diff options
27 files changed, 1481 insertions, 97 deletions
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index f97479f1ce35..d2f6d0be3503 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -601,7 +601,22 @@ static int probes_seq_show(struct seq_file *m, void *v) seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, trace_event_name(&tu->tp.call)); - seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset); + seq_printf(m, " %s:", tu->filename); + + /* Don't print "0x (null)" when offset is 0 */ + if (tu->offset) { + seq_printf(m, "0x%p", (void *)tu->offset); + } else { + switch (sizeof(void *)) { + case 4: + seq_printf(m, "0x00000000"); + break; + case 8: + default: + seq_printf(m, "0x0000000000000000"); + break; + } + } for (i = 0; i < tu->tp.nr_args; i++) seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); diff --git a/tools/build/Documentation/Build.txt b/tools/build/Documentation/Build.txt index 00ad2d608727..aa5e092c4352 100644 --- a/tools/build/Documentation/Build.txt +++ b/tools/build/Documentation/Build.txt @@ -66,6 +66,7 @@ To follow the above example, the user provides following 'Build' files: ex/Build: ex-y += a.o ex-y += b.o + ex-y += b.o # duplicates in the lists are allowed libex-y += c.o libex-y += d.o diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 8120af9c0341..0c5f485521d6 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -63,7 +63,7 @@ quiet_cmd_gen = GEN $@ # If there's nothing to link, create empty $@ object. quiet_cmd_ld_multi = LD $@ cmd_ld_multi = $(if $(strip $(obj-y)),\ - $(LD) -r -o $@ $(obj-y),rm -f $@; $(AR) rcs $@) + $(LD) -r -o $@ $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@) # Build rules $(OUTPUT)%.o: %.c FORCE diff --git a/tools/build/tests/ex/Build b/tools/build/tests/ex/Build index 70d876237c57..429c7d452101 100644 --- a/tools/build/tests/ex/Build +++ b/tools/build/tests/ex/Build @@ -1,6 +1,7 @@ ex-y += ex.o ex-y += a.o ex-y += b.o +ex-y += b.o ex-y += empty/ ex-y += empty2/ diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index 2866b62eb293..4a0501d7a3b4 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -142,19 +142,21 @@ which is the same as -e intel_pt/tsc=1,noretcomp=0/ +Note there are now new config terms - see section 'config terms' further below. + The config terms are listed in /sys/devices/intel_pt/format. They are bit fields within the config member of the struct perf_event_attr which is passed to the kernel by the perf_event_open system call. They correspond to bit fields in the IA32_RTIT_CTL MSR. Here is a list of them and their definitions: - $ for f in `ls /sys/devices/intel_pt/format`;do - > echo $f - > cat /sys/devices/intel_pt/format/$f - > done - noretcomp - config:11 - tsc - config:10 + $ grep -H . /sys/bus/event_source/devices/intel_pt/format/* + /sys/bus/event_source/devices/intel_pt/format/cyc:config:1 + /sys/bus/event_source/devices/intel_pt/format/cyc_thresh:config:19-22 + /sys/bus/event_source/devices/intel_pt/format/mtc:config:9 + /sys/bus/event_source/devices/intel_pt/format/mtc_period:config:14-17 + /sys/bus/event_source/devices/intel_pt/format/noretcomp:config:11 + /sys/bus/event_source/devices/intel_pt/format/psb_period:config:24-27 + /sys/bus/event_source/devices/intel_pt/format/tsc:config:10 Note that the default config must be overridden for each term i.e. @@ -209,9 +211,185 @@ perf_event_attr is displayed if the -vv option is used e.g. ------------------------------------------------------------ +config terms +------------ + +The June 2015 version of Intel 64 and IA-32 Architectures Software Developer +Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features. +Some of the features are reflect in new config terms. All the config terms are +described below. + +tsc Always supported. Produces TSC timestamp packets to provide + timing information. In some cases it is possible to decode + without timing information, for example a per-thread context + that does not