diff options
Diffstat (limited to '')
36 files changed, 2342 insertions, 0 deletions
diff --git a/tools/perf/arch/arm/Build b/tools/perf/arch/arm/Build new file mode 100644 index 000000000..41bf61da4 --- /dev/null +++ b/tools/perf/arch/arm/Build @@ -0,0 +1,2 @@ +libperf-y += util/ +libperf-$(CONFIG_DWARF_UNWIND) += tests/ diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile new file mode 100644 index 000000000..18b13518d --- /dev/null +++ b/tools/perf/arch/arm/Makefile @@ -0,0 +1,4 @@ +ifndef NO_DWARF +PERF_HAVE_DWARF_REGS := 1 +endif +PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c new file mode 100644 index 000000000..f64516d5b --- /dev/null +++ b/tools/perf/arch/arm/annotate/instructions.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <regex.h> + +struct arm_annotate { + regex_t call_insn, + jump_insn; +}; + +static struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const char *name) +{ + struct arm_annotate *arm = arch->priv; + struct ins_ops *ops; + regmatch_t match[2]; + + if (!regexec(&arm->call_insn, name, 2, match, 0)) + ops = &call_ops; + else if (!regexec(&arm->jump_insn, name, 2, match, 0)) + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + struct arm_annotate *arm; + int err; + + if (arch->initialized) + return 0; + + arm = zalloc(sizeof(*arm)); + if (!arm) + return -1; + +#define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)" + err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", 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 = '+'; + return 0; + +out_free_call: + regfree(&arm->call_insn); +out_free_arm: + free(arm); + return -1; +} diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h new file mode 100644 index 000000000..90ec4c8cb --- /dev/null +++ b/tools/perf/arch/arm/include/arch-tests.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_TESTS_H +#define ARCH_TESTS_H + +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +#endif + +extern struct test arch_tests[]; + +#endif diff --git a/tools/perf/arch/arm/include/dwarf-regs-table.h b/tools/perf/arch/arm/include/dwarf-regs-table.h new file mode 100644 index 000000000..5a45046fa --- /dev/null +++ b/tools/perf/arch/arm/include/dwarf-regs-table.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifdef DEFINE_DWARF_REGSTR_TABLE +/* This is included in perf/util/dwarf-regs.c */ + +static const char * const arm_regstr_tbl[] = { + "%r0", "%r1", "%r2", "%r3", "%r4", + "%r5", "%r6", "%r7", "%r8", "%r9", "%r10", + "%fp", "%ip", "%sp", "%lr", "%pc", +}; +#endif diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h new file mode 100644 index 000000000..ed20e0253 --- /dev/null +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include <linux/types.h> +#include <asm/perf_regs.h> + +void perf_regs_load(u64 *regs); + +#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_ARM_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 + +#define PERF_REG_IP PERF_REG_ARM_PC +#define PERF_REG_SP PERF_REG_ARM_SP + +static inline const char *perf_reg_name(int id) +{ + switch (id) { + case PERF_REG_ARM_R0: + return "r0"; + case PERF_REG_ARM_R1: + return "r1"; + case PERF_REG_ARM_R2: + return "r2"; + case PERF_REG_ARM_R3: + return "r3"; + case PERF_REG_ARM_R4: + return "r4"; + case PERF_REG_ARM_R5: + return "r5"; + case PERF_REG_ARM_R6: + return "r6"; + case PERF_REG_ARM_R7: + return "r7"; + case PERF_REG_ARM_R8: + return "r8"; + case PERF_REG_ARM_R9: + return "r9"; + case PERF_REG_ARM_R10: + return "r10"; + case PERF_REG_ARM_FP: + return "fp"; + case PERF_REG_ARM_IP: + return "ip"; + case PERF_REG_ARM_SP: + return "sp"; + case PERF_REG_ARM_LR: + return "lr"; + case PERF_REG_ARM_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build new file mode 100644 index 000000000..883c57ff0 --- /dev/null +++ b/tools/perf/arch/arm/tests/Build @@ -0,0 +1,4 @@ +libperf-y += regs_load.o +libperf-y += dwarf-unwind.o + +libperf-y += arch-tests.o diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c new file mode 100644 index 000000000..5b1543c98 --- /dev/null +++ b/tools/perf/arch/arm/tests/arch-tests.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include "tests/tests.h" +#include "arch-tests.h" + +struct test arch_tests[] = { +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "DWARF unwind", + .func = test__dwarf_unwind, + }, +#endif + { + .func = NULL, + }, +}; diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c new file mode 100644 index 000000000..9a0242e74 --- /dev/null +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include "perf_regs.h" +#include "thread.h" +#include "map.h" +#include "event.h" +#include "debug.h" +#include "tests/tests.h" + +#define STACK_SIZE 8192 + +static int sample_ustack(struct perf_sample *sample, + struct thread *thread, u64 *regs) +{ + struct stack_dump *stack = &sample->user_stack; + struct map *map; + unsigned long sp; + u64 stack_size, *buf; + + buf = malloc(STACK_SIZE); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + sp = (unsigned long) regs[PERF_REG_ARM_SP]; + + map = map_groups__find(thread->mg, (u64)sp); + if (!map) { + pr_debug("failed to get stack map\n"); + free(buf); + return -1; + } + + stack_size = map->end - sp; + stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; + + memcpy(buf, (void *) sp, stack_size); + stack->data = (char *) buf; + stack->size = stack_size; + return 0; +} + +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread) +{ + struct regs_dump *regs = &sample->user_regs; + u64 *buf; + + buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + perf_regs_load(buf); + regs->abi = PERF_SAMPLE_REGS_ABI; + regs->regs = buf; + regs->mask = PERF_REGS_MASK; + + return sample_ustack(sample, thread, buf); +} diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S new file mode 100644 index 000000000..6e2495cc4 --- /dev/null +++ b/tools/perf/arch/arm/tests/regs_load.S @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> + +#define R0 0x00 +#define R1 0x08 +#define R2 0x10 +#define R3 0x18 +#define R4 0x20 +#define R5 0x28 +#define R6 0x30 +#define R7 0x38 +#define R8 0x40 +#define R9 0x48 +#define SL 0x50 +#define FP 0x58 +#define IP 0x60 +#define SP 0x68 +#define LR 0x70 +#define PC 0x78 + +/* + * Implementation of void perf_regs_load(u64 *regs); + * + * This functions fills in the 'regs' buffer from the actual registers values, + * in the way the perf built-in unwinding test expects them: + * - the PC at the time at the call to this function. Since this function + * is called using a bl instruction, the PC value is taken from LR. + * The built-in unwinding test then unwinds the call stack from the dwarf + * information in unwind__get_entries. + * + * Notes: + * - the 8 bytes stride in the registers offsets comes from the fact + * that the registers are stored in an u64 array (u64 *regs), + * - the regs buffer needs to be zeroed before the call to this function, + * in this case using a calloc in dwarf-unwind.c. + */ + +.text +.type