diff options
Diffstat (limited to 'tools/perf/arch')
21 files changed, 667 insertions, 34 deletions
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c index f64516d5b23e..c7d1a69b894f 100644 --- a/tools/perf/arch/arm/annotate/instructions.c +++ b/tools/perf/arch/arm/annotate/instructions.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> +#include <linux/zalloc.h> #include <sys/types.h> #include <regex.h> diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 1ce6bdbda561..02014740a1aa 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -6,6 +6,7 @@ #include <stdbool.h> #include <linux/coresight-pmu.h> +#include <linux/zalloc.h> #include "../../util/auxtrace.h" #include "../../util/evlist.h" diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 911426721170..4208974c24f8 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/log2.h> #include <linux/types.h> +#include <linux/zalloc.h> #include "cs-etm.h" #include "../../perf.h" @@ -22,6 +23,7 @@ #include "../../util/pmu.h" #include "../../util/thread_map.h" #include "../../util/cs-etm.h" +#include "../../util/util.h" #include <errno.h> #include <stdlib.h> @@ -31,12 +33,158 @@ 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 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); +static int cs_etm_set_context_id(struct auxtrace_record *itr, + struct perf_evsel *evsel, int cpu) +{ + struct cs_etm_recording *ptr; + struct perf_pmu *cs_etm_pmu; + char path[PATH_MAX]; + int err = -EINVAL; + u32 val; + + ptr = container_of(itr, struct cs_etm_recording, itr); + cs_etm_pmu = ptr->cs_etm_pmu; + + if (!cs_etm_is_etmv4(itr, cpu)) + goto out; + + /* Get a handle on TRCIRD2 */ + snprintf(path, PATH_MAX, "cpu%d/%s", + cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR2]); + err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); + + /* There was a problem reading the file, bailing out */ + if (err != 1) { + pr_err("%s: can't read file %s\n", + CORESIGHT_ETM_PMU_NAME, path); + goto out; + } + + /* + * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID tracing + * is supported: + * 0b00000 Context ID tracing is not supported. + * 0b00100 Maximum of 32-bit Context ID size. + * All other values are reserved. + */ + val = BMVAL(val, 5, 9); + if (!val || val != 0x4) { + err = -EINVAL; + goto out; + } + + /* All good, let the kernel know */ + evsel->attr.config |= (1 << ETM_OPT_CTXTID); + err = 0; + +out: + + return err; +} + +static int cs_etm_set_timestamp(struct auxtrace_record *itr, + struct perf_evsel *evsel, int cpu) +{ + struct cs_etm_recording *ptr; + struct perf_pmu *cs_etm_pmu; + char path[PATH_MAX]; + int err = -EINVAL; + u32 val; + + ptr = container_of(itr, struct cs_etm_recording, itr); + cs_etm_pmu = ptr->cs_etm_pmu; + + if (!cs_etm_is_etmv4(itr, cpu)) + goto out; + + /* Get a handle on TRCIRD0 */ + snprintf(path, PATH_MAX, "cpu%d/%s", + cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]); + err = perf_pmu__scan_file(cs_etm_pmu, path, "%x", &val); + + /* There was a problem reading the file, bailing out */ + if (err != 1) { + pr_err("%s: can't read file %s\n", + CORESIGHT_ETM_PMU_NAME, path); + goto out; + } + + /* + * TRCIDR0.TSSIZE, bit [28-24], indicates whether global timestamping + * is supported: + * 0b00000 Global timestamping is not implemented + * 0b00110 Implementation supports a maximum timestamp of 48bits. + * 0b01000 Implementation supports a maximum timestamp of 64bits. + */ + val &= GENMASK(28, 24); + if (!val) { + err = -EINVAL; + goto out; + } + + /* All good, let the kernel know */ + evsel->attr.config |= (1 << ETM_OPT_TS); + err = 0; + +out: + return err; +} + +static int cs_etm_set_option(struct auxtrace_record *itr, + struct perf_evsel *evsel, u32 option) +{ + int i, err = -EINVAL; + struct cpu_map *event_cpus = evsel->evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); + + /* Set option of each CPU we have */ + for (i = 0; i < cpu__max_cpu(); i++) { + if (!cpu_map__has(event_cpus, i) || + !cpu_map__has(online_cpus, i)) + continue; + + if (option & ETM_OPT_CTXTID) { + err = cs_etm_set_context_id(itr, evsel, i); + if (err) + goto out; + } + if (option & ETM_OPT_TS) { + err = cs_etm_set_timestamp(itr, evsel, i); + if (err) + goto out; + } + if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS)) + /* Nothing else is currently supported */ + goto out; + } + + err = 0; +out: + cpu_map__put(online_cpus); + return err; +} + static int cs_etm_parse_snapshot_options(struct auxtrace_record *itr, struct record_opts *opts, const char *str) @@ -105,12 +253,16 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, 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; + struct cpu_map *cpus = evlist->cpus; bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0); + int err = 0; ptr->evlist = evlist; ptr->snapshot_mode = opts->auxtrace_snapshot_mode; + if (perf_can_record_switch_events()) + opts->record_switch_events = true; + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type == cs_etm_pmu->type) { if (cs_etm_evsel) { @@ -241,19 +393,25 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, /* * In the case of per-cpu mmaps, we need the CPU on the - * AUX event. + * AUX event. We also need the contextID in order to be notified + * when a context switch happened. */ - if (!cpu_map__empty(cpus)) + if (!cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(cs_etm_evsel, CPU); + err = cs_etm_set_option(itr, cs_etm_evsel, + ETM_OPT_CTXTID | ETM_OPT_TS); + if (err) + goto out; + } + /* 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; + goto out; tracking_evsel = perf_evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); @@ -266,7 +424,8 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, perf_evsel__set_sample_bit(tracking_evsel, TIME); } - return 0; +out: + return err; } static u64 cs_etm_get_config(struct auxtrace_record *itr) @@ -314,6 +473,8 @@ static u64 cs_etmv4_get_config(struct auxtrace_record *itr) 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)) @@ -363,19 +524,6 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, (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; @@ -536,16 +684,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, return 0; } -static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused, +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 __maybe_unused, + 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); - *old = *head; - *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; } @@ -586,6 +849,8 @@ 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); } diff --git a/tools/perf/arch/arm64/Build b/tools/perf/arch/arm64/Build index 36222e64bbf7..a7dd46a5b678 100644 --- a/tools/perf/arch/arm64/Build +++ b/tools/perf/arch/arm64/Build @@ -1,2 +1,2 @@ perf-y += util/ -perf-$(CONFIG_DWARF_UNWIND) += tests/ +perf-y += tests/ diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build index 41707fea74b3..a61c06bdb757 100644 --- a/tools/perf/arch/arm64/tests/Build +++ b/tools/perf/arch/arm64/tests/Build @@ -1,4 +1,4 @@ perf-y += regs_load.o -perf-y += dwarf-unwind.o +perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 5ccfce87e693..2c009aa74633 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -8,6 +8,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/zalloc.h> #include <time.h> #include "../../util/cpumap.h" diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index