diff options
Diffstat (limited to 'tools/perf/util/intel-pt-decoder')
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/Build | 6 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 309 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-decoder.h | 13 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c | 28 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-log.h | 4 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c | 112 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h | 7 | ||||
| -rw-r--r-- | tools/perf/util/intel-pt-decoder/x86-opcode-map.txt | 2 |
8 files changed, 447 insertions, 34 deletions
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 9b742ea8bfe8..7aca5d6d7e1f 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -23,4 +23,8 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init +CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder + +ifneq ($(CC), clang) + CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init +endif diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index e4e7dc781d21..aa1593ce551d 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -22,6 +22,7 @@ #include <errno.h> #include <stdint.h> #include <inttypes.h> +#include <linux/compiler.h> #include "../cache.h" #include "../util.h" @@ -63,6 +64,25 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_FUP_NO_TIP, }; +static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) +{ + switch (pkt_state) { + case INTEL_PT_STATE_NO_PSB: + case INTEL_PT_STATE_NO_IP: + case INTEL_PT_STATE_ERR_RESYNC: + case INTEL_PT_STATE_IN_SYNC: + case INTEL_PT_STATE_TNT: + return true; + case INTEL_PT_STATE_TIP: + case INTEL_PT_STATE_TIP_PGD: + case INTEL_PT_STATE_FUP: + case INTEL_PT_STATE_FUP_NO_TIP: + return false; + default: + return true; + }; +} + #ifdef INTEL_PT_STRICT #define INTEL_PT_STATE_ERR1 INTEL_PT_STATE_NO_PSB #define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_PSB @@ -86,11 +106,13 @@ struct intel_pt_decoder { const unsigned char *buf; size_t len; bool return_compression; + bool branch_enable; bool mtc_insn; bool pge; bool have_tma; bool have_cyc; bool fixup_last_mtc; + bool have_last_ip; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -98,6 +120,7 @@ struct intel_pt_decoder { uint64_t timestamp; uint64_t tsc_timestamp; uint64_t ref_timestamp; + uint64_t sample_timestamp; uint64_t ret_addr; uint64_t ctc_timestamp; uint64_t ctc_delta; @@ -118,6 +141,7 @@ struct intel_pt_decoder { int pkt_len; int last_packet_type; unsigned int cbr; + unsigned int cbr_seen; unsigned int max_non_turbo_ratio; double max_non_turbo_ratio_fp; double cbr_cyc_to_tsc; @@ -135,9 +159,18 @@ struct intel_pt_decoder { bool continuous_period; bool overflow; bool set_fup_tx_flags; + bool set_fup_ptw; + bool set_fup_mwait; + bool set_fup_pwre; + bool set_fup_exstop; unsigned int fup_tx_flags; unsigned int tx_flags; + uint64_t fup_ptw_payload; + uint64_t fup_mwait_payload; + uint64_t fup_pwre_payload; + uint64_t cbr_payload; uint64_t timestamp_insn_cnt; + uint64_t sample_insn_cnt; uint64_t stuck_ip; int no_progress; int stuck_ip_prd; @@ -191,6 +224,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->pgd_ip = params->pgd_ip; decoder->data = params->data; decoder->return_compression = params->return_compression; + decoder->branch_enable = params->branch_enable; decoder->period = params->period; decoder->period_type = params->period_type; @@ -397,6 +431,7 @@ static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); + decoder->have_last_ip = true; } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -634,6 +669,8 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_PAD: case INTEL_PT_VMCS: case INTEL_PT_MNT: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: return 0; case INTEL_PT_MTC: @@ -674,6 +711,12 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) break; case INTEL_PT_TSC: + /* + * For now, do not support using TSC packets - refer + * intel_pt_calc_cyc_to_tsc(). + */ + if (data->from_mtc) + return 1; timestamp = pkt_info->packet.payload | (data->timestamp & (0xffULL << 56)); if (data->from_mtc && timestamp < data->timestamp && @@ -732,6 +775,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_TIP_PGD: case INTEL_PT_TRACESTOP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: case INTEL_PT_OVF: case INTEL_PT_BAD: /* Does not happen */ default: @@ -786,6 +834,14 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder, .cbr_cyc_to_tsc = 0, }; + /* + * For