perf_regs_load,%function +ENTRY(perf_regs_load) + str r0, [r0, #R0] + str r1, [r0, #R1] + str r2, [r0, #R2] + str r3, [r0, #R3] + str r4, [r0, #R4] + str r5, [r0, #R5] + str r6, [r0, #R6] + str r7, [r0, #R7] + str r8, [r0, #R8] + str r9, [r0, #R9] + str sl, [r0, #SL] + str fp, [r0, #FP] + str ip, [r0, #IP] + str sp, [r0, #SP] + str lr, [r0, #LR] + str lr, [r0, #PC] // store pc as lr in order to skip the call + // to this function + mov pc, lr +ENDPROC(perf_regs_load) diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build new file mode 100644 index 000000000..e64c5f216 --- /dev/null +++ b/tools/perf/arch/arm/util/Build @@ -0,0 +1,6 @@ +libperf-$(CONFIG_DWARF) += dwarf-regs.o + +libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o + +libperf-$(CONFIG_AUXTRACE) += 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 new file mode 100644 index 000000000..1ce6bdbda --- /dev/null +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + */ + +#include <stdbool.h> +#include <linux/coresight-pmu.h> + +#include "../../util/auxtrace.h" +#include "../../util/evlist.h" +#include "../../util/pmu.h" +#include "cs-etm.h" +#include "arm-spe.h" + +static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) +{ + struct perf_pmu **arm_spe_pmus = NULL; + int ret, i, nr_cpus = sysconf(_SC_NPROCESSORS_CONF); + /* arm_spe_xxxxxxxxx\0 */ + char arm_spe_pmu_name[sizeof(ARM_SPE_PMU_NAME) + 10]; + + arm_spe_pmus = zalloc(sizeof(struct perf_pmu *) * nr_cpus); + if (!arm_spe_pmus) { + pr_err("spes alloc failed\n"); + *err = -ENOMEM; + return NULL; + } + + for (i = 0; i < nr_cpus; i++) { + ret = sprintf(arm_spe_pmu_name, "%s%d", ARM_SPE_PMU_NAME, i); + if (ret < 0) { + pr_err("sprintf failed\n"); + *err = -ENOMEM; + return NULL; + } + + arm_spe_pmus[*nr_spes] = perf_pmu__find(arm_spe_pmu_name); + if (arm_spe_pmus[*nr_spes]) { + pr_debug2("%s %d: arm_spe_pmu %d type %d name %s\n", + __func__, __LINE__, *nr_spes, + arm_spe_pmus[*nr_spes]->type, + arm_spe_pmus[*nr_spes]->name); + (*nr_spes)++; + } + } + + return arm_spe_pmus; +} + +struct auxtrace_record +*auxtrace_record__init(struct perf_evlist *evlist, int *err) +{ + struct perf_pmu *cs_etm_pmu; + struct perf_evsel *evsel; + bool found_etm = false; + bool found_spe = false; + static struct perf_pmu **arm_spe_pmus = NULL; + static int nr_spes = 0; + int i = 0; + + if (!evlist) + return NULL; + + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); + + if (!arm_spe_pmus) + arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err); + + evlist__for_each_entry(evlist, evsel) { + if (cs_etm_pmu && + evsel->attr.type == cs_etm_pmu->type) + found_etm = true; + + if (!nr_spes) + continue; + + for (i = 0; i < nr_spes; i++) { + if (evsel->attr.type == arm_spe_pmus[i]->type) { + found_spe = true; + break; + } + } + } + + if (found_etm && found_spe) { + pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n"); + *err = -EOPNOTSUPP; + return NULL; + } + + if (found_etm) + return cs_etm_record_init(err); + +#if defined(__aarch64__) + if (found_spe) + return arm_spe_recording_init(err, arm_spe_pmus[i]); +#endif + + /* + * Clear 'err' even if we haven't found an event - that way perf + * record can still be used even if tracers aren't present. The NULL + * return value will take care of telling the infrastructure HW tracing + * isn't available. + */ + *err = 0; + return NULL; +} diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c new file mode 100644 index 000000000..16af6c3b1 --- /dev/null +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -0,0 +1,770 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + */ + +#include <api/fs/fs.h> +#include <linux/bitops.h> +#include <linux/compiler.h> +#include <linux/coresight-pmu.h> +#include <linux/kernel.h> +#include <linux/log2.h> +#include <linux/types.h> + +#include "cs-etm.h" +#include "../../perf.h" +#include "../../util/auxtrace.h" +#include "../../util/cpumap.h" +#include "../../util/evlist.h" +#include "../../util/evsel.h" +#include "../../util/pmu.h" +#include "../../util/thread_map.h" +#include "../../util/cs-etm.h" + +#include <stdlib.h> +#include <sys/stat.h> + +#define ENABLE_SINK_MAX 128 +#define CS_BUS_DEVICE_PATH "/bus/coresight/devices/" + +struct cs_etm_recording { + struct auxtrace_record itr; + struct perf_pmu *cs_etm_pmu; + struct perf_evlist *evlist; + int wrapped_cnt; + bool *wrapped; + bool snapshot_mode; + size_t snapshot_size; +}; + +static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu); + +static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, + struct record_opts *opts, + const char *str) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + unsigned long long snapshot_size = 0; + char *endptr; + + if (str) { + snapshot_size = strtoull(str, &endptr, 0); + if (*endptr || snapshot_size > SIZE_MAX) + return -1; + } + + opts->auxtrace_snapshot_mode = true; + opts->auxtrace_snapshot_size = snapshot_size; + ptr->snapshot_size = snapshot_size; + + return 0; +} + +static int cs_etm_recording_options(struct auxtrace_record *itr, + struct perf_evlist *evlist, + struct record_opts *opts) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + struct perf_evsel *evsel, *cs_etm_evsel = NULL; + const struct cpu_map *cpus = evlist->cpus; + bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); + + ptr->evlist = evlist; + ptr->snapshot_mode = opts->auxtrace_snapshot_mode; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->attr.type == cs_etm_pmu->type) { + if (cs_etm_evsel) { + pr_err("There may be only one %s event\n", + CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } + evsel->attr.freq = 0; + evsel->attr.sample_period = 1; + cs_etm_evsel = evsel; + opts->full_auxtrace = true; + } + } + + /* no need to continue if at least one event of interest was found */ + if (!cs_etm_evsel) + return 0; + + if (opts->use_clockid) { + pr_err("Cannot use clockid (-k option) with %s\n", + CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } + + /* we are in snapshot mode */ + if (opts->auxtrace_snapshot_mode) { + /* + * No size were given to '-S' or '-m,', so go with + * the default + */ + if (!opts->auxtrace_snapshot_size && + !