f3824ca7c20b..1a9e22f78c22 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> +#include <stdlib.h> #include "common.h" #include "../util/env.h" -#include "../util/util.h" #include "../util/debug.h" +#include <linux/zalloc.h> const char *const arc_triplets[] = { "arc-linux-", diff --git a/tools/perf/arch/csky/annotate/instructions.c b/tools/perf/arch/csky/annotate/instructions.c new file mode 100644 index 000000000000..5337bfb7d5fc --- /dev/null +++ b/tools/perf/arch/csky/annotate/instructions.c @@ -0,0 +1,48 @@ +// 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; + + return 0; +} diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index 34d5134681d9..f14102b85509 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -2,12 +2,14 @@ #include <errno.h> #include <string.h> #include <regex.h> +#include <linux/zalloc.h> #include "../../perf.h" -#include "../../util/util.h" #include "../../util/perf_regs.h" #include "../../util/debug.h" +#include <linux/kernel.h> + const struct sample_reg sample_reg_masks[] = { SMPL_REG(r0, PERF_REG_POWERPC_R0), SMPL_REG(r1, PERF_REG_POWERPC_R1), diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 44c857388897..0fe1be93f375 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -3,6 +3,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/zalloc.h> #include "../../util/evlist.h" #include "../../util/auxtrace.h" diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index 3db85cd2069e..8b0b018d896a 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -11,10 +11,11 @@ #include <unistd.h> #include <stdio.h> #include <string.h> -#include <ctype.h> +#include <linux/ctype.h> +#include <linux/kernel.h> +#include <linux/zalloc.h> #include "../../util/header.h" -#include "../../util/util.h" #define SYSINFO_MANU "Manufacturer:" #define SYSINFO_TYPE "Type:" diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 613709cfbbd0..c41c5affe4be 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -9,6 +9,7 @@ struct test; int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__intel_pt_pkt_decoder(struct test *test, int subtest); int test__bp_modify(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 3d83d0c6982d..2997c506550c 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -4,5 +4,5 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o perf-y += rdpmc.o perf-y += perf-time-to-tsc.o -perf-$(CONFIG_AUXTRACE) += insn-x86.o +perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o perf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index d47d3f8e3c8e..6763135aec17 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -23,6 +23,10 @@ struct test arch_tests[] = { .desc = "x86 instruction decoder - new instructions", .func = test__insn_x86, }, + { + .desc = "Intel PT packet decoder", + .func = test__intel_pt_pkt_decoder, + }, #endif #if defined(__x86_64__) { diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 90a4a8c58a62..94aa0b673b7f 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -6,6 +6,7 @@ #include "evlist.h" #include "evsel.h" #include "arch-tests.h" +#include "util.h" #include <signal.h> #include <sys/mman.h> diff --git a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c new file mode 100644 index 000000000000..901bf1f449c4 --- /dev/null +++ b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include "intel-pt-decoder/intel-pt-pkt-decoder.h" + +#include "debug.h" +#include "tests/tests.h" +#include "arch-tests.h" + +/** + * struct test_data - Test data. + * @len: number of bytes to decode + * @bytes: bytes to decode + * @ctx: packet context to decode + * @packet: expected packet + * @new_ctx: expected new packet