diff options
Diffstat (limited to '')
365 files changed, 12812 insertions, 5928 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 8e0163b7ef01..20b8ab984d5f 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -37,6 +37,7 @@ trace/beauty/generated/ pmu-events/pmu-events.c pmu-events/jevents feature/ +libbpf/ fixdep libtraceevent-dynamic-list Documentation/doc.dep diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index 2d586fe5e4c5..c52755481e2f 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -20,6 +20,7 @@ L synthesize last branch entries on existing event records s skip initial number of events q quicker (less detailed) decoding + A approximate IPC Z prefer to ignore timestamps (so-called "timeless" decoding) The default is all events i.e. the same as --itrace=ibxwpe, @@ -61,5 +62,6 @@ debug messages will or will not be logged. Each flag must be preceded by either '+' or '-'. The flags are: a all perf events + o output to stdout If supported, the 'q' option may be repeated to increase the effect. diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index cd8ce6e8ec12..7e44b419d301 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -74,12 +74,15 @@ OPTIONS used when creating a uprobe for a process that resides in a different mount namespace from the perf(1) utility. ---debuginfod=URLs:: +--debuginfod[=URLs]:: Specify debuginfod URL to be used when retrieving perf.data binaries, it follows the same syntax as the DEBUGINFOD_URLS variable, like: buildid-cache.debuginfod=http://192.168.122.174:8002 + If the URLs is not specified, the value of DEBUGINFOD_URLS + system environment variable is used. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1] diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 3bb75c1f25e8..0420e71698ee 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -587,6 +587,15 @@ record.*:: Use 'n' control blocks in asynchronous (Posix AIO) trace writing mode ('n' default: 1, max: 4). + record.debuginfod:: + Specify debuginfod URL to be used when cacheing perf.data binaries, + it follows the same syntax as the DEBUGINFOD_URLS variable, like: + + http://192.168.122.174:8002 + + If the URLs is 'system', the value of DEBUGINFOD_URLS system environment + variable is used. + diff.*:: diff.order:: This option sets the number of columns to sort the result. diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt index 91108fe3ad5f..0570a1ccd344 100644 --- a/tools/perf/Documentation/perf-inject.txt +++ b/tools/perf/Documentation/perf-inject.txt @@ -45,6 +45,13 @@ OPTIONS tasks slept. sched_switch contains a callchain where a task slept and sched_stat contains a timeslice how long a task slept. +-k:: +--vmlinux=<file>:: + vmlinux pathname + +--ignore-vmlinux:: + Ignore vmlinux files. + --kallsyms=<file>:: kallsyms pathname diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index db465fa7ee91..cbb920f5d056 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -157,6 +157,17 @@ 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. +Even with the 'cyc' config term, it is possible to produce IPC information for +every change of timestamp, but at the expense of accuracy. That is selected by +specifying the itrace 'A' option. Due to the granularity of timestamps, the +actual number of cycles increases even though the cycles reported does not. +The number of instructions is known, but if IPC is reported, cycles can be too +low and so IPC is too high. Note that inaccuracy decreases as the period of +sampling increases i.e. if the number of cycles is too low by a small amount, +that becomes less significant if the number of cycles is large. It may also be +useful to use the 'A' option in conjunction with dlfilter-show-cycles.so to +provide higher granularity cycle information. + 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 @@ -873,6 +884,7 @@ The letters are: L synthesize last branch entries on existing event records s skip initial number of events q quicker (less detailed) decoding + A approximate IPC Z prefer to ignore timestamps (so-called "timeless" decoding) "Instructions" events look like they were recorded by "perf record -e @@ -941,6 +953,7 @@ by flags which affect what debug messages will or will not be logged. Each flag must be preceded by either '+' or '-'. The flags support by Intel PT are: -a Suppress logging of perf events +a Log all perf events + +o Output to stdout instead of "intel_pt.log" By default, logged perf events are filtered by any specified time ranges, but flag +a overrides that. @@ -1072,6 +1085,21 @@ The Z option is equivalent to having recorded a trace without TSC decoding a trace of a virtual machine. +dlfilter-show-cycles.so +~~~~~~~~~~~~~~~~~~~~~~~ + +Cycles can be displayed using dlfilter-show-cycles.so in which case the itrace A +option can be useful to provide higher granularity cycle information: + + perf script --itrace=A --call-trace --dlfilter dlfilter-show-cycles.so + +To see a list of dlfilters: + + perf script -v --list-dlfilters + +See also linkperf:perf-dlfilters[1] + + dump option ~~~~~~~~~~~ @@ -1144,7 +1172,12 @@ Recording is selected by using the aux-output config term e.g. perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname -Note that currently, software only supports redirecting at most one PEBS event. +Originally, software only supported redirecting at most one PEBS event because it +was not able to differentiate one event from another. To overcome that, more recent +kernels and perf tools add support for the PERF_RECORD_AUX_OUTPUT_HW_ID side-band event. +To check for the presence of that event in a PEBS-via-PT trace: + + perf script -D --no-itrace | grep PERF_RECORD_AUX_OUTPUT_HW_ID To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g. diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt index 85b8ac695c87..f378ac59353d 100644 --- a/tools/perf/Documentation/perf-kmem.txt +++ b/tools/perf/Documentation/perf-kmem.txt @@ -8,22 +8,25 @@ perf-kmem - Tool to trace/measure kernel memory properties SYNOPSIS -------- [verse] -'perf kmem' {record|stat} [<options>] +'perf kmem' [<options>] {record|stat} DESCRIPTION ----------- There are two variants of perf kmem: - 'perf kmem record <command>' to record the kmem events - of an arbitrary workload. + 'perf kmem [<options>] record [<perf-record-options>] <command>' to + record the kmem events of an arbitrary workload. Additional 'perf + record' options may be specified after record, such as '-o' to + change the output file name. - 'perf kmem stat' to report kernel memory statistics. + 'perf kmem [<options>] stat' to report kernel memory statistics. OPTIONS ------- -i <file>:: --input=<file>:: - Select the input file (default: perf.data unless stdin is a fifo) + For stat, select the input file (default: perf.data unless stdin is a + fifo) -f:: --force:: diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 4c7db1da8fcc..57384a97c04f 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -39,6 +39,10 @@ any extra expressions computed by perf stat. --deprecated:: Print deprecated events. By default the deprecated events are hidden. +--cputype:: +Print events applying cpu with this type for hybrid platform +(e.g. --cputype core or --cputype atom) + [[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- @@ -77,7 +81,11 @@ On AMD systems it is implemented using IBS (up to precise-level 2). The precise modifier works with event types 0x76 (cpu-cycles, CPU clocks not halted) and 0xC1 (micro-ops retired). Both events map to IBS execution sampling (IBS op) with the IBS Op Counter Control bit -(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s +(IbsOpCntCtl) set respectively (see the +Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS) +section of the [AMD Processor Programming Reference (PPR)] relevant to the +family, model and stepping of the processor being used). + Manual Volume 2: System Programming, 13.3 Instruction-Based Sampling). Examples to use IBS: @@ -90,10 +98,12 @@ RAW HARDWARE EVENT DESCRIPTOR Even when an event is not available in a symbolic form within perf right now, it can be encoded in a per processor specific way. -For instance For x86 CPUs NNN represents the raw register encoding with the +For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout -of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344, -Figure 13-7 Performance Event-Select Register (PerfEvtSeln)). +of IA32_PERFEVTSELx MSRs) or AMD's PERF_CTL MSRs (see the +Core Complex (CCX) -> Processor x86 Core -> MSR Registers section of the +[AMD Processor Programming Reference (PPR)] relevant to the family, model +and stepping of the processor being used). Note: Only the following bit fields can be set in x86 counter registers: event, umask, edge, inv, cmask. Esp. guest/host only and @@ -122,6 +132,38 @@ It's also possible to use pmu syntax: perf record -e cpu/r1a8/ ... perf record -e cpu/r0x1a8/ ... +Some processors, like those from AMD, support event codes and unit masks +larger than a byte. In such cases, the bits corresponding to the event +configuration parameters can be seen with: + + cat /sys/bus/event_source/devices/<pmu>/format/<config> + +Example: + +If the AMD docs for an EPYC 7713 processor describe an event as: + + Event Umask Event Mask + Num. Value Mnemonic Description + + 28FH 03H op_cache_hit_miss.op_cache_hit Counts Op Cache micro-tag + hit events. + +raw encoding of 0x0328F cannot be used since the upper nibble of the +EventSelect bits have to be specified via bits 32-35 as can be seen with: + + cat /sys/bus/event_source/devices/cpu/format/event + +raw encoding of 0x20000038F should be used instead: + + perf stat -e r20000038f -a sleep 1 + perf record -e r20000038f ... + +It's also possible to use pmu syntax: + + perf record -e r20000038f -a sleep 1 + perf record -e cpu/r20000038f/ ... + perf record -e cpu/r0x20000038f/ ... + You should refer to the processor specific documentation for getting these details. Some of them are referenced in the SEE ALSO section below. @@ -312,4 +354,4 @@ SEE ALSO linkperf:perf-stat[1], linkperf:perf-top[1], linkperf:perf-record[1], http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide], -http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming] +https://bugzilla.kernel.org/show_bug.cgi?id=206537[AMD Processor Programming Reference (PPR)] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index f1079ee7f2ec..9ccc75935bc5 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -30,8 +30,10 @@ OPTIONS - a symbolic event name (use 'perf list' to list all events) - - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + - a raw PMU event in the form of rN where N is a hexadecimal value + that represents the raw register encoding with the layout of the + event control registers as described by entries in + /sys/bus/event_sources/devices/cpu/format/*. - a symbolic or raw PMU event followed by an optional colon and a list of event modifiers, e.g., cpu-cycles:p. See the @@ -469,7 +471,7 @@ This option sets the time out limit. The default value is 500 ms. --switch-events:: Record context switch events i.e. events of type PERF_RECORD_SWITCH or -PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT or CoreSight) +PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE) switch events will be enabled automatically, which can be suppressed by by the option --no-switch-events. @@ -596,6 +598,22 @@ options. 'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj in config file is set to true. +--synth=TYPE:: +Collect and synthesize given type of events (comma separated). Note that +this option controls the synthesis from the /proc filesystem which represent +task status for pre-existing threads. + +Kernel (and some other) events are recorded regardless of the +choice in this option. For example, --synth=no would have MMAP events for +kernel and modules. + +Available types are: + 'task' - synthesize FORK and COMM events for each task + 'mmap' - synthesize MMAP events for each process (implies 'task') + 'cgroup' - synthesize CGROUP events for each cgroup + 'all' - synthesize all events (default) + 'no' - do not synthesize any of the above events + --tail-synthesize:: Instead of collecting non-sample events (for example, fork, comm, mmap) at the beginning of record, collect them during finalizing an output file. @@ -697,6 +715,15 @@ measurements: include::intel-hybrid.txt[] +--debuginfod[=URLs]:: + Specify debuginfod URL to be used when cacheing perf.data binaries, + it follows the same syntax as the DEBUGINFOD_URLS variable, like: + + http://192.168.122.174:8002 + + If the URLs is not specified, the value of DEBUGINFOD_URLS + system environment variable is used. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1] diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index c80515243560..b0070718784d 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -130,7 +130,7 @@ OPTIONS 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, ipc, data_page_size, code_page_size. + metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat. 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 diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 7e6fb7cbc0f4..c06c341e72b9 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -36,8 +36,10 @@ report:: - a symbolic event name (use 'perf list' to list all events) - - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + - a raw PMU event in the form of rN where N is a hexadecimal value + that represents the raw register encoding with the layout of the + event control registers as described by entries in + /sys/bus/event_sources/devices/cpu/format/*. - a symbolic or raw PMU event followed by an optional colon and a list of event modifiers, e.g., cpu-cycles:p. See the @@ -493,6 +495,10 @@ This option can be enabled in perf config by setting the variable $ perf config stat.no-csv-summary=true +--cputype:: +Only enable events on applying cpu with this type for hybrid platform +(e.g. core or atom)" + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 9898a32b8d9c..cac3dfbee7d8 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -38,9 +38,10 @@ Default is to monitor all CPUS. -e <event>:: --event=<event>:: Select the PMU event. Selection can be a symbolic event name - (use 'perf list' to list all events) or a raw PMU - event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + (use 'perf list' to list all events) or a raw PMU event in the form + of rN where N is a hexadecimal value that represents the raw register + encoding with the layout of the event control registers as described + by entries in /sys/bus/event_sources/devices/cpu/format/*. -E <entries>:: --entries=<entries>:: diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index e6ff8c898ada..f56d0e0fbff6 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -346,7 +346,7 @@ to special needs. HEADER_BPF_PROG_INFO = 25, -struct bpf_prog_info_linear, which contains detailed information about +struct perf_bpil, which contains detailed information about a BPF program, including type, id, tag, jited/xlated instructions, etc. HEADER_BPF_BTF = 26, diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index f05c4d48fd7e..f5d72f936a6b 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -17,7 +17,11 @@ tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h tools/lib/find_bit.c tools/lib/bitmap.c +tools/lib/list_sort.c tools/lib/str_error_r.c tools/lib/vsprintf.c tools/lib/zalloc.c scripts/bpf_doc.py +tools/bpf/bpftool +kernel/bpf/disasm.c +kernel/bpf/disasm.h diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 14e3e8d702a0..96ad944ca6a8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -17,6 +17,7 @@ detected = $(shell echo "$(1)=y" >> $(OUTPUT).config-detected) detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected) CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS)) +HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS)) include $(srctree)/tools/scripts/Makefile.arch @@ -143,7 +144,10 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++ +OPENCSDLIBS := -lopencsd_c_api +ifeq ($(findstring -static,${LDFLAGS}),-static) + OPENCSDLIBS += -lopencsd -lstdc++ +endif ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS) endif @@ -211,6 +215,7 @@ endif ifneq ($(WERROR),0) CORE_CFLAGS += -Werror CXXFLAGS += -Werror + HOSTCFLAGS += -Werror endif ifndef DEBUG @@ -271,8 +276,6 @@ endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) -FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) -FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt @@ -285,13 +288,16 @@ CORE_CFLAGS += -Wall CORE_CFLAGS += -Wextra CORE_CFLAGS += -std=gnu99 -CXXFLAGS += -std=gnu++11 -fno-exceptions -fno-rtti +CXXFLAGS += -std=gnu++14 -fno-exceptions -fno-rtti CXXFLAGS += -Wall CXXFLAGS += -fno-omit-frame-pointer CXXFLAGS += -ggdb3 CXXFLAGS += -funwind-tables CXXFLAGS += -Wno-strict-aliasing +HOSTCFLAGS += -Wall +HOSTCFLAGS += -Wextra + # Enforce a non-executable stack, as we may regress (again) in the future by # adding assembler files missing the .GNU-stack linker note. LDFLAGS += -Wl,-z,noexecstack @@ -1010,6 +1016,9 @@ ifndef NO_AUXTRACE ifndef NO_AUXTRACE $(call detected,CONFIG_AUXTRACE) CFLAGS += -DHAVE_AUXTRACE_SUPPORT + ifeq ($(feature-reallocarray), 0) + CFLAGS += -DCOMPAT_NEED_REALLOCARRAY + endif endif endif @@ -1093,11 +1102,32 @@ ifdef LIBTRACEEVENT_DYNAMIC $(call feature_check,libtraceevent) ifeq ($(feature-libtraceevent), 1) EXTLIBS += -ltraceevent + LIBTRACEEVENT_VERSION := $(shell $(PKG_CONFIG) --modversion libtraceevent) + LIBTRACEEVENT_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEEVENT_VERSION))) + LIBTRACEEVENT_VERSION_CPP := $(shell expr $(LIBTRACEEVENT_VERSION_1) \* 255 \* 255 + $(LIBTRACEEVENT_VERSION_2) \* 255 + $(LIBTRACEEVENT_VERSION_3)) + CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP) else dummy := $(error Error: No libtraceevent devel library found, please install libtraceevent-devel); endif endif +ifdef LIBTRACEFS_DYNAMIC + $(call feature_check,libtracefs) + ifeq ($(feature-libtracefs), 1) + EXTLIBS += -ltracefs + LIBTRACEFS_VERSION := $(shell $(PKG_CONFIG) --modversion libtracefs) + LIBTRACEFS_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEFS_VERSION))) + LIBTRACEFS_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEFS_VERSION))) + LIBTRACEFS_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEFS_VERSION))) + LIBTRACEFS_VERSION_CPP := $(shell expr $(LIBTRACEFS_VERSION_1) \* 255 \* 255 + $(LIBTRACEFS_VERSION_2) \* 255 + $(LIBTRACEFS_VERSION_3)) + CFLAGS += -DLIBTRACEFS_VERSION=$(LIBTRACEFS_VERSION_CPP) + else + dummy := $(error Error: No libtracefs devel library found, please install libtracefs-dev); + endif +endif + # Among the variables below, these: # perfexecdir # perf_include_dir diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index b856afa6eb52..ac861e42c8f7 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -130,6 +130,8 @@ include ../scripts/utilities.mak # # Define LIBTRACEEVENT_DYNAMIC to enable libtraceevent dynamic linking # +# Define LIBTRACEFS_DYNAMIC to enable libtracefs dynamic linking +# # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -224,7 +226,7 @@ else endif export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK -export HOSTCC HOSTLD HOSTAR +export HOSTCC HOSTLD HOSTAR HOSTCFLAGS include $(srctree)/tools/build/Makefile.include @@ -241,7 +243,7 @@ else # force_fixdep LIB_DIR = $(srctree)/tools/lib/api/ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ -BPF_DIR = $(srctree)/tools/lib/bpf/ +LIBBPF_DIR = $(srctree)/tools/lib/bpf/ SUBCMD_DIR = $(srctree)/tools/lib/subcmd/ LIBPERF_DIR = $(srctree)/tools/lib/perf/ DOC_DIR = $(srctree)/tools/perf/Documentation/ @@ -293,7 +295,6 @@ strip-libs = $(filter-out -l%,$(1)) ifneq ($(OUTPUT),) TE_PATH=$(OUTPUT) PLUGINS_PATH=$(OUTPUT) - BPF_PATH=$(OUTPUT) SUBCMD_PATH=$(OUTPUT) LIBPERF_PATH=$(OUTPUT) ifneq ($(subdir),) @@ -305,7 +306,6 @@ else TE_PATH=$(TRACE_EVENT_DIR) PLUGINS_PATH=$(TRACE_EVENT_DIR)plugins/ API_PATH=$(LIB_DIR) - BPF_PATH=$(BPF_DIR) SUBCMD_PATH=$(SUBCMD_DIR) LIBPERF_PATH=$(LIBPERF_DIR) endif @@ -324,7 +324,14 @@ LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = $(if $(findstring -static,$(LDFLAGS)),,$(DY LIBAPI = $(API_PATH)libapi.a export LIBAPI -LIBBPF = $(BPF_PATH)libbpf.a +ifneq ($(OUTPUT),) + LIBBPF_OUTPUT = $(abspath $(OUTPUT))/libbpf +else + LIBBPF_OUTPUT = $(CURDIR)/libbpf +endif +LIBBPF_DESTDIR = $(LIBBPF_OUTPUT) +LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include +LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a LIBSUBCMD = $(SUBCMD_PATH)libsubcmd.a @@ -360,7 +367,7 @@ ifndef NO_JVMTI PROGRAMS += $(OUTPUT)$(LIBJVMTI) endif -DLFILTERS := dlfilter-test-api-v0.so +DLFILTERS := dlfilter-test-api-v0.so dlfilter-show-cycles.so DLFILTERS := $(patsubst %,$(OUTPUT)dlfilters/%,$(DLFILTERS)) # what 'all' will build and 'install' will install, in perfexecdir @@ -509,17 +516,17 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl) $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@ -socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c -socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh +socket_arrays := $(beauty_outdir)/socket.c +socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh -$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl) - $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@ +$(socket_arrays): $(linux_uapi_dir)/in.h $(beauty_linux_dir)/socket.h $(socket_tbl) + $(Q)$(SHELL) '$(socket_tbl)' $(linux_uapi_dir) $(beauty_linux_dir) > $@ -socket_arrays := $(beauty_outdir)/socket_arrays.c -socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh +sockaddr_arrays := $(beauty_outdir)/sockaddr.c +sockaddr_tbl := $(srctree)/tools/perf/trace/beauty/sockaddr.sh -$(socket_arrays): $(beauty_linux_dir)/socket.h $(socket_tbl) - $(Q)$(SHELL) '$(socket_tbl)' $(beauty_linux_dir) > $@ +$(sockaddr_arrays): $(beauty_linux_dir)/socket.h $(sockaddr_tbl) + $(Q)$(SHELL) '$(sockaddr_tbl)' $(beauty_linux_dir) > $@ vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux @@ -729,8 +736,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(sndrv_ctl_ioctl_array) \ $(kcmp_type_array) \ $(kvm_ioctl_array) \ - $(socket_ipproto_array) \ $(socket_arrays) \ + $(sockaddr_arrays) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(mmap_flags_array) \ @@ -829,12 +836,14 @@ $(LIBAPI)-clean: $(call QUIET_CLEAN, libapi) $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null -$(LIBBPF): FORCE - $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) +$(LIBBPF): FORCE | $(LIBBPF_OUTPUT) + $(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \ + O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + $@ install_headers $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) - $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null + $(Q)$(RM) -r -- $(LIBBPF_OUTPUT) $(LIBPERF): FORCE $(Q)$(MAKE) -C $(LIBPERF_DIR) EXTRA_CFLAGS="$(LIBPERF_CFLAGS)" O=$(OUTPUT) $(OUTPUT)libperf.a @@ -1032,18 +1041,17 @@ SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel) SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp) SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h -SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h +SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h + +$(SKEL_TMP_OUT) $(LIBBPF_OUTPUT): + $(Q)$(MKDIR) -p $@ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -LIBBPF_SRC := $(abspath ../lib/bpf) -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(BPF_PATH) -I$(LIBBPF_SRC)/.. - -$(SKEL_TMP_OUT): - $(Q)$(MKDIR) -p $@ +BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(BPFTOOL): | $(SKEL_TMP_OUT) - CFLAGS= $(MAKE) -C ../bpf/bpftool \ + $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ @@ -1105,8 +1113,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(sndrv_pcm_ioctl_array) \ $(OUTPUT)$(kvm_ioctl_array) \ $(OUTPUT)$(kcmp_type_array) \ - $(OUTPUT)$(socket_ipproto_array) \ $(OUTPUT)$(socket_arrays) \ + $(OUTPUT)$(sockaddr_arrays) \ $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) \ $(OUTPUT)$(prctl_option_array) \ diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/arm/include/arch-tests.h +++ b/tools/perf/arch/arm/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index 4085419283d0..99a06550e25d 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -15,46 +15,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM_PC #define PERF_REG_SP PERF_REG_ARM_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_ARM_R0: - return "r0"; - case PERF_REG_ARM_R1: - return "r1"; - case PERF_REG_ARM_R2: - return "r2"; - case PERF_REG_ARM_R3: - return "r3"; - case PERF_REG_ARM_R4: - return "r4"; - case PERF_REG_ARM_R5: - return "r5"; - case PERF_REG_ARM_R6: - return "r6"; - case PERF_REG_ARM_R7: - return "r7"; - case PERF_REG_ARM_R8: - return "r8"; - case PERF_REG_ARM_R9: - return "r9"; - case PERF_REG_ARM_R10: - return "r10"; - case PERF_REG_ARM_FP: - return "fp"; - case PERF_REG_ARM_IP: - return "ip"; - case PERF_REG_ARM_SP: - return "sp"; - case PERF_REG_ARM_LR: - return "lr"; - case PERF_REG_ARM_PC: - return "pc"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c index 6848101a855f..69561111cc6f 100644 --- a/tools/perf/arch/arm/tests/arch-tests.c +++ b/tools/perf/arch/arm/tests/arch-tests.c @@ -3,18 +3,10 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .desc = "Vectors page", - .func = test__vectors_page, - }, - { - .func = NULL, - }, + &suite__vectors_page, + NULL, }; diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c index 7ffdd79971c8..55a835837466 100644 --- a/tools/perf/arch/arm/tests/vectors-page.c +++ b/tools/perf/arch/arm/tests/vectors-page.c @@ -9,8 +9,7 @@ #define VECTORS__MAP_NAME "[vectors]" -int test__vectors_page(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__vectors_page(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { void *start, *end; @@ -22,3 +21,5 @@ int test__vectors_page(struct test *test __maybe_unused, return TEST_OK; } + +DEFINE_SUITE("Vectors page", vectors_page); diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 293a23bf8be3..2e8b2c4365a0 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -203,9 +203,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr, struct perf_cpu_map *online_cpus = perf_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)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(event_cpus, cpu) || + !perf_cpu_map__has(online_cpus, cpu)) continue; if (option & BIT(ETM_OPT_CTXTID)) { @@ -407,25 +409,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } - /* Validate auxtrace_mmap_pages provided by user */ - if (opts->auxtrace_mmap_pages) { - unsigned int max_page = (KiB(128) / page_size); - size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; - - if (!privileged && - opts->auxtrace_mmap_pages > max_page) { - opts->auxtrace_mmap_pages = max_page; - pr_err("auxtrace too big, truncating to %d\n", - max_page); - } - - if (!is_power_of_2(sz)) { - pr_err("Invalid mmap size for %s: must be a power of 2\n", - CORESIGHT_ETM_PMU_NAME); - return -EINVAL; - } - } - if (opts->auxtrace_snapshot_mode) pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, opts->auxtrace_snapshot_size); @@ -541,9 +524,11 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, /* cpu map is not empty, we have specific CPUs to work with */ if (!perf_cpu_map__empty(event_cpus)) { - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(event_cpus, i) || - !cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(event_cpus, cpu) || + !perf_cpu_map__has(online_cpus, cpu)) continue; if (cs_etm_is_ete(itr, i)) @@ -555,8 +540,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, } } else { /* get configuration for all CPUs in the system */ - for (i = 0; i < cpu__max_cpu(); i++) { - if (!cpu_map__has(online_cpus, i)) + for (i = 0; i < cpu__max_cpu().cpu; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (!perf_cpu_map__has(online_cpus, cpu)) continue; if (cs_etm_is_ete(itr, i)) @@ -741,8 +728,10 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, } else { /* Make sure all specified CPUs are online */ for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) { - if (cpu_map__has(event_cpus, i) && - !cpu_map__has(online_cpus, i)) + struct perf_cpu cpu = { .cpu = i, }; + + if (perf_cpu_map__has(event_cpus, cpu) && + !perf_cpu_map__has(online_cpus, cpu)) return -EINVAL; } @@ -762,9 +751,12 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, offset = CS_ETM_SNAPSHOT + 1; - for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) - if (cpu_map__has(cpu_map, i)) + for (i = 0; i < cpu__max_cpu().cpu && offset < priv_size; i++) { + struct perf_cpu cpu = { .cpu = i, }; + + if (perf_cpu_map__has(cpu_map, cpu)) cs_etm_get_metadata(i, &offset, itr, info); + } perf_cpu_map__put(online_cpus); diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/arm64/include/arch-tests.h +++ b/tools/perf/arch/arm64/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h index fa3e07459f76..35a3cc775b39 100644 --- a/tools/perf/arch/arm64/include/perf_regs.h +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -4,7 +4,9 @@ #include <stdlib.h> #include <linux/types.h> +#define perf_event_arm_regs perf_event_arm64_regs #include <asm/perf_regs.h> +#undef perf_event_arm_regs void perf_regs_load(u64 *regs); @@ -15,80 +17,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM64_PC #define PERF_REG_SP PERF_REG_ARM64_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_ARM64_X0: - return "x0"; - case PERF_REG_ARM64_X1: - return "x1"; - case PERF_REG_ARM64_X2: - return "x2"; - case PERF_REG_ARM64_X3: - return "x3"; - case PERF_REG_ARM64_X4: - return "x4"; - case PERF_REG_ARM64_X5: - return "x5"; - case PERF_REG_ARM64_X6: - return "x6"; - case PERF_REG_ARM64_X7: - return "x7"; - case PERF_REG_ARM64_X8: - return "x8"; - case PERF_REG_ARM64_X9: - return "x9"; - case PERF_REG_ARM64_X10: - return "x10"; - case PERF_REG_ARM64_X11: - return "x11"; - case PERF_REG_ARM64_X12: - return "x12"; - case PERF_REG_ARM64_X13: - return "x13"; - case PERF_REG_ARM64_X14: - return "x14"; - case PERF_REG_ARM64_X15: - return "x15"; - case PERF_REG_ARM64_X16: - return "x16"; - case PERF_REG_ARM64_X17: - return "x17"; - case PERF_REG_ARM64_X18: - return "x18"; - case PERF_REG_ARM64_X19: - return "x19"; - case PERF_REG_ARM64_X20: - return "x20"; - case PERF_REG_ARM64_X21: - return "x21"; - case PERF_REG_ARM64_X22: - return "x22"; - case PERF_REG_ARM64_X23: - return "x23"; - case PERF_REG_ARM64_X24: - return "x24"; - case PERF_REG_ARM64_X25: - return "x25"; - case PERF_REG_ARM64_X26: - return "x26"; - case PERF_REG_ARM64_X27: - return "x27"; - case PERF_REG_ARM64_X28: - return "x28"; - case PERF_REG_ARM64_X29: - return "x29"; - case PERF_REG_ARM64_SP: - return "sp"; - case PERF_REG_ARM64_LR: - return "lr"; - case PERF_REG_ARM64_PC: - return "pc"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c index 5b1543c98022..ad16b4f8f63e 100644 --- a/tools/perf/arch/arm64/tests/arch-tests.c +++ b/tools/perf/arch/arm64/tests/arch-tests.c @@ -3,14 +3,9 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .func = NULL, - }, + NULL, }; diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index a4420d4df503..2100d46ccf5e 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -23,6 +23,7 @@ #include "../../../util/auxtrace.h" #include "../../../util/record.h" #include "../../../util/arm-spe.h" +#include <tools/libc_compat.h> // reallocarray #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -31,6 +32,8 @@ struct arm_spe_recording { struct auxtrace_record itr; struct perf_pmu *arm_spe_pmu; struct evlist *evlist; + int wrapped_cnt; + bool *wrapped; }; static void arm_spe_set_timestamp(struct auxtrace_record *itr, @@ -84,6 +87,55 @@ static int arm_spe_info_fill(struct auxtrace_record *itr, return 0; } +static void +arm_spe_snapshot_resolve_auxtrace_defaults(struct record_opts *opts, + bool privileged) +{ + /* + * The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size nor + * snapshot size is specified, then the default is 4MiB for privileged users, 128KiB for + * unprivileged users. + * + * The default auxtrace mmap size is 4MiB/page_size for privileged users, 128KiB for + * unprivileged users. If an unprivileged user does not specify mmap pages, the mmap pages + * will be reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the + * user is likely to get an error as they exceed their mlock limmit. + */ + + /* + * No size were given to '-S' or '-m,', so go with the default + */ + if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } else if (!opts->auxtrace_mmap_pages && !privileged && opts->mmap_pages == UINT_MAX) { + opts->mmap_pages = KiB(256) / page_size; + } + + /* + * '-m,xyz' was specified but no snapshot size, so make the snapshot size as big as the + * auxtrace mmap area. + */ + if (!opts->auxtrace_snapshot_size) + opts->auxtrace_snapshot_size = opts->auxtrace_mmap_pages * (size_t)page_size; + + /* + * '-Sxyz' was specified but no auxtrace mmap area, so make the auxtrace mmap area big + * enough to fit the requested snapshot size. + */ + if (!opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_snapshot_size; + + sz = round_up(sz, page_size) / page_size; + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } +} + static int arm_spe_recording_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) @@ -115,6 +167,36 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; + /* + * we are in snapshot mode. + */ + if (opts->auxtrace_snapshot_mode) { + /* + * Command arguments '-Sxyz' and/or '-m,xyz' are missing, so fill those in with + * default values. + */ + if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) + arm_spe_snapshot_resolve_auxtrace_defaults(opts, privileged); + + /* + * Snapshot size can't be bigger than the auxtrace area. + */ + if (opts->auxtrace_snapshot_size > opts->auxtrace_mmap_pages * (size_t)page_size) { + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", + opts->auxtrace_snapshot_size, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + + /* + * Something went wrong somewhere - this shouldn't happen. + */ + if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) { + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); + return -EINVAL; + } + } + /* We are in full trace mode but '-m,xyz' wasn't specified */ if (!opts->auxtrace_mmap_pages) { if (privileged) { @@ -138,6 +220,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, } } + if (opts->auxtrace_snapshot_mode) + pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, + opts->auxtrace_snapshot_size); /* * To obtain the auxtrace buffer file descriptor, the auxtrace event @@ -166,8 +251,199 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, tracking_evsel->core.attr.sample_period = 1; /* In per-cpu case, always need the time of mmap events etc */ - if (!perf_cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) { evsel__set_sample_bit(tracking_evsel, TIME); + evsel__set_sample_bit(tracking_evsel, CPU); + + /* also track task context switch */ + if (!record_opts__no_switch_events(opts)) + tracking_evsel->core.attr.context_switch = 1; + } + + return 0; +} + +static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, + struct record_opts *opts, + const char *str) +{ + unsigned long long snapshot_size = 0; + char *endptr; + + if (str) { + snapshot_size = strtoull(str, &endptr, 0); + if (*endptr || snapshot_size > SIZE_MAX) + return -1; + } + + opts->auxtrace_snapshot_mode = true; + opts->auxtrace_snapshot_size = snapshot_size; + + return 0; +} + +static int arm_spe_snapshot_start(struct auxtrace_record *itr) +{ + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->core.attr.type == ptr->arm_spe_pmu->type) + return evsel__disable(evsel); + } + return -EINVAL; +} + +static int arm_spe_snapshot_finish(struct auxtrace_record *itr) +{ + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->core.attr.type == ptr->arm_spe_pmu->type) + return evsel__enable(evsel); + } + return -EINVAL; +} + +static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx) +{ + bool *wrapped; + int cnt = ptr->wrapped_cnt, new_cnt, i; + + /* + * No need to allocate, so return early. + */ + if (idx < cnt) + return 0; + + /* + * Make ptr->wrapped as big as idx. + */ + new_cnt = idx + 1; + + /* + * Free'ed in arm_spe_recording_free(). + */ + wrapped = reallocarray(ptr->wrapped, new_cnt, sizeof(bool)); + if (!wrapped) + return -ENOMEM; + + /* + * init new allocated values. + */ + for (i = cnt; i < new_cnt; i++) + wrapped[i] = false; + + ptr->wrapped_cnt = new_cnt; + ptr->wrapped = wrapped; + + return 0; +} + +static bool arm_spe_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; + + /* + * Defensively handle the case where head might be continually increasing - if its value is + * equal or greater than the size of the ring buffer, then we can safely determine it has + * wrapped around. Otherwise, continue to detect if head might have wrapped. + */ + if (head >= buffer_size) + return true; + + /* + * We want to look the very last 512 byte (chosen arbitrarily) in the ring buffer. + */ + watermark = buf_size - 512; + + /* + * 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 /= sizeof(u64); + buf_size /= sizeof(u64); + + /* + * 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 arm_spe_find_snapshot(struct auxtrace_record *itr, int idx, + struct auxtrace_mmap *mm, unsigned char *data, + u64 *head, u64 *old) +{ + int err; + bool wrapped; + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_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 = arm_spe_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 && arm_spe_buffer_has_wrapped(data, mm->len, *head)) { + wrapped = true; + ptr->wrapped[idx] = true; + } + + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", + __func__, idx, (size_t)*old, (size_t)*head, mm->len); + + /* + * No wrap has occurred, we can just use *head and *old. + */ + if (!wrapped) + return 0; + + /* + * *head has wrapped around - adjust *head and *old to pickup the + * entire content of the AUX buffer. + */ + if (*head >= mm->len) { + *old = *head - mm->len; + } else { + *head += mm->len; + *old = *head - mm->len; + } return 0; } @@ -186,6 +462,7 @@ static void arm_spe_recording_free(struct auxtrace_record *itr) struct arm_spe_recording *sper = container_of(itr, struct arm_spe_recording, itr); + free(sper->wrapped); free(sper); } @@ -207,6 +484,10 @@ struct auxtrace_record *arm_spe_recording_init(int *err, sper->arm_spe_pmu = arm_spe_pmu; sper->itr.pmu = arm_spe_pmu; + sper->itr.snapshot_start = arm_spe_snapshot_start; + sper->itr.snapshot_finish = arm_spe_snapshot_finish; + sper->itr.find_snapshot = arm_spe_find_snapshot; + sper->itr.parse_snapshot_options = arm_spe_parse_snapshot_options; sper->itr.recording_options = arm_spe_recording_options; sper->itr.info_priv_size = arm_spe_info_priv_size; sper->itr.info_fill = arm_spe_info_fill; diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index 7e7714290a87..d2ce31e28cd7 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -5,6 +5,8 @@ #include <string.h> #include "debug.h" #include "symbol.h" +#include "callchain.h" +#include "record.h" /* On arm64, kernel text segment starts at high memory address, * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory @@ -26,3 +28,8 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) p->end = c->start; pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); } + +void arch__add_leaf_frame_record_opts(struct record_opts *opts) +{ + opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; +} diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index 2234fbd0a912..79124bba713e 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -3,7 +3,7 @@ #include "../../../util/cpumap.h" #include "../../../util/pmu.h" -struct pmu_events_map *pmu_events_map__find(void) +const struct pmu_events_map *pmu_events_map__find(void) { struct perf_pmu *pmu = NULL; @@ -15,7 +15,7 @@ struct pmu_events_map *pmu_events_map__find(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu()) + if (pmu->cpus->nr != cpu__max_cpu().cpu) return NULL; return perf_pmu__find_map(pmu); diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h index 25ac3bdcb9d1..1afcc0e916c2 100644 --- a/tools/perf/arch/csky/include/perf_regs.h +++ b/tools/perf/arch/csky/include/perf_regs.h @@ -15,86 +15,4 @@ #define PERF_REG_IP PERF_REG_CSKY_PC #define PERF_REG_SP PERF_REG_CSKY_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_CSKY_A0: - return "a0"; - case PERF_REG_CSKY_A1: - return "a1"; - case PERF_REG_CSKY_A2: - return "a2"; - case PERF_REG_CSKY_A3: - return "a3"; - case PERF_REG_CSKY_REGS0: - return "regs0"; - case PERF_REG_CSKY_REGS1: - return "regs1"; - case PERF_REG_CSKY_REGS2: - return "regs2"; - case PERF_REG_CSKY_REGS3: - return "regs3"; - case PERF_REG_CSKY_REGS4: - return "regs4"; - case PERF_REG_CSKY_REGS5: - return "regs5"; - case PERF_REG_CSKY_REGS6: - return "regs6"; - case PERF_REG_CSKY_REGS7: - return "regs7"; - case PERF_REG_CSKY_REGS8: - return "regs8"; - case PERF_REG_CSKY_REGS9: - return "regs9"; - case PERF_REG_CSKY_SP: - return "sp"; - case PERF_REG_CSKY_LR: - return "lr"; - case PERF_REG_CSKY_PC: - return "pc"; -#if defined(__CSKYABIV2__) - case PERF_REG_CSKY_EXREGS0: - return "exregs0"; - case PERF_REG_CSKY_EXREGS1: - return "exregs1"; - case PERF_REG_CSKY_EXREGS2: - return "exregs2"; - case PERF_REG_CSKY_EXREGS3: - return "exregs3"; - case PERF_REG_CSKY_EXREGS4: - return "exregs4"; - case PERF_REG_CSKY_EXREGS5: - return "exregs5"; - case PERF_REG_CSKY_EXREGS6: - return "exregs6"; - case PERF_REG_CSKY_EXREGS7: - return "exregs7"; - case PERF_REG_CSKY_EXREGS8: - return "exregs8"; - case PERF_REG_CSKY_EXREGS9: - return "exregs9"; - case PERF_REG_CSKY_EXREGS10: - return "exregs10"; - case PERF_REG_CSKY_EXREGS11: - return "exregs11"; - case PERF_REG_CSKY_EXREGS12: - return "exregs12"; - case PERF_REG_CSKY_EXREGS13: - return "exregs13"; - case PERF_REG_CSKY_EXREGS14: - return "exregs14"; - case PERF_REG_CSKY_TLS: - return "tls"; - case PERF_REG_CSKY_HI: - return "hi"; - case PERF_REG_CSKY_LO: - return "lo"; -#endif - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 1ca7bc337932..3f1886ad9d80 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -363,3 +363,5 @@ 446 n64 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease +449 n64 futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h index ee73b36a14d1..b8cd8bbb37ba 100644 --- a/tools/perf/arch/mips/include/perf_regs.h +++ b/tools/perf/arch/mips/include/perf_regs.h @@ -12,73 +12,4 @@ #define PERF_REGS_MASK ((1ULL << PERF_REG_MIPS_MAX) - 1) -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_MIPS_PC: - return "PC"; - case PERF_REG_MIPS_R1: - return "$1"; - case PERF_REG_MIPS_R2: - return "$2"; - case PERF_REG_MIPS_R3: - return "$3"; - case PERF_REG_MIPS_R4: - return "$4"; - case PERF_REG_MIPS_R5: - return "$5"; - case PERF_REG_MIPS_R6: - return "$6"; - case PERF_REG_MIPS_R7: - return "$7"; - case PERF_REG_MIPS_R8: - return "$8"; - case PERF_REG_MIPS_R9: - return "$9"; - case PERF_REG_MIPS_R10: - return "$10"; - case PERF_REG_MIPS_R11: - return "$11"; - case PERF_REG_MIPS_R12: - return "$12"; - case PERF_REG_MIPS_R13: - return "$13"; - case PERF_REG_MIPS_R14: - return "$14"; - case PERF_REG_MIPS_R15: - return "$15"; - case PERF_REG_MIPS_R16: - return "$16"; - case PERF_REG_MIPS_R17: - return "$17"; - case PERF_REG_MIPS_R18: - return "$18"; - case PERF_REG_MIPS_R19: - return "$19"; - case PERF_REG_MIPS_R20: - return "$20"; - case PERF_REG_MIPS_R21: - return "$21"; - case PERF_REG_MIPS_R22: - return "$22"; - case PERF_REG_MIPS_R23: - return "$23"; - case PERF_REG_MIPS_R24: - return "$24"; - case PERF_REG_MIPS_R25: - return "$25"; - case PERF_REG_MIPS_R28: - return "$28"; - case PERF_REG_MIPS_R29: - return "$29"; - case PERF_REG_MIPS_R30: - return "$30"; - case PERF_REG_MIPS_R31: - return "$31"; - default: - break; - } - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 7bef917cc84e..2600b4237292 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -528,3 +528,5 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/powerpc/include/arch-tests.h +++ b/tools/perf/arch/powerpc/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 04e5dc07e93f..9bb17c3f370b 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -19,68 +19,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_POWERPC_NIP #define PERF_REG_SP PERF_REG_POWERPC_R1 -static const char *reg_names[] = { - [PERF_REG_POWERPC_R0] = "r0", - [PERF_REG_POWERPC_R1] = "r1", - [PERF_REG_POWERPC_R2] = "r2", - [PERF_REG_POWERPC_R3] = "r3", - [PERF_REG_POWERPC_R4] = "r4", - [PERF_REG_POWERPC_R5] = "r5", - [PERF_REG_POWERPC_R6] = "r6", - [PERF_REG_POWERPC_R7] = "r7", - [PERF_REG_POWERPC_R8] = "r8", - [PERF_REG_POWERPC_R9] = "r9", - [PERF_REG_POWERPC_R10] = "r10", - [PERF_REG_POWERPC_R11] = "r11", - [PERF_REG_POWERPC_R12] = "r12", - [PERF_REG_POWERPC_R13] = "r13", - [PERF_REG_POWERPC_R14] = "r14", - [PERF_REG_POWERPC_R15] = "r15", - [PERF_REG_POWERPC_R16] = "r16", - [PERF_REG_POWERPC_R17] = "r17", - [PERF_REG_POWERPC_R18] = "r18", - [PERF_REG_POWERPC_R19] = "r19", - [PERF_REG_POWERPC_R20] = "r20", - [PERF_REG_POWERPC_R21] = "r21", - [PERF_REG_POWERPC_R22] = "r22", - [PERF_REG_POWERPC_R23] = "r23", - [PERF_REG_POWERPC_R24] = "r24", - [PERF_REG_POWERPC_R25] = "r25", - [PERF_REG_POWERPC_R26] = "r26", - [PERF_REG_POWERPC_R27] = "r27", - [PERF_REG_POWERPC_R28] = "r28", - [PERF_REG_POWERPC_R29] = "r29", - [PERF_REG_POWERPC_R30] = "r30", - [PERF_REG_POWERPC_R31] = "r31", - [PERF_REG_POWERPC_NIP] = "nip", - [PERF_REG_POWERPC_MSR] = "msr", - [PERF_REG_POWERPC_ORIG_R3] = "orig_r3", - [PERF_REG_POWERPC_CTR] = "ctr", - [PERF_REG_POWERPC_LINK] = "link", - [PERF_REG_POWERPC_XER] = "xer", - [PERF_REG_POWERPC_CCR] = "ccr", - [PERF_REG_POWERPC_SOFTE] = "softe", - [PERF_REG_POWERPC_TRAP] = "trap", - [PERF_REG_POWERPC_DAR] = "dar", - [PERF_REG_POWERPC_DSISR] = "dsisr", - [PERF_REG_POWERPC_SIER] = "sier", - [PERF_REG_POWERPC_MMCRA] = "mmcra", - [PERF_REG_POWERPC_MMCR0] = "mmcr0", - [PERF_REG_POWERPC_MMCR1] = "mmcr1", - [PERF_REG_POWERPC_MMCR2] = "mmcr2", - [PERF_REG_POWERPC_MMCR3] = "mmcr3", - [PERF_REG_POWERPC_SIER2] = "sier2", - [PERF_REG_POWERPC_SIER3] = "sier3", - [PERF_REG_POWERPC_PMC1] = "pmc1", - [PERF_REG_POWERPC_PMC2] = "pmc2", - [PERF_REG_POWERPC_PMC3] = "pmc3", - [PERF_REG_POWERPC_PMC4] = "pmc4", - [PERF_REG_POWERPC_PMC5] = "pmc5", - [PERF_REG_POWERPC_PMC6] = "pmc6", -}; - -static inline const char *__perf_reg_name(int id) -{ - return reg_names[id]; -} #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c index 8c3fbd4af817..eb98c57b5aeb 100644 --- a/tools/perf/arch/powerpc/tests/arch-tests.c +++ b/tools/perf/arch/powerpc/tests/arch-tests.c @@ -3,14 +3,10 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { + +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "Test dwarf unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .func = NULL, - }, + NULL, }; diff --git a/tools/perf/arch/powerpc/util/event.c b/tools/perf/arch/powerpc/util/event.c index 3bf441257466..cf430a4c55b9 100644 --- a/tools/perf/arch/powerpc/util/event.c +++ b/tools/perf/arch/powerpc/util/event.c @@ -40,8 +40,12 @@ const char *arch_perf_header_entry(const char *se_header) { if (!strcmp(se_header, "Local INSTR Latency")) return "Finish Cyc"; - else if (!strcmp(se_header, "Pipeline Stage Cycle")) + else if (!strcmp(se_header, "INSTR Latency")) + return "Global Finish_cyc"; + else if (!strcmp(se_header, "Local Pipeline Stage Cycle")) return "Dispatch Cyc"; + else if (!strcmp(se_header, "Pipeline Stage Cycle")) + return "Global Dispatch_cyc"; return se_header; } @@ -49,5 +53,7 @@ int arch_support_sort_key(const char *sort_key) { if (!strcmp(sort_key, "p_stage_cyc")) return 1; + if (!strcmp(sort_key, "local_p_stage_cyc")) + return 1; return 0; } diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 58b2d610aadb..e8fe36b10d20 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -40,7 +40,7 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused) return bufp; } -int arch_get_runtimeparam(struct pmu_event *pe) +int arch_get_runtimeparam(const struct pmu_event *pe) { int count; char path[PATH_MAX] = "/devices/hv_24x7/interface/"; diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index 16510686c138..1a9b40ea92a5 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -113,10 +113,11 @@ static int is_tracepoint_available(const char *str, struct evlist *evlist) struct parse_events_error err; int ret; - bzero(&err, sizeof(err)); + parse_events_error__init(&err); ret = parse_events(evlist, str, &err); if (err.str) - parse_events_print_error(&err, "tracepoint"); + parse_events_error__print(&err, "tracepoint"); + parse_events_error__exit(&err); return ret; } diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index 8116a253f91f..8d07a78e742a 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -74,6 +74,8 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(pmc4, PERF_REG_POWERPC_PMC4), SMPL_REG(pmc5, PERF_REG_POWERPC_PMC5), SMPL_REG(pmc6, PERF_REG_POWERPC_PMC6), + SMPL_REG(sdar, PERF_REG_POWERPC_SDAR), + SMPL_REG(siar, PERF_REG_POWERPC_SIAR), SMPL_REG_END }; diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h index 6b02a767c918..6944bf0de53e 100644 --- a/tools/perf/arch/riscv/include/perf_regs.h +++ b/tools/perf/arch/riscv/include/perf_regs.h @@ -19,78 +19,4 @@ #define PERF_REG_IP PERF_REG_RISCV_PC #define PERF_REG_SP PERF_REG_RISCV_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_RISCV_PC: - return "pc"; - case PERF_REG_RISCV_RA: - return "ra"; - case PERF_REG_RISCV_SP: - return "sp"; - case PERF_REG_RISCV_GP: - return "gp"; - case PERF_REG_RISCV_TP: - return "tp"; - case PERF_REG_RISCV_T0: - return "t0"; - case PERF_REG_RISCV_T1: - return "t1"; - case PERF_REG_RISCV_T2: - return "t2"; - case PERF_REG_RISCV_S0: - return "s0"; - case PERF_REG_RISCV_S1: - return "s1"; - case PERF_REG_RISCV_A0: - return "a0"; - case PERF_REG_RISCV_A1: - return "a1"; - case PERF_REG_RISCV_A2: - return "a2"; - case PERF_REG_RISCV_A3: - return "a3"; - case PERF_REG_RISCV_A4: - return "a4"; - case PERF_REG_RISCV_A5: - return "a5"; - case PERF_REG_RISCV_A6: - return "a6"; - case PERF_REG_RISCV_A7: - return "a7"; - case PERF_REG_RISCV_S2: - return "s2"; - case PERF_REG_RISCV_S3: - return "s3"; - case PERF_REG_RISCV_S4: - return "s4"; - case PERF_REG_RISCV_S5: - return "s5"; - case PERF_REG_RISCV_S6: - return "s6"; - case PERF_REG_RISCV_S7: - return "s7"; - case PERF_REG_RISCV_S8: - return "s8"; - case PERF_REG_RISCV_S9: - return "s9"; - case PERF_REG_RISCV_S10: - return "s10"; - case PERF_REG_RISCV_S11: - return "s11"; - case PERF_REG_RISCV_T3: - return "t3"; - case PERF_REG_RISCV_T4: - return "t4"; - case PERF_REG_RISCV_T5: - return "t5"; - case PERF_REG_RISCV_T6: - return "t6"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/riscv64/annotate/instructions.c b/tools/perf/arch/riscv64/annotate/instructions.c new file mode 100644 index 000000000000..869a0eb28953 --- /dev/null +++ b/tools/perf/arch/riscv64/annotate/instructions.