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = + KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } else if (!opts->auxtrace_mmap_pages && !privileged && + opts->mmap_pages == UINT_MAX) { + opts->mmap_pages = KiB(256) / page_size; + } + + /* + * '-m,xyz' was specified but no snapshot size, so make the + * snapshot size as big as the auxtrace mmap area. + */ + if (!opts->auxtrace_snapshot_size) { + opts->auxtrace_snapshot_size = + opts->auxtrace_mmap_pages * (size_t)page_size; + } + + /* + * -Sxyz was specified but no auxtrace mmap area, so make the + * auxtrace mmap area big enough to fit the requested snapshot + * size. + */ + if (!opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_snapshot_size; + + sz = round_up(sz, page_size) / page_size; + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } + + /* Snapshost size can't be bigger than the auxtrace area */ + if (opts->auxtrace_snapshot_size > + opts->auxtrace_mmap_pages * (size_t)page_size) { + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", + opts->auxtrace_snapshot_size, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + + /* Something went wrong somewhere - this shouldn't happen */ + if (!opts->auxtrace_snapshot_size || + !opts->auxtrace_mmap_pages) { + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); + return -EINVAL; + } + } + + /* We are in full trace mode but '-m,xyz' wasn't specified */ + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + + } + + /* Validate auxtrace_mmap_pages provided by user */ + if (opts->auxtrace_mmap_pages) { + unsigned int max_page = (KiB(128) / page_size); + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; + + if (!privileged && + opts->auxtrace_mmap_pages > max_page) { + opts->auxtrace_mmap_pages = max_page; + pr_err("auxtrace too big, truncating to %d\n", + max_page); + } + + if (!is_power_of_2(sz)) { + pr_err("Invalid mmap size for %s: must be a power of 2\n", + CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } + } + + if (opts->auxtrace_snapshot_mode) + pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, + opts->auxtrace_snapshot_size); + + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace + * event must come first. + */ + perf_evlist__to_front(evlist, cs_etm_evsel); + + /* + * In the case of per-cpu mmaps, we need the CPU on the + * AUX event. + */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); + + /* Add dummy event to keep tracking */ + if (opts->full_auxtrace) { + struct perf_evsel *tracking_evsel; + int err; + + err = parse_events(evlist, "dummy:u", NULL); + if (err) + return err; + + tracking_evsel = perf_evlist__last(evlist); + perf_evlist__set_tracking_event(evlist, tracking_evsel); + + tracking_evsel->attr.freq = 0; + tracking_evsel->attr.sample_period = 1; + + /* In per-cpu case, always need the time of mmap events etc */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(tracking_evsel, TIME); + } + + return 0; +} + +static u64 cs_etm_get_config(struct auxtrace_record *itr) +{ + u64 config = 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 perf_evlist *evlist = ptr->evlist; + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->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->attr.config; + break; + } + } + + return config; +} + +#ifndef BIT +#define BIT(N) (1UL << (N)) +#endif + +static u64 cs_etmv4_get_config(struct auxtrace_record *itr) +{ + u64 config = 0; + u64 config_opts = 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 + */ + 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_TS)) + config |= BIT(ETM4_CFG_BIT_TS); + if (config_opts & BIT(ETM_OPT_RETSTK)) + config |= BIT(ETM4_CFG_BIT_RETSTK); + + return config; +} + +static size_t +cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + int i; + int etmv3 = 0, etmv4 = 0; + struct cpu_map *event_cpus = evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); + + /* cpu map is not empty, we have specific CPUs to work with */ + if (!cpu_map__empty(event_cpus)) { + for (i = 0; i < cpu__max_cpu(); i++) { + if (!cpu_map__has(event_cpus, i) || + !cpu_map__has(online_cpus, i)) + continue; + + if (cs_etm_is_etmv4(itr, i)) + etmv4++; + else + etmv3++; + } + } else { + /* get configuration for all CPUs in the system */ + for (i = 0; i < cpu__max_cpu(); i++) { + if (!cpu_map__has(online_cpus, i)) + continue; + + if (cs_etm_is_etmv4(itr, i)) + etmv4++; + else + etmv3++; + } + } + + cpu_map__put(online_cpus); + + return (CS_ETM_HEADER_SIZE + + (etmv4 * CS_ETMV4_PRIV_SIZE) + + (etmv3 * CS_ETMV3_PRIV_SIZE)); +} + +static const char *metadata_etmv3_ro[CS_ETM_PRIV_MAX] = { + [CS_ETM_ETMCCER] = "mgmt/etmccer", + [CS_ETM_ETMIDR] = "mgmt/etmidr", +}; + +static const char *metadata_etmv4_ro[CS_ETMV4_PRIV_MAX] = { + [CS_ETMV4_TRCIDR0] = "trcidr/trcidr0", + [CS_ETMV4_TRCIDR1] = "trcidr/trcidr1", + [CS_ETMV4_TRCIDR2] = "trcidr/trcidr2", + [CS_ETMV4_TRCIDR8] = "trcidr/trcidr8", + [CS_ETMV4_TRCAUTHSTATUS] = "mgmt/trcauthstatus", +}; + +static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu) +{ + bool ret = false; + char path[PATH_MAX]; + int scan; + unsigned int val; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + + /* Take any of the RO files for ETMv4 and see if it present */ + snprintf(path, PATH_MAX, "cpu%d/%s", + cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]); + scan = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); + + /* The file was read successfully, we have a winner */ + if (scan == 1) + ret = true; + + return ret; +} + +static int cs_etm_get_ro(struct perf_pmu *pmu, int cpu, const char *path) +{ + char pmu_path[PATH_MAX]; + int scan; + unsigned int val = 0; + + /* Get RO metadata from sysfs */ + snprintf(pmu_path, PATH_MAX, "cpu%d/%s", cpu, path); + + scan = perf_pmu__scan_file(pmu, pmu_path, "%x", &val); + if (scan != 1) + pr_err("%s: error reading: %s\n", __func__, pmu_path); + + return val; +} + +static void cs_etm_get_metadata(int cpu, u32 *offset, + struct auxtrace_record *itr, + struct auxtrace_info_event *info) +{ + u32 increment; + u64 magic; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + + /* first see what kind of tracer this cpu is affined to */ + if (cs_etm_is_etmv4(itr, cpu)) { + magic = __perf_cs_etmv4_magic; + /* Get trace configuration register */ + info->priv[*offset + CS_ETMV4_TRCCONFIGR] = + cs_etmv4_get_config(itr); + /* Get traceID from the framework */ + info->priv[*offset + CS_ETMV4_TRCTRACEIDR] = + coresight_get_trace_id(cpu); + /* Get read-only information from sysFS */ + info->priv[*offset + CS_ETMV4_TRCIDR0] = + cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR0]); + info->priv[*offset + CS_ETMV4_TRCIDR1] = + cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR1]); + info->priv[*offset + CS_ETMV4_TRCIDR2] = + cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR2]); + info->priv[*offset + CS_ETMV4_TRCIDR8] = + cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro[CS_ETMV4_TRCIDR8]); + info->priv[*offset + CS_ETMV4_TRCAUTHSTATUS] = + cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv4_ro + [CS_ETMV4_TRCAUTHSTATUS]); + + /* How much space was used */ + increment = CS_ETMV4_PRIV_MAX; + } else { + magic = __perf_cs_etmv3_magic; + /* Get configuration register */ + info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr); + /* Get traceID from the framework */ + info->priv[*offset + CS_ETM_ETMTRACEIDR] = + coresight_get_trace_id(cpu); + /* Get read-only information from sysFS */ + info->priv[*offset + CS_ETM_ETMCCER] = + cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv3_ro[CS_ETM_ETMCCER]); + info->priv[*offset + CS_ETM_ETMIDR] = + cs_etm_get_ro(cs_etm_pmu, cpu, + metadata_etmv3_ro[CS_ETM_ETMIDR]); + + /* How much space was used */ + increment = CS_ETM_PRIV_MAX; + } + + /* Build generic header portion */ + info->priv[*offset + CS_ETM_MAGIC] = magic; + info->priv[*offset + CS_ETM_CPU] = cpu; + /* Where the next CPU entry should start from */ + *offset += increment; +} + +static int cs_etm_info_fill(struct auxtrace_record *itr, + struct perf_session *session, + struct auxtrace_info_event *info, + size_t priv_size) +{ + int i; + u32 offset; + u64 nr_cpu, type; + struct cpu_map *cpu_map; + struct cpu_map *event_cpus = session->evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; + + if (priv_size != cs_etm_info_priv_size(itr, session->evlist)) + return -EINVAL; + + if (!session->evlist->nr_mmaps) + return -EINVAL; + + /* If the cpu_map is empty all online CPUs are involved */ + if (cpu_map__empty(event_cpus)) { + cpu_map = online_cpus; + } else { + /* Make sure all specified CPUs are online */ + for (i = 0; i < cpu_map__nr(event_cpus); i++) { + if (cpu_map__has(event_cpus, i) && + !cpu_map__has(online_cpus, i)) + return -EINVAL; + } + + cpu_map = event_cpus; + } + + nr_cpu = cpu_map__nr(cpu_map); + /* Get PMU type as dynamically assigned by the core */ + type = cs_etm_pmu->type; + + /* First fill out the session header */ + info->type = PERF_AUXTRACE_CS_ETM; + info->priv[CS_HEADER_VERSION_0] = 0; + info->priv[CS_PMU_TYPE_CPUS] = type << 32; + info->priv[CS_PMU_TYPE_CPUS] |= nr_cpu; + info->priv[CS_ETM_SNAPSHOT] = ptr->snapshot_mode; + + offset = CS_ETM_SNAPSHOT + 1; + + for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) + if (cpu_map__has(cpu_map, i)) + cs_etm_get_metadata(i, &offset, itr, info); + + cpu_map__put(online_cpus); + + return 0; +} + +static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx) +{ + bool *wrapped; + int cnt = ptr->wrapped_cnt; + + /* Make @ptr->wrapped as big as @idx */ + while (cnt <= idx) + cnt++; + + /* + * Free'ed in cs_etm_recording_free(). Using realloc() to avoid + * cross compilation problems where the host's system supports + * reallocarray() but not the target. + */ + wrapped = realloc(ptr->wrapped, cnt * sizeof(bool)); + if (!wrapped) + return -ENOMEM; + + wrapped[cnt - 1] = false; + ptr->wrapped_cnt = cnt; + ptr->wrapped = wrapped; + + return 0; +} + +static bool cs_etm_buffer_has_wrapped(unsigned char *buffer, + size_t buffer_size, u64 head) +{ + u64 i, watermark; + u64 *buf = (u64 *)buffer; + size_t buf_size = buffer_size; + + /* + * We want to look the very last 512 byte (chosen arbitrarily) in + * the ring buffer. + */ + watermark = buf_size - 512; + + /* + * @head is continuously increasing - if its value is equal or greater + * than the size of the ring buffer, it has wrapped around. + */ + if (head >= buffer_size) + return true; + + /* + * The value of @head is somewhere within the size of the ring buffer. + * This can be that there hasn't been enough data to fill the ring + * buffer yet or the trace time was so long that @head has numerically + * wrapped around. To find we need to check if we have data at the very + * end of the ring buffer. We can reliably do this because mmap'ed + * pages are zeroed out and there is a fresh mapping with every new + * session. + */ + + /* @head is less than 512 byte from the end of the ring buffer */ + if (head > watermark) + watermark = head; + + /* + * Speed things up by using 64 bit transactions (see "u64 *buf" above) + */ + watermark >>= 3; + buf_size >>= 3; + + /* + * If we find trace data at the end of the ring buffer, @head has + * been there and has numerically wrapped around at least once. + */ + for (i = watermark; i < buf_size; i++) + if (buf[i]) + return true; + + return false; +} + +static int cs_etm_find_snapshot(struct auxtrace_record *itr, + int idx, struct auxtrace_mmap *mm, + unsigned char *data, + u64 *head, u64 *old) +{ + int err; + bool wrapped; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + + /* + * Allocate memory to keep track of wrapping if this is the first + * time we deal with this *mm. + */ + if (idx >= ptr->wrapped_cnt) { + err = cs_etm_alloc_wrapped_array(ptr, idx); + if (err) + return err; + } + + /* + * Check to see if *head has wrapped around. If it hasn't only the + * amount of data between *head and *old is snapshot'ed to avoid + * bloating the perf.data file with zeros. But as soon as *head has + * wrapped around the entire size of the AUX ring buffer it taken. + */ + wrapped = ptr->wrapped[idx]; + if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) { + wrapped = true; + ptr->wrapped[idx] = true; + } + + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", + __func__, idx, (size_t)*old, (size_t)*head, mm->len); + + /* No wrap has occurred, we can just use *head and *old. */ + if (!wrapped) + return 0; + + /* + * *head has wrapped around - adjust *head and *old to pickup the + * entire content of the AUX buffer. + */ + if (*head >= mm->len) { + *old = *head - mm->len; + } else { + *head += mm->len; + *old = *head - mm->len; + } + + return 0; +} + +static int cs_etm_snapshot_start(struct auxtrace_record *itr) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->cs_etm_pmu->type) + return perf_evsel__disable(evsel); + } + return -EINVAL; +} + +static int cs_etm_snapshot_finish(struct auxtrace_record *itr) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->cs_etm_pmu->type) + return perf_evsel__enable(evsel); + } + return -EINVAL; +} + +static u64 cs_etm_reference(struct auxtrace_record *itr __maybe_unused) +{ + return (((u64) rand() << 0) & 0x00000000FFFFFFFFull) | + (((u64) rand() << 32) & 0xFFFFFFFF00000000ull); +} + +static void cs_etm_recording_free(struct auxtrace_record *itr) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + + zfree(&ptr->wrapped); + free(ptr); +} + +static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) +{ + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->attr.type == ptr->cs_etm_pmu->type) + return perf_evlist__enable_event_idx(ptr->evlist, + evsel, idx); + } + + return -EINVAL; +} + +struct auxtrace_record *cs_etm_record_init(int *err) +{ + struct perf_pmu *cs_etm_pmu; + struct cs_etm_recording *ptr; + + cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); + + if (!cs_etm_pmu) { + *err = -EINVAL; + goto out; + } + + ptr = zalloc(sizeof(struct cs_etm_recording)); + if (!ptr) { + *err = -ENOMEM; + goto out; + } + + ptr->cs_etm_pmu = cs_etm_pmu; + ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options; + ptr->itr.recording_options = cs_etm_recording_options; + ptr->itr.info_priv_size = cs_etm_info_priv_size; + ptr->itr.info_fill = cs_etm_info_fill; + ptr->itr.find_snapshot = cs_etm_find_snapshot; + ptr->itr.snapshot_start = cs_etm_snapshot_start; + ptr->itr.snapshot_finish = cs_etm_snapshot_finish; + ptr->itr.reference = cs_etm_reference; + ptr->itr.free = cs_etm_recording_free; + ptr->itr.read_finish = cs_etm_read_finish; + + *err = 0; + return &ptr->itr; +out: + return NULL; +} + +static FILE *cs_device__open_file(const char *name) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs; + + sysfs = sysfs__mountpoint(); + if (!sysfs) + return NULL; + + snprintf(path, PATH_MAX, + "%s" CS_BUS_DEVICE_PATH "%s", sysfs, name); + + if (stat(path, &st) < 0) + return NULL; + + return fopen(path, "w"); + +} + +static int __printf(2, 3) cs_device__print_file(const char *name, const char *fmt, ...) +{ + va_list args; + FILE *file; + int ret = -EINVAL; + + va_start(args, fmt); + file = cs_device__open_file(name); + if (file) { + ret = vfprintf(file, fmt, args); + fclose(file); + } + va_end(args); + return ret; +} + +int cs_etm_set_drv_config(struct perf_evsel_config_term *term) +{ + int ret; + char enable_sink[ENABLE_SINK_MAX]; + + snprintf(enable_sink, ENABLE_SINK_MAX, "%s/%s", + term->val.drv_cfg, "enable_sink"); + + ret = cs_device__print_file(enable_sink, "%d", 1); + if (ret < 0) + return ret; + + return 0; +} diff --git a/tools/perf/arch/arm/util/cs-etm.h b/tools/perf/arch/arm/util/cs-etm.h new file mode 100644 index 000000000..1a12e64f5 --- /dev/null +++ b/tools/perf/arch/arm/util/cs-etm.