now, do not support using TSC packets for at least the reasons: + * 1) timing might have stopped + * 2) TSC packets within PSB+ can slip against CYC packets + */ + if (!from_mtc) + return; + intel_pt_pkt_lookahead(decoder, intel_pt_calc_cyc_cb, &data); } @@ -897,6 +953,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder, decoder->tot_insn_cnt += insn_cnt; decoder->timestamp_insn_cnt += insn_cnt; + decoder->sample_insn_cnt += insn_cnt; decoder->period_insn_cnt += insn_cnt; if (err) { @@ -989,6 +1046,57 @@ out_no_progress: return err; } +static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) +{ + bool ret = false; + + if (decoder->set_fup_tx_flags) { + decoder->set_fup_tx_flags = false; + decoder->tx_flags = decoder->fup_tx_flags; + decoder->state.type = INTEL_PT_TRANSACTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.flags = decoder->fup_tx_flags; + return true; + } + if (decoder->set_fup_ptw) { + decoder->set_fup_ptw = false; + decoder->state.type = INTEL_PT_PTW; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->fup_ptw_payload; + return true; + } + if (decoder->set_fup_mwait) { + decoder->set_fup_mwait = false; + decoder->state.type = INTEL_PT_MWAIT_OP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.mwait_payload = decoder->fup_mwait_payload; + ret = true; + } + if (decoder->set_fup_pwre) { + decoder->set_fup_pwre = false; + decoder->state.type |= INTEL_PT_PWR_ENTRY; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwre_payload = decoder->fup_pwre_payload; + ret = true; + } + if (decoder->set_fup_exstop) { + decoder->set_fup_exstop = false; + decoder->state.type |= INTEL_PT_EX_STOP; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + ret = true; + } + return ret; +} + static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) { struct intel_pt_insn intel_pt_insn; @@ -1002,15 +1110,8 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) if (err == INTEL_PT_RETURN) return 0; if (err == -EAGAIN) { - if (decoder->set_fup_tx_flags) { - decoder->set_fup_tx_flags = false; - decoder->tx_flags = decoder->fup_tx_flags; - decoder->state.type = INTEL_PT_TRANSACTION; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; - decoder->state.flags = decoder->fup_tx_flags; + if (intel_pt_fup_event(decoder)) return 0; - } return err; } decoder->set_fup_tx_flags = false; @@ -1359,7 +1460,9 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) { - unsigned int cbr = decoder->packet.payload; + unsigned int cbr = decoder->packet.payload & 0xff; + + decoder->cbr_payload = decoder->packet.payload; if (decoder->cbr == cbr) return; @@ -1416,6 +1519,13 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_TRACESTOP: case INTEL_PT_BAD: case INTEL_PT_PSB: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); return -EAGAIN; @@ -1445,7 +1555,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - intel_pt_set_last_ip(decoder); + if (decoder->packet.count) + intel_pt_set_last_ip(decoder); break; case INTEL_PT_MODE_TSX: @@ -1496,6 +1607,13 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_MODE_TSX: case INTEL_PT_BAD: case INTEL_PT_PSBEND: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Missing TIP after FUP\n"); decoder->pkt_state = INTEL_PT_STATE_ERR3; return -ENOENT; @@ -1624,6 +1742,15 @@ next: break; } intel_pt_set_last_ip(decoder); + if (!decoder->branch_enable) { + decoder->ip = decoder->last_ip; + if (intel_pt_fup_event(decoder)) + return 0; + no_tip = false; + break; + } + if (decoder->set_fup_mwait) + no_tip = true; err = intel_pt_walk_fup(decoder); if (err != -EAGAIN) { if (err) @@ -1649,6 +1776,8 @@ next: break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psbend(decoder); if (err == -EAGAIN) @@ -1695,6 +1824,16 @@ next: case INTEL_PT_CBR: intel_pt_calc_cbr(decoder); + if (!decoder->branch_enable && + decoder->cbr != decoder->cbr_seen) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type = INTEL_PT_CBR_CHG; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.cbr_payload = + decoder->packet.payload; + return 0; + } break; case INTEL_PT_MODE_EXEC: @@ -1721,6 +1860,71 @@ next: case INTEL_PT_PAD: break; + case INTEL_PT_PTWRITE_IP: + decoder->fup_ptw_payload = decoder->packet.payload; + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_ptw = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after PTWRITE", + decoder->pos); + } + goto next; + + case INTEL_PT_PTWRITE: + decoder->state.type = INTEL_PT_PTW; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_MWAIT: + decoder->fup_mwait_payload = decoder->packet.payload; + decoder->set_fup_mwait = true; + break; + + case INTEL_PT_PWRE: + if (decoder->set_fup_mwait) { + decoder->fup_pwre_payload = + decoder->packet.payload; + decoder->set_fup_pwre = true; + break; + } + decoder->state.type = INTEL_PT_PWR_ENTRY; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_EXSTOP_IP: + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_exstop = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after EXSTOP", + decoder->pos); + } + goto next; + + case INTEL_PT_EXSTOP: + decoder->state.type = INTEL_PT_EX_STOP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return 0; + + case INTEL_PT_PWRX: + decoder->state.type = INTEL_PT_PWR_EXIT; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + default: return intel_pt_bug(decoder); } @@ -1729,8 +1933,9 @@ next: static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) { - return decoder->last_ip || decoder->packet.count == 0 || - decoder->packet.count == 3 || decoder->packet.count == 6; + return decoder->packet.count && + (decoder->have_last_ip || decoder->packet.count == 3 || + decoder->packet.count == 6); } /* Walk PSB+ packets to get in sync. */ @@ -1746,8 +1951,16 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Unexpected packet\n"); return -ENOENT; @@ -1799,6 +2012,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; intel_pt_clear_tx_flags(decoder); + __fallthrough; + case INTEL_PT_TNT: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); @@ -1839,6 +2054,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; @@ -1849,14 +2065,10 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_FUP: - if (decoder->overflow) { - if (intel_pt_have_ip(decoder)) - intel_pt_set_ip(decoder); - if (decoder->ip) - return 0; - } - if (decoder->packet.count) - intel_pt_set_last_ip(decoder); + if (intel_pt_have_ip(decoder)) + intel_pt_set_ip(decoder); + if (decoder->ip) + return 0; break; case INTEL_PT_MTC: @@ -1905,6 +2117,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; + intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psb(decoder); if (err) return err; @@ -1920,6 +2135,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_VMCS: case INTEL_PT_MNT: case INTEL_PT_PAD: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: default: break; } @@ -1930,6 +2152,19 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) { int err; + decoder->set_fup_tx_flags = false; + decoder->set_fup_ptw = false; + decoder->set_fup_mwait = false; + decoder->set_fup_pwre = false; + decoder->set_fup_exstop = false; + + if (!decoder->branch_enable) { + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->overflow = false; + decoder->state.type = 0; /* Do not have a sample */ + return 0; + } + intel_pt_log("Scanning for full IP\n"); err = intel_pt_walk_to_ip(decoder); if (err) @@ -2038,6 +2273,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; + decoder->have_last_ip = false; decoder->last_ip = 0; decoder->ip = 0; intel_pt_clear_stack(&decoder->stack); @@ -2046,6 +2282,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) if (err) return err; + decoder->have_last_ip = true; decoder->pkt_state = INTEL_PT_STATE_NO_IP; err = intel_pt_walk_psb(decoder); @@ -2064,7 +2301,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) { - uint64_t est = decoder->timestamp_insn_cnt << 1; + uint64_t est = decoder->sample_insn_cnt << 1; if (!decoder->cbr || !decoder->max_non_turbo_ratio) goto out; @@ -2072,7 +2309,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) est *= decoder->max_non_turbo_ratio; est /= decoder->cbr; out: - return decoder->timestamp + est; + return decoder->sample_timestamp + est; } const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) @@ -2088,8 +2325,10 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_sync(decoder); break; case INTEL_PT_STATE_NO_IP: + decoder->have_last_ip = false; decoder->last_ip = 0; - /* Fall through */ + decoder->ip = 0; + __fallthrough; case INTEL_PT_STATE_ERR_RESYNC: err = intel_pt_sync_ip(decoder); break; @@ -2125,15 +2364,29 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) } } while (err == -ENOLINK); - decoder->state.err = err ? intel_pt_ext_err(err) : 0; - decoder->state.timestamp = decoder->timestamp; + if (err) { + decoder->state.err = intel_pt_ext_err(err); + decoder->state.from_ip = decoder->ip; + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } else { + decoder->state.err = 0; + if (decoder->cbr != decoder->cbr_seen && decoder->state.type) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type |= INTEL_PT_CBR_CHG; + decoder->state.cbr_payload = decoder->cbr_payload; + } + if (intel_pt_sample_time(decoder->pkt_state)) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } + } + + decoder->state.timestamp = decoder->sample_timestamp; decoder->state.est_timestamp = intel_pt_est_timestamp(decoder); decoder->state.cr3 = decoder->cr3; decoder->state.tot_insn_cnt = decoder->tot_insn_cnt; - if (err) - decoder->state.from_ip = decoder->ip; - return &decoder->state; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index e90619a43c0c..921b22e8ca0e 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -25,11 +25,18 @@ #define INTEL_PT_IN_TX (1 << 0) #define INTEL_PT_ABORT_TX (1 << 1) #define INTEL_PT_ASYNC (1 << 2) +#define INTEL_PT_FUP_IP (1 << 3) enum intel_pt_sample_type { INTEL_PT_BRANCH = 1 << 0, INTEL_PT_INSTRUCTION = 1 << 1, INTEL_PT_TRANSACTION = 1 << 2, + INTEL_PT_PTW = 1 << 3, + INTEL_PT_MWAIT_OP = 1 << 4, + INTEL_PT_PWR_ENTRY = 1 << 5, + INTEL_PT_EX_STOP = 1 << 6, + INTEL_PT_PWR_EXIT = 1 << 7, + INTEL_PT_CBR_CHG = 1 << 8, }; enum intel_pt_period_type { @@ -63,6 +70,11 @@ struct intel_pt_state { uint64_t timestamp; uint64_t est_timestamp; uint64_t trace_nr; + uint64_t ptw_payload; + uint64_t mwait_payload; + uint64_t pwre_payload; + uint64_t pwrx_payload; + uint64_t cbr_payload; uint32_t flags; enum intel_pt_insn_op insn_op; int insn_len; @@ -87,6 +99,7 @@ struct intel_pt_params { bool (*pgd_ip)(uint64_t ip, void *data); void *data; bool return_compression; + bool branch_enable; uint64_t period; enum intel_pt_period_type period_type; unsigned max_non_turbo_ratio; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 7913363bde5c..54818828023b 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -26,12 +26,13 @@ #include "insn.c" #include "intel-pt-insn-decoder.h" +#include "dump-insn.h" #if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN #error Instruction buffer size too small #endif -/* Based on branch_type() from perf_event_intel_lbr.c */ +/* Based on branch_type() from arch/x86/events/intel/lbr.c */ static void intel_pt_insn_decoder(struct insn *insn, struct intel_pt_insn *intel_pt_insn) { @@ -39,6 +40,8 @@ static void intel_pt_insn_decoder(struct insn *insn, enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH; int ext; + intel_pt_insn->rel = 0; + if (insn_is_avx(insn)) { intel_pt_insn->op = INTEL_PT_OP_OTHER; intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH; @@ -177,6 +180,29 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64, return 0; } +const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused, + u8 *inbuf, int inlen, int *lenp) +{ + struct insn insn; + int n, i; + int left; + + insn_init(&insn, inbuf, inlen, x->is64bit); + insn_get_length(&insn); + if (!insn_complete(&insn) || insn.length > inlen) + return "<bad>"; + if (lenp) + *lenp = insn.length; + left = sizeof(x->out); + n = snprintf(x->out, left, "insn: "); + left -= n; + for (i = 0; i < insn.length; i++) { + n += snprintf(x->out + n, left, "%02x ", inbuf[i]); + left -= n; + } + return x->out; +} + const char *branch_name[] = { [INTEL_PT_OP_OTHER] = "Other", [INTEL_PT_OP_CALL] = "Call", diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index debe751dc3d6..45b64f93f358 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -16,6 +16,7 @@ #ifndef INCLUDE__INTEL_PT_LOG_H__ #define INCLUDE__INTEL_PT_LOG_H__ +#include <linux/compiler.h> #include <stdint.h> #include <inttypes.h> @@ -34,8 +35,7 @@ void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip); void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip); -__attribute__((format(printf, 1, 2))) -void __intel_pt_log(const char *fmt, ...); +void __intel_pt_log(const char *fmt, ...) __printf(1, 2); #define intel_pt_log(fmt, ...) \ do { \ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 4f7b32020487..ba4c9dd18643 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -17,6 +17,7 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/compiler.h> #include "intel-pt-pkt-decoder.h" @@ -63,6 +64,13 @@ static const char * const packet_name[] = { [INTEL_PT_PIP] = "PIP", [INTEL_PT_OVF] = "OVF", [INTEL_PT_MNT] = "MNT", + [INTEL_PT_PTWRITE] = "PTWRITE", + [INTEL_PT_PTWRITE_IP] = "PTWRITE", + [INTEL_PT_EXSTOP] = "EXSTOP", + [INTEL_PT_EXSTOP_IP] = "EXSTOP", + [INTEL_PT_MWAIT] = "MWAIT", + [INTEL_PT_PWRE] = "PWRE", + [INTEL_PT_PWRX] = "PWRX", }; const