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +static +struct ins_ops *riscv64__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "jal", 3) || + !strncmp(name, "jr", 2) || + !strncmp(name, "call", 4)) + ops = &call_ops; + else if (!strncmp(name, "ret", 3)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int riscv64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = riscv64__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index df5261e5cfe1..799147658dee 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -451,3 +451,5 @@ 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index ce3031526623..52fcc0891da6 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -14,82 +14,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_S390_PC #define PERF_REG_SP PERF_REG_S390_R15 -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_S390_R0: - return "R0"; - case PERF_REG_S390_R1: - return "R1"; - case PERF_REG_S390_R2: - return "R2"; - case PERF_REG_S390_R3: - return "R3"; - case PERF_REG_S390_R4: - return "R4"; - case PERF_REG_S390_R5: - return "R5"; - case PERF_REG_S390_R6: - return "R6"; - case PERF_REG_S390_R7: - return "R7"; - case PERF_REG_S390_R8: - return "R8"; - case PERF_REG_S390_R9: - return "R9"; - case PERF_REG_S390_R10: - return "R10"; - case PERF_REG_S390_R11: - return "R11"; - case PERF_REG_S390_R12: - return "R12"; - case PERF_REG_S390_R13: - return "R13"; - case PERF_REG_S390_R14: - return "R14"; - case PERF_REG_S390_R15: - return "R15"; - case PERF_REG_S390_FP0: - return "FP0"; - case PERF_REG_S390_FP1: - return "FP1"; - case PERF_REG_S390_FP2: - return "FP2"; - case PERF_REG_S390_FP3: - return "FP3"; - case PERF_REG_S390_FP4: - return "FP4"; - case PERF_REG_S390_FP5: - return "FP5"; - case PERF_REG_S390_FP6: - return "FP6"; - case PERF_REG_S390_FP7: - return "FP7"; - case PERF_REG_S390_FP8: - return "FP8"; - case PERF_REG_S390_FP9: - return "FP9"; - case PERF_REG_S390_FP10: - return "FP10"; - case PERF_REG_S390_FP11: - return "FP11"; - case PERF_REG_S390_FP12: - return "FP12"; - case PERF_REG_S390_FP13: - return "FP13"; - case PERF_REG_S390_FP14: - return "FP14"; - case PERF_REG_S390_FP15: - return "FP15"; - case PERF_REG_S390_MASK: - return "MASK"; - case PERF_REG_S390_PC: - return "PC"; - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 24ea12ec7e02..305872692bfd 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -144,9 +144,32 @@ static struct ins x86__instructions[] = { { .name = "xorps", .ops = &mov_ops, }, }; -static bool x86__ins_is_fused(struct arch *arch, const char *ins1, +static bool amd__ins_is_fused(struct arch *arch, const char *ins1, const char *ins2) { + if (strstr(ins2, "jmp")) + return false; + + /* Family >= 15h supports cmp/test + branch fusion */ + if (arch->family >= 0x15 && (strstarts(ins1, "test") || + (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) { + return true; + } + + /* Family >= 19h supports some ALU + branch fusion */ + if (arch->family >= 0x19 && (strstarts(ins1, "add") || + strstarts(ins1, "sub") || strstarts(ins1, "and") || + strstarts(ins1, "inc") || strstarts(ins1, "dec") || + strstarts(ins1, "or") || strstarts(ins1, "xor"))) { + return true; + } + + return false; +} + +static bool intel__ins_is_fused(struct arch *arch, const char *ins1, + const char *ins2) +{ if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp")) return false; @@ -184,6 +207,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid) if (ret == 3) { arch->family = family; arch->model = model; + arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ? + amd__ins_is_fused : + intel__ins_is_fused; return 0; } diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 18b5500ea8bf..c84d12608cd2 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -370,6 +370,8 @@ 446 common landlock_restrict_self sys_landlock_restrict_self 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 9599e7a3f1af..6a1a1b3c0827 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -2,15 +2,15 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -struct test; +struct test_suite; /* Tests */ -int test__rdpmc(struct test *test, int subtest); -int test__insn_x86(struct test *test, int subtest); -int test__intel_pt_pkt_decoder(struct test *test, int subtest); -int test__bp_modify(struct test *test, int subtest); -int test__x86_sample_parsing(struct test *test, int subtest); +int test__rdpmc(struct test_suite *test, int subtest); +int test__insn_x86(struct test_suite *test, int subtest); +int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); +int test__bp_modify(struct test_suite *test, int subtest); +int test__x86_sample_parsing(struct test_suite *test, int subtest); -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index cddc4cdc0d9b..16e23b722042 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -23,86 +23,4 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_X86_IP #define PERF_REG_SP PERF_REG_X86_SP -static inline const char *__perf_reg_name(int id) -{ - switch (id) { - case PERF_REG_X86_AX: - return "AX"; - case PERF_REG_X86_BX: - return "BX"; - case PERF_REG_X86_CX: - return "CX"; - case PERF_REG_X86_DX: - return "DX"; - case PERF_REG_X86_SI: - return "SI"; - case PERF_REG_X86_DI: - return "DI"; - case PERF_REG_X86_BP: - return "BP"; - case PERF_REG_X86_SP: - return "SP"; - case PERF_REG_X86_IP: - return "IP"; - case PERF_REG_X86_FLAGS: - return "FLAGS"; - case PERF_REG_X86_CS: - return "CS"; - case PERF_REG_X86_SS: - return "SS"; - case PERF_REG_X86_DS: - return "DS"; - case PERF_REG_X86_ES: - return "ES"; - case PERF_REG_X86_FS: - return "FS"; - case PERF_REG_X86_GS: - return "GS"; -#ifdef HAVE_ARCH_X86_64_SUPPORT - case PERF_REG_X86_R8: - return "R8"; - case PERF_REG_X86_R9: - return "R9"; - case PERF_REG_X86_R10: - return "R10"; - case PERF_REG_X86_R11: - return "R11"; - case PERF_REG_X86_R12: - return "R12"; - case PERF_REG_X86_R13: - return "R13"; - case PERF_REG_X86_R14: - return "R14"; - case PERF_REG_X86_R15: - return "R15"; -#endif /* HAVE_ARCH_X86_64_SUPPORT */ - -#define XMM(x) \ - case PERF_REG_X86_XMM ## x: \ - case PERF_REG_X86_XMM ## x + 1: \ - return "XMM" #x; - XMM(0) - XMM(1) - XMM(2) - XMM(3) - XMM(4) - XMM(5) - XMM(6) - XMM(7) - XMM(8) - XMM(9) - XMM(10) - XMM(11) - XMM(12) - XMM(13) - XMM(14) - XMM(15) -#undef XMM - default: - return NULL; - } - - return NULL; -} - #endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index 71aa67367ad6..64fb73d14d2f 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -3,39 +3,28 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { - { - .desc = "x86 rdpmc", - .func = test__rdpmc, - }, +DEFINE_SUITE("x86 rdpmc", rdpmc); +#ifdef HAVE_AUXTRACE_SUPPORT +DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86); +DEFINE_SUITE("Intel PT packet decoder", intel_pt_pkt_decoder); +#endif +#if defined(__x86_64__) +DEFINE_SUITE("x86 bp modify", bp_modify); +#endif +DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); + +struct test_suite *arch_tests[] = { + &suite__rdpmc, #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif #ifdef HAVE_AUXTRACE_SUPPORT - { - .desc = "x86 instruction decoder - new instructions", - .func = test__insn_x86, - }, - { - .desc = "Intel PT packet decoder", - .func = test__intel_pt_pkt_decoder, - }, + &suite__insn_x86, + &suite__intel_pt_pkt_decoder, #endif #if defined(__x86_64__) - { - .desc = "x86 bp modify", - .func = test__bp_modify, - }, + &suite__bp_modify, #endif - { - .desc = "x86 Sample parsing", - .func = test__x86_sample_parsing, - }, - { - .func = NULL, - }, - + &suite__x86_sample_parsing, + NULL, }; diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c index dffcf9b52153..0924ccd9e36d 100644 --- a/tools/perf/arch/x86/tests/bp-modify.c +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -204,7 +204,7 @@ out: return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; } -int test__bp_modify(struct test *test __maybe_unused, +int test__bp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index 0262b0d8ccf5..94b490c434d0 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -173,7 +173,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64) * verbose (-v) option to see all the instructions and whether or not they * decoded successfully. */ -int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__insn_x86(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = 0; diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 27dd8cf9e060..cb5b2c6c3b3b 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -37,7 +37,7 @@ static pid_t spawn(void) * the last read counter value to avoid triggering a WARN_ON_ONCE() in * smp_call_function_many() caused by sending IPIs from NMI context. */ -int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__intel_cqm_count_nmi_context(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct evlist *evlist = NULL; struct evsel *evsel = NULL; 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 index c933e3dcd0a8..2fc882ab24c1 100644 --- a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c +++ b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c @@ -289,7 +289,7 @@ static int test_one(struct test_data *d) * 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) +int test__intel_pt_pkt_decoder(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct test_data *d = data; int ret; diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index 1ea916656a2d..498413ad9c97 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -157,7 +157,7 @@ out_close: return 0; } -int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__rdpmc(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int status = 0; int wret = 0; diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c index c92db87e4479..bfbd3662b69e 100644 --- a/tools/perf/arch/x86/tests/sample-parsing.c +++ b/tools/perf/arch/x86/tests/sample-parsing.c @@ -115,7 +115,7 @@ out_free: * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type. * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type. */ -int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__x86_sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return do_test(PERF_SAMPLE_WEIGHT_STRUCT); } diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index 0b0951030a2f..f924246eff78 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -17,3 +17,20 @@ int arch_evlist__add_default_attrs(struct evlist *evlist) else return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL); } + +struct evsel *arch_evlist__leader(struct list_head *list) +{ + struct evsel *evsel, *first; + + first = list_first_entry(list, struct evsel, core.node); + + if (!pmu_have_event("cpu", "slots")) + return first; + + __evlist__for_each_entry(list, evsel) { + if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && + evsel->name && strstr(evsel->name, "slots")) + return evsel; + } + return first; +} diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c index 2f733cdc8dbb..ac2899a25b7a 100644 --- a/tools/perf/arch/x86/util/evsel.c +++ b/tools/perf/arch/x86/util/evsel.c @@ -1,8 +1,31 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> +#include <stdlib.h> #include "util/evsel.h" +#include "util/env.h" +#include "linux/string.h" void arch_evsel__set_sample_weight(struct evsel *evsel) { evsel__set_sample_bit(evsel, WEIGHT_STRUCT); } + +void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr) +{ + struct perf_env env = { .total_mem = 0, } ; + + if (!perf_env__cpuid(&env)) + return; + + /* + * On AMD, precise cycles event sampling internally uses IBS pmu. + * But IBS does not have filtering capabilities and perf by default + * sets exclude_guest = 1. This makes IBS pmu event init fail and + * thus perf ends up doing non-precise sampling. Avoid it by clearing + * exclude_guest. + */ + if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD")) + attr->exclude_guest = 0; + + free(env.cpuid); +} diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index ddaca75c3bc0..740ae764537e 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -253,7 +253,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); if (ret) @@ -333,7 +333,7 @@ int bench_epoll_ctl(int argc, const char **argv) /* default to the number of CPUs */ if (!nthreads) - nthreads = cpu->nr; + nthreads = perf_cpu_map__nr(cpu); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 79d13dbc0a47..37de970c9743 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -342,7 +342,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); if (ret) @@ -452,7 +452,7 @@ int bench_epoll_wait(int argc, const char **argv) /* default to the number of CPUs and leave one for the writer pthread */ if (!nthreads) - nthreads = cpu->nr - 1; + nthreads = perf_cpu_map__nr(cpu) - 1; worker = calloc(nthreads, sizeof(*worker)); if (!worker) { diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c index 83e9897c64a1..de56601f69ee 100644 --- a/tools/perf/bench/evlist-open-close.c +++ b/tools/perf/bench/evlist-open-close.c @@ -25,6 +25,11 @@ static int iterations = 100; static int nr_events = 1; static const char *event_string = "dummy"; +static inline u64 timeval2usec(struct timeval *tv) +{ + return tv->tv_sec * USEC_PER_SEC + tv->tv_usec; +} + static struct record_opts opts = { .sample_time = true, .mmap_pages = UINT_MAX, @@ -66,14 +71,14 @@ static int evlist__count_evsel_fds(struct evlist *evlist) int cnt = 0; evlist__for_each_entry(evlist, evsel) - cnt += evsel->core.threads->nr * evsel->core.cpus->nr; + cnt += evsel->core.threads->nr * perf_cpu_map__nr(evsel->core.cpus); return cnt; } static struct evlist *bench__create_evlist(char *evstr) { - struct parse_events_error err = { .idx = 0, }; + struct parse_events_error err; struct evlist *evlist = evlist__new(); int ret; @@ -82,14 +87,16 @@ static struct evlist *bench__create_evlist(char *evstr) return NULL; } + parse_events_error__init(&err); ret = parse_events(evlist, evstr, &err); if (ret) { - parse_events_print_error(&err, evstr); + parse_events_error__print(&err, evstr); + parse_events_error__exit(&err); pr_err("Run 'perf list' for a list of valid events\n"); ret = 1; goto out_delete_evlist; } - + parse_events_error__exit(&err); ret = evlist__create_maps(evlist, &opts.target); if (ret < 0) { pr_err("Not enough memory to create thread/cpu maps\n"); @@ -144,7 +151,7 @@ static int bench_evlist_open_close__run(char *evstr) init_stats(&time_stats); - printf(" Number of cpus:\t%d\n", evlist->core.cpus->nr); + printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.cpus)); printf(" Number of threads:\t%d\n", evlist->core.threads->nr); printf(" Number of events:\t%d (%d fds)\n", evlist->core.nr_entries, evlist__count_evsel_fds(evlist)); @@ -167,7 +174,7 @@ static int bench_evlist_open_close__run(char *evstr) gettimeofday(&end, NULL); timersub(&end, &start, &diff); - runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + runtime_us = timeval2usec(&diff); update_stats(&time_stats, runtime_us); evlist__delete(evlist); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index fcdea3e44937..dbcecec4eeda 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -150,7 +150,7 @@ int bench_futex_hash(int argc, const char **argv) } if (!params.nthreads) /* default to the number of CPUs */ - params.nthreads = cpu->nr; + params.nthreads = perf_cpu_map__nr(cpu); worker = calloc(params.nthreads, sizeof(*worker)); if (!worker) @@ -177,7 +177,7 @@ int bench_futex_hash(int argc, const char **argv) goto errmem; CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); if (ret) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 5d1fe9c35807..6fc9a3d55c1f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -136,7 +136,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, worker[i].futex = &global_futex; CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); @@ -173,7 +173,7 @@ int bench_futex_lock_pi(int argc, const char **argv) } if (!params.nthreads) - params.nthreads = cpu->nr; + params.nthreads = perf_cpu_map__nr(cpu); worker = calloc(params.nthreads, sizeof(*worker)); if (!worker) @@ -233,6 +233,7 @@ int bench_futex_lock_pi(int argc, const char **argv) print_summary(); free(worker); + perf_cpu_map__put(cpu); return ret; err: usage_with_options(bench_futex_lock_pi_usage, options); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 97fe31fd3a23..2f59d5d1c509 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -131,7 +131,7 @@ static void block_threads(pthread_t *w, /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); @@ -175,7 +175,7 @@ int bench_futex_requeue(int argc, const char **argv) } if (!params.nthreads) - params.nthreads = cpu->nr; + params.nthreads = perf_cpu_map__nr(cpu); worker = calloc(params.nthreads, sizeof(*worker)); if (!worker) @@ -294,6 +294,7 @@ int bench_futex_requeue(int argc, const char **argv) print_summary(); free(worker); + perf_cpu_map__put(cpu); return ret; err: usage_with_options(bench_futex_requeue_usage, options); diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index e970e6b9ad53..861deb934745 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -152,7 +152,7 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr, /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); @@ -252,7 +252,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) err(EXIT_FAILURE, "calloc"); if (!params.nthreads) - params.nthreads = cpu->nr; + params.nthreads = perf_cpu_map__nr(cpu); /* some sanity checks */ if (params.nwakes > params.nthreads || @@ -329,6 +329,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) print_summary(); free(blocked_worker); + perf_cpu_map__put(cpu); return ret; } #endif /* HAVE_PTHREAD_BARRIER */ diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 77f058a47790..cfda48bef1d7 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -105,7 +105,7 @@ static void block_threads(pthread_t *w, /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); @@ -151,7 +151,7 @@ int bench_futex_wake(int argc, const char **argv) } if (!params.nthreads) - params.nthreads = cpu->nr; + params.nthreads = perf_cpu_map__nr(cpu); worker = calloc(params.nthreads, sizeof(*worker)); if (!worker) @@ -222,5 +222,6 @@ int bench_futex_wake(int argc, const char **argv) print_summary(); free(worker); + perf_cpu_map__put(cpu); return ret; } diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index b3853aac3021..ebdc2b032afc 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -28,7 +28,7 @@ struct bench_futex_parameters { }; /** - * futex() - SYS_futex syscall wrapper + * futex_syscall() - SYS_futex syscall wrapper * @uaddr: address of first futex * @op: futex op code * @val: typically expected value of uaddr, but varies by op @@ -38,17 +38,26 @@ struct bench_futex_parameters { * @val3: varies by op * @opflags: flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG * - * futex() is used by all the following futex op wrappers. It can also be + * futex_syscall() is used by all the following futex op wrappers. It can also be * used for misuse and abuse testing. Generally, the specific op wrappers - * should be used instead. It is a macro instead of an static inline function as - * some of the types over overloaded (timeout is used for nr_requeue for - * example). + * should be used instead. * * These argument descriptions are the defaults for all * like-named arguments in the following wrappers except where noted below. */ -#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \ - syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3) +static inline int +futex_syscall(volatile u_int32_t *uaddr, int op, u_int32_t val, struct timespec *timeout, + volatile u_int32_t *uaddr2, int val3, int opflags) +{ + return syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3); +} + +static inline int +futex_syscall_nr_requeue(volatile u_int32_t *uaddr, int op, u_int32_t val, int nr_requeue, + volatile u_int32_t *uaddr2, int val3, int opflags) +{ + return syscall(SYS_futex, uaddr, op | opflags, val, nr_requeue, uaddr2, val3); +} /** * futex_wait() - block on uaddr with optional timeout @@ -57,7 +66,7 @@ struct bench_futex_parameters { static inline int futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflags) { - return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags); } /** @@ -67,7 +76,7 @@ futex_wait(u_int32_t *uaddr, u_int32_t val, struct timespec *timeout, int opflag static inline int futex_wake(u_int32_t *uaddr, int nr_wake, int opflags) { - return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags); } /** @@ -76,7 +85,7 @@ futex_wake(u_int32_t *uaddr, int nr_wake, int opflags) static inline int futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int opflags) { - return futex(uaddr, FUTEX_LOCK_PI, 0, timeout, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_LOCK_PI, 0, timeout, NULL, 0, opflags); } /** @@ -85,7 +94,7 @@ futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int opflags) static inline int futex_unlock_pi(u_int32_t *uaddr, int opflags) { - return futex(uaddr, FUTEX_UNLOCK_PI, 0, NULL, NULL, 0, opflags); + return futex_syscall(uaddr, FUTEX_UNLOCK_PI, 0, NULL, NULL, 0, opflags); } /** @@ -97,8 +106,8 @@ static inline int futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake, int nr_requeue, int opflags) { - return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2, - val, opflags); + return futex_syscall_nr_requeue(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2, + val, opflags); } /** @@ -113,8 +122,8 @@ static inline int futex_wait_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, struct timespec *timeout, int opflags) { - return futex(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0, - opflags); + return futex_syscall(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0, + opflags); } /** @@ -130,8 +139,8 @@ static inline int futex_cmp_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_requeue, int opflags) { - return futex(uaddr, FUTEX_CMP_REQUEUE_PI, 1, nr_requeue, uaddr2, - val, opflags); + return futex_syscall_nr_requeue(uaddr, FUTEX_CMP_REQUEUE_PI, 1, nr_requeue, uaddr2, + val, opflags); } #endif /* _FUTEX_H */ diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 05f7c923c745..7401ebbac100 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -80,7 +80,7 @@ static int do_run_single_threaded(struct perf_session *session, NULL, target, threads, process_synthesized_event, - data_mmap, + true, data_mmap, nr_threads_synthesize); if (err) return err; @@ -171,7 +171,7 @@ static int do_run_multi_threaded(struct target *target, NULL, target, NULL, process_synthesized_event, - false, + true, false, nr_threads_synthesize); if (err) { perf_session__delete(session); diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 05eb098cb0e3..490bb9b8cf17 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -591,6 +591,10 @@ int cmd_annotate(int argc, const char **argv) return ret; } + ret = symbol__validate_sym_arguments(); + if (ret) + return ret; + if (quiet) perf_quiet_option(); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index d0895162c2ba..d291f3a8af5f 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -226,7 +226,6 @@ static void run_collection(struct collection *coll) if (!bench->fn) break; printf("# Running %s/%s benchmark...\n", coll->name, bench->name); - fflush(stdout); argv[1] = bench->name; run_bench(coll->name, bench->name, bench->fn, 1, argv); @@ -247,6 +246,9 @@ int cmd_bench(int argc, const char **argv) struct collection *coll; int ret = 0; + /* Unbuffered output */ + setvbuf(stdout, NULL, _IONBF, 0); + if (argc < 2) { /* No collection specified. */ print_usage(); @@ -300,7 +302,6 @@ int cmd_bench(int argc, const char **argv) if (bench_format == BENCH_FORMAT_DEFAULT) printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name); - fflush(stdout); ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1); goto end; } diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 0db3cfc04c47..cd381693658b 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -351,10 +351,14 @@ static int build_id_cache__show_all(void) static int perf_buildid_cache_config(const char *var, const char *value, void *cb) { - const char **debuginfod = cb; + struct perf_debuginfod *di = cb; - if (!strcmp(var, "buildid-cache.debuginfod")) - *debuginfod = strdup(value); + if (!strcmp(var, "buildid-cache.debuginfod")) { + di->urls = strdup(value); + if (!di->urls) + return -ENOMEM; + di->set = true; + } return 0; } @@ -373,8 +377,8 @@ int cmd_buildid_cache(int argc, const char **argv) *purge_name_list_str = NULL, *missing_filename = NULL, *update_name_list_str = NULL, - *kcore_filename = NULL, - *debuginfod = NULL; + *kcore_filename = NULL; + struct perf_debuginfod debuginfod = { }; char sbuf[STRERR_BUFSIZE]; struct perf_data data = { @@ -399,8 +403,10 @@ int cmd_buildid_cache(int argc, const char **argv) OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), OPT_STRING('u', "update", &update_name_list_str, "file list", "file(s) to update"), - OPT_STRING(0, "debuginfod", &debuginfod, "debuginfod url", - "set debuginfod url"), + OPT_STRING_OPTARG_SET(0, "debuginfod", &debuginfod.urls, + &debuginfod.set, "debuginfod urls", + "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls", + "system"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"), OPT_END() @@ -425,10 +431,7 @@ int cmd_buildid_cache(int argc, const char **argv) if (argc || !(list_files || opts_flag)) usage_with_options(buildid_cache_usage, buildid_cache_options); - if (debuginfod) { - pr_debug("DEBUGINFOD_URLS=%s\n", debuginfod); - setenv("DEBUGINFOD_URLS", debuginfod, 1); - } + perf_debuginfod_setup(&debuginfod); /* -l is exclusive. It can not be used with other options. */ if (list_files && opts_flag) { diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index a192014fa52b..77dd4afacca4 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2015,7 +2015,8 @@ static int setup_nodes(struct perf_session *session) { struct numa_node *n; unsigned long **nodes; - int node, cpu; + int node, idx; + struct perf_cpu cpu; int *cpu2node; if (c2c.node_info > 2) @@ -2038,8 +2039,8 @@ static int setup_nodes(struct perf_session *session) if (!cpu2node) return -ENOMEM; - for (cpu = 0; cpu < c2c.cpus_cnt; cpu++) - cpu2node[cpu] = -1; + for (idx = 0; idx < c2c.cpus_cnt; idx++) + cpu2node[idx] = -1; c2c.cpu2node = cpu2node; @@ -2057,13 +2058,13 @@ static int setup_nodes(struct perf_session *session) if (perf_cpu_map__empty(map)) continue; - for (cpu = 0; cpu < map->nr; cpu++) { - set_bit(map->map[cpu], set); + perf_cpu_map__for_each_cpu(cpu, idx, map) { + set_bit(cpu.cpu, set); - if (WARN_ONCE(cpu2node[map->map[cpu]] != -1, "node/cpu topology bug")) + if (WARN_ONCE(cpu2node[cpu.cpu] != -1, "node/cpu topology bug")) return -EINVAL; - cpu2node[map->map[cpu]] = node; + cpu2node[cpu.cpu] = node; } } @@ -2768,6 +2769,10 @@ static int perf_c2c__report(int argc, const char **argv) if (c2c.stats_only) c2c.use_stdio = true; + err = symbol__validate_sym_arguments(); + if (err) + goto out; + if (!input_name || !strlen(input_name)) input_name = "perf.data"; diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index 61929f63a047..6cb3f6cc36d0 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1121,8 +1121,6 @@ static int setup_config(struct daemon *daemon) #ifndef F_TLOCK #define F_TLOCK 2 -#include <sys/file.h> - static int lockf(int fd, int cmd, off_t len) { if (cmd != F_TLOCK || len != 0) @@ -1403,8 +1401,10 @@ out: static int send_cmd_list(struct daemon *daemon) { - union cmd cmd = { .cmd = CMD_LIST, }; + union cmd cmd; + memset(&cmd, 0, sizeof(cmd)); + cmd.list.cmd = CMD_LIST; cmd.list.verbose = verbose; cmd.list.csv_sep = daemon->csv_sep ? *daemon->csv_sep : 0; @@ -1432,6 +1432,7 @@ static int __cmd_signal(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); cmd.signal.cmd = CMD_SIGNAL, cmd.signal.sig = SIGUSR2; strncpy(cmd.signal.name, name, sizeof(cmd.signal.name) - 1); @@ -1446,7 +1447,7 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[], OPT_PARENT(parent_options), OPT_END() }; - union cmd cmd = { .cmd = CMD_STOP, }; + union cmd cmd; argc = parse_options(argc, argv, start_options, daemon_usage, 0); if (argc) @@ -1457,6 +1458,8 @@ static int __cmd_stop(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = CMD_STOP; return send_cmd(daemon, &cmd); } @@ -1470,7 +1473,7 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[], OPT_PARENT(parent_options), OPT_END() }; - union cmd cmd = { .cmd = CMD_PING, }; + union cmd cmd; argc = parse_options(argc, argv, ping_options, daemon_usage, 0); if (argc) @@ -1481,6 +1484,8 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[], return -1; } + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = CMD_PING; scnprintf(cmd.ping.name, sizeof(cmd.ping.name), "%s", name); return send_cmd(daemon, &cmd); } diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 87cb11a7a3ee..a8785dec5ca6 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -13,7 +13,9 @@ #include <signal.h> #include <stdlib.h> #include <fcntl.h> +#include <math.h> #include <poll.h> +#include <ctype.h> #include <linux/capability.h> #include <linux/string.h> @@ -28,36 +30,12 @@ #include "strfilter.h" #include "util/cap.h" #include "util/config.h" +#include "util/ftrace.h" #include "util/units.h" #include "util/parse-sublevel-options.h" #define DEFAULT_TRACER "function_graph" -struct perf_ftrace { - struct evlist *evlist; - struct target target; - const char *tracer; - struct list_head filters; - struct list_head notrace; - struct list_head graph_funcs; - struct list_head nograph_funcs; - int graph_depth; - unsigned long percpu_buffer_size; - bool inherit; - int func_stack_trace; - int func_irq_info; - int graph_nosleep_time; - int graph_noirqs; - int graph_verbose; - int graph_thresh; - unsigned int initial_delay; -}; - -struct filter_entry { - struct list_head list; - char name[]; -}; - static volatile int workload_exec_errno; static bool done; @@ -303,7 +281,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap) int ret; int last_cpu; - last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); + last_cpu = perf_cpu_map__cpu(cpumap, perf_cpu_map__nr(cpumap) - 1).cpu; mask_size = last_cpu / 4 + 2; /* one more byte for EOS */ mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ @@ -565,7 +543,24 @@ static int set_tracing_options(struct perf_ftrace *ftrace) return 0; } -static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) +static void select_tracer(struct perf_ftrace *ftrace) +{ + bool graph = !list_empty(&ftrace->graph_funcs) || + !list_empty(&ftrace->nograph_funcs); + bool func = !list_empty(&ftrace->filters) || + !list_empty(&ftrace->notrace); + + /* The function_graph has priority over function tracer. */ + if (graph) + ftrace->tracer = "function_graph"; + else if (func) + ftrace->tracer = "function"; + /* Otherwise, the default tracer is used. */ + + pr_debug("%s tracer is used\n", ftrace->tracer); +} + +static int __cmd_ftrace(struct perf_ftrace *ftrace) { char *trace_file; int trace_fd; @@ -586,10 +581,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) return -1; } - signal(SIGINT, sig_handler); - signal(SIGUSR1, sig_handler); - signal(SIGCHLD, sig_handler); - signal(SIGPIPE, sig_handler); + select_tracer(ftrace); if (reset_tracing_files(ftrace) < 0) { pr_err("failed to reset ftrace\n"); @@ -600,11 +592,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) if (write_tracing_file("trace", "0") < 0) goto out; - if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false, - ftrace__workload_exec_failed_signal) < 0) { - goto out; - } - if (set_tracing_options(ftrace) < 0) goto out_reset; @@ -693,6 +680,270 @@ out: return (done && !workload_exec_errno) ? 0 : -1; } +static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf) +{ + char *p, *q; + char *unit; + double num; + int i; + + /* ensure NUL termination */ + buf[len] = '\0'; + + /* handle data line by line */ + for (p = buf; (q = strchr(p, '\n')) != NULL; p = q + 1) { + *q = '\0'; + /* move it to the line buffer */ + strcat(linebuf, p); + + /* + * parse trace output to get function duration like in + * + * # tracer: function_graph + * # + * # CPU DURATION FUNCTION CALLS + * # | | | | | | | + * 1) + 10.291 us | do_filp_open(); + * 1) 4.889 us | do_filp_open(); + * 1) 6.086 us | do_filp_open(); + * + */ + if (linebuf[0] == '#') + goto next; + + /* ignore CPU */ + p = strchr(linebuf, ')'); + if (p == NULL) + p = linebuf; + + while (*p && !isdigit(*p) && (*p != '|')) + p++; + + /* no duration */ + if (*p == '\0' || *p == '|') + goto next; + + num = strtod(p, &unit); + if (!unit || strncmp(unit, " us", 3)) + goto next; + + i = log2(num); + if (i < 0) + i = 0; + if (i >= NUM_BUCKET) + i = NUM_BUCKET - 1; + + buckets[i]++; + +next: + /* empty the line buffer for the next output */ + linebuf[0] = '\0'; + } + + /* preserve any remaining output (before newline) */ + strcat(linebuf, p); +} + +static void display_histogram(int buckets[]) +{ + int i; + int total = 0; + int bar_total = 46; /* to fit in 80 column */ + char bar[] = "###############################################"; + int bar_len; + + for (i = 0; i < NUM_BUCKET; i++) + total += buckets[i]; + + if (total == 0) { + printf("No data found\n"); + return; + } + + printf("# %14s | %10s | %-*s |\n", + " DURATION ", "COUNT", bar_total, "GRAPH"); + + bar_len = buckets[0] * bar_total / total; + printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", + 0, 1, "us", buckets[0], bar_len, bar, bar_total - bar_len, ""); + + for (i = 1; i < NUM_BUCKET - 1; i++) { + int start = (1 << (i - 1)); + int stop = 1 << i; + const char *unit = "us"; + + if (start >= 1024) { + start >>= 10; + stop >>= 10; + unit = "ms"; + } + bar_len = buckets[i] * bar_total / total; + printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", + start, stop, unit, buckets[i], bar_len, bar, + bar_total - bar_len, ""); + } + + bar_len = buckets[NUM_BUCKET - 1] * bar_total / total; + printf(" %4d - %-4s %s | %10d | %.*s%*s |\n", + 1, "...", " s", buckets[NUM_BUCKET - 1], bar_len, bar, + bar_total - bar_len, ""); + +} + +static int prepare_func_latency(struct perf_ftrace *ftrace) +{ + char *trace_file; + int fd; + + if (ftrace->target.use_bpf) + return perf_ftrace__latency_prepare_bpf(ftrace); + + if (reset_tracing_files(ftrace) < 0) { + pr_err("failed to reset ftrace\n"); + return -1; + } + + /* reset ftrace buffer */ + if (write_tracing_file("trace", "0") < 0) + return -1; + + if (set_tracing_options(ftrace) < 0) + return -1; + + /* force to use the function_graph tracer to track duration */ + if (write_tracing_file("current_tracer", "function_graph") < 0) { + pr_err("failed to set current_tracer to function_graph\n"); + return -1; + } + + trace_file = get_tracing_file("trace_pipe"); + if (!trace_file) { + pr_err("failed to open trace_pipe\n"); + return -1; + } + + fd = open(trace_file, O_RDONLY); + if (fd < 0) + pr_err("failed to open trace_pipe\n"); + + put_tracing_file(trace_file); + return fd; +} + +static int start_func_latency(struct perf_ftrace *ftrace) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_start_bpf(ftrace); + + if (write_tracing_file("tracing_on", "1") < 0) { + pr_err("can't enable tracing\n"); + return -1; + } + + return 0; +} + +static int stop_func_latency(struct perf_ftrace *ftrace) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_stop_bpf(ftrace); + + write_tracing_file("tracing_on", "0"); + return 0; +} + +static int read_func_latency(struct perf_ftrace *ftrace, int buckets[]) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_read_bpf(ftrace, buckets); + + return 0; +} + +static int cleanup_func_latency(struct perf_ftrace *ftrace) +{ + if (ftrace->target.use_bpf) + return perf_ftrace__latency_cleanup_bpf(ftrace); + + reset_tracing_files(ftrace); + return 0; +} + +static int __cmd_latency(struct perf_ftrace *ftrace) +{ + int trace_fd; + char buf[4096]; + char line[256]; + struct pollfd pollfd = { + .events = POLLIN, + }; + int buckets[NUM_BUCKET] = { }; + + if (!(perf_cap__capable(CAP_PERFMON) || + perf_cap__capable(CAP_SYS_ADMIN))) { + pr_err("ftrace only works for %s!\n", +#ifdef HAVE_LIBCAP_SUPPORT + "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" +#else + "root" +#endif + ); + return -1; + } + + trace_fd = prepare_func_latency(ftrace); + if (trace_fd < 0) + goto out; + + fcntl(trace_fd, F_SETFL, O_NONBLOCK); + pollfd.fd = trace_fd; + + if (start_func_latency(ftrace) < 0) + goto out; + + evlist__start_workload(ftrace->evlist); + + line[0] = '\0'; + while (!done) { + if (poll(&pollfd, 1, -1) < 0) + break; + + if (pollfd.revents & POLLIN) { + int n = read(trace_fd, buf, sizeof(buf) - 1); + if (n < 0) + break; + + make_histogram(buckets, buf, n, line); + } + } + + stop_func_latency(ftrace); + + if (workload_exec_errno) { + const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf)); + pr_err("workload failed: %s\n", emsg); + goto out; + } + + /* read remaining buffer contents */ + while (!ftrace->target.use_bpf) { + int n = read(trace_fd, buf, sizeof(buf) - 1); + if (n <= 0) + break; + make_histogram(buckets, buf, n, line); + } + + read_func_latency(ftrace, buckets); + + display_histogram(buckets); + +out: + close(trace_fd); + cleanup_func_latency(ftrace); + + return (done && !workload_exec_errno) ? 0 : -1; +} + static int perf_ftrace_config(const char *var, const char *value, void *cb) { struct perf_ftrace *ftrace = cb; @@ -855,41 +1106,21 @@ static int parse_graph_tracer_opts(const struct option *opt, return 0; } -static void select_tracer(struct perf_ftrace *ftrace) -{ - bool graph = !list_empty(&ftrace->graph_funcs) || - !list_empty(&ftrace->nograph_funcs); - bool func = !list_empty(&ftrace->filters) || - !list_empty(&ftrace->notrace); - - /* The function_graph has priority over function tracer. */ - if (graph) - ftrace->tracer = "function_graph"; - else if (func) - ftrace->tracer = "function"; - /* Otherwise, the default tracer is used. */ - - pr_debug("%s tracer is used\n", ftrace->tracer); -} +enum perf_ftrace_subcommand { + PERF_FTRACE_NONE, + PERF_FTRACE_TRACE, + PERF_FTRACE_LATENCY, +}; int cmd_ftrace(int argc, const char **argv) { int ret; + int (*cmd_func)(struct perf_ftrace *) = NULL; struct perf_ftrace ftrace = { .tracer = DEFAULT_TRACER, .target = { .uid = UINT_MAX, }, }; - const char * const ftrace_usage[] = { - "perf ftrace [<options>] [<command>]", - "perf ftrace [<options>] -- <command> [<options>]", - NULL - }; - const struct option ftrace_options[] = { - OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", - "Tracer to use: function_graph(default) or function"), - OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]", - "Show available functions to filter", - opt_list_avail_functions, "*"), + const struct option common_options[] = { OPT_STRING('p', "pid", &ftrace.target.pid, "pid", "Trace on existing process id"), /* TODO: Add short option -t after -t/--tracer can be removed. */ @@ -901,6 +1132,14 @@ int cmd_ftrace(int argc, const char **argv) "System-wide collection from all CPUs"), OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu", "List of cpus to monitor"), + OPT_END() + }; + const struct option ftrace_options[] = { + OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", + "Tracer to use: function_graph(default) or function"), + OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]", + "Show available functions to filter", + opt_list_avail_functions, "*"), OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", "Trace given functions using function tracer", parse_filter_func), @@ -923,24 +1162,87 @@ int cmd_ftrace(int argc, const char **argv) "Trace children processes"), OPT_UINTEGER('D', "delay", &ftrace.initial_delay, "Number of milliseconds to wait before starting tracing after program start"), - OPT_END() + OPT_PARENT(common_options), + }; + const struct option latency_options[] = { + OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", + "Show latency of given function", parse_filter_func), +#ifdef HAVE_BPF_SKEL + OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf, + "Use BPF to measure function latency"), +#endif + OPT_PARENT(common_options), + }; + const struct option *options = ftrace_options; + + const char * const ftrace_usage[] = { + "perf ftrace [<options>] [<command>]", + "perf ftrace [<options>] -- [<command>] [<options>]", + "perf ftrace {trace|latency} [<options>] [<command>]", + "perf ftrace {trace|latency} [<options>] -- [<command>] [<options>]", + NULL }; + enum perf_ftrace_subcommand subcmd = PERF_FTRACE_NONE; INIT_LIST_HEAD(&ftrace.filters); INIT_LIST_HEAD(&ftrace.notrace); INIT_LIST_HEAD(&ftrace.graph_funcs); INIT_LIST_HEAD(&ftrace.nograph_funcs); + signal(SIGINT, sig_handler); + signal(SIGUSR1, sig_handler); + signal(SIGCHLD, sig_handler); + signal(SIGPIPE, sig_handler); + ret = perf_config(perf_ftrace_config, &ftrace); if (ret < 0) return -1; - argc = parse_options(argc, argv, ftrace_options, ftrace_usage, + if (argc > 1) { + if (!strcmp(argv[1], "trace")) { + subcmd = PERF_FTRACE_TRACE; + } else if (!strcmp(argv[1], "latency")) { + subcmd = PERF_FTRACE_LATENCY; + options = latency_options; + } + + if (subcmd != PERF_FTRACE_NONE) { + argc--; + argv++; + } + } + /* for backward compatibility */ + if (subcmd == PERF_FTRACE_NONE) + subcmd = PERF_FTRACE_TRACE; + + argc = parse_options(argc, argv, options, ftrace_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && target__none(&ftrace.target)) - ftrace.target.system_wide = true; + if (argc < 0) { + ret = -EINVAL; + goto out_delete_filters; + } - select_tracer(&ftrace); + switch (subcmd) { + case PERF_FTRACE_TRACE: + if (!argc && target__none(&ftrace.target)) + ftrace.target.system_wide = true; + cmd_func = __cmd_ftrace; + break; + case PERF_FTRACE_LATENCY: + if (list_empty(&ftrace.filters)) { + pr_err("Should provide a function to measure\n"); + parse_options_usage(ftrace_usage, options, "T", 1); + ret = -EINVAL; + goto out_delete_filters; + } + cmd_func = __cmd_latency; + break; + case PERF_FTRACE_NONE: + default: + pr_err("Invalid subcommand\n"); + ret = -EINVAL; + goto out_delete_filters; + } ret = target__validate(&ftrace.target); if (ret) { @@ -961,7 +1263,15 @@ int cmd_ftrace(int argc, const char **argv) if (ret < 0) goto out_delete_evlist; - ret = __cmd_ftrace(&ftrace, argc, argv); + if (argc) { + ret = evlist__prepare_workload(ftrace.evlist, &ftrace.target, + argv, false, + ftrace__workload_exec_failed_signal); + if (ret < 0) + goto out_delete_evlist; + } + + ret = cmd_func(&ftrace); out_delete_evlist: evlist__delete(ftrace.evlist); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 6ad191e731fc..fbf43a454cba 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -535,12 +535,9 @@ static int perf_event__repipe_exit(struct perf_tool *tool, static int perf_event__repipe_tracing_data(struct perf_session *session, union perf_event *event) { - int err; - perf_event__repipe_synth(session->tool, event); - err = perf_event__process_tracing_data(session, event); - return err; + return perf_event__process_tracing_data(session, event); } static int dso__read_build_id(struct dso *dso) @@ -755,12 +752,16 @@ static int parse_vm_time_correlation(const struct option *opt, const char *str, return inject->itrace_synth_opts.vm_tm_corr_args ? 0 : -ENOMEM; } +static int output_fd(struct perf_inject *inject) +{ + return inject->in_place_update ? -1 : perf_data__fd(&inject->output); +} + static int __cmd_inject(struct perf_inject *inject) { int ret = -EINVAL; struct perf_session *session = inject->session; - struct perf_data *data_out = &inject->output; - int fd = inject->in_place_update ? -1 : perf_data__fd(data_out); + int fd = output_fd(inject); u64 output_data_offset; signal(SIGINT, sig_handler); @@ -815,11 +816,12 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.auxtrace_info = perf_event__process_auxtrace_info; inject->tool.auxtrace = perf_event__process_auxtrace; inject->tool.aux = perf_event__drop_aux; - inject->tool.itrace_start = perf_event__drop_aux, + inject->tool.itrace_start = perf_event__drop_aux; + inject->tool.aux_output_hw_id = perf_event__drop_aux; inject->tool.ordered_events = true; inject->tool.ordering_requires_timestamps = true; /* Allow space in the header for new attributes */ - output_data_offset = 4096; + output_data_offset = roundup(8192 + session->header.data_offset, 4096); if (inject->strip) strip_init(inject); } @@ -882,6 +884,7 @@ int cmd_inject(int argc, const char **argv) .lost_samples = perf_event__repipe, .aux = perf_event__repipe, .itrace_start = perf_event__repipe, + .aux_output_hw_id = perf_event__repipe, .context_switch = perf_event__repipe, .throttle = perf_event__repipe, .unthrottle = perf_event__repipe, @@ -938,6 +941,10 @@ int cmd_inject(int argc, const char **argv) #endif OPT_INCR('v', "verbose", &verbose, "be more verbose (show build ids, etc)"), + OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, + "file", "vmlinux pathname"), + OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux, + "don't load vmlinux even if found"), OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file", "kallsyms pathname"), OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"), @@ -972,6 +979,9 @@ int cmd_inject(int argc, const char **argv) return -1; } + if (symbol__validate_sym_arguments()) + return -1; + if (inject.in_place_update) { if (!strcmp(inject.input_name, "-")) { pr_err("Input file name required for in-place updating\n"); @@ -1006,7 +1016,7 @@ int cmd_inject(int argc, const char **argv) } inject.session = __perf_session__new(&data, repipe, - perf_data__fd(&inject.output), + output_fd(&inject), &inject.tool); if (IS_ERR(inject.session)) { ret = PTR_ERR(inject.session); @@ -1069,7 +1079,8 @@ out_delete: zstd_fini(&(inject.session->zstd_data)); perf_session__delete(inject.session); out_close_output: - perf_data__close(&inject.output); + if (!inject.in_place_update) + perf_data__close(&inject.output); free(inject.itrace_synth_opts.vm_tm_corr_args); return ret; } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index da03a341c63c..99d7ff9a8eff 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -192,7 +192,7 @@ static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_samp int ret = evsel__process_alloc_event(evsel, sample); if (!ret) { - int node1 = cpu__get_node(sample->cpu), + int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}), node2 = evsel__intval(evsel, sample, "node"); if (node1 != node2) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index aa1b127ffb5b..c6f352ee57e6 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1456,7 +1456,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, perf_session__set_id_hdr_size(kvm->session); ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true); machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target, - kvm->evlist->core.threads, false, 1); + kvm->evlist->core.threads, true, false, 1); err = kvm_live_open_events(kvm); if (err) goto out; diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 10ab5e40a34f..468958154ed9 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -12,6 +12,7 @@ #include "util/parse-events.h" #include "util/pmu.h" +#include "util/pmu-hybrid.h" #include "util/debug.h" #include "util/metricgroup.h" #include <subcmd/pager.h> @@ -20,13 +21,15 @@ static bool desc_flag = true; static bool details_flag; +static const char *hybrid_type; int cmd_list(int argc, const char **argv) { - int i; + int i, ret = 0; bool raw_dump = false; bool long_desc_flag = false; bool deprecated = false; + char *pmu_name = NULL; struct option list_options[] = { OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"), OPT_BOOLEAN('d', "desc", &desc_flag, @@ -37,6 +40,9 @@ int cmd_list(int argc, const char **argv) "Print information on the perf event names and expressions used internally by events."), OPT_BOOLEAN(0, "deprecated", &deprecated, "Print deprecated events."), + OPT_STRING(0, "cputype", &hybrid_type, "hybrid cpu type", + "Print events applying cpu with this type for hybrid platform " + "(e.g. core or atom)"), OPT_INCR(0, "debug", &verbose, "Enable debugging output"), OPT_END() @@ -56,10 +62,16 @@ int cmd_list(int argc, const char **argv) if (!raw_dump && pager_in_use()) printf("\nList of pre-defined events (to be used in -e):\n\n"); + if (hybrid_type) { + pmu_name = perf_pmu__hybrid_type_to_pmu(hybrid_type); + if (!pmu_name) + pr_warning("WARNING: hybrid cputype is not supported!\n"); + } + if (argc == 0) { print_events(NULL, raw_dump, !desc_flag, long_desc_flag, - details_flag, deprecated); - return 0; + details_flag, deprecated, pmu_name); + goto out; } for (i = 0; i < argc; ++i) { @@ -82,25 +94,27 @@ int cmd_list(int argc, const char **argv) else if (strcmp(argv[i], "pmu") == 0) print_pmu_events(NULL, raw_dump, !desc_flag, long_desc_flag, details_flag, - deprecated); + deprecated, pmu_name); else if (strcmp(argv[i], "sdt") == 0) print_sdt_events(NULL, NULL, raw_dump); else if (strcmp(argv[i], "metric") == 0 || strcmp(argv[i], "metrics") == 0) - metricgroup__print(true, false, NULL, raw_dump, details_flag); + metricgroup__print(true, false, NULL, raw_dump, details_flag, pmu_name); else if (strcmp(argv[i], "metricgroup") == 0 || strcmp(argv[i], "metricgroups") == 0) - metricgroup__print(false, true, NULL, raw_dump, details_flag); + metricgroup__print(false, true, NULL, raw_dump, details_flag, pmu_name); else if ((sep = strchr(argv[i], ':')) != NULL) { int sep_idx; sep_idx = sep - argv[i]; s = strdup(argv[i]); - if (s == NULL) - return -1; + if (s == NULL) { + ret = -1; + goto out; + } s[sep_idx] = '\0'; print_tracepoint_events(s, s + sep_idx + 1, raw_dump); print_sdt_events(s, s + sep_idx + 1, raw_dump); - metricgroup__print(true, true, s, raw_dump, details_flag); + metricgroup__print(true, true, s, raw_dump, details_flag, pmu_name); free(s); } else { if (asprintf(&s, "*%s*", argv[i]) < 0) { @@ -116,12 +130,16 @@ int cmd_list(int argc, const char **argv) print_pmu_events(s, raw_dump, !desc_flag, long_desc_flag, details_flag, - deprecated); + deprecated, + pmu_name); print_tracepoint_events(NULL, s, raw_dump); print_sdt_events(NULL, s, raw_dump); - metricgroup__print(true, true, s, raw_dump, details_flag); + metricgroup__print(true, true, s, raw_dump, details_flag, pmu_name); free(s); } } - return 0; + +out: + free(pmu_name); + return ret; } diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index e1dd51f2874b..c31627af75d4 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -21,6 +21,7 @@ #include "util/build-id.h" #include "util/strlist.h" #include "util/strfilter.h" +#include "util/symbol.h" #include "util/symbol_conf.h" #include "util/debug.h" #include <subcmd/parse-options.h> @@ -629,6 +630,10 @@ __cmd_probe(int argc, const char **argv) params.command = 'a'; } + ret = symbol__validate_sym_arguments(); + if (ret) + return ret; + if (params.quiet) { if (verbose != 0) { pr_err(" Error: -v and -q are exclusive.\n"); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index b3509d9d20cc..bb716c953d02 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -111,6 +111,7 @@ struct record { unsigned long long samples; struct mmap_cpu_mask affinity_mask; unsigned long output_max_size; /* = 0: unlimited */ + struct perf_debuginfod debuginfod; }; static volatile int done; @@ -1255,6 +1256,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) { int err; struct perf_thread_map *thread_map; + bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP; if (rec->opts.tail_synthesize != tail) return 0; @@ -1266,6 +1268,7 @@ static int record__synthesize_workload(struct record *rec, bool tail) err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, + needs_mmap, rec->opts.sample_address); perf_thread_map__put(thread_map); return err; @@ -1409,7 +1412,7 @@ static int record__synthesize(struct record *rec, bool tail) goto out; /* Synthesize id_index before auxtrace_info */ - if (rec->opts.auxtrace_sample_mode) { + if (rec->opts.auxtrace_sample_mode || rec->opts.full_auxtrace) { err = perf_event__synthesize_id_index(tool, process_synthesized_event, session->evlist, machine); @@ -1470,19 +1473,26 @@ static int record__synthesize(struct record *rec, bool tail) if (err < 0) pr_warning("Couldn't synthesize bpf events.\n"); - err = perf_event__synthesize_cgroups(tool, process_synthesized_event, - machine); - if (err < 0) - pr_warning("Couldn't synthesize cgroup events.\n"); + if (rec->opts.synth & PERF_SYNTH_CGROUP) { + err = perf_event__synthesize_cgroups(tool, process_synthesized_event, + machine); + if (err < 0) + pr_warning("Couldn't synthesize cgroup events.\n"); + } if (rec->opts.nr_threads_synthesize > 1) { perf_set_multithreaded(); f = process_locked_synthesized_event; } - err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads, - f, opts->sample_address, - rec->opts.nr_threads_synthesize); + if (rec->opts.synth & PERF_SYNTH_TASK) { + bool needs_mmap = rec->opts.synth & PERF_SYNTH_MMAP; + + err = __machine__synthesize_threads(machine, tool, &opts->target, + rec->evlist->core.threads, + f, needs_mmap, opts->sample_address, + rec->opts.nr_threads_synthesize); + } if (rec->opts.nr_threads_synthesize > 1) perf_set_singlethreaded(); @@ -2168,6 +2178,12 @@ static int perf_record_config(const char *var, const char *value, void *cb) rec->opts.nr_cblocks = nr_cblocks_default; } #endif + if (!strcmp(var, "record.debuginfod")) { + rec->debuginfod.urls = strdup(value); + if (!rec->debuginfod.urls) + return -ENOMEM; + rec->debuginfod.set = true; + } return 0; } @@ -2258,6 +2274,10 @@ out_free: return ret; } +void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused) +{ +} + static int parse_control_option(const struct option *opt, const char *str, int unset __maybe_unused) @@ -2391,6 +2411,26 @@ static int process_timestamp_boundary(struct perf_tool *tool, return 0; } +static int parse_record_synth_option(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + struct record_opts *opts = opt->value; + char *p = strdup(str); + + if (p == NULL) + return -1; + + opts->synth = parse_synth_opt(p); + free(p); + + if (opts->synth < 0) { + pr_err("Invalid synth option: %s\n", str); + return -1; + } + return 0; +} + /* * XXX Ideally would be local to cmd_record() and passed to a record__new * because we need to have access to it in record__exit, that is called @@ -2416,6 +2456,7 @@ static struct record record = { .nr_threads_synthesize = 1, .ctl_fd = -1, .ctl_fd_ack = -1, + .synth = PERF_SYNTH_ALL, }, .tool = { .sample = process_sample_event, @@ -2631,6 +2672,12 @@ static struct option __record_options[] = { "\t\t\t Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n" "\t\t\t Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.", parse_control_option), + OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup", + "Fine-tune event synthesis: default=all", parse_record_synth_option), + OPT_STRING_OPTARG_SET(0, "debuginfod", &record.debuginfod.urls, + &record.debuginfod.set, "debuginfod urls", + "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls", + "system"), OPT_END() }; @@ -2680,6 +2727,12 @@ int cmd_record(int argc, const char **argv) if (quiet) perf_quiet_option(); + err = symbol__validate_sym_arguments(); + if (err) + return err; + + perf_debuginfod_setup(&record.debuginfod); + /* Make system wide (-a) the default target. */ if (!argc && target__none(&rec->opts.target)) rec->opts.target.system_wide = true; @@ -2756,7 +2809,7 @@ int cmd_record(int argc, const char **argv) symbol__init(NULL); if (rec->opts.affinity != PERF_AFFINITY_SYS) { - rec->affinity_mask.nbits = cpu__max_cpu(); + rec->affinity_mask.nbits = cpu__max_cpu().cpu; rec->affinity_mask.bits = bitmap_zalloc(rec->affinity_mask.nbits); if (!rec->affinity_mask.bits) { pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits); @@ -2862,6 +2915,10 @@ int cmd_record(int argc, const char **argv) } rec->opts.target.hybrid = perf_pmu__has_hybrid(); + + if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP) + arch__add_leaf_frame_record_opts(&rec->opts); + err = -ENOMEM; if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0) usage_with_options(record_usage, record_options); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index a0316ce910db..1dd92d8c9279 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -410,7 +410,7 @@ static int report__setup_sample_type(struct report *rep) } } - callchain_param_setup(sample_type); + callchain_param_setup(sample_type, perf_env__arch(&rep->session->header.env)); if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) { ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n" @@ -619,14 +619,17 @@ static int report__browse_hists(struct report *rep) int ret; struct perf_session *session = rep->session; struct evlist *evlist = session->evlist; - const char *help = perf_tip(system_path(TIPDIR)); + char *help = NULL, *path = NULL; - if (help == NULL) { + path = system_path(TIPDIR); + if (perf_tip(&help, path) || help == NULL) { /* fallback for people who don't install perf ;-) */ - help = perf_tip(DOCDIR); - if (help == NULL) - help = "Cannot load tips.txt file, please install perf!"; + free(path); + path = system_path(DOCDIR); + if (perf_tip(&help, path) || help == NULL) + help = strdup("Cannot load tips.txt file, please install perf!"); } + free(path); switch (use_browser) { case 1: @@ -651,7 +654,7 @@ static int report__browse_hists(struct report *rep) ret = evlist__tty_browse_hists(evlist, rep, help); break; } - + free(help); return ret; } @@ -1124,7 +1127,7 @@ static int process_attr(struct perf_tool *tool __maybe_unused, * on events sample_type. */ sample_type = evlist__combined_sample_type(*pevlist); - callchain_param_setup(sample_type); + callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env)); return 0; } @@ -1378,18 +1381,9 @@ int cmd_report(int argc, const char **argv) if (quiet) perf_quiet_option(); - if (symbol_conf.vmlinux_name && - access(symbol_conf.vmlinux_name, R_OK)) { - pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); - ret = -EINVAL; - goto exit; - } - if (symbol_conf.kallsyms_name && - access(symbol_conf.kallsyms_name, R_OK)) { - pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); - ret = -EINVAL; + ret = symbol__validate_sym_arguments(); + if (ret) goto exit; - } if (report.inverted_callchain) callchain_param.order = ORDER_CALLER; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 635a6b5a9ec9..72d446de9c60 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -167,7 +167,7 @@ struct trace_sched_handler { struct perf_sched_map { DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS); - int *comp_cpus; + struct perf_cpu *comp_cpus; bool comp; struct perf_thread_map *color_pids; const char *color_pids_str; @@ -191,7 +191,7 @@ struct perf_sched { * Track the current task - that way we can know whether there's any * weird events, such as a task being switched away that is not current. */ - int max_cpu; + struct perf_cpu max_cpu; u32 curr_pid[MAX_CPUS]; struct thread *curr_thread[MAX_CPUS]; char next_shortname1; @@ -1535,28 +1535,31 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; - int i, this_cpu = sample->cpu; + int i; + struct perf_cpu this_cpu = { + .cpu = sample->cpu, + }; int cpus_nr; bool new_cpu = false; const char *color = PERF_COLOR_NORMAL; char stimestamp[32]; - BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0); + BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0); - if (this_cpu > sched->max_cpu) + if (this_cpu.cpu > sched->max_cpu.cpu) sched->max_cpu = this_cpu; if (sched->map.comp) { cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS); - if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) { + if (!test_and_set_bit(this_cpu.cpu, sched->map.comp_cpus_mask)) { sched->map.comp_cpus[cpus_nr++] = this_cpu; new_cpu = true; } } else - cpus_nr = sched->max_cpu; + cpus_nr = sched->max_cpu.cpu; - timestamp0 = sched->cpu_last_switched[this_cpu]; - sched->cpu_last_switched[this_cpu] = timestamp; + timestamp0 = sched->cpu_last_switched[this_cpu.cpu]; + sched->cpu_last_switched[this_cpu.cpu] = timestamp; if (timestamp0) delta = timestamp - timestamp0; else @@ -1577,7 +1580,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, return -1; } - sched->curr_thread[this_cpu] = thread__get(sched_in); + sched->curr_thread[this_cpu.cpu] = thread__get(sched_in); printf(" "); @@ -1608,8 +1611,10 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, } for (i = 0; i < cpus_nr; i++) { - int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i; - struct thread *curr_thread = sched->curr_thread[cpu]; + struct perf_cpu cpu = { + .cpu = sched->map.comp ? sched->map.comp_cpus[i].cpu : i, + }; + struct thread *curr_thread = sched->curr_thread[cpu.cpu]; struct thread_runtime *curr_tr; const char *pid_color = color; const char *cpu_color = color; @@ -1617,19 +1622,19 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, if (curr_thread && thread__has_color(curr_thread)) pid_color = COLOR_PIDS; - if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu)) + if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, cpu)) continue; - if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu)) + if (sched->map.color_cpus && perf_cpu_map__has(sched->map.color_cpus, cpu)) cpu_color = COLOR_CPUS; - if (cpu != this_cpu) + if (cpu.cpu != this_cpu.cpu) color_fprintf(stdout, color, " "); else color_fprintf(stdout, cpu_color, "*"); - if (sched->curr_thread[cpu]) { - curr_tr = thread__get_runtime(sched->curr_thread[cpu]); + if (sched->curr_thread[cpu.cpu]) { + curr_tr = thread__get_runtime(sched->curr_thread[cpu.cpu]); if (curr_tr == NULL) { thread__put(sched_in); return -1; @@ -1639,7 +1644,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, color_fprintf(stdout, color, " "); } - if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu)) + if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, this_cpu)) goto out; timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp)); @@ -1929,7 +1934,7 @@ static char *timehist_get_commstr(struct thread *thread) static void timehist_header(struct perf_sched *sched) { - u32 ncpus = sched->max_cpu + 1; + u32 ncpus = sched->max_cpu.cpu + 1; u32 i, j; printf("%15s %6s ", "time", "cpu"); @@ -2008,7 +2013,7 @@ static void timehist_print_sample(struct perf_sched *sched, struct thread_runtime *tr = thread__priv(thread); const char *next_comm = evsel__strval(evsel, sample, "next_comm"); const u32 next_pid = evsel__intval(evsel, sample, "next_pid"); - u32 max_cpus = sched->max_cpu + 1; + u32 max_cpus = sched->max_cpu.cpu + 1; char tstr[64]; char nstr[30]; u64 wait_time; @@ -2389,7 +2394,7 @@ static void timehist_print_wakeup_event(struct perf_sched *sched, timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr)); printf("%15s [%04d] ", tstr, sample->cpu); if (sched->show_cpu_visual) - printf(" %*s ", sched->max_cpu + 1, ""); + printf(" %*s ", sched->max_cpu.cpu + 1, ""); printf(" %-*s ", comm_width, timehist_get_commstr(thread)); @@ -2449,13 +2454,13 @@ static void timehist_print_migration_event(struct perf_sched *sched, { struct thread *thread; char tstr[64]; - u32 max_cpus = sched->max_cpu + 1; + u32 max_cpus; u32 ocpu, dcpu; if (sched->summary_only) return; - max_cpus = sched->max_cpu + 1; + max_cpus = sched->max_cpu.cpu + 1; ocpu = evsel__intval(evsel, sample, "orig_cpu"); dcpu = evsel__intval(evsel, sample, "dest_cpu"); @@ -2918,7 +2923,7 @@ static void timehist_print_summary(struct perf_sched *sched, printf(" Total scheduling time (msec): "); print_sched_time(hist_time, 2); - printf(" (x %d)\n", sched->max_cpu); + printf(" (x %d)\n", sched->max_cpu.cpu); } typedef int (*sched_handler)(struct perf_tool *tool, @@ -2935,9 +2940,11 @@ static int perf_timehist__process_sample(struct perf_tool *tool, { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); int err = 0; - int this_cpu = sample->cpu; + struct perf_cpu this_cpu = { + .cpu = sample->cpu, + }; - if (this_cpu > sched->max_cpu) + if (this_cpu.cpu > sched->max_cpu.cpu) sched->max_cpu = this_cpu; if (evsel->handler != NULL) { @@ -3054,10 +3061,10 @@ static int perf_sched__timehist(struct perf_sched *sched) goto out; /* pre-allocate struct for per-CPU idle stats */ - sched->max_cpu = session->header.env.nr_cpus_online; - if (sched->max_cpu == 0) - sched->max_cpu = 4; - if (init_idle_threads(sched->max_cpu)) + sched->max_cpu.cpu = session->header.env.nr_cpus_online; + if (sched->max_cpu.cpu == 0) + sched->max_cpu.cpu = 4; + if (init_idle_threads(sched->max_cpu.cpu)) goto out; /* summary_only implies summary option, but don't overwrite summary if set */ @@ -3209,10 +3216,10 @@ static int setup_map_cpus(struct perf_sched *sched) { struct perf_cpu_map *map; - sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); + sched->max_cpu.cpu = sysconf(_SC_NPROCESSORS_CONF); if (sched->map.comp) { - sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int)); + sched->map.comp_cpus = zalloc(sched->max_cpu.cpu * sizeof(int)); if (!sched->map.comp_cpus) return -1; } @@ -3538,6 +3545,7 @@ int cmd_sched(int argc, const char **argv) .fork_event = replay_fork_event, }; unsigned int i; + int ret; for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++) sched.curr_pid[i] = -1; @@ -3598,6 +3606,9 @@ int cmd_sched(int argc, const char **argv) parse_options_usage(NULL, timehist_options, "n", true); return -EINVAL; } + ret = symbol__validate_sym_arguments(); + if (ret) + return ret; return perf_sched__timehist(&sched); } else { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index c32c2eb16d7d..abae8184e171 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -15,6 +15,7 @@ #include "util/symbol.h" #include "util/thread.h" #include "util/trace-event.h" +#include "util/env.h" #include "util/evlist.h" #include "util/evsel.h" #include "util/evsel_fprintf.h" @@ -122,6 +123,7 @@ enum perf_output_field { PERF_OUTPUT_TOD = 1ULL << 32, PERF_OUTPUT_DATA_PAGE_SIZE = 1ULL << 33, PERF_OUTPUT_CODE_PAGE_SIZE = 1ULL << 34, + PERF_OUTPUT_INS_LAT = 1ULL << 35, }; struct perf_script { @@ -188,6 +190,7 @@ struct output_option { {.str = "tod", .field = PERF_OUTPUT_TOD}, {.