context + * @ctx_unchanged: the packet context must not change + */ +struct test_data { + int len; + u8 bytes[INTEL_PT_PKT_MAX_SZ]; + enum intel_pt_pkt_ctx ctx; + struct intel_pt_pkt packet; + enum intel_pt_pkt_ctx new_ctx; + int ctx_unchanged; +} data[] = { + /* Padding Packet */ + {1, {0}, 0, {INTEL_PT_PAD, 0, 0}, 0, 1 }, + /* Short Taken/Not Taken Packet */ + {1, {4}, 0, {INTEL_PT_TNT, 1, 0}, 0, 0 }, + {1, {6}, 0, {INTEL_PT_TNT, 1, 0x20ULL << 58}, 0, 0 }, + {1, {0x80}, 0, {INTEL_PT_TNT, 6, 0}, 0, 0 }, + {1, {0xfe}, 0, {INTEL_PT_TNT, 6, 0x3fULL << 58}, 0, 0 }, + /* Long Taken/Not Taken Packet */ + {8, {0x02, 0xa3, 2}, 0, {INTEL_PT_TNT, 1, 0xa302ULL << 47}, 0, 0 }, + {8, {0x02, 0xa3, 3}, 0, {INTEL_PT_TNT, 1, 0x1a302ULL << 47}, 0, 0 }, + {8, {0x02, 0xa3, 0, 0, 0, 0, 0, 0x80}, 0, {INTEL_PT_TNT, 47, 0xa302ULL << 1}, 0, 0 }, + {8, {0x02, 0xa3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_TNT, 47, 0xffffffffffffa302ULL << 1}, 0, 0 }, + /* Target IP Packet */ + {1, {0x0d}, 0, {INTEL_PT_TIP, 0, 0}, 0, 0 }, + {3, {0x2d, 1, 2}, 0, {INTEL_PT_TIP, 1, 0x201}, 0, 0 }, + {5, {0x4d, 1, 2, 3, 4}, 0, {INTEL_PT_TIP, 2, 0x4030201}, 0, 0 }, + {7, {0x6d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 3, 0x60504030201}, 0, 0 }, + {7, {0x8d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 4, 0x60504030201}, 0, 0 }, + {9, {0xcd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP, 6, 0x807060504030201}, 0, 0 }, + /* Packet Generation Enable */ + {1, {0x11}, 0, {INTEL_PT_TIP_PGE, 0, 0}, 0, 0 }, + {3, {0x31, 1, 2}, 0, {INTEL_PT_TIP_PGE, 1, 0x201}, 0, 0 }, + {5, {0x51, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGE, 2, 0x4030201}, 0, 0 }, + {7, {0x71, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 3, 0x60504030201}, 0, 0 }, + {7, {0x91, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 4, 0x60504030201}, 0, 0 }, + {9, {0xd1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGE, 6, 0x807060504030201}, 0, 0 }, + /* Packet Generation Disable */ + {1, {0x01}, 0, {INTEL_PT_TIP_PGD, 0, 0}, 0, 0 }, + {3, {0x21, 1, 2}, 0, {INTEL_PT_TIP_PGD, 1, 0x201}, 0, 0 }, + {5, {0x41, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGD, 2, 0x4030201}, 0, 0 }, + {7, {0x61, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 3, 0x60504030201}, 0, 0 }, + {7, {0x81, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 4, 0x60504030201}, 0, 0 }, + {9, {0xc1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGD, 6, 0x807060504030201}, 0, 0 }, + /* Flow Update Packet */ + {1, {0x1d}, 0, {INTEL_PT_FUP, 0, 0}, 0, 0 }, + {3, {0x3d, 1, 2}, 0, {INTEL_PT_FUP, 1, 0x201}, 0, 0 }, + {5, {0x5d, 1, 2, 3, 4}, 0, {INTEL_PT_FUP, 2, 0x4030201}, 0, 0 }, + {7, {0x7d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 3, 0x60504030201}, 0, 0 }, + {7, {0x9d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 4, 0x60504030201}, 0, 0 }, + {9, {0xdd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_FUP, 6, 0x807060504030201}, 0, 0 }, + /* Paging Information Packet */ + {8, {0x02, 0x43, 2, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201}, 0, 0 }, + {8, {0x02, 0x43, 3, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0x60504030201 | (1ULL << 63)}, 0, 0 }, + /* Mode Exec Packet */ + {2, {0x99, 0x00}, 0, {INTEL_PT_MODE_EXEC, 0, 16}, 0, 0 }, + {2, {0x99, 0x01}, 0, {INTEL_PT_MODE_EXEC, 0, 64}, 0, 0 }, + {2, {0x99, 0x02}, 0, {INTEL_PT_MODE_EXEC, 0, 32}, 0, 0 }, + /* Mode TSX Packet */ + {2, {0x99, 0x20}, 0, {INTEL_PT_MODE_TSX, 0, 0}, 0, 0 }, + {2, {0x99, 0x21}, 0, {INTEL_PT_MODE_TSX, 0, 1}, 0, 0 }, + {2, {0x99, 0x22}, 0, {INTEL_PT_MODE_TSX, 0, 2}, 0, 0 }, + /* Trace Stop Packet */ + {2, {0x02, 0x83}, 0, {INTEL_PT_TRACESTOP, 0, 0}, 