overlap executable memory maps. + + The default config selects tsc (i.e. tsc=1). + +noretcomp Always supported. Disables "return compression" so a TIP packet + is produced when a function returns. Causes more packets to be + produced but might make decoding more reliable. + + The default config does not select noretcomp (i.e. noretcomp=0). + +psb_period Allows the frequency of PSB packets to be specified. + + The PSB packet is a synchronization packet that provides a + starting point for decoding or recovery from errors. + + Support for psb_period is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/psb_cyc + + which contains "1" if the feature is supported and "0" + otherwise. + + Valid values are given by: + + /sys/bus/event_source/devices/intel_pt/caps/psb_periods + + which contains a hexadecimal value, the bits of which represent + valid values e.g. bit 2 set means value 2 is valid. + + The psb_period value is converted to the approximate number of + trace bytes between PSB packets as: + + 2 ^ (value + 11) + + e.g. value 3 means 16KiB bytes between PSBs + + If an invalid value is entered, the error message + will give a list of valid values e.g. + + $ perf record -e intel_pt/psb_period=15/u uname + Invalid psb_period for intel_pt. Valid values are: 0-5 + + If MTC packets are selected, the default config selects a value + of 3 (i.e. psb_period=3) or the nearest lower value that is + supported (0 is always supported). Otherwise the default is 0. + + If decoding is expected to be reliable and the buffer is large + then a large PSB period can be used. + + Because a TSC packet is produced with PSB, the PSB period can + also affect the granularity to timing information in the absence + of MTC or CYC. + +mtc Produces MTC timing packets. + + MTC packets provide finer grain timestamp information than TSC + packets. MTC packets record time using the hardware crystal + clock (CTC) which is related to TSC packets using a TMA packet. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/mtc + + which contains "1" if the feature is supported and + "0" otherwise. + + The frequency of MTC packets can also be specified - see + mtc_period below. + +mtc_period Specifies how frequently MTC packets are produced - see mtc + above for how to determine if MTC packets are supported. + + Valid values are given by: + + /sys/bus/event_source/devices/intel_pt/caps/mtc_periods + + which contains a hexadecimal value, the bits of which represent + valid values e.g. bit 2 set means value 2 is valid. + + The mtc_period value is converted to the MTC frequency as: + + CTC-frequency / (2 ^ value) + + e.g. value 3 means one eighth of CTC-frequency + + Where CTC is the hardware crystal clock, the frequency of which + can be related to TSC via values provided in cpuid leaf 0x15. + + If an invalid value is entered, the error message + will give a list of valid values e.g. + + $ perf record -e intel_pt/mtc_period=15/u uname + Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9 + + The default value is 3 or the nearest lower value + that is supported (0 is always supported). + +cyc Produces CYC timing packets. + + CYC packets provide even finer grain timestamp information than + MTC and TSC packets. A CYC packet contains the number of CPU + cycles since the last CYC packet. Unlike MTC and TSC packets, + CYC packets are only sent when another packet is also sent. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/psb_cyc + + which contains "1" if the feature is supported and + "0" otherwise. + + The number of CYC packets produced can be reduced by specifying + a threshold - see cyc_thresh below. + +cyc_thresh Specifies how frequently CYC packets are produced - see cyc + above for how to determine if CYC packets are supported. + + Valid cyc_thresh values are given by: + + /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds + + which contains a hexadecimal value, the bits of which represent + valid values e.g. bit 2 set means value 2 is valid. + + The cyc_thresh value represents the minimum number of CPU cycles + that must have passed before a CYC packet can be sent. The + number of CPU cycles is: + + 2 ^ (value - 1) + + e.g. value 4 means 8 CPU cycles must pass before a CYC packet + can be sent. Note a CYC packet is still only sent when another + packet is sent, not at, e.g. every 8 CPU cycles. + + If an invalid value is entered, the error message + will give a list of valid values e.g. + + $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname + Invalid cyc_thresh for intel_pt. Valid values are: 0-12 + + CYC packets are not requested by default. + +no_force_psb This is a driver option and is not in the IA32_RTIT_CTL MSR. + + It stops the driver resetting the byte count to zero whenever + enabling the trace (for example on context switches) which in + turn results in no PSB being forced. However some processors + will produce a PSB anyway. + + In any case, there is still a PSB when the trace is enabled for + the first time. + + no_force_psb can be used to slightly decrease the trace size but + may make it harder for the decoder to recover from errors. + + no_force_psb is not selected by default. + + new snapshot option ------------------- +The difference between full trace and snapshot from the kernel's perspective is +that in full trace we don't overwrite trace data that the user hasn't collected +yet (and indicated that by advancing aux_tail), whereas in snapshot mode we let +the trace run and overwrite older data in the buffer so that whenever something +interesting happens, we can stop it and grab a snapshot of what was going on +around that interesting moment. + To select snapshot mode a new option has been added: -S diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index f31f15a5f873..af009bd6e6b7 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -41,7 +41,6 @@ tools/include/asm-generic/bitops.h tools/include/linux/atomic.h tools/include/linux/bitops.h tools/include/linux/compiler.h -tools/include/linux/export.h tools/include/linux/hash.h tools/include/linux/kernel.h tools/include/linux/list.h diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index da7d2c15e611..2ca10d796c0b 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -18,6 +18,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include <linux/log2.h> +#include <cpuid.h> #include "../../perf.h" #include "../../util/session.h" @@ -99,17 +100,137 @@ static int intel_pt_parse_terms(struct list_head *formats, const char *str, return intel_pt_parse_terms_with_default(formats, str, config); } -static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static u64 intel_pt_masked_bits(u64 mask, u64 bits) { - return 256; + const u64 top_bit = 1ULL << 63; + u64 res = 0; + int i; + + for (i = 0; i < 64; i++) { + if (mask & top_bit) { + res <<= 1; + if (bits & top_bit) + res |= 1; + } + mask <<= 1; + bits <<= 1; + } + + return res; +} + +static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, + struct perf_evlist *evlist, u64 *res) +{ + struct perf_evsel *evsel; + u64 mask; + + *res = 0; + + mask = perf_pmu__format_bits(&intel_pt_pmu->format, str); + if (!mask) + return -EINVAL; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type == intel_pt_pmu->type) { + *res = intel_pt_masked_bits(mask, evsel->attr.config); + return 0; + } + } + + return -EINVAL; +} + +static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu, + struct perf_evlist *evlist) +{ + u64 val; + int err, topa_multiple_entries; + size_t psb_period; + + if (perf_pmu__scan_file(intel_pt_pmu, "caps/topa_multiple_entries", + "%d", &topa_multiple_entries) != 1) + topa_multiple_entries = 0; + + /* + * Use caps/topa_multiple_entries to indicate early hardware that had + * extra frequent PSBs. + */ + if (!topa_multiple_entries) { + psb_period = 256; + goto out; + } + + err = intel_pt_read_config(intel_pt_pmu, "psb_period", evlist, &val); + if (err) + val = 0; + + psb_period = 1 << (val + 11); +out: + pr_debug2("%s psb_period %zu\n", intel_pt_pmu->name, psb_period); + return psb_period; +} + +static int intel_pt_pick_bit(int bits, int target) +{ + int pos, pick = -1; + + for (pos = 0; bits; bits >>= 1, pos++) { + if (bits & 1) { + if (pos <= target || pick < 0) + pick = pos; + if (pos >= target) + break; + } + } + + return pick; } static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) { + char buf[256]; + int mtc, mtc_periods = 0, mtc_period; + int psb_cyc, psb_periods, psb_period; + int pos = 0; u64 config; - intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &config); + pos += scnprintf(buf + pos, sizeof(buf) - pos, "tsc"); + + if (perf_pmu__scan_file(intel_pt_pmu, "caps/mtc", "%d", + &mtc) != 1) + mtc = 1; + + if (mtc) { + if (perf_pmu__scan_file(intel_pt_pmu, "caps/mtc_periods", "%x", + &mtc_periods) != 1) + mtc_periods = 0; + if (mtc_periods) { + mtc_period = intel_pt_pick_bit(mtc_periods, 3); + pos += scnprintf(buf + pos, sizeof(buf) - pos, + ",mtc,mtc_period=%d", mtc_period); + } + } + + if (perf_pmu__scan_file(intel_pt_pmu, "caps/psb_cyc", "%d", + &psb_cyc) != 1) + psb_cyc = 1; + + if (psb_cyc && mtc_periods) { + if (perf_pmu__scan_file(intel_pt_pmu, "caps/psb_periods", "%x", + &psb_periods) != 1) + psb_periods = 0; + if (psb_periods) { + psb_period = intel_pt_pick_bit(psb_periods, 3); + pos += scnprintf(buf + pos, sizeof(buf) - pos, + ",psb_period=%d", psb_period); + } + } + + pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf); + + intel_pt_parse_terms(&intel_pt_pmu->format, buf, &config); + return config; } @@ -157,6 +278,15 @@ static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused return INTEL_PT_AUXTRACE_PRIV_SIZE; } +static void intel_pt_tsc_ctc_ratio(u32 *n, u32 *d) +{ + unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0; + + __get_cpuid(0x15, &eax, &ebx, &ecx, &edx); + *n = ebx; + *d = eax; +} + static int intel_pt_info_fill(struct auxtrace_record *itr, struct perf_session *session, struct auxtrace_info_event *auxtrace_info, @@ -168,7 +298,8 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, struct perf_event_mmap_page *pc; struct perf_tsc_conversion tc = { .time_mult = 0, }; bool cap_user_time_zero = false, per_cpu_mmaps; - u64 tsc_bit, noretcomp_bit; + u64 tsc_bit, mtc_bit, mtc_freq_bits, cyc_bit, noretcomp_bit; + u32 tsc_ctc_ratio_n, tsc_ctc_ratio_d; int err; if (priv_size != INTEL_PT_AUXTRACE_PRIV_SIZE) @@ -177,6 +308,12 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit); intel_pt_parse_terms(&intel_pt_pmu->format, "noretcomp", &noretcomp_bit); + intel_pt_parse_terms(&intel_pt_pmu->format, "mtc", &mtc_bit); + mtc_freq_bits = perf_pmu__format_bits(&intel_pt_pmu->format, + "mtc_period"); + intel_pt_parse_terms(&intel_pt_pmu->format, "cyc", &cyc_bit); + + intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d); if (!session->evlist->nr_mmaps) return -EINVAL; @@ -207,6 +344,11 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, auxtrace_info->priv[INTEL_PT_HAVE_SCHED_SWITCH] = ptr->have_sched_switch; auxtrace_info->priv[INTEL_PT_SNAPSHOT_MODE] = ptr->snapshot_mode; auxtrace_info->priv[INTEL_PT_PER_CPU_MMAPS] = per_cpu_mmaps; + auxtrace_info->priv[INTEL_PT_MTC_BIT] = mtc_bit; + auxtrace_info->priv[INTEL_PT_MTC_FREQ_BITS] = mtc_freq_bits; + auxtrace_info->priv[INTEL_PT_TSC_CTC_N] = tsc_ctc_ratio_n; + auxtrace_info->priv[INTEL_PT_TSC_CTC_D] = tsc_ctc_ratio_d; + auxtrace_info->priv[INTEL_PT_CYC_BIT] = cyc_bit; return 0; } @@ -239,6 +381,117 @@ static int intel_pt_track_switches(struct perf_evlist *evlist) return 0; } +static void intel_pt_valid_str(char *str, size_t len, u64 valid) +{ + unsigned int val, last = 0, state = 1; + int p = 0; + + str[0] = '\0'; + + for (val = 0; val <= 64; val++, valid >>= 1) { + if (valid & 1) { + last = val; + switch (state) { + case 0: + p += scnprintf(str + p, len - p, ","); + /* Fall through */ + case 1: + p += scnprintf(str + p, len - p, "%u", val); + state = 