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE}, {.str = "code_page_size", .field = PERF_OUTPUT_CODE_PAGE_SIZE}, + {.str = "ins_lat", .field = PERF_OUTPUT_INS_LAT}, }; enum { @@ -262,7 +265,8 @@ static struct { PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR | - PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE, + PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE | + PERF_OUTPUT_INS_LAT, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -511,7 +515,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(PHYS_ADDR) && - evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR)) + evsel__do_check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR, allow_user_set)) return -EINVAL; if (PRINT_FIELD(DATA_PAGE_SIZE) && @@ -522,6 +526,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) evsel__check_stype(evsel, PERF_SAMPLE_CODE_PAGE_SIZE, "CODE_PAGE_SIZE", PERF_OUTPUT_CODE_PAGE_SIZE)) return -EINVAL; + if (PRINT_FIELD(INS_LAT) && + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_INS_LAT)) + return -EINVAL; + return 0; } @@ -641,7 +649,7 @@ out: return 0; } -static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, +static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, const char *arch, FILE *fp) { unsigned i = 0, r; @@ -654,7 +662,7 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) { u64 val = regs->regs[i++]; - printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val); + printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r, arch), val); } return printed; @@ -711,17 +719,17 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen, } static int perf_sample__fprintf_iregs(struct perf_sample *sample, - struct perf_event_attr *attr, FILE *fp) + struct perf_event_attr *attr, const char *arch, FILE *fp) { return perf_sample__fprintf_regs(&sample->intr_regs, - attr->sample_regs_intr, fp); + attr->sample_regs_intr, arch, fp); } static int perf_sample__fprintf_uregs(struct perf_sample *sample, - struct perf_event_attr *attr, FILE *fp) + struct perf_event_attr *attr, const char *arch, FILE *fp) { return perf_sample__fprintf_regs(&sample->user_regs, - attr->sample_regs_user, fp); + attr->sample_regs_user, arch, fp); } static int perf_sample__fprintf_start(struct perf_script *script, @@ -1993,6 +2001,7 @@ static void process_event(struct perf_script *script, struct evsel_script *es = evsel->priv; FILE *fp = es->fp; char str[PAGE_SIZE_NAME_LEN]; + const char *arch = perf_env__arch(machine->env); if (output[type].fields == 0) return; @@ -2039,6 +2048,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(WEIGHT)) fprintf(fp, "%16" PRIu64, sample->weight); + if (PRINT_FIELD(INS_LAT)) + fprintf(fp, "%16" PRIu16, sample->ins_lat); + if (PRINT_FIELD(IP)) { struct callchain_cursor *cursor = NULL; @@ -2056,10 +2068,10 @@ static void process_event(struct perf_script *script, } if (PRINT_FIELD(IREGS)) - perf_sample__fprintf_iregs(sample, attr, fp); + perf_sample__fprintf_iregs(sample, attr, arch, fp); if (PRINT_FIELD(UREGS)) - perf_sample__fprintf_uregs(sample, attr, fp); + perf_sample__fprintf_uregs(sample, attr, arch, fp); if (PRINT_FIELD(BRSTACK)) perf_sample__fprintf_brstack(sample, thread, attr, fp); @@ -2103,8 +2115,8 @@ static struct scripting_ops *scripting_ops; static void __process_stat(struct evsel *counter, u64 tstamp) { int nthreads = perf_thread_map__nr(counter->core.threads); - int ncpus = evsel__nr_cpus(counter); - int cpu, thread; + int idx, thread; + struct perf_cpu cpu; static int header_printed; if (counter->core.system_wide) @@ -2117,13 +2129,13 @@ static void __process_stat(struct evsel *counter, u64 tstamp) } for (thread = 0; thread < nthreads; thread++) { - for (cpu = 0; cpu < ncpus; cpu++) { + perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) { struct perf_counts_values *counts; - counts = perf_counts(counter->counts, cpu, thread); + counts = perf_counts(counter->counts, idx, thread); printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n", - counter->core.cpus->map[cpu], + cpu.cpu, perf_thread_map__pid(counter->core.threads, thread), counts->val, counts->ena, @@ -2306,7 +2318,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, * on events sample_type. */ sample_type = evlist__combined_sample_type(evlist); - callchain_param_setup(sample_type); + callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env)); /* Enable fields for callchain entries */ if (symbol_conf.use_callchain && @@ -2463,7 +2475,7 @@ static int process_switch_event(struct perf_tool *tool, if (perf_event__process_switch(tool, event, sample, machine) < 0) return -1; - if (scripting_ops && scripting_ops->process_switch) + if (scripting_ops && scripting_ops->process_switch && !filter_cpu(sample)) scripting_ops->process_switch(event, sample, machine); if (!script->show_switch_events) @@ -3456,16 +3468,7 @@ static void script__setup_sample_type(struct perf_script *script) struct perf_session *session = script->session; u64 sample_type = evlist__combined_sample_type(session->evlist); - if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { - if ((sample_type & PERF_SAMPLE_REGS_USER) && - (sample_type & PERF_SAMPLE_STACK_USER)) { - callchain_param.record_mode = CALLCHAIN_DWARF; - dwarf_callchain_users = true; - } else if (sample_type & PERF_SAMPLE_BRANCH_STACK) - callchain_param.record_mode = CALLCHAIN_LBR; - else - callchain_param.record_mode = CALLCHAIN_FP; - } + callchain_param_setup(sample_type, perf_env__arch(session->machines.host.env)); if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) { pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n" @@ -3715,7 +3718,7 @@ int cmd_script(int argc, const char **argv) "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,bpf-output,brstackinsn,brstackoff," "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod," - "data_page_size,code_page_size", + "data_page_size,code_page_size,ins_lat", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), @@ -3836,6 +3839,9 @@ int cmd_script(int argc, const char **argv) data.path = input_name; data.force = symbol_conf.force; + if (symbol__validate_sym_arguments()) + return -1; + if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { rec_script_path = get_script_path(argv[1], RECORD_SUFFIX); if (!rec_script_path) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f0ecfda34ece..3f98689dd687 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -230,11 +230,12 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b) if (!a->core.cpus || !b->core.cpus) return false; - if (a->core.cpus->nr != b->core.cpus->nr) + if (perf_cpu_map__nr(a->core.cpus) != perf_cpu_map__nr(b->core.cpus)) return false; - for (int i = 0; i < a->core.cpus->nr; i++) { - if (a->core.cpus->map[i] != b->core.cpus->map[i]) + for (int i = 0; i < perf_cpu_map__nr(a->core.cpus); i++) { + if (perf_cpu_map__cpu(a->core.cpus, i).cpu != + perf_cpu_map__cpu(b->core.cpus, i).cpu) return false; } @@ -327,34 +328,35 @@ static int write_stat_round_event(u64 tm, u64 type) #define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y) -static int evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread, +static int evsel__write_stat_event(struct evsel *counter, int cpu_map_idx, u32 thread, struct perf_counts_values *count) { - struct perf_sample_id *sid = SID(counter, cpu, thread); + struct perf_sample_id *sid = SID(counter, cpu_map_idx, thread); + struct perf_cpu cpu = perf_cpu_map__cpu(evsel__cpus(counter), cpu_map_idx); return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count, process_synthesized_event, NULL); } -static int read_single_counter(struct evsel *counter, int cpu, +static int read_single_counter(struct evsel *counter, int cpu_map_idx, int thread, struct timespec *rs) { if (counter->tool_event == PERF_TOOL_DURATION_TIME) { u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL; struct perf_counts_values *count = - perf_counts(counter->counts, cpu, thread); + perf_counts(counter->counts, cpu_map_idx, thread); count->ena = count->run = val; count->val = val; return 0; } - return evsel__read_counter(counter, cpu, thread); + return evsel__read_counter(counter, cpu_map_idx, thread); } /* * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) +static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_map_idx) { int nthreads = perf_thread_map__nr(evsel_list->core.threads); int thread; @@ -368,24 +370,24 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) for (thread = 0; thread < nthreads; thread++) { struct perf_counts_values *count; - count = perf_counts(counter->counts, cpu, thread); + count = perf_counts(counter->counts, cpu_map_idx, thread); /* * The leader's group read loads data into its group members * (via evsel__read_counter()) and sets their count->loaded. */ - if (!perf_counts__is_loaded(counter->counts, cpu, thread) && - read_single_counter(counter, cpu, thread, rs)) { + if (!perf_counts__is_loaded(counter->counts, cpu_map_idx, thread) && + read_single_counter(counter, cpu_map_idx, thread, rs)) { counter->counts->scaled = -1; - perf_counts(counter->counts, cpu, thread)->ena = 0; - perf_counts(counter->counts, cpu, thread)->run = 0; + perf_counts(counter->counts, cpu_map_idx, thread)->ena = 0; + perf_counts(counter->counts, cpu_map_idx, thread)->run = 0; return -1; } - perf_counts__set_loaded(counter->counts, cpu, thread, false); + perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, false); if (STAT_RECORD) { - if (evsel__write_stat_event(counter, cpu, thread, count)) { + if (evsel__write_stat_event(counter, cpu_map_idx, thread, count)) { pr_err("failed to write stat event\n"); return -1; } @@ -395,7 +397,8 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) fprintf(stat_config.output, "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", evsel__name(counter), - cpu, + perf_cpu_map__cpu(evsel__cpus(counter), + cpu_map_idx).cpu, count->val, count->ena, count->run); } } @@ -405,36 +408,33 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu) static int read_affinity_counters(struct timespec *rs) { - struct evsel *counter; - struct affinity affinity; - int i, ncpus, cpu; + struct evlist_cpu_iterator evlist_cpu_itr; + struct affinity saved_affinity, *affinity; if (all_counters_use_bpf) return 0; - if (affinity__setup(&affinity) < 0) + if (!target__has_cpu(&target) || target__has_per_thread(&target)) + affinity = NULL; + else if (affinity__setup(&saved_affinity) < 0) return -1; + else + affinity = &saved_affinity; - ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus); - if (!target__has_cpu(&target) || target__has_per_thread(&target)) - ncpus = 1; - evlist__for_each_cpu(evsel_list, i, cpu) { - if (i >= ncpus) - break; - affinity__set(&affinity, cpu); + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) { + struct evsel *counter = evlist_cpu_itr.evsel; - evlist__for_each_entry(evsel_list, counter) { - if (evsel__cpu_iter_skip(counter, cpu)) - continue; - if (evsel__is_bpf(counter)) - continue; - if (!counter->err) { - counter->err = read_counter_cpu(counter, rs, - counter->cpu_iter - 1); - } + if (evsel__is_bpf(counter)) + continue; + + if (!counter->err) { + counter->err = read_counter_cpu(counter, rs, + evlist_cpu_itr.cpu_map_idx); } } - affinity__cleanup(&affinity); + if (affinity) + affinity__cleanup(&saved_affinity); + return 0; } @@ -788,8 +788,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) int status = 0; const bool forks = (argc > 0); bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false; - struct affinity affinity; - int i, cpu, err; + struct evlist_cpu_iterator evlist_cpu_itr; + struct affinity saved_affinity, *affinity = NULL; + int err; bool second_pass = false; if (forks) { @@ -803,8 +804,11 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (group) evlist__set_leader(evsel_list); - if (affinity__setup(&affinity) < 0) - return -1; + if (!cpu_map__is_dummy(evsel_list->core.cpus)) { + if (affinity__setup(&saved_affinity) < 0) + return -1; + affinity = &saved_affinity; + } evlist__for_each_entry(evsel_list, counter) { if (bpf_counter__load(counter, &target)) @@ -813,103 +817,98 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) all_counters_use_bpf = false; } - evlist__for_each_cpu (evsel_list, i, cpu) { + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) { + counter = evlist_cpu_itr.evsel; + /* * bperf calls evsel__open_per_cpu() in bperf__load(), so * no need to call it again here. */ if (target.use_bpf) break; - affinity__set(&affinity, cpu); - evlist__for_each_entry(evsel_list, counter) { - if (evsel__cpu_iter_skip(counter, cpu)) + if (counter->reset_group || counter->errored) + continue; + if (evsel__is_bpf(counter)) + continue; +try_again: + if (create_perf_stat_counter(counter, &stat_config, &target, + evlist_cpu_itr.cpu_map_idx) < 0) { + + /* + * Weak group failed. We cannot just undo this here + * because earlier CPUs might be in group mode, and the kernel + * doesn't support mixing group and non group reads. Defer + * it to later. + * Don't close here because we're in the wrong affinity. + */ + if ((errno == EINVAL || errno == EBADF) && + evsel__leader(counter) != counter && + counter->weak_group) { + evlist__reset_weak_group(evsel_list, counter, false); + assert(counter->reset_group); + second_pass = true; continue; - if (counter->reset_group || counter->errored) + } + + switch (stat_handle_error(counter)) { + case COUNTER_FATAL: + return -1; + case COUNTER_RETRY: + goto try_again; + case COUNTER_SKIP: + continue; + default: + break; + } + + } + counter->supported = true; + } + + if (second_pass) { + /* + * Now redo all the weak group after closing them, + * and also close errored counters. + */ + + /* First close errored or weak retry */ + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) { + counter = evlist_cpu_itr.evsel; + + if (!counter->reset_group && !counter->errored) continue; - if (evsel__is_bpf(counter)) + + perf_evsel__close_cpu(&counter->core, evlist_cpu_itr.cpu_map_idx); + } + /* Now reopen weak */ + evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) { + counter = evlist_cpu_itr.evsel; + + if (!counter->reset_group && !counter->errored) continue; -try_again: + if (!counter->reset_group) + continue; +try_again_reset: + pr_debug2("reopening weak %s\n", evsel__name(counter)); if (create_perf_stat_counter(counter, &stat_config, &target, - counter->cpu_iter - 1) < 0) { - - /* - * Weak group failed. We cannot just undo this here - * because earlier CPUs might be in group mode, and the kernel - * doesn't support mixing group and non group reads. Defer - * it to later. - * Don't close here because we're in the wrong affinity. - */ - if ((errno == EINVAL || errno == EBADF) && - evsel__leader(counter) != counter && - counter->weak_group) { - evlist__reset_weak_group(evsel_list, counter, false); - assert(counter->reset_group); - second_pass = true; - continue; - } + evlist_cpu_itr.cpu_map_idx) < 0) { switch (stat_handle_error(counter)) { case COUNTER_FATAL: return -1; case COUNTER_RETRY: - goto try_again; + goto try_again_reset; case COUNTER_SKIP: continue; default: break; } - } counter->supported = true; } } - - if (second_pass) { - /* - * Now redo all the weak group after closing them, - * and also close errored counters. - */ - - evlist__for_each_cpu(evsel_list, i, cpu) { - affinity__set(&affinity, cpu); - /* First close errored or weak retry */ - evlist__for_each_entry(evsel_list, counter) { - if (!counter->reset_group && !counter->errored) - continue; - if (evsel__cpu_iter_skip_no_inc(counter, cpu)) - continue; - perf_evsel__close_cpu(&counter->core, counter->cpu_iter); - } - /* Now reopen weak */ - evlist__for_each_entry(evsel_list, counter) { - if (!counter->reset_group && !counter->errored) - continue; - if (evsel__cpu_iter_skip(counter, cpu)) - continue; - if (!counter->reset_group) - continue; -try_again_reset: - pr_debug2("reopening weak %s\n", evsel__name(counter)); - if (create_perf_stat_counter(counter, &stat_config, &target, - counter->cpu_iter - 1) < 0) { - - switch (stat_handle_error(counter)) { - case COUNTER_FATAL: - return -1; - case COUNTER_RETRY: - goto try_again_reset; - case COUNTER_SKIP: - continue; - default: - break; - } - } - counter->supported = true; - } - } - } - affinity__cleanup(&affinity); + affinity__cleanup(affinity); evlist__for_each_entry(evsel_list, counter) { if (!counter->supported) { @@ -1168,6 +1167,26 @@ static int parse_stat_cgroups(const struct option *opt, return parse_cgroups(opt, str, unset); } +static int parse_hybrid_type(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + struct evlist *evlist = *(struct evlist **)opt->value; + + if (!list_empty(&evlist->core.entries)) { + fprintf(stderr, "Must define cputype before events/metrics\n"); + return -1; + } + + evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu(str); + if (!evlist->hybrid_pmu_name) { + fprintf(stderr, "--cputype %s is not supported!\n", str); + return -1; + } + + return 0; +} + static struct option stat_options[] = { OPT_BOOLEAN('T', "transaction", &transaction_run, "hardware transaction statistics"), @@ -1282,6 +1301,10 @@ static struct option stat_options[] = { "don't print 'summary' for CSV summary output"), OPT_BOOLEAN(0, "quiet", &stat_config.quiet, "don't print output (useful with record)"), + OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type", + "Only enable events on applying cpu with this type " + "for hybrid platform (e.g. core or atom)", + parse_hybrid_type), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", @@ -1298,70 +1321,75 @@ static struct option stat_options[] = { OPT_END() }; +static const char *const aggr_mode__string[] = { + [AGGR_CORE] = "core", + [AGGR_DIE] = "die", + [AGGR_GLOBAL] = "global", + [AGGR_NODE] = "node", + [AGGR_NONE] = "none", + [AGGR_SOCKET] = "socket", + [AGGR_THREAD] = "thread", + [AGGR_UNSET] = "unset", +}; + static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_socket(map, cpu, NULL); + return aggr_cpu_id__socket(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_die(map, cpu, NULL); + return aggr_cpu_id__die(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_core(map, cpu, NULL); + return aggr_cpu_id__core(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int cpu) + struct perf_cpu cpu) { - return cpu_map__get_node(map, cpu, NULL); + return aggr_cpu_id__node(cpu, /*data=*/NULL); } static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config, - aggr_get_id_t get_id, struct perf_cpu_map *map, int idx) + aggr_get_id_t get_id, struct perf_cpu cpu) { - int cpu; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (idx >= map->nr) - return id; + if (aggr_cpu_id__is_empty(&config->cpus_aggr_map->map[cpu.cpu])) + config->cpus_aggr_map->map[cpu.cpu] = get_id(config, cpu); - cpu = map->map[idx]; - - if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu])) - config->cpus_aggr_map->map[cpu] = get_id(config, map, idx); - - id = config->cpus_aggr_map->map[cpu]; + id = config->cpus_aggr_map->map[cpu.cpu]; return id; } static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_socket, cpu); } static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_die, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_die, cpu); } static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_core, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_core, cpu); } static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_stat__get_aggr(config, perf_stat__get_node, map, idx); + return perf_stat__get_aggr(config, perf_stat__get_node, cpu); } static bool term_percore_set(void) @@ -1376,54 +1404,67 @@ static bool term_percore_set(void) return false; } -static int perf_stat_init_aggr_mode(void) +static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode) { - int nr; + switch (aggr_mode) { + case AGGR_SOCKET: + return aggr_cpu_id__socket; + case AGGR_DIE: + return aggr_cpu_id__die; + case AGGR_CORE: + return aggr_cpu_id__core; + case AGGR_NODE: + return aggr_cpu_id__node; + case AGGR_NONE: + if (term_percore_set()) + return aggr_cpu_id__core; - switch (stat_config.aggr_mode) { + return NULL; + case AGGR_GLOBAL: + case AGGR_THREAD: + case AGGR_UNSET: + default: + return NULL; + } +} + +static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode) +{ + switch (aggr_mode) { case AGGR_SOCKET: - if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build socket map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_socket_cached; - break; + return perf_stat__get_socket_cached; case AGGR_DIE: - if (cpu_map__build_die_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build die map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_die_cached; - break; + return perf_stat__get_die_cached; case AGGR_CORE: - if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_core_cached; - break; + return perf_stat__get_core_cached; case AGGR_NODE: - if (cpu_map__build_node_map(evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_node_cached; - break; + return perf_stat__get_node_cached; case AGGR_NONE: if (term_percore_set()) { - if (cpu_map__build_core_map(evsel_list->core.cpus, - &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_core_cached; + return perf_stat__get_core_cached; } - break; + return NULL; case AGGR_GLOBAL: case AGGR_THREAD: case AGGR_UNSET: default: - break; + return NULL; + } +} + +static int perf_stat_init_aggr_mode(void) +{ + int nr; + aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode); + + if (get_id) { + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, + get_id, /*data=*/NULL); + if (!stat_config.aggr_map) { + pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); + return -1; + } + stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode); } /* @@ -1431,7 +1472,7 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - nr = perf_cpu_map__max(evsel_list->core.cpus); + nr = perf_cpu_map__max(evsel_list->core.cpus).cpu; stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } @@ -1459,169 +1500,139 @@ static void perf_stat__exit_aggr_mode(void) stat_config.cpus_aggr_map = NULL; } -static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx) -{ - int cpu; - - if (idx > map->nr) - return -1; - - cpu = map->map[idx]; - - if (cpu >= env->nr_cpus_avail) - return -1; - - return cpu; -} - -static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu, void *data) { struct perf_env *env = data; - int cpu = perf_env__get_cpu(env, map, idx); - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (cpu != -1) - id.socket = env->cpu[cpu].socket_id; + if (cpu.cpu != -1) + id.socket = env->cpu[cpu.cpu].socket_id; return id; } -static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, void *data) { struct perf_env *env = data; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - int cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (cpu != -1) { + if (cpu.cpu != -1) { /* * die_id is relative to socket, so start * with the socket ID and then add die to * make a unique ID. */ - id.socket = env->cpu[cpu].socket_id; - id.die = env->cpu[cpu].die_id; + id.socket = env->cpu[cpu.cpu].socket_id; + id.die = env->cpu[cpu.cpu].die_id; } return id; } -static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, void *data) { struct perf_env *env = data; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - int cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (cpu != -1) { + if (cpu.cpu != -1) { /* * core_id is relative to socket and die, * we need a global id. So we set * socket, die id and core id */ - id.socket = env->cpu[cpu].socket_id; - id.die = env->cpu[cpu].die_id; - id.core = env->cpu[cpu].core_id; + id.socket = env->cpu[cpu.cpu].socket_id; + id.die = env->cpu[cpu.cpu].die_id; + id.core = env->cpu[cpu.cpu].core_id; } return id; } -static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(struct perf_cpu cpu, void *data) { - int cpu = perf_env__get_cpu(data, map, idx); - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); id.node = perf_env__numa_node(data, cpu); return id; } -static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **sockp) -{ - return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); -} - -static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **diep) -{ - return cpu_map__build_map(cpus, diep, perf_env__get_die, env); -} - -static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **corep) -{ - return cpu_map__build_map(cpus, corep, perf_env__get_core, env); -} - -static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct cpu_aggr_map **nodep) -{ - return cpu_map__build_map(cpus, nodep, perf_env__get_node, env); -} - static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_socket(map, idx, &perf_stat.session->header.env); + return perf_env__get_socket_aggr_by_cpu(cpu, &perf_stat.session->header.env); } static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_die(map, idx, &perf_stat.session->header.env); + return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env); } static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_core(map, idx, &perf_stat.session->header.env); + return perf_env__get_core_aggr_by_cpu(cpu, &perf_stat.session->header.env); } static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused, - struct perf_cpu_map *map, int idx) + struct perf_cpu cpu) { - return perf_env__get_node(map, idx, &perf_stat.session->header.env); + return perf_env__get_node_aggr_by_cpu(cpu, &perf_stat.session->header.env); } -static int perf_stat_init_aggr_mode_file(struct perf_stat *st) +static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode) { - struct perf_env *env = &st->session->header.env; + switch (aggr_mode) { + case AGGR_SOCKET: + return perf_env__get_socket_aggr_by_cpu; + case AGGR_DIE: + return perf_env__get_die_aggr_by_cpu; + case AGGR_CORE: + return perf_env__get_core_aggr_by_cpu; + case AGGR_NODE: + return perf_env__get_node_aggr_by_cpu; + case AGGR_NONE: + case AGGR_GLOBAL: + case AGGR_THREAD: + case AGGR_UNSET: + default: + return NULL; + } +} - switch (stat_config.aggr_mode) { +static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode) +{ + switch (aggr_mode) { case AGGR_SOCKET: - if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build socket map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_socket_file; - break; + return perf_stat__get_socket_file; case AGGR_DIE: - if (perf_env__build_die_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build die map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_die_file; - break; + return perf_stat__get_die_file; case AGGR_CORE: - if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_core_file; - break; + return perf_stat__get_core_file; case AGGR_NODE: - if (perf_env__build_node_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) { - perror("cannot build core map"); - return -1; - } - stat_config.aggr_get_id = perf_stat__get_node_file; - break; + return perf_stat__get_node_file; case AGGR_NONE: case AGGR_GLOBAL: case AGGR_THREAD: case AGGR_UNSET: default: - break; + return NULL; } +} +static int perf_stat_init_aggr_mode_file(struct perf_stat *st) +{ + struct perf_env *env = &st->session->header.env; + aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode); + + if (!get_id) + return 0; + + stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env); + if (!stat_config.aggr_map) { + pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]); + return -1; + } + stat_config.aggr_get_id = aggr_mode__get_id_file(stat_config.aggr_mode); return 0; } @@ -1750,14 +1761,12 @@ static int add_default_attributes(void) (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, }; - struct parse_events_error errinfo; - /* Set attrs if no event is selected and !null_run: */ if (stat_config.null_run) return 0; - bzero(&errinfo, sizeof(errinfo)); if (transaction_run) { + struct parse_events_error errinfo; /* Handle -T as -M transaction. Once platform specific metrics * support has been added to the json files, all architectures * will use this approach. To determine transaction support @@ -1772,6 +1781,7 @@ static int add_default_attributes(void) &stat_config.metric_events); } + parse_events_error__init(&errinfo); if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) err = parse_events(evsel_list, transaction_attrs, @@ -1782,13 +1792,14 @@ static int add_default_attributes(void) &errinfo); if (err) { fprintf(stderr, "Cannot set up transaction events\n"); - parse_events_print_error(&errinfo, transaction_attrs); - return -1; + parse_events_error__print(&errinfo, transaction_attrs); } - return 0; + parse_events_error__exit(&errinfo); + return err ? -1 : 0; } if (smi_cost) { + struct parse_events_error errinfo; int smi; if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) { @@ -1804,23 +1815,23 @@ static int add_default_attributes(void) smi_reset = true; } - if (pmu_have_event("msr", "aperf") && - pmu_have_event("msr", "smi")) { - if (!force_metric_only) - stat_config.metric_only = true; - err = parse_events(evsel_list, smi_cost_attrs, &errinfo); - } else { + if (!pmu_have_event("msr", "aperf") || + !pmu_have_event("msr", "smi")) { fprintf(stderr, "To measure SMI cost, it needs " "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); - parse_events_print_error(&errinfo, smi_cost_attrs); return -1; } + if (!force_metric_only) + stat_config.metric_only = true; + + parse_events_error__init(&errinfo); + err = parse_events(evsel_list, smi_cost_attrs, &errinfo); if (err) { - parse_events_print_error(&errinfo, smi_cost_attrs); + parse_events_error__print(&errinfo, smi_cost_attrs); fprintf(stderr, "Cannot set up SMI cost events\n"); - return -1; } - return 0; + parse_events_error__exit(&errinfo); + return err ? -1 : 0; } if (topdown_run) { @@ -1875,18 +1886,22 @@ static int add_default_attributes(void) return -1; } if (topdown_attrs[0] && str) { + struct parse_events_error errinfo; if (warn) arch_topdown_group_warn(); setup_metrics: + parse_events_error__init(&errinfo); err = parse_events(evsel_list, str, &errinfo); if (err) { fprintf(stderr, "Cannot set up top down events %s: %d\n", str, err); - parse_events_print_error(&errinfo, str); + parse_events_error__print(&errinfo, str); + parse_events_error__exit(&errinfo); free(str); return -1; } + parse_events_error__exit(&errinfo); } else { fprintf(stderr, "System does not support topdown\n"); return -1; @@ -1896,6 +1911,7 @@ setup_metrics: if (!evsel_list->core.nr_entries) { if (perf_pmu__has_hybrid()) { + struct parse_events_error errinfo; const char *hybrid_str = "cycles,instructions,branches,branch-misses"; if (target__has_cpu(&target)) @@ -1906,15 +1922,16 @@ setup_metrics: return -1; } + parse_events_error__init(&errinfo); err = parse_events(evsel_list, hybrid_str, &errinfo); if (err) { fprintf(stderr, "Cannot set up hybrid events %s: %d\n", hybrid_str, err); - parse_events_print_error(&errinfo, hybrid_str); - return -1; + parse_events_error__print(&errinfo, hybrid_str); } - return err; + parse_events_error__exit(&errinfo); + return err ? -1 : 0; } if (target__has_cpu(&target)) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a3ae9176a83e..1fc390f136dd 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1271,7 +1271,7 @@ static int __cmd_top(struct perf_top *top) pr_debug("Couldn't synthesize cgroup events.\n"); machine__synthesize_threads(&top->session->machines.host, &opts->target, - top->evlist->core.threads, false, + top->evlist->core.threads, true, false, top->nr_threads_synthesize); if (top->nr_threads_synthesize > 1) @@ -1618,6 +1618,10 @@ int cmd_top(int argc, const char **argv) if (argc) usage_with_options(top_usage, options); + status = symbol__validate_sym_arguments(); + if (status) + goto out_delete_evlist; + if (annotate_check_args(&top.annotation_opts) < 0) goto out_delete_evlist; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 2bf21194c7b3..32844d8a0ea5 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -979,6 +979,8 @@ static struct syscall_fmt syscall_fmts[] = { .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, }, { .name = "getrlimit", .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "getsockopt", + .arg = { [1] = STRARRAY(level, socket_level), }, }, { .name = "gettid", .errpid = true, }, { .name = "ioctl", .arg = { @@ -1121,6 +1123,8 @@ static struct syscall_fmt syscall_fmts[] = { .arg = { [0] = STRARRAY(which, itimers), }, }, { .name = "setrlimit", .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "setsockopt", + .arg = { [1] = STRARRAY(level, socket_level), }, }, { .name = "socket", .arg = { [0] = STRARRAY(family, socket_families), [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, @@ -1628,8 +1632,8 @@ static int trace__symbols_init(struct trace *trace, struct evlist *evlist) goto out; err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target, - evlist->core.threads, trace__tool_process, false, - 1); + evlist->core.threads, trace__tool_process, + true, false, 1); out: if (err) symbol__exit(); @@ -2722,6 +2726,8 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, offset = format_field__intval(field, sample, evsel->needs_swap); syscall_arg.len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } val = (uintptr_t)(sample->raw_data + offset); @@ -3063,15 +3069,11 @@ static bool evlist__add_vfs_getname(struct evlist *evlist) struct parse_events_error err; int ret; - bzero(&err, sizeof(err)); + parse_events_error__init(&err); ret = parse_events(evlist, "probe:vfs_getname*", &err); - if (ret) { - free(err.str); - free(err.help); - free(err.first_str); - free(err.first_help); + parse_events_error__exit(&err); + if (ret) return false; - } evlist__for_each_entry_safe(evlist, evsel, tmp) { if (!strstarts(evsel__name(evsel), "probe:vfs_getname")) @@ -3257,10 +3259,21 @@ static void trace__set_bpf_map_syscalls(struct trace *trace) static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name) { + struct bpf_program *pos, *prog = NULL; + const char *sec_name; + if (trace->bpf_obj == NULL) return NULL; - return bpf_object__find_program_by_title(trace->bpf_obj, name); + bpf_object__for_each_program(pos, trace->bpf_obj) { + sec_name = bpf_program__section_name(pos); + if (sec_name && !strcmp(sec_name, name)) { + prog = pos; + break; + } + } + + return prog; } static struct bpf_program *trace__find_syscall_bpf_prog(struct trace *trace, struct syscall *sc, @@ -3925,6 +3938,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) bool draining = false; trace->live = true; + signal(SIGCHLD, sig_handler); if (!trace->raw_augmented_syscalls) { if (trace->trace_syscalls && trace__add_syscall_newtp(trace)) @@ -3950,6 +3964,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv) evlist__add(evlist, pgfault_min); } + /* Enable ignoring missing threads when -u/-p option is defined. */ + trace->opts.ignore_missing_thread = trace->opts.target.uid != UINT_MAX || trace->opts.target.pid; + if (trace->sched && evlist__add_newtp(evlist, "sched", "sched_stat_runtime", trace__sched_stat_runtime)) goto out_error_sched_stat_runtime; @@ -4873,7 +4890,6 @@ int cmd_trace(int argc, const char **argv) signal(SIGSEGV, sighandler_dump_stack); signal(SIGFPE, sighandler_dump_stack); - signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); trace.evlist = evlist__new(); @@ -4925,12 +4941,13 @@ int cmd_trace(int argc, const char **argv) if (trace.perfconfig_events != NULL) { struct parse_events_error parse_err; - bzero(&parse_err, sizeof(parse_err)); + parse_events_error__init(&parse_err); err = parse_events(trace.evlist, trace.perfconfig_events, &parse_err); - if (err) { - parse_events_print_error(&parse_err, trace.perfconfig_events); + if (err) + parse_events_error__print(&parse_err, trace.perfconfig_events); + parse_events_error__exit(&parse_err); + if (err) goto out; - } } if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) { diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index f1e46277e822..30ecf3a0f68b 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -26,6 +26,7 @@ include/vdso/bits.h include/linux/const.h include/vdso/const.h include/linux/hash.h +include/linux/list-sort.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h arch/x86/include/asm/required-features.h @@ -150,6 +151,7 @@ check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"' check include/linux/ctype.h '-I "isdigit("' check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B' +check lib/list_sort.c '-I "^#include <linux/bug.h>"' # diff non-symmetric files check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl diff --git a/tools/perf/design.txt b/tools/perf/design.txt index a42fab308ff6..aa8cfeabb743 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -106,6 +106,9 @@ enum perf_hw_id { PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, PERF_COUNT_HW_BRANCH_MISSES = 5, PERF_COUNT_HW_BUS_CYCLES = 6, + PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7, + PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8, + PERF_COUNT_HW_REF_CPU_CYCLES = 9, }; These are standardized types of events that work relatively uniformly diff --git a/tools/perf/dlfilters/dlfilter-show-cycles.c b/tools/perf/dlfilters/dlfilter-show-cycles.c new file mode 100644 index 000000000000..9eccc97bff82 --- /dev/null +++ b/tools/perf/dlfilters/dlfilter-show-cycles.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * dlfilter-show-cycles.c: Print the number of cycles at the start of each line + * Copyright (c) 2021, Intel Corporation. + */ +#include <perf/perf_dlfilter.h> +#include <string.h> +#include <stdio.h> + +#define MAX_CPU 4096 + +enum { + INSTR_CYC, + BRNCH_CYC, + OTHER_CYC, + MAX_ENTRY +}; + +static __u64 cycles[MAX_CPU][MAX_ENTRY]; +static __u64 cycles_rpt[MAX_CPU][MAX_ENTRY]; + +#define BITS 16 +#define TABLESZ (1 << BITS) +#define TABLEMAX (TABLESZ / 2) +#define MASK (TABLESZ - 1) + +static struct entry { + __u32 used; + __s32 tid; + __u64 cycles[MAX_ENTRY]; + __u64 cycles_rpt[MAX_ENTRY]; +} table[TABLESZ]; + +static int tid_cnt; + +static int event_entry(const char *event) +{ + if (!event) + return OTHER_CYC; + if (!strncmp(event, "instructions", 12)) + return INSTR_CYC; + if (!strncmp(event, "branches", 8)) + return BRNCH_CYC; + return OTHER_CYC; +} + +static struct entry *find_entry(__s32 tid) +{ + __u32 pos = tid & MASK; + struct entry *e; + + e = &table[pos]; + while (e->used) { + if (e->tid == tid) + return e; + if (++pos == TABLESZ) + pos = 0; + e = &table[pos]; + } + + if (tid_cnt >= TABLEMAX) { + fprintf(stderr, "Too many threads\n"); + return NULL; + } + + tid_cnt += 1; + e->used = 1; + e->tid = tid; + return e; +} + +static void add_entry(__s32 tid, int pos, __u64 cnt) +{ + struct entry *e = find_entry(tid); + + if (e) + e->cycles[pos] += cnt; +} + +int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx) +{ + __s32 cpu = sample->cpu; + __s32 tid = sample->tid; + int pos; + + if (!sample->cyc_cnt) + return 0; + + pos = event_entry(sample->event); + + if (cpu >= 0 && cpu < MAX_CPU) + cycles[cpu][pos] += sample->cyc_cnt; + else if (tid != -1) + add_entry(tid, pos, sample->cyc_cnt); + return 0; +} + +static void print_vals(__u64 cycles, __u64 delta) +{ + if (delta) + printf("%10llu %10llu ", cycles, delta); + else + printf("%10llu %10s ", cycles, ""); +} + +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx) +{ + __s32 cpu = sample->cpu; + __s32 tid = sample->tid; + int pos; + + pos = event_entry(sample->event); + + if (cpu >= 0 && cpu < MAX_CPU) { + print_vals(cycles[cpu][pos], cycles[cpu][pos] - cycles_rpt[cpu][pos]); + cycles_rpt[cpu][pos] = cycles[cpu][pos]; + return 0; + } + + if (tid != -1) { + struct entry *e = find_entry(tid); + + if (e) { + print_vals(e->cycles[pos], e->cycles[pos] - e->cycles_rpt[pos]); + e->cycles_rpt[pos] = e->cycles[pos]; + return 0; + } + } + + printf("%22s", ""); + return 0; +} + +const char *filter_description(const char **long_description) +{ + static char *long_desc = "Cycle counts are accumulated per CPU (or " + "per thread if CPU is not recorded) from IPC information, and " + "printed together with the change since the last print, at the " + "start of each line. Separate counts are kept for branches, " + "instructions or other events."; + + *long_description = long_desc; + return "Print the number of cycles at the start of each line"; +} diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c index 7565a1852c74..b17eb52a0694 100644 --- a/tools/perf/dlfilters/dlfilter-test-api-v0.c +++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c @@ -308,8 +308,6 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx) { - struct filter_data *d = data; - pr_debug("%s API\n", __func__); return do_checks(data, sample, ctx, false); diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json index 9bea1ba1c4d2..cf48d0dfc759 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json @@ -18,6 +18,6 @@ "ArchStdEvent": "BUS_ACCESS_PERIPH" }, { - "ArchStdEvent": "BUS_ACCESS", + "ArchStdEvent": "BUS_ACCESS" } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json index 1e25f2ae4ae0..4cc50b7da526 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json @@ -39,31 +39,31 @@ "ArchStdEvent": "L2D_CACHE_INVAL" }, { - "ArchStdEvent": "L1I_CACHE_REFILL", + "ArchStdEvent": "L1I_CACHE_REFILL" }, { - "ArchStdEvent": "L1I_TLB_REFILL", + "ArchStdEvent": "L1I_TLB_REFILL" }, { - "ArchStdEvent": "L1D_CACHE_REFILL", + "ArchStdEvent": "L1D_CACHE_REFILL" }, { - "ArchStdEvent": "L1D_CACHE", + "ArchStdEvent": "L1D_CACHE" }, { - "ArchStdEvent": "L1D_TLB_REFILL", + "ArchStdEvent": "L1D_TLB_REFILL" }, { - "ArchStdEvent": "L1I_CACHE", + "ArchStdEvent": "L1I_CACHE" }, { - "ArchStdEvent": "L2D_CACHE", + "ArchStdEvent": "L2D_CACHE" }, { - "ArchStdEvent": "L2D_CACHE_REFILL", + "ArchStdEvent": "L2D_CACHE_REFILL" }, { - "ArchStdEvent": "L2D_CACHE_WB", + "ArchStdEvent": "L2D_CACHE_WB" }, { "PublicDescription": "This event counts any load or store operation which accesses the data L1 TLB", @@ -72,7 +72,7 @@ }, { "PublicDescription": "This event counts any instruction fetch which accesses the instruction L1 TLB", - "ArchStdEvent": "L1I_TLB", + "ArchStdEvent": "L1I_TLB" }, { "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json index 9076ca2daf9e..927a6f629a03 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json @@ -1,7 +1,7 @@ [ { "PublicDescription": "The number of core clock cycles", - "ArchStdEvent": "CPU_CYCLES", + "ArchStdEvent": "CPU_CYCLES" }, { "PublicDescription": "FSU clocking gated off cycle", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json index 9761433ad329..ada052e19632 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json @@ -36,9 +36,9 @@ "ArchStdEvent": "EXC_TRAP_FIQ" }, { - "ArchStdEvent": "EXC_TAKEN", + "ArchStdEvent": "EXC_TAKEN" }, { - "ArchStdEvent": "EXC_RETURN", + "ArchStdEvent": "EXC_RETURN" } ] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json index 482aa3f19e58..62f6276e3016 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json @@ -44,25 +44,25 @@ "BriefDescription": "Software increment" }, { - "ArchStdEvent": "INST_RETIRED", + "ArchStdEvent": "INST_RETIRED" }, { "ArchStdEvent": "CID_WRITE_RETIRED", "BriefDescription": "Write to CONTEXTIDR" }, { - "ArchStdEvent": "INST_SPEC", + "ArchStdEvent": "INST_SPEC" }, { - "ArchStdEvent": "TTBR_WRITE_RETIRED", + "ArchStdEvent": "TTBR_WRITE_RETIRED" }, { "PublicDescription": "This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches", - "ArchStdEvent": "BR_RETIRED", + "ArchStdEvent": "BR_RETIRED" }, { "PublicDescription": "This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush", - "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "ArchStdEvent": "BR_MIS_PRED_RETIRED" }, { "PublicDescription": "Operation speculatively executed, NOP", diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json index 2e7555696caf..50157e8c2005 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json @@ -15,10 +15,10 @@ "ArchStdEvent": "UNALIGNED_LDST_SPEC" }, { - "ArchStdEvent": "MEM_ACCESS", + "ArchStdEvent": "MEM_ACCESS" }, { "PublicDescription": "This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", - "ArchStdEvent": "MEMORY_ERROR", + "ArchStdEvent": "MEMORY_ERROR" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json index ec0dc92288ab..db68de188390 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json @@ -1,10 +1,10 @@ [ { "PublicDescription": "This event counts any predictable branch instruction which is mispredicted either due to dynamic misprediction or because the MMU is off and the branches are statically predicted not taken", - "ArchStdEvent": "BR_MIS_PRED", + "ArchStdEvent": "BR_MIS_PRED" }, { "PublicDescription": "This event counts all predictable branches.", - "ArchStdEvent": "BR_PRED", + "ArchStdEvent": "BR_PRED" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json index 6263929efce2..e0875d3a685d 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json @@ -1,21 +1,21 @@ [ { - "PublicDescription": "The number of core clock cycles" + "PublicDescription": "The number of core clock cycles", "ArchStdEvent": "CPU_CYCLES", "BriefDescription": "The number of core clock cycles." }, { "PublicDescription": "This event counts for every beat of data transferred over the data channels between the core and the SCU. If both read and write data beats are transferred on a given cycle, this event is counted twice on that cycle. This event counts the sum of BUS_ACCESS_RD and BUS_ACCESS_WR.", - "ArchStdEvent": "BUS_ACCESS", + "ArchStdEvent": "BUS_ACCESS" }, { - "PublicDescription": "This event duplicates CPU_CYCLES." - "ArchStdEvent": "BUS_CYCLES", + "PublicDescription": "This event duplicates CPU_CYCLES.", + "ArchStdEvent": "BUS_CYCLES" }, { - "ArchStdEvent": "BUS_ACCESS_RD", + "ArchStdEvent": "BUS_ACCESS_RD" }, { - "ArchStdEvent": "BUS_ACCESS_WR", + "ArchStdEvent": "BUS_ACCESS_WR" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json index cd67bb9df139..fc448c2d5ea4 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json @@ -1,47 +1,47 @@ [ { "PublicDescription": "This event counts any instruction fetch which misses in the cache.", - "ArchStdEvent": "L1I_CACHE_REFILL", + "ArchStdEvent": "L1I_CACHE_REFILL" }, { "PublicDescription": "This event counts any refill of the instruction L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", - "ArchStdEvent": "L1I_TLB_REFILL", + "ArchStdEvent": "L1I_TLB_REFILL" }, { "PublicDescription": "This event counts any load or store operation or page table walk access which causes data to be read from outside the L1, including accesses which do not allocate into L1.", - "ArchStdEvent": "L1D_CACHE_REFILL", + "ArchStdEvent": "L1D_CACHE_REFILL" }, { "PublicDescription": "This event counts any load or store operation or page table walk access which looks up in the L1 data cache. In particular, any access which could count the L1D_CACHE_REFILL event causes this event to count.", - "ArchStdEvent": "L1D_CACHE", + "ArchStdEvent": "L1D_CACHE" }, { "PublicDescription": "This event counts any refill of the data L1 TLB from the L2 TLB. This includes refills that result in a translation fault.", - "ArchStdEvent": "L1D_TLB_REFILL", + "ArchStdEvent": "L1D_TLB_REFILL" }, - {, + { "PublicDescription": "Level 1 instruction cache access or Level 0 Macro-op cache access. This event counts any instruction fetch which accesses the L1 instruction cache or L0 Macro-op cache.", - "ArchStdEvent": "L1I_CACHE", + "ArchStdEvent": "L1I_CACHE" }, { "PublicDescription": "This event counts any write-back of data from the L1 data cache to L2 or L3. This counts both victim line evictions and snoops, including cache maintenance operations.", - "ArchStdEvent": "L1D_CACHE_WB", + "ArchStdEvent": "L1D_CACHE_WB" }, { "PublicDescription": "This event counts any transaction from L1 which looks up in the L2 cache, and any write-back from the L1 to the L2. Snoops from outside the core and cache maintenance operations are not counted.", - "ArchStdEvent": "L2D_CACHE", + "ArchStdEvent": "L2D_CACHE" }, { "PublicDescription": "L2 data cache refill. This event counts any cacheable transaction from L1 which causes data to be read from outside the core. L2 refills caused by stashes into L2 should not be counted", - "ArchStdEvent": "L2D_CACHE_REFILL", + "ArchStdEvent": "L2D_CACHE_REFILL" }, { "PublicDescription": "This event counts any write-back of data from the L2 cache to outside the core. This includes snoops to the L2 which return data, regardless of whether they cause an invalidation. Invalidations from the L2 which do not write data outside of the core and snoops which return data from the L1 are not counted", - "ArchStdEvent": "L2D_CACHE_WB", + "ArchStdEvent": "L2D_CACHE_WB" }, { "PublicDescription": "This event counts any full cache line write into the L2 cache which does not cause a linefill, including write-backs from L1 to L2 and full-line writes which do not allocate into L1.", - "ArchStdEvent": "L2D_CACHE_ALLOCATE", + "ArchStdEvent": "L2D_CACHE_ALLOCATE" }, { "PublicDescription": "This event counts any load or store operation which accesses the data L1 TLB. If both a load and a store are executed on a cycle, this event counts twice. This event counts regardless of whether the MMU is enabled.", @@ -75,21 +75,21 @@ }, { "PublicDescription": "This event counts on any access to the L2 TLB (caused by a refill of any of the L1 TLBs). This event does not count if the MMU is disabled.", - "ArchStdEvent": "L2D_TLB", + "ArchStdEvent": "L2D_TLB" }, { "PublicDescription": "This event counts on any data access which causes L2D_TLB_REFILL to count.", - "ArchStdEvent": "DTLB_WALK", + "ArchStdEvent": "DTLB_WALK" }, { "PublicDescription": "This event counts on any instruction access which causes L2D_TLB_REFILL to count.", - "ArchStdEvent": "ITLB_WALK", + "ArchStdEvent": "ITLB_WALK" }, { - "ArchStdEvent": "LL_CACHE_RD", + "ArchStdEvent": "LL_CACHE_RD" }, { - "ArchStdEvent": "LL_CACHE_MISS_RD", + "ArchStdEvent": "LL_CACHE_MISS_RD" }, { "ArchStdEvent": "L1D_CACHE_INVAL" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json index ea4631db41b5..ce942324ee60 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json @@ -1,10 +1,10 @@ [ { - "ArchStdEvent": "EXC_TAKEN", + "ArchStdEvent": "EXC_TAKEN" }, { "PublicDescription": "This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs", - "ArchStdEvent": "MEMORY_ERROR", + "ArchStdEvent": "MEMORY_ERROR" }, { "ArchStdEvent": "EXC_DABORT" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json index 8e59566cba8b..b0b439a36ae9 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json @@ -1,32 +1,32 @@ [ { - "ArchStdEvent": "SW_INCR", + "ArchStdEvent": "SW_INCR" }, { "PublicDescription": "This event counts all retired instructions, including those that fail their condition check.", - "ArchStdEvent": "INST_RETIRED", + "ArchStdEvent": "INST_RETIRED" }, { - "ArchStdEvent": "EXC_RETURN", + "ArchStdEvent": "EXC_RETURN" }, { "PublicDescription": "This event only counts writes to CONTEXTIDR in AArch32 state, and via the CONTEXTIDR_EL1 mnemonic in AArch64 state.", - "ArchStdEvent": "CID_WRITE_RETIRED", + "ArchStdEvent": "CID_WRITE_RETIRED" }, { - "ArchStdEvent": "INST_SPEC", + "ArchStdEvent": "INST_SPEC" }, { "PublicDescription": "This event only counts writes to TTBR0/TTBR1 in AArch32 state and TTBR0_EL1/TTBR1_EL1 in AArch64 state.", - "ArchStdEvent": "TTBR_WRITE_RETIRED", + "ArchStdEvent": "TTBR_WRITE_RETIRED" }, - {, + { "PublicDescription": "This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches.", - "ArchStdEvent": "BR_RETIRED", + "ArchStdEvent": "BR_RETIRED" }, { "PublicDescription": "This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush.", - "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "ArchStdEvent": "BR_MIS_PRED_RETIRED" }, { "ArchStdEvent": "ASE_SPEC" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json index f06f399051c1..20a929e7728d 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json @@ -1,7 +1,7 @@ [ { "PublicDescription": "This event counts memory accesses due to load or store instructions. This event counts the sum of MEM_ACCESS_RD and MEM_ACCESS_WR.", - "ArchStdEvent": "MEM_ACCESS", + "ArchStdEvent": "MEM_ACCESS" }, { "ArchStdEvent": "MEM_ACCESS_RD" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json index c2ccbf6fbfa0..20d8365756c5 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/other.json @@ -1,5 +1,5 @@ [ { - "ArchStdEvent": "REMOTE_ACCESS", + "ArchStdEvent": "REMOTE_ACCESS" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json index d79f0aeaf7f1..b4e96551d51a 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json @@ -1,10 +1,10 @@ [ { "PublicDescription": "The counter counts on any cycle when there are no fetched instructions available to dispatch.", - "ArchStdEvent": "STALL_FRONTEND", + "ArchStdEvent": "STALL_FRONTEND" }, { "PublicDescription": "The counter counts on any cycle fetched instructions are not dispatched due to resource constraints.", - "ArchStdEvent": "STALL_BACKEND", + "ArchStdEvent": "STALL_BACKEND" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json new file mode 100644 index 000000000000..79f2016c53b0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json @@ -0,0 +1,8 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED" + }, + { + "ArchStdEvent": "BR_PRED" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json new file mode 100644 index 000000000000..579c1c993d17 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json @@ -0,0 +1,20 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS" + }, + { + "ArchStdEvent": "BUS_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS_RD" + }, + { + "ArchStdEvent": "BUS_ACCESS_WR" + }, + { + "ArchStdEvent": "CNT_CYCLES" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json new file mode 100644 index 000000000000..0141f749bff3 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json @@ -0,0 +1,155 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1I_TLB_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL" + }, + { + "ArchStdEvent": "L1I_CACHE" + }, + { + "ArchStdEvent": "L1D_CACHE_WB" + }, + { + "ArchStdEvent": "L2D_CACHE" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L2D_CACHE_WB" + }, + { + "ArchStdEvent": "L2D_CACHE_ALLOCATE" + }, + { + "ArchStdEvent": "L1D_TLB" + }, + { + "ArchStdEvent": "L1I_TLB" + }, + { + "ArchStdEvent": "L3D_CACHE_ALLOCATE" + }, + { + "ArchStdEvent": "L3D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L3D_CACHE" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL" + }, + { + "ArchStdEvent": "L2D_TLB" + }, + { + "ArchStdEvent": "DTLB_WALK" + }, + { + "ArchStdEvent": "ITLB_WALK" + }, + { + "ArchStdEvent": "LL_CACHE_RD" + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_TLB_RD" + }, + { + "ArchStdEvent": "L1D_TLB_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_TLB_RD" + }, + { + "ArchStdEvent": "L2D_TLB_WR" + }, + { + "ArchStdEvent": "L3D_CACHE_RD" + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS" + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json new file mode 100644 index 000000000000..344a2d552ad5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json @@ -0,0 +1,47 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN" + }, + { + "ArchStdEvent": "MEMORY_ERROR" + }, + { + "ArchStdEvent": "EXC_UNDEF" + }, + { + "ArchStdEvent": "EXC_SVC" + }, + { + "ArchStdEvent": "EXC_PABORT" + }, + { + "ArchStdEvent": "EXC_DABORT" + }, + { + "ArchStdEvent": "EXC_IRQ" + }, + { + "ArchStdEvent": "EXC_FIQ" + }, + { + "ArchStdEvent": "EXC_SMC" + }, + { + "ArchStdEvent": "EXC_HVC" + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER" + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ" + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json new file mode 100644 index 000000000000..e57cd55937c6 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json @@ -0,0 +1,143 @@ +[ + { + "ArchStdEvent": "SW_INCR" + }, + { + "ArchStdEvent": "INST_RETIRED" + }, + { + "ArchStdEvent": "EXC_RETURN" + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED" + }, + { + "ArchStdEvent": "INST_SPEC" + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED" + }, + { + "ArchStdEvent": "BR_RETIRED" + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED" + }, + { + "ArchStdEvent": "OP_RETIRED" + }, + { + "ArchStdEvent": "OP_SPEC" + }, + { + "ArchStdEvent": "LDREX_SPEC" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC" + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC" + }, + { + "ArchStdEvent": "STREX_SPEC" + }, + { + "ArchStdEvent": "LD_SPEC" + }, + { + "ArchStdEvent": "ST_SPEC" + }, + { + "ArchStdEvent": "DP_SPEC" + }, + { + "ArchStdEvent": "ASE_SPEC" + }, + { + "ArchStdEvent": "VFP_SPEC" + }, + { + "ArchStdEvent": "PC_WRITE_SPEC" + }, + { + "ArchStdEvent": "CRYPTO_SPEC" + }, + { + "ArchStdEvent": "BR_IMMED_SPEC" + }, + { + "ArchStdEvent": "BR_RETURN_SPEC" + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC" + }, + { + "ArchStdEvent": "ISB_SPEC" + }, + { + "ArchStdEvent": "DSB_SPEC" + }, + { + "ArchStdEvent": "DMB_SPEC" + }, + { + "ArchStdEvent": "RC_LD_SPEC" + }, + { + "ArchStdEvent": "RC_ST_SPEC" + }, + { + "ArchStdEvent": "ASE_INST_SPEC" + }, + { + "ArchStdEvent": "SVE_INST_SPEC" + }, + { + "ArchStdEvent": "FP_HP_SPEC" + }, + { + "ArchStdEvent": "FP_SP_SPEC" + }, + { + "ArchStdEvent": "FP_DP_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_EMPTY_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_FULL_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC" + }, + { + "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC" + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC" + }, + { + "ArchStdEvent": "SVE_LDFF_FAULT_SPEC" + }, + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC" + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT8_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT16_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT32_SPEC" + }, + { + "ArchStdEvent": "ASE_SVE_INT64_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json new file mode 100644 index 000000000000..e522113aeb96 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json @@ -0,0 +1,38 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS" + }, + { + "ArchStdEvent": "MEM_ACCESS_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_WR" + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC" + }, + { + "ArchStdEvent": "LDST_ALIGN_LAT" + }, + { + "ArchStdEvent": "LD_ALIGN_LAT" + }, + { + "ArchStdEvent": "ST_ALIGN_LAT" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_WR" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json new file mode 100644 index 000000000000..20d8365756c5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json @@ -0,0 +1,5 @@ +[ + { + "ArchStdEvent": "REMOTE_ACCESS" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json new file mode 100644 index 000000000000..f9fae15f7555 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json @@ -0,0 +1,23 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND" + }, + { + "ArchStdEvent": "STALL_BACKEND" + }, + { + "ArchStdEvent": "STALL" + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND" + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND" + }, + { + "ArchStdEvent": "STALL_SLOT" + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json new file mode 100644 index 000000000000..20f2165c85fe --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP" + }, + { + "ArchStdEvent": "SAMPLE_FEED" + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE" + }, + { + "ArchStdEvent": "SAMPLE_COLLISION" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json new file mode 100644 index 000000000000..3116135c59e2 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json @@ -0,0 +1,29 @@ +[ + { + "ArchStdEvent": "TRB_WRAP" + }, + { + "ArchStdEvent": "TRCEXTOUT0" + }, + { + "ArchStdEvent": "TRCEXTOUT1" + }, + { + "ArchStdEvent": "TRCEXTOUT2" + }, + { + "ArchStdEvent": "TRCEXTOUT3" + }, + { + "ArchStdEvent": "CTI_TRIGOUT4" + }, + { + "ArchStdEvent": "CTI_TRIGOUT5" + }, + { + "ArchStdEvent": "CTI_TRIGOUT6" + }, + { + "ArchStdEvent": "CTI_TRIGOUT7" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/branch.json new file mode 100644 index 000000000000..79f2016c53b0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/branch.json @@ -0,0 +1,8 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED" + }, + { + "ArchStdEvent": "BR_PRED" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/bus.json new file mode 100644 index 000000000000..579c1c993d17 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/bus.json @@ -0,0 +1,20 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS" + }, + { + "ArchStdEvent": "BUS_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS_RD" + }, + { + "ArchStdEvent": "BUS_ACCESS_WR" + }, + { + "ArchStdEvent": "CNT_CYCLES" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/cache.json new file mode 100644 index 000000000000..0141f749bff3 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/cache.json @@ -0,0 +1,155 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1I_TLB_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL" + }, + { + "ArchStdEvent": "L1I_CACHE" + }, + { + "ArchStdEvent": "L1D_CACHE_WB" + }, + { + "ArchStdEvent": "L2D_CACHE" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L2D_CACHE_WB" + }, + { + "ArchStdEvent": "L2D_CACHE_ALLOCATE" + }, + { + "ArchStdEvent": "L1D_TLB" + }, + { + "ArchStdEvent": "L1I_TLB" + }, + { + "ArchStdEvent": "L3D_CACHE_ALLOCATE" + }, + { + "ArchStdEvent": "L3D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L3D_CACHE" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL" + }, + { + "ArchStdEvent": "L2D_TLB" + }, + { + "ArchStdEvent": "DTLB_WALK" + }, + { + "ArchStdEvent": "ITLB_WALK" + }, + { + "ArchStdEvent": "LL_CACHE_RD" + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_TLB_RD" + }, + { + "ArchStdEvent": "L1D_TLB_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_TLB_RD" + }, + { + "ArchStdEvent": "L2D_TLB_WR" + }, + { + "ArchStdEvent": "L3D_CACHE_RD" + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS" + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/exception.json new file mode 100644 index 000000000000..344a2d552ad5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/exception.json @@ -0,0 +1,47 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN" + }, + { + "ArchStdEvent": "MEMORY_ERROR" + }, + { + "ArchStdEvent": "EXC_UNDEF" + }, + { + "ArchStdEvent": "EXC_SVC" + }, + { + "ArchStdEvent": "EXC_PABORT" + }, + { + "ArchStdEvent": "EXC_DABORT" + }, + { + "ArchStdEvent": "EXC_IRQ" + }, + { + "ArchStdEvent": "EXC_FIQ" + }, + { + "ArchStdEvent": "EXC_SMC" + }, + { + "ArchStdEvent": "EXC_HVC" + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER" + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ" + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/instruction.json new file mode 100644 index 000000000000..25825e14c535 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/instruction.json @@ -0,0 +1,89 @@ +[ + { + "ArchStdEvent": "SW_INCR" + }, + { + "ArchStdEvent": "INST_RETIRED" + }, + { + "ArchStdEvent": "EXC_RETURN" + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED" + }, + { + "ArchStdEvent": "INST_SPEC" + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED" + }, + { + "ArchStdEvent": "BR_RETIRED" + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED" + }, + { + "ArchStdEvent": "OP_RETIRED" + }, + { + "ArchStdEvent": "OP_SPEC" + }, + { + "ArchStdEvent": "LDREX_SPEC" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC" + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC" + }, + { + "ArchStdEvent": "STREX_SPEC" + }, + { + "ArchStdEvent": "LD_SPEC" + }, + { + "ArchStdEvent": "ST_SPEC" + }, + { + "ArchStdEvent": "DP_SPEC" + }, + { + "ArchStdEvent": "ASE_SPEC" + }, + { + "ArchStdEvent": "VFP_SPEC" + }, + { + "ArchStdEvent": "PC_WRITE_SPEC" + }, + { + "ArchStdEvent": "CRYPTO_SPEC" + }, + { + "ArchStdEvent": "BR_IMMED_SPEC" + }, + { + "ArchStdEvent": "BR_RETURN_SPEC" + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC" + }, + { + "ArchStdEvent": "ISB_SPEC" + }, + { + "ArchStdEvent": "DSB_SPEC" + }, + { + "ArchStdEvent": "DMB_SPEC" + }, + { + "ArchStdEvent": "RC_LD_SPEC" + }, + { + "ArchStdEvent": "RC_ST_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/memory.json new file mode 100644 index 000000000000..e3d08f1f7c92 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/memory.json @@ -0,0 +1,20 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS" + }, + { + "ArchStdEvent": "MEM_ACCESS_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_WR" + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/other.