0, 0 }, + /* Core:Bus Ratio Packet */ + {4, {0x02, 0x03, 0x12, 0}, 0, {INTEL_PT_CBR, 0, 0x12}, 0, 1 }, + /* Timestamp Counter Packet */ + {8, {0x19, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_TSC, 0, 0x7060504030201}, 0, 1 }, + /* Mini Time Counter Packet */ + {2, {0x59, 0x12}, 0, {INTEL_PT_MTC, 0, 0x12}, 0, 1 }, + /* TSC / MTC Alignment Packet */ + {7, {0x02, 0x73}, 0, {INTEL_PT_TMA, 0, 0}, 0, 1 }, + {7, {0x02, 0x73, 1, 2}, 0, {INTEL_PT_TMA, 0, 0x201}, 0, 1 }, + {7, {0x02, 0x73, 0, 0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0}, 0, 1 }, + {7, {0x02, 0x73, 0x80, 0xc0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0xc080}, 0, 1 }, + /* Cycle Count Packet */ + {1, {0x03}, 0, {INTEL_PT_CYC, 0, 0}, 0, 1 }, + {1, {0x0b}, 0, {INTEL_PT_CYC, 0, 1}, 0, 1 }, + {1, {0xfb}, 0, {INTEL_PT_CYC, 0, 0x1f}, 0, 1 }, + {2, {0x07, 2}, 0, {INTEL_PT_CYC, 0, 0x20}, 0, 1 }, + {2, {0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xfff}, 0, 1 }, + {3, {0x07, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x1000}, 0, 1 }, + {3, {0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7ffff}, 0, 1 }, + {4, {0x07, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x80000}, 0, 1 }, + {4, {0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3ffffff}, 0, 1 }, + {5, {0x07, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x4000000}, 0, 1 }, + {5, {0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1ffffffff}, 0, 1 }, + {6, {0x07, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x200000000}, 0, 1 }, + {6, {0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xffffffffff}, 0, 1 }, + {7, {0x07, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x10000000000}, 0, 1 }, + {7, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7fffffffffff}, 0, 1 }, + {8, {0x07, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x800000000000}, 0, 1 }, + {8, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3fffffffffffff}, 0, 1 }, + {9, {0x07, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x40000000000000}, 0, 1 }, + {9, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1fffffffffffffff}, 0, 1 }, + {10, {0x07, 1, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x2000000000000000}, 0, 1 }, + {10, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xe}, 0, {INTEL_PT_CYC, 0, 0xffffffffffffffff}, 0, 1 }, + /* Virtual-Machine Control Structure Packet */ + {7, {0x02, 0xc8, 1, 2, 3, 4, 5}, 0, {INTEL_PT_VMCS, 5, 0x504030201}, 0, 0 }, + /* Overflow Packet */ + {2, {0x02, 0xf3}, 0, {INTEL_PT_OVF, 0, 0}, 0, 0 }, + {2, {0x02, 0xf3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 }, + {2, {0x02, 0xf3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 }, + /* Packet Stream Boundary*/ + {16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, 0, {INTEL_PT_PSB, 0, 0}, 0, 0 }, + {16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_4_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 }, + {16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_8_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 }, + /* PSB End Packet */ + {2, {0x02, 0x23}, 0, {INTEL_PT_PSBEND, 0, 0}, 0, 0 }, + /* Maintenance Packet */ + {11, {0x02, 0xc3, 0x88, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_MNT, 0, 0x7060504030201}, 0, 1 }, + /* Write Data to PT Packet */ + {6, {0x02, 0x12, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE, 0, 0x4030201}, 0, 0 }, + {10, {0x02, 0x32, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE, 1, 0x807060504030201}, 0, 0 }, + {6, {0x02, 0x92, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE_IP, 0, 0x4030201}, 0, 0 }, + {10, {0x02, 0xb2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE_IP, 