diff options
58 files changed, 3581 insertions, 863 deletions
diff --git a/tools/perf/Documentation/db-export.txt b/tools/perf/Documentation/db-export.txt new file mode 100644 index 000000000000..52ffccb02d55 --- /dev/null +++ b/tools/perf/Documentation/db-export.txt @@ -0,0 +1,41 @@ +Database Export +=============== + +perf tool's python scripting engine: + + tools/perf/util/scripting-engines/trace-event-python.c + +supports scripts: + + tools/perf/scripts/python/export-to-sqlite.py + tools/perf/scripts/python/export-to-postgresql.py + +which export data to a SQLite3 or PostgreSQL database. + +The export process provides records with unique sequential ids which allows the +data to be imported directly to a database and provides the relationships +between tables. + +Over time it is possible to continue to expand the export while maintaining +backward and forward compatibility, by following some simple rules: + +1. Because of the nature of SQL, existing tables and columns can continue to be +used so long as the names and meanings (and to some extent data types) remain +the same. + +2. New tables and columns can be added, without affecting existing SQL queries, +so long as the new names are unique. + +3. Scripts that use a database (e.g. exported-sql-viewer.py) can maintain +backward compatibility by testing for the presence of new tables and columns +before using them. e.g. function IsSelectable() in exported-sql-viewer.py + +4. The export scripts themselves maintain forward compatibility (i.e. an existing +script will continue to work with new versions of perf) by accepting a variable +number of arguments (e.g. def call_return_table(*x)) i.e. perf can pass more +arguments which old scripts will ignore. + +5. The scripting engine tests for the existence of script handler functions +before calling them. The scripting engine can also test for the support of new +or optional features by checking for the existence and value of script global +variables. diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index 60d99e5e7921..50c5b60101bd 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -103,6 +103,36 @@ The flags are "bcrosyiABEx" which stand for branch, call, return, conditional, system, asynchronous, interrupt, transaction abort, trace begin, trace end, and in transaction, respectively. +Another interesting field that is not printed by default is 'ipc' which can be +displayed as follows: + + perf script --itrace=be -F+ipc + +There are two ways that instructions-per-cycle (IPC) can be calculated depending +on the recording. + +If the 'cyc' config term (see config terms section below) was used, then IPC is +calculated using the cycle count from CYC packets, otherwise MTC packets are +used - refer to the 'mtc' config term. When MTC is used, however, the values +are less accurate because the timing is less accurate. + +Because Intel PT does not update the cycle count on every branch or instruction, +the values will often be zero. When there are values, they will be the number +of instructions and number of cycles since the last update, and thus represent +the average IPC since the last IPC for that event type. Note IPC for "branches" +events is calculated separately from IPC for "instructions" events. + +Also note that the IPC instruction count may or may not include the current +instruction. If the cycle count is associated with an asynchronous branch +(e.g. page fault or interrupt), then the instruction count does not include the +current instruction, otherwise it does. That is consistent with whether or not +that instruction has retired when the cycle count is updated. + +Another note, in the case of "branches" events, non-taken branches are not +presently sampled, so IPC values for them do not appear e.g. a CYC packet with a +TNT packet that starts with a non-taken branch. To see every possible IPC +value, "instructions" events can be used e.g. --itrace=i0ns + While it is possible to create scripts to analyze the data, an alternative approach is available to export the data to a sqlite or postgresql database. Refer to script export-to-sqlite.py or export-to-postgresql.py for more details, diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 462b3cde0675..e4aa268d2e38 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -564,9 +564,12 @@ llvm.