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/other.json new file mode 100644 index 000000000000..20d8365756c5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/other.json @@ -0,0 +1,5 @@ +[ + { + "ArchStdEvent": "REMOTE_ACCESS" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/pipeline.json new file mode 100644 index 000000000000..f9fae15f7555 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/pipeline.json @@ -0,0 +1,23 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND" + }, + { + "ArchStdEvent": "STALL_BACKEND" + }, + { + "ArchStdEvent": "STALL" + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND" + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND" + }, + { + "ArchStdEvent": "STALL_SLOT" + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json deleted file mode 100644 index 913fb200ea52..000000000000 --- a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json +++ /dev/null @@ -1,476 +0,0 @@ -[ - { - "PublicDescription": "Instruction architecturally executed, Condition code check pass, software increment", - "EventCode": "0x00", - "EventName": "SW_INCR", - "BriefDescription": "Instruction architecturally executed, Condition code check pass, software increment" - }, - { - "PublicDescription": "Level 1 instruction cache refill", - "EventCode": "0x01", - "EventName": "L1I_CACHE_REFILL", - "BriefDescription": "Level 1 instruction cache refill" - }, - { - "PublicDescription": "Attributable Level 1 instruction TLB refill", - "EventCode": "0x02", - "EventName": "L1I_TLB_REFILL", - "BriefDescription": "Attributable Level 1 instruction TLB refill" - }, - { - "PublicDescription": "Level 1 data cache refill", - "EventCode": "0x03", - "EventName": "L1D_CACHE_REFILL", - "BriefDescription": "Level 1 data cache refill" - }, - { - "PublicDescription": "Level 1 data cache access", - "EventCode": "0x04", - "EventName": "L1D_CACHE", - "BriefDescription": "Level 1 data cache access" - }, - { - "PublicDescription": "Attributable Level 1 data TLB refill", - "EventCode": "0x05", - "EventName": "L1D_TLB_REFILL", - "BriefDescription": "Attributable Level 1 data TLB refill" - }, - { - "PublicDescription": "Instruction architecturally executed", - "EventCode": "0x08", - "EventName": "INST_RETIRED", - "BriefDescription": "Instruction architecturally executed" - }, - { - "PublicDescription": "Exception taken", - "EventCode": "0x09", - "EventName": "EXC_TAKEN", - "BriefDescription": "Exception taken" - }, - { - "PublicDescription": "Instruction architecturally executed, condition check pass, exception return", - "EventCode": "0x0a", - "EventName": "EXC_RETURN", - "BriefDescription": "Instruction architecturally executed, condition check pass, exception return" - }, - { - "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR", - "EventCode": "0x0b", - "EventName": "CID_WRITE_RETIRED", - "BriefDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR" - }, - { - "PublicDescription": "Mispredicted or not predicted branch speculatively executed", - "EventCode": "0x10", - "EventName": "BR_MIS_PRED", - "BriefDescription": "Mispredicted or not predicted branch speculatively executed" - }, - { - "PublicDescription": "Cycle", - "EventCode": "0x11", - "EventName": "CPU_CYCLES", - "BriefDescription": "Cycle" - }, - { - "PublicDescription": "Predictable branch speculatively executed", - "EventCode": "0x12", - "EventName": "BR_PRED", - "BriefDescription": "Predictable branch speculatively executed" - }, - { - "PublicDescription": "Data memory access", - "EventCode": "0x13", - "EventName": "MEM_ACCESS", - "BriefDescription": "Data memory access" - }, - { - "PublicDescription": "Attributable Level 1 instruction cache access", - "EventCode": "0x14", - "EventName": "L1I_CACHE", - "BriefDescription": "Attributable Level 1 instruction cache access" - }, - { - "PublicDescription": "Attributable Level 1 data cache write-back", - "EventCode": "0x15", - "EventName": "L1D_CACHE_WB", - "BriefDescription": "Attributable Level 1 data cache write-back" - }, - { - "PublicDescription": "Level 2 data cache access", - "EventCode": "0x16", - "EventName": "L2D_CACHE", - "BriefDescription": "Level 2 data cache access" - }, - { - "PublicDescription": "Level 2 data refill", - "EventCode": "0x17", - "EventName": "L2D_CACHE_REFILL", - "BriefDescription": "Level 2 data refill" - }, - { - "PublicDescription": "Attributable Level 2 data cache write-back", - "EventCode": "0x18", - "EventName": "L2D_CACHE_WB", - "BriefDescription": "Attributable Level 2 data cache write-back" - }, - { - "PublicDescription": "Attributable Bus access", - "EventCode": "0x19", - "EventName": "BUS_ACCESS", - "BriefDescription": "Attributable Bus access" - }, - { - "PublicDescription": "Local memory error", - "EventCode": "0x1a", - "EventName": "MEMORY_ERROR", - "BriefDescription": "Local memory error" - }, - { - "PublicDescription": "Operation speculatively executed", - "EventCode": "0x1b", - "EventName": "INST_SPEC", - "BriefDescription": "Operation speculatively executed" - }, - { - "PublicDescription": "Instruction architecturally executed, Condition code check pass, write to TTBR", - "EventCode": "0x1c", - "EventName": "TTBR_WRITE_RETIRED", - "BriefDescription": "Instruction architecturally executed, Condition code check pass, write to TTBR" - }, - { - "PublicDescription": "Bus cycle", - "EventCode": "0x1D", - "EventName": "BUS_CYCLES", - "BriefDescription": "Bus cycle" - }, - { - "PublicDescription": "Attributable Level 2 data cache allocation without refill", - "EventCode": "0x20", - "EventName": "L2D_CACHE_ALLOCATE", - "BriefDescription": "Attributable Level 2 data cache allocation without refill" - }, - { - "PublicDescription": "Instruction architecturally executed, branch", - "EventCode": "0x21", - "EventName": "BR_RETIRED", - "BriefDescription": "Instruction architecturally executed, branch" - }, - { - "PublicDescription": "Instruction architecturally executed, mispredicted branch", - "EventCode": "0x22", - "EventName": "BR_MIS_PRED_RETIRED", - "BriefDescription": "Instruction architecturally executed, mispredicted branch" - }, - { - "PublicDescription": "No operation issued because of the frontend", - "EventCode": "0x23", - "EventName": "STALL_FRONTEND", - "BriefDescription": "No operation issued because of the frontend" - }, - { - "PublicDescription": "No operation issued due to the backend", - "EventCode": "0x24", - "EventName": "STALL_BACKEND", - "BriefDescription": "No operation issued due to the backend" - }, - { - "PublicDescription": "Attributable Level 1 data or unified TLB access", - "EventCode": "0x25", - "EventName": "L1D_TLB", - "BriefDescription": "Attributable Level 1 data or unified TLB access" - }, - { - "PublicDescription": "Attributable Level 1 instruction TLB access", - "EventCode": "0x26", - "EventName": "L1I_TLB", - "BriefDescription": "Attributable Level 1 instruction TLB access" - }, - { - "PublicDescription": "Attributable Level 3 data cache allocation without refill", - "EventCode": "0x29", - "EventName": "L3D_CACHE_ALLOCATE", - "BriefDescription": "Attributable Level 3 data cache allocation without refill" - }, - { - "PublicDescription": "Attributable Level 3 data cache refill", - "EventCode": "0x2A", - "EventName": "L3D_CACHE_REFILL", - "BriefDescription": "Attributable Level 3 data cache refill" - }, - { - "PublicDescription": "Attributable Level 3 data cache access", - "EventCode": "0x2B", - "EventName": "L3D_CACHE", - "BriefDescription": "Attributable Level 3 data cache access" - }, - { - "PublicDescription": "Attributable Level 2 data TLB refill", - "EventCode": "0x2D", - "EventName": "L2D_TLB_REFILL", - "BriefDescription": "Attributable Level 2 data TLB refill" - }, - { - "PublicDescription": "Attributable Level 2 instruction TLB refill.", - "EventCode": "0x2E", - "EventName": "L2I_TLB_REFILL", - "BriefDescription": "Attributable Level 2 instruction TLB refill." - }, - { - "PublicDescription": "Attributable Level 2 data or unified TLB access", - "EventCode": "0x2F", - "EventName": "L2D_TLB", - "BriefDescription": "Attributable Level 2 data or unified TLB access" - }, - { - "PublicDescription": "Attributable Level 2 instruction TLB access.", - "EventCode": "0x30", - "EventName": "L2I_TLB", - "BriefDescription": "Attributable Level 2 instruction TLB access." - }, - { - "PublicDescription": "Access to another socket in a multi-socket system", - "EventCode": "0x31", - "EventName": "REMOTE_ACCESS", - "BriefDescription": "Access to another socket in a multi-socket system" - }, - { - "PublicDescription": "Access to data TLB causes a translation table walk", - "EventCode": "0x34", - "EventName": "DTLB_WALK", - "BriefDescription": "Access to data TLB causes a translation table walk" - }, - { - "PublicDescription": "Access to instruction TLB that causes a translation table walk", - "EventCode": "0x35", - "EventName": "ITLB_WALK", - "BriefDescription": "Access to instruction TLB that causes a translation table walk" - }, - { - "PublicDescription": "Attributable Last level cache memory read", - "EventCode": "0x36", - "EventName": "LL_CACHE_RD", - "BriefDescription": "Attributable Last level cache memory read" - }, - { - "PublicDescription": "Last level cache miss, read", - "EventCode": "0x37", - "EventName": "LL_CACHE_MISS_RD", - "BriefDescription": "Last level cache miss, read" - }, - { - "PublicDescription": "SIMD Instruction architecturally executed.", - "EventCode": "0x8000", - "EventName": "SIMD_INST_RETIRED", - "BriefDescription": "SIMD Instruction architecturally executed." - }, - { - "PublicDescription": "Instruction architecturally executed, SVE.", - "EventCode": "0x8002", - "EventName": "SVE_INST_RETIRED", - "BriefDescription": "Instruction architecturally executed, SVE." - }, - { - "PublicDescription": "Microarchitectural operation, Operations speculatively executed.", - "EventCode": "0x8008", - "EventName": "UOP_SPEC", - "BriefDescription": "Microarchitectural operation, Operations speculatively executed." - }, - { - "PublicDescription": "SVE Math accelerator Operations speculatively executed.", - "EventCode": "0x800E", - "EventName": "SVE_MATH_SPEC", - "BriefDescription": "SVE Math accelerator Operations speculatively executed." - }, - { - "PublicDescription": "Floating-point Operations speculatively executed.", - "EventCode": "0x8010", - "EventName": "FP_SPEC", - "BriefDescription": "Floating-point Operations speculatively executed." - }, - { - "PublicDescription": "Floating-point FMA Operations speculatively executed.", - "EventCode": "0x8028", - "EventName": "FP_FMA_SPEC", - "BriefDescription": "Floating-point FMA Operations speculatively executed." - }, - { - "PublicDescription": "Floating-point reciprocal estimate Operations speculatively executed.", - "EventCode": "0x8034", - "EventName": "FP_RECPE_SPEC", - "BriefDescription": "Floating-point reciprocal estimate Operations speculatively executed." - }, - { - "PublicDescription": "floating-point convert Operations speculatively executed.", - "EventCode": "0x8038", - "EventName": "FP_CVT_SPEC", - "BriefDescription": "floating-point convert Operations speculatively executed." - }, - { - "PublicDescription": "Advanced SIMD and SVE integer Operations speculatively executed.", - "EventCode": "0x8043", - "EventName": "ASE_SVE_INT_SPEC", - "BriefDescription": "Advanced SIMD and SVE integer Operations speculatively executed." - }, - { - "PublicDescription": "SVE predicated Operations speculatively executed.", - "EventCode": "0x8074", - "EventName": "SVE_PRED_SPEC", - "BriefDescription": "SVE predicated Operations speculatively executed." - }, - { - "PublicDescription": "SVE MOVPRFX Operations speculatively executed.", - "EventCode": "0x807C", - "EventName": "SVE_MOVPRFX_SPEC", - "BriefDescription": "SVE MOVPRFX Operations speculatively executed." - }, - { - "PublicDescription": "SVE MOVPRFX unfused Operations speculatively executed.", - "EventCode": "0x807F", - "EventName": "SVE_MOVPRFX_U_SPEC", - "BriefDescription": "SVE MOVPRFX unfused Operations speculatively executed." - }, - { - "PublicDescription": "Advanced SIMD and SVE load Operations speculatively executed.", - "EventCode": "0x8085", - "EventName": "ASE_SVE_LD_SPEC", - "BriefDescription": "Advanced SIMD and SVE load Operations speculatively executed." - }, - { - "PublicDescription": "Advanced SIMD and SVE store Operations speculatively executed.", - "EventCode": "0x8086", - "EventName": "ASE_SVE_ST_SPEC", - "BriefDescription": "Advanced SIMD and SVE store Operations speculatively executed." - }, - { - "PublicDescription": "Prefetch Operations speculatively executed.", - "EventCode": "0x8087", - "EventName": "PRF_SPEC", - "BriefDescription": "Prefetch Operations speculatively executed." - }, - { - "PublicDescription": "General-purpose register load Operations speculatively executed.", - "EventCode": "0x8089", - "EventName": "BASE_LD_REG_SPEC", - "BriefDescription": "General-purpose register load Operations speculatively executed." - }, - { - "PublicDescription": "General-purpose register store Operations speculatively executed.", - "EventCode": "0x808A", - "EventName": "BASE_ST_REG_SPEC", - "BriefDescription": "General-purpose register store Operations speculatively executed." - }, - { - "PublicDescription": "SVE unpredicated load register Operations speculatively executed.", - "EventCode": "0x8091", - "EventName": "SVE_LDR_REG_SPEC", - "BriefDescription": "SVE unpredicated load register Operations speculatively executed." - }, - { - "PublicDescription": "SVE unpredicated store register Operations speculatively executed.", - "EventCode": "0x8092", - "EventName": "SVE_STR_REG_SPEC", - "BriefDescription": "SVE unpredicated store register Operations speculatively executed." - }, - { - "PublicDescription": "SVE load predicate register Operations speculatively executed.", - "EventCode": "0x8095", - "EventName": "SVE_LDR_PREG_SPEC", - "BriefDescription": "SVE load predicate register Operations speculatively executed." - }, - { - "PublicDescription": "SVE store predicate register Operations speculatively executed.", - "EventCode": "0x8096", - "EventName": "SVE_STR_PREG_SPEC", - "BriefDescription": "SVE store predicate register Operations speculatively executed." - }, - { - "PublicDescription": "SVE contiguous prefetch element Operations speculatively executed.", - "EventCode": "0x809F", - "EventName": "SVE_PRF_CONTIG_SPEC", - "BriefDescription": "SVE contiguous prefetch element Operations speculatively executed." - }, - { - "PublicDescription": "Advanced SIMD and SVE contiguous load multiple vector Operations speculatively executed.", - "EventCode": "0x80A5", - "EventName": "ASE_SVE_LD_MULTI_SPEC", - "BriefDescription": "Advanced SIMD and SVE contiguous load multiple vector Operations speculatively executed." - }, - { - "PublicDescription": "Advanced SIMD and SVE contiguous store multiple vector Operations speculatively executed.", - "EventCode": "0x80A6", - "EventName": "ASE_SVE_ST_MULTI_SPEC", - "BriefDescription": "Advanced SIMD and SVE contiguous store multiple vector Operations speculatively executed." - }, - { - "PublicDescription": "SVE gather-load Operations speculatively executed.", - "EventCode": "0x80AD", - "EventName": "SVE_LD_GATHER_SPEC", - "BriefDescription": "SVE gather-load Operations speculatively executed." - }, - { - "PublicDescription": "SVE scatter-store Operations speculatively executed.", - "EventCode": "0x80AE", - "EventName": "SVE_ST_SCATTER_SPEC", - "BriefDescription": "SVE scatter-store Operations speculatively executed." - }, - { - "PublicDescription": "SVE gather-prefetch Operations speculatively executed.", - "EventCode": "0x80AF", - "EventName": "SVE_PRF_GATHER_SPEC", - "BriefDescription": "SVE gather-prefetch Operations speculatively executed." - }, - { - "PublicDescription": "SVE First-fault load Operations speculatively executed.", - "EventCode": "0x80BC", - "EventName": "SVE_LDFF_SPEC", - "BriefDescription": "SVE First-fault load Operations speculatively executed." - }, - { - "PublicDescription": "Scalable floating-point element Operations speculatively executed.", - "EventCode": "0x80C0", - "EventName": "FP_SCALE_OPS_SPEC", - "BriefDescription": "Scalable floating-point element Operations speculatively executed." - }, - { - "PublicDescription": "Non-scalable floating-point element Operations speculatively executed.", - "EventCode": "0x80C1", - "EventName": "FP_FIXED_OPS_SPEC", - "BriefDescription": "Non-scalable floating-point element Operations speculatively executed." - }, - { - "PublicDescription": "Scalable half-precision floating-point element Operations speculatively executed.", - "EventCode": "0x80C2", - "EventName": "FP_HP_SCALE_OPS_SPEC", - "BriefDescription": "Scalable half-precision floating-point element Operations speculatively executed." - }, - { - "PublicDescription": "Non-scalable half-precision floating-point element Operations speculatively executed.", - "EventCode": "0x80C3", - "EventName": "FP_HP_FIXED_OPS_SPEC", - "BriefDescription": "Non-scalable half-precision floating-point element Operations speculatively executed." - }, - { - "PublicDescription": "Scalable single-precision floating-point element Operations speculatively executed.", - "EventCode": "0x80C4", - "EventName": "FP_SP_SCALE_OPS_SPEC", - "BriefDescription": "Scalable single-precision floating-point element Operations speculatively executed." - }, - { - "PublicDescription": "Non-scalable single-precision floating-point element Operations speculatively executed.", - "EventCode": "0x80C5", - "EventName": "FP_SP_FIXED_OPS_SPEC", - "BriefDescription": "Non-scalable single-precision floating-point element Operations speculatively executed." - }, - { - "PublicDescription": "Scalable double-precision floating-point element Operations speculatively executed.", - "EventCode": "0x80C6", - "EventName": "FP_DP_SCALE_OPS_SPEC", - "BriefDescription": "Scalable double-precision floating-point element Operations speculatively executed." - }, - { - "PublicDescription": "Non-scalable double-precision floating-point element Operations speculatively executed.", - "EventCode": "0x80C7", - "EventName": "FP_DP_FIXED_OPS_SPEC", - "BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed." - } -] diff --git a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json b/tools/perf/pmu-events/arch/arm64/armv8-recommended.json deleted file mode 100644 index d0a19866563d..000000000000 --- a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json +++ /dev/null @@ -1,452 +0,0 @@ -[ - { - "PublicDescription": "Attributable Level 1 data cache access, read", - "EventCode": "0x40", - "EventName": "L1D_CACHE_RD", - "BriefDescription": "L1D cache access, read" - }, - { - "PublicDescription": "Attributable Level 1 data cache access, write", - "EventCode": "0x41", - "EventName": "L1D_CACHE_WR", - "BriefDescription": "L1D cache access, write" - }, - { - "PublicDescription": "Attributable Level 1 data cache refill, read", - "EventCode": "0x42", - "EventName": "L1D_CACHE_REFILL_RD", - "BriefDescription": "L1D cache refill, read" - }, - { - "PublicDescription": "Attributable Level 1 data cache refill, write", - "EventCode": "0x43", - "EventName": "L1D_CACHE_REFILL_WR", - "BriefDescription": "L1D cache refill, write" - }, - { - "PublicDescription": "Attributable Level 1 data cache refill, inner", - "EventCode": "0x44", - "EventName": "L1D_CACHE_REFILL_INNER", - "BriefDescription": "L1D cache refill, inner" - }, - { - "PublicDescription": "Attributable Level 1 data cache refill, outer", - "EventCode": "0x45", - "EventName": "L1D_CACHE_REFILL_OUTER", - "BriefDescription": "L1D cache refill, outer" - }, - { - "PublicDescription": "Attributable Level 1 data cache Write-Back, victim", - "EventCode": "0x46", - "EventName": "L1D_CACHE_WB_VICTIM", - "BriefDescription": "L1D cache Write-Back, victim" - }, - { - "PublicDescription": "Level 1 data cache Write-Back, cleaning and coherency", - "EventCode": "0x47", - "EventName": "L1D_CACHE_WB_CLEAN", - "BriefDescription": "L1D cache Write-Back, cleaning and coherency" - }, - { - "PublicDescription": "Attributable Level 1 data cache invalidate", - "EventCode": "0x48", - "EventName": "L1D_CACHE_INVAL", - "BriefDescription": "L1D cache invalidate" - }, - { - "PublicDescription": "Attributable Level 1 data TLB refill, read", - "EventCode": "0x4C", - "EventName": "L1D_TLB_REFILL_RD", - "BriefDescription": "L1D tlb refill, read" - }, - { - "PublicDescription": "Attributable Level 1 data TLB refill, write", - "EventCode": "0x4D", - "EventName": "L1D_TLB_REFILL_WR", - "BriefDescription": "L1D tlb refill, write" - }, - { - "PublicDescription": "Attributable Level 1 data or unified TLB access, read", - "EventCode": "0x4E", - "EventName": "L1D_TLB_RD", - "BriefDescription": "L1D tlb access, read" - }, - { - "PublicDescription": "Attributable Level 1 data or unified TLB access, write", - "EventCode": "0x4F", - "EventName": "L1D_TLB_WR", - "BriefDescription": "L1D tlb access, write" - }, - { - "PublicDescription": "Attributable Level 2 data cache access, read", - "EventCode": "0x50", - "EventName": "L2D_CACHE_RD", - "BriefDescription": "L2D cache access, read" - }, - { - "PublicDescription": "Attributable Level 2 data cache access, write", - "EventCode": "0x51", - "EventName": "L2D_CACHE_WR", - "BriefDescription": "L2D cache access, write" - }, - { - "PublicDescription": "Attributable Level 2 data cache refill, read", - "EventCode": "0x52", - "EventName": "L2D_CACHE_REFILL_RD", - "BriefDescription": "L2D cache refill, read" - }, - { - "PublicDescription": "Attributable Level 2 data cache refill, write", - "EventCode": "0x53", - "EventName": "L2D_CACHE_REFILL_WR", - "BriefDescription": "L2D cache refill, write" - }, - { - "PublicDescription": "Attributable Level 2 data cache Write-Back, victim", - "EventCode": "0x56", - "EventName": "L2D_CACHE_WB_VICTIM", - "BriefDescription": "L2D cache Write-Back, victim" - }, - { - "PublicDescription": "Level 2 data cache Write-Back, cleaning and coherency", - "EventCode": "0x57", - "EventName": "L2D_CACHE_WB_CLEAN", - "BriefDescription": "L2D cache Write-Back, cleaning and coherency" - }, - { - "PublicDescription": "Attributable Level 2 data cache invalidate", - "EventCode": "0x58", - "EventName": "L2D_CACHE_INVAL", - "BriefDescription": "L2D cache invalidate" - }, - { - "PublicDescription": "Attributable Level 2 data or unified TLB refill, read", - "EventCode": "0x5c", - "EventName": "L2D_TLB_REFILL_RD", - "BriefDescription": "L2D cache refill, read" - }, - { - "PublicDescription": "Attributable Level 2 data or unified TLB refill, write", - "EventCode": "0x5d", - "EventName": "L2D_TLB_REFILL_WR", - "BriefDescription": "L2D cache refill, write" - }, - { - "PublicDescription": "Attributable Level 2 data or unified TLB access, read", - "EventCode": "0x5e", - "EventName": "L2D_TLB_RD", - "BriefDescription": "L2D cache access, read" - }, - { - "PublicDescription": "Attributable Level 2 data or unified TLB access, write", - "EventCode": "0x5f", - "EventName": "L2D_TLB_WR", - "BriefDescription": "L2D cache access, write" - }, - { - "PublicDescription": "Bus access read", - "EventCode": "0x60", - "EventName": "BUS_ACCESS_RD", - "BriefDescription": "Bus access read" - }, - { - "PublicDescription": "Bus access write", - "EventCode": "0x61", - "EventName": "BUS_ACCESS_WR", - "BriefDescription": "Bus access write" - }, - { - "PublicDescription": "Bus access, Normal, Cacheable, Shareable", - "EventCode": "0x62", - "EventName": "BUS_ACCESS_SHARED", - "BriefDescription": "Bus access, Normal, Cacheable, Shareable" - }, - { - "PublicDescription": "Bus access, not Normal, Cacheable, Shareable", - "EventCode": "0x63", - "EventName": "BUS_ACCESS_NOT_SHARED", - "BriefDescription": "Bus access, not Normal, Cacheable, Shareable" - }, - { - "PublicDescription": "Bus access, Normal", - "EventCode": "0x64", - "EventName": "BUS_ACCESS_NORMAL", - "BriefDescription": "Bus access, Normal" - }, - { - "PublicDescription": "Bus access, peripheral", - "EventCode": "0x65", - "EventName": "BUS_ACCESS_PERIPH", - "BriefDescription": "Bus access, peripheral" - }, - { - "PublicDescription": "Data memory access, read", - "EventCode": "0x66", - "EventName": "MEM_ACCESS_RD", - "BriefDescription": "Data memory access, read" - }, - { - "PublicDescription": "Data memory access, write", - "EventCode": "0x67", - "EventName": "MEM_ACCESS_WR", - "BriefDescription": "Data memory access, write" - }, - { - "PublicDescription": "Unaligned access, read", - "EventCode": "0x68", - "EventName": "UNALIGNED_LD_SPEC", - "BriefDescription": "Unaligned access, read" - }, - { - "PublicDescription": "Unaligned access, write", - "EventCode": "0x69", - "EventName": "UNALIGNED_ST_SPEC", - "BriefDescription": "Unaligned access, write" - }, - { - "PublicDescription": "Unaligned access", - "EventCode": "0x6a", - "EventName": "UNALIGNED_LDST_SPEC", - "BriefDescription": "Unaligned access" - }, - { - "PublicDescription": "Exclusive operation speculatively executed, LDREX or LDX", - "EventCode": "0x6c", - "EventName": "LDREX_SPEC", - "BriefDescription": "Exclusive operation speculatively executed, LDREX or LDX" - }, - { - "PublicDescription": "Exclusive operation speculatively executed, STREX or STX pass", - "EventCode": "0x6d", - "EventName": "STREX_PASS_SPEC", - "BriefDescription": "Exclusive operation speculatively executed, STREX or STX pass" - }, - { - "PublicDescription": "Exclusive operation speculatively executed, STREX or STX fail", - "EventCode": "0x6e", - "EventName": "STREX_FAIL_SPEC", - "BriefDescription": "Exclusive operation speculatively executed, STREX or STX fail" - }, - { - "PublicDescription": "Exclusive operation speculatively executed, STREX or STX", - "EventCode": "0x6f", - "EventName": "STREX_SPEC", - "BriefDescription": "Exclusive operation speculatively executed, STREX or STX" - }, - { - "PublicDescription": "Operation speculatively executed, load", - "EventCode": "0x70", - "EventName": "LD_SPEC", - "BriefDescription": "Operation speculatively executed, load" - }, - { - "PublicDescription": "Operation speculatively executed, store", - "EventCode": "0x71", - "EventName": "ST_SPEC", - "BriefDescription": "Operation speculatively executed, store" - }, - { - "PublicDescription": "Operation speculatively executed, load or store", - "EventCode": "0x72", - "EventName": "LDST_SPEC", - "BriefDescription": "Operation speculatively executed, load or store" - }, - { - "PublicDescription": "Operation speculatively executed, integer data processing", - "EventCode": "0x73", - "EventName": "DP_SPEC", - "BriefDescription": "Operation speculatively executed, integer data processing" - }, - { - "PublicDescription": "Operation speculatively executed, Advanced SIMD instruction", - "EventCode": "0x74", - "EventName": "ASE_SPEC", - "BriefDescription": "Operation speculatively executed, Advanced SIMD instruction" - }, - { - "PublicDescription": "Operation speculatively executed, floating-point instruction", - "EventCode": "0x75", - "EventName": "VFP_SPEC", - "BriefDescription": "Operation speculatively executed, floating-point instruction" - }, - { - "PublicDescription": "Operation speculatively executed, software change of the PC", - "EventCode": "0x76", - "EventName": "PC_WRITE_SPEC", - "BriefDescription": "Operation speculatively executed, software change of the PC" - }, - { - "PublicDescription": "Operation speculatively executed, Cryptographic instruction", - "EventCode": "0x77", - "EventName": "CRYPTO_SPEC", - "BriefDescription": "Operation speculatively executed, Cryptographic instruction" - }, - { - "PublicDescription": "Branch speculatively executed, immediate branch", - "EventCode": "0x78", - "EventName": "BR_IMMED_SPEC", - "BriefDescription": "Branch speculatively executed, immediate branch" - }, - { - "PublicDescription": "Branch speculatively executed, procedure return", - "EventCode": "0x79", - "EventName": "BR_RETURN_SPEC", - "BriefDescription": "Branch speculatively executed, procedure return" - }, - { - "PublicDescription": "Branch speculatively executed, indirect branch", - "EventCode": "0x7a", - "EventName": "BR_INDIRECT_SPEC", - "BriefDescription": "Branch speculatively executed, indirect branch" - }, - { - "PublicDescription": "Barrier speculatively executed, ISB", - "EventCode": "0x7c", - "EventName": "ISB_SPEC", - "BriefDescription": "Barrier speculatively executed, ISB" - }, - { - "PublicDescription": "Barrier speculatively executed, DSB", - "EventCode": "0x7d", - "EventName": "DSB_SPEC", - "BriefDescription": "Barrier speculatively executed, DSB" - }, - { - "PublicDescription": "Barrier speculatively executed, DMB", - "EventCode": "0x7e", - "EventName": "DMB_SPEC", - "BriefDescription": "Barrier speculatively executed, DMB" - }, - { - "PublicDescription": "Exception taken, Other synchronous", - "EventCode": "0x81", - "EventName": "EXC_UNDEF", - "BriefDescription": "Exception taken, Other synchronous" - }, - { - "PublicDescription": "Exception taken, Supervisor Call", - "EventCode": "0x82", - "EventName": "EXC_SVC", - "BriefDescription": "Exception taken, Supervisor Call" - }, - { - "PublicDescription": "Exception taken, Instruction Abort", - "EventCode": "0x83", - "EventName": "EXC_PABORT", - "BriefDescription": "Exception taken, Instruction Abort" - }, - { - "PublicDescription": "Exception taken, Data Abort and SError", - "EventCode": "0x84", - "EventName": "EXC_DABORT", - "BriefDescription": "Exception taken, Data Abort and SError" - }, - { - "PublicDescription": "Exception taken, IRQ", - "EventCode": "0x86", - "EventName": "EXC_IRQ", - "BriefDescription": "Exception taken, IRQ" - }, - { - "PublicDescription": "Exception taken, FIQ", - "EventCode": "0x87", - "EventName": "EXC_FIQ", - "BriefDescription": "Exception taken, FIQ" - }, - { - "PublicDescription": "Exception taken, Secure Monitor Call", - "EventCode": "0x88", - "EventName": "EXC_SMC", - "BriefDescription": "Exception taken, Secure Monitor Call" - }, - { - "PublicDescription": "Exception taken, Hypervisor Call", - "EventCode": "0x8a", - "EventName": "EXC_HVC", - "BriefDescription": "Exception taken, Hypervisor Call" - }, - { - "PublicDescription": "Exception taken, Instruction Abort not taken locally", - "EventCode": "0x8b", - "EventName": "EXC_TRAP_PABORT", - "BriefDescription": "Exception taken, Instruction Abort not taken locally" - }, - { - "PublicDescription": "Exception taken, Data Abort or SError not taken locally", - "EventCode": "0x8c", - "EventName": "EXC_TRAP_DABORT", - "BriefDescription": "Exception taken, Data Abort or SError not taken locally" - }, - { - "PublicDescription": "Exception taken, Other traps not taken locally", - "EventCode": "0x8d", - "EventName": "EXC_TRAP_OTHER", - "BriefDescription": "Exception taken, Other traps not taken locally" - }, - { - "PublicDescription": "Exception taken, IRQ not taken locally", - "EventCode": "0x8e", - "EventName": "EXC_TRAP_IRQ", - "BriefDescription": "Exception taken, IRQ not taken locally" - }, - { - "PublicDescription": "Exception taken, FIQ not taken locally", - "EventCode": "0x8f", - "EventName": "EXC_TRAP_FIQ", - "BriefDescription": "Exception taken, FIQ not taken locally" - }, - { - "PublicDescription": "Release consistency operation speculatively executed, Load-Acquire", - "EventCode": "0x90", - "EventName": "RC_LD_SPEC", - "BriefDescription": "Release consistency operation speculatively executed, Load-Acquire" - }, - { - "PublicDescription": "Release consistency operation speculatively executed, Store-Release", - "EventCode": "0x91", - "EventName": "RC_ST_SPEC", - "BriefDescription": "Release consistency operation speculatively executed, Store-Release" - }, - { - "PublicDescription": "Attributable Level 3 data or unified cache access, read", - "EventCode": "0xa0", - "EventName": "L3D_CACHE_RD", - "BriefDescription": "Attributable Level 3 data or unified cache access, read" - }, - { - "PublicDescription": "Attributable Level 3 data or unified cache access, write", - "EventCode": "0xa1", - "EventName": "L3D_CACHE_WR", - "BriefDescription": "Attributable Level 3 data or unified cache access, write" - }, - { - "PublicDescription": "Attributable Level 3 data or unified cache refill, read", - "EventCode": "0xa2", - "EventName": "L3D_CACHE_REFILL_RD", - "BriefDescription": "Attributable Level 3 data or unified cache refill, read" - }, - { - "PublicDescription": "Attributable Level 3 data or unified cache refill, write", - "EventCode": "0xa3", - "EventName": "L3D_CACHE_REFILL_WR", - "BriefDescription": "Attributable Level 3 data or unified cache refill, write" - }, - { - "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, victim", - "EventCode": "0xa6", - "EventName": "L3D_CACHE_WB_VICTIM", - "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, victim" - }, - { - "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean", - "EventCode": "0xa7", - "EventName": "L3D_CACHE_WB_CLEAN", - "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean" - }, - { - "PublicDescription": "Attributable Level 3 data or unified cache access, invalidate", - "EventCode": "0xa8", - "EventName": "L3D_CACHE_INVAL", - "BriefDescription": "Attributable Level 3 data or unified cache access, invalidate" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json new file mode 100644 index 000000000000..80d7a70829a0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json @@ -0,0 +1,746 @@ +[ + { + "PublicDescription": "Instruction architecturally executed, Condition code check pass, software increment", + "EventCode": "0x00", + "EventName": "SW_INCR", + "BriefDescription": "Instruction architecturally executed, Condition code check pass, software increment" + }, + { + "PublicDescription": "Level 1 instruction cache refill", + "EventCode": "0x01", + "EventName": "L1I_CACHE_REFILL", + "BriefDescription": "Level 1 instruction cache refill" + }, + { + "PublicDescription": "Attributable Level 1 instruction TLB refill", + "EventCode": "0x02", + "EventName": "L1I_TLB_REFILL", + "BriefDescription": "Attributable Level 1 instruction TLB refill" + }, + { + "PublicDescription": "Level 1 data cache refill", + "EventCode": "0x03", + "EventName": "L1D_CACHE_REFILL", + "BriefDescription": "Level 1 data cache refill" + }, + { + "PublicDescription": "Level 1 data cache access", + "EventCode": "0x04", + "EventName": "L1D_CACHE", + "BriefDescription": "Level 1 data cache access" + }, + { + "PublicDescription": "Attributable Level 1 data TLB refill", + "EventCode": "0x05", + "EventName": "L1D_TLB_REFILL", + "BriefDescription": "Attributable Level 1 data TLB refill" + }, + { + "PublicDescription": "Instruction architecturally executed", + "EventCode": "0x08", + "EventName": "INST_RETIRED", + "BriefDescription": "Instruction architecturally executed" + }, + { + "PublicDescription": "Exception taken", + "EventCode": "0x09", + "EventName": "EXC_TAKEN", + "BriefDescription": "Exception taken" + }, + { + "PublicDescription": "Instruction architecturally executed, condition check pass, exception return", + "EventCode": "0x0a", + "EventName": "EXC_RETURN", + "BriefDescription": "Instruction architecturally executed, condition check pass, exception return" + }, + { + "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR", + "EventCode": "0x0b", + "EventName": "CID_WRITE_RETIRED", + "BriefDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR" + }, + { + "PublicDescription": "Mispredicted or not predicted branch speculatively executed", + "EventCode": "0x10", + "EventName": "BR_MIS_PRED", + "BriefDescription": "Mispredicted or not predicted branch speculatively executed" + }, + { + "PublicDescription": "Cycle", + "EventCode": "0x11", + "EventName": "CPU_CYCLES", + "BriefDescription": "Cycle" + }, + { + "PublicDescription": "Predictable branch speculatively executed", + "EventCode": "0x12", + "EventName": "BR_PRED", + "BriefDescription": "Predictable branch speculatively executed" + }, + { + "PublicDescription": "Data memory access", + "EventCode": "0x13", + "EventName": "MEM_ACCESS", + "BriefDescription": "Data memory access" + }, + { + "PublicDescription": "Attributable Level 1 instruction cache access", + "EventCode": "0x14", + "EventName": "L1I_CACHE", + "BriefDescription": "Attributable Level 1 instruction cache access" + }, + { + "PublicDescription": "Attributable Level 1 data cache write-back", + "EventCode": "0x15", + "EventName": "L1D_CACHE_WB", + "BriefDescription": "Attributable Level 1 data cache write-back" + }, + { + "PublicDescription": "Level 2 data cache access", + "EventCode": "0x16", + "EventName": "L2D_CACHE", + "BriefDescription": "Level 2 data cache access" + }, + { + "PublicDescription": "Level 2 data refill", + "EventCode": "0x17", + "EventName": "L2D_CACHE_REFILL", + "BriefDescription": "Level 2 data refill" + }, + { + "PublicDescription": "Attributable Level 2 data cache write-back", + "EventCode": "0x18", + "EventName": "L2D_CACHE_WB", + "BriefDescription": "Attributable Level 2 data cache write-back" + }, + { + "PublicDescription": "Attributable Bus access", + "EventCode": "0x19", + "EventName": "BUS_ACCESS", + "BriefDescription": "Attributable Bus access" + }, + { + "PublicDescription": "Local memory error", + "EventCode": "0x1a", + "EventName": "MEMORY_ERROR", + "BriefDescription": "Local memory error" + }, + { + "PublicDescription": "Operation speculatively executed", + "EventCode": "0x1b", + "EventName": "INST_SPEC", + "BriefDescription": "Operation speculatively executed" + }, + { + "PublicDescription": "Instruction architecturally executed, Condition code check pass, write to TTBR", + "EventCode": "0x1c", + "EventName": "TTBR_WRITE_RETIRED", + "BriefDescription": "Instruction architecturally executed, Condition code check pass, write to TTBR" + }, + { + "PublicDescription": "Bus cycle", + "EventCode": "0x1D", + "EventName": "BUS_CYCLES", + "BriefDescription": "Bus cycle" + }, + { + "PublicDescription": "Attributable Level 2 data cache allocation without refill", + "EventCode": "0x20", + "EventName": "L2D_CACHE_ALLOCATE", + "BriefDescription": "Attributable Level 2 data cache allocation without refill" + }, + { + "PublicDescription": "Instruction architecturally executed, branch", + "EventCode": "0x21", + "EventName": "BR_RETIRED", + "BriefDescription": "Instruction architecturally executed, branch" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted branch", + "EventCode": "0x22", + "EventName": "BR_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted branch" + }, + { + "PublicDescription": "No operation issued because of the frontend", + "EventCode": "0x23", + "EventName": "STALL_FRONTEND", + "BriefDescription": "No operation issued because of the frontend" + }, + { + "PublicDescription": "No operation issued due to the backend", + "EventCode": "0x24", + "EventName": "STALL_BACKEND", + "BriefDescription": "No operation issued due to the backend" + }, + { + "PublicDescription": "Attributable Level 1 data or unified TLB access", + "EventCode": "0x25", + "EventName": "L1D_TLB", + "BriefDescription": "Attributable Level 1 data or unified TLB access" + }, + { + "PublicDescription": "Attributable Level 1 instruction TLB access", + "EventCode": "0x26", + "EventName": "L1I_TLB", + "BriefDescription": "Attributable Level 1 instruction TLB access" + }, + { + "PublicDescription": "Attributable Level 3 data cache allocation without refill", + "EventCode": "0x29", + "EventName": "L3D_CACHE_ALLOCATE", + "BriefDescription": "Attributable Level 3 data cache allocation without refill" + }, + { + "PublicDescription": "Attributable Level 3 data cache refill", + "EventCode": "0x2A", + "EventName": "L3D_CACHE_REFILL", + "BriefDescription": "Attributable Level 3 data cache refill" + }, + { + "PublicDescription": "Attributable Level 3 data cache access", + "EventCode": "0x2B", + "EventName": "L3D_CACHE", + "BriefDescription": "Attributable Level 3 data cache access" + }, + { + "PublicDescription": "Attributable Level 2 data TLB refill", + "EventCode": "0x2D", + "EventName": "L2D_TLB_REFILL", + "BriefDescription": "Attributable Level 2 data TLB refill" + }, + { + "PublicDescription": "Attributable Level 2 instruction TLB refill.", + "EventCode": "0x2E", + "EventName": "L2I_TLB_REFILL", + "BriefDescription": "Attributable Level 2 instruction TLB refill." + }, + { + "PublicDescription": "Attributable Level 2 data or unified TLB access", + "EventCode": "0x2F", + "EventName": "L2D_TLB", + "BriefDescription": "Attributable Level 2 data or unified TLB access" + }, + { + "PublicDescription": "Attributable Level 2 instruction TLB access.", + "EventCode": "0x30", + "EventName": "L2I_TLB", + "BriefDescription": "Attributable Level 2 instruction TLB access." + }, + { + "PublicDescription": "Access to another socket in a multi-socket system", + "EventCode": "0x31", + "EventName": "REMOTE_ACCESS", + "BriefDescription": "Access to another socket in a multi-socket system" + }, + { + "PublicDescription": "Access to data TLB causes a translation table walk", + "EventCode": "0x34", + "EventName": "DTLB_WALK", + "BriefDescription": "Access to data TLB causes a translation table walk" + }, + { + "PublicDescription": "Access to instruction TLB that causes a translation table walk", + "EventCode": "0x35", + "EventName": "ITLB_WALK", + "BriefDescription": "Access to instruction TLB that causes a translation table walk" + }, + { + "PublicDescription": "Attributable Last level cache memory read", + "EventCode": "0x36", + "EventName": "LL_CACHE_RD", + "BriefDescription": "Attributable Last level cache memory read" + }, + { + "PublicDescription": "Last level cache miss, read", + "EventCode": "0x37", + "EventName": "LL_CACHE_MISS_RD", + "BriefDescription": "Last level cache miss, read" + }, + { + "PublicDescription": "Level 1 data cache long-latency read miss. The counter counts each memory read access counted by L1D_CACHE that incurs additional latency because it returns data from outside the Level 1 data or unified cache of this processing element.", + "EventCode": "0x39", + "EventName": "L1D_CACHE_LMISS_RD", + "BriefDescription": "Level 1 data cache long-latency read miss" + }, + { + "PublicDescription": "Micro-operation architecturally executed. The counter counts each operation counted by OP_SPEC that would be executed in a simple sequential execution of the program.", + "EventCode": "0x3A", + "EventName": "OP_RETIRED", + "BriefDescription": "Micro-operation architecturally executed" + }, + { + "PublicDescription": "Micro-operation speculatively executed. The counter counts the number of operations executed by the processing element, including those that are executed speculatively and would not be executed in a simple sequential execution of the program.", + "EventCode": "0x3B", + "EventName": "OP_SPEC", + "BriefDescription": "Micro-operation speculatively executed" + }, + { + "PublicDescription": "No operation sent for execution. The counter counts every attributable cycle on which no attributable instruction or operation was sent for execution on this processing element.", + "EventCode": "0x3C", + "EventName": "STALL", + "BriefDescription": "No operation sent for execution" + }, + { + "PublicDescription": "No operation sent for execution on a slot due to the backend. Counts each slot counted by STALL_SLOT where no attributable instruction or operation was sent for execution because the backend is unable to accept it.", + "EventCode": "0x3D", + "EventName": "STALL_SLOT_BACKEND", + "BriefDescription": "No operation sent for execution on a slot due to the backend" + }, + { + "PublicDescription": "No operation sent for execution on a slot due to the frontend. Counts each slot counted by STALL_SLOT where no attributable instruction or operation was sent for execution because there was no attributable instruction or operation available to issue from the processing element from the frontend for the slot.", + "EventCode": "0x3E", + "EventName": "STALL_SLOT_FRONTEND", + "BriefDescription": "No operation sent for execution on a slot due to the frontend" + }, + { + "PublicDescription": "No operation sent for execution on a slot. The counter counts on each attributable cycle the number of instruction or operation slots that were not occupied by an instruction or operation attributable to the processing element.", + "EventCode": "0x3F", + "EventName": "STALL_SLOT", + "BriefDescription": "No operation sent for execution on a slot" + }, + { + "PublicDescription": "Sample Population", + "EventCode": "0x4000", + "EventName": "SAMPLE_POP", + "BriefDescription": "Sample Population" + }, + { + "PublicDescription": "Sample Taken", + "EventCode": "0x4001", + "EventName": "SAMPLE_FEED", + "BriefDescription": "Sample Taken" + }, + { + "PublicDescription": "Sample Taken and not removed by filtering", + "EventCode": "0x4002", + "EventName": "SAMPLE_FILTRATE", + "BriefDescription": "Sample Taken and not removed by filtering" + }, + { + "PublicDescription": "Sample collided with previous sample", + "EventCode": "0x4003", + "EventName": "SAMPLE_COLLISION", + "BriefDescription": "Sample collided with previous sample" + }, + { + "PublicDescription": "Constant frequency cycles. The counter increments at a constant frequency equal to the rate of increment of the system counter, CNTPCT_EL0.", + "EventCode": "0x4004", + "EventName": "CNT_CYCLES", + "BriefDescription": "Constant frequency cycles" + }, + { + "PublicDescription": "Memory stall cycles. The counter counts each cycle counted by STALL_BACKEND where there is a cache miss in the last level of cache within the processing element clock domain", + "EventCode": "0x4005", + "EventName": "STALL_BACKEND_MEM", + "BriefDescription": "Memory stall cycles" + }, + { + "PublicDescription": "Level 1 instruction cache long-latency read miss. If the L1I_CACHE_RD event is implemented, the counter counts each access counted by L1I_CACHE_RD that incurs additional latency because it returns instructions from outside of the Level 1 instruction cache of this PE. If the L1I_CACHE_RD event is not implemented, the counter counts each access counted by L1I_CACHE that incurs additional latency because it returns instructions from outside the Level 1 instruction cache of this PE. The event indicates to software that the access missed in the Level 1 instruction cache and might have a significant performance impact due to the additional latency, compared to the latency of an access that hits in the Level 1 instruction cache.", + "EventCode": "0x4006", + "EventName": "L1I_CACHE_LMISS", + "BriefDescription": "Level 1 instruction cache long-latency read miss" + }, + { + "PublicDescription": "Level 2 data cache long-latency read miss. The counter counts each memory read access counted by L2D_CACHE that incurs additional latency because it returns data from outside the Level 2 data or unified cache of this processing element. The event indicates to software that the access missed in the Level 2 data or unified cache and might have a significant performance impact compared to the latency of an access that hits in the Level 2 data or unified cache.", + "EventCode": "0x4009", + "EventName": "L2D_CACHE_LMISS_RD", + "BriefDescription": "Level 2 data cache long-latency read miss" + }, + { + "PublicDescription": "Level 3 data cache long-latency read miss. The counter counts each memory read access counted by L3D_CACHE that incurs additional latency because it returns data from outside the Level 3 data or unified cache of this processing element. The event indicates to software that the access missed in the Level 3 data or unified cache and might have a significant performance impact compared to the latency of an access that hits in the Level 3 data or unified cache.", + "EventCode": "0x400B", + "EventName": "L3D_CACHE_LMISS_RD", + "BriefDescription": "Level 3 data cache long-latency read miss" + }, + { + "PublicDescription": "Trace buffer current write pointer wrapped", + "EventCode": "0x400C", + "EventName": "TRB_WRAP", + "BriefDescription": "Trace buffer current write pointer wrapped" + }, + { + "PublicDescription": "PE Trace Unit external output 0", + "EventCode": "0x4010", + "EventName": "TRCEXTOUT0", + "BriefDescription": "PE Trace Unit external output 0" + }, + { + "PublicDescription": "PE Trace Unit external output 1", + "EventCode": "0x4011", + "EventName": "TRCEXTOUT1", + "BriefDescription": "PE Trace Unit external output 1" + }, + { + "PublicDescription": "PE Trace Unit external output 2", + "EventCode": "0x4012", + "EventName": "TRCEXTOUT2", + "BriefDescription": "PE Trace Unit external output 2" + }, + { + "PublicDescription": "PE Trace Unit external output 3", + "EventCode": "0x4013", + "EventName": "TRCEXTOUT3", + "BriefDescription": "PE Trace Unit external output 3" + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 4", + "EventCode": "0x4018", + "EventName": "CTI_TRIGOUT4", + "BriefDescription": "Cross-trigger Interface output trigger 4" + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 5 ", + "EventCode": "0x4019", + "EventName": "CTI_TRIGOUT5", + "BriefDescription": "Cross-trigger Interface output trigger 5 " + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 6", + "EventCode": "0x401A", + "EventName": "CTI_TRIGOUT6", + "BriefDescription": "Cross-trigger Interface output trigger 6" + }, + { + "PublicDescription": "Cross-trigger Interface output trigger 7", + "EventCode": "0x401B", + "EventName": "CTI_TRIGOUT7", + "BriefDescription": "Cross-trigger Interface output trigger 7" + }, + { + "PublicDescription": "Access with additional latency from alignment", + "EventCode": "0x4020", + "EventName": "LDST_ALIGN_LAT", + "BriefDescription": "Access with additional latency from alignment" + }, + { + "PublicDescription": "Load with additional latency from alignment", + "EventCode": "0x4021", + "EventName": "LD_ALIGN_LAT", + "BriefDescription": "Load with additional latency from alignment" + }, + { + "PublicDescription": "Store with additional latency from alignment", + "EventCode": "0x4022", + "EventName": "ST_ALIGN_LAT", + "BriefDescription": "Store with additional latency from alignment" + }, + { + "PublicDescription": "Checked data memory access", + "EventCode": "0x4024", + "EventName": "MEM_ACCESS_CHECKED", + "BriefDescription": "Checked data memory access" + }, + { + "PublicDescription": "Checked data memory access, read", + "EventCode": "0x4025", + "EventName": "MEM_ACCESS_CHECKED_RD", + "BriefDescription": "Checked data memory access, read" + }, + { + "PublicDescription": "Checked data memory access, write", + "EventCode": "0x4026", + "EventName": "MEM_ACCESS_CHECKED_WR", + "BriefDescription": "Checked data memory access, write" + }, + { + "PublicDescription": "SIMD Instruction architecturally executed.", + "EventCode": "0x8000", + "EventName": "SIMD_INST_RETIRED", + "BriefDescription": "SIMD Instruction architecturally executed." + }, + { + "PublicDescription": "Instruction architecturally executed, SVE.", + "EventCode": "0x8002", + "EventName": "SVE_INST_RETIRED", + "BriefDescription": "Instruction architecturally executed, SVE." + }, + { + "PublicDescription": "ASE operations speculatively executed", + "EventCode": "0x8005", + "EventName": "ASE_INST_SPEC", + "BriefDescription": "ASE operations speculatively executed" + }, + { + "PublicDescription": "SVE operations speculatively executed", + "EventCode": "0x8006", + "EventName": "SVE_INST_SPEC", + "BriefDescription": "SVE operations speculatively executed" + }, + { + "PublicDescription": "Microarchitectural operation, Operations speculatively executed.", + "EventCode": "0x8008", + "EventName": "UOP_SPEC", + "BriefDescription": "Microarchitectural operation, Operations speculatively executed." + }, + { + "PublicDescription": "SVE Math accelerator Operations speculatively executed.", + "EventCode": "0x800E", + "EventName": "SVE_MATH_SPEC", + "BriefDescription": "SVE Math accelerator Operations speculatively executed." + }, + { + "PublicDescription": "Floating-point Operations speculatively executed.", + "EventCode": "0x8010", + "EventName": "FP_SPEC", + "BriefDescription": "Floating-point Operations speculatively executed." + }, + { + "PublicDescription": "Floating-point half-precision operations speculatively executed", + "EventCode": "0x8014", + "EventName": "FP_HP_SPEC", + "BriefDescription": "Floating-point half-precision operations speculatively executed" + }, + { + "PublicDescription": "Floating-point single-precision operations speculatively executed", + "EventCode": "0x8018", + "EventName": "FP_SP_SPEC", + "BriefDescription": "Floating-point single-precision operations speculatively executed" + }, + { + "PublicDescription": "Floating-point double-precision operations speculatively executed", + "EventCode": "0x801C", + "EventName": "FP_DP_SPEC", + "BriefDescription": "Floating-point double-precision operations speculatively executed" + }, + { + "PublicDescription": "Floating-point FMA Operations speculatively executed.", + "EventCode": "0x8028", + "EventName": "FP_FMA_SPEC", + "BriefDescription": "Floating-point FMA Operations speculatively executed." + }, + { + "PublicDescription": "Floating-point reciprocal estimate Operations speculatively executed.", + "EventCode": "0x8034", + "EventName": "FP_RECPE_SPEC", + "BriefDescription": "Floating-point reciprocal estimate Operations speculatively executed." + }, + { + "PublicDescription": "floating-point convert Operations speculatively executed.", + "EventCode": "0x8038", + "EventName": "FP_CVT_SPEC", + "BriefDescription": "floating-point convert Operations speculatively executed." + }, + { + "PublicDescription": "Advanced SIMD and SVE integer Operations speculatively executed.", + "EventCode": "0x8043", + "EventName": "ASE_SVE_INT_SPEC", + "BriefDescription": "Advanced SIMD and SVE integer Operations speculatively executed." + }, + { + "PublicDescription": "SVE predicated Operations speculatively executed.", + "EventCode": "0x8074", + "EventName": "SVE_PRED_SPEC", + "BriefDescription": "SVE predicated Operations speculatively executed." + }, + { + "PublicDescription": "SVE predicated operations with no active predicates speculatively executed", + "EventCode": "0x8075", + "EventName": "SVE_PRED_EMPTY_SPEC", + "BriefDescription": "SVE predicated operations with no active predicates speculatively executed" + }, + { + "PublicDescription": "SVE predicated operations speculatively executed with all active predicates", + "EventCode": "0x8076", + "EventName": "SVE_PRED_FULL_SPEC", + "BriefDescription": "SVE predicated operations speculatively executed with all active predicates" + }, + { + "PublicDescription": "SVE predicated operations speculatively executed with partially active predicates", + "EventCode": "0x8077", + "EventName": "SVE_PRED_PARTIAL_SPEC", + "BriefDescription": "SVE predicated operations speculatively executed with partially active predicates" + }, + { + "PublicDescription": "SVE predicated operations with empty or partially active predicates", + "EventCode": "0x8079", + "EventName": "SVE_PRED_NOT_FULL_SPEC", + "BriefDescription": "SVE predicated operations with empty or partially active predicates" + }, + { + "PublicDescription": "SVE MOVPRFX Operations speculatively executed.", + "EventCode": "0x807C", + "EventName": "SVE_MOVPRFX_SPEC", + "BriefDescription": "SVE MOVPRFX Operations speculatively executed." + }, + { + "PublicDescription": "SVE MOVPRFX unfused Operations speculatively executed.", + "EventCode": "0x807F", + "EventName": "SVE_MOVPRFX_U_SPEC", + "BriefDescription": "SVE MOVPRFX unfused Operations speculatively executed." + }, + { + "PublicDescription": "Advanced SIMD and SVE load Operations speculatively executed.", + "EventCode": "0x8085", + "EventName": "ASE_SVE_LD_SPEC", + "BriefDescription": "Advanced SIMD and SVE load Operations speculatively executed." + }, + { + "PublicDescription": "Advanced SIMD and SVE store Operations speculatively executed.", + "EventCode": "0x8086", + "EventName": "ASE_SVE_ST_SPEC", + "BriefDescription": "Advanced SIMD and SVE store Operations speculatively executed." + }, + { + "PublicDescription": "Prefetch Operations speculatively executed.", + "EventCode": "0x8087", + "EventName": "PRF_SPEC", + "BriefDescription": "Prefetch Operations speculatively executed." + }, + { + "PublicDescription": "General-purpose register load Operations speculatively executed.", + "EventCode": "0x8089", + "EventName": "BASE_LD_REG_SPEC", + "BriefDescription": "General-purpose register load Operations speculatively executed." + }, + { + "PublicDescription": "General-purpose register store Operations speculatively executed.", + "EventCode": "0x808A", + "EventName": "BASE_ST_REG_SPEC", + "BriefDescription": "General-purpose register store Operations speculatively executed." + }, + { + "PublicDescription": "SVE unpredicated load register Operations speculatively executed.", + "EventCode": "0x8091", + "EventName": "SVE_LDR_REG_SPEC", + "BriefDescription": "SVE unpredicated load register Operations speculatively executed." + }, + { + "PublicDescription": "SVE unpredicated store register Operations speculatively executed.", + "EventCode": "0x8092", + "EventName": "SVE_STR_REG_SPEC", + "BriefDescription": "SVE unpredicated store register