1, 0x807060504030201}, 0, 0 }, + /* Execution Stop Packet */ + {2, {0x02, 0x62}, 0, {INTEL_PT_EXSTOP, 0, 0}, 0, 1 }, + {2, {0x02, 0xe2}, 0, {INTEL_PT_EXSTOP_IP, 0, 0}, 0, 1 }, + /* Monitor Wait Packet */ + {10, {0x02, 0xc2}, 0, {INTEL_PT_MWAIT, 0, 0}, 0, 0 }, + {10, {0x02, 0xc2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x807060504030201}, 0, 0 }, + {10, {0x02, 0xc2, 0xff, 2, 3, 4, 7, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x8070607040302ff}, 0, 0 }, + /* Power Entry Packet */ + {4, {0x02, 0x22}, 0, {INTEL_PT_PWRE, 0, 0}, 0, 1 }, + {4, {0x02, 0x22, 1, 2}, 0, {INTEL_PT_PWRE, 0, 0x0201}, 0, 1 }, + {4, {0x02, 0x22, 0x80, 0x34}, 0, {INTEL_PT_PWRE, 0, 0x3480}, 0, 1 }, + {4, {0x02, 0x22, 0x00, 0x56}, 0, {INTEL_PT_PWRE, 0, 0x5600}, 0, 1 }, + /* Power Exit Packet */ + {7, {0x02, 0xa2}, 0, {INTEL_PT_PWRX, 0, 0}, 0, 1 }, + {7, {0x02, 0xa2, 1, 2, 3, 4, 5}, 0, {INTEL_PT_PWRX, 0, 0x504030201}, 0, 1 }, + {7, {0x02, 0xa2, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_PWRX, 0, 0xffffffffff}, 0, 1 }, + /* Block Begin Packet */ + {3, {0x02, 0x63, 0x00}, 0, {INTEL_PT_BBP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 }, + {3, {0x02, 0x63, 0x80}, 0, {INTEL_PT_BBP, 1, 0}, INTEL_PT_BLK_4_CTX, 0 }, + {3, {0x02, 0x63, 0x1f}, 0, {INTEL_PT_BBP, 0, 0x1f}, INTEL_PT_BLK_8_CTX, 0 }, + {3, {0x02, 0x63, 0x9f}, 0, {INTEL_PT_BBP, 1, 0x1f}, INTEL_PT_BLK_4_CTX, 0 }, + /* 4-byte Block Item Packet */ + {5, {0x04}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_4_CTX, 0 }, + {5, {0xfc}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_4_CTX, 0 }, + {5, {0x04, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 }, + {5, {0xfc, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 }, + /* 8-byte Block Item Packet */ + {9, {0x04}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 }, + {9, {0xfc}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_8_CTX, 0 }, + {9, {0x04, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 }, + {9, {0xfc, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 }, + /* Block End Packet */ + {2, {0x02, 0x33}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 }, + {2, {0x02, 0xb3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 }, + {2, {0x02, 0x33}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 }, + {2, {0x02, 0xb3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 }, + /* Terminator */ + {0, {0}, 0, {0, 0, 0}, 0, 0 }, +}; + +static int dump_packet(struct intel_pt_pkt *packet, u8 *bytes, int len) +{ + char desc[INTEL_PT_PKT_DESC_MAX]; + int ret, i; + + for (i = 0; i < len; i++) + pr_debug(" %02x", bytes[i]); + for (; i < INTEL_PT_PKT_MAX_SZ; i++) + pr_debug(" "); + pr_debug(" "); + ret = intel_pt_pkt_desc(packet, desc, INTEL_PT_PKT_DESC_MAX); + if (ret < 0) { + pr_debug("intel_pt_pkt_desc failed!\n"); + return TEST_FAIL; + } + pr_debug("%s\n", desc); + + return TEST_OK; +} + +static void decoding_failed(struct test_data *d) +{ + pr_debug("Decoding failed!\n"); + pr_debug("Decoding: "); + dump_packet(&d->packet, d->bytes, d->len); +} + +static int fail(struct test_data *d, struct intel_pt_pkt *packet, int len, + enum intel_pt_pkt_ctx new_ctx) +{ + decoding_failed(d); + + if (len != d->len) + pr_debug("Expected length: %d Decoded length %d\n", + d->len, len); + + if (packet->type != d->packet.type) + pr_debug("Expected type: %d Decoded type %d\n", + d->packet.type, packet->type); + + if (packet->count != d->packet.count) + pr_debug("Expected count: %d Decoded count %d\n", + d->packet.count, packet->count); + + if (packet->payload != d->packet.payload) + pr_debug("Expected payload: 0x%llx Decoded payload 0x%llx\n", + (unsigned long long)d->packet.payload, + (unsigned long long)packet->payload); + + if (new_ctx != d->new_ctx) + pr_debug("Expected packet context: %d Decoded packet context %d\n", + d->new_ctx, new_ctx); + + return TEST_FAIL; +} + +static int test_ctx_unchanged(struct test_data *d, struct intel_pt_pkt *packet, + enum intel_pt_pkt_ctx ctx) +{ + enum intel_pt_pkt_ctx old_ctx = ctx; + + intel_pt_upd_pkt_ctx(packet, &ctx); + + if (ctx != old_ctx) { + decoding_failed(d); + pr_debug("Packet context changed!