x14, PERF_REG_ARM64_X14), - SMPL_REG(x15, PERF_REG_ARM64_X15), - SMPL_REG(x16, PERF_REG_ARM64_X16), - SMPL_REG(x17, PERF_REG_ARM64_X17), - SMPL_REG(x18, PERF_REG_ARM64_X18), - SMPL_REG(x19, PERF_REG_ARM64_X19), - SMPL_REG(x20, PERF_REG_ARM64_X20), - SMPL_REG(x21, PERF_REG_ARM64_X21), - SMPL_REG(x22, PERF_REG_ARM64_X22), - SMPL_REG(x23, PERF_REG_ARM64_X23), - SMPL_REG(x24, PERF_REG_ARM64_X24), - SMPL_REG(x25, PERF_REG_ARM64_X25), - SMPL_REG(x26, PERF_REG_ARM64_X26), - SMPL_REG(x27, PERF_REG_ARM64_X27), - SMPL_REG(x28, PERF_REG_ARM64_X28), - SMPL_REG(x29, PERF_REG_ARM64_X29), - SMPL_REG(lr, PERF_REG_ARM64_LR), - SMPL_REG(sp, PERF_REG_ARM64_SP), - SMPL_REG(pc, PERF_REG_ARM64_PC), - SMPL_REG(vg, PERF_REG_ARM64_VG), - SMPL_REG_END -}; - -/* %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 arch_sdt_arg_parse_op(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 arch__intr_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - 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 (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. - */ - if (attr.sample_regs_user != PERF_REGS_MASK) { - event_attr_init(&attr); - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - if (fd != -1) { - close(fd); - return attr.sample_regs_user; - } - } - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c deleted file mode 100644 index b89b0a7e5ad9..000000000000 --- a/tools/perf/arch/arm64/util/unwind-libdw.c +++ /dev/null @@ -1,61 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <elfutils/libdwfl.h> -#include "perf_regs.h" -#include "../../../util/unwind-libdw.h" -#include "../../../util/perf_regs.h" -#include "../../../util/sample.h" - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX], dwarf_pc; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_ARM64_##r); \ - val; \ -}) - - dwarf_regs[0] = REG(X0); - dwarf_regs[1] = REG(X1); - dwarf_regs[2] = REG(X2); - dwarf_regs[3] = REG(X3); - dwarf_regs[4] = REG(X4); - dwarf_regs[5] = REG(X5); - dwarf_regs[6] = REG(X6); - dwarf_regs[7] = REG(X7); - dwarf_regs[8] = REG(X8); - dwarf_regs[9] = REG(X9); - dwarf_regs[10] = REG(X10); - dwarf_regs[11] = REG(X11); - dwarf_regs[12] = REG(X12); - dwarf_regs[13] = REG(X13); - dwarf_regs[14] = REG(X14); - dwarf_regs[15] = REG(X15); - dwarf_regs[16] = REG(X16); - dwarf_regs[17] = REG(X17); - dwarf_regs[18] = REG(X18); - dwarf_regs[19] = REG(X19); - dwarf_regs[20] = REG(X20); - dwarf_regs[21] = REG(X21); - dwarf_regs[22] = REG(X22); - dwarf_regs[23] = REG(X23); - dwarf_regs[24] = REG(X24); - dwarf_regs[25] = REG(X25); - dwarf_regs[26] = REG(X26); - dwarf_regs[27] = REG(X27); - dwarf_regs[28] = REG(X28); - dwarf_regs[29] = REG(X29); - dwarf_regs[30] = REG(LR); - dwarf_regs[31] = REG(SP); - - if (!dwfl_thread_state_registers(thread, 0, PERF_REG_ARM64_MAX, - dwarf_regs)) - return false; - - dwarf_pc = REG(PC); - dwfl_thread_state_register_pc(thread, dwarf_pc); - - return true; -} diff --git a/tools/perf/arch/csky/Build b/tools/perf/arch/csky/Build deleted file mode 100644 index e63eabc2c8f4..000000000000 --- a/tools/perf/arch/csky/Build +++ /dev/null @@ -1 +0,0 @@ -perf-util-y += util/ diff --git a/tools/perf/arch/csky/annotate/instructions.c b/tools/perf/arch/csky/annotate/instructions.c deleted file mode 100644 index 14270311d215..000000000000 --- a/tools/perf/arch/csky/annotate/instructions.c +++ /dev/null @@ -1,53 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. - -#include <linux/compiler.h> - -static struct ins_ops *csky__associate_ins_ops(struct arch *arch, - const char *name) -{ - 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; -} - -static int csky__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - arch->initialized = true; - arch->objdump.comment_char = '/'; - arch->associate_instruction_ops = csky__associate_ins_ops; - arch->e_machine = EM_CSKY; -#if defined(__CSKYABIV2__) - arch->e_flags = EF_CSKY_ABIV2; -#else - arch->e_flags = EF_CSKY_ABIV1; -#endif - return 0; -} diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h index 076c7746c8a2..0bf7b963909c 100644 --- a/tools/perf/arch/csky/include/perf_regs.h +++ b/tools/perf/arch/csky/include/perf_regs.h @@ -6,7 +6,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/csky/include/uapi/asm/perf_regs.h" #define PERF_REGS_MASK ((1ULL << PERF_REG_CSKY_MAX) - 1) #define PERF_REGS_MAX PERF_REG_CSKY_MAX diff --git a/tools/perf/arch/csky/util/Build b/tools/perf/arch/csky/util/Build deleted file mode 100644 index 5e6ea82c4202..000000000000 --- a/tools/perf/arch/csky/util/Build +++ /dev/null @@ -1,3 +0,0 @@ -perf-util-y += perf_regs.o - -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/csky/util/perf_regs.c b/tools/perf/arch/csky/util/perf_regs.c deleted file mode 100644 index 6b1665f41180..000000000000 --- a/tools/perf/arch/csky/util/perf_regs.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "perf_regs.h" -#include "../../util/perf_regs.h" - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG_END -}; - -uint64_t arch__intr_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/csky/util/unwind-libdw.c b/tools/perf/arch/csky/util/unwind-libdw.c deleted file mode 100644 index b20b1569783d..000000000000 --- a/tools/perf/arch/csky/util/unwind-libdw.c +++ /dev/null @@ -1,78 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. - -#include <elfutils/libdwfl.h> -#include "perf_regs.h" -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/event.h" - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[PERF_REG_CSKY_MAX]; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_CSKY_##r); \ - val; \ -}) - -#if defined(__CSKYABIV2__) - dwarf_regs[0] = REG(A0); - dwarf_regs[1] = REG(A1); - dwarf_regs[2] = REG(A2); - dwarf_regs[3] = REG(A3); - dwarf_regs[4] = REG(REGS0); - dwarf_regs[5] = REG(REGS1); - dwarf_regs[6] = REG(REGS2); - dwarf_regs[7] = REG(REGS3); - dwarf_regs[8] = REG(REGS4); - dwarf_regs[9] = REG(REGS5); - dwarf_regs[10] = REG(REGS6); - dwarf_regs[11] = REG(REGS7); - dwarf_regs[12] = REG(REGS8); - dwarf_regs[13] = REG(REGS9); - dwarf_regs[14] = REG(SP); - dwarf_regs[15] = REG(LR); - dwarf_regs[16] = REG(EXREGS0); - dwarf_regs[17] = REG(EXREGS1); - dwarf_regs[18] = REG(EXREGS2); - dwarf_regs[19] = REG(EXREGS3); - dwarf_regs[20] = REG(EXREGS4); - dwarf_regs[21] = REG(EXREGS5); - dwarf_regs[22] = REG(EXREGS6); - dwarf_regs[23] = REG(EXREGS7); - dwarf_regs[24] = REG(EXREGS8); - dwarf_regs[25] = REG(EXREGS9); - dwarf_regs[26] = REG(EXREGS10); - dwarf_regs[27] = REG(EXREGS11); - dwarf_regs[28] = REG(EXREGS12); - dwarf_regs[29] = REG(EXREGS13); - dwarf_regs[30] = REG(EXREGS14); - dwarf_regs[31] = REG(TLS); - dwarf_regs[32] = REG(PC); -#else - dwarf_regs[0] = REG(SP); - dwarf_regs[1] = REG(REGS9); - dwarf_regs[2] = REG(A0); - dwarf_regs[3] = REG(A1); - dwarf_regs[4] = REG(A2); - dwarf_regs[5] = REG(A3); - dwarf_regs[6] = REG(REGS0); - dwarf_regs[7] = REG(REGS1); - dwarf_regs[8] = REG(REGS2); - dwarf_regs[9] = REG(REGS3); - dwarf_regs[10] = REG(REGS4); - dwarf_regs[11] = REG(REGS5); - dwarf_regs[12] = REG(REGS6); - dwarf_regs[13] = REG(REGS7); - dwarf_regs[14] = REG(REGS8); - dwarf_regs[15] = REG(LR); -#endif - dwfl_thread_state_register_pc(thread, REG(PC)); - - return dwfl_thread_state_registers(thread, 0, PERF_REG_CSKY_MAX, - dwarf_regs); -} diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile index 087e099fb453..44cc3f023318 100644 --- a/tools/perf/arch/loongarch/Makefile +++ b/tools/perf/arch/loongarch/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 -HAVE_KVM_STAT_SUPPORT := 1 diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c deleted file mode 100644 index 70262d5f1444..000000000000 --- a/tools/perf/arch/loongarch/annotate/instructions.c +++ /dev/null @@ -1,139 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Perf annotate functions. - * - * Copyright (C) 2020-2023 Loongson Technology Corporation Limited - */ - -static int loongarch_call__parse(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 = { - .ms = { .map = map, }, - }; - - 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.addr = map__objdump_2mem(map, ops->target.addr); - - if (maps__find_ams(ms->maps, &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; - - return 0; -} - -static struct ins_ops loongarch_call_ops = { - .parse = loongarch_call__parse, - .scnprintf = call__scnprintf, -}; - -static int loongarch_jump__parse(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, }, - }; - 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(ms->maps, &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; - } - - return 0; -} - -static struct ins_ops loongarch_jump_ops = { - .parse = loongarch_jump__parse, - .scnprintf = jump__scnprintf, -}; - -static -struct ins_ops *loongarch__associate_ins_ops(struct arch *arch, const char *name) -{ - 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; -} - -static -int loongarch__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - if (!arch->initialized) { - arch->associate_instruction_ops = loongarch__associate_ins_ops; - arch->initialized = true; - arch->objdump.comment_char = '#'; - arch->e_machine = EM_LOONGARCH; - arch->e_flags = 0; - } - - return 0; -} diff --git a/tools/perf/arch/loongarch/include/perf_regs.h b/tools/perf/arch/loongarch/include/perf_regs.h index 45c799fa5330..b86078a55e90 100644 --- a/tools/perf/arch/loongarch/include/perf_regs.h +++ b/tools/perf/arch/loongarch/include/perf_regs.h @@ -4,7 +4,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/loongarch/include/uapi/asm/perf_regs.h" #define PERF_REGS_MAX PERF_REG_LOONGARCH_MAX diff --git a/tools/perf/arch/loongarch/util/Build b/tools/perf/arch/loongarch/util/Build index 0aa31986ecb5..3ad73d0289f3 100644 --- a/tools/perf/arch/loongarch/util/Build +++ b/tools/perf/arch/loongarch/util/Build @@ -1,6 +1,4 @@ perf-util-y += header.o -perf-util-y += perf_regs.o perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o -perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o diff --git a/tools/perf/arch/loongarch/util/kvm-stat.c b/tools/perf/arch/loongarch/util/kvm-stat.c deleted file mode 100644 index a7859a3a9a51..000000000000 --- a/tools/perf/arch/loongarch/util/kvm-stat.c +++ /dev/null @@ -1,139 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <memory.h> -#include "util/kvm-stat.h" -#include "util/parse-events.h" -#include "util/debug.h" -#include "util/evsel.h" -#include "util/evlist.h" -#include "util/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); - -const char *vcpu_id_str = "vcpu_id"; -const char *kvm_exit_reason = "reason"; -const char *kvm_entry_trace = "kvm:kvm_enter"; -const char *kvm_reenter_trace = "kvm:kvm_reenter"; -const char *kvm_exit_trace = "kvm:kvm_exit"; -const char *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) || 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 struct child_event_ops child_events[] = { - { .name = "kvm:kvm_exit_gspr", .get_key = event_gspr_get_key }, - { NULL, NULL }, -}; - -static 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" -}; - -struct kvm_reg_events_ops kvm_reg_events_ops[] = { - { .name = "vmexit", .ops = &exit_events, }, - { NULL, NULL }, -}; - -const char * const kvm_skip_events[] = { - NULL, -}; - -int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) -{ - kvm->exit_reasons_isa = "loongarch64"; - kvm->exit_reasons = loongarch_exit_reasons; - return 0; -} diff --git a/tools/perf/arch/loongarch/util/perf_regs.c b/tools/perf/arch/loongarch/util/perf_regs.c deleted file mode 100644 index f94a0210c7b7..000000000000 --- a/tools/perf/arch/loongarch/util/perf_regs.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "perf_regs.h" -#include "../../../util/perf_regs.h" - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG_END -}; - -uint64_t arch__intr_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/loongarch/util/unwind-libdw.c b/tools/perf/arch/loongarch/util/unwind-libdw.c deleted file mode 100644 index 60b1144bedd5..000000000000 --- a/tools/perf/arch/loongarch/util/unwind-libdw.c +++ /dev/null @@ -1,57 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2020-2023 Loongson Technology Corporation Limited */ - -#include <elfutils/libdwfl.h> -#include "perf_regs.h" -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/sample.h" - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[PERF_REG_LOONGARCH_MAX]; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_LOONGARCH_##r); \ - val; \ -}) - - dwarf_regs[0] = 0; - dwarf_regs[1] = REG(R1); - dwarf_regs[2] = REG(R2); - dwarf_regs[3] = REG(R3); - dwarf_regs[4] = REG(R4); - dwarf_regs[5] = REG(R5); - dwarf_regs[6] = REG(R6); - dwarf_regs[7] = REG(R7); - dwarf_regs[8] = REG(R8); - dwarf_regs[9] = REG(R9); - dwarf_regs[10] = REG(R10); - dwarf_regs[11] = REG(R11); - dwarf_regs[12] = REG(R12); - dwarf_regs[13] = REG(R13); - dwarf_regs[14] = REG(R14); - dwarf_regs[15] = REG(R15); - dwarf_regs[16] = REG(R16); - dwarf_regs[17] = REG(R17); - dwarf_regs[18] = REG(R18); - dwarf_regs[19] = REG(R19); - dwarf_regs[20] = REG(R20); - dwarf_regs[21] = REG(R21); - dwarf_regs[22] = REG(R22); - dwarf_regs[23] = REG(R23); - dwarf_regs[24] = REG(R24); - dwarf_regs[25] = REG(R25); - dwarf_regs[26] = REG(R26); - dwarf_regs[27] = REG(R27); - dwarf_regs[28] = REG(R28); - dwarf_regs[29] = REG(R29); - dwarf_regs[30] = REG(R30); - dwarf_regs[31] = REG(R31); - dwfl_thread_state_register_pc(thread, REG(PC)); - - return dwfl_thread_state_registers(thread, 0, PERF_REG_LOONGARCH_MAX, dwarf_regs); -} diff --git a/tools/perf/arch/mips/annotate/instructions.c b/tools/perf/arch/mips/annotate/instructions.c deleted file mode 100644 index b50b46c613d6..000000000000 --- a/tools/perf/arch/mips/annotate/instructions.c +++ /dev/null @@ -1,48 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -static -struct ins_ops *mips__associate_ins_ops(struct arch *arch, const char *name) -{ - 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; -} - -static -int mips__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - if (!arch->initialized) { - arch->associate_instruction_ops = mips__associate_ins_ops; - arch->initialized = true; - arch->objdump.comment_char = '#'; - arch->e_machine = EM_MIPS; - arch->e_flags = 0; - } - - return 0; -} diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index c844cd5cda62..630aab9e5425 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -381,3 +381,8 @@ 464 n64 getxattrat sys_getxattrat 465 n64 listxattrat sys_listxattrat 466 n64 removexattrat sys_removexattrat +467 n64 open_tree_attr sys_open_tree_attr +468 n64 file_getattr sys_file_getattr +469 n64 file_setattr sys_file_setattr +470 n64 listns sys_listns +471 n64 rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h index 7082e91e0ed1..66655f0c4fea 100644 --- a/tools/perf/arch/mips/include/perf_regs.h +++ b/tools/perf/arch/mips/include/perf_regs.h @@ -4,7 +4,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/mips/include/uapi/asm/perf_regs.h" #define PERF_REGS_MAX PERF_REG_MIPS_MAX diff --git a/tools/perf/arch/mips/util/Build b/tools/perf/arch/mips/util/Build index 691fa2051958..818b808a8247 100644 --- a/tools/perf/arch/mips/util/Build +++ b/tools/perf/arch/mips/util/Build @@ -1,2 +1 @@ -perf-util-y += perf_regs.o perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o diff --git a/tools/perf/arch/mips/util/perf_regs.c b/tools/perf/arch/mips/util/perf_regs.c deleted file mode 100644 index 6b1665f41180..000000000000 --- a/tools/perf/arch/mips/util/perf_regs.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "perf_regs.h" -#include "../../util/perf_regs.h" - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG_END -}; - -uint64_t arch__intr_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index a295a80ea078..44cc3f023318 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c deleted file mode 100644 index ca567cfdcbdb..000000000000 --- a/tools/perf/arch/powerpc/annotate/instructions.c +++ /dev/null @@ -1,317 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/compiler.h> - -static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, const char *name) -{ - int i; - 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; -} - -#define PPC_OP(op) (((op) >> 26) & 0x3F) -#define PPC_21_30(R) (((R) >> 1) & 0x3ff) -#define PPC_22_30(R) (((R) >> 1) & 0x1ff) - -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); -} - -static 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 */ - -static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - if (!arch->initialized) { - arch->initialized = true; - arch->associate_instruction_ops = powerpc__associate_instruction_ops; - arch->objdump.comment_char = '#'; - annotate_opts.show_asm_raw = true; - arch->e_machine = EM_PPC; - arch->e_flags = 0; - } - - return 0; -} diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index d8b4ab78bef0..4fcc7c58a105 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -557,3 +557,8 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 nospu rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 1c66f6ba6773..22b492a3dd58 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -4,7 +4,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/powerpc/include/uapi/asm/perf_regs.h" void perf_regs_load(u64 *regs); diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index ed82715080f9..d66574cbb9a9 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,13 +1,10 @@ perf-util-y += header.o -perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o -perf-util-y += perf_regs.o perf-util-y += mem-events.o perf-util-y += pmu.o perf-util-y += sym-handling.o perf-util-y += evsel.o -perf-util-y += event.o perf-util-$(CONFIG_LIBDW) += skip-callchain-idx.o perf-util-$(CONFIG_LIBUNWIND) += unwind-libunwind.o -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o +perf-util-y += auxtrace.o diff --git a/tools/perf/arch/powerpc/util/auxtrace.c b/tools/perf/arch/powerpc/util/auxtrace.c new file mode 100644 index 000000000000..292ea335e4ff --- /dev/null +++ b/tools/perf/arch/powerpc/util/auxtrace.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * VPA support + */ +#include <errno.