Operations speculatively executed." + }, + { + "PublicDescription": "SVE load predicate register Operations speculatively executed.", + "EventCode": "0x8095", + "EventName": "SVE_LDR_PREG_SPEC", + "BriefDescription": "SVE load predicate register Operations speculatively executed." + }, + { + "PublicDescription": "SVE store predicate register Operations speculatively executed.", + "EventCode": "0x8096", + "EventName": "SVE_STR_PREG_SPEC", + "BriefDescription": "SVE store predicate register Operations speculatively executed." + }, + { + "PublicDescription": "SVE contiguous prefetch element Operations speculatively executed.", + "EventCode": "0x809F", + "EventName": "SVE_PRF_CONTIG_SPEC", + "BriefDescription": "SVE contiguous prefetch element Operations speculatively executed." + }, + { + "PublicDescription": "Advanced SIMD and SVE contiguous load multiple vector Operations speculatively executed.", + "EventCode": "0x80A5", + "EventName": "ASE_SVE_LD_MULTI_SPEC", + "BriefDescription": "Advanced SIMD and SVE contiguous load multiple vector Operations speculatively executed." + }, + { + "PublicDescription": "Advanced SIMD and SVE contiguous store multiple vector Operations speculatively executed.", + "EventCode": "0x80A6", + "EventName": "ASE_SVE_ST_MULTI_SPEC", + "BriefDescription": "Advanced SIMD and SVE contiguous store multiple vector Operations speculatively executed." + }, + { + "PublicDescription": "SVE gather-load Operations speculatively executed.", + "EventCode": "0x80AD", + "EventName": "SVE_LD_GATHER_SPEC", + "BriefDescription": "SVE gather-load Operations speculatively executed." + }, + { + "PublicDescription": "SVE scatter-store Operations speculatively executed.", + "EventCode": "0x80AE", + "EventName": "SVE_ST_SCATTER_SPEC", + "BriefDescription": "SVE scatter-store Operations speculatively executed." + }, + { + "PublicDescription": "SVE gather-prefetch Operations speculatively executed.", + "EventCode": "0x80AF", + "EventName": "SVE_PRF_GATHER_SPEC", + "BriefDescription": "SVE gather-prefetch Operations speculatively executed." + }, + { + "PublicDescription": "SVE First-fault load Operations speculatively executed.", + "EventCode": "0x80BC", + "EventName": "SVE_LDFF_SPEC", + "BriefDescription": "SVE First-fault load Operations speculatively executed." + }, + { + "PublicDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0", + "EventCode": "0x80BD", + "EventName": "SVE_LDFF_FAULT_SPEC", + "BriefDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0" + }, + { + "PublicDescription": "Scalable floating-point element Operations speculatively executed.", + "EventCode": "0x80C0", + "EventName": "FP_SCALE_OPS_SPEC", + "BriefDescription": "Scalable floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Non-scalable floating-point element Operations speculatively executed.", + "EventCode": "0x80C1", + "EventName": "FP_FIXED_OPS_SPEC", + "BriefDescription": "Non-scalable floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Scalable half-precision floating-point element Operations speculatively executed.", + "EventCode": "0x80C2", + "EventName": "FP_HP_SCALE_OPS_SPEC", + "BriefDescription": "Scalable half-precision floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Non-scalable half-precision floating-point element Operations speculatively executed.", + "EventCode": "0x80C3", + "EventName": "FP_HP_FIXED_OPS_SPEC", + "BriefDescription": "Non-scalable half-precision floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Scalable single-precision floating-point element Operations speculatively executed.", + "EventCode": "0x80C4", + "EventName": "FP_SP_SCALE_OPS_SPEC", + "BriefDescription": "Scalable single-precision floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Non-scalable single-precision floating-point element Operations speculatively executed.", + "EventCode": "0x80C5", + "EventName": "FP_SP_FIXED_OPS_SPEC", + "BriefDescription": "Non-scalable single-precision floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Scalable double-precision floating-point element Operations speculatively executed.", + "EventCode": "0x80C6", + "EventName": "FP_DP_SCALE_OPS_SPEC", + "BriefDescription": "Scalable double-precision floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Non-scalable double-precision floating-point element Operations speculatively executed.", + "EventCode": "0x80C7", + "EventName": "FP_DP_FIXED_OPS_SPEC", + "BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed." + }, + { + "PublicDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed", + "EventCode": "0x80E3", + "EventName": "ASE_SVE_INT8_SPEC", + "BriefDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed" + }, + { + "PublicDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed", + "EventCode": "0x80E7", + "EventName": "ASE_SVE_INT16_SPEC", + "BriefDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed" + }, + { + "PublicDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed", + "EventCode": "0x80EB", + "EventName": "ASE_SVE_INT32_SPEC", + "BriefDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed" + }, + { + "PublicDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed", + "EventCode": "0x80EF", + "EventName": "ASE_SVE_INT64_SPEC", + "BriefDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json index dda8e59149d2..6970203cb247 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json @@ -229,5 +229,5 @@ "BriefDescription": "Store bound L3 topdown metric", "MetricGroup": "TopDownL3", "MetricName": "store_bound" - }, + } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json index 61514d38601b..2b3cb55df288 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json @@ -1,56 +1,56 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_ddrc.flux_wr", + "ConfigCode": "0x00", + "EventName": "flux_wr", "BriefDescription": "DDRC total write operations", "PublicDescription": "DDRC total write operations", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_ddrc.flux_rd", + "ConfigCode": "0x01", + "EventName": "flux_rd", "BriefDescription": "DDRC total read operations", "PublicDescription": "DDRC total read operations", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_ddrc.flux_wcmd", + "ConfigCode": "0x02", + "EventName": "flux_wcmd", "BriefDescription": "DDRC write commands", "PublicDescription": "DDRC write commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_ddrc.flux_rcmd", + "ConfigCode": "0x03", + "EventName": "flux_rcmd", "BriefDescription": "DDRC read commands", "PublicDescription": "DDRC read commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x04", - "EventName": "uncore_hisi_ddrc.pre_cmd", + "ConfigCode": "0x04", + "EventName": "pre_cmd", "BriefDescription": "DDRC precharge commands", "PublicDescription": "DDRC precharge commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x05", - "EventName": "uncore_hisi_ddrc.act_cmd", + "ConfigCode": "0x05", + "EventName": "act_cmd", "BriefDescription": "DDRC active commands", "PublicDescription": "DDRC active commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x06", - "EventName": "uncore_hisi_ddrc.rnk_chg", + "ConfigCode": "0x06", + "EventName": "rnk_chg", "BriefDescription": "DDRC rank commands", "PublicDescription": "DDRC rank commands", "Unit": "hisi_sccl,ddrc" }, { - "EventCode": "0x07", - "EventName": "uncore_hisi_ddrc.rw_chg", + "ConfigCode": "0x07", + "EventName": "rw_chg", "BriefDescription": "DDRC read and write changes", "PublicDescription": "DDRC read and write changes", "Unit": "hisi_sccl,ddrc" diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json index ada86782933f..9a7ec7af2060 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json @@ -1,72 +1,152 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_hha.rx_ops_num", + "ConfigCode": "0x00", + "EventName": "rx_ops_num", "BriefDescription": "The number of all operations received by the HHA", "PublicDescription": "The number of all operations received by the HHA", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_hha.rx_outer", + "ConfigCode": "0x01", + "EventName": "rx_outer", "BriefDescription": "The number of all operations received by the HHA from another socket", "PublicDescription": "The number of all operations received by the HHA from another socket", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_hha.rx_sccl", + "ConfigCode": "0x02", + "EventName": "rx_sccl", "BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket", "PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_hha.rx_ccix", + "ConfigCode": "0x03", + "EventName": "rx_ccix", "BriefDescription": "Count of the number of operations that HHA has received from CCIX", "PublicDescription": "Count of the number of operations that HHA has received from CCIX", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1c", - "EventName": "uncore_hisi_hha.rd_ddr_64b", + "ConfigCode": "0x4", + "EventName": "rx_wbi", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x5", + "EventName": "rx_wbip", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x11", + "EventName": "rx_wtistash", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x1c", + "EventName": "rd_ddr_64b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes", "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1d", - "EventName": "uncore_hisi_hha.wr_ddr_64b", + "ConfigCode": "0x1d", + "EventName": "wr_ddr_64b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1e", - "EventName": "uncore_hisi_hha.rd_ddr_128b", + "ConfigCode": "0x1e", + "EventName": "rd_ddr_128b", "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x1f", - "EventName": "uncore_hisi_hha.wr_ddr_128b", + "ConfigCode": "0x1f", + "EventName": "wr_ddr_128b", "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x20", - "EventName": "uncore_hisi_hha.spill_num", + "ConfigCode": "0x20", + "EventName": "spill_num", "BriefDescription": "Count of the number of spill operations that the HHA has sent", "PublicDescription": "Count of the number of spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" }, { - "EventCode": "0x21", - "EventName": "uncore_hisi_hha.spill_success", + "ConfigCode": "0x21", + "EventName": "spill_success", "BriefDescription": "Count of the number of successful spill operations that the HHA has sent", "PublicDescription": "Count of the number of successful spill operations that the HHA has sent", "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x23", + "EventName": "bi_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x32", + "EventName": "mediated_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x33", + "EventName": "tx_snp_num", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x34", + "EventName": "tx_snp_outer", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x35", + "EventName": "tx_snp_ccix", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x38", + "EventName": "rx_snprspdata", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x3c", + "EventName": "rx_snprsp_outer", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x40", + "EventName": "sdir-lookup", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x41", + "EventName": "edir-lookup", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x42", + "EventName": "sdir-hit", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x43", + "EventName": "edir-hit", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x4c", + "EventName": "sdir-home-migrate", + "Unit": "hisi_sccl,hha" + }, + { + "ConfigCode": "0x4d", + "EventName": "edir-home-migrate", + "Unit": "hisi_sccl,hha" } ] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json index 67ab19e8cf3a..e3479b65be9a 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json @@ -1,91 +1,91 @@ [ { - "EventCode": "0x00", - "EventName": "uncore_hisi_l3c.rd_cpipe", + "ConfigCode": "0x00", + "EventName": "rd_cpipe", "BriefDescription": "Total read accesses", "PublicDescription": "Total read accesses", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x01", - "EventName": "uncore_hisi_l3c.wr_cpipe", + "ConfigCode": "0x01", + "EventName": "wr_cpipe", "BriefDescription": "Total write accesses", "PublicDescription": "Total write accesses", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x02", - "EventName": "uncore_hisi_l3c.rd_hit_cpipe", + "ConfigCode": "0x02", + "EventName": "rd_hit_cpipe", "BriefDescription": "Total read hits", "PublicDescription": "Total read hits", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x03", - "EventName": "uncore_hisi_l3c.wr_hit_cpipe", + "ConfigCode": "0x03", + "EventName": "wr_hit_cpipe", "BriefDescription": "Total write hits", "PublicDescription": "Total write hits", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x04", - "EventName": "uncore_hisi_l3c.victim_num", + "ConfigCode": "0x04", + "EventName": "victim_num", "BriefDescription": "l3c precharge commands", "PublicDescription": "l3c precharge commands", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x20", - "EventName": "uncore_hisi_l3c.rd_spipe", + "ConfigCode": "0x20", + "EventName": "rd_spipe", "BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", "PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x21", - "EventName": "uncore_hisi_l3c.wr_spipe", + "ConfigCode": "0x21", + "EventName": "wr_spipe", "BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", "PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x22", - "EventName": "uncore_hisi_l3c.rd_hit_spipe", + "ConfigCode": "0x22", + "EventName": "rd_hit_spipe", "BriefDescription": "Count of the number of read lines that hits in spipe of this L3C", "PublicDescription": "Count of the number of read lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x23", - "EventName": "uncore_hisi_l3c.wr_hit_spipe", + "ConfigCode": "0x23", + "EventName": "wr_hit_spipe", "BriefDescription": "Count of the number of write lines that hits in spipe of this L3C", "PublicDescription": "Count of the number of write lines that hits in spipe of this L3C", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x29", - "EventName": "uncore_hisi_l3c.back_invalid", + "ConfigCode": "0x29", + "EventName": "back_invalid", "BriefDescription": "Count of the number of L3C back invalid operations", "PublicDescription": "Count of the number of L3C back invalid operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x40", - "EventName": "uncore_hisi_l3c.retry_cpu", + "ConfigCode": "0x40", + "EventName": "retry_cpu", "BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations", "PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x41", - "EventName": "uncore_hisi_l3c.retry_ring", + "ConfigCode": "0x41", + "EventName": "retry_ring", "BriefDescription": "Count of the number of retry that L3C suppresses the ring operations", "PublicDescription": "Count of the number of retry that L3C suppresses the ring operations", "Unit": "hisi_sccl,l3c" }, { - "EventCode": "0x42", - "EventName": "uncore_hisi_l3c.prefetch_drop", + "ConfigCode": "0x42", + "EventName": "prefetch_drop", "BriefDescription": "Count of the number of prefetch drops from this L3C", "PublicDescription": "Count of the number of prefetch drops from this L3C", "Unit": "hisi_sccl,l3c" diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index c43591d831b8..b899db48c12a 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -18,6 +18,8 @@ 0x00000000410fd080,v1,arm/cortex-a57-a72,core 0x00000000410fd0b0,v1,arm/cortex-a76-n1,core 0x00000000410fd0c0,v1,arm/cortex-a76-n1,core +0x00000000410fd400,v1,arm/neoverse-v1,core +0x00000000410fd490,v1,arm/neoverse-n2,core 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000460f0010,v1,fujitsu/a64fx,core diff --git a/tools/perf/pmu-events/arch/arm64/recommended.json b/tools/perf/pmu-events/arch/arm64/recommended.json new file mode 100644 index 000000000000..210afa856091 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/recommended.json @@ -0,0 +1,452 @@ +[ + { + "PublicDescription": "Attributable Level 1 data cache access, read", + "EventCode": "0x40", + "EventName": "L1D_CACHE_RD", + "BriefDescription": "L1D cache access, read" + }, + { + "PublicDescription": "Attributable Level 1 data cache access, write", + "EventCode": "0x41", + "EventName": "L1D_CACHE_WR", + "BriefDescription": "L1D cache access, write" + }, + { + "PublicDescription": "Attributable Level 1 data cache refill, read", + "EventCode": "0x42", + "EventName": "L1D_CACHE_REFILL_RD", + "BriefDescription": "L1D cache refill, read" + }, + { + "PublicDescription": "Attributable Level 1 data cache refill, write", + "EventCode": "0x43", + "EventName": "L1D_CACHE_REFILL_WR", + "BriefDescription": "L1D cache refill, write" + }, + { + "PublicDescription": "Attributable Level 1 data cache refill, inner", + "EventCode": "0x44", + "EventName": "L1D_CACHE_REFILL_INNER", + "BriefDescription": "L1D cache refill, inner" + }, + { + "PublicDescription": "Attributable Level 1 data cache refill, outer", + "EventCode": "0x45", + "EventName": "L1D_CACHE_REFILL_OUTER", + "BriefDescription": "L1D cache refill, outer" + }, + { + "PublicDescription": "Attributable Level 1 data cache Write-Back, victim", + "EventCode": "0x46", + "EventName": "L1D_CACHE_WB_VICTIM", + "BriefDescription": "L1D cache Write-Back, victim" + }, + { + "PublicDescription": "Level 1 data cache Write-Back, cleaning and coherency", + "EventCode": "0x47", + "EventName": "L1D_CACHE_WB_CLEAN", + "BriefDescription": "L1D cache Write-Back, cleaning and coherency" + }, + { + "PublicDescription": "Attributable Level 1 data cache invalidate", + "EventCode": "0x48", + "EventName": "L1D_CACHE_INVAL", + "BriefDescription": "L1D cache invalidate" + }, + { + "PublicDescription": "Attributable Level 1 data TLB refill, read", + "EventCode": "0x4C", + "EventName": "L1D_TLB_REFILL_RD", + "BriefDescription": "L1D tlb refill, read" + }, + { + "PublicDescription": "Attributable Level 1 data TLB refill, write", + "EventCode": "0x4D", + "EventName": "L1D_TLB_REFILL_WR", + "BriefDescription": "L1D tlb refill, write" + }, + { + "PublicDescription": "Attributable Level 1 data or unified TLB access, read", + "EventCode": "0x4E", + "EventName": "L1D_TLB_RD", + "BriefDescription": "L1D tlb access, read" + }, + { + "PublicDescription": "Attributable Level 1 data or unified TLB access, write", + "EventCode": "0x4F", + "EventName": "L1D_TLB_WR", + "BriefDescription": "L1D tlb access, write" + }, + { + "PublicDescription": "Attributable Level 2 data cache access, read", + "EventCode": "0x50", + "EventName": "L2D_CACHE_RD", + "BriefDescription": "L2D cache access, read" + }, + { + "PublicDescription": "Attributable Level 2 data cache access, write", + "EventCode": "0x51", + "EventName": "L2D_CACHE_WR", + "BriefDescription": "L2D cache access, write" + }, + { + "PublicDescription": "Attributable Level 2 data cache refill, read", + "EventCode": "0x52", + "EventName": "L2D_CACHE_REFILL_RD", + "BriefDescription": "L2D cache refill, read" + }, + { + "PublicDescription": "Attributable Level 2 data cache refill, write", + "EventCode": "0x53", + "EventName": "L2D_CACHE_REFILL_WR", + "BriefDescription": "L2D cache refill, write" + }, + { + "PublicDescription": "Attributable Level 2 data cache Write-Back, victim", + "EventCode": "0x56", + "EventName": "L2D_CACHE_WB_VICTIM", + "BriefDescription": "L2D cache Write-Back, victim" + }, + { + "PublicDescription": "Level 2 data cache Write-Back, cleaning and coherency", + "EventCode": "0x57", + "EventName": "L2D_CACHE_WB_CLEAN", + "BriefDescription": "L2D cache Write-Back, cleaning and coherency" + }, + { + "PublicDescription": "Attributable Level 2 data cache invalidate", + "EventCode": "0x58", + "EventName": "L2D_CACHE_INVAL", + "BriefDescription": "L2D cache invalidate" + }, + { + "PublicDescription": "Attributable Level 2 data or unified TLB refill, read", + "EventCode": "0x5c", + "EventName": "L2D_TLB_REFILL_RD", + "BriefDescription": "L2D cache refill, read" + }, + { + "PublicDescription": "Attributable Level 2 data or unified TLB refill, write", + "EventCode": "0x5d", + "EventName": "L2D_TLB_REFILL_WR", + "BriefDescription": "L2D cache refill, write" + }, + { + "PublicDescription": "Attributable Level 2 data or unified TLB access, read", + "EventCode": "0x5e", + "EventName": "L2D_TLB_RD", + "BriefDescription": "L2D cache access, read" + }, + { + "PublicDescription": "Attributable Level 2 data or unified TLB access, write", + "EventCode": "0x5f", + "EventName": "L2D_TLB_WR", + "BriefDescription": "L2D cache access, write" + }, + { + "PublicDescription": "Bus access read", + "EventCode": "0x60", + "EventName": "BUS_ACCESS_RD", + "BriefDescription": "Bus access read" + }, + { + "PublicDescription": "Bus access write", + "EventCode": "0x61", + "EventName": "BUS_ACCESS_WR", + "BriefDescription": "Bus access write" + }, + { + "PublicDescription": "Bus access, Normal, Cacheable, Shareable", + "EventCode": "0x62", + "EventName": "BUS_ACCESS_SHARED", + "BriefDescription": "Bus access, Normal, Cacheable, Shareable" + }, + { + "PublicDescription": "Bus access, not Normal, Cacheable, Shareable", + "EventCode": "0x63", + "EventName": "BUS_ACCESS_NOT_SHARED", + "BriefDescription": "Bus access, not Normal, Cacheable, Shareable" + }, + { + "PublicDescription": "Bus access, Normal", + "EventCode": "0x64", + "EventName": "BUS_ACCESS_NORMAL", + "BriefDescription": "Bus access, Normal" + }, + { + "PublicDescription": "Bus access, peripheral", + "EventCode": "0x65", + "EventName": "BUS_ACCESS_PERIPH", + "BriefDescription": "Bus access, peripheral" + }, + { + "PublicDescription": "Data memory access, read", + "EventCode": "0x66", + "EventName": "MEM_ACCESS_RD", + "BriefDescription": "Data memory access, read" + }, + { + "PublicDescription": "Data memory access, write", + "EventCode": "0x67", + "EventName": "MEM_ACCESS_WR", + "BriefDescription": "Data memory access, write" + }, + { + "PublicDescription": "Unaligned access, read", + "EventCode": "0x68", + "EventName": "UNALIGNED_LD_SPEC", + "BriefDescription": "Unaligned access, read" + }, + { + "PublicDescription": "Unaligned access, write", + "EventCode": "0x69", + "EventName": "UNALIGNED_ST_SPEC", + "BriefDescription": "Unaligned access, write" + }, + { + "PublicDescription": "Unaligned access", + "EventCode": "0x6a", + "EventName": "UNALIGNED_LDST_SPEC", + "BriefDescription": "Unaligned access" + }, + { + "PublicDescription": "Exclusive operation speculatively executed, LDREX or LDX", + "EventCode": "0x6c", + "EventName": "LDREX_SPEC", + "BriefDescription": "Exclusive operation speculatively executed, LDREX or LDX" + }, + { + "PublicDescription": "Exclusive operation speculatively executed, STREX or STX pass", + "EventCode": "0x6d", + "EventName": "STREX_PASS_SPEC", + "BriefDescription": "Exclusive operation speculatively executed, STREX or STX pass" + }, + { + "PublicDescription": "Exclusive operation speculatively executed, STREX or STX fail", + "EventCode": "0x6e", + "EventName": "STREX_FAIL_SPEC", + "BriefDescription": "Exclusive operation speculatively executed, STREX or STX fail" + }, + { + "PublicDescription": "Exclusive operation speculatively executed, STREX or STX", + "EventCode": "0x6f", + "EventName": "STREX_SPEC", + "BriefDescription": "Exclusive operation speculatively executed, STREX or STX" + }, + { + "PublicDescription": "Operation speculatively executed, load", + "EventCode": "0x70", + "EventName": "LD_SPEC", + "BriefDescription": "Operation speculatively executed, load" + }, + { + "PublicDescription": "Operation speculatively executed, store", + "EventCode": "0x71", + "EventName": "ST_SPEC", + "BriefDescription": "Operation speculatively executed, store" + }, + { + "PublicDescription": "Operation speculatively executed, load or store", + "EventCode": "0x72", + "EventName": "LDST_SPEC", + "BriefDescription": "Operation speculatively executed, load or store" + }, + { + "PublicDescription": "Operation speculatively executed, integer data processing", + "EventCode": "0x73", + "EventName": "DP_SPEC", + "BriefDescription": "Operation speculatively executed, integer data processing" + }, + { + "PublicDescription": "Operation speculatively executed, Advanced SIMD instruction", + "EventCode": "0x74", + "EventName": "ASE_SPEC", + "BriefDescription": "Operation speculatively executed, Advanced SIMD instruction" + }, + { + "PublicDescription": "Operation speculatively executed, floating-point instruction", + "EventCode": "0x75", + "EventName": "VFP_SPEC", + "BriefDescription": "Operation speculatively executed, floating-point instruction" + }, + { + "PublicDescription": "Operation speculatively executed, software change of the PC", + "EventCode": "0x76", + "EventName": "PC_WRITE_SPEC", + "BriefDescription": "Operation speculatively executed, software change of the PC" + }, + { + "PublicDescription": "Operation speculatively executed, Cryptographic instruction", + "EventCode": "0x77", + "EventName": "CRYPTO_SPEC", + "BriefDescription": "Operation speculatively executed, Cryptographic instruction" + }, + { + "PublicDescription": "Branch speculatively executed, immediate branch", + "EventCode": "0x78", + "EventName": "BR_IMMED_SPEC", + "BriefDescription": "Branch speculatively executed, immediate branch" + }, + { + "PublicDescription": "Branch speculatively executed, procedure return", + "EventCode": "0x79", + "EventName": "BR_RETURN_SPEC", + "BriefDescription": "Branch speculatively executed, procedure return" + }, + { + "PublicDescription": "Branch speculatively executed, indirect branch", + "EventCode": "0x7a", + "EventName": "BR_INDIRECT_SPEC", + "BriefDescription": "Branch speculatively executed, indirect branch" + }, + { + "PublicDescription": "Barrier speculatively executed, ISB", + "EventCode": "0x7c", + "EventName": "ISB_SPEC", + "BriefDescription": "Barrier speculatively executed, ISB" + }, + { + "PublicDescription": "Barrier speculatively executed, DSB", + "EventCode": "0x7d", + "EventName": "DSB_SPEC", + "BriefDescription": "Barrier speculatively executed, DSB" + }, + { + "PublicDescription": "Barrier speculatively executed, DMB", + "EventCode": "0x7e", + "EventName": "DMB_SPEC", + "BriefDescription": "Barrier speculatively executed, DMB" + }, + { + "PublicDescription": "Exception taken, Other synchronous", + "EventCode": "0x81", + "EventName": "EXC_UNDEF", + "BriefDescription": "Exception taken, Other synchronous" + }, + { + "PublicDescription": "Exception taken, Supervisor Call", + "EventCode": "0x82", + "EventName": "EXC_SVC", + "BriefDescription": "Exception taken, Supervisor Call" + }, + { + "PublicDescription": "Exception taken, Instruction Abort", + "EventCode": "0x83", + "EventName": "EXC_PABORT", + "BriefDescription": "Exception taken, Instruction Abort" + }, + { + "PublicDescription": "Exception taken, Data Abort and SError", + "EventCode": "0x84", + "EventName": "EXC_DABORT", + "BriefDescription": "Exception taken, Data Abort and SError" + }, + { + "PublicDescription": "Exception taken, IRQ", + "EventCode": "0x86", + "EventName": "EXC_IRQ", + "BriefDescription": "Exception taken, IRQ" + }, + { + "PublicDescription": "Exception taken, FIQ", + "EventCode": "0x87", + "EventName": "EXC_FIQ", + "BriefDescription": "Exception taken, FIQ" + }, + { + "PublicDescription": "Exception taken, Secure Monitor Call", + "EventCode": "0x88", + "EventName": "EXC_SMC", + "BriefDescription": "Exception taken, Secure Monitor Call" + }, + { + "PublicDescription": "Exception taken, Hypervisor Call", + "EventCode": "0x8a", + "EventName": "EXC_HVC", + "BriefDescription": "Exception taken, Hypervisor Call" + }, + { + "PublicDescription": "Exception taken, Instruction Abort not taken locally", + "EventCode": "0x8b", + "EventName": "EXC_TRAP_PABORT", + "BriefDescription": "Exception taken, Instruction Abort not taken locally" + }, + { + "PublicDescription": "Exception taken, Data Abort or SError not taken locally", + "EventCode": "0x8c", + "EventName": "EXC_TRAP_DABORT", + "BriefDescription": "Exception taken, Data Abort or SError not taken locally" + }, + { + "PublicDescription": "Exception taken, Other traps not taken locally", + "EventCode": "0x8d", + "EventName": "EXC_TRAP_OTHER", + "BriefDescription": "Exception taken, Other traps not taken locally" + }, + { + "PublicDescription": "Exception taken, IRQ not taken locally", + "EventCode": "0x8e", + "EventName": "EXC_TRAP_IRQ", + "BriefDescription": "Exception taken, IRQ not taken locally" + }, + { + "PublicDescription": "Exception taken, FIQ not taken locally", + "EventCode": "0x8f", + "EventName": "EXC_TRAP_FIQ", + "BriefDescription": "Exception taken, FIQ not taken locally" + }, + { + "PublicDescription": "Release consistency operation speculatively executed, Load-Acquire", + "EventCode": "0x90", + "EventName": "RC_LD_SPEC", + "BriefDescription": "Release consistency operation speculatively executed, Load-Acquire" + }, + { + "PublicDescription": "Release consistency operation speculatively executed, Store-Release", + "EventCode": "0x91", + "EventName": "RC_ST_SPEC", + "BriefDescription": "Release consistency operation speculatively executed, Store-Release" + }, + { + "PublicDescription": "Attributable Level 3 data or unified cache access, read", + "EventCode": "0xa0", + "EventName": "L3D_CACHE_RD", + "BriefDescription": "Attributable Level 3 data or unified cache access, read" + }, + { + "PublicDescription": "Attributable Level 3 data or unified cache access, write", + "EventCode": "0xa1", + "EventName": "L3D_CACHE_WR", + "BriefDescription": "Attributable Level 3 data or unified cache access, write" + }, + { + "PublicDescription": "Attributable Level 3 data or unified cache refill, read", + "EventCode": "0xa2", + "EventName": "L3D_CACHE_REFILL_RD", + "BriefDescription": "Attributable Level 3 data or unified cache refill, read" + }, + { + "PublicDescription": "Attributable Level 3 data or unified cache refill, write", + "EventCode": "0xa3", + "EventName": "L3D_CACHE_REFILL_WR", + "BriefDescription": "Attributable Level 3 data or unified cache refill, write" + }, + { + "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, victim", + "EventCode": "0xa6", + "EventName": "L3D_CACHE_WB_VICTIM", + "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, victim" + }, + { + "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean", + "EventCode": "0xa7", + "EventName": "L3D_CACHE_WB_CLEAN", + "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean" + }, + { + "PublicDescription": "Attributable Level 3 data or unified cache access, invalidate", + "EventCode": "0xa8", + "EventName": "L3D_CACHE_INVAL", + "BriefDescription": "Attributable Level 3 data or unified cache access, invalidate" + } +] diff --git a/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json b/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json index 5347350c360c..3e7ac409d894 100644 --- a/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json +++ b/tools/perf/pmu-events/arch/nds32/n13/atcpmu.json @@ -286,5 +286,5 @@ "EventCode": "0x21e", "EventName": "pop25_inst", "BriefDescription": "V3 POP25 instructions" - }, + } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json new file mode 100644 index 000000000000..b57526fa44f2 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json @@ -0,0 +1,676 @@ +[ + { + "BriefDescription": "Percentage of cycles that are run cycles", + "MetricExpr": "PM_RUN_CYC / PM_CYC * 100", + "MetricGroup": "General", + "MetricName": "RUN_CYCLES_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average cycles per completed instruction", + "MetricExpr": "PM_CYC / PM_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "CYCLES_PER_INSTRUCTION" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled for any reason", + "MetricExpr": "PM_DISP_STALL_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because there was a flush", + "MetricExpr": "PM_DISP_STALL_FLUSH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_FLUSH_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because the MMU was handling a translation miss", + "MetricExpr": "PM_DISP_STALL_TRANSLATION / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_TRANSLATION_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction ERAT miss", + "MetricExpr": "PM_DISP_STALL_IERAT_ONLY_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IERAT_ONLY_MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction TLB miss", + "MetricExpr": "PM_DISP_STALL_ITLB_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_ITLB_MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss", + "MetricExpr": "PM_DISP_STALL_IC_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L2", + "MetricExpr": "PM_DISP_STALL_IC_L2 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_L2_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L3", + "MetricExpr": "PM_DISP_STALL_IC_L3 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_L3_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from any source beyond the local L3", + "MetricExpr": "PM_DISP_STALL_IC_L3MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_L3MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss after a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_ICMISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_ICMISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L2 after suffering a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L2 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_IC_L2_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L3 after suffering a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_IC_L3_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from any source beyond the local L3 after suffering a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_IC_L3MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any reason", + "MetricExpr": "PM_DISP_STALL_HELD_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch", + "MetricExpr": "PM_DISP_STALL_HELD_SYNC_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISP_HELD_STALL_SYNC_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch while waiting on the scoreboard", + "MetricExpr": "PM_DISP_STALL_HELD_SCOREBOARD_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISP_HELD_STALL_SCOREBOARD_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch due to issue queue full", + "MetricExpr": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISP_HELD_STALL_ISSQ_FULL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the mapper/SRB was full", + "MetricExpr": "PM_DISP_STALL_HELD_RENAME_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_RENAME_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the STF mapper/SRB was full", + "MetricExpr": "PM_DISP_STALL_HELD_STF_MAPPER_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_STF_MAPPER_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the XVFC mapper/SRB was full", + "MetricExpr": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_XVFC_MAPPER_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any other reason", + "MetricExpr": "PM_DISP_STALL_HELD_OTHER_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_OTHER_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction has been dispatched but not issued for any reason", + "MetricExpr": "PM_ISSUE_STALL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "ISSUE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting to be finished in one of the execution units", + "MetricExpr": "PM_EXEC_STALL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "EXECUTION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction spent executing an NTC instruction that gets flushed some time after dispatch", + "MetricExpr": "PM_EXEC_STALL_NTC_FLUSH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "NTC_FLUSH_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTF instruction finishes at dispatch", + "MetricExpr": "PM_EXEC_STALL_FIN_AT_DISP / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "FIN_AT_DISP_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the branch unit", + "MetricExpr": "PM_EXEC_STALL_BRU / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "BRU_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a simple fixed point instruction that is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_SIMPLE_FX / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "SIMPLE_FX_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the VSU", + "MetricExpr": "PM_EXEC_STALL_VSU / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "VSU_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting to be finished in one of the execution units", + "MetricExpr": "PM_EXEC_STALL_TRANSLATION / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "TRANSLATION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a load or store that suffered a translation miss", + "MetricExpr": "PM_EXEC_STALL_DERAT_ONLY_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DERAT_ONLY_MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is recovering from a TLB miss", + "MetricExpr": "PM_EXEC_STALL_DERAT_DTLB_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DERAT_DTLB_MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_LSU / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LSU_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a load that is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_LOAD / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LOAD_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3", + "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L2L3_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3, with an RC dispatch conflict", + "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L2L3_CONFLICT_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3, without an RC dispatch conflict", + "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L2L3_NOCONFLICT_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a source beyond the local L2 and local L3", + "MetricExpr": "PM_EXEC_STALL_DMISS_L3MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L3MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a neighbor chiplet's L2 or L3 in the same chip", + "MetricExpr": "PM_EXEC_STALL_DMISS_L21_L31 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L21_L31_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from L4, local memory or OpenCAPI chip", + "MetricExpr": "PM_EXEC_STALL_DMISS_LMEM / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_LMEM_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a remote chip (cache, L4, memory or OpenCAPI) in the same group", + "MetricExpr": "PM_EXEC_STALL_DMISS_OFF_CHIP / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_OFF_CHIP_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a distant chip (cache, L4, memory or OpenCAPI chip)", + "MetricExpr": "PM_EXEC_STALL_DMISS_OFF_NODE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_OFF_NODE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing a TLBIEL instruction", + "MetricExpr": "PM_EXEC_STALL_TLBIEL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "TLBIEL_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is finishing a load after its data has been reloaded from a data source beyond the local L1, OR when the LSU is processing an L1-hit, OR when the NTF instruction merged with another load in the LMQ", + "MetricExpr": "PM_EXEC_STALL_LOAD_FINISH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LOAD_FINISH_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a store that is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_STORE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STORE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is in the store unit outside of handling store misses or other special store operations", + "MetricExpr": "PM_EXEC_STALL_STORE_PIPE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STORE_PIPE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a store whose cache line was not resident in the L1 and had to wait for allocation of the missing line into the L1", + "MetricExpr": "PM_EXEC_STALL_STORE_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STORE_MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a TLBIE instruction waiting for a response from the L2", + "MetricExpr": "PM_EXEC_STALL_TLBIE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "TLBIE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing a PTESYNC instruction", + "MetricExpr": "PM_EXEC_STALL_PTESYNC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "PTESYNC_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction cannot complete because the thread was blocked", + "MetricExpr": "PM_CMPL_STALL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction cannot complete because it was interrupted by ANY exception", + "MetricExpr": "PM_CMPL_STALL_EXCEPTION / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "EXCEPTION_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is stuck at finish waiting for the non-speculative finish of either a STCX instruction waiting for its result or a load waiting for non-critical sectors of data and ECC", + "MetricExpr": "PM_CMPL_STALL_MEM_ECC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "MEM_ECC_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a STCX instruction waiting for resolution from the nest", + "MetricExpr": "PM_CMPL_STALL_STCX / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STCX_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a LWSYNC instruction waiting to complete", + "MetricExpr": "PM_CMPL_STALL_LWSYNC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LWSYNC_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a HWSYNC instruction stuck at finish waiting for a response from the L2", + "MetricExpr": "PM_CMPL_STALL_HWSYNC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "HWSYNC_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction required special handling before completion", + "MetricExpr": "PM_CMPL_STALL_SPECIAL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "SPECIAL_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because fetch was being held, so there was nothing in the pipeline for this thread", + "MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_FETCH_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of power management", + "MetricExpr": "PM_DISP_STALL_HELD_HALT_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_HALT_CPI" + }, + { + "BriefDescription": "Percentage of flushes per completed instruction", + "MetricExpr": "PM_FLUSH / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "FLUSH_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of flushes due to a branch mispredict per completed instruction", + "MetricExpr": "PM_FLUSH_MPRED / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "BR_MPRED_FLUSH_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of branch mispredictions per completed instruction", + "MetricExpr": "PM_BR_MPRED_CMPL / PM_RUN_INST_CMPL", + "MetricGroup": "Others", + "MetricName": "BRANCH_MISPREDICTION_RATE" + }, + { + "BriefDescription": "Percentage of finished loads that missed in the L1", + "MetricExpr": "PM_LD_MISS_L1 / PM_LD_REF_L1 * 100", + "MetricGroup": "Others", + "MetricName": "L1_LD_MISS_RATIO", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were loads that missed the L1", + "MetricExpr": "PM_LD_MISS_L1 / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "L1_LD_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions when the DPTEG required for the load/store instruction in execution was missing from the TLB", + "MetricExpr": "PM_DTLB_MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "DTLB_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of completed instructions dispatched per instruction completed", + "MetricExpr": "PM_INST_DISP / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "DISPATCH_PER_INST_CMPL" + }, + { + "BriefDescription": "Percentage of completed instructions that were a demand load that did not hit in the L1 or L2", + "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "General", + "MetricName": "L2_LD_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were demand fetches that missed the L1 icache", + "MetricExpr": "PM_L1_ICACHE_MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Instruction_Misses", + "MetricName": "L1_INST_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were demand fetches that reloaded from beyond the L3 icache", + "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "General", + "MetricName": "L3_INST_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of completed instructions per cycle", + "MetricExpr": "PM_INST_CMPL / PM_CYC", + "MetricGroup": "General", + "MetricName": "IPC" + }, + { + "BriefDescription": "Average number of cycles per completed instruction group", + "MetricExpr": "PM_CYC / PM_1PLUS_PPC_CMPL", + "MetricGroup": "General", + "MetricName": "CYCLES_PER_COMPLETED_INSTRUCTIONS_SET" + }, + { + "BriefDescription": "Percentage of cycles when at least 1 instruction dispatched", + "MetricExpr": "PM_1PLUS_PPC_DISP / PM_RUN_CYC * 100", + "MetricGroup": "General", + "MetricName": "CYCLES_ATLEAST_ONE_INST_DISPATCHED", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of finished loads per completed instruction", + "MetricExpr": "PM_LD_REF_L1 / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "LOADS_PER_INST" + }, + { + "BriefDescription": "Average number of finished stores per completed instruction", + "MetricExpr": "PM_ST_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "STORES_PER_INST" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction", + "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L2_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from beyond the L3 per completed instruction", + "MetricExpr": "PM_DATA_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 4k page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_4K / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_4K_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 64k page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_64K / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_64K_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of run cycles per completed instruction", + "MetricExpr": "PM_RUN_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "RUN_CPI" + }, + { + "BriefDescription": "Percentage of DERAT misses per completed instruction", + "MetricExpr": "PM_DERAT_MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of completed instructions per run cycle", + "MetricExpr": "PM_RUN_INST_CMPL / PM_RUN_CYC", + "MetricGroup": "General", + "MetricName": "RUN_IPC" + }, + { + "BriefDescription": "Average number of completed instructions per instruction group", + "MetricExpr": "PM_RUN_INST_CMPL / PM_1PLUS_PPC_CMPL", + "MetricGroup": "General", + "MetricName": "AVERAGE_COMPLETED_INSTRUCTION_SET_SIZE" + }, + { + "BriefDescription": "Average number of finished instructions per completed instructions", + "MetricExpr": "PM_INST_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "INST_FIN_PER_CMPL" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTF instruction is completing and the finish was overlooked", + "MetricExpr": "PM_EXEC_STALL_UNKNOWN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "EXEC_STALL_UNKOWN_CPI" + }, + { + "BriefDescription": "Percentage of finished branches that were taken", + "MetricExpr": "PM_BR_TAKEN_CMPL / PM_BR_FIN * 100", + "MetricGroup": "General", + "MetricName": "TAKEN_BRANCHES", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were a demand load that did not hit in the L1, L2, or the L3", + "MetricExpr": "PM_DATA_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "General", + "MetricName": "L3_LD_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of finished branches per completed instruction", + "MetricExpr": "PM_BR_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "BRANCHES_PER_INST" + }, + { + "BriefDescription": "Average number of instructions finished in the LSU per completed instruction", + "MetricExpr": "PM_LSU_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "LSU_PER_INST" + }, + { + "BriefDescription": "Average number of instructions finished in the VSU per completed instruction", + "MetricExpr": "PM_VSU_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "VSU_PER_INST" + }, + { + "BriefDescription": "Average number of TLBIE instructions finished in the LSU per completed instruction", + "MetricExpr": "PM_TLBIE_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "TLBIE_PER_INST" + }, + { + "BriefDescription": "Average number of STCX instructions finshed per completed instruction", + "MetricExpr": "PM_STCX_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "STXC_PER_INST" + }, + { + "BriefDescription": "Average number of LARX instructions finshed per completed instruction", + "MetricExpr": "PM_LARX_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "LARX_PER_INST" + }, + { + "BriefDescription": "Average number of PTESYNC instructions finshed per completed instruction", + "MetricExpr": "PM_PTESYNC_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "PTESYNC_PER_INST" + }, + { + "BriefDescription": "Average number of simple fixed-point instructions finshed in the store unit per completed instruction", + "MetricExpr": "PM_FX_LSU_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "FX_PER_INST" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded the L1 cache", + "MetricExpr": "PM_LD_DEMAND_MISS_L1 / PM_LD_MISS_L1 * 100", + "MetricGroup": "General", + "MetricName": "DL1_MISS_RELOADS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L2", + "MetricExpr": "PM_DATA_FROM_L2MISS / PM_LD_DEMAND_MISS_L1 * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L2_MISS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L3", + "MetricExpr": "PM_DATA_FROM_L3MISS / PM_LD_DEMAND_MISS_L1 * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3_MISS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of cycles stalled due to the NTC instruction waiting for a load miss to resolve from a source beyond the local L2 and local L3", + "MetricExpr": "DMISS_L3MISS_STALL_CPI / RUN_CPI * 100", + "MetricGroup": "General", + "MetricName": "DCACHE_MISS_CPI", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 2M page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_2M / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_2M_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 16M page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_16M / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_16M_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "DERAT miss ratio for 4K page size", + "MetricExpr": "PM_DERAT_MISS_4K / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_4K_MISS_RATIO" + }, + { + "BriefDescription": "DERAT miss ratio for 2M page size", + "MetricExpr": "PM_DERAT_MISS_2M / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_2M_MISS_RATIO" + }, + { + "BriefDescription": "DERAT miss ratio for 16M page size", + "MetricExpr": "PM_DERAT_MISS_16M / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_16M_MISS_RATIO" + }, + { + "BriefDescription": "DERAT miss ratio for 64K page size", + "MetricExpr": "PM_DERAT_MISS_64K / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_64K_MISS_RATIO" + }, + { + "BriefDescription": "Percentage of DERAT misses that resulted in TLB reloads", + "MetricExpr": "PM_DTLB_MISS / PM_DERAT_MISS * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_MISS_RELOAD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of icache misses that were reloaded from beyond the local L3", + "MetricExpr": "PM_INST_FROM_L3MISS / PM_L1_ICACHE_MISS * 100", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L3_MISS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of icache reloads from the beyond the L3 per completed instruction", + "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L3_MISS_RATE", + "ScaleUnit": "1%" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json index b6b7f29ca831..86bd8ba9391d 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json @@ -124,5 +124,5 @@ "EventName": "L2C_STORES_SENT", "BriefDescription": "L2C Stores Sent", "PublicDescription": "Incremented by one for every store sent to Level-2 (L1.5) cache" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json index 5da8296b667e..1a5e4f89c57e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -390,5 +390,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json index 17fb5241928b..fc762e9f1d6e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json @@ -54,5 +54,5 @@ "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json index 89e070727e1b..4942b20a1ea1 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -369,5 +369,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/basic.json b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json index 17fb5241928b..fc762e9f1d6e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json @@ -54,5 +54,5 @@ "EventName": "PROBLEM_STATE_INSTRUCTIONS", "BriefDescription": "Problem-State Instructions", "PublicDescription": "Problem-State Instruction Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json index c998e4f1d1d2..ad79189050a0 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json @@ -26,5 +26,5 @@ "EventName": "ECC_BLOCKED_CYCLES_COUNT", "BriefDescription": "ECC Blocked Cycles Count", "PublicDescription": "This counter counts the total number of CPU cycles blocked for the elliptic-curve cryptography (ECC) functions issued by the CPU because the ECC coprocessor is busy performing a function issued by another CPU." - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json index 24c4ba2a9ae5..8ac61f8f286b 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json @@ -397,5 +397,5 @@ "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE", "BriefDescription": "Cycle count with two threads active", "PublicDescription": "Cycle count with two threads active" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json index b7b42a870bb0..86b29fd181cf 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json @@ -166,5 +166,5 @@ "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", "BriefDescription": "L1I Off-Chip L3 Sourced Writes", "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json index 2dd8dafff2ef..783de7f1aeaa 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json @@ -82,5 +82,5 @@ "EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES", "BriefDescription": "Problem-State L1D Penalty Cycles", "PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json index db286f19e7b6..3f28007d3892 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json @@ -110,5 +110,5 @@ "EventName": "AES_BLOCKED_CYCLES", "BriefDescription": "AES Blocked Cycles", "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" - }, + } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json index 162251037219..f40cbed89418 100644 --- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json @@ -243,5 +243,5 @@ "EventName": "TX_C_TABORT_SPECIAL", "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic", "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete" - }, + } ] diff --git a/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json index 788766f45dbc..41bac1c6a008 100644 --- a/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json +++ b/tools/perf/pmu-events/arch/test/test_soc/cpu/uncore.json @@ -19,6 +19,22 @@ "EdgeDetect": "0" }, { + "Unit": "CBO", + "EventCode": "0xE0", + "UMask": "0x00", + "EventName": "event-hyphen", + "BriefDescription": "UNC_CBO_HYPHEN", + "PublicDescription": "UNC_CBO_HYPHEN" + }, + { + "Unit": "CBO", + "EventCode": "0xC0", + "UMask": "0x00", + "EventName": "event-two-hyph", + "BriefDescription": "UNC_CBO_TWO_HYPH", + "PublicDescription": "UNC_CBO_TWO_HYPH" + }, + { "EventCode": "0x7", "EventName": "uncore_hisi_l3c.rd_hit_cpipe", "BriefDescription": "Total read hits", @@ -38,5 +54,5 @@ "BriefDescription": "Total cache hits", "PublicDescription": "Total cache hits", "Unit": "imc" - }, + } ] diff --git a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json index 0f681a6e10ea..c7e7528db315 100644 --- a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json +++ b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json @@ -6,4 +6,11 @@ "Unit": "sys_ddr_pmu", "Compat": "v8" }, + { + "BriefDescription": "ccn read-cycles event", + "ConfigCode": "0x2c", + "EventName": "sys_ccn_pmu.read_cycles", + "Unit": "sys_ccn_pmu", + "Compat": "0x01" + } ] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 57ddbb9f9b31..14b9a8ab15b9 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -311,5 +311,5 @@ "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency" - }, + } ] diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 7c887d37b893..1a57c3f81dd4 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -45,6 +45,7 @@ #include <sys/resource.h> /* getrlimit */ #include <ftw.h> #include <sys/stat.h> +#include <linux/compiler.h> #include <linux/list.h> #include "jsmn.h" #include "json.h" @@ -70,7 +71,7 @@ struct json_event { char *metric_constraint; }; -enum aggr_mode_class convert(const char *aggr_mode) +static enum aggr_mode_class convert(const char *aggr_mode) { if (!strcmp(aggr_mode, "PerCore")) return PerCore; @@ -81,8 +82,6 @@ enum aggr_mode_class convert(const char *aggr_mode) return -1; } -typedef int (*func)(void *data, struct json_event *je); - static LIST_HEAD(sys_event_tables); struct sys_event_table { @@ -361,7 +360,7 @@ static int close_table; static void print_events_table_prefix(FILE *fp, const char *tblname) { - fprintf(fp, "struct pmu_event %s[] = {\n", tblname); + fprintf(fp, "static const struct pmu_event %s[] = {\n", tblname); close_table = 1; } @@ -369,7 +368,7 @@ static int print_events_table_entry(void *data, struct json_event *je) { struct perf_entry_data *pd = data; FILE *outfp = pd->outfp; - char *topic = pd->topic; + char *topic_local = pd->topic; /* * TODO: Remove formatting chars after debugging to reduce @@ -384,7 +383,7 @@ static int print_events_table_entry(void *data, struct json_event *je) fprintf(outfp, "\t.desc = \"%s\",\n", je->desc); if (je->compat) fprintf(outfp, "\t.compat = \"%s\",\n", je->compat); - fprintf(outfp, "\t.topic = \"%s\",\n", topic); + fprintf(outfp, "\t.topic = \"%s\",\n", topic_local); if (je->long_desc && je->long_desc[0]) fprintf(outfp, "\t.long_desc = \"%s\",\n", je->long_desc); if (je->pmu) @@ -470,7 +469,7 @@ static void free_arch_std_events(void) } } -static int save_arch_std_events(void *data, struct json_event *je) +static int save_arch_std_events(void *data __maybe_unused, struct json_event *je) { struct event_struct *es; @@ -575,10 +574,12 @@ static int json_events(const char *fn, struct json_event je = {}; char *arch_std = NULL; unsigned long long eventcode = 0; + unsigned long long configcode = 0; struct msrmap *msr = NULL; jsmntok_t *msrval = NULL; jsmntok_t *precise = NULL; jsmntok_t *obj = tok++; + bool configcode_present = false; EXPECT(obj->type == JSMN_OBJECT, obj, "expected object"); for (j = 0; j < obj->size; j += 2) { @@ -601,6 +602,12 @@ static int json_events(const char *fn, addfield(map, &code, "", "", val); eventcode |= strtoul(code, NULL, 0); free(code); + } else if (json_streq(map, field, "ConfigCode")) { + char *code = NULL; + addfield(map, &code, "", "", val); + configcode |= strtoul(code, NULL, 0); + free(code); + configcode_present = true; } else if (json_streq(map, field, "ExtSel")) { char *code = NULL; addfield(map, &code, "", "", val); @@ -665,8 +672,6 @@ static int json_events(const char *fn, addfield(map, &je.metric_constraint, "", "", val); } else if (json_streq(map, field, "MetricExpr")) { addfield(map, &je.metric_expr, "", "", val); - for (s = je.metric_expr; *s; s++) - *s = tolower(*s); } else if (json_streq(map, field, "ArchStdEvent")) { addfield(map, &arch_std, "", "", val); for (s = arch_std; *s; s++) @@ -682,7 +687,10 @@ static int json_events(const char *fn, addfield(map, &extra_desc, " ", "(Precise event)", NULL); } - snprintf(buf, sizeof buf, "event=%#llx", eventcode); + if (configcode_present) + snprintf(buf, sizeof buf, "config=%#llx", configcode); + else + snprintf(buf, sizeof buf, "event=%#llx", eventcode); addfield(map, &event, ",", buf, NULL); if (je.desc && extra_desc) addfield(map, &je.desc, " ", extra_desc, NULL); @@ -786,7 +794,7 @@ static bool is_sys_dir(char *fname) static void print_mapping_table_prefix(FILE *outfp) { - fprintf(outfp, "struct pmu_events_map pmu_events_map[] = {\n"); + fprintf(outfp, "const struct pmu_events_map pmu_events_map[] = {\n"); } static void print_mapping_table_suffix(FILE *outfp) @@ -820,7 +828,7 @@ static void print_mapping_test_table(FILE *outfp) static void print_system_event_mapping_table_prefix(FILE *outfp) { - fprintf(outfp, "\nstruct pmu_sys_events pmu_sys_event_tables[] = {"); + fprintf(outfp, "\nconst struct pmu_sys_events pmu_sys_event_tables[] = {"); } static void print_system_event_mapping_table_suffix(FILE *outfp) @@ -1196,7 +1204,7 @@ int main(int argc, char *argv[]) const char *arch; const char *output_file; const char *start_dirname; - char *err_string_ext = ""; + const char *err_string_ext = ""; struct stat stbuf; prog = basename(argv[0]); diff --git a/tools/perf/pmu-events/jsmn.c b/tools/perf/pmu-events/jsmn.c index 11d1fa18bfa5..831dc44c4558 100644 --- a/tools/perf/pmu-events/jsmn.c +++ b/tools/perf/pmu-events/jsmn.c @@ -24,6 +24,7 @@ #include <stdlib.h> #include "jsmn.h" +#define JSMN_STRICT /* * Allocates a fresh unused token from the token pool. @@ -176,6 +177,14 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, jsmnerr_t r; int i; jsmntok_t *token; +#ifdef JSMN_STRICT + /* + * Keeps track of whether a new object/list/primitive is expected. New items are only + * allowed after an opening brace, comma or colon. A closing brace after a comma is not + * valid JSON. + */ + int expecting_item = 1; +#endif for (; parser->pos < len; parser->pos++) { char c; @@ -185,6 +194,10 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, switch (c) { case '{': case '[': +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; +#endif token = jsmn_alloc_token(parser, tokens, num_tokens); if (token == NULL) return JSMN_ERROR_NOMEM; @@ -196,6 +209,10 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, break; case '}': case ']': +#ifdef JSMN_STRICT + if (expecting_item) + return JSMN_ERROR_INVAL; +#endif type = (c == '}' ? JSMN_OBJECT : JSMN_ARRAY); for (i = parser->toknext - 1; i >= 0; i--) { token = &tokens[i]; @@ -219,6 +236,11 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, } break; case '\"': +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 0; +#endif r = jsmn_parse_string(parser, js, len, tokens, num_tokens); if (r < 0) @@ -229,11 +251,15 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, case '\t': case '\r': case '\n': - case ':': - case ',': case ' ': break; #ifdef JSMN_STRICT + case ':': + case ',': + if (expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 1; + break; /* * In strict mode primitives are: * numbers and booleans. @@ -253,6 +279,9 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, case 'f': case 'n': #else + case ':': + case ',': + break; /* * In non-strict mode every unquoted value * is a primitive. @@ -260,6 +289,12 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, /*FALL THROUGH */ default: #endif + +#ifdef JSMN_STRICT + if (!expecting_item) + return JSMN_ERROR_INVAL; + expecting_item = 0; +#endif r = jsmn_parse_primitive(parser, js, len, tokens, num_tokens); if (r < 0) @@ -282,7 +317,11 @@ jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len, return JSMN_ERROR_PART; } +#ifdef JSMN_STRICT + return expecting_item ? JSMN_ERROR_INVAL : JSMN_SUCCESS; +#else return JSMN_SUCCESS; +#endif } /* diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 5c2bf7275c1c..6efe73976440 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -41,19 +41,19 @@ struct pmu_events_map { const char *cpuid; const char *version; const char *type; /* core, uncore etc */ - struct pmu_event *table; + const struct pmu_event *table; }; struct pmu_sys_events { const char *name; - struct pmu_event *table; + const struct pmu_event *table; }; /* * Global table mapping each known CPU for the architecture to its * table of PMU events. */ -extern struct pmu_events_map pmu_events_map[]; -extern struct pmu_sys_events pmu_sys_event_tables[]; +extern const struct pmu_events_map pmu_events_map[]; +extern const struct pmu_sys_events pmu_sys_event_tables[]; #endif diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py index 1d3a189a9a54..66452a8ec358 100644 --- a/tools/perf/scripts/python/intel-pt-events.py +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -32,8 +32,7 @@ try: except: broken_pipe_exception = IOError -glb_switch_str = None -glb_switch_printed = True +glb_switch_str = {} glb_insn = False glb_disassembler = None glb_src = False @@ -70,6 +69,7 @@ def trace_begin(): ap = argparse.ArgumentParser(usage = "", add_help = False) ap.add_argument("--insn-trace", action='store_true') ap.add_argument("--src-trace", action='store_true') + ap.add_argument("--all-switch-events", action='store_true') global glb_args global glb_insn global glb_src @@ -256,10 +256,6 @@ def print_srccode(comm, param_dict, sample, symbol, dso, with_insn): print(start_str, src_str) def do_process_event(param_dict): - global glb_switch_printed - if not glb_switch_printed: - print(glb_switch_str) - glb_switch_printed = True event_attr = param_dict["attr"] sample = param_dict["sample"] raw_buf = param_dict["raw_buf"] @@ -274,6 +270,11 @@ def do_process_event(param_dict): dso = get_optional(param_dict, "dso") symbol = get_optional(param_dict, "symbol") + cpu = sample["cpu"] + if cpu in glb_switch_str: + print(glb_switch_str[cpu]) + del glb_switch_str[cpu] + if name[0:12] == "instructions": if glb_src: print_srccode(comm, param_dict, sample, symbol, dso, True) @@ -336,8 +337,6 @@ def auxtrace_error(typ, code, cpu, pid, tid, ip, ts, msg, cpumode, *x): sys.exit(1) def context_switch(ts, cpu, pid, tid, np_pid, np_tid, machine_pid, out, out_preempt, *x): - global glb_switch_printed - global glb_switch_str if out: out_str = "Switch out " else: @@ -350,6 +349,10 @@ def context_switch(ts, cpu, pid, tid, np_pid, np_tid, machine_pid, out, out_pree machine_str = "" else: machine_str = "machine PID %d" % machine_pid - glb_switch_str = "%16s %5d/%-5d [%03u] %9u.