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + */ + +#ifndef INCLUDE__PERF_CS_ETM_H__ +#define INCLUDE__PERF_CS_ETM_H__ + +#include "../../util/evsel.h" + +struct auxtrace_record *cs_etm_record_init(int *err); +int cs_etm_set_drv_config(struct perf_evsel_config_term *term); + +#endif diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c new file mode 100644 index 000000000..8bb176a37 --- /dev/null +++ b/tools/perf/arch/arm/util/dwarf-regs.c @@ -0,0 +1,64 @@ +/* + * Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2010 Will Deacon, ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <stddef.h> +#include <linux/stringify.h> +#include <dwarf-regs.h> + +struct pt_regs_dwarfnum { + const char *name; + unsigned int dwarfnum; +}; + +#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} +#define GPR_DWARFNUM_NAME(num) \ + {.name = __stringify(%r##num), .dwarfnum = num} +#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} + +/* + * Reference: + * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0040a/IHI0040A_aadwarf.pdf + */ +static const struct pt_regs_dwarfnum regdwarfnum_table[] = { + GPR_DWARFNUM_NAME(0), + GPR_DWARFNUM_NAME(1), + GPR_DWARFNUM_NAME(2), + GPR_DWARFNUM_NAME(3), + GPR_DWARFNUM_NAME(4), + GPR_DWARFNUM_NAME(5), + GPR_DWARFNUM_NAME(6), + GPR_DWARFNUM_NAME(7), + GPR_DWARFNUM_NAME(8), + GPR_DWARFNUM_NAME(9), + GPR_DWARFNUM_NAME(10), + REG_DWARFNUM_NAME("%fp", 11), + REG_DWARFNUM_NAME("%ip", 12), + REG_DWARFNUM_NAME("%sp", 13), + REG_DWARFNUM_NAME("%lr", 14), + REG_DWARFNUM_NAME("%pc", 15), + REG_DWARFNUM_END, +}; + +/** + * get_arch_regstr() - lookup register name from it's DWARF register number + * @n: the DWARF register number + * + * get_arch_regstr() returns the name of the register in struct + * regdwarfnum_table from it's DWARF register number. If the register is not + * found in the table, this returns NULL; + */ +const char *get_arch_regstr(unsigned int n) +{ + const struct pt_regs_dwarfnum *roff; + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (roff->dwarfnum == n) + return roff->name; + return NULL; +} diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c new file mode 100644 index 000000000..e047571e6 --- /dev/null +++ b/tools/perf/arch/arm/util/pmu.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2015 Linaro Limited. All rights reserved. + * Author: Mathieu Poirier <mathieu.poirier@linaro.org> + */ + +#include <string.h> +#include <linux/coresight-pmu.h> +#include <linux/perf_event.h> + +#include "cs-etm.h" +#include "arm-spe.h" +#include "../../util/pmu.h" + +struct perf_event_attr +*perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) +{ +#ifdef HAVE_AUXTRACE_SUPPORT + if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) { + /* add ETM default config here */ + pmu->selectable = true; + pmu->set_drv_config = cs_etm_set_drv_config; +#if defined(__aarch64__) + } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) { + return arm_spe_pmu_default_config(pmu); +#endif + } + +#endif + return NULL; +} diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c new file mode 100644 index 000000000..36ba4c69c --- /dev/null +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <elfutils/libdwfl.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 = &ui->sample->user_regs; + 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/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c new file mode 100644 index 000000000..3a550225d --- /dev/null +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <libunwind.h> +#include "perf_regs.h" +#include "../../util/unwind.h" +#include "../../util/debug.h" + +int libunwind__arch_reg_id(int regnum) +{ + switch (regnum) { + case UNW_ARM_R0: + return PERF_REG_ARM_R0; + case UNW_ARM_R1: + return PERF_REG_ARM_R1; + case UNW_ARM_R2: + return PERF_REG_ARM_R2; + case UNW_ARM_R3: + return PERF_REG_ARM_R3; + case UNW_ARM_R4: + return PERF_REG_ARM_R4; + case UNW_ARM_R5: + return PERF_REG_ARM_R5; + case UNW_ARM_R6: + return PERF_REG_ARM_R6; + case UNW_ARM_R7: + return PERF_REG_ARM_R7; + case UNW_ARM_R8: + return PERF_REG_ARM_R8; + case UNW_ARM_R9: + return PERF_REG_ARM_R9; + case UNW_ARM_R10: + return PERF_REG_ARM_R10; + case UNW_ARM_R11: + return PERF_REG_ARM_FP; + case UNW_ARM_R12: + return PERF_REG_ARM_IP; + case UNW_ARM_R13: + return PERF_REG_ARM_SP; + case UNW_ARM_R14: + return PERF_REG_ARM_LR; + case UNW_ARM_R15: + return PERF_REG_ARM_PC; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return -EINVAL; +} diff --git a/tools/perf/arch/arm64/Build b/tools/perf/arch/arm64/Build new file mode 100644 index 000000000..41bf61da4 --- /dev/null +++ b/tools/perf/arch/arm64/Build @@ -0,0 +1,2 @@ +libperf-y += util/ +libperf-$(CONFIG_DWARF_UNWIND) += tests/ diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile new file mode 100644 index 000000000..dbef716a1 --- /dev/null +++ b/tools/perf/arch/arm64/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +ifndef NO_DWARF +PERF_HAVE_DWARF_REGS := 1 +endif +PERF_HAVE_JITDUMP := 1 +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/arm64/include/generated/asm +header := $(out)/syscalls.c +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h +sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, arm64) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c new file mode 100644 index 000000000..6688977e4 --- /dev/null +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <regex.h> + +struct arm64_annotate { + regex_t call_insn, + jump_insn; +}; + +static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name) +{ + struct arm64_annotate *arm = arch->priv; + struct ins_ops *ops; + regmatch_t match[2]; + + if (!regexec(&arm->jump_insn, name, 2, match, 0)) + ops = &jump_ops; + else if (!regexec(&arm->call_insn, name, 2, match, 0)) + ops = &call_ops; + else if (!strcmp(name, "ret")) + ops = &ret_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + struct arm64_annotate *arm; + int err; + + if (arch->initialized) + return 0; + + arm = zalloc(sizeof(*arm)); + if (!arm) + return -1; + + /* bl, blr */ + err = regcomp(&arm->call_insn, "^blr?