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/string.h> + +#include "../../util/evlist.h" +#include "../../util/debug.h" +#include "../../util/auxtrace.h" +#include "../../util/powerpc-vpadtl.h" +#include "../../util/record.h" +#include <internal/lib.h> // page_size + +#define KiB(x) ((x) * 1024) + +static int +powerpc_vpadtl_recording_options(struct auxtrace_record *ar __maybe_unused, + struct evlist *evlist __maybe_unused, + struct record_opts *opts) +{ + opts->full_auxtrace = true; + + /* + * Set auxtrace_mmap_pages to minimum + * two pages + */ + if (!opts->auxtrace_mmap_pages) { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + + return 0; +} + +static size_t powerpc_vpadtl_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct evlist *evlist __maybe_unused) +{ + return VPADTL_AUXTRACE_PRIV_SIZE; +} + +static int +powerpc_vpadtl_info_fill(struct auxtrace_record *itr __maybe_unused, + struct perf_session *session __maybe_unused, + struct perf_record_auxtrace_info *auxtrace_info, + size_t priv_size __maybe_unused) +{ + auxtrace_info->type = PERF_AUXTRACE_VPA_DTL; + + return 0; +} + +static void powerpc_vpadtl_free(struct auxtrace_record *itr) +{ + free(itr); +} + +static u64 powerpc_vpadtl_reference(struct auxtrace_record *itr __maybe_unused) +{ + return 0; +} + +struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, + int *err) +{ + struct auxtrace_record *aux; + struct evsel *pos; + int found = 0; + + evlist__for_each_entry(evlist, pos) { + if (strstarts(pos->name, "vpa_dtl")) { + found = 1; + pos->needs_auxtrace_mmap = true; + break; + } + } + + if (!found) + return NULL; + + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace event + * must come first. + */ + evlist__to_front(pos->evlist, pos); + + aux = zalloc(sizeof(*aux)); + if (aux == NULL) { + pr_debug("aux record is NULL\n"); + *err = -ENOMEM; + return NULL; + } + + aux->recording_options = powerpc_vpadtl_recording_options; + aux->info_priv_size = powerpc_vpadtl_info_priv_size; + aux->info_fill = powerpc_vpadtl_info_fill; + aux->free = powerpc_vpadtl_free; + aux->reference = powerpc_vpadtl_reference; + return aux; +} diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h deleted file mode 100644 index 488f4339b83c..000000000000 --- a/tools/perf/arch/powerpc/util/book3s_hcalls.h +++ /dev/null @@ -1,124 +0,0 @@ -/* 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/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h deleted file mode 100644 index 2011376c7ab5..000000000000 --- a/tools/perf/arch/powerpc/util/book3s_hv_exits.h +++ /dev/null @@ -1,33 +0,0 @@ -/* 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/arch/powerpc/util/event.c b/tools/perf/arch/powerpc/util/event.c deleted file mode 100644 index 77d8cc2b5691..000000000000 --- a/tools/perf/arch/powerpc/util/event.c +++ /dev/null @@ -1,60 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/types.h> -#include <linux/string.h> -#include <linux/zalloc.h> - -#include "../../../util/event.h" -#include "../../../util/synthetic-events.h" -#include "../../../util/machine.h" -#include "../../../util/tool.h" -#include "../../../util/map.h" -#include "../../../util/debug.h" -#include "../../../util/sample.h" - -void arch_perf_parse_sample_weight(struct perf_sample *data, - const __u64 *array, u64 type) -{ - union perf_sample_weight weight; - - weight.full = *array; - if (type & PERF_SAMPLE_WEIGHT) - data->weight = weight.full; - else { - data->weight = weight.var1_dw; - data->ins_lat = weight.var2_w; - data->p_stage_cyc = weight.var3_w; - } -} - -void arch_perf_synthesize_sample_weight(const struct perf_sample *data, - __u64 *array, u64 type) -{ - *array = data->weight; - - if (type & PERF_SAMPLE_WEIGHT_STRUCT) { - *array &= 0xffffffff; - *array |= ((u64)data->ins_lat << 32); - } -} - -const char *arch_perf_header_entry(const char *se_header) -{ - 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; -} - -int arch_support_sort_key(const char *sort_key) -{ - if (!strcmp(sort_key, "p_stage_cyc")) - return 1; - if (!strcmp(sort_key, "local_p_stage_cyc")) - return 1; - return 0; -} diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c deleted file mode 100644 index c8357b571ccf..000000000000 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ /dev/null @@ -1,219 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include "util/kvm-stat.h" -#include "util/parse-events.h" -#include "util/debug.h" -#include "util/evsel.h" -#include "util/evlist.h" -#include "util/pmus.h" - -#include "book3s_hv_exits.h" -#include "book3s_hcalls.h" -#include <subcmd/parse-options.h> - -#define NR_TPS 4 - -const char *vcpu_id_str = "vcpu_id"; -const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter"; -const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit"; - -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 */ -const char *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 */ -const char *kvm_events_tp[NR_TPS + 1]; -const char *kvm_exit_reason; - -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 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 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" -}; - -struct kvm_reg_events_ops kvm_reg_events_ops[] = { - { .name = "vmexit", .ops = &exit_events }, - { .name = "hcall", .ops = &hcall_events }, - { NULL, NULL }, -}; - -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 **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_reason = "trap"; - 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(struct perf_kvm_stat *kvm) -{ - return ppc__setup_kvm_tp(kvm); -} - -int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) -{ - 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(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; -} diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c deleted file mode 100644 index bd36cfd420a2..000000000000 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ /dev/null @@ -1,240 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <string.h> -#include <regex.h> -#include <linux/zalloc.h> - -#include "perf_regs.h" -#include "../../../util/perf_regs.h" -#include "../../../util/debug.h" -#include "../../../util/event.h" -#include "../../../util/header.h" -#include "../../../perf-sys.h" -#include "utils_header.h" - -#include <linux/kernel.h> - -#define PVR_POWER9 0x004E -#define PVR_POWER10 0x0080 -#define PVR_POWER11 0x0082 - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG(r0, PERF_REG_POWERPC_R0), - SMPL_REG(r1, PERF_REG_POWERPC_R1), - SMPL_REG(r2, PERF_REG_POWERPC_R2), - SMPL_REG(r3, PERF_REG_POWERPC_R3), - SMPL_REG(r4, PERF_REG_POWERPC_R4), - SMPL_REG(r5, PERF_REG_POWERPC_R5), - SMPL_REG(r6, PERF_REG_POWERPC_R6), - SMPL_REG(r7, PERF_REG_POWERPC_R7), - SMPL_REG(r8, PERF_REG_POWERPC_R8), - SMPL_REG(r9, PERF_REG_POWERPC_R9), - SMPL_REG(r10, PERF_REG_POWERPC_R10), - SMPL_REG(r11, PERF_REG_POWERPC_R11), - SMPL_REG(r12, PERF_REG_POWERPC_R12), - SMPL_REG(r13, PERF_REG_POWERPC_R13), - SMPL_REG(r14, PERF_REG_POWERPC_R14), - SMPL_REG(r15, PERF_REG_POWERPC_R15), - SMPL_REG(r16, PERF_REG_POWERPC_R16), - SMPL_REG(r17, PERF_REG_POWERPC_R17), - SMPL_REG(r18, PERF_REG_POWERPC_R18), - SMPL_REG(r19, PERF_REG_POWERPC_R19), - SMPL_REG(r20, PERF_REG_POWERPC_R20), - SMPL_REG(r21, PERF_REG_POWERPC_R21), - SMPL_REG(r22, PERF_REG_POWERPC_R22), - SMPL_REG(r23, PERF_REG_POWERPC_R23), - SMPL_REG(r24, PERF_REG_POWERPC_R24), - SMPL_REG(r25, PERF_REG_POWERPC_R25), - SMPL_REG(r26, PERF_REG_POWERPC_R26), - SMPL_REG(r27, PERF_REG_POWERPC_R27), - SMPL_REG(r28, PERF_REG_POWERPC_R28), - SMPL_REG(r29, PERF_REG_POWERPC_R29), - SMPL_REG(r30, PERF_REG_POWERPC_R30), - SMPL_REG(r31, PERF_REG_POWERPC_R31), - SMPL_REG(nip, PERF_REG_POWERPC_NIP), - SMPL_REG(msr, PERF_REG_POWERPC_MSR), - SMPL_REG(orig_r3, PERF_REG_POWERPC_ORIG_R3), - SMPL_REG(ctr, PERF_REG_POWERPC_CTR), - SMPL_REG(link, PERF_REG_POWERPC_LINK), - SMPL_REG(xer, PERF_REG_POWERPC_XER), - SMPL_REG(ccr, PERF_REG_POWERPC_CCR), - SMPL_REG(softe, PERF_REG_POWERPC_SOFTE), - SMPL_REG(trap, PERF_REG_POWERPC_TRAP), - SMPL_REG(dar, PERF_REG_POWERPC_DAR), - SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR), - SMPL_REG(sier, PERF_REG_POWERPC_SIER), - SMPL_REG(mmcra, PERF_REG_POWERPC_MMCRA), - SMPL_REG(mmcr0, PERF_REG_POWERPC_MMCR0), - SMPL_REG(mmcr1, PERF_REG_POWERPC_MMCR1), - SMPL_REG(mmcr2, PERF_REG_POWERPC_MMCR2), - SMPL_REG(mmcr3, PERF_REG_POWERPC_MMCR3), - SMPL_REG(sier2, PERF_REG_POWERPC_SIER2), - SMPL_REG(sier3, PERF_REG_POWERPC_SIER3), - SMPL_REG(pmc1, PERF_REG_POWERPC_PMC1), - SMPL_REG(pmc2, PERF_REG_POWERPC_PMC2), - SMPL_REG(pmc3, PERF_REG_POWERPC_PMC3), - SMPL_REG(pmc4, PERF_REG_POWERPC_PMC4), - SMPL_REG(pmc5, PERF_REG_POWERPC_PMC5), - SMPL_REG(pmc6, PERF_REG_POWERPC_PMC6), - SMPL_REG(sdar, PERF_REG_POWERPC_SDAR), - SMPL_REG(siar, PERF_REG_POWERPC_SIAR), - SMPL_REG_END -}; - -/* 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 arch_sdt_arg_parse_op(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; -} - -uint64_t arch__intr_reg_mask(void) -{ - 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; - - /* - * 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. - */ - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - if (fd != -1) { - close(fd); - mask |= extended_mask; - } - return mask; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 356786432fd3..e57f10798fa6 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -30,14 +30,6 @@ * The libdwfl code in this file is based on code from elfutils * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc). */ -static char *debuginfo_path; - -static const Dwfl_Callbacks offline_callbacks = { - .debuginfo_path = &debuginfo_path, - .find_debuginfo = dwfl_standard_find_debuginfo, - .section_address = dwfl_offline_section_address, -}; - /* * Use the DWARF expression for the Call-frame-address and determine @@ -149,44 +141,22 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) * yet used) * -1 in case of errors */ -static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) +static int check_return_addr(struct dso *dso, Dwarf_Addr mapped_pc) { int rc = -1; Dwfl *dwfl; Dwfl_Module *mod; Dwarf_Frame *frame; int ra_regno; - Dwarf_Addr start = pc; - Dwarf_Addr end = pc; + Dwarf_Addr start = mapped_pc; + Dwarf_Addr end = mapped_pc; bool signalp; - const char *exec_file = dso__long_name(dso); - - dwfl = RC_CHK_ACCESS(dso)->dwfl; - - if (!dwfl) { - dwfl = dwfl_begin(&offline_callbacks); - if (!dwfl) { - pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1)); - return -1; - } - - mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1, - map_start, false); - if (!mod) { - pr_debug("dwfl_report_elf() failed %s\n", - dwarf_errmsg(-1)); - /* - * We normally cache the DWARF debug info and never - * call dwfl_end(). But to prevent fd leak, free in - * case of error. - */ - dwfl_end(dwfl); - goto out; - } - RC_CHK_ACCESS(dso)->dwfl = dwfl; - } - mod = dwfl_addrmodule(dwfl, pc); + dwfl = dso__libdw_dwfl(dso); + if (!dwfl) + return -1; + + mod = dwfl_addrmodule(dwfl, mapped_pc); if (!mod) { pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1)); goto out; @@ -196,9 +166,9 @@ static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) * To work with split debug info files (eg: glibc), check both * .eh_frame and .debug_frame sections of the ELF header. */ - frame = get_eh_frame(mod, pc); + frame = get_eh_frame(mod, mapped_pc); if (!frame) { - frame = get_dwarf_frame(mod, pc); + frame = get_dwarf_frame(mod, mapped_pc); if (!frame) goto out; } @@ -264,7 +234,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) return skip_slot; } - rc = check_return_addr(dso, map__start(al.map), ip); + rc = check_return_addr(dso, map__map_ip(al.map, ip)); pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n", dso__long_name(dso), al.sym->name, ip, rc); diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c deleted file mode 100644 index 82d0c28ae345..000000000000 --- a/tools/perf/arch/powerpc/util/unwind-libdw.c +++ /dev/null @@ -1,76 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <elfutils/libdwfl.h> -#include <linux/kernel.h> -#include "perf_regs.h" -#include "../../../util/unwind-libdw.h" -#include "../../../util/perf_regs.h" -#include "../../../util/sample.h" - -/* See backends/ppc_initreg.c and backends/ppc_regs.c in elfutils. */ -static const int special_regs[3][2] = { - { 65, PERF_REG_POWERPC_LINK }, - { 101, PERF_REG_POWERPC_XER }, - { 109, PERF_REG_POWERPC_CTR }, -}; - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[32], dwarf_nip; - size_t i; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_POWERPC_##r); \ - val; \ -}) - - dwarf_regs[0] = REG(R0); - dwarf_regs[1] = REG(R1); - dwarf_regs[2] = REG(R2); - dwarf_regs[3] = REG(R3); - dwarf_regs[4] = REG(R4); - dwarf_regs[5] = REG(R5); - dwarf_regs[6] = REG(R6); - dwarf_regs[7] = REG(R7); - dwarf_regs[8] = REG(R8); - dwarf_regs[9] = REG(R9); - dwarf_regs[10] = REG(R10); - dwarf_regs[11] = REG(R11); - dwarf_regs[12] = REG(R12); - dwarf_regs[13] = REG(R13); - dwarf_regs[14] = REG(R14); - dwarf_regs[15] = REG(R15); - dwarf_regs[16] = REG(R16); - dwarf_regs[17] = REG(R17); - dwarf_regs[18] = REG(R18); - dwarf_regs[19] = REG(R19); - dwarf_regs[20] = REG(R20); - dwarf_regs[21] = REG(R21); - dwarf_regs[22] = REG(R22); - dwarf_regs[23] = REG(R23); - dwarf_regs[24] = REG(R24); - dwarf_regs[25] = REG(R25); - dwarf_regs[26] = REG(R26); - dwarf_regs[27] = REG(R27); - dwarf_regs[28] = REG(R28); - dwarf_regs[29] = REG(R29); - dwarf_regs[30] = REG(R30); - dwarf_regs[31] = REG(R31); - if (!dwfl_thread_state_registers(thread, 0, 32, dwarf_regs)) - return false; - - dwarf_nip = REG(NIP); - dwfl_thread_state_register_pc(thread, dwarf_nip); - for (i = 0; i < ARRAY_SIZE(special_regs); i++) { - Dwarf_Word val = 0; - perf_reg_value(&val, user_regs, special_regs[i][1]); - if (!dwfl_thread_state_registers(thread, - special_regs[i][0], 1, - &val)) - return false; - } - - return true; -} diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile index 087e099fb453..44cc3f023318 100644 --- a/tools/perf/arch/riscv/Makefile +++ b/tools/perf/arch/riscv/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 -HAVE_KVM_STAT_SUPPORT := 1 diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h index d482edb413e5..af7a1b47bf66 100644 --- a/tools/perf/arch/riscv/include/perf_regs.h +++ b/tools/perf/arch/riscv/include/perf_regs.h @@ -6,14 +6,19 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/riscv/include/uapi/asm/perf_regs.h" #define PERF_REGS_MASK ((1ULL << PERF_REG_RISCV_MAX) - 1) #define PERF_REGS_MAX PERF_REG_RISCV_MAX + +#if defined(__riscv_xlen) #if __riscv_xlen == 64 -#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 #else #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 #endif +#else +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_NONE +#endif #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/riscv/util/Build b/tools/perf/arch/riscv/util/Build index 58a672246024..2328fb9a30a3 100644 --- a/tools/perf/arch/riscv/util/Build +++ b/tools/perf/arch/riscv/util/Build @@ -1,5 +1 @@ -perf-util-y += perf_regs.o perf-util-y += header.o - -perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/riscv/util/kvm-stat.c b/tools/perf/arch/riscv/util/kvm-stat.c deleted file mode 100644 index 491aef449d1a..000000000000 --- a/tools/perf/arch/riscv/util/kvm-stat.c +++ /dev/null @@ -1,78 +0,0 @@ -// 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 "../../../util/evsel.h" -#include "../../../util/kvm-stat.h" -#include "riscv_exception_types.h" -#include "debug.h" - -define_exit_reasons_table(riscv_exit_reasons, kvm_riscv_exception_class); - -const char *vcpu_id_str = "id"; -const char *kvm_exit_reason = "scause"; -const char *kvm_entry_trace = "kvm:kvm_entry"; -const char *kvm_exit_trace = "kvm:kvm_exit"; - -const char *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); - 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); -} - -static bool event_end(struct evsel *evsel, - struct perf_sample *sample, - struct event_key *key) -{ - if (evsel__name_is(evsel, kvm_exit_trace)) { - event_get_key(evsel, sample, key); - return true; - } - return false; -} - -static 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" -}; - -struct kvm_reg_events_ops kvm_reg_events_ops[] = { - { - .name = "vmexit", - .ops = &exit_events, - }, - { NULL, NULL }, -}; - -const char * const kvm_skip_events[] = { - NULL, -}; - -int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) -{ - kvm->exit_reasons_isa = "riscv64"; - return 0; -} diff --git a/tools/perf/arch/riscv/util/perf_regs.c b/tools/perf/arch/riscv/util/perf_regs.c deleted file mode 100644 index 6b1665f41180..000000000000 --- a/tools/perf/arch/riscv/util/perf_regs.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "perf_regs.h" -#include "../../util/perf_regs.h" - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG_END -}; - -uint64_t arch__intr_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/riscv/util/riscv_exception_types.h b/tools/perf/arch/riscv/util/riscv_exception_types.h deleted file mode 100644 index c49b8fa5e847..000000000000 --- a/tools/perf/arch/riscv/util/riscv_exception_types.h +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#ifndef ARCH_PERF_RISCV_EXCEPTION_TYPES_H -#define ARCH_PERF_RISCV_EXCEPTION_TYPES_H - -#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 EXC(x) {EXC_##x, #x } - -#define kvm_riscv_exception_class \ - EXC(INST_MISALIGNED), EXC(INST_ACCESS), EXC(INST_ILLEGAL), \ - EXC(BREAKPOINT), EXC(LOAD_MISALIGNED), EXC(LOAD_ACCESS), \ - EXC(STORE_MISALIGNED), EXC(STORE_ACCESS), EXC(SYSCALL), \ - EXC(HYPERVISOR_SYSCALL), EXC(SUPERVISOR_SYSCALL), \ - EXC(INST_PAGE_FAULT), EXC(LOAD_PAGE_FAULT), EXC(STORE_PAGE_FAULT), \ - EXC(INST_GUEST_PAGE_FAULT), EXC(LOAD_GUEST_PAGE_FAULT), \ - EXC(VIRTUAL_INST_FAULT), EXC(STORE_GUEST_PAGE_FAULT) - -#endif /* ARCH_PERF_RISCV_EXCEPTION_TYPES_H */ diff --git a/tools/perf/arch/riscv/util/unwind-libdw.c b/tools/perf/arch/riscv/util/unwind-libdw.c deleted file mode 100644 index dc1476e16321..000000000000 --- a/tools/perf/arch/riscv/util/unwind-libdw.c +++ /dev/null @@ -1,58 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */ - -#include <elfutils/libdwfl.h> -#include "perf_regs.h" -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/sample.h" - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[32]; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_RISCV_##r); \ - val; \ -}) - - dwarf_regs[0] = 0; - dwarf_regs[1] = REG(RA); - dwarf_regs[2] = REG(SP); - dwarf_regs[3] = REG(GP); - dwarf_regs[4] = REG(TP); - dwarf_regs[5] = REG(T0); - dwarf_regs[6] = REG(T1); - dwarf_regs[7] = REG(T2); - dwarf_regs[8] = REG(S0); - dwarf_regs[9] = REG(S1); - dwarf_regs[10] = REG(A0); - dwarf_regs[11] = REG(A1); - dwarf_regs[12] = REG(A2); - dwarf_regs[13] = REG(A3); - dwarf_regs[14] = REG(A4); - dwarf_regs[15] = REG(A5); - dwarf_regs[16] = REG(A6); - dwarf_regs[17] = REG(A7); - dwarf_regs[18] = REG(S2); - dwarf_regs[19] = REG(S3); - dwarf_regs[20] = REG(S4); - dwarf_regs[21] = REG(S5); - dwarf_regs[22] = REG(S6); - dwarf_regs[23] = REG(S7); - dwarf_regs[24] = REG(S8); - dwarf_regs[25] = REG(S9); - dwarf_regs[26] = REG(S10); - dwarf_regs[27] = REG(S11); - dwarf_regs[28] = REG(T3); - dwarf_regs[29] = REG(T4); - dwarf_regs[30] = REG(T5); - dwarf_regs[31] = REG(T6); - dwfl_thread_state_register_pc(thread, REG(PC)); - - return dwfl_thread_state_registers(thread, 0, PERF_REG_RISCV_MAX, - dwarf_regs); -} diff --git a/tools/perf/arch/riscv64/annotate/instructions.c b/tools/perf/arch/riscv64/annotate/instructions.c deleted file mode 100644 index 55cf911633f8..000000000000 --- a/tools/perf/arch/riscv64/annotate/instructions.c +++ /dev/null @@ -1,36 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -static -struct ins_ops *riscv64__associate_ins_ops(struct arch *arch, const char *name) -{ - 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; -} - -static -int riscv64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - if (!arch->initialized) { - arch->associate_instruction_ops = riscv64__associate_ins_ops; - arch->initialized = true; - arch->objdump.comment_char = '#'; - arch->e_machine = EM_RISCV; - arch->e_flags = 0; - } - - return 0; -} diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 0033698a65ce..8b59ce8efb89 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c deleted file mode 100644 index c61193f1e096..000000000000 --- a/tools/perf/arch/s390/annotate/instructions.c +++ /dev/null @@ -1,174 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/compiler.h> - -static int s390_call__parse(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, }, - }; - - 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.addr = map__objdump_2mem(map, ops->target.addr); - - if (maps__find_ams(ms->maps, &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; - - return 0; -} - -static struct ins_ops s390_call_ops = { - .parse = s390_call__parse, - .scnprintf = call__scnprintf, -}; - -static int s390_mov__parse(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 struct ins_ops s390_mov_ops = { - .parse = s390_mov__parse, - .scnprintf = mov__scnprintf, -}; - -static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name) -{ - 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, 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; -} - -static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - int err = 0; - - if (!arch->initialized) { - arch->initialized = true; - arch->associate_instruction_ops = s390__associate_ins_ops; - if (cpuid) { - if (s390__cpuid_parse(arch, cpuid)) - err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING; - } - arch->e_machine = EM_S390; - arch->e_flags = 0; - } - - return