%09u %5d/%-5d %s %s" % \ + switch_str = "%16s %5d/%-5d [%03u] %9u.%09u %5d/%-5d %s %s" % \ (out_str, pid, tid, cpu, ts / 1000000000, ts %1000000000, np_pid, np_tid, machine_str, preempt_str) - glb_switch_printed = False + if glb_args.all_switch_events: + print(switch_str); + else: + global glb_switch_str + glb_switch_str[cpu] = switch_str diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 803ca426f8e6..af2b37ef7c70 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -65,6 +65,7 @@ perf-y += pe-file-parsing.o perf-y += expand-cgroup.o perf-y += perf-time-to-tsc.o perf-y += dlfilter-test.o +perf-y += sigtrap.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/api-io.c b/tools/perf/tests/api-io.c index 2ada86ad6084..e91cf2c127f1 100644 --- a/tools/perf/tests/api-io.c +++ b/tools/perf/tests/api-io.c @@ -289,8 +289,8 @@ static int test_get_dec(void) return ret; } -int test__api_io(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__api_io(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int ret = 0; @@ -302,3 +302,5 @@ int test__api_io(struct test *test __maybe_unused, ret = TEST_FAIL; return ret; } + +DEFINE_SUITE("Test api io", api_io); diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 9b40a25376ae..56fba08a3037 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -65,7 +65,7 @@ do { \ #define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field) -static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, +static int store_event(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags) { FILE *file; @@ -93,7 +93,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, /* syscall arguments */ __WRITE_ASS(fd, "d", fd); __WRITE_ASS(group_fd, "d", group_fd); - __WRITE_ASS(cpu, "d", cpu); + __WRITE_ASS(cpu, "d", cpu.cpu); __WRITE_ASS(pid, "d", pid); __WRITE_ASS(flags, "lu", flags); @@ -144,7 +144,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, return 0; } -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, +void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags) { int errno_saved = errno; @@ -178,7 +178,7 @@ static int run_dir(const char *d, const char *perf) return system(cmd) ? TEST_FAIL : TEST_OK; } -int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__attr(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct stat st; char path_perf[PATH_MAX]; @@ -207,3 +207,5 @@ int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) return TEST_SKIP; } + +DEFINE_SUITE("Setup struct perf_event_attr", attr); diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index b4b9a9488d51..79a980b1e786 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -82,7 +82,7 @@ static int do_test(struct evlist *evlist, int mmap_pages, } -int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0; char pid[16], sbuf[STRERR_BUFSIZE]; @@ -115,12 +115,13 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m goto out_delete_evlist; } - bzero(&parse_error, sizeof(parse_error)); + parse_events_error__init(&parse_error); /* * Set backward bit, ring buffer should be writing from end. Record * it in aux evlist */ err = parse_events(evlist, "syscalls:sys_enter_prctl/overwrite/", &parse_error); + parse_events_error__exit(&parse_error); if (err) { pr_debug("Failed to parse tracepoint event, try use root\n"); ret = TEST_SKIP; @@ -166,3 +167,5 @@ out_delete_evlist: evlist__delete(evlist); return ret; } + +DEFINE_SUITE("Read backward ring buffer", backward_ring_buffer); diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 12b805efdca0..4965dd666956 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -17,8 +17,8 @@ static unsigned long *get_bitmap(const char *str, int nbits) bm = bitmap_zalloc(nbits); if (map && bm) { - for (i = 0; i < map->nr; i++) - set_bit(map->map[i], bm); + for (i = 0; i < perf_cpu_map__nr(map); i++) + set_bit(perf_cpu_map__cpu(map, i).cpu, bm); } if (map) @@ -40,7 +40,7 @@ static int test_bitmap(const char *str) return ret; } -int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bitmap_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", test_bitmap("1")); TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5")); @@ -51,3 +51,5 @@ int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to convert map", test_bitmap("1-10,12-20,22-30,32-40")); return 0; } + +DEFINE_SUITE("Print bitmap", bitmap_print); diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index 489b50604cf2..d1ebb5561e5b 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -19,6 +19,19 @@ #include "../perf-sys.h" #include "cloexec.h" +/* + * PowerPC and S390 do not support creation of instruction breakpoints using the + * perf_event interface. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) +#define BP_ACCOUNT_IS_SUPPORTED 0 +#else +#define BP_ACCOUNT_IS_SUPPORTED 1 +#endif + static volatile long the_var; static noinline int test_function(void) @@ -173,13 +186,18 @@ static int detect_share(int wp_cnt, int bp_cnt) * we create another watchpoint to ensure * the slot accounting is correct */ -int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_accounting(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int has_ioctl = detect_ioctl(); int wp_cnt = detect_cnt(false); int bp_cnt = detect_cnt(true); int share = detect_share(wp_cnt, bp_cnt); + if (!BP_ACCOUNT_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + pr_debug("watchpoints count %d, breakpoints count %d, has_ioctl %d, share %d\n", wp_cnt, bp_cnt, has_ioctl, share); @@ -189,18 +207,4 @@ int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_un return bp_accounting(wp_cnt, share); } -bool test__bp_account_is_supported(void) -{ - /* - * PowerPC and S390 do not support creation of instruction - * breakpoints using the perf_event interface. - * - * Just disable the test for these architectures until these - * issues are resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) - return false; -#else - return true; -#endif -} +DEFINE_SUITE("Breakpoint accounting", bp_accounting); diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index ef37353636d8..1f2908f02389 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -161,11 +161,16 @@ static long long bp_count(int fd) return count; } -int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_signal(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct sigaction sa; long long count1, count2, count3; + if (!BP_SIGNAL_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); sa.sa_sigaction = (void *) sig_handler; @@ -285,29 +290,4 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused TEST_OK : TEST_FAIL; } -bool test__bp_signal_is_supported(void) -{ - /* - * PowerPC and S390 do not support creation of instruction - * breakpoints using the perf_event interface. - * - * ARM requires explicit rounding down of the instruction - * pointer in Thumb mode, and then requires the single-step - * to be handled explicitly in the overflow handler to avoid - * stepping into the SIGIO handler and getting stuck on the - * breakpointed instruction. - * - * Since arm64 has the same issue with arm for the single-step - * handling, this case also gets stuck on the breakpointed - * instruction. - * - * Just disable the test for these architectures until these - * issues are resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || \ - defined(__aarch64__) - return false; -#else - return true; -#endif -} +DEFINE_SUITE("Breakpoint overflow signal handler", bp_signal); diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index eb4dbbddf4ff..4e897c2cf26b 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -59,13 +59,18 @@ static long long bp_count(int fd) #define EXECUTIONS 10000 #define THRESHOLD 100 -int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_signal_overflow(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_event_attr pe; struct sigaction sa; long long count; int fd, i, fails = 0; + if (!BP_SIGNAL_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); sa.sa_sigaction = (void *) sig_handler; @@ -133,3 +138,5 @@ int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __may return fails ? TEST_FAIL : TEST_OK; } + +DEFINE_SUITE("Breakpoint overflow sampling", bp_signal_overflow); diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index fa03ff0dc083..573490530194 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -62,7 +62,6 @@ static int llseek_loop(void) static struct { enum test_llvm__testcase prog_id; - const char *desc; const char *name; const char *msg_compile_fail; const char *msg_load_fail; @@ -72,7 +71,6 @@ static struct { } bpf_testcase_table[] = { { .prog_id = LLVM_TESTCASE_BASE, - .desc = "Basic BPF filtering", .name = "[basic_bpf_test]", .msg_compile_fail = "fix 'perf test LLVM' first", .msg_load_fail = "load bpf object failed", @@ -81,7 +79,6 @@ static struct { }, { .prog_id = LLVM_TESTCASE_BASE, - .desc = "BPF pinning", .name = "[bpf_pinning]", .msg_compile_fail = "fix kbuild first", .msg_load_fail = "check your vmlinux setting?", @@ -92,7 +89,6 @@ static struct { #ifdef HAVE_BPF_PROLOGUE { .prog_id = LLVM_TESTCASE_BPF_PROLOGUE, - .desc = "BPF prologue generation", .name = "[bpf_prologue_test]", .msg_compile_fail = "fix kbuild first", .msg_load_fail = "check your vmlinux setting?", @@ -123,12 +119,13 @@ static int do_test(struct bpf_object *obj, int (*func)(void), struct parse_events_state parse_state; struct parse_events_error parse_error; - bzero(&parse_error, sizeof(parse_error)); + parse_events_error__init(&parse_error); bzero(&parse_state, sizeof(parse_state)); parse_state.error = &parse_error; INIT_LIST_HEAD(&parse_state.list); err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL); + parse_events_error__exit(&parse_error); if (err || list_empty(&parse_state.list)) { pr_debug("Failed to add events selected by BPF\n"); return TEST_FAIL; @@ -282,18 +279,6 @@ out: return ret; } -int test__bpf_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(bpf_testcase_table); -} - -const char *test__bpf_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table)) - return NULL; - return bpf_testcase_table[i].desc; -} - static int check_env(void) { int err; @@ -311,9 +296,13 @@ static int check_env(void) return err; } +/* temporarily disable libbpf deprecation warnings */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, - sizeof(insns) / sizeof(insns[0]), + ARRAY_SIZE(insns), license, kver_int, NULL, 0); +#pragma GCC diagnostic pop if (err < 0) { pr_err("Missing basic BPF support, skip this test: %s\n", strerror(errno)); @@ -324,7 +313,7 @@ static int check_env(void) return 0; } -int test__bpf(struct test *test __maybe_unused, int i) +static int test__bpf(int i) { int err; @@ -342,21 +331,60 @@ int test__bpf(struct test *test __maybe_unused, int i) err = __test__bpf(i); return err; } +#endif -#else -int test__bpf_subtest_get_nr(void) +static int test__basic_bpf_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return 0; +#ifdef HAVE_LIBBPF_SUPPORT + return test__bpf(0); +#else + pr_debug("Skip BPF test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -const char *test__bpf_subtest_get_desc(int i __maybe_unused) +static int test__bpf_pinning(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return NULL; +#ifdef HAVE_LIBBPF_SUPPORT + return test__bpf(1); +#else + pr_debug("Skip BPF test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -int test__bpf(struct test *test __maybe_unused, int i __maybe_unused) +static int test__bpf_prologue_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE) + return test__bpf(2); +#else pr_debug("Skip BPF test because BPF support is not compiled\n"); return TEST_SKIP; +#endif } + + +static struct test_case bpf_tests[] = { +#ifdef HAVE_LIBBPF_SUPPORT + TEST_CASE("Basic BPF filtering", basic_bpf_test), + TEST_CASE("BPF pinning", bpf_pinning), +#ifdef HAVE_BPF_PROLOGUE + TEST_CASE("BPF prologue generation", bpf_prologue_test), +#else + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), +#endif +#else + TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in"), + TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in"), + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), #endif + { .name = NULL, } +}; + +struct test_suite suite__bpf = { + .desc = "BPF filter", + .test_cases = bpf_tests, +}; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index da7dc5e45d0c..fac3717d9ba1 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -30,350 +30,135 @@ static bool dont_fork; -struct test __weak arch_tests[] = { - { - .func = NULL, - }, +struct test_suite *__weak arch_tests[] = { + NULL, }; -static struct test generic_tests[] = { - { - .desc = "vmlinux symtab matches kallsyms", - .func = test__vmlinux_matches_kallsyms, - }, - { - .desc = "Detect openat syscall event", - .func = test__openat_syscall_event, - }, - { - .desc = "Detect openat syscall event on all cpus", - .func = test__openat_syscall_event_on_all_cpus, - }, - { - .desc = "Read samples using the mmap interface", - .func = test__basic_mmap, - }, - { - .desc = "Test data source output", - .func = test__mem, - }, - { - .desc = "Parse event definition strings", - .func = test__parse_events, - }, - { - .desc = "Simple expression parser", - .func = test__expr, - }, - { - .desc = "PERF_RECORD_* events & perf_sample fields", - .func = test__PERF_RECORD, - }, - { - .desc = "Parse perf pmu format", - .func = test__pmu, - }, - { - .desc = "PMU events", - .func = test__pmu_events, - .subtest = { - .skip_if_fail = false, - .get_nr = test__pmu_events_subtest_get_nr, - .get_desc = test__pmu_events_subtest_get_desc, - .skip_reason = test__pmu_events_subtest_skip_reason, - }, - - }, - { - .desc = "DSO data read", - .func = test__dso_data, - }, - { - .desc = "DSO data cache", - .func = test__dso_data_cache, - }, - { - .desc = "DSO data reopen", - .func = test__dso_data_reopen, - }, - { - .desc = "Roundtrip evsel->name", - .func = test__perf_evsel__roundtrip_name_test, - }, - { - .desc = "Parse sched tracepoints fields", - .func = test__perf_evsel__tp_sched_test, - }, - { - .desc = "syscalls:sys_enter_openat event fields", - .func = test__syscall_openat_tp_fields, - }, - { - .desc = "Setup struct perf_event_attr", - .func = test__attr, - }, - { - .desc = "Match and link multiple hists", - .func = test__hists_link, - }, - { - .desc = "'import perf' in python", - .func = test__python_use, - }, - { - .desc = "Breakpoint overflow signal handler", - .func = test__bp_signal, - .is_supported = test__bp_signal_is_supported, - }, - { - .desc = "Breakpoint overflow sampling", - .func = test__bp_signal_overflow, - .is_supported = test__bp_signal_is_supported, - }, - { - .desc = "Breakpoint accounting", - .func = test__bp_accounting, - .is_supported = test__bp_account_is_supported, - }, - { - .desc = "Watchpoint", - .func = test__wp, - .is_supported = test__wp_is_supported, - .subtest = { - .skip_if_fail = false, - .get_nr = test__wp_subtest_get_nr, - .get_desc = test__wp_subtest_get_desc, - .skip_reason = test__wp_subtest_skip_reason, - }, - }, - { - .desc = "Number of exit events of a simple workload", - .func = test__task_exit, - }, - { - .desc = "Software clock events period values", - .func = test__sw_clock_freq, - }, - { - .desc = "Object code reading", - .func = test__code_reading, - }, - { - .desc = "Sample parsing", - .func = test__sample_parsing, - }, - { - .desc = "Use a dummy software event to keep tracking", - .func = test__keep_tracking, - }, - { - .desc = "Parse with no sample_id_all bit set", - .func = test__parse_no_sample_id_all, - }, - { - .desc = "Filter hist entries", - .func = test__hists_filter, - }, - { - .desc = "Lookup mmap thread", - .func = test__mmap_thread_lookup, - }, - { - .desc = "Share thread maps", - .func = test__thread_maps_share, - }, - { - .desc = "Sort output of hist entries", - .func = test__hists_output, - }, - { - .desc = "Cumulate child hist entries", - .func = test__hists_cumulate, - }, - { - .desc = "Track with sched_switch", - .func = test__switch_tracking, - }, - { - .desc = "Filter fds with revents mask in a fdarray", - .func = test__fdarray__filter, - }, - { - .desc = "Add fd to a fdarray, making it autogrow", - .func = test__fdarray__add, - }, - { - .desc = "kmod_path__parse", - .func = test__kmod_path__parse, - }, - { - .desc = "Thread map", - .func = test__thread_map, - }, - { - .desc = "LLVM search and compile", - .func = test__llvm, - .subtest = { - .skip_if_fail = true, - .get_nr = test__llvm_subtest_get_nr, - .get_desc = test__llvm_subtest_get_desc, - }, - }, - { - .desc = "Session topology", - .func = test__session_topology, - }, - { - .desc = "BPF filter", - .func = test__bpf, - .subtest = { - .skip_if_fail = true, - .get_nr = test__bpf_subtest_get_nr, - .get_desc = test__bpf_subtest_get_desc, - }, - }, - { - .desc = "Synthesize thread map", - .func = test__thread_map_synthesize, - }, - { - .desc = "Remove thread map", - .func = test__thread_map_remove, - }, - { - .desc = "Synthesize cpu map", - .func = test__cpu_map_synthesize, - }, - { - .desc = "Synthesize stat config", - .func = test__synthesize_stat_config, - }, - { - .desc = "Synthesize stat", - .func = test__synthesize_stat, - }, - { - .desc = "Synthesize stat round", - .func = test__synthesize_stat_round, - }, - { - .desc = "Synthesize attr update", - .func = test__event_update, - }, - { - .desc = "Event times", - .func = test__event_times, - }, - { - .desc = "Read backward ring buffer", - .func = test__backward_ring_buffer, - }, - { - .desc = "Print cpu map", - .func = test__cpu_map_print, - }, - { - .desc = "Merge cpu map", - .func = test__cpu_map_merge, - }, - - { - .desc = "Probe SDT events", - .func = test__sdt_event, - }, - { - .desc = "is_printable_array", - .func = test__is_printable_array, - }, - { - .desc = "Print bitmap", - .func = test__bitmap_print, - }, - { - .desc = "perf hooks", - .func = test__perf_hooks, - }, - { - .desc = "builtin clang support", - .func = test__clang, - .subtest = { - .skip_if_fail = true, - .get_nr = test__clang_subtest_get_nr, - .get_desc = test__clang_subtest_get_desc, - } - }, - { - .desc = "unit_number__scnprintf", - .func = test__unit_number__scnprint, - }, - { - .desc = "mem2node", - .func = test__mem2node, - }, - { - .desc = "time utils", - .func = test__time_utils, - }, - { - .desc = "Test jit_write_elf", - .func = test__jit_write_elf, - }, - { - .desc = "Test libpfm4 support", - .func = test__pfm, - .subtest = { - .skip_if_fail = true, - .get_nr = test__pfm_subtest_get_nr, - .get_desc = test__pfm_subtest_get_desc, - } - }, - { - .desc = "Test api io", - .func = test__api_io, - }, - { - .desc = "maps__merge_in", - .func = test__maps__merge_in, - }, - { - .desc = "Demangle Java", - .func = test__demangle_java, - }, - { - .desc = "Demangle OCaml", - .func = test__demangle_ocaml, - }, - { - .desc = "Parse and process metrics", - .func = test__parse_metric, - }, - { - .desc = "PE file support", - .func = test__pe_file_parsing, - }, - { - .desc = "Event expansion for cgroups", - .func = test__expand_cgroup_events, - }, - { - .desc = "Convert perf time to TSC", - .func = test__perf_time_to_tsc, - .is_supported = test__tsc_is_supported, - }, - { - .desc = "dlfilter C API", - .func = test__dlfilter, - }, - { - .func = NULL, - }, +static struct test_suite *generic_tests[] = { + &suite__vmlinux_matches_kallsyms, + &suite__openat_syscall_event, + &suite__openat_syscall_event_on_all_cpus, + &suite__basic_mmap, + &suite__mem, + &suite__parse_events, + &suite__expr, + &suite__PERF_RECORD, + &suite__pmu, + &suite__pmu_events, + &suite__dso_data, + &suite__dso_data_cache, + &suite__dso_data_reopen, + &suite__perf_evsel__roundtrip_name_test, + &suite__perf_evsel__tp_sched_test, + &suite__syscall_openat_tp_fields, + &suite__attr, + &suite__hists_link, + &suite__python_use, + &suite__bp_signal, + &suite__bp_signal_overflow, + &suite__bp_accounting, + &suite__wp, + &suite__task_exit, + &suite__sw_clock_freq, + &suite__code_reading, + &suite__sample_parsing, + &suite__keep_tracking, + &suite__parse_no_sample_id_all, + &suite__hists_filter, + &suite__mmap_thread_lookup, + &suite__thread_maps_share, + &suite__hists_output, + &suite__hists_cumulate, + &suite__switch_tracking, + &suite__fdarray__filter, + &suite__fdarray__add, + &suite__kmod_path__parse, + &suite__thread_map, + &suite__llvm, + &suite__session_topology, + &suite__bpf, + &suite__thread_map_synthesize, + &suite__thread_map_remove, + &suite__cpu_map_synthesize, + &suite__synthesize_stat_config, + &suite__synthesize_stat, + &suite__synthesize_stat_round, + &suite__event_update, + &suite__event_times, + &suite__backward_ring_buffer, + &suite__cpu_map_print, + &suite__cpu_map_merge, + &suite__sdt_event, + &suite__is_printable_array, + &suite__bitmap_print, + &suite__perf_hooks, + &suite__clang, + &suite__unit_number__scnprint, + &suite__mem2node, + &suite__time_utils, + &suite__jit_write_elf, + &suite__pfm, + &suite__api_io, + &suite__maps__merge_in, + &suite__demangle_java, + &suite__demangle_ocaml, + &suite__parse_metric, + &suite__pe_file_parsing, + &suite__expand_cgroup_events, + &suite__perf_time_to_tsc, + &suite__dlfilter, + &suite__sigtrap, + NULL, }; -static struct test *tests[] = { +static struct test_suite **tests[] = { generic_tests, arch_tests, }; +static int num_subtests(const struct test_suite *t) +{ + int num; + + if (!t->test_cases) + return 0; + + num = 0; + while (t->test_cases[num].name) + num++; + + return num; +} + +static bool has_subtests(const struct test_suite *t) +{ + return num_subtests(t) > 1; +} + +static const char *skip_reason(const struct test_suite *t, int subtest) +{ + if (t->test_cases && subtest >= 0) + return t->test_cases[subtest].skip_reason; + + return NULL; +} + +static const char *test_description(const struct test_suite *t, int subtest) +{ + if (t->test_cases && subtest >= 0) + return t->test_cases[subtest].desc; + + return t->desc; +} + +static test_fnptr test_function(const struct test_suite *t, int subtest) +{ + if (subtest <= 0) + return t->test_cases[0].run_case; + + return t->test_cases[subtest].run_case; +} + static bool perf_test__matches(const char *desc, int curr, int argc, const char *argv[]) { int i; @@ -398,7 +183,7 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char return false; } -static int run_test(struct test *test, int subtest) +static int run_test(struct test_suite *test, int subtest) { int status, err = -1, child = dont_fork ? 0 : fork(); char sbuf[STRERR_BUFSIZE]; @@ -430,7 +215,7 @@ static int run_test(struct test *test, int subtest) } } - err = test->func(test, subtest); + err = test_function(test, subtest)(test, subtest); if (!dont_fork) exit(err); } @@ -450,24 +235,19 @@ static int run_test(struct test *test, int subtest) return err; } -#define for_each_test(j, t) \ +#define for_each_test(j, k, t) \ for (j = 0; j < ARRAY_SIZE(tests); j++) \ - for (t = &tests[j][0]; t->func; t++) + for (k = 0, t = tests[j][k]; tests[j][k]; k++, t = tests[j][k]) -static int test_and_print(struct test *t, bool force_skip, int subtest) +static int test_and_print(struct test_suite *t, int subtest) { int err; - if (!force_skip) { - pr_debug("\n--- start ---\n"); - err = run_test(t, subtest); - pr_debug("---- end ----\n"); - } else { - pr_debug("\n--- force skipped ---\n"); - err = TEST_SKIP; - } + pr_debug("\n--- start ---\n"); + err = run_test(t, subtest); + pr_debug("---- end ----\n"); - if (!t->subtest.get_nr) + if (!has_subtests(t)) pr_debug("%s:", t->desc); else pr_debug("%s subtest %d:", t->desc, subtest + 1); @@ -477,11 +257,10 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) pr_info(" Ok\n"); break; case TEST_SKIP: { - const char *skip_reason = NULL; - if (t->subtest.skip_reason) - skip_reason = t->subtest.skip_reason(subtest); - if (skip_reason) - color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", skip_reason); + const char *reason = skip_reason(t, subtest); + + if (reason) + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", reason); else color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n"); } @@ -580,7 +359,7 @@ struct shell_test { const char *file; }; -static int shell_test__run(struct test *test, int subdir __maybe_unused) +static int shell_test__run(struct test_suite *test, int subdir __maybe_unused) { int err; char script[PATH_MAX]; @@ -622,24 +401,34 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, for_each_shell_test(entlist, n_dirs, st.dir, ent) { int curr = i++; char desc[256]; - struct test test = { - .desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name), - .func = shell_test__run, + struct test_case test_cases[] = { + { + .desc = shell_test__description(desc, + sizeof(desc), + st.dir, + ent->d_name), + .run_case = shell_test__run, + }, + { .name = NULL, } + }; + struct test_suite test_suite = { + .desc = test_cases[0].desc, + .test_cases = test_cases, .priv = &st, }; - if (!perf_test__matches(test.desc, curr, argc, argv)) + if (!perf_test__matches(test_suite.desc, curr, argc, argv)) continue; st.file = ent->d_name; - pr_info("%2d: %-*s:", i, width, test.desc); + pr_info("%3d: %-*s:", i, width, test_suite.desc); if (intlist__find(skiplist, i)) { color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); continue; } - test_and_print(&test, false, -1); + test_and_print(&test_suite, 0); } for (e = 0; e < n_dirs; e++) @@ -650,33 +439,31 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) { - struct test *t; - unsigned int j; + struct test_suite *t; + unsigned int j, k; int i = 0; int width = shell_tests__max_desc_width(); - for_each_test(j, t) { - int len = strlen(t->desc); + for_each_test(j, k, t) { + int len = strlen(test_description(t, -1)); if (width < len) width = len; } - for_each_test(j, t) { - int curr = i++, err; + for_each_test(j, k, t) { + int curr = i++; int subi; - if (!perf_test__matches(t->desc, curr, argc, argv)) { + if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) { bool skip = true; int subn; - if (!t->subtest.get_nr) - continue; - - subn = t->subtest.get_nr(); + subn = num_subtests(t); for (subi = 0; subi < subn; subi++) { - if (perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv)) + if (perf_test__matches(test_description(t, subi), + curr, argc, argv)) skip = false; } @@ -684,22 +471,17 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) continue; } - if (t->is_supported && !t->is_supported()) { - pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc); - continue; - } - - pr_info("%2d: %-*s:", i, width, t->desc); + pr_info("%3d: %-*s:", i, width, test_description(t, -1)); if (intlist__find(skiplist, i)) { color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); continue; } - if (!t->subtest.get_nr) { - test_and_print(t, false, -1); + if (!has_subtests(t)) { + test_and_print(t, -1); } else { - int subn = t->subtest.get_nr(); + int subn = num_subtests(t); /* * minus 2 to align with normal testcases. * For subtest we print additional '.x' in number. @@ -709,7 +491,6 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) * 35.1: Basic BPF llvm compiling test : Ok */ int subw = width > 2 ? width - 2 : width; - bool skip = false; if (subn <= 0) { color_fprintf(stderr, PERF_COLOR_YELLOW, @@ -719,21 +500,20 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) pr_info("\n"); for (subi = 0; subi < subn; subi++) { - int len = strlen(t->subtest.get_desc(subi)); + int len = strlen(test_description(t, subi)); if (subw < len) subw = len; } for (subi = 0; subi < subn; subi++) { - if (!perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv)) + if (!perf_test__matches(test_description(t, subi), + curr, argc, argv)) continue; - pr_info("%2d.%1d: %-*s:", i, subi + 1, subw, - t->subtest.get_desc(subi)); - err = test_and_print(t, skip, subi); - if (err != TEST_OK && t->subtest.skip_if_fail) - skip = true; + pr_info("%3d.%1d: %-*s:", i, subi + 1, subw, + test_description(t, subi)); + test_and_print(t, subi); } } } @@ -759,14 +539,14 @@ static int perf_test__list_shell(int argc, const char **argv, int i) for_each_shell_test(entlist, n_dirs, path, ent) { int curr = i++; char bf[256]; - struct test t = { + struct test_suite t = { .desc = shell_test__description(bf, sizeof(bf), path, ent->d_name), }; if (!perf_test__matches(t.desc, curr, argc, argv)) continue; - pr_info("%2d: %s\n", i, t.desc); + pr_info("%3d: %s\n", i, t.desc); } @@ -778,26 +558,25 @@ static int perf_test__list_shell(int argc, const char **argv, int i) static int perf_test__list(int argc, const char **argv) { - unsigned int j; - struct test *t; + unsigned int j, k; + struct test_suite *t; int i = 0; - for_each_test(j, t) { + for_each_test(j, k, t) { int curr = i++; - if (!perf_test__matches(t->desc, curr, argc, argv) || - (t->is_supported && !t->is_supported())) + if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) continue; - pr_info("%2d: %s\n", i, t->desc); + pr_info("%3d: %s\n", i, test_description(t, -1)); - if (t->subtest.get_nr) { - int subn = t->subtest.get_nr(); + if (has_subtests(t)) { + int subn = num_subtests(t); int subi; for (subi = 0; subi < subn; subi++) - pr_info("%2d:%1d: %s\n", i, subi + 1, - t->subtest.get_desc(subi)); + pr_info("%3d:%1d: %s\n", i, subi + 1, + test_description(t, subi)); } } @@ -828,6 +607,9 @@ int cmd_test(int argc, const char **argv) if (ret < 0) return ret; + /* Unbuffered output */ + setvbuf(stdout, NULL, _IONBF, 0); + argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) return perf_test__list(argc - 1, argv + 1); diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c index 2577d3ed1531..a7111005d5b9 100644 --- a/tools/perf/tests/clang.c +++ b/tools/perf/tests/clang.c @@ -3,44 +3,30 @@ #include "c++/clang-c.h" #include <linux/kernel.h> -static struct { - int (*func)(void); - const char *desc; -} clang_testcase_table[] = { -#ifdef HAVE_LIBCLANGLLVM_SUPPORT - { - .func = test__clang_to_IR, - .desc = "builtin clang compile C source to IR", - }, - { - .func = test__clang_to_obj, - .desc = "builtin clang compile C source to ELF object", - }, -#endif -}; - -int test__clang_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(clang_testcase_table); -} - -const char *test__clang_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table)) - return NULL; - return clang_testcase_table[i].desc; -} - #ifndef HAVE_LIBCLANGLLVM_SUPPORT -int test__clang(struct test *test __maybe_unused, int i __maybe_unused) +static int test__clang_to_IR(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { return TEST_SKIP; } -#else -int test__clang(struct test *test __maybe_unused, int i) + +static int test__clang_to_obj(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table)) - return TEST_FAIL; - return clang_testcase_table[i].func(); + return TEST_SKIP; } #endif + +static struct test_case clang_tests[] = { + TEST_CASE_REASON("builtin clang compile C source to IR", clang_to_IR, + "not compiled in"), + TEST_CASE_REASON("builtin clang compile C source to ELF object", + clang_to_obj, + "not compiled in"), + { .name = NULL, } +}; + +struct test_suite suite__clang = { + .desc = "builtin clang support", + .test_cases = clang_tests, +}; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9b4a765e4b73..5610767b407f 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -606,7 +606,8 @@ static int do_test_code_reading(bool try_kcore) } ret = perf_event__synthesize_thread_map(NULL, threads, - perf_event__process, machine, false); + perf_event__process, machine, + true, false); if (ret < 0) { pr_debug("perf_event__synthesize_thread_map failed\n"); goto out_err; @@ -715,7 +716,7 @@ out_err: return err; } -int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__code_reading(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret; @@ -742,3 +743,5 @@ int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unu return -1; }; } + +DEFINE_SUITE("Object code reading", code_reading); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 0472b110fe65..84e87e31f119 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -38,7 +38,7 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", map->nr == 20); for (i = 0; i < 20; i++) { - TEST_ASSERT_VAL("wrong cpu", map->map[i] == i); + TEST_ASSERT_VAL("wrong cpu", map->map[i].cpu == i); } perf_cpu_map__put(map); @@ -67,15 +67,15 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, map = cpu_map__new_data(data); TEST_ASSERT_VAL("wrong nr", map->nr == 2); - TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1); - TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256); + TEST_ASSERT_VAL("wrong cpu", map->map[0].cpu == 1); + TEST_ASSERT_VAL("wrong cpu", map->map[1].cpu == 256); TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); perf_cpu_map__put(map); return 0; } -int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_cpu_map *cpus; @@ -111,7 +111,7 @@ static int cpu_map_print(const char *str) return !strcmp(buf, str); } -int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1")); TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5")); @@ -123,7 +123,7 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un return 0; } -int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_merge(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_cpu_map *a = perf_cpu_map__new("4,2,1"); struct perf_cpu_map *b = perf_cpu_map__new("4,5,7"); @@ -137,3 +137,7 @@ int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_un perf_cpu_map__put(c); return 0; } + +DEFINE_SUITE("Synthesize cpu map", cpu_map_synthesize); +DEFINE_SUITE("Print cpu map", cpu_map_print); +DEFINE_SUITE("Merge cpu map", cpu_map_merge); diff --git a/tools/perf/tests/demangle-java-test.c b/tools/perf/tests/demangle-java-test.c index 8f3b90832fb0..44d1be303b67 100644 --- a/tools/perf/tests/demangle-java-test.c +++ b/tools/perf/tests/demangle-java-test.c @@ -7,7 +7,7 @@ #include "debug.h" #include "demangle-java.h" -int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__demangle_java(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_OK; char *buf = NULL; @@ -40,3 +40,5 @@ int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_un return ret; } + +DEFINE_SUITE("Demangle Java", demangle_java); diff --git a/tools/perf/tests/demangle-ocaml-test.c b/tools/perf/tests/demangle-ocaml-test.c index 0043be812355..90a4285e2ad5 100644 --- a/tools/perf/tests/demangle-ocaml-test.c +++ b/tools/perf/tests/demangle-ocaml-test.c @@ -7,7 +7,7 @@ #include "debug.h" #include "demangle-ocaml.h" -int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_OK; char *buf = NULL; @@ -41,3 +41,5 @@ int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_u return ret; } + +DEFINE_SUITE("Demangle OCaml", demangle_ocaml); diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c index bc03b5df6828..84352d55347d 100644 --- a/tools/perf/tests/dlfilter-test.c +++ b/tools/perf/tests/dlfilter-test.c @@ -398,7 +398,7 @@ static void test_data__free(struct test_data *td) } } -int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct test_data td = {.fd = -1}; int pid = getpid(); @@ -414,3 +414,5 @@ int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused) test_data__free(&td); return err; } + +DEFINE_SUITE("dlfilter C API", dlfilter); diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 43e1b01e5afc..3419a4ab5590 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -113,7 +113,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine) return fd; } -int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; struct dso *dso; @@ -248,7 +248,7 @@ static int set_fd_limit(int n) return setrlimit(RLIMIT_NOFILE, &rlim); } -int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data_cache(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(); @@ -318,7 +318,7 @@ static long new_limit(int count) return ret; } -int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(), lim = new_limit(3); @@ -393,3 +393,7 @@ int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_ TEST_ASSERT_VAL("failed leaking files", nr == nr_end); return 0; } + +DEFINE_SUITE("DSO data read", dso_data); +DEFINE_SUITE("DSO data cache", dso_data_cache); +DEFINE_SUITE("DSO data reopen", dso_data_reopen); diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index c756284b3b13..2dab2d262060 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -195,7 +195,8 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *th return ret; } -int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dwarf_unwind(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct machine *machine; struct thread *thread; @@ -237,3 +238,5 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu machine__delete(machine); return err; } + +DEFINE_SUITE("Test dwarf unwind", dwarf_unwind); diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 04ce4401f775..7606eb3df92f 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -216,7 +216,7 @@ out_err: * and checks that enabled and running times * match. */ -int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__event_times(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err, ret = 0; @@ -239,3 +239,5 @@ int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unus #undef _T return ret; } + +DEFINE_SUITE("Event times", event_times); diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 44a50527f9d9..78db4d704e76 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -75,20 +75,19 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong id", ev->id == 123); TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS); - TEST_ASSERT_VAL("wrong cpus", map->nr == 3); - TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1); - TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2); - TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3); + TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__nr(map) == 3); + TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 0).cpu == 1); + TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 1).cpu == 2); + TEST_ASSERT_VAL("wrong cpus", perf_cpu_map__cpu(map, 2).cpu == 3); perf_cpu_map__put(map); return 0; } -int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__event_update(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct evsel *evsel; struct event_name tmp; struct evlist *evlist = evlist__new_default(); - char *unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to get evlist", evlist); @@ -99,7 +98,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123); - evsel->unit = unit; + free((char *)evsel->unit); + evsel->unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to synthesize attr update unit", !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit)); @@ -119,7 +119,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); - free(unit); evlist__delete(evlist); return 0; } + +DEFINE_SUITE("Synthesize attr update", event_update); diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 4e09f0a312af..fdbf17642e45 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -99,7 +99,8 @@ out_delete_evlist: #define perf_evsel__name_array_test(names, distance) \ __perf_evsel__name_array_test(names, ARRAY_SIZE(names), distance) -int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_evsel__roundtrip_name_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = 0, ret = 0; @@ -120,3 +121,5 @@ int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int return ret; } + +DEFINE_SUITE("Roundtrip evsel->name", perf_evsel__roundtrip_name_test); diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index f9e34bd26cf3..cf4da3d748c2 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -32,7 +32,8 @@ static int evsel__test_field(struct evsel *evsel, const char *name, int size, bo return ret; } -int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evsel *evsel = evsel__newtp("sched", "sched_switch"); int ret = 0; @@ -87,3 +88,5 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes evsel__delete(evsel); return ret; } + +DEFINE_SUITE("Parse sched tracepoints fields", perf_evsel__tp_sched_test); diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index 0e46aeb843ce..dfefe5b60eb2 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -124,17 +124,19 @@ static int expand_group_events(void) evlist = evlist__new(); TEST_ASSERT_VAL("failed to get evlist", evlist); + parse_events_error__init(&err); ret = parse_events(evlist, event_str, &err); if (ret < 0) { pr_debug("failed to parse event '%s', err %d, str '%s'\n", event_str, ret, err.str); - parse_events_print_error(&err, event_str); + parse_events_error__print(&err, event_str); goto out; } rblist__init(&metric_events); ret = test_expand_events(evlist, &metric_events); out: + parse_events_error__exit(&err); evlist__delete(evlist); return ret; } @@ -193,7 +195,7 @@ static int expand_metric_events(void) .metric_name = NULL, }, }; - struct pmu_events_map ev_map = { + const struct pmu_events_map ev_map = { .cpuid = "test", .version = "1", .type = "core", @@ -219,8 +221,8 @@ out: return ret; } -int test__expand_cgroup_events(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__expand_cgroup_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int ret; @@ -238,3 +240,5 @@ int test__expand_cgroup_events(struct test *test __maybe_unused, return ret; } + +DEFINE_SUITE("Event expansion for cgroups", expand_cgroup_events); diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 4d01051951cd..d54c5371c6a6 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -1,88 +1,193 @@ // SPDX-License-Identifier: GPL-2.0 #include "util/debug.h" #include "util/expr.h" +#include "util/smt.h" #include "tests.h" #include <stdlib.h> #include <string.h> #include <linux/zalloc.h> +static int test_ids_union(void) +{ + struct hashmap *ids1, *ids2; + + /* Empty union. */ + ids1 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids1); + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 0); + + /* Union {foo, bar} against {}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("foo")), 0); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids1, strdup("bar")), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2); + + /* Union {foo, bar} against {foo}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("foo")), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 2); + + /* Union {foo, bar} against {bar,baz}. */ + ids2 = ids__new(); + TEST_ASSERT_VAL("ids__new", ids2); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("bar")), 0); + TEST_ASSERT_EQUAL("ids__insert", ids__insert(ids2, strdup("baz")), 0); + + ids1 = ids__union(ids1, ids2); + TEST_ASSERT_EQUAL("union", (int)hashmap__size(ids1), 3); + + ids__free(ids1); + + return 0; +} + static int test(struct expr_parse_ctx *ctx, const char *e, double val2) { double val; - if (expr__parse(&val, ctx, e, 1)) + if (expr__parse(&val, ctx, e)) TEST_ASSERT_VAL("parse test failed", 0); TEST_ASSERT_VAL("unexpected value", val == val2); return 0; } -int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct expr_id_data *val_ptr; const char *p; - double val; + double val, num_cpus, num_cores, num_dies, num_packages; int ret; - struct expr_parse_ctx ctx; - - expr__ctx_init(&ctx); - expr__add_id_val(&ctx, strdup("FOO"), 1); - expr__add_id_val(&ctx, strdup("BAR"), 2); - - ret = test(&ctx, "1+1", 2); - ret |= test(&ctx, "FOO+BAR", 3); - ret |= test(&ctx, "(BAR/2)%2", 1); - ret |= test(&ctx, "1 - -4", 5); - ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); - ret |= test(&ctx, "1-1 | 1", 1); - ret |= test(&ctx, "1-1 & 1", 0); - ret |= test(&ctx, "min(1,2) + 1", 2); - ret |= test(&ctx, "max(1,2) + 1", 3); - ret |= test(&ctx, "1+1 if 3*4 else 0", 2); - ret |= test(&ctx, "1.1 + 2.1", 3.2); - ret |= test(&ctx, ".1 + 2.", 2.1); - ret |= test(&ctx, "d_ratio(1, 2)", 0.5); - ret |= test(&ctx, "d_ratio(2.5, 0)", 0); - ret |= test(&ctx, "1.1 < 2.2", 1); - ret |= test(&ctx, "2.2 > 1.1", 1); - ret |= test(&ctx, "1.1 < 1.1", 0); - ret |= test(&ctx, "2.2 > 2.2", 0); - ret |= test(&ctx, "2.2 < 1.1", 0); - ret |= test(&ctx, "1.1 > 2.2", 0); - - if (ret) + struct expr_parse_ctx *ctx; + + TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0); + + ctx = expr__ctx_new(); + TEST_ASSERT_VAL("expr__ctx_new", ctx); + expr__add_id_val(ctx, strdup("FOO"), 1); + expr__add_id_val(ctx, strdup("BAR"), 2); + + ret = test(ctx, "1+1", 2); + ret |= test(ctx, "FOO+BAR", 3); + ret |= test(ctx, "(BAR/2)%2", 1); + ret |= test(ctx, "1 - -4", 5); + ret |= test(ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); + ret |= test(ctx, "1-1 | 1", 1); + ret |= test(ctx, "1-1 & 1", 0); + ret |= test(ctx, "min(1,2) + 1", 2); + ret |= test(ctx, "max(1,2) + 1", 3); + ret |= test(ctx, "1+1 if 3*4 else 0", 2); + ret |= test(ctx, "1.1 + 2.1", 3.2); + ret |= test(ctx, ".1 + 2.", 2.1); + ret |= test(ctx, "d_ratio(1, 2)", 0.5); + ret |= test(ctx, "d_ratio(2.5, 0)", 0); + ret |= test(ctx, "1.1 < 2.2", 1); + ret |= test(ctx, "2.2 > 1.1", 1); + ret |= test(ctx, "1.1 < 1.1", 0); + ret |= test(ctx, "2.2 > 2.2", 0); + ret |= test(ctx, "2.2 < 1.1", 0); + ret |= test(ctx, "1.1 > 2.2", 0); + + if (ret) { + expr__ctx_free(ctx); return ret; + } p = "FOO/0"; - ret = expr__parse(&val, &ctx, p, 1); + ret = expr__parse(&val, ctx, p); TEST_ASSERT_VAL("division by zero", ret == -1); p = "BAR/"; - ret = expr__parse(&val, &ctx, p, 1); + ret = expr__parse(&val, ctx, p); TEST_ASSERT_VAL("missing operand", ret == -1); - expr__ctx_clear(&ctx); - TEST_ASSERT_VAL("find other", - expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", - &ctx, 1) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 3); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAR", + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO", + ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", + (void **)&val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", + (void **)&val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BAZ", + + expr__ctx_clear(ctx); + ctx->runtime = 3; + TEST_ASSERT_VAL("find ids", + expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "BOZO", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", (void **)&val_ptr)); - expr__ctx_clear(&ctx); - TEST_ASSERT_VAL("find other", - expr__find_other("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", - NULL, &ctx, 3) == 0); - TEST_ASSERT_VAL("find other", hashmap__size(&ctx.ids) == 2); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT1,param=3/", + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("dash\\-event1 - dash\\-event2", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", (void **)&val_ptr)); - TEST_ASSERT_VAL("find other", hashmap__find(&ctx.ids, "EVENT2,param=3/", + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", (void **)&val_ptr)); - expr__ctx_clear(&ctx); + /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("EVENT1 if #smt_on else EVENT2", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, + smt_on() ? "EVENT1" : "EVENT2", + (void **)&val_ptr)); + + /* The expression is a constant 1.0 without needing to evaluate EVENT1. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("1.0 if EVENT1 > 100.0 else 1.0", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0); + + /* Test toplogy constants appear well ordered. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0); + TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0); + TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores); + TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0); + TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies); + TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0); + + if (num_dies) // Some platforms do not have CPU die support, for example s390 + TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); + + /* + * Source count returns the number of events aggregating in a leader + * event including the leader. Check parsing yields an id. + */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("source count", + expr__find_ids("source_count(EVENT1)", + NULL, ctx) == 0); + TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1); + TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", + (void **)&val_ptr)); + + expr__ctx_free(ctx); return 0; } + +DEFINE_SUITE("Simple expression parser", expr); diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c index d9eca8e86a6b..40983c3574b1 100644 --- a/tools/perf/tests/fdarray.c +++ b/tools/perf/tests/fdarray.c @@ -28,7 +28,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE return printed + fdarray__fprintf(fda, fp); } -int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__fdarray__filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int nr_fds, err = TEST_FAIL; struct fdarray *fda = fdarray__new(5, 5); @@ -89,7 +89,7 @@ out: return err; } -int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__fdarray__add(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct fdarray *fda = fdarray__new(2, 2); @@ -158,3 +158,6 @@ out_delete: out: return err; } + +DEFINE_SUITE("Filter fds with revents mask in a fdarray", fdarray__filter); +DEFINE_SUITE("Add fd to a fdarray, making it autogrow", fdarray__add); diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c index f797f9823e89..95f3be1b683a 100644 --- a/tools/perf/tests/genelf.c +++ b/tools/perf/tests/genelf.c @@ -16,8 +16,8 @@ #define TEMPL "/tmp/perf-test-XXXXXX" -int test__jit_write_elf(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__jit_write_elf(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { #ifdef HAVE_JITDUMP static unsigned char x86_code[] = { @@ -49,3 +49,5 @@ int test__jit_write_elf(struct test *test __maybe_unused, return TEST_SKIP; #endif } + +DEFINE_SUITE("Test jit_write_elf", jit_write_elf); diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 890cb1f5bf53..17f4fcd6bdce 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -689,7 +689,7 @@ out: return err; } -int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_cumulate(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -736,3 +736,5 @@ out: return err; } + +DEFINE_SUITE("Cumulate child hist entries", hists_cumulate); diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index ca6120cd1d90..08cbeb9e39ae 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -101,7 +101,7 @@ out: return TEST_FAIL; } -int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -325,3 +325,5 @@ out: return err; } + +DEFINE_SUITE("Filter hist entries", hists_filter); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index a024d3f3a412..c575e13a850d 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -264,7 +264,7 @@ static int validate_link(struct hists *leader, struct hists *other) return __validate_link(leader, 0) || __validate_link(other, 1); } -int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_link(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; struct hists *hists, *first_hists; @@ -339,3 +339,5 @@ out: return err; } + +DEFINE_SUITE("Match and link multiple hists", hists_link); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 8973f35df604..0bde4a768c15 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -575,7 +575,7 @@ out: return err; } -int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_output(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -623,3 +623,5 @@ out: return err; } + +DEFINE_SUITE("Sort output of hist entries", hists_output); diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c index 9c7b3baca4fe..f72de2457ff1 100644 --- a/tools/perf/tests/is_printable_array.c +++ b/tools/perf/tests/is_printable_array.c @@ -5,7 +5,7 @@ #include "debug.h" #include "print_binary.h" -int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__is_printable_array(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 }; char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 }; @@ -36,3 +36,5 @@ int test__is_printable_array(struct test *test __maybe_unused, int subtest __may return TEST_OK; } + +DEFINE_SUITE("is_printable_array", is_printable_array); diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index a0438b0f0805..dd2067312452 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -61,7 +61,7 @@ static int find_comm(struct evlist *evlist, const char *comm) * when an event is disabled but a dummy software event is not disabled. If the * test passes %0 is returned, otherwise %-1 is returned. */ -int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__keep_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, @@ -160,3 +160,5 @@ out_err: return err; } + +DEFINE_SUITE("Use a dummy software event to keep tracking", keep_tracking); diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index e483210b176b..dfe1bd5dabaa 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -47,7 +47,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect) #define M(path, c, e) \ TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e)) -int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__kmod_path__parse(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { /* path alloc_name kmod comp name */ T("/xxxx/xxxx/x-x.ko", true , true, 0 , "[x_x]"); @@ -159,3 +159,5 @@ int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_un return 0; } + +DEFINE_SUITE("kmod_path__parse", kmod_path__parse); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 33e43cce9064..8ac0a3a457ef 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -124,7 +124,7 @@ out: return ret; } -int test__llvm(struct test *test __maybe_unused, int subtest) +static int test__llvm(int subtest) { int ret; void *obj_buf = NULL; @@ -148,32 +148,72 @@ int test__llvm(struct test *test __maybe_unused, int subtest) return ret; } +#endif //HAVE_LIBBPF_SUPPORT -int test__llvm_subtest_get_nr(void) +static int test__llvm__bpf_base_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return __LLVM_TESTCASE_MAX; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BASE); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -const char *test__llvm_subtest_get_desc(int subtest) -{ - if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) - return NULL; - - return bpf_source_table[subtest].desc; -} -#else //HAVE_LIBBPF_SUPPORT -int test__llvm(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__llvm__bpf_test_kbuild_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_KBUILD); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); return TEST_SKIP; +#endif } -int test__llvm_subtest_get_nr(void) +static int test__llvm__bpf_test_prologue_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return 0; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BPF_PROLOGUE); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -const char *test__llvm_subtest_get_desc(int subtest __maybe_unused) +static int test__llvm__bpf_test_relocation(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return NULL; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BPF_RELOCATION); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -#endif // HAVE_LIBBPF_SUPPORT + + +static struct test_case llvm_tests[] = { +#ifdef HAVE_LIBBPF_SUPPORT + TEST_CASE("Basic BPF llvm compile", llvm__bpf_base_prog), + TEST_CASE("kbuild searching", llvm__bpf_test_kbuild_prog), + TEST_CASE("Compile source for BPF prologue generation", + llvm__bpf_test_prologue_prog), + TEST_CASE("Compile source for BPF relocation", llvm__bpf_test_relocation), +#else + TEST_CASE_REASON("Basic BPF llvm compile", llvm__bpf_base_prog, "not compiled in"), + TEST_CASE_REASON("kbuild searching", llvm__bpf_test_kbuild_prog, "not compiled in"), + TEST_CASE_REASON("Compile source for BPF prologue generation", + llvm__bpf_test_prologue_prog, "not compiled in"), + TEST_CASE_REASON("Compile source for BPF relocation", + llvm__bpf_test_relocation, "not compiled in"), +#endif + { .name = NULL, } +}; + +struct test_suite suite__llvm = { + .desc = "LLVM search and compile", + .test_cases = llvm_tests, +}; diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index 1ac72919fa35..e308a3296cef 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -33,7 +33,7 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma return TEST_OK; } -int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct maps maps; unsigned int i; @@ -120,3 +120,5 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus maps__exit(&maps); return TEST_OK; } + +DEFINE_SUITE("maps__merge_in", maps__merge_in); diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c index 673a11a6cd1b..56014ec7d49d 100644 --- a/tools/perf/tests/mem.c +++ b/tools/perf/tests/mem.c @@ -23,7 +23,7 @@ static int check(union perf_mem_data_src data_src, return 0; } -int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused) +static int test__mem(struct test_suite *text __maybe_unused, int subtest __maybe_unused) { int ret = 0; union perf_mem_data_src src; @@ -56,3 +56,5 @@ int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused) return ret; } + +DEFINE_SUITE("Test data source output", mem); diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c index e4d0d58b97f8..4c96829510c9 100644 --- a/tools/perf/tests/mem2node.c +++ b/tools/perf/tests/mem2node.c @@ -25,14 +25,15 @@ static unsigned long *get_bitmap(const char *str, int nbits) { struct perf_cpu_map *map = perf_cpu_map__new(str); unsigned long *bm = NULL; - int i; bm = bitmap_zalloc(nbits); if (map && bm) { - for (i = 0; i < map->nr; i++) { - set_bit(map->map[i], bm); - } + struct perf_cpu cpu; + int i; + + perf_cpu_map__for_each_cpu(cpu, i, map) + set_bit(cpu.cpu, bm); } if (map) @@ -43,7 +44,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) return bm && map ? bm : NULL; } -int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__mem2node(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct mem2node map; struct memory_node nodes[3]; @@ -77,3 +78,5 @@ int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused) mem2node__exit(&map); return 0; } + +DEFINE_SUITE("mem2node", mem2node); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index d38757db2dc2..c3c17600f29c 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -29,7 +29,7 @@ * Then it checks if the number of syscalls reported as perf events by * the kernel corresponds to the number of syscalls made. */ -int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; @@ -59,11 +59,12 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse } CPU_ZERO(&cpu_set); - CPU_SET(cpus->map[0], &cpu_set); + CPU_SET(perf_cpu_map__cpu(cpus, 0).cpu, &cpu_set); sched_setaffinity(0, sizeof(cpu_set), &cpu_set); if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { pr_debug("sched_setaffinity() failed on CPU %d: %s ", - cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf))); + perf_cpu_map__cpu(cpus, 0).cpu, + str_error_r(errno, sbuf, sizeof(sbuf))); goto out_free_cpus; } @@ -164,3 +165,5 @@ out_free_threads: perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Read samples using the mmap interface", basic_mmap); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 8d9d4cbff76d..a4301fc7b770 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -135,7 +135,7 @@ static int synth_all(struct machine *machine) { return perf_event__synthesize_threads(NULL, perf_event__process, - machine, 0, 1); + machine, 1, 0, 1); } static int synth_process(struct machine *machine) @@ -147,7 +147,7 @@ static int synth_process(struct machine *machine) err = perf_event__synthesize_thread_map(NULL, map, perf_event__process, - machine, 0); + machine, 1, 0); perf_thread_map__put(map); return err; @@ -224,7 +224,7 @@ static int mmap_events(synth_cb synth) * * by using all thread objects. */ -int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__mmap_thread_lookup(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { /* perf_event__synthesize_threads synthesize */ TEST_ASSERT_VAL("failed with sythesizing all", @@ -236,3 +236,5 @@ int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __may return 0; } + +DEFINE_SUITE("Lookup mmap thread", mmap_thread_lookup); diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index f7dd6c463f04..1ab362323d25 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -19,9 +19,11 @@ #include "stat.h" #include "util/counts.h" -int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - int err = -1, fd, cpu; + int err = -1, fd, idx; + struct perf_cpu cpu; struct perf_cpu_map *cpus; struct evsel *evsel; unsigned int nr_openat_calls = 111, i; @@ -57,23 +59,23 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int goto out_evsel_delete; } - for (cpu = 0; cpu < cpus->nr; ++cpu) { - unsigned int ncalls = nr_openat_calls + cpu; + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + unsigned int ncalls = nr_openat_calls + idx; /* * XXX eventually lift this restriction in a way that * keeps perf building on older glibc installations * without CPU_ALLOC. 1024 cpus in 2010 still seems * a reasonable upper limit tho :-) */ - if (cpus->map[cpu] >= CPU_SETSIZE) { - pr_debug("Ignoring CPU %d\n", cpus->map[cpu]); + if (cpu.cpu >= CPU_SETSIZE) { + pr_debug("Ignoring CPU %d\n", cpu.cpu); continue; } - CPU_SET(cpus->map[cpu], &cpu_set); + CPU_SET(cpu.cpu, &cpu_set); if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { pr_debug("sched_setaffinity() failed on CPU %d: %s ", - cpus->map[cpu], + cpu.cpu, str_error_r(errno, sbuf, sizeof(sbuf))); goto out_close_fd; } @@ -81,37 +83,29 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int fd = openat(0, "/etc/passwd", O_RDONLY); close(fd); } - CPU_CLR(cpus->map[cpu], &cpu_set); + CPU_CLR(cpu.cpu, &cpu_set); } - /* - * Here we need to explicitly preallocate the counts, as if - * we use the auto allocation it will allocate just for 1 cpu, - * as we start by cpu 0. - */ - if (evsel__alloc_counts(evsel, cpus->nr, 1) < 0) { - pr_debug("evsel__alloc_counts(ncpus=%d)\n", cpus->nr); - goto out_close_fd; - } + evsel->core.cpus = perf_cpu_map__get(cpus); err = 0; - for (cpu = 0; cpu < cpus->nr; ++cpu) { + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { unsigned int expected; - if (cpus->map[cpu] >= CPU_SETSIZE) + if (cpu.cpu >= CPU_SETSIZE) continue; - if (evsel__read_on_cpu(evsel, cpu, 0) < 0) { + if (evsel__read_on_cpu(evsel, idx, 0) < 0) { pr_debug("evsel__read_on_cpu\n"); err = -1; break; } - expected = nr_openat_calls + cpu; - if (perf_counts(evsel->counts, cpu, 0)->val != expected) { + expected = nr_openat_calls + idx; + if (perf_counts(evsel->counts, idx, 0)->val != expected) { pr_debug("evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", - expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val); + expected, cpu.cpu, perf_counts(evsel->counts, idx, 0)->val); err = -1; } } @@ -127,3 +121,5 @@ out_thread_map_delete: perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Detect openat syscall event on all cpus", openat_syscall_event_on_all_cpus); diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 5e4af2f0f14a..a7b2800652e4 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -22,7 +22,8 @@ #define AT_FDCWD -100 #endif -int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct record_opts opts = { .target = { @@ -142,3 +143,5 @@ out_delete_evlist: out: return err; } + +DEFINE_SUITE("syscalls:sys_enter_openat event fields", syscall_openat_tp_fields); diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index 85a8f0fe7aea..7f4c13c4b14d 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -13,7 +13,8 @@ #include "tests.h" #include "util/counts.h" -int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__openat_syscall_event(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = -1, fd; struct evsel *evsel; @@ -66,3 +67,5 @@ out_thread_map_delete: perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Detect openat syscall event", openat_syscall_event); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index fd3556cc9ad4..e71efadb24f5 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -605,7 +605,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 10); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config")); /* config1 */ term = list_entry(term->list.next, struct parse_events_term, list); @@ -614,7 +614,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 1); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config1")); /* config2=3 */ term = list_entry(term->list.next, struct parse_events_term, list); @@ -623,7 +623,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 3); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config2")); /* umask=1*/ term = list_entry(term->list.next, struct parse_events_term, list); @@ -661,7 +661,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong type val", term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); TEST_ASSERT_VAL("wrong val", term->val.num == 0xead); - TEST_ASSERT_VAL("wrong config", !term->config); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config")); return 0; } @@ -2045,7 +2045,6 @@ static int test_event(struct evlist_test *e) struct evlist *evlist; int ret; - bzero(&err, sizeof(err)); if (e->valid && !e->valid()) { pr_debug("... SKIP"); return 0; @@ -2055,15 +2054,41 @@ static int test_event(struct evlist_test *e) if (evlist == NULL) return -ENOMEM; + parse_events_error__init(&err); ret = parse_events(evlist, e->name, &err); if (ret) { pr_debug("failed to parse event '%s', err %d, str '%s'\n", e->name, ret, err.str); - parse_events_print_error(&err, e->name); + parse_events_error__print(&err, e->name); } else { ret = e->check(evlist); } + parse_events_error__exit(&err); + evlist__delete(evlist); + + return ret; +} + +static int test_event_fake_pmu(const char *str) +{ + struct parse_events_error err; + struct evlist *evlist; + int ret; + + evlist = evlist__new(); + if (!evlist) + return -ENOMEM; + + parse_events_error__init(&err); + perf_pmu__test_parse_init(); + ret = __parse_events(evlist, str, &err, &perf_pmu__fake); + if (ret) { + pr_debug("failed to parse event '%s', err %d, str '%s'\n", + str, ret, err.str); + parse_events_error__print(&err, str); + } + parse_events_error__exit(&err); evlist__delete(evlist); return ret; @@ -2276,7 +2301,27 @@ static int test_pmu_events_alias(char *event, char *alias) return test_event(&e); } -int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test_pmu_events_alias2(void) +{ + static const char events[][30] = { + "event-hyphen", + "event-two-hyph", + }; + unsigned long i; + int ret = 0; + + for (i = 0; i < ARRAY_SIZE(events); i++) { + ret = test_event_fake_pmu(&events[i][0]); + if (ret) { + pr_err("check_parse_fake %s failed\n", &events[i][0]); + break; + } + } + + return ret; +} + +static int test__parse_events(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret1, ret2 = 0; char *event, *alias; @@ -2313,9 +2358,15 @@ do { \ return ret; } + ret1 = test_pmu_events_alias2(); + if (!ret2) + ret2 = ret1; + ret1 = test_terms(test__terms, ARRAY_SIZE(test__terms)); if (!ret2) ret2 = ret1; return ret2; } + +DEFINE_SUITE("Parse event definition strings", parse_events); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 4f6f4904e852..07b6f4ec024f 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -79,7 +79,7 @@ static struct pmu_event pme_test[] = { } }; -static struct pmu_events_map map = { +static const struct pmu_events_map map = { .cpuid = "test", .version = "1", .type = "core", @@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, struct evsel *evsel; u64 count; + perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); perf_stat__update_shadow_stats(evsel, count, 0, st); @@ -369,7 +370,7 @@ static int test_metric_group(void) return 0; } -int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("IPC failed", test_ipc() == 0); TEST_ASSERT_VAL("frontend failed", test_frontend() == 0); @@ -383,3 +384,5 @@ int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unu } return 0; } + +DEFINE_SUITE("Parse and process metrics", parse_metric); diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 471273676701..d62e31595ab2 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -67,7 +67,8 @@ struct test_attr_event { * * Return: %0 on success, %-1 if the test fails. */ -int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__parse_no_sample_id_all(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err; @@ -103,3 +104,5 @@ int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest _ return 0; } + +DEFINE_SUITE("Parse with no sample_id_all bit set", parse_no_sample_id_all); diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c index 58b90c42eb38..c09a9fae1689 100644 --- a/tools/perf/tests/pe-file-parsing.c +++ b/tools/perf/tests/pe-file-parsing.c @@ -68,7 +68,7 @@ static int run_dir(const char *d) return TEST_OK; } -int test__pe_file_parsing(struct test *test __maybe_unused, +static int test__pe_file_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct stat st; @@ -89,10 +89,12 @@ int test__pe_file_parsing(struct test *test __maybe_unused, #else -int test__pe_file_parsing(struct test *test __maybe_unused, +static int test__pe_file_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return TEST_SKIP; } #endif + +DEFINE_SUITE("PE file support", pe_file_parsing); diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c index dd865e0bea12..78cdeb89645e 100644 --- a/tools/perf/tests/perf-hooks.c +++ b/tools/perf/tests/perf-hooks.c @@ -26,7 +26,7 @@ static void the_hook(void *_hook_flags) raise(SIGSEGV); } -int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_hooks(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int hook_flags = 0; @@ -45,3 +45,5 @@ int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unuse return TEST_FAIL; return TEST_OK; } + +DEFINE_SUITE("perf hooks", perf_hooks); diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 0df471bf1590..6354465067b8 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -41,7 +41,7 @@ realloc: return cpu; } -int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .target = { @@ -332,3 +332,5 @@ out_delete_evlist: out: return (err < 0 || errs > 0) ? -1 : 0; } + +DEFINE_SUITE("PERF_RECORD_* events & perf_sample fields", PERF_RECORD); diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 7c56bc1f4cff..d12d0ad81801 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -23,6 +23,16 @@ #include "pmu.h" #include "pmu-hybrid.h" +/* + * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. Just + * enable the test for x86_64/i386 and Arm64 archs. + */ +#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) +#define TSC_IS_SUPPORTED 1 +#else +#define TSC_IS_SUPPORTED 0 +#endif + #define CHECK__(x) { \ while ((x) < 0) { \ pr_debug(#x " failed!\n"); \ @@ -45,7 +55,7 @@ * %0 is returned, otherwise %-1 is returned. If TSC conversion is not * supported then then the test passes but " (not supported)" is printed. */ -int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, @@ -69,6 +79,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -185,15 +200,4 @@ out_err: return err; } -bool test__tsc_is_supported(void) -{ - /* - * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. - * Just enable the test for x86_64/i386 and Arm64 archs. - */ -#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) - return true; -#else - return false; -#endif -} +DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c index e8fd0da0762b..71b76deb1f92 100644 --- a/tools/perf/tests/pfm.c +++ b/tools/perf/tests/pfm.c @@ -12,27 +12,6 @@ #include <linux/kernel.h> #ifdef HAVE_LIBPFM -static int test__pfm_events(void); -static int test__pfm_group(void); -#endif - -static const struct { - int (*func)(void); - const char *desc; -} pfm_testcase_table[] = { -#ifdef HAVE_LIBPFM - { - .func = test__pfm_events, - .desc = "test of individual --pfm-events", - }, - { - .func = test__pfm_group, - .desc = "test groups of --pfm-events", - }, -#endif -}; - -#ifdef HAVE_LIBPFM static int count_pfm_events(struct perf_evlist *evlist) { struct perf_evsel *evsel; @@ -44,7 +23,8 @@ static int count_pfm_events(struct perf_evlist *evlist) return count; } -static int test__pfm_events(void) +static int test__pfm_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evlist *evlist; struct option opt; @@ -104,7 +84,8 @@ static int test__pfm_events(void) return 0; } -static int test__pfm_group(void) +static int test__pfm_group(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evlist *evlist; struct option opt; @@ -187,27 +168,27 @@ static int test__pfm_group(void) } return 0; } -#endif - -const char *test__pfm_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table)) - return NULL; - return pfm_testcase_table[i].desc; -} - -int test__pfm_subtest_get_nr(void) +#else +static int test__pfm_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return (int)ARRAY_SIZE(pfm_testcase_table); + return TEST_SKIP; } -int test__pfm(struct test *test __maybe_unused, int i __maybe_unused) +static int test__pfm_group(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { -#ifdef HAVE_LIBPFM - if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table)) - return TEST_FAIL; - return pfm_testcase_table[i].func(); -#else return TEST_SKIP; -#endif } +#endif + +static struct test_case pfm_tests[] = { + TEST_CASE_REASON("test of individual --pfm-events", pfm_events, "not compiled in"), + TEST_CASE_REASON("test groups of --pfm-events", pfm_group, "not compiled in"), + { .name = NULL, } +}; + +struct test_suite suite__pfm = { + .desc = "Test libpfm4 support", + .test_cases = pfm_tests, +}; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 43743cf719ef..1c695fb5a79c 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -67,7 +67,7 @@ static const struct perf_pmu_test_event segment_reg_loads_any = { .desc = "Number of segment register loads", .topic = "other", }, - .alias_str = "umask=0x80,(null)=0x30d40,event=0x6", + .alias_str = "umask=0x80,period=0x30d40,event=0x6", .alias_long_desc = "Number of segment register loads", }; @@ -78,7 +78,7 @@ static const struct perf_pmu_test_event dispatch_blocked_any = { .desc = "Memory cluster signals to block micro-op dispatch for any reason", .topic = "other", }, - .alias_str = "umask=0x20,(null)=0x30d40,event=0x9", + .alias_str = "umask=0x20,period=0x30d40,event=0x9", .alias_long_desc = "Memory cluster signals to block micro-op dispatch for any reason", }; @@ -89,7 +89,7 @@ static const struct perf_pmu_test_event eist_trans = { .desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", .topic = "other", }, - .alias_str = "umask=0,(null)=0x30d40,event=0x3a", + .alias_str = "umask=0,period=0x30d40,event=0x3a", .alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", }; @@ -143,10 +143,38 @@ static const struct perf_pmu_test_event unc_cbo_xsnp_response_miss_eviction = { .matching_pmu = "uncore_cbox_0", }; +static const struct perf_pmu_test_event uncore_hyphen = { + .event = { + .name = "event-hyphen", + .event = "umask=0x00,event=0xe0", + .desc = "Unit: uncore_cbox UNC_CBO_HYPHEN", + .topic = "uncore", + .long_desc = "UNC_CBO_HYPHEN", + .pmu = "uncore_cbox", + }, + .alias_str = "umask=0,event=0xe0", + .alias_long_desc = "UNC_CBO_HYPHEN", + .matching_pmu = "uncore_cbox_0", +}; + +static const struct perf_pmu_test_event uncore_two_hyph = { + .event = { + .name = "event-two-hyph", + .event = "umask=0x00,event=0xc0", + .desc = "Unit: uncore_cbox UNC_CBO_TWO_HYPH", + .topic = "uncore", + .long_desc = "UNC_CBO_TWO_HYPH", + .pmu = "uncore_cbox", + }, + .alias_str = "umask=0,event=0xc0", + .alias_long_desc = "UNC_CBO_TWO_HYPH", + .matching_pmu = "uncore_cbox_0", +}; + static const struct perf_pmu_test_event uncore_hisi_l3c_rd_hit_cpipe = { .event = { .name = "uncore_hisi_l3c.rd_hit_cpipe", - .event = "event=0x2", + .event = "event=0x7", .desc = "Total read hits. Unit: hisi_sccl,l3c ", .topic = "uncore", .long_desc = "Total read hits", @@ -188,6 +216,8 @@ static const struct perf_pmu_test_event uncore_imc_cache_hits = { static const struct perf_pmu_test_event *uncore_events[] = { &uncore_hisi_ddrc_flux_wcmd, &unc_cbo_xsnp_response_miss_eviction, + &uncore_hyphen, + &uncore_two_hyph, &uncore_hisi_l3c_rd_hit_cpipe, &uncore_imc_free_running_cache_miss, &uncore_imc_cache_hits, @@ -208,8 +238,23 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = { .matching_pmu = "uncore_sys_ddr_pmu", }; +static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = { + .event = { + .name = "sys_ccn_pmu.read_cycles", + .event = "config=0x2c", + .desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .topic = "uncore", + .pmu = "uncore_sys_ccn_pmu", + .compat = "0x01", + }, + .alias_str = "config=0x2c", + .alias_long_desc = "ccn read-cycles event. Unit: uncore_sys_ccn_pmu ", + .matching_pmu = "uncore_sys_ccn_pmu", +}; + static const struct perf_pmu_test_event *sys_events[] = { &sys_ddr_pmu_write_cycles, + &sys_ccn_pmu_read_cycles, NULL }; @@ -227,9 +272,9 @@ static bool is_same(const char *reference, const char *test) return !strcmp(reference, test); } -static struct pmu_events_map *__test_pmu_get_events_map(void) +static const struct pmu_events_map *__test_pmu_get_events_map(void) { - struct pmu_events_map *map; + const struct pmu_events_map *map; for (map = &pmu_events_map[0]; map->cpuid; map++) { if (!strcmp(map->cpuid, "testcpu")) @@ -241,9 +286,9 @@ static struct pmu_events_map *__test_pmu_get_events_map(void) return NULL; } -static struct pmu_event *__test_pmu_get_sys_events_table(void) +static const struct pmu_event *__test_pmu_get_sys_events_table(void) { - struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; + const struct pmu_sys_events *tables = &pmu_sys_event_tables[0]; for ( ; tables->name; tables++) { if (!strcmp("pme_test_soc_sys", tables->name)) @@ -253,8 +298,26 @@ static struct pmu_event *__test_pmu_get_sys_events_table(void) return NULL; } -static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) +static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event *e2) { + if (!is_same(e1->name, e2->name)) { + pr_debug2("testing event e1 %s: mismatched name string, %s vs %s\n", + e1->name, e1->name, e2->name); + return -1; + } + + if (!is_same(e1->compat, e2->compat)) { + pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n", + e1->name, e1->compat, e2->compat); + return -1; + } + + if (!is_same(e1->event, e2->event)) { + pr_debug2("testing event e1 %s: mismatched event, %s vs %s\n", + e1->name, e1->event, e2->event); + return -1; + } + if (!is_same(e1->desc, e2->desc)) { pr_debug2("testing event e1 %s: mismatched desc, %s vs %s\n", e1->name, e1->desc, e2->desc); @@ -273,6 +336,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->pmu, e2->pmu)) { + pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n", + e1->name, e1->pmu, e2->pmu); + return -1; + } + if (!is_same(e1->unit, e2->unit)) { pr_debug2("testing event e1 %s: mismatched unit, %s vs %s\n", e1->name, e1->unit, e2->unit); @@ -285,6 +354,12 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } + if (!is_same(e1->aggr_mode, e2->aggr_mode)) { + pr_debug2("testing event e1 %s: mismatched aggr_mode, %s vs %s\n", + e1->name, e1->aggr_mode, e2->aggr_mode); + return -1; + } + if (!is_same(e1->metric_expr, e2->metric_expr)) { pr_debug2("testing event e1 %s: mismatched metric_expr, %s vs %s\n", e1->name, e1->metric_expr, e2->metric_expr); @@ -297,21 +372,21 @@ static int compare_pmu_events(struct pmu_event *e1, const struct pmu_event *e2) return -1; } - if (!is_same(e1->deprecated, e2->deprecated)) { - pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n", - e1->name, e1->deprecated, e2->deprecated); + if (!is_same(e1->metric_group, e2->metric_group)) { + pr_debug2("testing event e1 %s: mismatched metric_group, %s vs %s\n", + e1->name, e1->metric_group, e2->metric_group); return -1; } - if (!is_same(e1->pmu, e2->pmu)) { - pr_debug2("testing event e1 %s: mismatched pmu string, %s vs %s\n", - e1->name, e1->pmu, e2->pmu); + if (!is_same(e1->deprecated, e2->deprecated)) { + pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n", + e1->name, e1->deprecated, e2->deprecated); return -1; } - if (!is_same(e1->compat, e2->compat)) { - pr_debug2("testing event e1 %s: mismatched compat string, %s vs %s\n", - e1->name, e1->compat, e2->compat); + if (!is_same(e1->metric_constraint, e2->metric_constraint)) { + pr_debug2("testing event e1 %s: mismatched metric_constant, %s vs %s\n", + e1->name, e1->metric_constraint, e2->metric_constraint); return -1; } @@ -373,11 +448,12 @@ static int compare_alias_to_test_event(struct perf_pmu_alias *alias, } /* Verify generated events from pmu-events.c are as expected */ -static int test_pmu_event_table(void) +static int test__pmu_event_table(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - struct pmu_event *sys_event_tables = __test_pmu_get_sys_events_table(); - struct pmu_events_map *map = __test_pmu_get_events_map(); - struct pmu_event *table; + const struct pmu_event *sys_event_tables = __test_pmu_get_sys_events_table(); + const struct pmu_events_map *map = __test_pmu_get_events_map(); + const struct pmu_event *table; int map_events = 0, expected_events; /* ignore 3x sentinels */ @@ -473,7 +549,7 @@ static int __test_core_pmu_event_aliases(char *pmu_name, int *count) struct perf_pmu *pmu; LIST_HEAD(aliases); int res = 0; - struct pmu_events_map *map = __test_pmu_get_events_map(); + const struct pmu_events_map *map = __test_pmu_get_events_map(); struct perf_pmu_alias *a, *tmp; if (!map) @@ -526,7 +602,7 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) struct perf_pmu *pmu = &test_pmu->pmu; const char *pmu_name = pmu->name; struct perf_pmu_alias *a, *tmp, *alias; - struct pmu_events_map *map; + const struct pmu_events_map *map; LIST_HEAD(aliases); int res = 0; @@ -608,6 +684,8 @@ static struct perf_pmu_test_pmu test_pmus[] = { }, .aliases = { &unc_cbo_xsnp_response_miss_eviction, + &uncore_hyphen, + &uncore_two_hyph, }, }, { @@ -647,10 +725,21 @@ static struct perf_pmu_test_pmu test_pmus[] = { &sys_ddr_pmu_write_cycles, }, }, + { + .pmu = { + .name = (char *)"uncore_sys_ccn_pmu4", + .is_uncore = 1, + .id = (char *)"0x01", + }, + .aliases = { + &sys_ccn_pmu_read_cycles, + }, + }, }; /* Test that aliases generated are as expected */ -static int test_aliases(void) +static int test__aliases(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct perf_pmu *pmu = NULL; unsigned long i; @@ -706,6 +795,7 @@ static int check_parse_id(const char *id, struct parse_events_error *error, { struct evlist *evlist; int ret; + char *dup, *cur; /* Numbers are always valid. */ if (is_number(id)) @@ -714,16 +804,28 @@ static int check_parse_id(const char *id, struct parse_events_error *error, evlist = evlist__new(); if (!evlist) return -ENOMEM; - ret = __parse_events(evlist, id, error, fake_pmu); + + dup = strdup(id); + if (!dup) + return -ENOMEM; + + for (cur = strchr(dup, '@') ; cur; cur = strchr(++cur, '@')) + *cur = '/'; + + ret = __parse_events(evlist, dup, error, fake_pmu); + free(dup); + evlist__delete(evlist); return ret; } -static int check_parse_cpu(const char *id, bool same_cpu, struct pmu_event *pe) +static int check_parse_cpu(const char *id, bool same_cpu, const struct pmu_event *pe) { - struct parse_events_error error = { .idx = 0, }; + struct parse_events_error error; + int ret; - int ret = check_parse_id(id, &error, NULL); + parse_events_error__init(&error); + ret = check_parse_id(id, &error, NULL); if (ret && same_cpu) { pr_warning("Parse event failed metric '%s' id '%s' expr '%s'\n", pe->metric_name, id, pe->metric_expr); @@ -734,22 +836,18 @@ static int check_parse_cpu(const char *id, bool same_cpu, struct pmu_event *pe) id, pe->metric_name, pe->metric_expr); ret = 0; } - free(error.str); - free(error.help); - free(error.first_str); - free(error.first_help); + parse_events_error__exit(&error); return ret; } static int check_parse_fake(const char *id) { - struct parse_events_error error = { .idx = 0, }; - int ret = check_parse_id(id, &error, &perf_pmu__fake); + struct parse_events_error error; + int ret; - free(error.str); - free(error.help); - free(error.first_str); - free(error.first_help); + parse_events_error__init(&error); + ret = check_parse_id(id, &error, &perf_pmu__fake); + parse_events_error__exit(&error); return ret; } @@ -770,7 +868,7 @@ struct metric { static int resolve_metric_simple(struct expr_parse_ctx *pctx, struct list_head *compound_list, - struct pmu_events_map *map, + const struct pmu_events_map *map, const char *metric_name) { struct hashmap_entry *cur, *cur_tmp; @@ -781,9 +879,9 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx, do { all = true; - hashmap__for_each_entry_safe((&pctx->ids), cur, cur_tmp, bkt) { + hashmap__for_each_entry_safe(pctx->ids, cur, cur_tmp, bkt) { struct metric_ref *ref; - struct pmu_event *pe; + const struct pmu_event *pe; pe = metricgroup__find_metric(cur->key, map); if (!pe) @@ -811,7 +909,7 @@ static int resolve_metric_simple(struct expr_parse_ctx *pctx, ref->metric_expr = pe->metric_expr; list_add_tail(&metric->list, compound_list); - rc = expr__find_other(pe->metric_expr, NULL, pctx, 0); + rc = expr__find_ids(pe->metric_expr, NULL, pctx); if (rc) goto out_err; break; /* The hashmap has been modified, so restart */ @@ -828,16 +926,22 @@ out_err: } -static int test_parsing(void) +static int test__parsing(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - struct pmu_events_map *cpus_map = pmu_events_map__find(); - struct pmu_events_map *map; - struct pmu_event *pe; + const struct pmu_events_map *cpus_map = pmu_events_map__find(); + const struct pmu_events_map *map; + const struct pmu_event *pe; int i, j, k; int ret = 0; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; double result; + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return TEST_FAIL; + } i = 0; for (;;) { map = &pmu_events_map[i++]; @@ -855,15 +959,14 @@ static int test_parsing(void) break; if (!pe->metric_expr) continue; - expr__ctx_init(&ctx); - if (expr__find_other(pe->metric_expr, NULL, &ctx, 0) - < 0) { - expr_failure("Parse other failed", map, pe); + expr__ctx_clear(ctx); + if (expr__find_ids(pe->metric_expr, NULL, ctx) < 0) { + expr_failure("Parse find ids failed", map, pe); ret++; continue; } - if (resolve_metric_simple(&ctx, &compound_list, map, + if (resolve_metric_simple(ctx, &compound_list, map, pe->metric_name)) { expr_failure("Could not resolve metrics", map, pe); ret++; @@ -876,27 +979,27 @@ static int test_parsing(void) * make them unique. */ k = 1; - hashmap__for_each_entry((&ctx.ids), cur, bkt) - expr__add_id_val(&ctx, strdup(cur->key), k++); + hashmap__for_each_entry(ctx->ids, cur, bkt) + expr__add_id_val(ctx, strdup(cur->key), k++); - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { if (check_parse_cpu(cur->key, map == cpus_map, pe)) ret++; } list_for_each_entry_safe(metric, tmp, &compound_list, list) { - expr__add_ref(&ctx, &metric->metric_ref); + expr__add_ref(ctx, &metric->metric_ref); free(metric); } - if (expr__parse(&result, &ctx, pe->metric_expr, 0)) { + if (expr__parse(&result, ctx, pe->metric_expr)) { expr_failure("Parse failed", map, pe); ret++; } - expr__ctx_clear(&ctx); } } + expr__ctx_free(ctx); /* TODO: fail when not ok */ exit: return ret == 0 ? TEST_OK : TEST_SKIP; @@ -916,7 +1019,7 @@ static struct test_metric metrics[] = { static int metric_parse_fake(const char *str) { - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; struct hashmap_entry *cur; double result; int ret = -1; @@ -925,9 +1028,13 @@ static int metric_parse_fake(const char *str) pr_debug("parsing '%s'\n", str); - expr__ctx_init(&ctx); - if (expr__find_other(str, NULL, &ctx, 0) < 0) { - pr_err("expr__find_other failed\n"); + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return TEST_FAIL; + } + if (expr__find_ids(str, NULL, ctx) < 0) { + pr_err("expr__find_ids failed\n"); return -1; } @@ -937,23 +1044,23 @@ static int metric_parse_fake(const char *str) * make them unique. */ i = 1; - hashmap__for_each_entry((&ctx.ids), cur, bkt) - expr__add_id_val(&ctx, strdup(cur->key), i++); + hashmap__for_each_entry(ctx->ids, cur, bkt) + expr__add_id_val(ctx, strdup(cur->key), i++); - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { if (check_parse_fake(cur->key)) { pr_err("check_parse_fake failed\n"); goto out; } } - if (expr__parse(&result, &ctx, str, 0)) + if (expr__parse(&result, ctx, str)) pr_err("expr__parse failed\n"); else ret = 0; out: - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); return ret; } @@ -962,10 +1069,11 @@ out: * or all defined cpus via the 'fake_pmu' * in parse_events. */ -static int test_parsing_fake(void) +static int test__parsing_fake(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - struct pmu_events_map *map; - struct pmu_event *pe; + const struct pmu_events_map *map; + const struct pmu_event *pe; unsigned int i, j; int err = 0; @@ -996,55 +1104,16 @@ static int test_parsing_fake(void) return 0; } -static const struct { - int (*func)(void); - const char *desc; -} pmu_events_testcase_table[] = { - { - .func = test_pmu_event_table, - .desc = "PMU event table sanity", - }, - { - .func = test_aliases, - .desc = "PMU event map aliases", - }, - { - .func = test_parsing, - .desc = "Parsing of PMU event table metrics", - }, - { - .func = test_parsing_fake, - .desc = "Parsing of PMU event table metrics with fake PMUs", - }, +static struct test_case pmu_events_tests[] = { + TEST_CASE("PMU event table sanity", pmu_event_table), + TEST_CASE("PMU event map aliases", aliases), + TEST_CASE_REASON("Parsing of PMU event table metrics", parsing, + "some metrics failed"), + TEST_CASE("Parsing of PMU event table metrics with fake PMUs", parsing_fake), + { .name = NULL, } }; -const char *test__pmu_events_subtest_get_desc(int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return NULL; - return pmu_events_testcase_table[subtest].desc; -} - -const char *test__pmu_events_subtest_skip_reason(int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return NULL; - if (pmu_events_testcase_table[subtest].func != test_parsing) - return NULL; - return "some metrics failed"; -} - -int test__pmu_events_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(pmu_events_testcase_table); -} - -int test__pmu_events(struct test *test __maybe_unused, int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return TEST_FAIL; - return pmu_events_testcase_table[subtest].func(); -} +struct test_suite suite__pmu_events = { + .desc = "PMU events", + .test_cases = pmu_events_tests, +}; diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 714e6830a758..8507bd615e97 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -137,7 +137,7 @@ static struct list_head *test_terms_list(void) return &terms; } -int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char *format = test_format_dir_get(); LIST_HEAD(formats); @@ -177,3 +177,5 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused) test_format_dir_put(format); return ret; } + +DEFINE_SUITE("Parse perf pmu format", pmu); diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 98c6d474aa6f..6b990ee38575 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -9,7 +9,7 @@ #include "tests.h" #include "util/debug.h" -int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__python_use(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char *cmd; int ret; @@ -23,3 +23,5 @@ int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unuse free(cmd); return ret; } + +DEFINE_SUITE("'import perf' in python", python_use); diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 8fd8a4ef97da..07f2411b0ad4 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -13,6 +13,7 @@ #include "evsel.h" #include "debug.h" #include "util/synthetic-events.h" +#include "util/trace-event.h" #include "tests.h" @@ -30,9 +31,18 @@ } \ } while (0) +/* + * Hardcode the expected values for branch_entry flags. + * These are based on the input value (213) specified + * in branch_stack variable. + */ +#define BS_EXPECTED_BE 0xa000d00000000000 +#define BS_EXPECTED_LE 0xd5000000 +#define FLAG(s) s->branch_stack->entries[i].flags + static bool samples_same(const struct perf_sample *s1, const struct perf_sample *s2, - u64 type, u64 read_format) + u64 type, u64 read_format, bool needs_swap) { size_t i; @@ -100,8 +110,14 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_BRANCH_STACK) { COMP(branch_stack->nr); COMP(branch_stack->hw_idx); - for (i = 0; i < s1->branch_stack->nr; i++) - MCOMP(branch_stack->entries[i]); + for (i = 0; i < s1->branch_stack->nr; i++) { + if (needs_swap) + return ((tep_is_bigendian()) ? + (FLAG(s2).value == BS_EXPECTED_BE) : + (FLAG(s2).value == BS_EXPECTED_LE)); + else + MCOMP(branch_stack->entries[i]); + } } if (type & PERF_SAMPLE_REGS_USER) { @@ -248,7 +264,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) }, }; struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},}; - struct perf_sample sample_out; + struct perf_sample sample_out, sample_out_endian; size_t i, sz, bufsz; int err, ret = -1; @@ -313,12 +329,29 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) goto out_free; } - if (!samples_same(&sample, &sample_out, sample_type, read_format)) { + if (!samples_same(&sample, &sample_out, sample_type, read_format, evsel.needs_swap)) { pr_debug("parsing failed for sample_type %#"PRIx64"\n", sample_type); goto out_free; } + if (sample_type == PERF_SAMPLE_BRANCH_STACK) { + evsel.needs_swap = true; + evsel.sample_size = __evsel__sample_size(sample_type); + err = evsel__parse_sample(&evsel, event, &sample_out_endian); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "evsel__parse_sample", sample_type, err); + goto out_free; + } + + if (!samples_same(&sample, &sample_out_endian, sample_type, read_format, evsel.needs_swap)) { + pr_debug("parsing failed for sample_type %#"PRIx64"\n", + sample_type); + goto out_free; + } + } + ret = 0; out_free: free(event); @@ -335,7 +368,7 @@ out_free: * checks sample format bits separately and together. If the test passes %0 is * returned, otherwise %-1 is returned. */ -int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; u64 sample_type; @@ -393,3 +426,5 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u return 0; } + +DEFINE_SUITE("Sample parsing", sample_parsing); diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index ed76c693f65e..919712899251 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -76,7 +76,7 @@ static int search_cached_probe(const char *target, return ret; } -int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) +static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused) { int ret = TEST_FAIL; char __tempdir[] = "./test-buildid-XXXXXX"; @@ -114,9 +114,11 @@ error: return ret; } #else -int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) +static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused) { pr_debug("Skip SDT event test because SDT support is not compiled\n"); return TEST_SKIP; } #endif + +DEFINE_SUITE("Probe SDT events", sdt_event); diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh index bf9e729b3ecf..8d9c04e450ae 100755 --- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh +++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh @@ -15,9 +15,6 @@ skip_if_no_perf_probe || exit 2 . $(dirname $0)/lib/probe_vfs_getname.sh -perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) -file=$(mktemp /tmp/temporary_file.XXXXX) - record_open_file() { echo "Recording open file:" perf record -o ${perfdata} -e probe:vfs_getname\* touch $file @@ -35,6 +32,9 @@ if [ $err -ne 0 ] ; then exit $err fi +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +file=$(mktemp /tmp/temporary_file.XXXXX) + record_open_file && perf_script_filenames err=$? rm -f ${perfdata} diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 8a168cf8bacc..49bd875d5122 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -12,7 +12,7 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" - [[ "$(uname -m)" != s390x ]] && gflag='-g' + [ "$(uname -m)" != s390x ] && gflag='-g' $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh new file mode 100755 index 000000000000..cb35e488809a --- /dev/null +++ b/tools/perf/tests/shell/stat_all_metricgroups.sh @@ -0,0 +1,12 @@ +#!/bin/sh +# perf all metricgroups test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for m in $(perf list --raw-dump metricgroups); do + echo "Testing $m" + perf stat -M "$m" -a true +done + +exit 0 diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh new file mode 100755 index 000000000000..7f4ba3cad632 --- /dev/null +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# perf all metrics test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for m in $(perf list --raw-dump metrics); do + echo "Testing $m" + result=$(perf stat -M "$m" true 2>&1) + if [[ ! "$result" =~ "$m" ]] && [[ ! "$result" =~ "<not supported>" ]]; then + # We failed to see the metric and the events are support. Possibly the + # workload was too small so retry with something longer. + result=$(perf stat -M "$m" perf bench internals synthesize 2>&1) + if [[ ! "$result" =~ "$m" ]]; then + echo "Metric '$m' not printed in:" + echo "$result" + exit 1 + fi + fi +done + +exit 0 diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh new file mode 100755 index 000000000000..b30dba455f36 --- /dev/null +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# perf all PMU test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +for p in $(perf list --raw-dump pmu); do + echo "Testing $p" + result=$(perf stat -e "$p" true 2>&1) + if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then + # We failed to see the event and it is supported. Possibly the workload was + # too small so retry with something longer. + result=$(perf stat -e "$p" perf bench internals synthesize 2>&1) + if ! echo "$result" | grep -q "$p" ; then + echo "Event '$p' not printed in:" + echo "$result" + exit 1 + fi + fi +done + +exit 0 diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh index 2aed20dc2262..13473aeba489 100755 --- a/tools/perf/tests/shell/stat_bpf_counters.sh +++ b/tools/perf/tests/shell/stat_bpf_counters.sh @@ -23,7 +23,7 @@ compare_number() # skip if --bpf-counters is not supported if ! perf stat --bpf-counters true > /dev/null 2>&1; then - if [ "$1" == "-v" ]; then + if [ "$1" = "-v" ]; then echo "Skipping: --bpf-counters not supported" perf --no-pager stat --bpf-counters true || true fi diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index c9eef0bba6f1..6de53b7ef5ff 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -9,8 +9,6 @@ # SPDX-License-Identifier: GPL-2.0 # Leo Yan <leo.yan@linaro.org>, 2020 -perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) -file=$(mktemp /tmp/temporary_file.XXXXX) glb_err=0 skip_if_no_cs_etm_event() { @@ -22,13 +20,20 @@ skip_if_no_cs_etm_event() { skip_if_no_cs_etm_event || exit 2 +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +file=$(mktemp /tmp/temporary_file.XXXXX) + cleanup_files() { rm -f ${perfdata} rm -f ${file} + rm -f "${perfdata}.old" + trap - exit term int + kill -2 $$ + exit $glb_err } -trap cleanup_files exit +trap cleanup_files exit term int record_touch_file() { echo "Recording trace (only user mode) with path: CPU$2 => $1" diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh new file mode 100755 index 000000000000..e59044edc406 --- /dev/null +++ b/tools/perf/tests/shell/test_arm_spe.sh @@ -0,0 +1,89 @@ +#!/bin/sh +# Check Arm SPE trace data recording and synthesized samples + +# Uses the 'perf record' to record trace data of Arm SPE events; +# then verify if any SPE event samples are generated by SPE with +# 'perf script' and 'perf report' commands. + +# SPDX-License-Identifier: GPL-2.0 +# German Gomez <german.gomez@arm.com>, 2021 + +skip_if_no_arm_spe_event() { + perf list | egrep -q 'arm_spe_[0-9]+//' && return 0 + + # arm_spe event doesn't exist + return 2 +} + +skip_if_no_arm_spe_event || exit 2 + +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +glb_err=0 + +cleanup_files() +{ + rm -f ${perfdata} + exit $glb_err +} + +trap cleanup_files exit term int + +arm_spe_report() { + if [ $2 != 0 ]; then + echo "$1: FAIL" + glb_err=$2 + else + echo "$1: PASS" + fi +} + +perf_script_samples() { + echo "Looking at perf.data file for dumping samples:" + + # from arm-spe.c/arm_spe_synth_events() + events="(ld1-miss|ld1-access|llc-miss|lld-access|tlb-miss|tlb-access|branch-miss|remote-access|memory)" + + # Below is an example of the samples dumping: + # dd 3048 [002] 1 l1d-access: ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so) + # dd 3048 [002] 1 tlb-access: ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so) + # dd 3048 [002] 1 memory: ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so) + perf script -F,-time -i ${perfdata} 2>&1 | \ + egrep " +$1 +[0-9]+ .* +${events}:(.*:)? +" > /dev/null 2>&1 +} + +perf_report_samples() { + echo "Looking at perf.data file for reporting samples:" + + # Below is an example of the samples reporting: + # 73.04% 73.04% dd libc-2.27.so [.] _dl_addr + # 7.71% 7.71% dd libc-2.27.so [.] getenv + # 2.59% 2.59% dd ld-2.27.so [.] strcmp + perf report --stdio -i ${perfdata} 2>&1 | \ + egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 " > /dev/null 2>&1 +} + +arm_spe_snapshot_test() { + echo "Recording trace with snapshot mode $perfdata" + perf record -o ${perfdata} -e arm_spe// -S \ + -- dd if=/dev/zero of=/dev/null > /dev/null 2>&1 & + PERFPID=$! + + # Wait for perf program + sleep 1 + + # Send signal to snapshot trace data + kill -USR2 $PERFPID + + # Stop perf program + kill $PERFPID + wait $PERFPID + + perf_script_samples dd && + perf_report_samples dd + + err=$? + arm_spe_report "SPE snapshot testing" $err +} + +arm_spe_snapshot_test +exit $glb_err diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 3d31c1d560d6..3d60e993d2b8 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -17,8 +17,6 @@ skip_if_no_perf_trace || exit 2 . $(dirname $0)/lib/probe_vfs_getname.sh -file=$(mktemp /tmp/temporary_file.XXXXX) - trace_open_vfs_getname() { evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') perf trace -e $evts touch $file 2>&1 | \ @@ -32,6 +30,8 @@ if [ $err -ne 0 ] ; then exit $err fi +file=$(mktemp /tmp/temporary_file.XXXXX) + # Do not use whatever ~/.perfconfig file, it may change the output # via trace.{show_timestamp,show_prefix,etc} export PERF_CONFIG=/dev/null diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c new file mode 100644 index 000000000000..1f147fe6595f --- /dev/null +++ b/tools/perf/tests/sigtrap.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic test for sigtrap support. + * + * Copyright (C) 2021, Google LLC. + */ + +#include <errno.h> +#include <stdint.h> +#include <stdlib.h> +#include <linux/hw_breakpoint.h> +#include <linux/string.h> +#include <pthread.h> +#include <signal.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> +#include <unistd.h> + +#include "cloexec.h" +#include "debug.h" +#include "event.h" +#include "tests.h" +#include "../perf-sys.h" + +/* + * PowerPC and S390 do not support creation of instruction breakpoints using the + * perf_event interface. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) +#define BP_ACCOUNT_IS_SUPPORTED 0 +#else +#define BP_ACCOUNT_IS_SUPPORTED 1 +#endif + +#define NUM_THREADS 5 + +static struct { + int tids_want_signal; /* Which threads still want a signal. */ + int signal_count; /* Sanity check number of signals received. */ + volatile int iterate_on; /* Variable to set breakpoint on. */ + siginfo_t first_siginfo; /* First observed siginfo_t. */ +} ctx; + +#define TEST_SIG_DATA (~(unsigned long)(&ctx.iterate_on)) + +static struct perf_event_attr make_event_attr(void) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_BREAKPOINT, + .size = sizeof(attr), + .sample_period = 1, + .disabled = 1, + .bp_addr = (unsigned long)&ctx.iterate_on, + .bp_type = HW_BREAKPOINT_RW, + .bp_len = HW_BREAKPOINT_LEN_1, + .inherit = 1, /* Children inherit events ... */ + .inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */ + .remove_on_exec = 1, /* Required by sigtrap. */ + .sigtrap = 1, /* Request synchronous SIGTRAP on event. */ + .sig_data = TEST_SIG_DATA, + .exclude_kernel = 1, /* To allow */ + .exclude_hv = 1, /* running as !root */ + }; + return attr; +} + +static void +sigtrap_handler(int signum __maybe_unused, siginfo_t *info, void *ucontext __maybe_unused) +{ + if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED)) + ctx.first_siginfo = *info; + __atomic_fetch_sub(&ctx.tids_want_signal, syscall(SYS_gettid), __ATOMIC_RELAXED); +} + +static void *test_thread(void *arg) +{ + pthread_barrier_t *barrier = (pthread_barrier_t *)arg; + pid_t tid = syscall(SYS_gettid); + int i; + + pthread_barrier_wait(barrier); + + __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED); + for (i = 0; i < ctx.iterate_on - 1; i++) + __atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED); + + return NULL; +} + +static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier) +{ + int i; + + pthread_barrier_wait(barrier); + for (i = 0; i < NUM_THREADS; i++) + TEST_ASSERT_EQUAL("pthread_join() failed", pthread_join(threads[i], NULL), 0); + + return TEST_OK; +} + +static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier) +{ + int ret; + + ctx.iterate_on = 3000; + + TEST_ASSERT_EQUAL("misfired signal?", ctx.signal_count, 0); + TEST_ASSERT_EQUAL("enable failed", ioctl(fd, PERF_EVENT_IOC_ENABLE, 0), 0); + ret = run_test_threads(threads, barrier); + TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0); + + TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on); + TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0); + TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on); +#if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */ + TEST_ASSERT_EQUAL("unexpected si_perf_type", ctx.first_siginfo.si_perf_type, + PERF_TYPE_BREAKPOINT); + TEST_ASSERT_EQUAL("unexpected si_perf_data", ctx.first_siginfo.si_perf_data, + TEST_SIG_DATA); +#endif + + return ret; +} + +static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + struct perf_event_attr attr = make_event_attr(); + struct sigaction action = {}; + struct sigaction oldact; + pthread_t threads[NUM_THREADS]; + pthread_barrier_t barrier; + char sbuf[STRERR_BUFSIZE]; + int i, fd, ret = TEST_FAIL; + + if (!BP_ACCOUNT_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + + pthread_barrier_init(&barrier, NULL, NUM_THREADS + 1); + + action.sa_flags = SA_SIGINFO | SA_NODEFER; + action.sa_sigaction = sigtrap_handler; + sigemptyset(&action.sa_mask); + if (sigaction(SIGTRAP, &action, &oldact)) { + pr_debug("FAILED sigaction(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + goto out; + } + + fd = sys_perf_event_open(&attr, 0, -1, -1, perf_event_open_cloexec_flag()); + if (fd < 0) { + pr_debug("FAILED sys_perf_event_open(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + goto out_restore_sigaction; + } + + for (i = 0; i < NUM_THREADS; i++) { + if (pthread_create(&threads[i], NULL, test_thread, &barrier)) { + pr_debug("FAILED pthread_create(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf))); + goto out_close_perf_event; + } + } + + ret = run_stress_test(fd, threads, &barrier); + +out_close_perf_event: + close(fd); +out_restore_sigaction: + sigaction(SIGTRAP, &oldact, NULL); +out: + pthread_barrier_destroy(&barrier); + return ret; +} + +DEFINE_SUITE("Sigtrap", sigtrap); diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index c1911501c39c..500974040fe3 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -47,7 +47,8 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat_config(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct perf_stat_config stat_config = { .aggr_mode = AGGR_CORE, @@ -77,7 +78,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_counts_values count; @@ -86,7 +87,8 @@ int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_ count.run = 300; TEST_ASSERT_VAL("failed to synthesize stat_config", - !perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL)); + !perf_event__synthesize_stat(NULL, (struct perf_cpu){.cpu = 1}, 2, 3, + &count, process_stat_event, NULL)); return 0; } @@ -103,7 +105,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat_round(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to synthesize stat_config", !