$", 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|le|ls|lt|mi|ne|pl)?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 = '+'; + return 0; + +out_free_call: + regfree(&arm->call_insn); +out_free_arm: + free(arm); + return -1; +} diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000..2dbb8cade --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -0,0 +1,62 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# powerpc script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> +# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> +# Changed by: Kim Phillips <kim.phillips@arm.com> + +gcc=$1 +hostcc=$2 +incpath=$3 +input=$4 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table_from_c() +{ + local sc nr last_sc + + create_table_exe=`mktemp /tmp/create-table-XXXXXX` + + { + + cat <<-_EoHEADER + #include <stdio.h> + #include "$input" + int main(int argc, char *argv[]) + { + _EoHEADER + + while read sc nr; do + printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);" + last_sc=$sc + done + + printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" + printf "}\n" + + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - + + $create_table_exe + + rm -f $create_table_exe +} + +create_table() +{ + echo "static const char *syscalltbl_arm64[] = {" + create_table_from_c + echo "};" +} + +$gcc -E -dM -x c $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -nu \ + |create_table diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h new file mode 100644 index 000000000..90ec4c8cb --- /dev/null +++ b/tools/perf/arch/arm64/include/arch-tests.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_TESTS_H +#define ARCH_TESTS_H + +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +#endif + +extern struct test arch_tests[]; + +#endif diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h new file mode 100644 index 000000000..177b2855f --- /dev/null +++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifdef DEFINE_DWARF_REGSTR_TABLE +/* This is included in perf/util/dwarf-regs.c */ + +static const char * const aarch64_regstr_tbl[] = { + "%x0", "%x1", "%x2", "%x3", "%x4", + "%x5", "%x6", "%x7", "%x8", "%x9", + "%x10", "%x11", "%x12", "%x13", "%x14", + "%x15", "%x16", "%x17", "%x18", "%x19", + "%x20", "%x21", "%x22", "%x23", "%x24", + "%x25", "%x26", "%x27", "%x28", "%x29", + "%lr", "%sp", +}; +#endif diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h new file mode 100644 index 000000000..baaa5e64a --- /dev/null +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include <linux/types.h> +#include <asm/perf_regs.h> + +void perf_regs_load(u64 *regs); + +#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM64_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_ARM64_MAX +#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 + +#define PERF_REG_IP PERF_REG_ARM64_PC +#define PERF_REG_SP PERF_REG_ARM64_SP + +static inline const char *perf_reg_name(int id) +{ + switch (id) { + case PERF_REG_ARM64_X0: + return "x0"; + case PERF_REG_ARM64_X1: + return "x1"; + case PERF_REG_ARM64_X2: + return "x2"; + case PERF_REG_ARM64_X3: + return "x3"; + case PERF_REG_ARM64_X4: + return "x4"; + case PERF_REG_ARM64_X5: + return "x5"; + case PERF_REG_ARM64_X6: + return "x6"; + case PERF_REG_ARM64_X7: + return "x7"; + case PERF_REG_ARM64_X8: + return "x8"; + case PERF_REG_ARM64_X9: + return "x9"; + case PERF_REG_ARM64_X10: + return "x10"; + case PERF_REG_ARM64_X11: + return "x11"; + case PERF_REG_ARM64_X12: + return "x12"; + case PERF_REG_ARM64_X13: + return "x13"; + case PERF_REG_ARM64_X14: + return "x14"; + case PERF_REG_ARM64_X15: + return "x15"; + case PERF_REG_ARM64_X16: + return "x16"; + case PERF_REG_ARM64_X17: + return "x17"; + case PERF_REG_ARM64_X18: + return "x18"; + case PERF_REG_ARM64_X19: + return "x19"; + case PERF_REG_ARM64_X20: + return "x20"; + case PERF_REG_ARM64_X21: + return "x21"; + case PERF_REG_ARM64_X22: + return "x22"; + case PERF_REG_ARM64_X23: + return "x23"; + case PERF_REG_ARM64_X24: + return "x24"; + case PERF_REG_ARM64_X25: + return "x25"; + case PERF_REG_ARM64_X26: + return "x26"; + case PERF_REG_ARM64_X27: + return "x27"; + case PERF_REG_ARM64_X28: + return "x28"; + case PERF_REG_ARM64_X29: + return "x29"; + case PERF_REG_ARM64_SP: + return "sp"; + case PERF_REG_ARM64_LR: + return "lr"; + case PERF_REG_ARM64_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build new file mode 100644 index 000000000..883c57ff0 --- /dev/null +++ b/tools/perf/arch/arm64/tests/Build @@ -0,0 +1,4 @@ +libperf-y += regs_load.o +libperf-y += dwarf-unwind.o + +libperf-y += arch-tests.o diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c new file mode 100644 index 000000000..5b1543c98 --- /dev/null +++ b/tools/perf/arch/arm64/tests/arch-tests.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include "tests/tests.h" +#include "arch-tests.h" + +struct test arch_tests[] = { +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "DWARF unwind", + .func = test__dwarf_unwind, + }, +#endif + { + .func = NULL, + }, +}; diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c new file mode 100644 index 000000000..5522ce384 --- /dev/null +++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include "perf_regs.h" +#include "thread.h" +#include "map.h" +#include "event.h" +#include "debug.h" +#include "tests/tests.h" + +#define STACK_SIZE 8192 + +static int sample_ustack(struct perf_sample *sample, + struct thread *thread, u64 *regs) +{ + struct stack_dump *stack = &sample->user_stack; + struct map *map; + unsigned long sp; + u64 stack_size, *buf; + + buf = malloc(STACK_SIZE); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + sp = (unsigned long) regs[PERF_REG_ARM64_SP]; + + map = map_groups__find(thread->mg, (u64)sp); + if (!map) { + pr_debug("failed to get stack map\n"); + free(buf); + return -1; + } + + stack_size = map->end - sp; + stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; + + memcpy(buf, (void *) sp, stack_size); + stack->data = (char *) buf; + stack->size = stack_size; + return 0; +} + +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread) +{ + struct regs_dump *regs = &sample->user_regs; + u64 *buf; + + buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); + if (!buf) { + pr_debug("failed to allocate sample uregs data\n"); + return -1; + } + + perf_regs_load(buf); + regs->abi = PERF_SAMPLE_REGS_ABI; + regs->regs = buf; + regs->mask = PERF_REGS_MASK; + + return sample_ustack(sample, thread, buf); +} diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S new file mode 100644 index 000000000..07042511d --- /dev/null +++ b/tools/perf/arch/arm64/tests/regs_load.S @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> + +.text +.type perf_regs_load,%function +#define STR_REG(r) str x##r, [x0, 8 * r] +#define LDR_REG(r) ldr x##r, [x0, 8 * r] +#define SP (8 * 31) +#define PC (8 * 