2; + break; + case 2: + state = 3; + break; + case 3: + state = 4; + break; + default: + break; + } + } else { + switch (state) { + case 3: + p += scnprintf(str + p, len - p, ",%u", last); + state = 0; + break; + case 4: + p += scnprintf(str + p, len - p, "-%u", last); + state = 0; + break; + default: + break; + } + if (state != 1) + state = 0; + } + } +} + +static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, + const char *caps, const char *name, + const char *supported, u64 config) +{ + char valid_str[256]; + unsigned int shift; + unsigned long long valid; + u64 bits; + int ok; + + if (perf_pmu__scan_file(intel_pt_pmu, caps, "%llx", &valid) != 1) + valid = 0; + + if (supported && + perf_pmu__scan_file(intel_pt_pmu, supported, "%d", &ok) == 1 && !ok) + valid = 0; + + valid |= 1; + + bits = perf_pmu__format_bits(&intel_pt_pmu->format, name); + + config &= bits; + + for (shift = 0; bits && !(bits & 1); shift++) + bits >>= 1; + + config >>= shift; + + if (config > 63) + goto out_err; + + if (valid & (1 << config)) + return 0; +out_err: + intel_pt_valid_str(valid_str, sizeof(valid_str), valid); + pr_err("Invalid %s for %s. Valid values are: %s\n", + name, INTEL_PT_PMU_NAME, valid_str); + return -EINVAL; +} + +static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, + struct perf_evsel *evsel) +{ + int err; + + if (!evsel) + return 0; + + err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds", + "cyc_thresh", "caps/psb_cyc", + evsel->attr.config); + if (err) + return err; + + err = intel_pt_val_config_term(intel_pt_pmu, "caps/mtc_periods", + "mtc_period", "caps/mtc", + evsel->attr.config); + if (err) + return err; + + return intel_pt_val_config_term(intel_pt_pmu, "caps/psb_periods", + "psb_period", "caps/psb_cyc", + evsel->attr.config); +} + static int intel_pt_recording_options(struct auxtrace_record *itr, struct perf_evlist *evlist, struct record_opts *opts) @@ -251,6 +504,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, const struct cpu_map *cpus = evlist->cpus; bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; u64 tsc_bit; + int err; ptr->evlist = evlist; ptr->snapshot_mode = opts->auxtrace_snapshot_mode; @@ -281,6 +535,10 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; + err = intel_pt_validate_config(intel_pt_pmu, intel_pt_evsel); + if (err) + return err; + /* Set default sizes for snapshot mode */ if (opts->auxtrace_snapshot_mode) { size_t psb_period = intel_pt_psb_period(intel_pt_pmu, evlist); @@ -366,8 +624,6 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * threads. */ if (have_timing_info && !cpu_map__empty(cpus)) { - int err; - err = intel_pt_track_switches(evlist); if (err == -EPERM) pr_debug2("Unable to select sched:sched_switch\n"); @@ -394,7 +650,6 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, /* 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) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index a32a64ef08e2..8edc205ff9a7 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -67,6 +67,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, rb_erase(&al->sym->rb_node, &al->map->dso->symbols[al->map->type]); symbol__delete(al->sym); + dso__reset_find_symbol_cache(al->map->dso); } return 0; } diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c index c61d14b101e0..c4b99008e2c9 100644 --- a/tools/perf/ui/tui/progress.c +++ b/tools/perf/ui/tui/progress.c @@ -33,9 +33,26 @@ static void tui_progress__update(struct ui_progress *p) pthread_mutex_unlock(&ui__lock); } +static void tui_progress__finish(void) +{ + int y; + + if (use_browser <= 0) + return; + + ui__refresh_dimensions(false); + pthread_mutex_lock(&ui__lock); + y = SLtt_Screen_Rows / 2 - 2; + SLsmg_set_color(0); + SLsmg_fill_region(y, 0, 3, SLtt_Screen_Cols, ' '); + SLsmg_refresh(); + pthread_mutex_unlock(&ui__lock); +} + static struct ui_progress_ops tui_progress__ops = { - .update = tui_progress__update, + .update = tui_progress__update, + .finish = tui_progress__finish, }; void