char *intel_pt_pkt_name(enum intel_pt_pkt_type type) @@ -122,7 +130,7 @@ static int intel_pt_get_cbr(const unsigned char *buf, size_t len, if (len < 4) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_CBR; - packet->payload = buf[2]; + packet->payload = le16_to_cpu(*(uint16_t *)(buf + 2)); return 4; } @@ -216,12 +224,80 @@ static int intel_pt_get_3byte(const unsigned char *buf, size_t len, } } +static int intel_pt_get_ptwrite(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + packet->count = (buf[1] >> 5) & 0x3; + packet->type = buf[1] & BIT(7) ? INTEL_PT_PTWRITE_IP : + INTEL_PT_PTWRITE; + + switch (packet->count) { + case 0: + if (len < 6) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le32_to_cpu(*(uint32_t *)(buf + 2)); + return 6; + case 1: + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; + default: + return INTEL_PT_BAD_PACKET; + } +} + +static int intel_pt_get_exstop(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP; + return 2; +} + +static int intel_pt_get_exstop_ip(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP_IP; + return 2; +} + +static int intel_pt_get_mwait(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_MWAIT; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; +} + +static int intel_pt_get_pwre(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 4) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRE; + memcpy_le64(&packet->payload, buf + 2, 2); + return 4; +} + +static int intel_pt_get_pwrx(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 7) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRX; + memcpy_le64(&packet->payload, buf + 2, 5); + return 7; +} + static int intel_pt_get_ext(const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { if (len < 2) return INTEL_PT_NEED_MORE_BYTES; + if ((buf[1] & 0x1f) == 0x12) + return intel_pt_get_ptwrite(buf, len, packet); + switch (buf[1]) { case 0xa3: /* Long TNT */ return intel_pt_get_long_tnt(buf, len, packet); @@ -243,6 +319,16 @@ static int intel_pt_get_ext(const unsigned char *buf, size_t len, return intel_pt_get_tma(buf, len, packet); case 0xC3: /* 3-byte header */ return intel_pt_get_3byte(buf, len, packet); + case 0x62: /* EXSTOP no IP */ + return intel_pt_get_exstop(packet); + case 0xE2: /* EXSTOP with IP */ + return intel_pt_get_exstop_ip(packet); + case 0xC2: /* MWAIT */ + return intel_pt_get_mwait(buf, len, packet); + case 0x22: /* PWRE */ + return intel_pt_get_pwre(buf, len, packet); + case 0xA2: /* PWRX */ + return intel_pt_get_pwrx(buf, len, packet); default: return INTEL_PT_BAD_PACKET; } @@ -498,6 +584,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, case INTEL_PT_FUP: if (!(packet->count)) return snprintf(buf, buf_len, "%s no ip", name); + __fallthrough; case INTEL_PT_CYC: case INTEL_PT_VMCS: case INTEL_PT_MTC: @@ -520,6 +607,29 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, ret = snprintf(buf, buf_len, "%s 0x%llx (NR=%d)", name, payload, nr); return ret; + case INTEL_PT_PTWRITE: + return snprintf(buf, buf_len, "%s 0x%llx IP:0", name, payload); + case INTEL_PT_PTWRITE_IP: + return snprintf(buf, buf_len, "%s 0x%llx IP:1", name, payload); + case INTEL_PT_EXSTOP: + return snprintf(buf, buf_len, "%s IP:0", name); + case INTEL_PT_EXSTOP_IP: + return snprintf(buf, buf_len, "%s IP:1", name); + case INTEL_PT_MWAIT: + return snprintf(buf, buf_len, "%s 0x%llx Hints 0x%x Extensions 0x%x", + name, payload, (unsigned int)(payload & 0xff), + (unsigned int)((payload >> 32) & 0x3)); + case INTEL_PT_PWRE: + return snprintf(buf, buf_len, "%s 0x%llx HW:%u CState:%u Sub-CState:%u", + name, payload, !!(payload & 0x80), + (unsigned int)((payload >> 12) & 0xf), + (unsigned int)((payload >> 8) & 0xf)); + case INTEL_PT_PWRX: + return snprintf(buf, buf_len, "%s 0x%llx Last CState:%u Deepest CState:%u Wake Reason 0x%x", + name, payload, + (unsigned int)((payload >> 4) & 0xf), + (unsigned int)(payload & 0xf), + (unsigned int)((payload >> 8) & 0xf)); default: break; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h index 781bb79883bd..73ddc3a88d07 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h @@ -52,6 +52,13 @@ enum intel_pt_pkt_type { INTEL_PT_PIP, INTEL_PT_OVF, INTEL_PT_MNT, + INTEL_PT_PTWRITE, + INTEL_PT_PTWRITE_IP, + INTEL_PT_EXSTOP, + INTEL_PT_EXSTOP_IP, + INTEL_PT_MWAIT, + INTEL_PT_PWRE, + INTEL_PT_PWRX, }; struct intel_pt_pkt { diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) |