*:: llvm.clang-bpf-cmd-template:: Cmdline template. Below lines show its default value. Environment variable is used to pass options. - "$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS $KERNEL_INC_OPTIONS \ - -Wno-unused-value -Wno-pointer-sign -working-directory \ - $WORKING_DIR -c $CLANG_SOURCE -target bpf -O2 -o -" + "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ + "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \ + "$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \ + "-Wno-unused-value -Wno-pointer-sign " \ + "-working-directory $WORKING_DIR " \ + "-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE" llvm.clang-opt:: Options passed to clang. diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index da7809b15cc9..facd91e4e945 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -142,12 +142,14 @@ OPTIONS perf diff --time 0%-10%,30%-40% It also supports analyzing samples within a given time window - <start>,<stop>. Times have the format seconds.microseconds. If 'start' - is not given (i.e., time string is ',x.y') then analysis starts at - the beginning of the file. If stop time is not given (i.e, time - string is 'x.y,') then analysis goes to the end of the file. Time string is - 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different - perf.data files. + <start>,<stop>. Times have the format seconds.nanoseconds. If 'start' + is not given (i.e. time string is ',x.y') then analysis starts at + the beginning of the file. If stop time is not given (i.e. time + string is 'x.y,') then analysis goes to the end of the file. + Multiple ranges can be separated by spaces, which requires the argument + to be quoted e.g. --time "1234.567,1234.789 1235," + Time string is'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps + for different perf.data files. For example, we get the timestamp information from 'perf script'. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index de269430720a..15e0fa87241b 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -490,6 +490,17 @@ Configure all used events to run in kernel space. --all-user:: Configure all used events to run in user space. +--kernel-callchains:: +Collect callchains only from kernel space. I.e. this option sets +perf_event_attr.exclude_callchain_user to 1. + +--user-callchains:: +Collect callchains only from user space. I.e. this option sets +perf_event_attr.exclude_callchain_kernel to 1. + +Don't use both --kernel-callchains and --user-callchains at the same time or no +callchains will be collected. + --timestamp-filename Append timestamp to output file name. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index f441baa794ce..8c4372819e11 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -412,12 +412,13 @@ OPTIONS --time:: Only analyze samples within given time window: <start>,<stop>. Times - have the format seconds.microseconds. If start is not given (i.e., time + have the format seconds.nanoseconds. If start is not given (i.e. time string is ',x.y') then analysis starts at the beginning of the file. If - stop time is not given (i.e, time string is 'x.y,') then analysis goes - to end of file. + stop time is not given (i.e. time string is 'x.y,') then analysis goes + to end of file. Multiple ranges can be separated by spaces, which + requires the argument to be quoted e.g. --time "1234.567,1234.789 1235," - Also support time percent with multiple time range. Time string is + Also support time percent with multiple time ranges. Time string is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index af8282782911..d4e2e18a5881 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -117,7 +117,7 @@ OPTIONS Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, - brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode. + brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -203,6 +203,9 @@ OPTIONS The synth field is used by synthesized events which may be created when Instruction Trace decoding. + The ipc (instructions per cycle) field is synthesized and may have a value when + Instruction Trace decoding. + Finally, a user may not set fields to none for all event types. i.e., -F "" is not allowed. @@ -358,12 +361,13 @@ include::itrace.txt[] --time:: Only analyze samples within given time window: <start>,<stop>. Times - have the format seconds.microseconds. If start is not given (i.e., time + have the format seconds.nanoseconds. If start is not given (i.e. time string is ',x.y') then analysis starts at the beginning of the file. If - stop time is not given (i.e, time string is 'x.y,') then analysis goes - to end of file. + stop time is not given (i.e. time string is 'x.y,') then analysis goes + to end of file. Multiple ranges can be separated by spaces, which + requires the argument to be quoted e.g. --time "1234.567,1234.789 1235," - Also support time percent with multipe time range. Time string is + Also support time percent with multiple time ranges. Time string is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 1e312c2672e4..930c51c01201 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -200,6 +200,13 @@ use --per-socket in addition to -a. (system-wide). The output includes the socket number and the number of online processors on that socket. This is useful to gauge the amount of aggregation. +--per-die:: +Aggregate counts per processor die for system-wide mode measurements. This +is a useful mode to detect imbalance between dies. To enable this mode, +use --per-die in addition to -a. (system-wide). The output includes the +die number and the number of online processors on that die. This is +useful to gauge the amount of aggregation. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements. This is a useful mode to detect imbalance between physical cores. To enable this mode, @@ -239,6 +246,9 @@ Input file name. --per-socket:: Aggregate counts per processor socket for system-wide mode measurements. +--per-die:: +Aggregate counts per processor die for system-wide mode measurements. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements. diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index 6967e9b02be5..5f54feb19977 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -151,25 +151,45 @@ struct { HEADER_CPU_TOPOLOGY = 13, -String lists defining the core and CPU threads topology. -The string lists are followed by a variable length array -which contains core_id and socket_id of each cpu. -The number of entries can be determined by the size of the -section minus the sizes of both string lists. - struct { + /* + * First revision of HEADER_CPU_TOPOLOGY + * + * See 'struct perf_header_string_list' definition earlier + * in this file. + */ + struct perf_header_string_list cores; /* Variable length */ struct perf_header_string_list threads; /* Variable length */ + + /* + * Second revision of HEADER_CPU_TOPOLOGY, older tools + * will not consider what comes next + */ + struct { uint32_t core_id; uint32_t socket_id; } cpus[nr]; /* Variable length records */ + /* 'nr' comes from previously processed HEADER_NRCPUS's nr_cpu_avail */ + + /* + * Third revision of HEADER_CPU_TOPOLOGY, older tools + * will not consider what comes next + */ + + struct perf_header_string_list dies; /* Variable length */ + uint32_t die_id[nr_cpus_avail]; /* from previously processed HEADER_NR_CPUS, VLA */ }; Example: - sibling cores : 0-3 + sibling sockets : 0-8 + sibling dies : 0-3 + sibling dies : 4-7 sibling threads : 0-1 sibling threads : 2-3 + sibling threads : 4-5 + sibling threads : 6-7 HEADER_NUMA_TOPOLOGY = 14, @@ -272,6 +292,69 @@ struct { Two uint64_t for the time of first sample and the time of last sample. + HEADER_SAMPLE_TOPOLOGY = 22, + +Physical memory map and its node assignments. + +The format of data in MEM_TOPOLOGY is as follows: + + 0 - version | for future changes + 8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes + 16 - count | number of nodes + +For each node we store map of physical indexes: + + 32 - node id | node index + 40 - size | size of bitmap + 48 - bitmap | bitmap of memory indexes that belongs to node + | /sys/devices/system/node/node<NODE>/memory<INDEX> + +The MEM_TOPOLOGY can be displayed with following command: + +$ perf report --header-only -I +... +# memory nodes (nr 1, block size 0x8000000): +# 0 [7G]: 0-23,32-69 + + HEADER_CLOCKID = 23, + +One uint64_t for the clockid frequency, specified, for instance, via 'perf +record -k' (see clock_gettime()), to enable timestamps derived metrics +conversion into wall clock time on the reporting stage. + + HEADER_DIR_FORMAT = 24, + +The data files layout is described by HEADER_DIR_FORMAT feature. Currently it +holds only version number (1): + + uint64_t version; + +The current version holds only version value (1) means that data files: + +- Follow the 'data.*' name format. + +- Contain raw events data in standard perf format as read from kernel (and need + to be sorted) + +Future versions are expected to describe different data files layout according +to special needs. + + HEADER_BPF_PROG_INFO = 25, + +struct bpf_prog_info_linear, which contains detailed information about +a BPF program, including type, id, tag, jited/xlated instructions, etc. + + HEADER_BPF_BTF = 26, + +Contains BPF Type Format (BTF). For more information about BTF, please +refer to Documentation/bpf/btf.rst. + +struct { + u32 id; + u32 data_size; + char data[]; +}; + HEADER_COMPRESSED = 27, struct { diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 85fbcd265351..51dd00f65709 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -413,6 +413,9 @@ ifdef CORESIGHT $(call feature_check,libopencsd) ifeq ($(feature-libopencsd), 1) CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS) + ifeq ($(feature-reallocarray), 0) + CFLAGS += -DCOMPAT_NEED_REALLOCARRAY + endif LDFLAGS += $(LIBOPENCSD_LDFLAGS) EXTLIBS += $(OPENCSDLIBS) $(call detected,CONFIG_LIBOPENCSD) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 911426721170..279c69caef91 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -31,12 +31,159 @@ 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_ |