\n"); + return TEST_FAIL; + } + + return TEST_OK; +} + +static int test_one(struct test_data *d) +{ + struct intel_pt_pkt packet; + enum intel_pt_pkt_ctx ctx = d->ctx; + int ret; + + memset(&packet, 0xff, sizeof(packet)); + + /* Decode a packet */ + ret = intel_pt_get_packet(d->bytes, d->len, &packet, &ctx); + if (ret < 0 || ret > INTEL_PT_PKT_MAX_SZ) { + decoding_failed(d); + pr_debug("intel_pt_get_packet returned %d\n", ret); + return TEST_FAIL; + } + + /* Some packets must always leave the packet context unchanged */ + if (d->ctx_unchanged) { + int err; + + err = test_ctx_unchanged(d, &packet, INTEL_PT_NO_CTX); + if (err) + return err; + err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_4_CTX); + if (err) + return err; + err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_8_CTX); + if (err) + return err; + } + + /* Compare to the expected values */ + if (ret != d->len || packet.type != d->packet.type || + packet.count != d->packet.count || + packet.payload != d->packet.payload || ctx != d->new_ctx) + return fail(d, &packet, ret, ctx); + + pr_debug("Decoded ok:"); + ret = dump_packet(&d->packet, d->bytes, d->len); + + return ret; +} + +/* + * This test feeds byte sequences to the Intel PT packet decoder and checks the + * results. Changes to the packet context are also checked. + */ +int test__intel_pt_pkt_decoder(struct test *test __maybe_unused, int subtest __maybe_unused) +{ + struct test_data *d = data; + int ret; + + for (d = data; d->len; d++) { + ret = test_one(d); + if (ret) + return ret; + } + + return TEST_OK; +} diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index 675a0213044d..a3a0b6884779 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/string.h> +#include <linux/zalloc.h> #include "../../util/machine.h" #include "../../util/tool.h" #include "../../util/map.h" -#include "../../util/util.h" #include "../../util/debug.h" #if defined(__x86_64__) diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index e6d4d9591c79..ec5c1bb84095 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -9,12 +9,12 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/zalloc.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/tsc.h" diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 1869f62a10cd..609088c01e3a 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <linux/zalloc.h> #include <cpuid.h> #include "../../perf.h" diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c index 4520ac53caa9..1e9ec783b9a1 100644 --- a/tools/perf/arch/x86/util/machine.c +++ b/tools/perf/arch/x86/util/machine.c @@ -3,10 +3,11 @@ #include <linux/string.h> #include <stdlib.h> +#include "../../util/util.h" #include "../../util/machine.h" #include "../../util/map.h" #include "../../util/symbol.h" -#include "../../util/sane_ctype.h" +#include <linux/ctype.h> #include <symbol/kallsyms.h> diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 3666c0076df9..0d7b77ff0ae6 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -2,9 +2,9 @@ #include <errno.h> #include <string.h> #include <regex.h> +#include <linux/zalloc.h> #include "../../perf.h" -#include "../../util/util.h" #include "../../util/perf_regs.h" #include "../../util/debug.h" |