tui_progress__init(void) diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index c73276db6d6f..fc8db9c764ac 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -324,6 +324,8 @@ struct dso *__dsos__findnew(struct dsos *dsos, const char *name); struct dso *dsos__findnew(struct dsos *dsos, const char *name); bool __dsos__read_build_ids(struct list_head *head, bool with_hits); +void dso__reset_find_symbol_cache(struct dso *dso); + size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm); size_t __dsos__fprintf(struct list_head *head, FILE *fp); diff --git a/tools/perf/util/intel-pt-decoder/inat.c b/tools/perf/util/intel-pt-decoder/inat.c index feeaa509dfe4..906d94aa0a24 100644 --- a/tools/perf/util/intel-pt-decoder/inat.c +++ b/tools/perf/util/intel-pt-decoder/inat.c @@ -18,7 +18,7 @@ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * */ -#include <asm/insn.h> +#include "insn.h" /* Attribute tables are generated from opcode map */ #include "inat-tables.c" diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h index 74a2e312e8a2..611645e903a8 100644 --- a/tools/perf/util/intel-pt-decoder/inat.h +++ b/tools/perf/util/intel-pt-decoder/inat.h @@ -20,7 +20,7 @@ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * */ -#include <asm/inat_types.h> +#include "inat_types.h" /* * Internal bits. Don't use bitmasks directly, because these bits are diff --git a/tools/perf/util/intel-pt-decoder/inat_types.h b/tools/perf/util/intel-pt-decoder/inat_types.h new file mode 100644 index 000000000000..cb3c20ce39cf --- /dev/null +++ b/tools/perf/util/intel-pt-decoder/inat_types.h @@ -0,0 +1,29 @@ +#ifndef _ASM_X86_INAT_TYPES_H +#define _ASM_X86_INAT_TYPES_H +/* + * x86 instruction attributes + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +/* Instruction attributes */ +typedef unsigned int insn_attr_t; +typedef unsigned char insn_byte_t; +typedef signed int insn_value_t; + +#endif diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c index 8f72b334aea0..47314a64399c 100644 --- a/tools/perf/util/intel-pt-decoder/insn.c +++ b/tools/perf/util/intel-pt-decoder/insn.c @@ -23,8 +23,8 @@ #else #include <string.h> #endif -#include <asm/inat.h> -#include <asm/insn.h> +#include "inat.h" +#include "insn.h" /* Verify next sizeof(t) bytes can be on the same instruction */ #define validate_next(t, insn, n) \ diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h index e7814b74caf8..dd12da0f4593 100644 --- a/tools/perf/util/intel-pt-decoder/insn.h +++ b/tools/perf/util/intel-pt-decoder/insn.h @@ -21,7 +21,7 @@ */ /* insn_attr_t is defined in inat.h */ -#include <asm/inat.h> +#include "inat.h" struct insn_field { union { 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 f8ac462fec1a..22ba50224319 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -85,7 +85,10 @@ struct intel_pt_decoder { const unsigned char *buf; size_t len; bool return_compression; + bool mtc_insn; bool pge; + bool have_tma; + bool have_cyc; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -94,20 +97,37 @@ struct intel_pt_decoder { uint64_t tsc_timestamp; uint64_t ref_timestamp; uint64_t ret_addr; + uint64_t ctc_timestamp; + uint64_t ctc_delta; + uint64_t cycle_cnt; + uint64_t cyc_ref_timestamp; + uint32_t last_mtc; + uint32_t tsc_ctc_ratio_n; + uint32_t tsc_ctc_ratio_d; + uint32_t tsc_ctc_mult; + uint32_t tsc_slip; + uint32_t ctc_rem_mask; + int mtc_shift; struct intel_pt_stack stack; enum intel_pt_pkt_state pkt_state; struct intel_pt_pkt packet; struct intel_pt_pkt tnt; int pkt_step; int pkt_len; + int last_packet_type; unsigned int cbr; unsigned int max_non_turbo_ratio; + double max_non_turbo_ratio_fp; + double cbr_cyc_to_tsc; + double calc_cyc_to_tsc; + bool have_calc_cyc_to_tsc; int exec_mode; unsigned int insn_bytes; uint64_t sign_bit; uint64_t sign_bits; uint64_t period; enum intel_pt_period_type period_type; + uint64_t tot_insn_cnt; uint64_t period_insn_cnt; uint64_t period_mask; uint64_t period_ticks; @ |