32) +ENTRY(perf_regs_load) + STR_REG(0) + STR_REG(1) + STR_REG(2) + STR_REG(3) + STR_REG(4) + STR_REG(5) + STR_REG(6) + STR_REG(7) + STR_REG(8) + STR_REG(9) + STR_REG(10) + STR_REG(11) + STR_REG(12) + STR_REG(13) + STR_REG(14) + STR_REG(15) + STR_REG(16) + STR_REG(17) + STR_REG(18) + STR_REG(19) + STR_REG(20) + STR_REG(21) + STR_REG(22) + STR_REG(23) + STR_REG(24) + STR_REG(25) + STR_REG(26) + STR_REG(27) + STR_REG(28) + STR_REG(29) + STR_REG(30) + mov x1, sp + str x1, [x0, #SP] + str x30, [x0, #PC] + LDR_REG(1) + ret +ENDPROC(perf_regs_load) diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build new file mode 100644 index 000000000..68f8a8eb3 --- /dev/null +++ b/tools/perf/arch/arm64/util/Build @@ -0,0 +1,10 @@ +libperf-y += header.o +libperf-y += sym-handling.o +libperf-$(CONFIG_DWARF) += dwarf-regs.o +libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o + +libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ + ../../arm/util/auxtrace.o \ + ../../arm/util/cs-etm.o \ + arm-spe.o diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c new file mode 100644 index 000000000..5ccfce87e --- /dev/null +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Arm Statistical Profiling Extensions (SPE) support + * Copyright (c) 2017-2018, Arm Ltd. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/log2.h> +#include <time.h> + +#include "../../util/cpumap.h" +#include "../../util/evsel.h" +#include "../../util/evlist.h" +#include "../../util/session.h" +#include "../../util/util.h" +#include "../../util/pmu.h" +#include "../../util/debug.h" +#include "../../util/auxtrace.h" +#include "../../util/arm-spe.h" + +#define KiB(x) ((x) * 1024) +#define MiB(x) ((x) * 1024 * 1024) + +struct arm_spe_recording { + struct auxtrace_record itr; + struct perf_pmu *arm_spe_pmu; + struct perf_evlist *evlist; +}; + +static size_t +arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + return ARM_SPE_AUXTRACE_PRIV_SIZE; +} + +static int arm_spe_info_fill(struct auxtrace_record *itr, + struct perf_session *session, + struct auxtrace_info_event *auxtrace_info, + size_t priv_size) +{ + struct arm_spe_recording *sper = + container_of(itr, struct arm_spe_recording, itr); + struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu; + + if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE) + return -EINVAL; + + if (!session->evlist->nr_mmaps) + return -EINVAL; + + auxtrace_info->type = PERF_AUXTRACE_ARM_SPE; + auxtrace_info->priv[ARM_SPE_PMU_TYPE] = arm_spe_pmu->type; + + return 0; +} + +static int arm_spe_recording_options(struct auxtrace_record *itr, + struct perf_evlist *evlist, + struct record_opts *opts) +{ + struct arm_spe_recording *sper = + container_of(itr, struct arm_spe_recording, itr); + struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu; + struct perf_evsel *evsel, *arm_spe_evsel = NULL; + bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; + struct perf_evsel *tracking_evsel; + int err; + + sper->evlist = evlist; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->attr.type == arm_spe_pmu->type) { + if (arm_spe_evsel) { + pr_err("There may be only one " ARM_SPE_PMU_NAME "x event\n"); + return -EINVAL; + } + evsel->attr.freq = 0; + evsel->attr.sample_period = 1; + arm_spe_evsel = evsel; + opts->full_auxtrace = true; + } + } + + if (!opts->full_auxtrace) + return 0; + + /* We are in full trace mode but '-m,xyz' wasn't specified */ + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } + + /* Validate auxtrace_mmap_pages */ + if (opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; + size_t min_sz = KiB(8); + + if (sz < min_sz || !is_power_of_2(sz)) { + pr_err("Invalid mmap size for ARM SPE: must be at least %zuKiB and a power of 2\n", + min_sz / 1024); + return -EINVAL; + } + } + + + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace event + * must come first. + */ + perf_evlist__to_front(evlist, arm_spe_evsel); + + perf_evsel__set_sample_bit(arm_spe_evsel, CPU); + perf_evsel__set_sample_bit(arm_spe_evsel, TIME); + perf_evsel__set_sample_bit(arm_spe_evsel, TID); + + /* Add dummy event to keep tracking */ + err = parse_events(evlist, "dummy:u", NULL); + if (err) + return err; + + tracking_evsel = perf_evlist__last(evlist); + perf_evlist__set_tracking_event(evlist, tracking_evsel); + + tracking_evsel->attr.freq = 0; + tracking_evsel->attr.sample_period = 1; + perf_evsel__set_sample_bit(tracking_evsel, TIME); + perf_evsel__set_sample_bit(tracking_evsel, CPU); + perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK); + + return 0; +} + +static u64 arm_spe_reference(struct auxtrace_record *itr __maybe_unused) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC_RAW, &ts); + + return ts.tv_sec ^ ts.tv_nsec; +} + +static void arm_spe_recording_free(struct auxtrace_record *itr) +{ + struct arm_spe_recording *sper = + container_of(itr, struct arm_spe_recording, itr); + + free(sper); +} + +static int arm_spe_read_finish(struct auxtrace_record *itr, int idx) +{ + struct arm_spe_recording *sper = + container_of(itr, struct arm_spe_recording, itr); + struct perf_evsel *evsel; + + evlist__for_each_entry(sper->evlist, evsel) { + if (evsel->attr.type == sper->arm_spe_pmu->type) + return perf_evlist__enable_event_idx(sper->evlist, + evsel, idx); + } + return -EINVAL; +} + +struct auxtrace_record *arm_spe_recording_init(int *err, + struct perf_pmu *arm_spe_pmu) +{ + struct arm_spe_recording *sper; + + if (!arm_spe_pmu) { + *err = -ENODEV; + return NULL; + } + + sper = zalloc(sizeof(struct arm_spe_recording)); + if (!sper) { + *err = -ENOMEM; + return NULL; + } + + sper->arm_spe_pmu = arm_spe_pmu; + sper->itr.recording_options = arm_spe_recording_options; + sper->itr.info_priv_size = arm_spe_info_priv_size; + sper->itr.info_fill = arm_spe_info_fill; + sper->itr.free = arm_spe_recording_free; + sper->itr.reference = arm_spe_reference; + sper->itr.read_finish = arm_spe_read_finish; + sper->itr.alignment = 0; + + *err = 0; + return &sper->itr; +} + +struct perf_event_attr +*arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu) +{ + struct perf_event_attr *attr; + + attr = zalloc(sizeof(struct perf_event_attr)); + if (!attr) { + pr_err("arm_spe default config cannot allocate a perf_event_attr\n"); + return NULL; + } + + /* + * If kernel driver doesn't advertise a minimum, + * use max allowable by PMSIDR_EL1.INTERVAL + */ + if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu", + &attr->sample_period) != 1) { + pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n"); + attr->sample_period = 4096; + } + + arm_spe_pmu->selectable = true; + arm_spe_pmu->is_uncore = false; + + return attr; +} diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c new file mode 100644 index 000000000..cd764a9fd --- /dev/null +++ b/tools/perf/arch/arm64/util/dwarf-regs.c @@ -0,0 +1,96 @@ +/* + * Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2010 Will Deacon, ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <errno.h> +#include <stddef.h> +#include <string.h> +#include <dwarf-regs.h> +#include <linux/ptrace.h> /* for struct user_pt_regs */ +#include <linux/stringify.h> +#include "util.h" + +struct pt_regs_dwarfnum { + const char *name; + unsigned int dwarfnum; +}; + +#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} +#define GPR_DWARFNUM_NAME(num) \ + {.name = __stringify(%x##num), .dwarfnum = num} +#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} +#define DWARFNUM2OFFSET(index) \ + (index * sizeof((struct user_pt_regs *)0)->regs[0]) + +/* + * Reference: + * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0057b/IHI0057B_aadwarf64.pdf + */ +static const struct pt_regs_dwarfnum regdwarfnum_table[] = { + GPR_DWARFNUM_NAME(0), + GPR_DWARFNUM_NAME(1), + GPR_DWARFNUM_NAME(2), + GPR_DWARFNUM_NAME(3), + GPR_DWARFNUM_NAME(4), + GPR_DWARFNUM_NAME(5), + GPR_DWARFNUM_NAME(6), + GPR_DWARFNUM_NAME(7), + GPR_DWARFNUM_NAME(8), + GPR_DWARFNUM_NAME(9), + GPR_DWARFNUM_NAME(10), + GPR_DWARFNUM_NAME(11), + GPR_DWARFNUM_NAME(12), + GPR_DWARFNUM_NAME(13), + GPR_DWARFNUM_NAME(14), + GPR_DWARFNUM_NAME(15), + GPR_DWARFNUM_NAME(16), + GPR_DWARFNUM_NAME(17), + GPR_DWARFNUM_NAME(18), + GPR_DWARFNUM_NAME(19), + GPR_DWARFNUM_NAME(20), + GPR_DWARFNUM_NAME(21), + GPR_DWARFNUM_NAME(22), + GPR_DWARFNUM_NAME(23), + GPR_DWARFNUM_NAME(24), + GPR_DWARFNUM_NAME(25), + GPR_DWARFNUM_NAME(26), + GPR_DWARFNUM_NAME(27), + GPR_DWARFNUM_NAME(28), + GPR_DWARFNUM_NAME(29), + REG_DWARFNUM_NAME("%lr", 30), + REG_DWARFNUM_NAME("%sp", 31), + REG_DWARFNUM_END, +}; + +/** + * get_arch_regstr() - lookup register name from it's DWARF register number + * @n: the DWARF register number + * + * get_arch_regstr() returns the name of the register in struct + * regdwarfnum_table from it's DWARF register number. If the register is not + * found in the table, this returns NULL; + */ +const char *get_arch_regstr(unsigned int n) +{ + const struct pt_regs_dwarfnum *roff; + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (roff->dwarfnum == n) + return roff->name; + return NULL; +} + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return DWARFNUM2OFFSET(roff->dwarfnum); + return -EINVAL; +} diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c new file mode 100644 index 000000000..534cd2507 --- /dev/null +++ b/tools/perf/arch/arm64/util/header.c @@ -0,0 +1,65 @@ +#include <stdio.h> +#include <stdlib.h> +#include <api/fs/fs.h> +#include "header.h" + +#define MIDR "/regs/identification/midr_el1" +#define MIDR_SIZE 19 +#define MIDR_REVISION_MASK 0xf +#define MIDR_VARIANT_SHIFT 20 +#define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT) + +char *get_cpuid_str(struct perf_pmu *pmu) +{ + char *buf = NULL; + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + int cpu; + u64 midr = 0; + struct cpu_map *cpus; + FILE *file; + + if (!sysfs || !pmu || !pmu->cpus) + return NULL; + + buf = malloc(MIDR_SIZE); + if (!buf) + return NULL; + + /* read midr from list of cpus mapped to this pmu */ + cpus = cpu_map__get(pmu->cpus); + for (cpu = 0; cpu < cpus->nr; cpu++) { + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, + sysfs, cpus->map[cpu]); + + file = fopen(path, "r"); + if (!file) { + pr_debug("fopen failed for file %s\n", path); + continue; + } + + if (!fgets(buf, MIDR_SIZE, file)) { + fclose(file); + continue; + } + fclose(file); + + /* Ignore/clear Variant[23:20] and + * Revision[3:0] of MIDR + */ + midr = strtoul(buf, NULL, 16); + midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK)); + scnprintf(buf, MIDR_SIZE, "0x%016lx", midr); + /* got midr break loop */ + break; + } + + if (!midr) { + pr_err("failed to get cpuid string for PMU %s\n", pmu->name); + free(buf); + buf = NULL; + } + + cpu_map__put(cpus); + return buf; +} diff --git a/tools/perf/arch/arm64/util/sym-handling.c b/tools/perf/arch/arm64/util/sym-handling.c new file mode 100644 index 000000000..0051b1ee8 --- /dev/null +++ b/tools/perf/arch/arm64/util/sym-handling.c @@ -0,0 +1,22 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright (C) 2015 Naveen N. Rao, IBM Corporation + */ + +#include "debug.h" +#include "symbol.h" +#include "map.h" +#include "probe-event.h" +#include "probe-file.h" + +#ifdef HAVE_LIBELF_SUPPORT +bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) +{ + return ehdr.e_type == ET_EXEC || + ehdr.e_type == ET_REL || + ehdr.e_type == ET_DYN; +} +#endif diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c new file mode 100644 index 000000000..7623d85e7 --- /dev/null +++ b/tools/perf/arch/arm64/util/unwind-libdw.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <elfutils/libdwfl.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 = &ui->sample->user_regs; + 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/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c new file mode 100644 index 000000000..002520d40 --- /dev/null +++ b/tools/perf/arch/arm64/util/unwind-libunwind.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> + +#ifndef REMOTE_UNWIND_LIBUNWIND +#include <libunwind.h> +#include "perf_regs.h" +#include "../../util/unwind.h" +#include "../../util/debug.h" +#endif + +int LIBUNWIND__ARCH_REG_ID(int regnum) +{ + switch (regnum) { + case UNW_AARCH64_X0: + return PERF_REG_ARM64_X0; + case UNW_AARCH64_X1: + return PERF_REG_ARM64_X1; + case UNW_AARCH64_X2: + return PERF_REG_ARM64_X2; + case UNW_AARCH64_X3: + return PERF_REG_ARM64_X3; + case UNW_AARCH64_X4: + return PERF_REG_ARM64_X4; + case UNW_AARCH64_X5: + return PERF_REG_ARM64_X5; + case UNW_AARCH64_X6: + return PERF_REG_ARM64_X6; + case UNW_AARCH64_X7: + return PERF_REG_ARM64_X7; + case UNW_AARCH64_X8: + return PERF_REG_ARM64_X8; + case UNW_AARCH64_X9: + return PERF_REG_ARM64_X9; + case UNW_AARCH64_X10: + return PERF_REG_ARM64_X10; + case UNW_AARCH64_X11: + return PERF_REG_ARM64_X11; + case UNW_AARCH64_X12: + return PERF_REG_ARM64_X12; + case UNW_AARCH64_X13: + return PERF_REG_ARM64_X13; + case UNW_AARCH64_X14: + return PERF_REG_ARM64_X14; + case UNW_AARCH64_X15: + return PERF_REG_ARM64_X15; + case UNW_AARCH64_X16: + return PERF_REG_ARM64_X16; + case UNW_AARCH64_X17: + return PERF_REG_ARM64_X17; + case UNW_AARCH64_X18: + return PERF_REG_ARM64_X18; + case UNW_AARCH64_X19: + return PERF_REG_ARM64_X19; + case UNW_AARCH64_X20: + return PERF_REG_ARM64_X20; + case UNW_AARCH64_X21: + return PERF_REG_ARM64_X21; + case UNW_AARCH64_X22: + return PERF_REG_ARM64_X22; + case UNW_AARCH64_X23: + return PERF_REG_ARM64_X23; + case UNW_AARCH64_X24: + return PERF_REG_ARM64_X24; + case UNW_AARCH64_X25: + return PERF_REG_ARM64_X25; + case UNW_AARCH64_X26: + return PERF_REG_ARM64_X26; + case UNW_AARCH64_X27: + return PERF_REG_ARM64_X27; + case UNW_AARCH64_X28: + return PERF_REG_ARM64_X28; + case UNW_AARCH64_X29: + return PERF_REG_ARM64_X29; + case UNW_AARCH64_X30: + return PERF_REG_ARM64_LR; + case UNW_AARCH64_SP: + return PERF_REG_ARM64_SP; + case UNW_AARCH64_PC: + return PERF_REG_ARM64_PC; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return -EINVAL; +} |