err; -} diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index e9115b4d8b63..09a7ef04d979 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -3,469 +3,398 @@ # System call table for s390 # # Format: +# <nr> <abi> <syscall> <entry> # -# <nr> <abi> <syscall> <entry-64bit> <compat-entry> -# -# where <abi> can be common, 64, or 32 +# <abi> is always common. -1 common exit sys_exit sys_exit -2 common fork sys_fork sys_fork -3 common read sys_read compat_sys_s390_read -4 common write sys_write compat_sys_s390_write -5 common open sys_open compat_sys_open -6 common close sys_close sys_close -7 common restart_syscall sys_restart_syscall sys_restart_syscall -8 common creat sys_creat sys_creat -9 common link sys_link sys_link -10 common unlink sys_unlink sys_unlink -11 common execve sys_execve compat_sys_execve -12 common chdir sys_chdir sys_chdir -13 32 time - sys_time32 -14 common mknod sys_mknod sys_mknod -15 common chmod sys_chmod sys_chmod -16 32 lchown - sys_lchown16 -19 common lseek sys_lseek compat_sys_lseek -20 common getpid sys_getpid sys_getpid -21 common mount sys_mount sys_mount -22 common umount sys_oldumount sys_oldumount -23 32 setuid - sys_setuid16 -24 32 getuid - sys_getuid16 -25 32 stime - sys_stime32 -26 common ptrace sys_ptrace compat_sys_ptrace -27 common alarm sys_alarm sys_alarm -29 common pause sys_pause sys_pause -30 common utime sys_utime sys_utime32 -33 common access sys_access sys_access -34 common nice sys_nice sys_nice -36 common sync sys_sync sys_sync -37 common kill sys_kill sys_kill -38 common rename sys_rename sys_rename -39 common mkdir sys_mkdir sys_mkdir -40 common rmdir sys_rmdir sys_rmdir -41 common dup sys_dup sys_dup -42 common pipe sys_pipe sys_pipe -43 common times sys_times compat_sys_times -45 common brk sys_brk sys_brk -46 32 setgid - sys_setgid16 -47 32 getgid - sys_getgid16 -48 common signal sys_signal sys_signal -49 32 geteuid - sys_geteuid16 -50 32 getegid - sys_getegid16 -51 common acct sys_acct sys_acct -52 common umount2 sys_umount sys_umount -54 common ioctl sys_ioctl compat_sys_ioctl -55 common fcntl sys_fcntl compat_sys_fcntl -57 common setpgid sys_setpgid sys_setpgid -60 common umask sys_umask sys_umask -61 common chroot sys_chroot sys_chroot -62 common ustat sys_ustat compat_sys_ustat -63 common dup2 sys_dup2 sys_dup2 -64 common getppid sys_getppid sys_getppid -65 common getpgrp sys_getpgrp sys_getpgrp -66 common setsid sys_setsid sys_setsid -67 common sigaction sys_sigaction compat_sys_sigaction -70 32 setreuid - sys_setreuid16 -71 32 setregid - sys_setregid16 -72 common sigsuspend sys_sigsuspend sys_sigsuspend -73 common sigpending sys_sigpending compat_sys_sigpending -74 common sethostname sys_sethostname sys_sethostname -75 common setrlimit sys_setrlimit compat_sys_setrlimit -76 32 getrlimit - compat_sys_old_getrlimit -77 common getrusage sys_getrusage compat_sys_getrusage -78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday -79 common settimeofday sys_settimeofday compat_sys_settimeofday -80 32 getgroups - sys_getgroups16 -81 32 setgroups - sys_setgroups16 -83 common symlink sys_symlink sys_symlink -85 common readlink sys_readlink sys_readlink -86 common uselib sys_uselib sys_uselib -87 common swapon sys_swapon sys_swapon -88 common reboot sys_reboot sys_reboot -89 common readdir - compat_sys_old_readdir -90 common mmap sys_old_mmap compat_sys_s390_old_mmap -91 common munmap sys_munmap sys_munmap -92 common truncate sys_truncate compat_sys_truncate -93 common ftruncate sys_ftruncate compat_sys_ftruncate -94 common fchmod sys_fchmod sys_fchmod -95 32 fchown - sys_fchown16 -96 common getpriority sys_getpriority sys_getpriority -97 common setpriority sys_setpriority sys_setpriority -99 common statfs sys_statfs compat_sys_statfs -100 common fstatfs sys_fstatfs compat_sys_fstatfs -101 32 ioperm - - -102 common socketcall sys_socketcall compat_sys_socketcall -103 common syslog sys_syslog sys_syslog -104 common setitimer sys_setitimer compat_sys_setitimer -105 common getitimer sys_getitimer compat_sys_getitimer -106 common stat sys_newstat compat_sys_newstat -107 common lstat sys_newlstat compat_sys_newlstat -108 common fstat sys_newfstat compat_sys_newfstat -110 common lookup_dcookie - - -111 common vhangup sys_vhangup sys_vhangup -112 common idle - - -114 common wait4 sys_wait4 compat_sys_wait4 -115 common swapoff sys_swapoff sys_swapoff -116 common sysinfo sys_sysinfo compat_sys_sysinfo -117 common ipc sys_s390_ipc compat_sys_s390_ipc -118 common fsync sys_fsync sys_fsync -119 common sigreturn sys_sigreturn compat_sys_sigreturn -120 common clone sys_clone sys_clone -121 common setdomainname sys_setdomainname sys_setdomainname -122 common uname sys_newuname sys_newuname -124 common adjtimex sys_adjtimex sys_adjtimex_time32 -125 common mprotect sys_mprotect sys_mprotect -126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask -127 common create_module - - -128 common init_module sys_init_module sys_init_module -129 common delete_module sys_delete_module sys_delete_module -130 common get_kernel_syms - - -131 common quotactl sys_quotactl sys_quotactl -132 common getpgid sys_getpgid sys_getpgid -133 common fchdir sys_fchdir sys_fchdir -134 common bdflush sys_ni_syscall sys_ni_syscall -135 common sysfs sys_sysfs sys_sysfs -136 common personality sys_s390_personality sys_s390_personality -137 common afs_syscall - - -138 32 setfsuid - sys_setfsuid16 -139 32 setfsgid - sys_setfsgid16 -140 32 _llseek - sys_llseek -141 common getdents sys_getdents compat_sys_getdents -142 32 _newselect - compat_sys_select -142 64 select sys_select - -143 common flock sys_flock sys_flock -144 common msync sys_msync sys_msync -145 common readv sys_readv sys_readv -146 common writev sys_writev sys_writev -147 common getsid sys_getsid sys_getsid -148 common fdatasync sys_fdatasync sys_fdatasync -149 common _sysctl - - -150 common mlock sys_mlock sys_mlock -151 common munlock sys_munlock sys_munlock -152 common mlockall sys_mlockall sys_mlockall -153 common munlockall sys_munlockall sys_munlockall -154 common sched_setparam sys_sched_setparam sys_sched_setparam -155 common sched_getparam sys_sched_getparam sys_sched_getparam -156 common sched_setscheduler sys_sched_setscheduler sys_sched_setscheduler -157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler -158 common sched_yield sys_sched_yield sys_sched_yield -159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max -160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 -162 common nanosleep sys_nanosleep sys_nanosleep_time32 -163 common mremap sys_mremap sys_mremap -164 32 setresuid - sys_setresuid16 -165 32 getresuid - sys_getresuid16 -167 common query_module - - -168 common poll sys_poll sys_poll -169 common nfsservctl - - -170 32 setresgid - sys_setresgid16 -171 32 getresgid - sys_getresgid16 -172 common prctl sys_prctl sys_prctl -173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn -174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction -175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask -176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 -178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo -179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -180 common pread64 sys_pread64 compat_sys_s390_pread64 -181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 -182 32 chown - sys_chown16 -183 common getcwd sys_getcwd sys_getcwd -184 common capget sys_capget sys_capget -185 common capset sys_capset sys_capset -186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack -187 common sendfile sys_sendfile64 compat_sys_sendfile -188 common getpmsg - - -189 common putpmsg - - -190 common vfork sys_vfork sys_vfork -191 32 ugetrlimit - compat_sys_getrlimit -191 64 getrlimit sys_getrlimit - -192 32 mmap2 - compat_sys_s390_mmap2 -193 32 truncate64 - compat_sys_s390_truncate64 -194 32 ftruncate64 - compat_sys_s390_ftruncate64 -195 32 stat64 - compat_sys_s390_stat64 -196 32 lstat64 - compat_sys_s390_lstat64 -197 32 fstat64 - compat_sys_s390_fstat64 -198 32 lchown32 - sys_lchown -198 64 lchown sys_lchown - -199 32 getuid32 - sys_getuid -199 64 getuid sys_getuid - -200 32 getgid32 - sys_getgid -200 64 getgid sys_getgid - -201 32 geteuid32 - sys_geteuid -201 64 geteuid sys_geteuid - -202 32 getegid32 - sys_getegid -202 64 getegid sys_getegid - -203 32 setreuid32 - sys_setreuid -203 64 setreuid sys_setreuid - -204 32 setregid32 - sys_setregid -204 64 setregid sys_setregid - -205 32 getgroups32 - sys_getgroups -205 64 getgroups sys_getgroups - -206 32 setgroups32 - sys_setgroups -206 64 setgroups sys_setgroups - -207 32 fchown32 - sys_fchown -207 64 fchown sys_fchown - -208 32 setresuid32 - sys_setresuid -208 64 setresuid sys_setresuid - -209 32 getresuid32 - sys_getresuid -209 64 getresuid sys_getresuid - -210 32 setresgid32 - sys_setresgid -210 64 setresgid sys_setresgid - -211 32 getresgid32 - sys_getresgid -211 64 getresgid sys_getresgid - -212 32 chown32 - sys_chown -212 64 chown sys_chown - -213 32 setuid32 - sys_setuid -213 64 setuid sys_setuid - -214 32 setgid32 - sys_setgid -214 64 setgid sys_setgid - -215 32 setfsuid32 - sys_setfsuid -215 64 setfsuid sys_setfsuid - -216 32 setfsgid32 - sys_setfsgid -216 64 setfsgid sys_setfsgid - -217 common pivot_root sys_pivot_root sys_pivot_root -218 common mincore sys_mincore sys_mincore -219 common madvise sys_madvise sys_madvise -220 common getdents64 sys_getdents64 sys_getdents64 -221 32 fcntl64 - compat_sys_fcntl64 -222 common readahead sys_readahead compat_sys_s390_readahead -223 32 sendfile64 - compat_sys_sendfile64 -224 common setxattr sys_setxattr sys_setxattr -225 common lsetxattr sys_lsetxattr sys_lsetxattr -226 common fsetxattr sys_fsetxattr sys_fsetxattr -227 common getxattr sys_getxattr sys_getxattr -228 common lgetxattr sys_lgetxattr sys_lgetxattr -229 common fgetxattr sys_fgetxattr sys_fgetxattr -230 common listxattr sys_listxattr sys_listxattr -231 common llistxattr sys_llistxattr sys_llistxattr -232 common flistxattr sys_flistxattr sys_flistxattr -233 common removexattr sys_removexattr sys_removexattr -234 common lremovexattr sys_lremovexattr sys_lremovexattr -235 common fremovexattr sys_fremovexattr sys_fremovexattr -236 common gettid sys_gettid sys_gettid -237 common tkill sys_tkill sys_tkill -238 common futex sys_futex sys_futex_time32 -239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity -240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity -241 common tgkill sys_tgkill sys_tgkill -243 common io_setup sys_io_setup compat_sys_io_setup -244 common io_destroy sys_io_destroy sys_io_destroy -245 common io_getevents sys_io_getevents sys_io_getevents_time32 -246 common io_submit sys_io_submit compat_sys_io_submit -247 common io_cancel sys_io_cancel sys_io_cancel -248 common exit_group sys_exit_group sys_exit_group -249 common epoll_create sys_epoll_create sys_epoll_create -250 common epoll_ctl sys_epoll_ctl sys_epoll_ctl -251 common epoll_wait sys_epoll_wait sys_epoll_wait -252 common set_tid_address sys_set_tid_address sys_set_tid_address -253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 -254 common timer_create sys_timer_create compat_sys_timer_create -255 common timer_settime sys_timer_settime sys_timer_settime32 -256 common timer_gettime sys_timer_gettime sys_timer_gettime32 -257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun -258 common timer_delete sys_timer_delete sys_timer_delete -259 common clock_settime sys_clock_settime sys_clock_settime32 -260 common clock_gettime sys_clock_gettime sys_clock_gettime32 -261 common clock_getres sys_clock_getres sys_clock_getres_time32 -262 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 -264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 -265 common statfs64 sys_statfs64 compat_sys_statfs64 -266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages -268 common mbind sys_mbind sys_mbind -269 common get_mempolicy sys_get_mempolicy sys_get_mempolicy -270 common set_mempolicy sys_set_mempolicy sys_set_mempolicy -271 common mq_open sys_mq_open compat_sys_mq_open -272 common mq_unlink sys_mq_unlink sys_mq_unlink -273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 -274 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 -275 common mq_notify sys_mq_notify compat_sys_mq_notify -276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr -277 common kexec_load sys_kexec_load compat_sys_kexec_load -278 common add_key sys_add_key sys_add_key -279 common request_key sys_request_key sys_request_key -280 common keyctl sys_keyctl compat_sys_keyctl -281 common waitid sys_waitid compat_sys_waitid -282 common ioprio_set sys_ioprio_set sys_ioprio_set -283 common ioprio_get sys_ioprio_get sys_ioprio_get -284 common inotify_init sys_inotify_init sys_inotify_init -285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch -286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch -287 common migrate_pages sys_migrate_pages sys_migrate_pages -288 common openat sys_openat compat_sys_openat -289 common mkdirat sys_mkdirat sys_mkdirat -290 common mknodat sys_mknodat sys_mknodat -291 common fchownat sys_fchownat sys_fchownat -292 common futimesat sys_futimesat sys_futimesat_time32 -293 32 fstatat64 - compat_sys_s390_fstatat64 -293 64 newfstatat sys_newfstatat - -294 common unlinkat sys_unlinkat sys_unlinkat -295 common renameat sys_renameat sys_renameat -296 common linkat sys_linkat sys_linkat -297 common symlinkat sys_symlinkat sys_symlinkat -298 common readlinkat sys_readlinkat sys_readlinkat -299 common fchmodat sys_fchmodat sys_fchmodat -300 common faccessat sys_faccessat sys_faccessat -301 common pselect6 sys_pselect6 compat_sys_pselect6_time32 -302 common ppoll sys_ppoll compat_sys_ppoll_time32 -303 common unshare sys_unshare sys_unshare -304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list -305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list -306 common splice sys_splice sys_splice -307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range -308 common tee sys_tee sys_tee -309 common vmsplice sys_vmsplice sys_vmsplice -310 common move_pages sys_move_pages sys_move_pages -311 common getcpu sys_getcpu sys_getcpu -312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -313 common utimes sys_utimes sys_utimes_time32 -314 common fallocate sys_fallocate compat_sys_s390_fallocate -315 common utimensat sys_utimensat sys_utimensat_time32 -316 common signalfd sys_signalfd compat_sys_signalfd -317 common timerfd - - -318 common eventfd sys_eventfd sys_eventfd -319 common timerfd_create sys_timerfd_create sys_timerfd_create -320 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 -321 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 -322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 -323 common eventfd2 sys_eventfd2 sys_eventfd2 -324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 -325 common pipe2 sys_pipe2 sys_pipe2 -326 common dup3 sys_dup3 sys_dup3 -327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 -328 common preadv sys_preadv compat_sys_preadv -329 common pwritev sys_pwritev compat_sys_pwritev -330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo -331 common perf_event_open sys_perf_event_open sys_perf_event_open -332 common fanotify_init sys_fanotify_init sys_fanotify_init -333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark -334 common prlimit64 sys_prlimit64 sys_prlimit64 -335 common name_to_handle_at sys_name_to_handle_at sys_name_to_handle_at -336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -337 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 -338 common syncfs sys_syncfs sys_syncfs -339 common setns sys_setns sys_setns -340 common process_vm_readv sys_process_vm_readv sys_process_vm_readv -341 common process_vm_writev sys_process_vm_writev sys_process_vm_writev -342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr -343 common kcmp sys_kcmp sys_kcmp -344 common finit_module sys_finit_module sys_finit_module -345 common sched_setattr sys_sched_setattr sys_sched_setattr -346 common sched_getattr sys_sched_getattr sys_sched_getattr -347 common renameat2 sys_renameat2 sys_renameat2 -348 common seccomp sys_seccomp sys_seccomp -349 common getrandom sys_getrandom sys_getrandom -350 common memfd_create sys_memfd_create sys_memfd_create -351 common bpf sys_bpf sys_bpf -352 common s390_pci_mmio_write sys_s390_pci_mmio_write sys_s390_pci_mmio_write -353 common s390_pci_mmio_read sys_s390_pci_mmio_read sys_s390_pci_mmio_read -354 common execveat sys_execveat compat_sys_execveat -355 common userfaultfd sys_userfaultfd sys_userfaultfd -356 common membarrier sys_membarrier sys_membarrier -357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 -358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg -359 common socket sys_socket sys_socket -360 common socketpair sys_socketpair sys_socketpair -361 common bind sys_bind sys_bind -362 common connect sys_connect sys_connect -363 common listen sys_listen sys_listen -364 common accept4 sys_accept4 sys_accept4 -365 common getsockopt sys_getsockopt sys_getsockopt -366 common setsockopt sys_setsockopt sys_setsockopt -367 common getsockname sys_getsockname sys_getsockname -368 common getpeername sys_getpeername sys_getpeername -369 common sendto sys_sendto sys_sendto -370 common sendmsg sys_sendmsg compat_sys_sendmsg -371 common recvfrom sys_recvfrom compat_sys_recvfrom -372 common recvmsg sys_recvmsg compat_sys_recvmsg -373 common shutdown sys_shutdown sys_shutdown -374 common mlock2 sys_mlock2 sys_mlock2 -375 common copy_file_range sys_copy_file_range sys_copy_file_range -376 common preadv2 sys_preadv2 compat_sys_preadv2 -377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 -378 common s390_guarded_storage sys_s390_guarded_storage sys_s390_guarded_storage -379 common statx sys_statx sys_statx -380 common s390_sthyi sys_s390_sthyi sys_s390_sthyi -381 common kexec_file_load sys_kexec_file_load sys_kexec_file_load -382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents -383 common rseq sys_rseq sys_rseq -384 common pkey_mprotect sys_pkey_mprotect sys_pkey_mprotect -385 common pkey_alloc sys_pkey_alloc sys_pkey_alloc -386 common pkey_free sys_pkey_free sys_pkey_free +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open +6 common close sys_close +7 common restart_syscall sys_restart_syscall +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve +12 common chdir sys_chdir +14 common mknod sys_mknod +15 common chmod sys_chmod +19 common lseek sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 common umount sys_oldumount +26 common ptrace sys_ptrace +27 common alarm sys_alarm +29 common pause sys_pause +30 common utime sys_utime +33 common access sys_access +34 common nice sys_nice +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times +45 common brk sys_brk +48 common signal sys_signal +51 common acct sys_acct +52 common umount2 sys_umount +54 common ioctl sys_ioctl +55 common fcntl sys_fcntl +57 common setpgid sys_setpgid +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit +77 common getrusage sys_getrusage +78 common gettimeofday sys_gettimeofday +79 common settimeofday sys_settimeofday +83 common symlink sys_symlink +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +89 common readdir sys_ni_syscall +90 common mmap sys_old_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate +93 common ftruncate sys_ftruncate +94 common fchmod sys_fchmod +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +99 common statfs sys_statfs +100 common fstatfs sys_fstatfs +102 common socketcall sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer +105 common getitimer sys_getitimer +106 common stat sys_newstat +107 common lstat sys_newlstat +108 common fstat sys_newfstat +110 common lookup_dcookie sys_ni_syscall +111 common vhangup sys_vhangup +112 common idle sys_ni_syscall +114 common wait4 sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo +117 common ipc sys_s390_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +124 common adjtimex sys_adjtimex +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask +127 common create_module sys_ni_syscall +128 common init_module sys_init_module +129 common delete_module sys_delete_module +130 common get_kernel_syms sys_ni_syscall +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_s390_personality +137 common afs_syscall sys_ni_syscall +141 common getdents sys_getdents +142 common select sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval +162 common nanosleep sys_nanosleep +163 common mremap sys_mremap +167 common query_module sys_ni_syscall +168 common poll sys_poll +169 common nfsservctl sys_ni_syscall +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend +180 common pread64 sys_pread64 +181 common pwrite64 sys_pwrite64 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack +187 common sendfile sys_sendfile64 +188 common getpmsg sys_ni_syscall +189 common putpmsg sys_ni_syscall +190 common vfork sys_vfork +191 common getrlimit sys_getrlimit +198 common lchown sys_lchown +199 common getuid sys_getuid +200 common getgid sys_getgid +201 common geteuid sys_geteuid +202 common getegid sys_getegid +203 common setreuid sys_setreuid +204 common setregid sys_setregid +205 common getgroups sys_getgroups +206 common setgroups sys_setgroups +207 common fchown sys_fchown +208 common setresuid sys_setresuid +209 common getresuid sys_getresuid +210 common setresgid sys_setresgid +211 common getresgid sys_getresgid +212 common chown sys_chown +213 common setuid sys_setuid +214 common setgid sys_setgid +215 common setfsuid sys_setfsuid +216 common setfsgid sys_setfsgid +217 common pivot_root sys_pivot_root +218 common mincore sys_mincore +219 common madvise sys_madvise +220 common getdents64 sys_getdents64 +222 common readahead sys_readahead +224 common setxattr sys_setxattr +225 common lsetxattr sys_lsetxattr +226 common fsetxattr sys_fsetxattr +227 common getxattr sys_getxattr +228 common lgetxattr sys_lgetxattr +229 common fgetxattr sys_fgetxattr +230 common listxattr sys_listxattr +231 common llistxattr sys_llistxattr +232 common flistxattr sys_flistxattr +233 common removexattr sys_removexattr +234 common lremovexattr sys_lremovexattr +235 common fremovexattr sys_fremovexattr +236 common gettid sys_gettid +237 common tkill sys_tkill +238 common futex sys_futex +239 common sched_setaffinity sys_sched_setaffinity +240 common sched_getaffinity sys_sched_getaffinity +241 common tgkill sys_tgkill +243 common io_setup sys_io_setup +244 common io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents +246 common io_submit sys_io_submit +247 common io_cancel sys_io_cancel +248 common exit_group sys_exit_group +249 common epoll_create sys_epoll_create +250 common epoll_ctl sys_epoll_ctl +251 common epoll_wait sys_epoll_wait +252 common set_tid_address sys_set_tid_address +253 common fadvise64 sys_fadvise64_64 +254 common timer_create sys_timer_create +255 common timer_settime sys_timer_settime +256 common timer_gettime sys_timer_gettime +257 common timer_getoverrun sys_timer_getoverrun +258 common timer_delete sys_timer_delete +259 common clock_settime sys_clock_settime +260 common clock_gettime sys_clock_gettime +261 common clock_getres sys_clock_getres +262 common clock_nanosleep sys_clock_nanosleep +265 common statfs64 sys_statfs64 +266 common fstatfs64 sys_fstatfs64 +267 common remap_file_pages sys_remap_file_pages +268 common mbind sys_mbind +269 common get_mempolicy sys_get_mempolicy +270 common set_mempolicy sys_set_mempolicy +271 common mq_open sys_mq_open +272 common mq_unlink sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend +274 common mq_timedreceive sys_mq_timedreceive +275 common mq_notify sys_mq_notify +276 common mq_getsetattr sys_mq_getsetattr +277 common kexec_load sys_kexec_load +278 common add_key sys_add_key +279 common request_key sys_request_key +280 common keyctl sys_keyctl +281 common waitid sys_waitid +282 common ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get +284 common inotify_init sys_inotify_init +285 common inotify_add_watch sys_inotify_add_watch +286 common inotify_rm_watch sys_inotify_rm_watch +287 common migrate_pages sys_migrate_pages +288 common openat sys_openat +289 common mkdirat sys_mkdirat +290 common mknodat sys_mknodat +291 common fchownat sys_fchownat +292 common futimesat sys_futimesat +293 common newfstatat sys_newfstatat +294 common unlinkat sys_unlinkat +295 common renameat sys_renameat +296 common linkat sys_linkat +297 common symlinkat sys_symlinkat +298 common readlinkat sys_readlinkat +299 common fchmodat sys_fchmodat +300 common faccessat sys_faccessat +301 common pselect6 sys_pselect6 +302 common ppoll sys_ppoll +303 common unshare sys_unshare +304 common set_robust_list sys_set_robust_list +305 common get_robust_list sys_get_robust_list +306 common splice sys_splice +307 common sync_file_range sys_sync_file_range +308 common tee sys_tee +309 common vmsplice sys_vmsplice +310 common move_pages sys_move_pages +311 common getcpu sys_getcpu +312 common epoll_pwait sys_epoll_pwait +313 common utimes sys_utimes +314 common fallocate sys_fallocate +315 common utimensat sys_utimensat +316 common signalfd sys_signalfd +317 common timerfd sys_ni_syscall +318 common eventfd sys_eventfd +319 common timerfd_create sys_timerfd_create +320 common timerfd_settime sys_timerfd_settime +321 common timerfd_gettime sys_timerfd_gettime +322 common signalfd4 sys_signalfd4 +323 common eventfd2 sys_eventfd2 +324 common inotify_init1 sys_inotify_init1 +325 common pipe2 sys_pipe2 +326 common dup3 sys_dup3 +327 common epoll_create1 sys_epoll_create1 +328 common preadv sys_preadv +329 common pwritev sys_pwritev +330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +331 common perf_event_open sys_perf_event_open +332 common fanotify_init sys_fanotify_init +333 common fanotify_mark sys_fanotify_mark +334 common prlimit64 sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at +336 common open_by_handle_at sys_open_by_handle_at +337 common clock_adjtime sys_clock_adjtime +338 common syncfs sys_syncfs +339 common setns sys_setns +340 common process_vm_readv sys_process_vm_readv +341 common process_vm_writev sys_process_vm_writev +342 common s390_runtime_instr sys_s390_runtime_instr +343 common kcmp sys_kcmp +344 common finit_module sys_finit_module +345 common sched_setattr sys_sched_setattr +346 common sched_getattr sys_sched_getattr +347 common renameat2 sys_renameat2 +348 common seccomp sys_seccomp +349 common getrandom sys_getrandom +350 common memfd_create sys_memfd_create +351 common bpf sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read +354 common execveat sys_execveat +355 common userfaultfd sys_userfaultfd +356 common membarrier sys_membarrier +357 common recvmmsg sys_recvmmsg +358 common sendmmsg sys_sendmmsg +359 common socket sys_socket +360 common socketpair sys_socketpair +361 common bind sys_bind +362 common connect sys_connect +363 common listen sys_listen +364 common accept4 sys_accept4 +365 common getsockopt sys_getsockopt +366 common setsockopt sys_setsockopt +367 common getsockname sys_getsockname +368 common getpeername sys_getpeername +369 common sendto sys_sendto +370 common sendmsg sys_sendmsg +371 common recvfrom sys_recvfrom +372 common recvmsg sys_recvmsg +373 common shutdown sys_shutdown +374 common mlock2 sys_mlock2 +375 common copy_file_range sys_copy_file_range +376 common preadv2 sys_preadv2 +377 common pwritev2 sys_pwritev2 +378 common s390_guarded_storage sys_s390_guarded_storage +379 common statx sys_statx +380 common s390_sthyi sys_s390_sthyi +381 common kexec_file_load sys_kexec_file_load +382 common io_pgetevents sys_io_pgetevents +383 common rseq sys_rseq +384 common pkey_mprotect sys_pkey_mprotect +385 common pkey_alloc sys_pkey_alloc +386 common pkey_free sys_pkey_free # room for arch specific syscalls -392 64 semtimedop sys_semtimedop - -393 common semget sys_semget sys_semget -394 common semctl sys_semctl compat_sys_semctl -395 common shmget sys_shmget sys_shmget -396 common shmctl sys_shmctl compat_sys_shmctl -397 common shmat sys_shmat compat_sys_shmat -398 common shmdt sys_shmdt sys_shmdt -399 common msgget sys_msgget sys_msgget -400 common msgsnd sys_msgsnd compat_sys_msgsnd -401 common msgrcv sys_msgrcv compat_sys_msgrcv -402 common msgctl sys_msgctl compat_sys_msgctl -403 32 clock_gettime64 - sys_clock_gettime -404 32 clock_settime64 - sys_clock_settime -405 32 clock_adjtime64 - sys_clock_adjtime -406 32 clock_getres_time64 - sys_clock_getres -407 32 clock_nanosleep_time64 - sys_clock_nanosleep -408 32 timer_gettime64 - sys_timer_gettime -409 32 timer_settime64 - sys_timer_settime -410 32 timerfd_gettime64 - sys_timerfd_gettime -411 32 timerfd_settime64 - sys_timerfd_settime -412 32 utimensat_time64 - sys_utimensat -413 32 pselect6_time64 - compat_sys_pselect6_time64 -414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 -417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 -418 32 mq_timedsend_time64 - sys_mq_timedsend -419 32 mq_timedreceive_time64 - sys_mq_timedreceive -420 32 semtimedop_time64 - sys_semtimedop -421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 -422 32 futex_time64 - sys_futex -423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval -424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal -425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup -426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter -427 common io_uring_register sys_io_uring_register sys_io_uring_register -428 common open_tree sys_open_tree sys_open_tree -429 common move_mount sys_move_mount sys_move_mount -430 common fsopen sys_fsopen sys_fsopen -431 common fsconfig sys_fsconfig sys_fsconfig -432 common fsmount sys_fsmount sys_fsmount -433 common fspick sys_fspick sys_fspick -434 common pidfd_open sys_pidfd_open sys_pidfd_open -435 common clone3 sys_clone3 sys_clone3 -436 common close_range sys_close_range sys_close_range -437 common openat2 sys_openat2 sys_openat2 -438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd -439 common faccessat2 sys_faccessat2 sys_faccessat2 -440 common process_madvise sys_process_madvise sys_process_madvise -441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 -442 common mount_setattr sys_mount_setattr sys_mount_setattr -443 common quotactl_fd sys_quotactl_fd sys_quotactl_fd -444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset -445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule -446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -447 common memfd_secret sys_memfd_secret sys_memfd_secret -448 common process_mrelease sys_process_mrelease sys_process_mrelease -449 common futex_waitv sys_futex_waitv sys_futex_waitv -450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node -451 common cachestat sys_cachestat sys_cachestat -452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 -453 common map_shadow_stack sys_map_shadow_stack sys_map_shadow_stack -454 common futex_wake sys_futex_wake sys_futex_wake -455 common futex_wait sys_futex_wait sys_futex_wait -456 common futex_requeue sys_futex_requeue sys_futex_requeue -457 common statmount sys_statmount sys_statmount -458 common listmount sys_listmount sys_listmount -459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr -460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr -461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules -462 common mseal sys_mseal sys_mseal -463 common setxattrat sys_setxattrat sys_setxattrat -464 common getxattrat sys_getxattrat sys_getxattrat -465 common listxattrat sys_listxattrat sys_listxattrat -466 common removexattrat sys_removexattrat sys_removexattrat +392 common semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl +397 common shmat sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd +401 common msgrcv sys_msgrcv +402 common msgctl sys_msgctl +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +447 common memfd_secret sys_memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index 130dfad2b96a..9c95589965fe 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -3,7 +3,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/s390/include/uapi/asm/perf_regs.h" void perf_regs_load(u64 *regs); diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index 736c0ad09194..65d75cd5b138 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,10 +1,6 @@ perf-util-y += header.o -perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o -perf-util-y += perf_regs.o - -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-util-y += machine.o perf-util-y += pmu.o -perf-util-$(CONFIG_AUXTRACE) += auxtrace.o +perf-util-y += auxtrace.o diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 5068baa3e092..1a3676145066 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -1,3 +1,4 @@ +#include <errno.h> #include <stdbool.h> #include <stdlib.h> #include <linux/kernel.h> diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c deleted file mode 100644 index 0aed92df51ba..000000000000 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ /dev/null @@ -1,110 +0,0 @@ -// 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 "../../util/kvm-stat.h" -#include "../../util/evsel.h" -#include <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); - -const char *vcpu_id_str = "id"; -const char *kvm_exit_reason = "icptcode"; -const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter"; -const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit"; - -static void event_icpt_insn_get_key(struct evsel *evsel, - struct perf_sample *sample, - struct event_key *key) -{ - unsigned long 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 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 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" -}; - -const char *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, -}; - -struct kvm_reg_events_ops kvm_reg_events_ops[] = { - { .name = "vmexit", .ops = &exit_events }, - { NULL, NULL }, -}; - -const char * const kvm_skip_events[] = { - "Wait state", - NULL, -}; - -int cpu_isa_init(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; -} diff --git a/tools/perf/arch/s390/util/perf_regs.c b/tools/perf/arch/s390/util/perf_regs.c deleted file mode 100644 index 6b1665f41180..000000000000 --- a/tools/perf/arch/s390/util/perf_regs.c +++ /dev/null @@ -1,22 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "perf_regs.h" -#include "../../util/perf_regs.h" - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG_END -}; - -uint64_t arch__intr_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c deleted file mode 100644 index c27c7a0d1076..000000000000 --- a/tools/perf/arch/s390/util/unwind-libdw.c +++ /dev/null @@ -1,65 +0,0 @@ -#include <linux/kernel.h> -#include <elfutils/libdwfl.h> -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/event.h" -#include "../../util/sample.h" -#include "dwarf-regs-table.h" -#include "perf_regs.h" - - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[ARRAY_SIZE(s390_dwarf_regs)]; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_S390_##r); \ - val; \ -}) - /* - * For DWARF register mapping details, - * see also perf/arch/s390/include/dwarf-regs-table.h - */ - dwarf_regs[0] = REG(R0); - dwarf_regs[1] = REG(R1); - dwarf_regs[2] = REG(R2); - dwarf_regs[3] = REG(R3); - dwarf_regs[4] = REG(R4); - dwarf_regs[5] = REG(R5); - dwarf_regs[6] = REG(R6); - dwarf_regs[7] = REG(R7); - dwarf_regs[8] = REG(R8); - dwarf_regs[9] = REG(R9); - dwarf_regs[10] = REG(R10); - dwarf_regs[11] = REG(R11); - dwarf_regs[12] = REG(R12); - dwarf_regs[13] = REG(R13); - dwarf_regs[14] = REG(R14); - dwarf_regs[15] = REG(R15); - - dwarf_regs[16] = REG(FP0); - dwarf_regs[17] = REG(FP2); - dwarf_regs[18] = REG(FP4); - dwarf_regs[19] = REG(FP6); - dwarf_regs[20] = REG(FP1); - dwarf_regs[21] = REG(FP3); - dwarf_regs[22] = REG(FP5); - dwarf_regs[23] = REG(FP7); - dwarf_regs[24] = REG(FP8); - dwarf_regs[25] = REG(FP10); - dwarf_regs[26] = REG(FP12); - dwarf_regs[27] = REG(FP14); - dwarf_regs[28] = REG(FP9); - dwarf_regs[29] = REG(FP11); - dwarf_regs[30] = REG(FP13); - dwarf_regs[31] = REG(FP15); - - dwarf_regs[64] = REG(MASK); - dwarf_regs[65] = REG(PC); - - dwfl_thread_state_register_pc(thread, dwarf_regs[65]); - return dwfl_thread_state_registers(thread, 0, 32, dwarf_regs); -} diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl index c8cad33bf250..70b315cbe710 100644 --- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl @@ -470,3 +470,8 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/sparc/annotate/instructions.c b/tools/perf/arch/sparc/annotate/instructions.c deleted file mode 100644 index 68c31580ccfc..000000000000 --- a/tools/perf/arch/sparc/annotate/instructions.c +++ /dev/null @@ -1,171 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -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 struct ins_ops *sparc__associate_instruction_ops(struct arch *arch, const char *name) -{ - 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; -} - -static int sparc__annotate_init(struct arch *arch, char *cpuid __maybe_unused) -{ - if (!arch->initialized) { - arch->initialized = true; - arch->associate_instruction_ops = sparc__associate_instruction_ops; - arch->objdump.comment_char = '#'; - arch->e_machine = EM_SPARC; - arch->e_flags = 0; - } - - return 0; -} diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl index 727f99d333b3..7e71bf7fcd14 100644 --- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl @@ -480,7 +480,7 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 common clone3 __sys_clone3 436 common close_range sys_close_range 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd @@ -512,3 +512,8 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/x86/Build b/tools/perf/arch/x86/Build index afae7b8f6bd6..d31a1168757c 100644 --- a/tools/perf/arch/x86/Build +++ b/tools/perf/arch/x86/Build @@ -10,6 +10,6 @@ endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) - $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) + $(Q)$(call echo-cmd,test)$(SHELLCHECK) "$<" > $@ || (cat $@ && rm $@ && false) perf-test-y += $(SHELL_TEST_LOGS) diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index a295a80ea078..44cc3f023318 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c deleted file mode 100644 index c6d403eae744..000000000000 --- a/tools/perf/arch/x86/annotate/instructions.c +++ /dev/null @@ -1,608 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * 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 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 = "cmovbe", .ops = &mov_ops, }, - { .name = "cmove", .ops = &mov_ops, }, - { .name = "cmovae", .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 = "movsd", .ops = &mov_ops, }, - { .name = "movss", .ops = &mov_ops, }, - { .name = "movsb", .ops = &mov_ops, }, - { .name = "movsw", .ops = &mov_ops, }, - { .name = "movsl", .ops = &mov_ops, }, - { .name = "movupd", .ops = &mov_ops, }, - { .name = "movups", .ops = &mov_ops, }, - { .name = "movzb", .ops = &mov_ops, }, - { .name = "movzw", .ops = &mov_ops, }, - { .name = "movzl", .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 = "pand", .ops = &mov_ops, }, - { .name = "paddq", .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(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(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, 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; -} - -static int x86__annotate_init(struct arch *arch, char *cpuid) -{ - int err = 0; - - if (arch->initialized) - return 0; - - if (cpuid) { - if (x86__cpuid_parse(arch, cpuid)) - err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING; - } - arch->e_machine = EM_X86_64; - arch->e_flags = 0; - arch->initialized = true; - return err; -} - -#ifdef HAVE_LIBDW_SUPPORT -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; - - if (func == NULL) - return; - - /* __fentry__ will preserve all registers */ - if (!strcmp(func->name, "__fentry__")) - return; - - pr_debug_dtp("call [%x] %s\n", insn_offset, func->name); - - /* Otherwise invalidate caller-saved registers after call */ - for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) { - if (state->regs[i].caller_saved) - state->regs[i].ok = false; - } - - /* Update register with the return type (if any) */ - if (die_find_func_rettype(cu_die, func->name, &type_die)) { - tsr = &state->regs[state->ret_reg]; - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - 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; - - 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->ok = true; - imm_value = tsr->imm_value; - } - } - else - return; - - 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_POINTER; - 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, "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->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)) { - tsr->ok = false; - return; - } - - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - 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->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) { - tsr->ok = false; - 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->ok = true; - - /* To copy back the variable type later (hopefully) */ - if (tsr->kind == TSR_KIND_TYPE) - 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) { - tsr->ok = false; - return; - } else if (!stack->compound) { - tsr->type = stack->type; - tsr->kind = stack->kind; - 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->ok = true; - } else { - tsr->ok = false; - 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, &type_die)) { - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - 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); - } - /* 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)) { - tsr->ok = false; - return; - } - - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - 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->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 { - tsr->ok = false; - } - } - /* 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_POINTER && - die_get_member_type(&state->regs[sreg].type, - src->offset, &type_die)) { - tsr->type = type_die; - tsr->kind = TSR_KIND_TYPE; - 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->ok = true; - - pr_debug_dtp("mov [%x] percpu base reg%d\n", - insn_offset, dst->reg1); - return; - } - } - - tsr->ok = false; - } - } - /* 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); - } else { - findnew_stack_state(state, offset, tsr->kind, - &tsr->type); - } - - 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); - } - 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 diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl index 4d0fb2fba7e2..f832ebd2d79b 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl @@ -396,7 +396,7 @@ 381 i386 pkey_alloc sys_pkey_alloc 382 i386 pkey_free sys_pkey_free 383 i386 statx sys_statx -384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl +384 i386 arch_prctl sys_arch_prctl 385 i386 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents 386 i386 rseq sys_rseq 393 i386 semget sys_semget @@ -472,3 +472,8 @@ 464 i386 getxattrat sys_getxattrat 465 i386 listxattrat sys_listxattrat 466 i386 removexattrat sys_removexattrat +467 i386 open_tree_attr sys_open_tree_attr +468 i386 file_getattr sys_file_getattr +469 i386 file_setattr sys_file_setattr +470 i386 listns sys_listns +471 i386 rseq_slice_yield sys_rseq_slice_yield diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 5eb708bff1c7..524155d655da 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,7 @@ 333 common io_pgetevents sys_io_pgetevents 334 common rseq sys_rseq 335 common uretprobe sys_uretprobe +336 common uprobe sys_uprobe # don't use numbers 387 through 423, add new calls after the last # 'common' entry 424 common pidfd_send_signal sys_pidfd_send_signal @@ -390,6 +391,11 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c0421a26b875..7d65b9e51840 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -2,6 +2,8 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H +#include "tests/tests.h" + struct test_suite; /* Tests */ @@ -12,10 +14,12 @@ int test__insn_x86(struct test_suite *test, int subtest); int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest); int test__bp_modify(struct test_suite *test, int subtest); -int test__x86_sample_parsing(struct test_suite *test, int subtest); int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest); +int test__amd_ibs_period(struct test_suite *test, int subtest); int test__hybrid(struct test_suite *test, int subtest); +DECLARE_SUITE(x86_topdown); + extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index f209ce2c1dd9..5495e5ca7cdc 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -4,7 +4,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <asm/perf_regs.h> +#include "../../../../arch/x86/include/uapi/asm/perf_regs.h" void perf_regs_load(u64 *regs); diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 86262c720857..b017d1ca6e3c 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -2,14 +2,15 @@ perf-test-$(CONFIG_DWARF_UNWIND) += regs_load.o perf-test-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-test-y += arch-tests.o -perf-test-y += sample-parsing.o perf-test-y += hybrid.o -perf-test-$(CONFIG_AUXTRACE) += intel-pt-test.o +perf-test-y += intel-pt-test.o ifeq ($(CONFIG_EXTRA_TESTS),y) -perf-test-$(CONFIG_AUXTRACE) += insn-x86.o +perf-test-y += insn-x86.o endif perf-test-$(CONFIG_X86_64) += bp-modify.o perf-test-y += amd-ibs-via-core-pmu.o +perf-test-y += amd-ibs-period.o +perf-test-y += topdown.o ifdef SHELLCHECK SHELL_TESTS := gen-insn-x86-dat.sh @@ -21,6 +22,6 @@ endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) - $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) + $(Q)$(call echo-cmd,test)$(SHELLCHECK) "$<" > $@ || (cat $@ && rm $@ && false) perf-test-y += $(SHELL_TEST_LOGS) diff --git a/tools/perf/arch/x86/tests/amd-ibs-period.c b/tools/perf/arch/x86/tests/amd-ibs-period.c new file mode 100644 index 000000000000..223e059e04de --- /dev/null +++ b/tools/perf/arch/x86/tests/amd-ibs-period.c @@ -0,0 +1,1032 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sched.h> +#include <sys/syscall.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/utsname.h> +#include <string.h> + +#include "arch-tests.h" +#include "linux/perf_event.h" +#include "linux/zalloc.h" +#include "tests/tests.h" +#include "../perf-sys.h" +#include "pmu.h" +#include "pmus.h" +#include "debug.h" +#include "util.h" +#include "strbuf.h" +#include "../util/env.h" + +static int page_size; + +#define PERF_MMAP_DATA_PAGES 32L +#define PERF_MMAP_DATA_SIZE (PERF_MMAP_DATA_PAGES * page_size) +#define PERF_MMAP_DATA_MASK (PERF_MMAP_DATA_SIZE - 1) +#define PERF_MMAP_TOTAL_PAGES (PERF_MMAP_DATA_PAGES + 1) +#define PERF_MMAP_TOTAL_SIZE (PERF_MMAP_TOTAL_PAGES * page_size) + +#define rmb() asm volatile("lfence":::"memory") + +enum { + FD_ERROR, + FD_SUCCESS, +}; + +enum { + IBS_FETCH, + IBS_OP, +}; + +struct perf_pmu *fetch_pmu; +struct perf_pmu *op_pmu; +unsigned int perf_event_max_sample_rate; + +/* Dummy workload to generate IBS samples. */ +static int dummy_workload_1(unsigned long count) +{ + int (*func)(void); + int ret = 0; + char *p; + char insn1[] = { + 0xb8, 0x01, 0x00, 0x00, 0x00, /* mov 1,%eax */ + 0xc3, /* ret */ + 0xcc, /* int 3 */ + }; + + char insn2[] = { + 0xb8, 0x02, 0x00, 0x00, 0x00, /* mov 2,%eax */ + 0xc3, /* ret */ + 0xcc, /* int 3 */ + }; + + p = zalloc(2 * page_size); + if (!p) { + printf("malloc() failed. %m"); + return 1; + } + + func = (void *)((unsigned long)(p + page_size - 1) & ~(page_size - 1)); + + ret = mprotect(func, page_size, PROT_READ | PROT_WRITE | PROT_EXEC); + if (ret) { + printf("mprotect() failed. %m"); + goto out; + } + + if (count < 100000) + count = 100000; + else if (count > 10000000) + count = 10000000; + while (count--) { + memcpy((void *)func, insn1, sizeof(insn1)); + if (func() != 1) { + pr_debug("ERROR insn1\n"); + ret = -1; + goto out; + } + memcpy((void *)func, insn2, sizeof(insn2)); + if (func() != 2) { + pr_debug("ERROR insn2\n"); + ret = -1; + goto out; + } + } + +out: + free(p); + return ret; +} + +/* Another dummy workload to generate IBS samples. */ +static void dummy_workload_2(char *perf) +{ + char bench[] = " bench sched messaging -g 10 -l 5000 > /dev/null 2>&1"; + char taskset[] = "taskset -c 0 "; + int ret __maybe_unused; + struct strbuf sb; + char *cmd; + + strbuf_init(&sb, 0); + strbuf_add(&sb, taskset, strlen(taskset)); + strbuf_add(&sb, perf, strlen(perf)); + strbuf_add(&sb, bench, strlen(bench)); + cmd = strbuf_detach(&sb, NULL); + ret = system(cmd); + free(cmd); +} + +static int sched_affine(int cpu) +{ + cpu_set_t set; + + CPU_ZERO(&set); + CPU_SET(cpu, &set); + if (sched_setaffinity(getpid(), sizeof(set), &set) == -1) { + pr_debug("sched_setaffinity() failed. [%m]"); + return -1; + } + return 0; +} + +static void +copy_sample_data(void *src, unsigned long offset, void *dest, size_t size) +{ + size_t chunk1_size, chunk2_size; + + if ((offset + size) < (size_t)PERF_MMAP_DATA_SIZE) { + memcpy(dest, src + offset, size); + } else { + chunk1_size = PERF_MMAP_DATA_SIZE - offset; + chunk2_size = size - chunk1_size; + + memcpy(dest, src + offset, chunk1_size); + memcpy(dest + chunk1_size, src, chunk2_size); + } +} + +static int rb_read(struct perf_event_mmap_page *rb, void *dest, size_t size) +{ + void *base; + unsigned long data_tail, data_head; + + /* Casting to (void *) is needed. */ + base = (void *)rb + page_size; + + data_head = rb->data_head; + rmb(); + data_tail = rb->data_tail; + + if ((data_head - data_tail) < size) + return -1; + + data_tail &= PERF_MMAP_DATA_MASK; + copy_sample_data(base, data_tail, dest, size); + rb->data_tail += size; + return 0; +} + +static void rb_skip(struct perf_event_mmap_page *rb, size_t size) +{ + size_t data_head = rb->data_head; + + rmb(); + + if ((rb->data_tail + size) > data_head) + rb->data_tail = data_head; + else + rb->data_tail += size; +} + +/* Sample period value taken from perf sample must match with expected value. */ +static int period_equal(unsigned long exp_period, unsigned long act_period) +{ + return exp_period == act_period ? 0 : -1; +} + +/* + * Sample period value taken from perf sample must be >= minimum sample period + * supported by IBS HW. + */ +static int period_higher(unsigned long min_period, unsigned long act_period) +{ + return min_period <= act_period ? 0 : -1; +} + +static int rb_drain_samples(struct perf_event_mmap_page *rb, + unsigned long exp_period, + int *nr_samples, + int (*callback)(unsigned long, unsigned long)) +{ + struct perf_event_header hdr; + unsigned long period; + int ret = 0; + + /* + * PERF_RECORD_SAMPLE: + * struct { + * struct perf_event_header hdr; + * { u64 period; } && PERF_SAMPLE_PERIOD + * }; + */ + while (1) { + if (rb_read(rb, &hdr, sizeof(hdr))) + return ret; + + if (hdr.type == PERF_RECORD_SAMPLE) { + (*nr_samples)++; + period = 0; + if (rb_read(rb, &period, sizeof(period))) + pr_debug("rb_read(period) error. [%m]"); + ret |= callback(exp_period, period); + } else { + rb_skip(rb, hdr.size - sizeof(hdr)); + } + } + return ret; +} + +static long perf_event_open(struct perf_event_attr *attr, pid_t pid, + int cpu, int group_fd, unsigned long flags) +{ + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); +} + +static void fetch_prepare_attr(struct perf_event_attr *attr, + unsigned long long config, int freq, + unsigned long sample_period) +{ + memset(attr, 0, sizeof(struct perf_event_attr)); + + attr->type = fetch_pmu->type; + attr->size = sizeof(struct perf_event_attr); + attr->config = config; + attr->disabled = 1; + attr->sample_type = PERF_SAMPLE_PERIOD; + attr->freq = freq; + attr->sample_period = sample_period; /* = ->sample_freq */ +} + +static void op_prepare_attr(struct perf_event_attr *attr, + unsigned long config, int freq, + unsigned long sample_period) +{ + memset(attr, 0, sizeof(struct perf_event_attr)); + + attr->type = op_pmu->type; + attr->size = sizeof(struct perf_event_attr); + attr->config = config; + attr->disabled = 1; + attr->sample_type = PERF_SAMPLE_PERIOD; + attr->freq = freq; + attr->sample_period = sample_period; /* = ->sample_freq */ +} + +struct ibs_configs { + /* Input */ + unsigned long config; + + /* Expected output */ + unsigned long period; + int fd; +}; + +/* + * Somehow first Fetch event with sample period = 0x10 causes 0 + * samples. So start with large period and decrease it gradually. + */ +struct ibs_configs fetch_configs[] = { + { .config = 0xffff, .period = 0xffff0, .fd = FD_SUCCESS }, + { .config = 0x1000, .period = 0x10000, .fd = FD_SUCCESS }, + { .config = 0xff, .period = 0xff0, .fd = FD_SUCCESS }, + { .config = 0x1, .period = 0x10, .fd = FD_SUCCESS }, + { .config = 0x0, .period = -1, .fd = FD_ERROR }, + { .config = 0x10000, .period = -1, .fd = FD_ERROR }, +}; + +struct ibs_configs op_configs[] = { + { .config = 0x0, .period = -1, .fd = FD_ERROR }, + { .config = 0x1, .period = -1, .fd = FD_ERROR }, + { .config = 0x8, .period = -1, .fd = FD_ERROR }, + { .config = 0x9, .period = 0x90, .fd = FD_SUCCESS }, + { .config = 0xf, .period = 0xf0, .fd = FD_SUCCESS }, + { .config = 0x1000, .period = 0x10000, .fd = FD_SUCCESS }, + { .config = 0xffff, .period = 0xffff0, .fd = FD_SUCCESS }, + { .config = 0x10000, .period = -1, .fd = FD_ERROR }, + { .config = 0x100000, .period = 0x100000, .fd = FD_SUCCESS }, + { .config = 0xf00000, .period = 0xf00000, .fd = FD_SUCCESS }, + { .config = 0xf0ffff, .period = 0xfffff0, .fd = FD_SUCCESS }, + { .config = 0x1f0ffff, .period = 0x1fffff0, .fd = FD_SUCCESS }, + { .config = 0x7f0ffff, .period = 0x7fffff0, .fd = FD_SUCCESS }, + { .config = 0x8f0ffff, .period = -1, .fd = FD_ERROR }, + { .config = 0x17f0ffff, .period = -1, .fd = FD_ERROR }, +}; + +static int __ibs_config_test(int ibs_type, struct ibs_configs *config, int *nr_samples) +{ + struct perf_event_attr attr; + int fd, i; + void *rb; + int ret = 0; + + if (ibs_type == IBS_FETCH) + fetch_prepare_attr(&attr, config->config, 0, 0); + else + op_prepare_attr(&attr, config->config, 0, 0); + + /* CPU0, All processes */ + fd = perf_event_open(&attr, -1, 0, -1, 0); + if (config->fd == FD_ERROR) { + if (fd != -1) { + close(fd); + return -1; + } + return 0; + } + if (fd <= -1) + return -1; + + rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (rb == MAP_FAILED) { + pr_debug("mmap() failed. [%m]\n"); + return -1; + } + + ioctl(fd, PERF_EVENT_IOC_RESET, 0); + ioctl(fd, PERF_EVENT_IOC_ENABLE, 0); + + i = 5; + while (i--) { + dummy_workload_1(1000000); + + ret = rb_drain_samples(rb, config->period, nr_samples, + period_equal); + if (ret) + break; + } + + ioctl(fd, PERF_EVENT_IOC_DISABLE, 0); + munmap(rb, PERF_MMAP_TOTAL_SIZE); + close(fd); + return ret; +} + +static int ibs_config_test(void) +{ + int nr_samples = 0; + unsigned long i; + int ret = 0; + int r; + + pr_debug("\nIBS config tests:\n"); + pr_debug("-----------------\n"); + + pr_debug("Fetch PMU tests:\n"); + for (i = 0; i < ARRAY_SIZE(fetch_configs); i++) { + nr_samples = 0; + r = __ibs_config_test(IBS_FETCH, &(fetch_configs[i]), &nr_samples); + + if (fetch_configs[i].fd == FD_ERROR) { + pr_debug("0x%-16lx: %-4s\n", fetch_configs[i].config, + !r ? "Ok" : "Fail"); + } else { + /* + * Although nr_samples == 0 is reported as Fail here, + * the failure status is not cascaded up because, we + * can not decide whether test really failed or not + * without actual samples. + */ + pr_debug("0x%-16lx: %-4s (nr samples: %d)\n", fetch_configs[i].config, + (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples); + } + + ret |= r; + } + + pr_debug("Op PMU tests:\n"); + for (i = 0; i < ARRAY_SIZE(op_configs); i++) { + nr_samples = 0; + r = __ibs_config_test(IBS_OP, &(op_configs[i]), &nr_samples); + + if (op_configs[i].fd == FD_ERROR) { + pr_debug("0x%-16lx: %-4s\n", op_configs[i].config, + !r ? "Ok" : "Fail"); + } else { + /* + * Although nr_samples == 0 is reported as Fail here, + * the failure status is not cascaded up because, we + * can not decide whether test really failed or not + * without actual samples. + */ + pr_debug("0x%-16lx: %-4s (nr samples: %d)\n", op_configs[i].config, + (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples); + } + + ret |= r; + } + + return ret; +} + +struct ibs_period { + /* Input */ + int freq; + unsigned long sample_freq; + + /* Output */ + int ret; + unsigned long period; +}; + +struct ibs_period fetch_period[] = { + { .freq = 0, .sample_freq = 0, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 1, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 0xf, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 0x10, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 0, .sample_freq = 0x11, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 0, .sample_freq = 0x8f, .ret = FD_SUCCESS, .period = 0x80 }, + { .freq = 0, .sample_freq = 0x90, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 0, .sample_freq = 0x91, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 0, .sample_freq = 0x4d2, .ret = FD_SUCCESS, .period = 0x4d0 }, + { .freq = 0, .sample_freq = 0x1007, .ret = FD_SUCCESS, .period = 0x1000 }, + { .freq = 0, .sample_freq = 0xfff0, .ret = FD_SUCCESS, .period = 0xfff0 }, + { .freq = 0, .sample_freq = 0xffff, .ret = FD_SUCCESS, .period = 0xfff0 }, + { .freq = 0, .sample_freq = 0x10010, .ret = FD_SUCCESS, .period = 0x10010 }, + { .freq = 0, .sample_freq = 0x7fffff, .ret = FD_SUCCESS, .period = 0x7ffff0 }, + { .freq = 0, .sample_freq = 0xfffffff, .ret = FD_SUCCESS, .period = 0xffffff0 }, + { .freq = 1, .sample_freq = 0, .ret = FD_ERROR, .period = -1 }, + { .freq = 1, .sample_freq = 1, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0xf, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x10, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x11, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x8f, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x90, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x91, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x4d2, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x1007, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0xfff0, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0xffff, .ret = FD_SUCCESS, .period = 0x10 }, + { .freq = 1, .sample_freq = 0x10010, .ret = FD_SUCCESS, .period = 0x10 }, + /* ret=FD_ERROR because freq > default perf_event_max_sample_rate (100000) */ + { .freq = 1, .sample_freq = 0x7fffff, .ret = FD_ERROR, .period = -1 }, +}; + +struct ibs_period op_period[] = { + { .freq = 0, .sample_freq = 0, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 1, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 0xf, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 0x10, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 0x11, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 0x8f, .ret = FD_ERROR, .period = -1 }, + { .freq = 0, .sample_freq = 0x90, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 0, .sample_freq = 0x91, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 0, .sample_freq = 0x4d2, .ret = FD_SUCCESS, .period = 0x4d0 }, + { .freq = 0, .sample_freq = 0x1007, .ret = FD_SUCCESS, .period = 0x1000 }, + { .freq = 0, .sample_freq = 0xfff0, .ret = FD_SUCCESS, .period = 0xfff0 }, + { .freq = 0, .sample_freq = 0xffff, .ret = FD_SUCCESS, .period = 0xfff0 }, + { .freq = 0, .sample_freq = 0x10010, .ret = FD_SUCCESS, .period = 0x10010 }, + { .freq = 0, .sample_freq = 0x7fffff, .ret = FD_SUCCESS, .period = 0x7ffff0 }, + { .freq = 0, .sample_freq = 0xfffffff, .ret = FD_SUCCESS, .period = 0xffffff0 }, + { .freq = 1, .sample_freq = 0, .ret = FD_ERROR, .period = -1 }, + { .freq = 1, .sample_freq = 1, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0xf, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x10, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x11, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x8f, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x90, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x91, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x4d2, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x1007, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0xfff0, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0xffff, .ret = FD_SUCCESS, .period = 0x90 }, + { .freq = 1, .sample_freq = 0x10010, .ret = FD_SUCCESS, .period = 0x90 }, + /* ret=FD_ERROR because freq > default perf_event_max_sample_rate (100000) */ + { .freq = 1, .sample_freq = 0x7fffff, .ret = FD_ERROR, .period = -1 }, +}; + +static int __ibs_period_constraint_test(int ibs_type, struct ibs_period *period, + int *nr_samples) +{ + struct perf_event_attr attr; + int ret = 0; + void *rb; + int fd; + + if (period->freq && period->sample_freq > perf_event_max_sample_rate) + period->ret = FD_ERROR; + + if (ibs_type == IBS_FETCH) + fetch_prepare_attr(&attr, 0, period->freq, period->sample_freq); + else + op_prepare_attr(&attr, 0, period->freq, period->sample_freq); + + /* CPU0, All processes */ + fd = perf_event_open(&attr, -1, 0, -1, 0); + if (period->ret == FD_ERROR) { + if (fd != -1) { + close(fd); + return -1; + } + return 0; + } + if (fd <= -1) + return -1; + + rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (rb == MAP_FAILED) { + pr_debug("mmap() failed. [%m]\n"); + close(fd); + return -1; + } + + ioctl(fd, PERF_EVENT_IOC_RESET, 0); + ioctl(fd, PERF_EVENT_IOC_ENABLE, 0); + + if (period->freq) { + dummy_workload_1(100000); + ret = rb_drain_samples(rb, period->period, nr_samples, + period_higher); + } else { + dummy_workload_1(period->sample_freq * 10); + ret = rb_drain_samples(rb, period->period, nr_samples, + period_equal); + } + + ioctl(fd, PERF_EVENT_IOC_DISABLE, 0); + munmap(rb, PERF_MMAP_TOTAL_SIZE); + close(fd); + return ret; +} + +static int ibs_period_constraint_test(void) +{ + unsigned long i; + int nr_samples; + int ret = 0; + int r; + + pr_debug("\nIBS sample period constraint tests:\n"); + pr_debug("-----------------------------------\n"); + + pr_debug("Fetch PMU test:\n"); + for (i = 0; i < ARRAY_SIZE(fetch_period); i++) { + nr_samples = 0; + r = __ibs_period_constraint_test(IBS_FETCH, &fetch_period[i], + &nr_samples); + + if (fetch_period[i].ret == FD_ERROR) { + pr_debug("freq %d, sample_freq %9ld: %-4s\n", + fetch_period[i].freq, fetch_period[i].sample_freq, + !r ? "Ok" : "Fail"); + } else { + /* + * Although nr_samples == 0 is reported as Fail here, + * the failure status is not cascaded up because, we + * can not decide whether test really failed or not + * without actual samples. + */ + pr_debug("freq %d, sample_freq %9ld: %-4s (nr samples: %d)\n", + fetch_period[i].freq, fetch_period[i].sample_freq, + (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples); + } + ret |= r; + } + + pr_debug("Op PMU test:\n"); + for (i = 0; i < ARRAY_SIZE(op_period); i++) { + nr_samples = 0; + r = __ibs_period_constraint_test(IBS_OP, &op_period[i], + &nr_samples); + + if (op_period[i].ret == FD_ERROR) { + pr_debug("freq %d, sample_freq %9ld: %-4s\n", + op_period[i].freq, op_period[i].sample_freq, + !r ? "Ok" : "Fail"); + } else { + /* + * Although nr_samples == 0 is reported as Fail here, + * the failure status is not cascaded up because, we + * can not decide whether test really failed or not + * without actual samples. + */ + pr_debug("freq %d, sample_freq %9ld: %-4s (nr samples: %d)\n", + op_period[i].freq, op_period[i].sample_freq, + (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples); + } + ret |= r; + } + + return ret; +} + +struct ibs_ioctl { + /* Input */ + int freq; + unsigned long period; + + /* Expected output */ + int ret; +}; + +struct ibs_ioctl fetch_ioctl[] = { + { .freq = 0, .period = 0x0, .ret = FD_ERROR }, + { .freq = 0, .period = 0x1, .ret = FD_ERROR }, + { .freq = 0, .period = 0xf, .ret = FD_ERROR }, + { .freq = 0, .period = 0x10, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x11, .ret = FD_ERROR }, + { .freq = 0, .period = 0x1f, .ret = FD_ERROR }, + { .freq = 0, .period = 0x20, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x80, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x8f, .ret = FD_ERROR }, + { .freq = 0, .period = 0x90, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x91, .ret = FD_ERROR }, + { .freq = 0, .period = 0x100, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0xfff0, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0xffff, .ret = FD_ERROR }, + { .freq = 0, .period = 0x10000, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x1fff0, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x1fff5, .ret = FD_ERROR }, + { .freq = 1, .period = 0x0, .ret = FD_ERROR }, + { .freq = 1, .period = 0x1, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0xf, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x10, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x11, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x1f, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x20, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x80, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x8f, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x90, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x91, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x100, .ret = FD_SUCCESS }, +}; + +struct ibs_ioctl op_ioctl[] = { + { .freq = 0, .period = 0x0, .ret = FD_ERROR }, + { .freq = 0, .period = 0x1, .ret = FD_ERROR }, + { .freq = 0, .period = 0xf, .ret = FD_ERROR }, + { .freq = 0, .period = 0x10, .ret = FD_ERROR }, + { .freq = 0, .period = 0x11, .ret = FD_ERROR }, + { .freq = 0, .period = 0x1f, .ret = FD_ERROR }, + { .freq = 0, .period = 0x20, .ret = FD_ERROR }, + { .freq = 0, .period = 0x80, .ret = FD_ERROR }, + { .freq = 0, .period = 0x8f, .ret = FD_ERROR }, + { .freq = 0, .period = 0x90, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x91, .ret = FD_ERROR }, + { .freq = 0, .period = 0x100, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0xfff0, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0xffff, .ret = FD_ERROR }, + { .freq = 0, .period = 0x10000, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x1fff0, .ret = FD_SUCCESS }, + { .freq = 0, .period = 0x1fff5, .ret = FD_ERROR }, + { .freq = 1, .period = 0x0, .ret = FD_ERROR }, + { .freq = 1, .period = 0x1, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0xf, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x10, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x11, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x1f, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x20, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x80, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x8f, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x90, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x91, .ret = FD_SUCCESS }, + { .freq = 1, .period = 0x100, .ret = FD_SUCCESS }, +}; + +static int __ibs_ioctl_test(int ibs_type, struct ibs_ioctl *ibs_ioctl) +{ + struct perf_event_attr attr; + int ret = 0; + int fd; + int r; + + if (ibs_type == IBS_FETCH) + fetch_prepare_attr(&attr, 0, ibs_ioctl->freq, 1000); + else + op_prepare_attr(&attr, 0, ibs_ioctl->freq, 1000); + + /* CPU0, All processes */ + fd = perf_event_open(&attr, -1, 0, -1, 0); + if (fd <= -1) { + pr_debug("event_open() Failed\n"); + return -1; + } + + r = ioctl(fd, PERF_EVENT_IOC_PERIOD, &ibs_ioctl->period); + if ((ibs_ioctl->ret == FD_SUCCESS && r <= -1) || + (ibs_ioctl->ret == FD_ERROR && r >= 0)) { + ret = -1; + } + + close(fd); + return ret; +} + +static int ibs_ioctl_test(void) +{ + unsigned long i; + int ret = 0; + int r; + + pr_debug("\nIBS ioctl() tests:\n"); + pr_debug("------------------\n"); + + pr_debug("Fetch PMU tests\n"); + for (i = 0; i < ARRAY_SIZE(fetch_ioctl); i++) { + r = __ibs_ioctl_test(IBS_FETCH, &fetch_ioctl[i]); + + pr_debug("ioctl(%s = 0x%-7lx): %s\n", + fetch_ioctl[i].freq ? "freq " : "period", + fetch_ioctl[i].period, r ? "Fail" : "Ok"); + ret |= r; + } + + pr_debug("Op PMU tests\n"); + for (i = 0; i < ARRAY_SIZE(op_ioctl); i++) { + r = __ibs_ioctl_test(IBS_OP, &op_ioctl[i]); + + pr_debug("ioctl(%s = 0x%-7lx): %s\n", + op_ioctl[i].freq ? "freq " : "period", + op_ioctl[i].period, r ? "Fail" : "Ok"); + ret |= r; + } + + return ret; +} + +static int ibs_freq_neg_test(void) +{ + struct perf_event_attr attr; + int fd; + + pr_debug("\nIBS freq (negative) tests:\n"); + pr_debug("--------------------------\n"); + + /* + * Assuming perf_event_max_sample_rate <= 100000, + * config: 0x300D40 ==> MaxCnt: 200000 + */ + op_prepare_attr(&attr, 0x300D40, 1, 0); + + /* CPU0, All processes */ + fd = perf_event_open(&attr, -1, 0, -1, 0); + if (fd != -1) { + pr_debug("freq 1, sample_freq 200000: Fail\n"); + close(fd); + return -1; + } + + pr_debug("freq 1, sample_freq 200000: Ok\n"); + + return 0; +} + +struct ibs_l3missonly { + /* Input */ + int freq; + unsigned long sample_freq; + + /* Expected output */ + int ret; + unsigned long min_period; +}; + +struct ibs_l3missonly fetch_l3missonly = { + .freq = 1, + .sample_freq = 10000, + .ret = FD_SUCCESS, + .min_period = 0x10, +}; + +struct ibs_l3missonly op_l3missonly = { + .freq = 1, + .sample_freq = 10000, + .ret = FD_SUCCESS, + .min_period = 0x90, +}; + +static int __ibs_l3missonly_test(char *perf, int ibs_type, int *nr_samples, + struct ibs_l3missonly *l3missonly) +{ + struct perf_event_attr attr; + int ret = 0; + void *rb; + int fd; + + if (l3missonly->sample_freq > perf_event_max_sample_rate) + l3missonly->ret = FD_ERROR; + + if (ibs_type == IBS_FETCH) { + fetch_prepare_attr(&attr, 0x800000000000000UL, l3missonly->freq, + l3missonly->sample_freq); + } else { + op_prepare_attr(&attr, 0x10000, l3missonly->freq, + l3missonly->sample_freq); + } + + /* CPU0, All processes */ + fd = perf_event_open(&attr, -1, 0, -1, 0); + if (l3missonly->ret == FD_ERROR) { + if (fd != -1) { + close(fd); + return -1; + } + return 0; + } + if (fd == -1) { + pr_debug("perf_event_open() failed. [%m]\n"); + return -1; + } + + rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE, + MAP_SHARED, fd, 0); + if (rb == MAP_FAILED) { + pr_debug("mmap() failed. [%m]\n"); + close(fd); + return -1; + } + + ioctl(fd, PERF_EVENT_IOC_RESET, 0); + ioctl(fd, PERF_EVENT_IOC_ENABLE, 0); + + dummy_workload_2(perf); + + ioctl(fd, PERF_EVENT_IOC_DISABLE, 0); + + ret = rb_drain_samples(rb, l3missonly->min_period, nr_samples, period_higher); + + munmap(rb, PERF_MMAP_TOTAL_SIZE); + close(fd); + return ret; +} + +static int ibs_l3missonly_test(char *perf) +{ + int nr_samples = 0; + int ret = 0; + int r = 0; + + pr_debug("\nIBS L3MissOnly test: (takes a while)\n"); + pr_debug("--------------------\n"); + + if (perf_pmu__has_format(fetch_pmu, "l3missonly")) { + nr_samples = 0; + r = __ibs_l3missonly_test(perf, IBS_FETCH, &nr_samples, &fetch_l3missonly); + if (fetch_l3missonly.ret == FD_ERROR) { + pr_debug("Fetch L3MissOnly: %-4s\n", !r ? "Ok" : "Fail"); + } else { + /* + * Although nr_samples == 0 is reported as Fail here, + * the failure status is not cascaded up because, we + * can not decide whether test really failed or not + * without actual samples. + */ + pr_debug("Fetch L3MissOnly: %-4s (nr_samples: %d)\n", + (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples); + } + ret |= r; + } + + if (perf_pmu__has_format(op_pmu, "l3missonly")) { + nr_samples = 0; + r = __ibs_l3missonly_test(perf, IBS_OP, &nr_samples, &op_l3missonly); + if (op_l3missonly.ret == FD_ERROR) { + pr_debug("Op L3MissOnly: %-4s\n", !r ? "Ok" : "Fail"); + } else { + /* + * Although nr_samples == 0 is reported as Fail here, + * the failure status is not cascaded up because, we + * can not decide whether test really failed or not + * without actual samples. + */ + pr_debug("Op L3MissOnly: %-4s (nr_samples: %d)\n", + (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples); + } + ret |= r; + } + + return ret; +} + +static unsigned int get_perf_event_max_sample_rate(void) +{ + unsigned int max_sample_rate = 100000; + FILE *fp; + int ret; + + fp = fopen("/proc/sys/kernel/perf_event_max_sample_rate", "r"); + if (!fp) { + pr_debug("Can't open perf_event_max_sample_rate. Assuming %d\n", + max_sample_rate); + goto out; + } + + ret = fscanf(fp, "%d", &max_sample_rate); + if (ret == EOF) { + pr_debug("Can't read perf_event_max_sample_rate. Assuming 100000\n"); + max_sample_rate = 100000; + } + fclose(fp); + +out: + return max_sample_rate; +} + +/* + * Bunch of IBS sample period fixes that this test exercise went in v6.15. + * Skip the test on older kernels to distinguish between test failure due + * to a new bug vs known failure due to older kernel. + */ +static bool kernel_v6_15_or_newer(void) +{ + struct utsname utsname; + char *endptr = NULL; + long major, minor; + + if (uname(&utsname) < 0) { + pr_debug("uname() failed. [%m]"); + return false; + } + + major = strtol(utsname.release, &endptr, 10); + endptr++; + minor = strtol(endptr, NULL, 10); + + return major >= 6 && minor >= 15; +} + +int test__amd_ibs_period(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + char perf[PATH_MAX] = {'\0'}; + int ret = TEST_OK; + + page_size = sysconf(_SC_PAGESIZE); + + /* + * Reading perf_event_max_sample_rate only once _might_ cause some + * of the test to fail if kernel changes it after reading it here. + */ + perf_event_max_sample_rate = get_perf_event_max_sample_rate(); + fetch_pmu = perf_pmus__find("ibs_fetch"); + op_pmu = perf_pmus__find("ibs_op"); + + if (!x86__is_amd_cpu() || !fetch_pmu || !op_pmu) + return TEST_SKIP; + + if (!kernel_v6_15_or_newer()) { + pr_debug("Need v6.15 or newer kernel. Skipping.\n"); + return TEST_SKIP; + } + + perf_exe(perf, sizeof(perf)); + + if (sched_affine(0)) + return TEST_FAIL; + + /* + * Perf event can be opened in two modes: + * 1 Freq mode + * perf_event_attr->freq = 1, ->sample_freq = <frequency> + * 2 Sample period mode + * perf_event_attr->freq = 0, ->sample_period = <period> + * + * Instead of using above interface, IBS event in 'sample period mode' + * can also be opened by passing <period> value directly in a MaxCnt + * bitfields of perf_event_attr->config. Test this IBS specific special + * interface. + */ + if (ibs_config_test()) + ret = TEST_FAIL; + + /* + * IBS Fetch and Op PMUs have HW constraints on minimum sample period. + * Also, sample period value must be in multiple of 0x10. Test that IBS + * driver honors HW constraints for various possible values in Freq as + * well as Sample Period mode IBS events. + */ + if (ibs_period_constraint_test()) + ret = TEST_FAIL; + + /* + * Test ioctl() with various sample period values for IBS event. + */ + if (ibs_ioctl_test()) + ret = TEST_FAIL; + + /* + * Test that opening of freq mode IBS event fails when the freq value + * is passed through ->config, not explicitly in ->sample_freq. Also + * use high freq value (beyond perf_event_max_sample_rate) to test IBS + * driver do not bypass perf_event_max_sample_rate checks. + */ + if (ibs_freq_neg_test()) + ret = TEST_FAIL; + + /* + * L3MissOnly is a post-processing filter, i.e. IBS HW checks for L3 + * Miss at the completion of the tagged uOp. The sample is discarded + * if the tagged uOp did not cause L3Miss. Also, IBS HW internally + * resets CurCnt to a small pseudo-random value and resumes counting. + * A new uOp is tagged once CurCnt reaches to MaxCnt. But the process + * repeats until the tagged uOp causes an L3 Miss. + * + * With the freq mode event, the next sample period is calculated by + * generic kernel on every sample to achieve desired freq of samples. + * + * Since the number of times HW internally reset CurCnt and the pseudo- + * random value of CurCnt for all those occurrences are not known to SW, + * the sample period adjustment by kernel goes for a toes for freq mode + * IBS events. Kernel will set very small period for the next sample if + * the window between current sample and prev sample is too high due to + * multiple samples being discarded internally by IBS HW. + * + * Test that IBS sample period constraints are honored when L3MissOnly + * is ON. + */ + if (ibs_l3missonly_test(perf)) + ret = TEST_FAIL; + + return ret; +} diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index a216a5d172ed..c3e1619c5e79 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -3,7 +3,6 @@ #include "tests/tests.h" #include "arch-tests.h" -#ifdef HAVE_AUXTRACE_SUPPORT #ifdef HAVE_EXTRA_TESTS DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86); #endif @@ -19,12 +18,11 @@ struct test_suite suite__intel_pt = { .test_cases = intel_pt_tests, }; -#endif #if defined(__x86_64__) DEFINE_SUITE("x86 bp modify", bp_modify); #endif -DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu); +DEFINE_SUITE_EXCLUSIVE("AMD IBS sample period", amd_ibs_period); static struct test_case hybrid_tests[] = { TEST_CASE_REASON("x86 hybrid event parsing", hybrid, "not hybrid"), { .name = NULL, } @@ -39,17 +37,16 @@ struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT &suite__dwarf_unwind, #endif -#ifdef HAVE_AUXTRACE_SUPPORT #ifdef HAVE_EXTRA_TESTS &suite__insn_x86, #endif &suite__intel_pt, -#endif #if defined(__x86_64__) &suite__bp_modify, #endif - &suite__x86_sample_parsing, &suite__amd_ibs_via_core_pmu, + &suite__amd_ibs_period, &suite__hybrid, + &suite__x86_topdown, NULL, }; diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c index 0924ccd9e36d..589b43273948 100644 --- a/tools/perf/arch/x86/tests/bp-modify.c +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -80,26 +80,24 @@ static int bp_modify1(void) */ if (ptrace(PTRACE_POKEUSER, child, offsetof(struct user, u_debugreg[0]), bp_2)) { - pr_debug("failed to set breakpoint, 1st time: %s\n", - strerror(errno)); + pr_debug("failed to set breakpoint, 1st time: %m\n"); goto out; } if (ptrace(PTRACE_POKEUSER, child, offsetof(struct user, u_debugreg[0]), bp_1)) { - pr_debug("failed to set breakpoint, 2nd time: %s\n", - strerror(errno)); + pr_debug("failed to set breakpoint, 2nd time: %m\n"); goto out; } if (ptrace(PTRACE_POKEUSER, child, offsetof(struct user, u_debugreg[7]), dr7)) { - pr_debug("failed to set dr7: %s\n", strerror(errno)); + pr_debug("failed to set dr7: %m\n"); goto out; } if (ptrace(PTRACE_CONT, child, NULL, NULL)) { - pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + pr_debug("failed to PTRACE_CONT: %m\n"); goto out; } @@ -112,19 +110,17 @@ static int bp_modify1(void) rip = ptrace(PTRACE_PEEKUSER, child, offsetof(struct user_regs_struct, rip), NULL); if (rip == (unsigned long) -1) { - pr_debug("failed to PTRACE_PEEKUSER: %s\n", - strerror(errno)); + pr_debug("failed to PTRACE_PEEKUSER: %m\n"); goto out; } pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); - out: if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { - pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + pr_debug("failed to PTRACE_DETACH: %m\n"); return TEST_FAIL; - } + } return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; } @@ -157,14 +153,13 @@ static int bp_modify2(void) */ if (ptrace(PTRACE_POKEUSER, child, offsetof(struct user, u_debugreg[0]), bp_1)) { - pr_debug("failed to set breakpoint: %s\n", - strerror(errno)); + pr_debug("failed to set breakpoint: %m\n"); goto out; } if (ptrace(PTRACE_POKEUSER, child, offsetof(struct user, u_debugreg[7]), dr7)) { - pr_debug("failed to set dr7: %s\n", strerror(errno)); + pr_debug("failed to set dr7: %m\n"); goto out; } @@ -175,7 +170,7 @@ static int bp_modify2(void) } if (ptrace(PTRACE_CONT, child, NULL, NULL)) { - pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + pr_debug("failed to PTRACE_CONT: %m\n"); goto out; } @@ -188,8 +183,7 @@ static int bp_modify2(void) rip = ptrace(PTRACE_PEEKUSER, child, offsetof(struct user_regs_struct, rip), NULL); if (rip == (unsigned long) -1) { - pr_debug("failed to PTRACE_PEEKUSER: %s\n", - strerror(errno)); + pr_debug("failed to PTRACE_PEEKUSER: %m\n"); goto out; } @@ -197,7 +191,7 @@ static int bp_modify2(void) out: if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { - pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + pr_debug("failed to PTRACE_DETACH: %m\n"); return TEST_FAIL; } diff --git a/tools/perf/arch/x86/tests/intel-pt-test.c b/tools/perf/arch/x86/tests/intel-pt-test.c index b217ed67cd4e..970997759ec2 100644 --- a/tools/perf/arch/x86/tests/intel-pt-test.c +++ b/tools/perf/arch/x86/tests/intel-pt-test.c @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/bits.h> #include <string.h> -#include <cpuid.h> #include <sched.h> #include "intel-pt-decoder/intel-pt-pkt-decoder.h" @@ -11,6 +10,7 @@ #include "debug.h" #include "tests/tests.h" #include "arch-tests.h" +#include "../util/cpuid.h" #include "cpumap.h" /** @@ -363,7 +363,7 @@ static int get_pt_caps(int cpu, struct pt_caps *caps) memset(caps, 0, sizeof(*caps)); for (i = 0; i < INTEL_PT_SUBLEAF_CNT; i++) { - __get_cpuid_count(20, i, &r.eax, &r.ebx, &r.ecx, &r.edx); + cpuid(20, i, &r.eax, &r.ebx, &r.ecx, &r.edx); pr_debug("CPU %d CPUID leaf 20 subleaf %d\n", cpu, i); pr_debug("eax = 0x%08x\n", r.eax); pr_debug("ebx = 0x%08x\n", r.ebx); @@ -380,7 +380,7 @@ static bool is_hybrid(void) unsigned int eax, ebx, ecx, edx = 0; bool result; - __get_cpuid_count(7, 0, &eax, &ebx, &ecx, &edx); + cpuid(7, 0, &eax, &ebx, &ecx, &edx); result = edx & BIT(15); pr_debug("Is %shybrid : CPUID leaf 7 subleaf 0 edx %#x (bit-15 indicates hybrid)\n", result ? "" : "not ", edx); diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c deleted file mode 100644 index a061e8619267..000000000000 --- a/tools/perf/arch/x86/tests/sample-parsing.c +++ /dev/null @@ -1,125 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include <stdbool.h> -#include <inttypes.h> -#include <stdlib.h> -#include <string.h> -#include <linux/bitops.h> -#include <linux/kernel.h> -#include <linux/types.h> - -#include "event.h" -#include "evsel.h" -#include "debug.h" -#include "util/sample.h" -#include "util/synthetic-events.h" - -#include "tests/tests.h" -#include "arch-tests.h" - -#define COMP(m) do { \ - if (s1->m != s2->m) { \ - pr_debug("Samples differ at '"#m"'\n"); \ - return false; \ - } \ -} while (0) - -static bool samples_same(const struct perf_sample *s1, - const struct perf_sample *s2, - u64 type) -{ - if (type & PERF_SAMPLE_WEIGHT_STRUCT) { - COMP(ins_lat); - COMP(retire_lat); - } - - return true; -} - -static int do_test(u64 sample_type) -{ - struct evsel evsel = { - .needs_swap = false, - .core = { - . attr = { - .sample_type = sample_type, - .read_format = 0, - }, - }, - }; - union perf_event *event; - struct perf_sample sample = { - .weight = 101, - .ins_lat = 102, - .retire_lat = 103, - }; - struct perf_sample sample_out; - size_t i, sz, bufsz; - int err, ret = -1; - - sz = perf_event__sample_event_size(&sample, sample_type, 0); - bufsz = sz + 4096; /* Add a bit for overrun checking */ - event = malloc(bufsz); - if (!event) { - pr_debug("malloc failed\n"); - return -1; - } - - memset(event, 0xff, bufsz); - event->header.type = PERF_RECORD_SAMPLE; - event->header.misc = 0; - event->header.size = sz; - - err = perf_event__synthesize_sample(event, sample_type, 0, &sample); - if (err) { - pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", - "perf_event__synthesize_sample", sample_type, err); - goto out_free; - } - - /* The data does not contain 0xff so we use that to check the size */ - for (i = bufsz; i > 0; i--) { - if (*(i - 1 + (u8 *)event) != 0xff) - break; - } - if (i != sz) { - pr_debug("Event size mismatch: actual %zu vs expected %zu\n", - i, sz); - goto out_free; - } - - evsel.sample_size = __evsel__sample_size(sample_type); - - err = evsel__parse_sample(&evsel, event, &sample_out); - if (err) { - pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", - "evsel__parse_sample", sample_type, err); - goto out_free; - } - - if (!samples_same(&sample, &sample_out, sample_type)) { - pr_debug("parsing failed for sample_type %#"PRIx64"\n", - sample_type); - goto out_free; - } - - ret = 0; -out_free: - free(event); - - return ret; -} - -/** - * test__x86_sample_parsing - test X86 specific sample parsing - * - * This function implements a test that synthesizes a sample event, parses it - * and then checks that the parsed sample matches the original sample. If the - * test passes %0 is returned, otherwise %-1 is returned. - * - * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type. - * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type. - */ -int test__x86_sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) -{ - return do_test(PERF_SAMPLE_WEIGHT_STRUCT); -} diff --git a/tools/perf/arch/x86/tests/topdown.c b/tools/perf/arch/x86/tests/topdown.c new file mode 100644 index 000000000000..3ee4e5e71be3 --- /dev/null +++ b/tools/perf/arch/x86/tests/topdown.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include "arch-tests.h" +#include "../util/topdown.h" +#include "debug.h" +#include "evlist.h" +#include "parse-events.h" +#include "pmu.h" +#include "pmus.h" + +static int event_cb(void *state, struct pmu_event_info *info) +{ + char buf[256]; + struct parse_events_error parse_err; + int *ret = state, err; + struct evlist *evlist = evlist__new(); + struct evsel *evsel; + + if (!evlist) + return -ENOMEM; + + parse_events_error__init(&parse_err); + snprintf(buf, sizeof(buf), "%s/%s/", info->pmu->name, info->name); + err = parse_events(evlist, buf, &parse_err); + if (err) { + parse_events_error__print(&parse_err, buf); + *ret = TEST_FAIL; + } + parse_events_error__exit(&parse_err); + evlist__for_each_entry(evlist, evsel) { + bool fail = false; + bool p_core_pmu = evsel->pmu->type == PERF_TYPE_RAW; + const char *name = evsel__name(evsel); + + if (strcasestr(name, "uops_retired.slots") || + strcasestr(name, "topdown.backend_bound_slots") || + strcasestr(name, "topdown.br_mispredict_slots") || + strcasestr(name, "topdown.memory_bound_slots") || + strcasestr(name, "topdown.bad_spec_slots") || + strcasestr(name, "topdown.slots_p")) { + if (arch_is_topdown_slots(evsel) || arch_is_topdown_metrics(evsel)) + fail = true; + } else if (strcasestr(name, "slots")) { + if (arch_is_topdown_slots(evsel) != p_core_pmu || + arch_is_topdown_metrics(evsel)) + fail = true; + } else if (strcasestr(name, "topdown")) { + if (arch_is_topdown_slots(evsel) || + arch_is_topdown_metrics(evsel) != p_core_pmu) + fail = true; + } else if (arch_is_topdown_slots(evsel) || arch_is_topdown_metrics(evsel)) { + fail = true; + } + if (fail) { + pr_debug("Broken topdown information for '%s'\n", evsel__name(evsel)); + *ret = TEST_FAIL; + } + } + evlist__delete(evlist); + return 0; +} + +static int test__x86_topdown(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + int ret = TEST_OK; + struct perf_pmu *pmu = NULL; + + if (!topdown_sys_has_perf_metrics()) + return TEST_OK; + + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + if (perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/false, &ret, event_cb)) + break; + } + return ret; +} + +DEFINE_SUITE("x86 topdown", x86_topdown); diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 06d7c0205b3d..b94c91984c66 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -1,8 +1,6 @@ perf-util-y += header.o perf-util-y += tsc.o perf-util-y += pmu.o -perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o -perf-util-y += perf_regs.o perf-util-y += topdown.o perf-util-y += machine.o perf-util-y += event.o @@ -12,9 +10,7 @@ perf-util-y += evsel.o perf-util-y += iostat.o perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o -perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o -perf-util-$(CONFIG_AUXTRACE) += auxtrace.o -perf-util-y += archinsn.o -perf-util-$(CONFIG_AUXTRACE) += intel-pt.o -perf-util-$(CONFIG_AUXTRACE) += intel-bts.o +perf-util-y += auxtrace.o +perf-util-y += intel-pt.o +perf-util-y += intel-bts.o diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c deleted file mode 100644 index 546feda08428..000000000000 --- a/tools/perf/arch/x86/util/archinsn.c +++ /dev/null @@ -1,27 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "archinsn.h" -#include "event.h" -#include "machine.h" -#include "thread.h" -#include "symbol.h" -#include "../../../../arch/x86/include/asm/insn.h" - -void arch_fetch_insn(struct perf_sample *sample, - struct thread *thread, - struct machine *machine) -{ - struct insn insn; - int len, ret; - bool is64bit = false; - - if (!sample->ip) - return; - len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit); - if (len <= 0) - return; - - 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/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index a0400707180c..3cd384317739 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -91,49 +91,3 @@ int perf_event__synthesize_extra_kmaps(const struct perf_tool *tool, } #endif - -void arch_perf_parse_sample_weight(struct perf_sample *data, - const __u64 *array, u64 type) -{ - union perf_sample_weight weight; - - weight.full = *array; - if (type & PERF_SAMPLE_WEIGHT) - data->weight = weight.full; - else { - data->weight = weight.var1_dw; - data->ins_lat = weight.var2_w; - data->retire_lat = weight.var3_w; - } -} - -void arch_perf_synthesize_sample_weight(const struct perf_sample *data, - __u64 *array, u64 type) -{ - *array = data->weight; - - if (type & PERF_SAMPLE_WEIGHT_STRUCT) { - *array &= 0xffffffff; - *array |= ((u64)data->ins_lat << 32); - *array |= ((u64)data->retire_lat << 48); - } -} - -const char *arch_perf_header_entry(const char *se_header) -{ - if (!strcmp(se_header, "Local Pipeline Stage Cycle")) - return "Local Retire Latency"; - else if (!strcmp(se_header, "Pipeline Stage Cycle")) - return "Retire Latency"; - - return se_header; -} - -int arch_support_sort_key(const char *sort_key) -{ - if (!strcmp(sort_key, "p_stage_cyc")) - return 1; - if (!strcmp(sort_key, "local_p_stage_cyc")) - return 1; - return 0; -} diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index 1969758cc8c1..75e9d00a1494 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -81,3 +81,27 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) /* Default ordering by insertion index. */ return lhs->core.idx - rhs->core.idx; } + +int arch_evlist__add_required_events(struct list_head *list) +{ + struct evsel *pos, *metric_event = NULL; + int idx = 0; + + if (!topdown_sys_has_perf_metrics()) + return 0; + + list_for_each_entry(pos, list, core.node) { + if (arch_is_topdown_slots(pos)) { + /* Slots event already present, nothing to do. */ + return 0; + } + if (metric_event == NULL && arch_is_topdown_metrics(pos)) + metric_event = pos; + idx++; + } + if (metric_event == NULL) { + /* No topdown metric events, nothing to do. */ + return 0; + } + return topdown_insert_slots_event(list, idx + 1, metric_event); +} diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c index 3dd29ba2c23b..23a8e662a912 100644 --- a/tools/perf/arch/x86/util/evsel.c +++ b/tools/perf/arch/x86/util/evsel.c @@ -1,10 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 +#include <errno.h> #include <stdio.h> #include <stdlib.h> +#include "util/evlist.h" #include "util/evsel.h" +#include "util/evsel_config.h" #include "util/env.h" #include "util/pmu.h" #include "util/pmus.h" +#include "util/stat.h" +#include "util/strbuf.h" #include "linux/string.h" #include "topdown.h" #include "evsel.h" @@ -23,47 +28,25 @@ void arch_evsel__set_sample_weight(struct evsel *evsel) bool evsel__sys_has_perf_metrics(const struct evsel *evsel) { struct perf_pmu *pmu; - u32 type = evsel->core.attr.type; - /* - * The PERF_TYPE_RAW type is the core PMU type, e.g., "cpu" PMU - * on a non-hybrid machine, "cpu_core" PMU on a hybrid machine. - * The slots event is only available for the core PMU, which - * supports the perf metrics feature. - * Checking both the PERF_TYPE_RAW type and the slots event - * should be good enough to detect the perf metrics feature. - */ -again: - switch (type) { - case PERF_TYPE_HARDWARE: - case PERF_TYPE_HW_CACHE: - type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT; - if (type) - goto again; - break; - case PERF_TYPE_RAW: - break; - default: + if (!topdown_sys_has_perf_metrics()) return false; - } - pmu = evsel->pmu; - if (pmu && perf_pmu__is_fake(pmu)) - pmu = NULL; - - if (!pmu) { - while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { - if (pmu->type == PERF_TYPE_RAW) - break; - } - } - return pmu && perf_pmu__have_event(pmu, "slots"); + /* + * The PERF_TYPE_RAW type is the core PMU type, e.g., "cpu" PMU on a + * non-hybrid machine, "cpu_core" PMU on a hybrid machine. The + * topdown_sys_has_perf_metrics checks the slots event is only available + * for the core PMU, which supports the perf metrics feature. Checking + * both the PERF_TYPE_RAW type and the slots event should be good enough + * to detect the perf metrics feature. + */ + pmu = evsel__find_pmu(evsel); + return pmu && pmu->type == PERF_TYPE_RAW; } bool arch_evsel__must_be_in_group(const struct evsel *evsel) { - if (!evsel__sys_has_perf_metrics(evsel) || !evsel->name || - strcasestr(evsel->name, "uops_retired.slots")) + if (!evsel__sys_has_perf_metrics(evsel)) return false; return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel); @@ -89,6 +72,57 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size) event_name); } +void arch_evsel__apply_ratio_to_prev(struct evsel *evsel, + struct perf_event_attr *attr) +{ + struct perf_event_attr *prev_attr = NULL; + struct evsel *evsel_prev = NULL; + const char *name = "acr_mask"; + int evsel_idx = 0; + __u64 ev_mask, pr_ev_mask; + + if (!perf_pmu__has_format(evsel->pmu, name)) { + pr_err("'%s' does not have acr_mask format support\n", evsel->pmu->name); + return; + } + if (perf_pmu__format_type(evsel->pmu, name) != + PERF_PMU_FORMAT_VALUE_CONFIG2) { + pr_err("'%s' does not have config2 format support\n", evsel->pmu->name); + return; + } + + evsel_prev = evsel__prev(evsel); + if (!evsel_prev) { + pr_err("Previous event does not exist.\n"); + return; + } + + prev_attr = &evsel_prev->core.attr; + + if (prev_attr->config2) { + pr_err("'%s' has set config2 (acr_mask?) already, configuration not supported\n", evsel_prev->name); + return; + } + + /* + * acr_mask (config2) is calculated using the event's index in + * the event group. The first event will use the index of the + * second event as its mask (e.g., 0x2), indicating that the + * second event counter will be reset and a sample taken for + * the first event if its counter overflows. The second event + * will use the mask consisting of the first and second bits + * (e.g., 0x3), meaning both counters will be reset if the + * second event counter overflows. + */ + + evsel_idx = evsel__group_idx(evsel); + ev_mask = 1ull << evsel_idx; + pr_ev_mask = 1ull << (evsel_idx - 1); + + prev_attr->config2 = ev_mask; + attr->config2 = ev_mask | pr_ev_mask; +} + static void ibs_l3miss_warn(void) { pr_warning( @@ -124,13 +158,15 @@ 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) +static int amd_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size) { - if (!x86__is_amd_cpu()) + struct perf_pmu *pmu; + + if (evsel->core.attr.precise_ip == 0) return 0; - if (!evsel->core.attr.precise_ip && - !(evsel->pmu && !strncmp(evsel->pmu->name, "ibs", 3))) + pmu = evsel__find_pmu(evsel); + if (!pmu || strncmp(pmu->name, "ibs", 3)) return 0; /* More verbose IBS errors. */ @@ -140,6 +176,54 @@ int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size) return scnprintf(msg, size, "AMD IBS doesn't support privilege filtering. Try " "again without the privilege modifiers (like 'k') at the end."); } + return 0; +} + +static int intel_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size) +{ + struct strbuf sb = STRBUF_INIT; + int ret; + if (err != EINVAL) + return 0; + + if (!topdown_sys_has_perf_metrics()) + return 0; + + if (arch_is_topdown_slots(evsel)) { + if (!evsel__is_group_leader(evsel)) { + evlist__uniquify_evsel_names(evsel->evlist, &stat_config); + evlist__format_evsels(evsel->evlist, &sb, 2048); + ret = scnprintf(msg, size, "Topdown slots event can only be group leader " + "in '%s'.", sb.buf); + strbuf_release(&sb); + return ret; + } + } else if (arch_is_topdown_metrics(evsel)) { + struct evsel *pos; + + evlist__for_each_entry(evsel->evlist, pos) { + if (pos == evsel || !arch_is_topdown_metrics(pos)) + continue; + + if (pos->core.attr.config != evsel->core.attr.config) + continue; + + evlist__uniquify_evsel_names(evsel->evlist, &stat_config); + evlist__format_evsels(evsel->evlist, &sb, 2048); + ret = scnprintf(msg, size, "Perf metric event '%s' is duplicated " + "in the same group (only one event is allowed) in '%s'.", + evsel__name(evsel), sb.buf); + strbuf_release(&sb); + return ret; + } + } return 0; } + +int arch_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size) +{ + return x86__is_amd_cpu() + ? amd_evsel__open_strerror(evsel, msg, size) + : intel_evsel__open_strerror(evsel, err, msg, size); +} diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 8f235d8b67b6..c131a727774f 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -12,13 +12,13 @@ #include <linux/log2.h> #include <linux/zalloc.h> #include <linux/err.h> -#include <cpuid.h> #include "../../../util/session.h" #include "../../../util/event.h" #include "../../../util/evlist.h" #include "../../../util/evsel.h" #include "../../../util/evsel_config.h" +#include "../../../util/config.h" #include "../../../util/cpumap.h" #include "../../../util/mmap.h" #include <subcmd/parse-options.h> @@ -33,6 +33,7 @@ #include <internal/lib.h> // page_size #include "../../../util/intel-pt.h" #include <api/fs/fs.h> +#include "cpuid.h" #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -52,6 +53,7 @@ struct intel_pt_recording { struct perf_pmu *intel_pt_pmu; int have_sched_switch; struct evlist *evlist; + bool all_switch_events; bool snapshot_mode; bool snapshot_init_done; size_t snapshot_size; @@ -70,7 +72,7 @@ static int intel_pt_parse_terms_with_default(const struct perf_pmu *pmu, int err; parse_events_terms__init(&terms); - err = parse_events_terms(&terms, str, /*input=*/ NULL); + err = parse_events_terms(&terms, str); if (err) goto out_free; @@ -309,7 +311,7 @@ static void intel_pt_tsc_ctc_ratio(u32 *n, u32 *d) { unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0; - __get_cpuid(0x15, &eax, &ebx, &ecx, &edx); + cpuid(0x15, 0, &eax, &ebx, &ecx, &edx); *n = ebx; *d = eax; } @@ -662,8 +664,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, return 0; if (opts->auxtrace_sample_mode) - evsel__set_config_if_unset(intel_pt_pmu, intel_pt_evsel, - "psb_period", 0); + evsel__set_config_if_unset(intel_pt_evsel, "psb_period", 0); err = intel_pt_validate_config(intel_pt_pmu, intel_pt_evsel); if (err) @@ -794,7 +795,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, bool cpu_wide = !target__none(&opts->target) && !target__has_task(&opts->target); - if (!cpu_wide && perf_can_record_cpu_wide()) { + if (ptr->all_switch_events && !cpu_wide && perf_can_record_cpu_wide()) { struct evsel *switch_evsel; switch_evsel = evlist__add_dummy_on_all_cpus(evlist); @@ -1178,6 +1179,16 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused) return rdtsc(); } +static int intel_pt_perf_config(const char *var, const char *value, void *data) +{ + struct intel_pt_recording *ptr = data; + + if (!strcmp(var, "intel-pt.all-switch-events")) + ptr->all_switch_events = perf_config_bool(var, value); + + return 0; +} + struct auxtrace_record *intel_pt_recording_init(int *err) { struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME); @@ -1197,6 +1208,8 @@ struct auxtrace_record *intel_pt_recording_init(int *err) return NULL; } + perf_config(intel_pt_perf_config, ptr); + ptr->intel_pt_pmu = intel_pt_pmu; ptr->itr.recording_options = intel_pt_recording_options; ptr->itr.info_priv_size = intel_pt_info_priv_size; diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c deleted file mode 100644 index 424716518b75..000000000000 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ /dev/null @@ -1,213 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <string.h> -#include "../../../util/kvm-stat.h" -#include "../../../util/evsel.h" -#include <asm/svm.h> -#include <asm/vmx.h> -#include <asm/kvm.h> - -define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS); -define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS); - -static 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" -}; - -const char *vcpu_id_str = "vcpu_id"; -const char *kvm_exit_reason = "exit_reason"; -const char *kvm_entry_trace = "kvm:kvm_entry"; -const char *kvm_exit_trace = "kvm:kvm_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 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 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 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" -}; - -const char *kvm_events_tp[] = { - "kvm:kvm_entry", - "kvm:kvm_exit", - "kvm:kvm_mmio", - "kvm:kvm_pio", - "kvm:kvm_msr", - NULL, -}; - -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 }, -}; - -const char * const kvm_skip_events[] = { - "HLT", - NULL, -}; - -int cpu_isa_init(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; -} diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c index 62df03e91c7e..b38f519020ff 100644 --- a/tools/perf/arch/x86/util/mem-events.c +++ b/tools/perf/arch/x86/util/mem-events.c @@ -26,3 +26,9 @@ struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = { E(NULL, NULL, NULL, false, 0), E("mem-ldst", "%s//", NULL, false, 0), }; + +struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX] = { + E(NULL, NULL, NULL, false, 0), + E(NULL, NULL, NULL, false, 0), + E("mem-ldst", "%s/ldlat=%u/", NULL, true, 0), +}; diff --git a/tools/perf/arch/x86/util/mem-events.h b/tools/perf/arch/x86/util/mem-events.h index f55c8d3b7d59..11e09a256f5b 100644 --- a/tools/perf/arch/x86/util/mem-events.h +++ b/tools/perf/arch/x86/util/mem-events.h @@ -6,5 +6,6 @@ extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX]; extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX]; extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX]; +extern struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX]; #endif /* _X86_MEM_EVENTS_H */ diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c deleted file mode 100644 index 12fd93f04802..000000000000 --- a/tools/perf/arch/x86/util/perf_regs.c +++ /dev/null @@ -1,330 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <string.h> -#include <regex.h> -#include <linux/kernel.h> -#include <linux/zalloc.h> - -#include "perf_regs.h" -#include "../../../perf-sys.h" -#include "../../../util/perf_regs.h" -#include "../../../util/debug.h" -#include "../../../util/event.h" -#include "../../../util/pmu.h" -#include "../../../util/pmus.h" - -static const struct sample_reg sample_reg_masks[] = { - SMPL_REG(AX, PERF_REG_X86_AX), - SMPL_REG(BX, PERF_REG_X86_BX), - SMPL_REG(CX, PERF_REG_X86_CX), - SMPL_REG(DX, PERF_REG_X86_DX), - SMPL_REG(SI, PERF_REG_X86_SI), - SMPL_REG(DI, PERF_REG_X86_DI), - SMPL_REG(BP, PERF_REG_X86_BP), - SMPL_REG(SP, PERF_REG_X86_SP), - SMPL_REG(IP, PERF_REG_X86_IP), - SMPL_REG(FLAGS, PERF_REG_X86_FLAGS), - SMPL_REG(CS, PERF_REG_X86_CS), - SMPL_REG(SS, PERF_REG_X86_SS), -#ifdef HAVE_ARCH_X86_64_SUPPORT - SMPL_REG(R8, PERF_REG_X86_R8), - SMPL_REG(R9, PERF_REG_X86_R9), - SMPL_REG(R10, PERF_REG_X86_R10), - SMPL_REG(R11, PERF_REG_X86_R11), - SMPL_REG(R12, PERF_REG_X86_R12), - SMPL_REG(R13, PERF_REG_X86_R13), - SMPL_REG(R14, PERF_REG_X86_R14), - SMPL_REG(R15, PERF_REG_X86_R15), -#endif - SMPL_REG2(XMM0, PERF_REG_X86_XMM0), - SMPL_REG2(XMM1, PERF_REG_X86_XMM1), - SMPL_REG2(XMM2, PERF_REG_X86_XMM2), - SMPL_REG2(XMM3, PERF_REG_X86_XMM3), - SMPL_REG2(XMM4, PERF_REG_X86_XMM4), - SMPL_REG2(XMM5, PERF_REG_X86_XMM5), - SMPL_REG2(XMM6, PERF_REG_X86_XMM6), - SMPL_REG2(XMM7, PERF_REG_X86_XMM7), - SMPL_REG2(XMM8, PERF_REG_X86_XMM8), - SMPL_REG2(XMM9, PERF_REG_X86_XMM9), - SMPL_REG2(XMM10, PERF_REG_X86_XMM10), - SMPL_REG2(XMM11, PERF_REG_X86_XMM11), - SMPL_REG2(XMM12, PERF_REG_X86_XMM12), - SMPL_REG2(XMM13, PERF_REG_X86_XMM13), - SMPL_REG2(XMM14, PERF_REG_X86_XMM14), - SMPL_REG2(XMM15, PERF_REG_X86_XMM15), - SMPL_REG_END -}; - -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 arch_sdt_arg_parse_op(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; -} - -const struct sample_reg *arch__sample_reg_masks(void) -{ - return sample_reg_masks; -} - -uint64_t arch__intr_reg_mask(void) -{ - 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; - /* - * 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, 0, -1, -1, 0); - if (fd != -1) { - close(fd); - return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK); - } - - return PERF_REGS_MASK; -} - -uint64_t arch__user_reg_mask(void) -{ - return PERF_REGS_MASK; -} diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index e0060dac2a9f..a3f96221758d 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -8,6 +8,8 @@ #include <linux/perf_event.h> #include <linux/zalloc.h> #include <api/fs/fs.h> +#include <api/io_dir.h> +#include <internal/cpumap.h> #include <errno.h> #include "../../../util/intel-pt.h" @@ -16,11 +18,261 @@ #include "../../../util/fncache.h" #include "../../../util/pmus.h" #include "mem-events.h" +#include "util/debug.h" #include "util/env.h" +#include "util/header.h" -void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) +static bool x86__is_intel_graniterapids(void) { -#ifdef HAVE_AUXTRACE_SUPPORT + static bool checked_if_graniterapids; + static bool is_graniterapids; + + if (!checked_if_graniterapids) { + const char *graniterapids_cpuid = "GenuineIntel-6-A[DE]"; + char *cpuid = get_cpuid_str((struct perf_cpu){0}); + + is_graniterapids = cpuid && strcmp_cpuid_str(graniterapids_cpuid, cpuid) == 0; + free(cpuid); + checked_if_graniterapids = true; + } + return is_graniterapids; +} + +static struct perf_cpu_map *read_sysfs_cpu_map(const char *sysfs_path) +{ + struct perf_cpu_map *cpus; + char *buf = NULL; + size_t buf_len; + + if (sysfs__read_str(sysfs_path, &buf, &buf_len) < 0) + return NULL; + + cpus = perf_cpu_map__new(buf); + free(buf); + return cpus; +} + +static int snc_nodes_per_l3_cache(void) +{ + static bool checked_snc; + static int snc_nodes; + + if (!checked_snc) { + struct perf_cpu_map *node_cpus = + read_sysfs_cpu_map("devices/system/node/node0/cpulist"); + struct perf_cpu_map *cache_cpus = + read_sysfs_cpu_map("devices/system/cpu/cpu0/cache/index3/shared_cpu_list"); + + snc_nodes = perf_cpu_map__nr(cache_cpus) / perf_cpu_map__nr(node_cpus); + perf_cpu_map__put(cache_cpus); + perf_cpu_map__put(node_cpus); + checked_snc = true; + } + return snc_nodes; +} + +static bool starts_with(const char *str, const char *prefix) +{ + return !strncmp(prefix, str, strlen(prefix)); +} + +static int num_chas(void) +{ + static bool checked_chas; + static int num_chas; + + if (!checked_chas) { + int fd = perf_pmu__event_source_devices_fd(); + struct io_dir dir; + struct io_dirent64 *dent; + + if (fd < 0) + return -1; + + io_dir__init(&dir, fd); + + while ((dent = io_dir__readdir(&dir)) != NULL) { + /* Note, dent->d_type will be DT_LNK and so isn't a useful filter. */ + if (starts_with(dent->d_name, "uncore_cha_")) + num_chas++; + } + close(fd); + checked_chas = true; + } + return num_chas; +} + +#define MAX_SNCS 6 + +static int uncore_cha_snc(struct perf_pmu *pmu) +{ + // CHA SNC numbers are ordered correspond to the CHAs number. + unsigned int cha_num; + int num_cha, chas_per_node, cha_snc; + int snc_nodes = snc_nodes_per_l3_cache(); + + if (snc_nodes <= 1) + return 0; + + num_cha = num_chas(); + if (num_cha <= 0) { + pr_warning("Unexpected: no CHAs found\n"); + return 0; + } + + /* Compute SNC for PMU. */ + if (sscanf(pmu->name, "uncore_cha_%u", &cha_num) != 1) { + pr_warning("Unexpected: unable to compute CHA number '%s'\n", pmu->name); + return 0; + } + chas_per_node = num_cha / snc_nodes; + cha_snc = cha_num / chas_per_node; + + /* Range check cha_snc. for unexpected out of bounds. */ + return cha_snc >= MAX_SNCS ? 0 : cha_snc; +} + +static int uncore_imc_snc(struct perf_pmu *pmu) +{ + // Compute the IMC SNC using lookup tables. + unsigned int imc_num; + int snc_nodes = snc_nodes_per_l3_cache(); + const u8 snc2_map[] = {1, 1, 0, 0, 1, 1, 0, 0}; + const u8 snc3_map[] = {1, 1, 0, 0, 2, 2, 1, 1, 0, 0, 2, 2}; + const u8 *snc_map; + size_t snc_map_len; + + switch (snc_nodes) { + case 2: + snc_map = snc2_map; + snc_map_len = ARRAY_SIZE(snc2_map); + break; + case 3: + snc_map = snc3_map; + snc_map_len = ARRAY_SIZE(snc3_map); + break; + default: + /* Error or no lookup support for SNC with >3 nodes. */ + return 0; + } + + /* Compute SNC for PMU. */ + if (sscanf(pmu->name, "uncore_imc_%u", &imc_num) != 1) { + pr_warning("Unexpected: unable to compute IMC number '%s'\n", pmu->name); + return 0; + } + if (imc_num >= snc_map_len) { + pr_warning("Unexpected IMC %d for SNC%d mapping\n", imc_num, snc_nodes); + return 0; + } + return snc_map[imc_num]; +} + +static int uncore_cha_imc_compute_cpu_adjust(int pmu_snc) +{ + static bool checked_cpu_adjust[MAX_SNCS]; + static int cpu_adjust[MAX_SNCS]; + struct perf_cpu_map *node_cpus; + char node_path[] = "devices/system/node/node0/cpulist"; + + /* Was adjust already computed? */ + if (checked_cpu_adjust[pmu_snc]) + return cpu_adjust[pmu_snc]; + + /* SNC0 doesn't need an adjust. */ + if (pmu_snc == 0) { + cpu_adjust[0] = 0; + checked_cpu_adjust[0] = true; + return 0; + } + + /* + * Use NUMA topology to compute first CPU of the NUMA node, we want to + * adjust CPU 0 to be this and similarly for other CPUs if there is >1 + * socket. + */ + assert(pmu_snc >= 0 && pmu_snc <= 9); + node_path[24] += pmu_snc; // Shift node0 to be node<pmu_snc>. + node_cpus = read_sysfs_cpu_map(node_path); + cpu_adjust[pmu_snc] = perf_cpu_map__cpu(node_cpus, 0).cpu; + if (cpu_adjust[pmu_snc] < 0) { + pr_debug("Failed to read valid CPU list from <sysfs>/%s\n", node_path); + cpu_adjust[pmu_snc] = 0; + } else { + checked_cpu_adjust[pmu_snc] = true; + } + perf_cpu_map__put(node_cpus); + return cpu_adjust[pmu_snc]; +} + +static void gnr_uncore_cha_imc_adjust_cpumask_for_snc(struct perf_pmu *pmu, bool cha) +{ + // With sub-NUMA clustering (SNC) there is a NUMA node per SNC in the + // topology. For example, a two socket graniterapids machine may be set + // up with 3-way SNC meaning there are 6 NUMA nodes that should be + // displayed with --per-node. The cpumask of the CHA and IMC PMUs + // reflects per-socket information meaning, for example, uncore_cha_60 + // on a two socket graniterapids machine with 120 cores per socket will + // have a cpumask of "0,120". This cpumask needs adjusting to "40,160" + // to reflect that uncore_cha_60 is used for the 2nd SNC of each + // socket. Without the adjustment events on uncore_cha_60 will appear in + // node 0 and node 3 (in our example 2 socket 3-way set up), but with + // the adjustment they will appear in node 1 and node 4. The number of + // CHAs is typically larger than the number of cores. The CHA numbers + // are assumed to split evenly and inorder wrt core numbers. There are + // fewer memory IMC PMUs than cores and mapping is handled using lookup + // tables. + static struct perf_cpu_map *cha_adjusted[MAX_SNCS]; + static struct perf_cpu_map *imc_adjusted[MAX_SNCS]; + struct perf_cpu_map **adjusted = cha ? cha_adjusted : imc_adjusted; + int idx, pmu_snc, cpu_adjust; + struct perf_cpu cpu; + bool alloc; + + // Cpus from the kernel holds first CPU of each socket. e.g. 0,120. + if (perf_cpu_map__cpu(pmu->cpus, 0).cpu != 0) { + pr_debug("Ignoring cpumask adjust for %s as unexpected first CPU\n", pmu->name); + return; + } + + pmu_snc = cha ? uncore_cha_snc(pmu) : uncore_imc_snc(pmu); + if (pmu_snc == 0) { + // No adjustment necessary for the first SNC. + return; + } + + alloc = adjusted[pmu_snc] == NULL; + if (alloc) { + // Hold onto the perf_cpu_map globally to avoid recomputation. + cpu_adjust = uncore_cha_imc_compute_cpu_adjust(pmu_snc); + adjusted[pmu_snc] = perf_cpu_map__empty_new(perf_cpu_map__nr(pmu->cpus)); + if (!adjusted[pmu_snc]) + return; + } + + perf_cpu_map__for_each_cpu(cpu, idx, pmu->cpus) { + // Compute the new cpu map values or if not allocating, assert + // that they match expectations. asserts will be removed to + // avoid overhead in NDEBUG builds. + if (alloc) { + RC_CHK_ACCESS(adjusted[pmu_snc])->map[idx].cpu = cpu.cpu + cpu_adjust; + } else if (idx == 0) { + cpu_adjust = perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu - cpu.cpu; + assert(uncore_cha_imc_compute_cpu_adjust(pmu_snc) == cpu_adjust); + } else { + assert(perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu == + cpu.cpu + cpu_adjust); + } + } + + perf_cpu_map__put(pmu->cpus); + pmu->cpus = perf_cpu_map__get(adjusted[pmu_snc]); +} + +void perf_pmu__arch_init(struct perf_pmu *pmu) +{ + struct perf_pmu_caps *ldlat_cap; + if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) { pmu->auxtrace = true; pmu->selectable = true; @@ -30,15 +282,33 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) pmu->auxtrace = true; pmu->selectable = true; } -#endif if (x86__is_amd_cpu()) { - if (!strcmp(pmu->name, "ibs_op")) - pmu->mem_events = perf_mem_events_amd; - } else if (pmu->is_core) { - if (perf_pmu__have_event(pmu, "mem-loads-aux")) - pmu->mem_events = perf_mem_events_intel_aux; - else - pmu->mem_events = perf_mem_events_intel; + if (strcmp(pmu->name, "ibs_op")) + return; + + pmu->mem_events = perf_mem_events_amd; + + if (!perf_pmu__caps_parse(pmu)) + return; + + ldlat_cap = perf_pmu__get_cap(pmu, "ldlat"); + if (!ldlat_cap || strcmp(ldlat_cap->value, "1")) + return; + + perf_mem_events__loads_ldlat = 0; + pmu->mem_events = perf_mem_events_amd_ldlat; + } else { + if (pmu->is_core) { + if (perf_pmu__have_event(pmu, "mem-loads-aux")) + pmu->mem_events = perf_mem_events_intel_aux; + else + pmu->mem_events = perf_mem_events_intel; + } else if (x86__is_intel_graniterapids()) { + if (starts_with(pmu->name, "uncore_cha_")) + gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/true); + else if (starts_with(pmu->name, "uncore_imc_")) + gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/false); + } } } diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c index d1c654839049..bafd285119d7 100644 --- a/tools/perf/arch/x86/util/topdown.c +++ b/tools/perf/arch/x86/util/topdown.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "api/fs/fs.h" -#include "util/evsel.h" +#include <errno.h> #include "util/evlist.h" #include "util/pmu.h" #include "util/pmus.h" @@ -8,6 +7,9 @@ #include "topdown.h" #include "evsel.h" +// cmask=0, inv=0, pc=0, edge=0, umask=4, event=0 +#define TOPDOWN_SLOTS 0x0400 + /* Check whether there is a PMU which supports the perf metrics. */ bool topdown_sys_has_perf_metrics(void) { @@ -32,31 +34,19 @@ bool topdown_sys_has_perf_metrics(void) return has_perf_metrics; } -#define TOPDOWN_SLOTS 0x0400 bool arch_is_topdown_slots(const struct evsel *evsel) { - if (evsel->core.attr.config == TOPDOWN_SLOTS) - return true; - - return false; + return evsel->core.attr.type == PERF_TYPE_RAW && + evsel->core.attr.config == TOPDOWN_SLOTS && + evsel->core.attr.config1 == 0; } bool arch_is_topdown_metrics(const struct evsel *evsel) { - int config = evsel->core.attr.config; - const char *name_from_config; - struct perf_pmu *pmu; - - /* All topdown events have an event code of 0. */ - if ((config & 0xFF) != 0) - return false; - - pmu = evsel__find_pmu(evsel); - if (!pmu || !pmu->is_core) - return false; - - name_from_config = perf_pmu__name_from_config(pmu, config); - return name_from_config && strcasestr(name_from_config, "topdown"); + // cmask=0, inv=0, pc=0, edge=0, umask=0x80-0x87, event=0 + return evsel->core.attr.type == PERF_TYPE_RAW && + (evsel->core.attr.config & 0xFFFFF8FF) == 0x8000 && + evsel->core.attr.config1 == 0; } /* @@ -88,3 +78,31 @@ bool arch_topdown_sample_read(struct evsel *leader) return false; } + +/* + * Make a copy of the topdown metric event metric_event with the given index but + * change its configuration to be a topdown slots event. Copying from + * metric_event ensures modifiers are the same. + */ +int topdown_insert_slots_event(struct list_head *list, int idx, struct evsel *metric_event) +{ + struct evsel *evsel = evsel__new_idx(&metric_event->core.attr, idx); + + if (!evsel) + return -ENOMEM; + + evsel->core.attr.config = TOPDOWN_SLOTS; + evsel->core.cpus = perf_cpu_map__get(metric_event->core.cpus); + evsel->core.pmu_cpus = perf_cpu_map__get(metric_event->core.pmu_cpus); + evsel->core.is_pmu_core = true; + evsel->pmu = metric_event->pmu; + evsel->name = strdup("slots"); + evsel->precise_max = metric_event->precise_max; + evsel->sample_read = metric_event->sample_read; + evsel->weak_group = metric_event->weak_group; + evsel->bpf_counter = metric_event->bpf_counter; + evsel->retire_lat = metric_event->retire_lat; + evsel__set_leader(evsel, evsel__leader(metric_event)); + list_add_tail(&evsel->core.node, list); + return 0; +} diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h index 1bae9b1822d7..69035565e649 100644 --- a/tools/perf/arch/x86/util/topdown.h +++ b/tools/perf/arch/x86/util/topdown.h @@ -2,8 +2,14 @@ #ifndef _TOPDOWN_H #define _TOPDOWN_H 1 +#include <stdbool.h> + +struct evsel; +struct list_head; + bool topdown_sys_has_perf_metrics(void); bool arch_is_topdown_slots(const struct evsel *evsel); bool arch_is_topdown_metrics(const struct evsel *evsel); +int topdown_insert_slots_event(struct list_head *list, int idx, struct evsel *metric_event); #endif diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c deleted file mode 100644 index 798493e887d7..000000000000 --- a/tools/perf/arch/x86/util/unwind-libdw.c +++ /dev/null @@ -1,54 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <elfutils/libdwfl.h> -#include "perf_regs.h" -#include "../../../util/unwind-libdw.h" -#include "../../../util/perf_regs.h" -#include "util/sample.h" - -bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) -{ - struct unwind_info *ui = arg; - struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); - Dwarf_Word dwarf_regs[17]; - unsigned nregs; - -#define REG(r) ({ \ - Dwarf_Word val = 0; \ - perf_reg_value(&val, user_regs, PERF_REG_X86_##r); \ - val; \ -}) - - if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) { - dwarf_regs[0] = REG(AX); - dwarf_regs[1] = REG(CX); - dwarf_regs[2] = REG(DX); - dwarf_regs[3] = REG(BX); - dwarf_regs[4] = REG(SP); - dwarf_regs[5] = REG(BP); - dwarf_regs[6] = REG(SI); - dwarf_regs[7] = REG(DI); - dwarf_regs[8] = REG(IP); - nregs = 9; - } else { - dwarf_regs[0] = REG(AX); - dwarf_regs[1] = REG(DX); - dwarf_regs[2] = REG(CX); - dwarf_regs[3] = REG(BX); - dwarf_regs[4] = REG(SI); - dwarf_regs[5] = REG(DI); - dwarf_regs[6] = REG(BP); - dwarf_regs[7] = REG(SP); - dwarf_regs[8] = REG(R8); - dwarf_regs[9] = REG(R9); - dwarf_regs[10] = REG(R10); - dwarf_regs[11] = REG(R11); - dwarf_regs[12] = REG(R12); - dwarf_regs[13] = REG(R13); - dwarf_regs[14] = REG(R14); - dwarf_regs[15] = REG(R15); - dwarf_regs[16] = REG(IP); - nregs = 17; - } - - return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs); -} diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl index 37effc1b134e..a9bca4e484de 100644 --- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl @@ -437,3 +437,8 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 common rseq_slice_yield sys_rseq_slice_yield |