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL, @@ -111,3 +113,7 @@ int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __ return 0; } + +DEFINE_SUITE("Synthesize stat config", synthesize_stat_config); +DEFINE_SUITE("Synthesize stat", synthesize_stat); +DEFINE_SUITE("Synthesize stat round", synthesize_stat_round); diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 74988846be1d..9cd6fec375ee 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -133,7 +133,7 @@ out_delete_evlist: return err; } -int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__sw_clock_freq(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret; @@ -143,3 +143,5 @@ int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_un return ret; } + +DEFINE_SUITE("Software clock events period values", sw_clock_freq); diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 62c0ec21aaa8..0c0c2328bf4e 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -321,7 +321,7 @@ out_free_nodes: * evsel->core.system_wide and evsel->tracking flags (respectively) with other events * sometimes enabled or disabled. */ -int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__switch_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { const char *sched_switch = "sched:sched_switch"; struct switch_tracking switch_tracking = { .tids = NULL, }; @@ -588,3 +588,5 @@ out_err: err = -1; goto out; } + +DEFINE_SUITE("Track with sched_switch", switch_tracking); diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 4c2969db59b0..25f075fa9125 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -39,7 +39,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, * if the number of exit event reported by the kernel is 1 or not * in order to check the kernel returns correct number of event. */ -int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__task_exit(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; @@ -151,3 +151,5 @@ out_delete_evlist: evlist__delete(evlist); return err; } + +DEFINE_SUITE("Number of exit events of a simple workload", task_exit); diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index fe1306f58495..5bbb8f6a48fc 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -27,112 +27,147 @@ enum { TEST_SKIP = -2, }; -struct test { +struct test_suite; + +typedef int (*test_fnptr)(struct test_suite *, int); + +struct test_case { + const char *name; + const char *desc; + const char *skip_reason; + test_fnptr run_case; +}; + +struct test_suite { const char *desc; - int (*func)(struct test *test, int subtest); - struct { - bool skip_if_fail; - int (*get_nr)(void); - const char *(*get_desc)(int subtest); - const char *(*skip_reason)(int subtest); - } subtest; - bool (*is_supported)(void); + struct test_case *test_cases; void *priv; }; +#define DECLARE_SUITE(name) \ + extern struct test_suite suite__##name; + +#define TEST_CASE(description, _name) \ + { \ + .name = #_name, \ + .desc = description, \ + .run_case = test__##_name, \ + } + +#define TEST_CASE_REASON(description, _name, _reason) \ + { \ + .name = #_name, \ + .desc = description, \ + .run_case = test__##_name, \ + .skip_reason = _reason, \ + } + +#define DEFINE_SUITE(description, _name) \ + struct test_case tests__##_name[] = { \ + TEST_CASE(description, _name), \ + { .name = NULL, } \ + }; \ + struct test_suite suite__##_name = { \ + .desc = description, \ + .test_cases = tests__##_name, \ + } + /* Tests */ -int test__vmlinux_matches_kallsyms(struct test *test, int subtest); -int test__openat_syscall_event(struct test *test, int subtest); -int test__openat_syscall_event_on_all_cpus(struct test *test, int subtest); -int test__basic_mmap(struct test *test, int subtest); -int test__PERF_RECORD(struct test *test, int subtest); -int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest); -int test__perf_evsel__tp_sched_test(struct test *test, int subtest); -int test__syscall_openat_tp_fields(struct test *test, int subtest); -int test__pmu(struct test *test, int subtest); -int test__pmu_events(struct test *test, int subtest); -const char *test__pmu_events_subtest_get_desc(int subtest); -const char *test__pmu_events_subtest_skip_reason(int subtest); -int test__pmu_events_subtest_get_nr(void); -int test__attr(struct test *test, int subtest); -int test__dso_data(struct test *test, int subtest); -int test__dso_data_cache(struct test *test, int subtest); -int test__dso_data_reopen(struct test *test, int subtest); -int test__parse_events(struct test *test, int subtest); -int test__hists_link(struct test *test, int subtest); -int test__python_use(struct test *test, int subtest); -int test__bp_signal(struct test *test, int subtest); -int test__bp_signal_overflow(struct test *test, int subtest); -int test__bp_accounting(struct test *test, int subtest); -int test__wp(struct test *test, int subtest); -const char *test__wp_subtest_get_desc(int subtest); -const char *test__wp_subtest_skip_reason(int subtest); -int test__wp_subtest_get_nr(void); -int test__task_exit(struct test *test, int subtest); -int test__mem(struct test *test, int subtest); -int test__sw_clock_freq(struct test *test, int subtest); -int test__code_reading(struct test *test, int subtest); -int test__sample_parsing(struct test *test, int subtest); -int test__keep_tracking(struct test *test, int subtest); -int test__parse_no_sample_id_all(struct test *test, int subtest); -int test__dwarf_unwind(struct test *test, int subtest); -int test__expr(struct test *test, int subtest); -int test__hists_filter(struct test *test, int subtest); -int test__mmap_thread_lookup(struct test *test, int subtest); -int test__thread_maps_share(struct test *test, int subtest); -int test__hists_output(struct test *test, int subtest); -int test__hists_cumulate(struct test *test, int subtest); -int test__switch_tracking(struct test *test, int subtest); -int test__fdarray__filter(struct test *test, int subtest); -int test__fdarray__add(struct test *test, int subtest); -int test__kmod_path__parse(struct test *test, int subtest); -int test__thread_map(struct test *test, int subtest); -int test__llvm(struct test *test, int subtest); -const char *test__llvm_subtest_get_desc(int subtest); -int test__llvm_subtest_get_nr(void); -int test__bpf(struct test *test, int subtest); -const char *test__bpf_subtest_get_desc(int subtest); -int test__bpf_subtest_get_nr(void); -int test__session_topology(struct test *test, int subtest); -int test__thread_map_synthesize(struct test *test, int subtest); -int test__thread_map_remove(struct test *test, int subtest); -int test__cpu_map_synthesize(struct test *test, int subtest); -int test__synthesize_stat_config(struct test *test, int subtest); -int test__synthesize_stat(struct test *test, int subtest); -int test__synthesize_stat_round(struct test *test, int subtest); -int test__event_update(struct test *test, int subtest); -int test__event_times(struct test *test, int subtest); -int test__backward_ring_buffer(struct test *test, int subtest); -int test__cpu_map_print(struct test *test, int subtest); -int test__cpu_map_merge(struct test *test, int subtest); -int test__sdt_event(struct test *test, int subtest); -int test__is_printable_array(struct test *test, int subtest); -int test__bitmap_print(struct test *test, int subtest); -int test__perf_hooks(struct test *test, int subtest); -int test__clang(struct test *test, int subtest); -const char *test__clang_subtest_get_desc(int subtest); -int test__clang_subtest_get_nr(void); -int test__unit_number__scnprint(struct test *test, int subtest); -int test__mem2node(struct test *t, int subtest); -int test__maps__merge_in(struct test *t, int subtest); -int test__time_utils(struct test *t, int subtest); -int test__jit_write_elf(struct test *test, int subtest); -int test__api_io(struct test *test, int subtest); -int test__demangle_java(struct test *test, int subtest); -int test__demangle_ocaml(struct test *test, int subtest); -int test__pfm(struct test *test, int subtest); -const char *test__pfm_subtest_get_desc(int subtest); -int test__pfm_subtest_get_nr(void); -int test__parse_metric(struct test *test, int subtest); -int test__pe_file_parsing(struct test *test, int subtest); -int test__expand_cgroup_events(struct test *test, int subtest); -int test__perf_time_to_tsc(struct test *test, int subtest); -int test__dlfilter(struct test *test, int subtest); - -bool test__bp_signal_is_supported(void); -bool test__bp_account_is_supported(void); -bool test__wp_is_supported(void); -bool test__tsc_is_supported(void); +DECLARE_SUITE(vmlinux_matches_kallsyms); +DECLARE_SUITE(openat_syscall_event); +DECLARE_SUITE(openat_syscall_event_on_all_cpus); +DECLARE_SUITE(basic_mmap); +DECLARE_SUITE(PERF_RECORD); +DECLARE_SUITE(perf_evsel__roundtrip_name_test); +DECLARE_SUITE(perf_evsel__tp_sched_test); +DECLARE_SUITE(syscall_openat_tp_fields); +DECLARE_SUITE(pmu); +DECLARE_SUITE(pmu_events); +DECLARE_SUITE(attr); +DECLARE_SUITE(dso_data); +DECLARE_SUITE(dso_data_cache); +DECLARE_SUITE(dso_data_reopen); +DECLARE_SUITE(parse_events); +DECLARE_SUITE(hists_link); +DECLARE_SUITE(python_use); +DECLARE_SUITE(bp_signal); +DECLARE_SUITE(bp_signal_overflow); +DECLARE_SUITE(bp_accounting); +DECLARE_SUITE(wp); +DECLARE_SUITE(task_exit); +DECLARE_SUITE(mem); +DECLARE_SUITE(sw_clock_freq); +DECLARE_SUITE(code_reading); +DECLARE_SUITE(sample_parsing); +DECLARE_SUITE(keep_tracking); +DECLARE_SUITE(parse_no_sample_id_all); +DECLARE_SUITE(dwarf_unwind); +DECLARE_SUITE(expr); +DECLARE_SUITE(hists_filter); +DECLARE_SUITE(mmap_thread_lookup); +DECLARE_SUITE(thread_maps_share); +DECLARE_SUITE(hists_output); +DECLARE_SUITE(hists_cumulate); +DECLARE_SUITE(switch_tracking); +DECLARE_SUITE(fdarray__filter); +DECLARE_SUITE(fdarray__add); +DECLARE_SUITE(kmod_path__parse); +DECLARE_SUITE(thread_map); +DECLARE_SUITE(llvm); +DECLARE_SUITE(bpf); +DECLARE_SUITE(session_topology); +DECLARE_SUITE(thread_map_synthesize); +DECLARE_SUITE(thread_map_remove); +DECLARE_SUITE(cpu_map_synthesize); +DECLARE_SUITE(synthesize_stat_config); +DECLARE_SUITE(synthesize_stat); +DECLARE_SUITE(synthesize_stat_round); +DECLARE_SUITE(event_update); +DECLARE_SUITE(event_times); +DECLARE_SUITE(backward_ring_buffer); +DECLARE_SUITE(cpu_map_print); +DECLARE_SUITE(cpu_map_merge); +DECLARE_SUITE(sdt_event); +DECLARE_SUITE(is_printable_array); +DECLARE_SUITE(bitmap_print); +DECLARE_SUITE(perf_hooks); +DECLARE_SUITE(clang); +DECLARE_SUITE(unit_number__scnprint); +DECLARE_SUITE(mem2node); +DECLARE_SUITE(maps__merge_in); +DECLARE_SUITE(time_utils); +DECLARE_SUITE(jit_write_elf); +DECLARE_SUITE(api_io); +DECLARE_SUITE(demangle_java); +DECLARE_SUITE(demangle_ocaml); +DECLARE_SUITE(pfm); +DECLARE_SUITE(parse_metric); +DECLARE_SUITE(pe_file_parsing); +DECLARE_SUITE(expand_cgroup_events); +DECLARE_SUITE(perf_time_to_tsc); +DECLARE_SUITE(dlfilter); +DECLARE_SUITE(sigtrap); + +/* + * PowerPC and S390 do not support creation of instruction breakpoints using the + * perf_event interface. + * + * ARM requires explicit rounding down of the instruction pointer in Thumb mode, + * and then requires the single-step to be handled explicitly in the overflow + * handler to avoid stepping into the SIGIO handler and getting stuck on the + * breakpointed instruction. + * + * Since arm64 has the same issue with arm for the single-step handling, this + * case also gets stuck on the breakpointed instruction. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || defined(__aarch64__) +#define BP_SIGNAL_IS_SUPPORTED 0 +#else +#define BP_SIGNAL_IS_SUPPORTED 1 +#endif #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; @@ -142,7 +177,7 @@ int test__arch_unwind_sample(struct perf_sample *sample, #endif #if defined(__arm__) -int test__vectors_page(struct test *test, int subtest); +DECLARE_SUITE(vectors_page); #endif #endif /* TESTS_H */ diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index d1e208b4a571..e413c1387fcb 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -19,7 +19,7 @@ struct machine; #define NAME (const char *) "perf" #define NAMEUL (unsigned long) NAME -int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *map; @@ -86,7 +86,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *threads; @@ -106,7 +106,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __ return 0; } -int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map_remove(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *threads; char *str; @@ -145,3 +145,7 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb perf_thread_map__put(threads); return 0; } + +DEFINE_SUITE("Thread map", thread_map); +DEFINE_SUITE("Synthesize thread map", thread_map_synthesize); +DEFINE_SUITE("Remove thread map", thread_map_remove); diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c index 9371484973f2..84edd82c519e 100644 --- a/tools/perf/tests/thread-maps-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -4,7 +4,7 @@ #include "thread.h" #include "debug.h" -int test__thread_maps_share(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_maps_share(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machines machines; struct machine *machine; @@ -96,3 +96,5 @@ int test__thread_maps_share(struct test *test __maybe_unused, int subtest __mayb machines__exit(&machines); return 0; } + +DEFINE_SUITE("Share thread maps", thread_maps_share); diff --git a/tools/perf/tests/time-utils-test.c b/tools/perf/tests/time-utils-test.c index fe57ca3b6e54..38df10373c1e 100644 --- a/tools/perf/tests/time-utils-test.c +++ b/tools/perf/tests/time-utils-test.c @@ -131,7 +131,7 @@ out: return pass; } -int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__time_utils(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { bool pass = true; @@ -249,3 +249,5 @@ int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused) return pass ? 0 : TEST_FAIL; } + +DEFINE_SUITE("time utils", time_utils); diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index b9028e304ddd..ee1e3dcbc0bd 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -49,7 +49,9 @@ static int session_write_header(char *path) session->evlist = evlist__new(); TEST_ASSERT_VAL("can't get evlist", session->evlist); + parse_events_error__init(&err); parse_events(session->evlist, "cpu_core/cycles/", &err); + parse_events_error__exit(&err); } perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY); @@ -110,62 +112,88 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu); for (i = 0; i < session->header.env.nr_cpus_avail; i++) { - if (!cpu_map__has(map, i)) + struct perf_cpu cpu = { .cpu = i }; + + if (!perf_cpu_map__has(map, cpu)) continue; pr_debug("CPU %d, core %d, socket %d\n", i, session->header.env.cpu[i].core_id, session->header.env.cpu[i].socket_id); } + // Test that CPU ID contains socket, die, core and CPU + for (i = 0; i < perf_cpu_map__nr(map); i++) { + id = aggr_cpu_id__cpu(perf_cpu_map__cpu(map, i), NULL); + TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match", + perf_cpu_map__cpu(map, i).cpu == id.cpu.cpu); + + TEST_ASSERT_VAL("Cpu map - Core ID doesn't match", + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core); + TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match", + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id == + id.socket); + + TEST_ASSERT_VAL("Cpu map - Die ID doesn't match", + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die); + TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Cpu map - Thread is set", id.thread == -1); + } + // Test that core ID contains socket, die and core - for (i = 0; i < map->nr; i++) { - id = cpu_map__get_core(map, i, NULL); + for (i = 0; i < perf_cpu_map__nr(map); i++) { + id = aggr_cpu_id__core(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Core map - Core ID doesn't match", - session->header.env.cpu[map->map[i]].core_id == id.core); + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core); TEST_ASSERT_VAL("Core map - Socket ID doesn't match", - session->header.env.cpu[map->map[i]].socket_id == id.socket); + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id == + id.socket); TEST_ASSERT_VAL("Core map - Die ID doesn't match", - session->header.env.cpu[map->map[i]].die_id == id.die); + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die); TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1); TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1); } // Test that die ID contains socket and die - for (i = 0; i < map->nr; i++) { - id = cpu_map__get_die(map, i, NULL); + for (i = 0; i < perf_cpu_map__nr(map); i++) { + id = aggr_cpu_id__die(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Die map - Socket ID doesn't match", - session->header.env.cpu[map->map[i]].socket_id == id.socket); + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id == + id.socket); TEST_ASSERT_VAL("Die map - Die ID doesn't match", - session->header.env.cpu[map->map[i]].die_id == id.die); + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die); TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1); TEST_ASSERT_VAL("Die map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Die map - CPU is set", id.cpu.cpu == -1); TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1); } // Test that socket ID contains only socket - for (i = 0; i < map->nr; i++) { - id = cpu_map__get_socket(map, i, NULL); + for (i = 0; i < perf_cpu_map__nr(map); i++) { + id = aggr_cpu_id__socket(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Socket map - Socket ID doesn't match", - session->header.env.cpu[map->map[i]].socket_id == id.socket); + session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id == + id.socket); TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1); TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1); TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Socket map - CPU is set", id.cpu.cpu == -1); TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1); } // Test that node ID contains only node - for (i = 0; i < map->nr; i++) { - id = cpu_map__get_node(map, i, NULL); + for (i = 0; i < perf_cpu_map__nr(map); i++) { + id = aggr_cpu_id__node(perf_cpu_map__cpu(map, i), NULL); TEST_ASSERT_VAL("Node map - Node ID doesn't match", - cpu__get_node(map->map[i]) == id.node); + cpu__get_node(perf_cpu_map__cpu(map, i)) == id.node); TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1); TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1); TEST_ASSERT_VAL("Node map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Node map - CPU is set", id.cpu.cpu == -1); TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1); } perf_session__delete(session); @@ -173,7 +201,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) return 0; } -int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__session_topology(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char path[PATH_MAX]; struct perf_cpu_map *map; @@ -199,3 +227,5 @@ free_path: unlink(path); return ret; } + +DEFINE_SUITE("Session topology", session_topology); diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c index 3721757435da..88bcada1c78f 100644 --- a/tools/perf/tests/unit_number__scnprintf.c +++ b/tools/perf/tests/unit_number__scnprintf.c @@ -7,7 +7,7 @@ #include "units.h" #include "debug.h" -int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__unit_number__scnprint(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct { u64 n; @@ -38,3 +38,5 @@ int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __may return TEST_OK; } + +DEFINE_SUITE("unit_number__scnprintf", unit_number__scnprint); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 193b7c91b4e2..e80df13c0420 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -3,6 +3,7 @@ #include <linux/rbtree.h> #include <inttypes.h> #include <string.h> +#include <ctype.h> #include <stdlib.h> #include "dso.h" #include "map.h" @@ -14,7 +15,104 @@ #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x)) -int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused) +static bool is_ignored_symbol(const char *name, char type) +{ + /* Symbol names that exactly match to the following are ignored.*/ + static const char * const ignored_symbols[] = { + /* + * Symbols which vary between passes. Passes 1 and 2 must have + * identical symbol lists. The kallsyms_* symbols below are + * only added after pass 1, they would be included in pass 2 + * when --all-symbols is specified so exclude them to get a + * stable symbol list. + */ + "kallsyms_addresses", + "kallsyms_offsets", + "kallsyms_relative_base", + "kallsyms_num_syms", + "kallsyms_names", + "kallsyms_markers", + "kallsyms_token_table", + "kallsyms_token_index", + /* Exclude linker generated symbols which vary between passes */ + "_SDA_BASE_", /* ppc */ + "_SDA2_BASE_", /* ppc */ + NULL + }; + + /* Symbol names that begin with the following are ignored.*/ + static const char * const ignored_prefixes[] = { + "$", /* local symbols for ARM, MIPS, etc. */ + ".LASANPC", /* s390 kasan local symbols */ + "__crc_", /* modversions */ + "__efistub_", /* arm64 EFI stub namespace */ + "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ + "__AArch64ADRPThunk_", /* arm64 lld */ + "__ARMV5PILongThunk_", /* arm lld */ + "__ARMV7PILongThunk_", + "__ThumbV7PILongThunk_", + "__LA25Thunk_", /* mips lld */ + "__microLA25Thunk_", + NULL + }; + + /* Symbol names that end with the following are ignored.*/ + static const char * const ignored_suffixes[] = { + "_from_arm", /* arm */ + "_from_thumb", /* arm */ + "_veneer", /* arm */ + NULL + }; + + /* Symbol names that contain the following are ignored.*/ + static const char * const ignored_matches[] = { + ".long_branch.", /* ppc stub */ + ".plt_branch.", /* ppc stub */ + NULL + }; + + const char * const *p; + + for (p = ignored_symbols; *p; p++) + if (!strcmp(name, *p)) + return true; + + for (p = ignored_prefixes; *p; p++) + if (!strncmp(name, *p, strlen(*p))) + return true; + + for (p = ignored_suffixes; *p; p++) { + int l = strlen(name) - strlen(*p); + + if (l >= 0 && !strcmp(name + l, *p)) + return true; + } + + for (p = ignored_matches; *p; p++) { + if (strstr(name, *p)) + return true; + } + + if (type == 'U' || type == 'u') + return true; + /* exclude debugging symbols */ + if (type == 'N' || type == 'n') + return true; + + if (toupper(type) == 'A') { + /* Keep these useful absolute symbols */ + if (strcmp(name, "__kernel_syscall_via_break") && + strcmp(name, "__kernel_syscall_via_epc") && + strcmp(name, "__kernel_sigtramp") && + strcmp(name, "__gp")) + return true; + } + + return false; +} + +static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = -1; struct rb_node *nd; @@ -169,6 +267,11 @@ next_pair: * such as __indirect_thunk_end. */ continue; + } else if (is_ignored_symbol(sym->name, sym->type)) { + /* + * Ignore hidden symbols, see scripts/kallsyms.c for the details + */ + continue; } else { pr_debug("ERR : %#" PRIx64 ": %s not on kallsyms\n", mem_start, sym->name); @@ -250,3 +353,5 @@ out: machine__exit(&vmlinux); return err; } + +DEFINE_SUITE("vmlinux symtab matches kallsyms", vmlinux_matches_kallsyms); diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c index 9387fa76faa5..9d4c45184e71 100644 --- a/tools/perf/tests/wp.c +++ b/tools/perf/tests/wp.c @@ -21,6 +21,7 @@ do { \ volatile u64 data1; volatile u8 data2[3]; +#ifndef __s390x__ static int wp_read(int fd, long long *count, int size) { int ret = read(fd, count, size); @@ -61,9 +62,14 @@ static int __event(int wp_type, void *wp_addr, unsigned long wp_len) return fd; } +#endif -static int wp_ro_test(void) +static int test__wp_ro(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) || defined(__x86_64__) || defined(__i386__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -79,10 +85,15 @@ static int wp_ro_test(void) close(fd); return 0; +#endif } -static int wp_wo_test(void) +static int test__wp_wo(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -98,10 +109,15 @@ static int wp_wo_test(void) close(fd); return 0; +#endif } -static int wp_rw_test(void) +static int test__wp_rw(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -118,10 +134,15 @@ static int wp_rw_test(void) close(fd); return 0; +#endif } -static int wp_modify_test(void) +static int test__wp_modify(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd, ret; unsigned long tmp = rand(); struct perf_event_attr new_attr; @@ -163,93 +184,18 @@ static int wp_modify_test(void) close(fd); return 0; -} - -static bool wp_ro_supported(void) -{ -#if defined (__x86_64__) || defined (__i386__) - return false; -#else - return true; -#endif -} - -static const char *wp_ro_skip_msg(void) -{ -#if defined (__x86_64__) || defined (__i386__) - return "missing hardware support"; -#else - return NULL; #endif } -static struct { - const char *desc; - int (*target_func)(void); - bool (*is_supported)(void); - const char *(*skip_msg)(void); -} wp_testcase_table[] = { - { - .desc = "Read Only Watchpoint", - .target_func = &wp_ro_test, - .is_supported = &wp_ro_supported, - .skip_msg = &wp_ro_skip_msg, - }, - { - .desc = "Write Only Watchpoint", - .target_func = &wp_wo_test, - }, - { - .desc = "Read / Write Watchpoint", - .target_func = &wp_rw_test, - }, - { - .desc = "Modify Watchpoint", - .target_func = &wp_modify_test, - }, +static struct test_case wp_tests[] = { + TEST_CASE_REASON("Read Only Watchpoint", wp_ro, "missing hardware support"), + TEST_CASE_REASON("Write Only Watchpoint", wp_wo, "missing hardware support"), + TEST_CASE_REASON("Read / Write Watchpoint", wp_rw, "missing hardware support"), + TEST_CASE_REASON("Modify Watchpoint", wp_modify, "missing hardware support"), + { .name = NULL, } }; -int test__wp_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(wp_testcase_table); -} - -const char *test__wp_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return NULL; - return wp_testcase_table[i].desc; -} - -const char *test__wp_subtest_skip_reason(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return NULL; - if (!wp_testcase_table[i].skip_msg) - return NULL; - return wp_testcase_table[i].skip_msg(); -} - -int test__wp(struct test *test __maybe_unused, int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return TEST_FAIL; - - if (wp_testcase_table[i].is_supported && - !wp_testcase_table[i].is_supported()) - return TEST_SKIP; - - return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL; -} - -/* The s390 so far does not have support for - * instruction breakpoint using the perf_event_open() system call. - */ -bool test__wp_is_supported(void) -{ -#if defined(__s390x__) - return false; -#else - return true; -#endif -} +struct test_suite suite__wp = { + .desc = "Watchpoint", + .test_cases = wp_tests, +}; diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index d6dfe68a7612..f527a46ab4e7 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -62,6 +62,8 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_ extern struct strarray strarray__socket_families; +extern struct strarray strarray__socket_level; + /** * augmented_arg: extra payload for syscall pointer arguments @@ -230,6 +232,9 @@ size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg); #define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol +size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SK_LEVEL syscall_arg__scnprintf_socket_level + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 041d6032a348..8ef26d89ef49 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -364,6 +364,8 @@ struct ucred { #define SOL_KCM 281 #define SOL_TLS 282 #define SOL_XDP 283 +#define SOL_MPTCP 284 +#define SOL_MCTP 285 /* IPX options */ #define IPX_TYPE 1 diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh index 3109d7b05e11..3d278785fe57 100755 --- a/tools/perf/trace/beauty/prctl_option.sh +++ b/tools/perf/trace/beauty/prctl_option.sh @@ -4,7 +4,7 @@ [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *prctl_options[] = {\n" -regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*' +regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$' egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \ sed -r "s/$regex/\2 \1/g" | \ sort -n | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c index cd110634ab09..2e0e867c0c1b 100644 --- a/tools/perf/trace/beauty/sockaddr.c +++ b/tools/perf/trace/beauty/sockaddr.c @@ -7,7 +7,7 @@ #include <sys/un.h> #include <arpa/inet.h> -#include "trace/beauty/generated/socket_arrays.c" +#include "trace/beauty/generated/sockaddr.c" DEFINE_STRARRAY(socket_families, "PF_"); static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size) diff --git a/tools/perf/trace/beauty/sockaddr.sh b/tools/perf/trace/beauty/sockaddr.sh new file mode 100755 index 000000000000..3820e5c82293 --- /dev/null +++ b/tools/perf/trace/beauty/sockaddr.sh @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: LGPL-2.1 + +# This one uses a copy from the kernel sources headers that is in a +# place used just for these tools/perf/beauty/ usage, we shouldn't not +# put it in tools/include/linux otherwise they would be used in the +# normal compiler building process and would drag needless stuff from the +# kernel. + +# When what these scripts need is already in tools/include/ then use it, +# otherwise grab and check the copy from the kernel sources just for these +# string table building scripts. + +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/ + +printf "static const char *socket_families[] = {\n" +# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ +regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*' + +egrep $regex ${header_dir}/socket.h | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[%s] = \"%s\",\n" | \ + egrep -v "\"(UNIX|MAX)\"" +printf "};\n" diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c index f23a3dda2902..b0870c7b48e5 100644 --- a/tools/perf/trace/beauty/socket.c +++ b/tools/perf/trace/beauty/socket.c @@ -9,9 +9,10 @@ #include <sys/types.h> #include <sys/socket.h> +#include "trace/beauty/generated/socket.c" + static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size, bool show_prefix) { -#include "trace/beauty/generated/socket_ipproto_array.c" static DEFINE_STRARRAY(socket_ipproto, "IPPROTO_"); return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", show_prefix, protocol); @@ -26,3 +27,21 @@ size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct sysc return syscall_arg__scnprintf_int(bf, size, arg); } + +static size_t socket__scnprintf_level(int level, char *bf, size_t size, bool show_prefix) +{ +#if defined(__alpha__) || defined(__hppa__) || defined(__mips__) || defined(__sparc__) + const int sol_socket = 0xffff; +#else + const int sol_socket = 1; +#endif + if (level == sol_socket) + return scnprintf(bf, size, "%sSOCKET", show_prefix ? "SOL_" : ""); + + return strarray__scnprintf(&strarray__socket_level, bf, size, "%d", show_prefix, level); +} + +size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg) +{ + return socket__scnprintf_level(arg->val, bf, size, arg->show_string_prefix); +} diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh index 3820e5c82293..76330acb27e5 100755 --- a/tools/perf/trace/beauty/socket.sh +++ b/tools/perf/trace/beauty/socket.sh @@ -1,24 +1,28 @@ #!/bin/sh # SPDX-License-Identifier: LGPL-2.1 -# This one uses a copy from the kernel sources headers that is in a -# place used just for these tools/perf/beauty/ usage, we shouldn't not -# put it in tools/include/linux otherwise they would be used in the -# normal compiler building process and would drag needless stuff from the -# kernel. +if [ $# -gt 0 ] ; then + uapi_header_dir=$1 + beauty_header_dir=$2 +else + uapi_header_dir=tools/include/uapi/linux/ + beauty_header_dir=tools/perf/trace/beauty/include/linux/ +fi -# When what these scripts need is already in tools/include/ then use it, -# otherwise grab and check the copy from the kernel sources just for these -# string table building scripts. +printf "static const char *socket_ipproto[] = {\n" +ipproto_regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' -[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/ +egrep $ipproto_regex ${uapi_header_dir}/in.h | \ + sed -r "s/$ipproto_regex/\2 \1/g" | \ + sort -n | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n\n" -printf "static const char *socket_families[] = {\n" -# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ -regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*' +printf "static const char *socket_level[] = {\n" +socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+\/.*)?' -egrep $regex ${header_dir}/socket.h | \ - sed -r "s/$regex/\2 \1/g" | \ - xargs printf "\t[%s] = \"%s\",\n" | \ - egrep -v "\"(UNIX|MAX)\"" -printf "};\n" +egrep $socket_level_regex ${beauty_header_dir}/socket.h | \ + sed -r "s/$socket_level_regex/\2 \1/g" | \ + sort -n | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n\n" + +printf 'DEFINE_STRARRAY(socket_level, "SOL_");\n' diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh deleted file mode 100755 index de0f2f29017f..000000000000 --- a/tools/perf/trace/beauty/socket_ipproto.sh +++ /dev/null @@ -1,12 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: LGPL-2.1 - -[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ - -printf "static const char *socket_ipproto[] = {\n" -regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' - -egrep $regex ${header_dir}/in.h | \ - sed -r "s/$regex/\2 \1/g" | \ - sort | xargs printf "\t[%s] = \"%s\",\n" -printf "};\n" diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index e81c2493efdf..44ba900828f6 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -966,6 +966,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, .opts = opts, }; int ret = -1, err; + int not_annotated = list_empty(¬es->src->source); if (sym == NULL) return -1; @@ -973,13 +974,15 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, if (ms->map->dso->annotate_warned) return -1; - err = symbol__annotate2(ms, evsel, opts, &browser.arch); - if (err) { - char msg[BUFSIZ]; - ms->map->dso->annotate_warned = true; - symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); - ui__error("Couldn't annotate %s:\n%s", sym->name, msg); - goto out_free_offsets; + if (not_annotated) { + err = symbol__annotate2(ms, evsel, opts, &browser.arch); + if (err) { + char msg[BUFSIZ]; + ms->map->dso->annotate_warned = true; + symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); + ui__error("Couldn't annotate %s:\n%s", sym->name, msg); + goto out_free_offsets; + } } ui_helpline__push("Press ESC to exit"); @@ -994,9 +997,11 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, ret = annotate_browser__run(&browser, evsel, hbt); - annotated_source__purge(notes->src); + if(not_annotated) + annotated_source__purge(notes->src); out_free_offsets: - zfree(¬es->offsets); + if(not_annotated) + zfree(¬es->offsets); return ret; } diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index c1f24d004852..5075ecead5f3 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -535,6 +535,18 @@ struct perf_hpp_list perf_hpp_list = { #undef __HPP_SORT_ACC_FN #undef __HPP_SORT_RAW_FN +static void fmt_free(struct perf_hpp_fmt *fmt) +{ + /* + * At this point fmt should be completely + * unhooked, if not it's a bug. + */ + BUG_ON(!list_empty(&fmt->list)); + BUG_ON(!list_empty(&fmt->sort_list)); + + if (fmt->free) + fmt->free(fmt); +} void perf_hpp__init(void) { @@ -598,9 +610,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, list_add(&format->sort_list, &list->sorts); } -void perf_hpp__column_unregister(struct perf_hpp_fmt *format) +static void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { list_del_init(&format->list); + fmt_free(format); } void perf_hpp__cancel_cumulate(void) @@ -672,19 +685,6 @@ next: } -static void fmt_free(struct perf_hpp_fmt *fmt) -{ - /* - * At this point fmt should be completely - * unhooked, if not it's a bug. - */ - BUG_ON(!list_empty(&fmt->list)); - BUG_ON(!list_empty(&fmt->sort_list)); - - if (fmt->free) - fmt->free(fmt); -} - void perf_hpp__reset_output_field(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt, *tmp; diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index e9bfe856a5de..b1be59b4e2a4 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -170,9 +170,11 @@ void ui__exit(bool wait_for_ok) "Press any key...", 0); SLtt_set_cursor_visibility(1); - SLsmg_refresh(); - SLsmg_reset_smg(); + if (!pthread_mutex_trylock(&ui__lock)) { + SLsmg_refresh(); + SLsmg_reset_smg(); + pthread_mutex_unlock(&ui__lock); + } SLang_reset_tty(); - perf_error__unregister(&perf_tui_eops); } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index f2914d5bed6e..2a403cefcaf2 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,3 +1,4 @@ +perf-y += arm64-frame-pointer-unwind-support.o perf-y += annotate.o perf-y += block-info.o perf-y += block-range.o @@ -138,11 +139,13 @@ perf-y += expr.o perf-y += branch.o perf-y += mem2node.o perf-y += clockid.o +perf-y += list_sort.o perf-$(CONFIG_LIBBPF) += bpf-loader.o perf-$(CONFIG_LIBBPF) += bpf_map.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o @@ -201,6 +204,7 @@ endif perf-y += perf-hooks.o perf-$(CONFIG_LIBBPF) += bpf-event.o +perf-$(CONFIG_LIBBPF) += bpf-utils.o perf-$(CONFIG_CXX) += c++/ @@ -315,3 +319,7 @@ $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/list_sort.o: ../lib/list_sort.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c index 7b12bd7a3080..4d216c0dc425 100644 --- a/tools/perf/util/affinity.c +++ b/tools/perf/util/affinity.c @@ -11,7 +11,7 @@ static int get_cpu_set_size(void) { - int sz = cpu__max_cpu() + 8 - 1; + int sz = cpu__max_cpu().cpu + 8 - 1; /* * sched_getaffinity doesn't like masks smaller than the kernel. * Hopefully that's big enough. @@ -62,7 +62,7 @@ void affinity__set(struct affinity *a, int cpu) clear_bit(cpu, a->sched_cpus); } -void affinity__cleanup(struct affinity *a) +static void __affinity__cleanup(struct affinity *a) { int cpu_set_size = get_cpu_set_size(); @@ -71,3 +71,9 @@ void affinity__cleanup(struct affinity *a) zfree(&a->sched_cpus); zfree(&a->orig_cpus); } + +void affinity__cleanup(struct affinity *a) +{ + if (a != NULL) + __affinity__cleanup(a); +} diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0bae061b2d6d..8190a124b99d 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -28,6 +28,7 @@ #include "evsel.h" #include "evlist.h" #include "bpf-event.h" +#include "bpf-utils.h" #include "block-range.h" #include "string2.h" #include "util/event.h" @@ -151,6 +152,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" +#include "arch/riscv64/annotate/instructions.c" #include "arch/s390/annotate/instructions.c" #include "arch/sparc/annotate/instructions.c" @@ -183,7 +185,6 @@ static struct arch architectures[] = { .init = x86__annotate_init, .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), - .ins_is_fused = x86__ins_is_fused, .objdump = { .comment_char = '#', }, @@ -193,6 +194,10 @@ static struct arch architectures[] = { .init = powerpc__annotate_init, }, { + .name = "riscv64", + .init = riscv64__annotate_init, + }, + { .name = "s390", .init = s390__annotate_init, .objdump = { @@ -1250,6 +1255,17 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name); } +void annotation__init(struct annotation *notes) +{ + pthread_mutex_init(¬es->lock, NULL); +} + +void annotation__exit(struct annotation *notes) +{ + annotated_source__delete(notes->src); + pthread_mutex_destroy(¬es->lock); +} + static void annotation_line__add(struct annotation_line *al, struct list_head *head) { list_add_tail(&al->node, head); @@ -1700,12 +1716,12 @@ static int symbol__disassemble_bpf(struct symbol *sym, { struct annotation *notes = symbol__annotation(sym); struct annotation_options *opts = args->options; - struct bpf_prog_info_linear *info_linear; struct bpf_prog_linfo *prog_linfo = NULL; struct bpf_prog_info_node *info_node; int len = sym->end - sym->start; disassembler_ftype disassemble; struct map *map = args->ms.map; + struct perf_bpil *info_linear; struct disassemble_info info; struct dso *dso = map->dso; int pc = 0, count, sub_id; @@ -2020,6 +2036,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) memset(&objdump_process, 0, sizeof(objdump_process)); objdump_process.argv = objdump_argv; objdump_process.out = -1; + objdump_process.err = -1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; @@ -3127,7 +3144,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, notes->nr_events = nr_pcnt; annotation__update_column_widths(notes); - sym->annotate2 = true; + sym->annotate2 = 1; return 0; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 3757416bcf46..986f2bbe4870 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -299,6 +299,9 @@ struct annotation { struct annotated_source *src; }; +void annotation__init(struct annotation *notes); +void annotation__exit(struct annotation *notes); + static inline int annotation__cycles_width(struct annotation *notes) { if (notes->have_cycles && notes->options->show_minmax_cycle) diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 32fe41835fa6..5e390a1a79ab 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -151,6 +151,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) u64 payload, ip; memset(&decoder->record, 0x0, sizeof(decoder->record)); + decoder->record.context_id = (u64)-1; while (1) { err = arm_spe_get_next_packet(decoder); @@ -178,8 +179,11 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) decoder->record.phys_addr = ip; break; case ARM_SPE_COUNTER: + if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT) + decoder->record.latency = payload; break; case ARM_SPE_CONTEXT: + decoder->record.context_id = payload; break; case ARM_SPE_OP_TYPE: if (idx == SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC) { diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 59bdb7309674..69b31084d6be 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -33,11 +33,13 @@ struct arm_spe_record { enum arm_spe_sample_type type; int err; u32 op; + u32 latency; u64 from_ip; u64 to_ip; u64 timestamp; u64 virt_addr; u64 phys_addr; + u64 context_id; }; struct arm_spe_insn; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index 2e5eff4f8f03..2f311189c6e8 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -13,7 +13,7 @@ #include "arm-spe-pkt-decoder.h" -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ #define le16_to_cpu bswap_16 #define le32_to_cpu bswap_32 #define le64_to_cpu bswap_64 diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 58b7069c5a5f..d2b64e3f588b 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -51,12 +51,15 @@ struct arm_spe { u8 timeless_decoding; u8 data_queued; + u64 sample_type; u8 sample_flc; u8 sample_llc; u8 sample_tlb; u8 sample_branch; u8 sample_remote_access; u8 sample_memory; + u8 sample_instructions; + u64 instructions_sample_period; u64 l1d_miss_id; u64 l1d_access_id; @@ -67,10 +70,12 @@ struct arm_spe { u64 branch_miss_id; u64 remote_access_id; u64 memory_id; + u64 instructions_id; u64 kernel_start; unsigned long num_events; + u8 use_ctx_pkt_for_pid; }; struct arm_spe_queue { @@ -88,6 +93,7 @@ struct arm_spe_queue { u64 time; u64 timestamp; struct thread *thread; + u64 period_instructions; }; static void arm_spe_dump(struct arm_spe *spe __maybe_unused, @@ -100,7 +106,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused, const char *color = PERF_COLOR_BLUE; color_fprintf(stdout, color, - ". ... ARM SPE data: size %zu bytes\n", + ". ... ARM SPE data: size %#zx bytes\n", len); while (len) { @@ -200,6 +206,7 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe, speq->pid = -1; speq->tid = -1; speq->cpu = -1; + speq->period_instructions = 0; /* params set */ params.get_trace = arm_spe_get_trace; @@ -226,6 +233,44 @@ static inline u8 arm_spe_cpumode(struct arm_spe *spe, u64 ip) PERF_RECORD_MISC_USER; } +static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, + struct auxtrace_queue *queue) +{ + struct arm_spe_queue *speq = queue->priv; + pid_t tid; + + tid = machine__get_current_tid(spe->machine, speq->cpu); + if (tid != -1) { + speq->tid = tid; + thread__zput(speq->thread); + } else + speq->tid = queue->tid; + + if ((!speq->thread) && (speq->tid != -1)) { + speq->thread = machine__find_thread(spe->machine, -1, + speq->tid); + } + + if (speq->thread) { + speq->pid = speq->thread->pid_; + if (queue->cpu == -1) + speq->cpu = speq->thread->cpu; + } +} + +static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid) +{ + struct arm_spe *spe = speq->spe; + int err = machine__set_current_tid(spe->machine, speq->cpu, -1, tid); + + if (err) + return err; + + arm_spe_set_pid_tid_cpu(spe, &spe->queues.queue_array[speq->queue_nr]); + + return 0; +} + static void arm_spe_prep_sample(struct arm_spe *spe, struct arm_spe_queue *speq, union perf_event *event, @@ -248,6 +293,12 @@ static void arm_spe_prep_sample(struct arm_spe *spe, event->sample.header.size = sizeof(struct perf_event_header); } +static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type) +{ + event->header.size = perf_event__sample_event_size(sample, type, 0); + return perf_event__synthesize_sample(event, type, 0, sample); +} + static inline int arm_spe_deliver_synth_event(struct arm_spe *spe, struct arm_spe_queue *speq __maybe_unused, @@ -256,6 +307,12 @@ arm_spe_deliver_synth_event(struct arm_spe *spe, { int ret; + if (spe->synth_opts.inject) { + ret = arm_spe__inject_event(event, sample, spe->sample_type); + if (ret) + return ret; + } + ret = perf_session__deliver_synth_event(spe->session, event, sample); if (ret) pr_err("ARM SPE: failed to deliver event, error %d\n", ret); @@ -278,6 +335,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, sample.addr = record->virt_addr; sample.phys_addr = record->phys_addr; sample.data_src = data_src; + sample.weight = record->latency; return arm_spe_deliver_synth_event(spe, speq, event, &sample); } @@ -295,6 +353,36 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, sample.id = spe_events_id; sample.stream_id = spe_events_id; sample.addr = record->to_ip; + sample.weight = record->latency; + + return arm_spe_deliver_synth_event(spe, speq, event, &sample); +} + +static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, + u64 spe_events_id, u64 data_src) +{ + struct arm_spe *spe = speq->spe; + struct arm_spe_record *record = &speq->decoder->record; + union perf_event *event = speq->event_buf; + struct perf_sample sample = { .ip = 0, }; + + /* + * Handles perf instruction sampling period. + */ + speq->period_instructions++; + if (speq->period_instructions < spe->instructions_sample_period) + return 0; + speq->period_instructions = 0; + + arm_spe_prep_sample(spe, speq, event, &sample); + + sample.id = spe_events_id; + sample.stream_id = spe_events_id; + sample.addr = record->virt_addr; + sample.phys_addr = record->phys_addr; + sample.data_src = data_src; + sample.period = spe->instructions_sample_period; + sample.weight = record->latency; return arm_spe_deliver_synth_event(spe, speq, event, &sample); } @@ -428,6 +516,12 @@ static int arm_spe_sample(struct arm_spe_queue *speq) return err; } + if (spe->sample_instructions) { + err = arm_spe__synth_instruction_sample(speq, spe->instructions_id, data_src); + if (err) + return err; + } + return 0; } @@ -460,6 +554,19 @@ static int arm_spe_run_decoder(struct arm_spe_queue *speq, u64 *timestamp) * can correlate samples between Arm SPE trace data and other * perf events with correct time ordering. */ + + /* + * Update pid/tid info. + */ + record = &speq->decoder->record; + if (!spe->timeless_decoding && record->context_id != (u64)-1) { + ret = arm_spe_set_tid(speq, record->context_id); + if (ret) + return ret; + + spe->use_ctx_pkt_for_pid = true; + } + ret = arm_spe_sample(speq); if (ret) return ret; @@ -586,31 +693,6 @@ static bool arm_spe__is_timeless_decoding(struct arm_spe *spe) return timeless_decoding; } -static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, - struct auxtrace_queue *queue) -{ - struct arm_spe_queue *speq = queue->priv; - pid_t tid; - - tid = machine__get_current_tid(spe->machine, speq->cpu); - if (tid != -1) { - speq->tid = tid; - thread__zput(speq->thread); - } else - speq->tid = queue->tid; - - if ((!speq->thread) && (speq->tid != -1)) { - speq->thread = machine__find_thread(spe->machine, -1, - speq->tid); - } - - if (speq->thread) { - speq->pid = speq->thread->pid_; - if (queue->cpu == -1) - speq->cpu = speq->thread->cpu; - } -} - static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) { unsigned int queue_nr; @@ -641,7 +723,12 @@ static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) ts = timestamp; } - arm_spe_set_pid_tid_cpu(spe, queue); + /* + * A previous context-switch event has set pid/tid in the machine's context, so + * here we need to update the pid/tid in the thread and SPE queue. + */ + if (!spe->use_ctx_pkt_for_pid) + arm_spe_set_pid_tid_cpu(spe, queue); ret = arm_spe_run_decoder(speq, &ts); if (ret < 0) { @@ -681,6 +768,25 @@ static int arm_spe_process_timeless_queues(struct arm_spe *spe, pid_t tid, return 0; } +static int arm_spe_context_switch(struct arm_spe *spe, union perf_event *event, + struct perf_sample *sample) +{ + pid_t pid, tid; + int cpu; + + if (!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT)) + return 0; + + pid = event->context_switch.next_prev_pid; + tid = event->context_switch.next_prev_tid; + cpu = sample->cpu; + + if (tid == -1) + pr_warning("context_switch event has no tid\n"); + + return machine__set_current_tid(spe->machine, cpu, pid, tid); +} + static int arm_spe_process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -718,6 +824,13 @@ static int arm_spe_process_event(struct perf_session *session, } } else if (timestamp) { err = arm_spe_process_queues(spe, timestamp); + if (err) + return err; + + if (!spe->use_ctx_pkt_for_pid && + (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE || + event->header.type == PERF_RECORD_SWITCH)) + err = arm_spe_context_switch(spe, event, sample); } return err; @@ -783,7 +896,15 @@ static int arm_spe_flush(struct perf_session *session __maybe_unused, return arm_spe_process_timeless_queues(spe, -1, MAX_TIMESTAMP - 1); - return arm_spe_process_queues(spe, MAX_TIMESTAMP); + ret = arm_spe_process_queues(spe, MAX_TIMESTAMP); + if (ret) + return ret; + + if (!spe->use_ctx_pkt_for_pid) + ui__warning("Arm SPE CONTEXT packets not found in the traces.\n" + "Matching of TIDs to SPE events could be inaccurate.\n"); + + return 0; } static void arm_spe_free_queue(void *priv) @@ -914,12 +1035,15 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) attr.type = PERF_TYPE_HARDWARE; attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | - PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC; + PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC | + PERF_SAMPLE_WEIGHT; if (spe->timeless_decoding) attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; else attr.sample_type |= PERF_SAMPLE_TIME; + spe->sample_type = attr.sample_type; + attr.exclude_user = evsel->core.attr.exclude_user; attr.exclude_kernel = evsel->core.attr.exclude_kernel; attr.exclude_hv = evsel->core.attr.exclude_hv; @@ -1026,7 +1150,29 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) return err; spe->memory_id = id; arm_spe_set_event_name(evlist, id, "memory"); + id += 1; + } + + if (spe->synth_opts.instructions) { + if (spe->synth_opts.period_type != PERF_ITRACE_PERIOD_INSTRUCTIONS) { + pr_warning("Only instruction-based sampling period is currently supported by Arm SPE.\n"); + goto synth_instructions_out; + } + if (spe->synth_opts.period > 1) + pr_warning("Arm SPE has a hardware-based sample period.\n" + "Additional instruction events will be discarded by --itrace\n"); + + spe->sample_instructions = true; + attr.config = PERF_COUNT_HW_INSTRUCTIONS; + attr.sample_period = spe->synth_opts.period; + spe->instructions_sample_period = attr.sample_period; + err = arm_spe_synth_event(session, &attr, id); + if (err) + return err; + spe->instructions_id = id; + arm_spe_set_event_name(evlist, id, "instructions"); } +synth_instructions_out: return 0; } diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c new file mode 100644 index 000000000000..2242a885fbd7 --- /dev/null +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "arm64-frame-pointer-unwind-support.h" +#include "callchain.h" +#include "event.h" +#include "perf_regs.h" // SMPL_REG_MASK +#include "unwind.h" + +#define perf_event_arm_regs perf_event_arm64_regs +#include "../../arch/arm64/include/uapi/asm/perf_regs.h" +#undef perf_event_arm_regs + +struct entries { + u64 stack[2]; + size_t length; +}; + +static bool get_leaf_frame_caller_enabled(struct perf_sample *sample) +{ + return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs + && sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR); +} + +static int add_entry(struct unwind_entry *entry, void *arg) +{ + struct entries *entries = arg; + + entries->stack[entries->length++] = entry->ip; + return 0; +} + +u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int usr_idx) +{ + int ret; + struct entries entries = {}; + struct regs_dump old_regs = sample->user_regs; + + if (!get_leaf_frame_caller_enabled(sample)) + return 0; + + /* + * If PC and SP are not recorded, get the value of PC from the stack + * and set its mask. SP is not used when doing the unwinding but it + * still needs to be set to prevent failures. + */ + + if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) { + sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC); + sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1]; + } + + if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) { + sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP); + sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; + } + + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + sample->user_regs = old_regs; + + if (ret || entries.length != 2) + return ret; + + return callchain_param.order == ORDER_CALLER ? entries.stack[0] : entries.stack[1]; +} diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h new file mode 100644 index 000000000000..32af9ce94398 --- /dev/null +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H +#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H + +#include "event.h" +#include "thread.h" + +u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx); + +#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */ diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 8d2865b9ade2..825336304a37 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -123,7 +123,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, mm->prev = 0; mm->idx = mp->idx; mm->tid = mp->tid; - mm->cpu = mp->cpu; + mm->cpu = mp->cpu.cpu; if (!mp->len) { mm->base = NULL; @@ -174,13 +174,13 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, mp->idx = idx; if (per_cpu) { - mp->cpu = evlist->core.cpus->map[idx]; + mp->cpu = perf_cpu_map__cpu(evlist->core.cpus, idx); if (evlist->core.threads) mp->tid = perf_thread_map__pid(evlist->core.threads, 0); else mp->tid = -1; } else { - mp->cpu = -1; + mp->cpu.cpu = -1; mp->tid = perf_thread_map__pid(evlist->core.threads, idx); } } @@ -292,7 +292,7 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues, if (!queue->set) { queue->set = true; queue->tid = buffer->tid; - queue->cpu = buffer->cpu; + queue->cpu = buffer->cpu.cpu; } buffer->buffer_nr = queues->next_buffer_nr++; @@ -339,11 +339,11 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues, return 0; } -static bool filter_cpu(struct perf_session *session, int cpu) +static bool filter_cpu(struct perf_session *session, struct perf_cpu cpu) { unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; - return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); + return cpu_bitmap && cpu.cpu != -1 && !test_bit(cpu.cpu, cpu_bitmap); } static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, @@ -399,7 +399,7 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, struct auxtrace_buffer buffer = { .pid = -1, .tid = event->auxtrace.tid, - .cpu = event->auxtrace.cpu, + .cpu = { event->auxtrace.cpu }, .data_offset = data_offset, .offset = event->auxtrace.offset, .reference = event->auxtrace.reference, @@ -1564,6 +1564,9 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, case 'q': synth_opts->quick += 1; break; + case 'A': + synth_opts->approx_ipc = true; + break; case 'Z': synth_opts->timeless_decoding = true; break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 5f383908ca6e..19910b9011f3 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -15,6 +15,7 @@ #include <linux/list.h> #include <linux/perf_event.h> #include <linux/types.h> +#include <internal/cpumap.h> #include <asm/bitsperlong.h> #include <asm/barrier.h> @@ -59,6 +60,7 @@ enum itrace_period_type { #define AUXTRACE_ERR_FLG_DATA_LOST (1 << ('l' - 'a')) #define AUXTRACE_LOG_FLG_ALL_PERF_EVTS (1 << ('a' - 'a')) +#define AUXTRACE_LOG_FLG_USE_STDOUT (1 << ('o' - 'a')) /** * struct itrace_synth_opts - AUX area tracing synthesis options. @@ -84,6 +86,7 @@ enum itrace_period_type { * @thread_stack: feed branches to the thread_stack * @last_branch: add branch context to 'instruction' events * @add_last_branch: add branch context to existing event records + * @approx_ipc: approximate IPC * @flc: whether to synthesize first level cache events * @llc: whether to synthesize last level cache events * @tlb: whether to synthesize TLB events @@ -127,6 +130,7 @@ struct itrace_synth_opts { bool thread_stack; bool last_branch; bool add_last_branch; + bool approx_ipc; bool flc; bool llc; bool tlb; @@ -237,7 +241,7 @@ struct auxtrace_buffer { size_t size; pid_t pid; pid_t tid; - int cpu; + struct perf_cpu cpu; void *data; off_t data_offset; void *mmap_addr; @@ -347,7 +351,7 @@ struct auxtrace_mmap_params { int prot; int idx; pid_t tid; - int cpu; + struct perf_cpu cpu; }; /** @@ -639,6 +643,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session, " d[flags]: create a debug log\n" \ " each flag must be preceded by + or -\n" \ " log flags are: a (all perf events)\n" \ +" o (output to stdout)\n" \ " f: synthesize first level cache events\n" \ " m: synthesize last level cache events\n" \ " t: synthesize TLB events\n" \ @@ -649,6 +654,8 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session, " L[len]: synthesize last branch entries on existing event records\n" \ " sNUMBER: skip initial number of events\n" \ " q: quicker (less detailed) decoding\n" \ +" A: approximate IPC\n" \ +" Z: prefer to ignore timestamps (so-called \"timeless\" decoding)\n" \ " PERIOD[ns|us|ms|i|t]: specify period to sample stream\n" \ " concatenate multiple options. Default is ibxwpe or cewp\n" diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 1a7112a87736..a517eaa51eb3 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -10,6 +10,7 @@ #include <internal/lib.h> #include <symbol/kallsyms.h> #include "bpf-event.h" +#include "bpf-utils.h" #include "debug.h" #include "dso.h" #include "symbol.h" @@ -32,7 +33,32 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) return err ? ERR_PTR(err) : btf; } -#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) +struct bpf_program * __weak +bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return bpf_program__next(prev, obj); +#pragma GCC diagnostic pop +} + +struct bpf_map * __weak +bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return bpf_map__next(prev, obj); +#pragma GCC diagnostic pop +} + +const void * __weak +btf__raw_data(const struct btf *btf_ro, __u32 *size) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return btf__get_raw_data(btf_ro, size); +#pragma GCC diagnostic pop +} static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len) { @@ -48,9 +74,9 @@ static int machine__process_bpf_event_load(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_info_node *info_node; struct perf_env *env = machine->env; + struct perf_bpil *info_linear; int id = event->bpf.id; unsigned int i; @@ -110,7 +136,7 @@ static int perf_env__fetch_btf(struct perf_env *env, u32 data_size; const void *data; - data = btf__get_raw_data(btf, &data_size); + data = btf__raw_data(btf, &data_size); node = malloc(data_size + sizeof(struct btf_node)); if (!node) @@ -120,7 +146,11 @@ static int perf_env__fetch_btf(struct perf_env *env, node->data_size = data_size; memcpy(node->data, data, data_size); - perf_env__insert_btf(env, node); + if (!perf_env__insert_btf(env, node)) { + /* Insertion failed because of a duplicate. */ + free(node); + return -1; + } return 0; } @@ -175,9 +205,9 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, { struct perf_record_ksymbol *ksymbol_event = &event->ksymbol; struct perf_record_bpf_event *bpf_event = &event->bpf; - struct bpf_prog_info_linear *info_linear; struct perf_tool *tool = session->tool; struct bpf_prog_info_node *info_node; + struct perf_bpil *info_linear; struct bpf_prog_info *info; struct btf *btf = NULL; struct perf_env *env; @@ -191,15 +221,15 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, */ env = session->data ? &session->header.env : &perf_env; - arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS; - arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; - arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; - arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS; - arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS; - arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; - arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; + arrays = 1UL << PERF_BPIL_JITED_KSYMS; + arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS; + arrays |= 1UL << PERF_BPIL_FUNC_INFO; + arrays |= 1UL << PERF_BPIL_PROG_TAGS; + arrays |= 1UL << PERF_BPIL_JITED_INSNS; + arrays |= 1UL << PERF_BPIL_LINE_INFO; + arrays |= 1UL << PERF_BPIL_JITED_LINE_INFO; - info_linear = bpf_program__get_prog_info_linear(fd, arrays); + info_linear = get_bpf_prog_info_linear(fd, arrays); if (IS_ERR_OR_NULL(info_linear)) { info_linear = NULL; pr_debug("%s: failed to get BPF program info. aborting\n", __func__); @@ -452,8 +482,8 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, static void perf_env__add_bpf_info(struct perf_env *env, u32 id) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_info_node *info_node; + struct perf_bpil *info_linear; struct btf *btf = NULL; u64 arrays; u32 btf_id; @@ -463,15 +493,15 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) if (fd < 0) return; - arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS; - arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; - arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; - arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS; - arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS; - arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; - arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; + arrays = 1UL << PERF_BPIL_JITED_KSYMS; + arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS; + arrays |= 1UL << PERF_BPIL_FUNC_INFO; + arrays |= 1UL << PERF_BPIL_PROG_TAGS; + arrays |= 1UL << PERF_BPIL_JITED_INSNS; + arrays |= 1UL << PERF_BPIL_LINE_INFO; + arrays |= 1UL << PERF_BPIL_JITED_LINE_INFO; - info_linear = bpf_program__get_prog_info_linear(fd, arrays); + info_linear = get_bpf_prog_info_linear(fd, arrays); if (IS_ERR_OR_NULL(info_linear)) { pr_debug("%s: failed to get BPF program info. aborting\n", __func__); goto out; @@ -576,7 +606,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, 0); fprintf(fp, "# bpf_prog_info %u: %s addr 0x%llx size %u\n", info->id, name, prog_addrs[0], prog_lens[0]); - return; + goto out; } fprintf(fp, "# bpf_prog_info %u:\n", info->id); @@ -586,4 +616,6 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, fprintf(fp, "# \tsub_prog %u: %s addr 0x%llx size %u\n", i, name, prog_addrs[i], prog_lens[i]); } +out: + btf__free(btf); } diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h index 68f315c3df5b..144a8a24cc69 100644 --- a/tools/perf/util/bpf-event.h +++ b/tools/perf/util/bpf-event.h @@ -19,7 +19,7 @@ struct evlist; struct target; struct bpf_prog_info_node { - struct bpf_prog_info_linear *info_linear; + struct perf_bpil *info_linear; struct rb_node rb_node; }; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index fbb3c4057c30..7ecfaac7536a 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -29,6 +29,9 @@ #include <internal/xyarray.h> +/* temporarily disable libbpf deprecation warnings */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)), const char *fmt, va_list args) { @@ -421,7 +424,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n, size_t prologue_cnt = 0; int i, err; - if (IS_ERR(priv) || !priv || priv->is_tp) + if (IS_ERR_OR_NULL(priv) || priv->is_tp) goto errout; pev = &priv->pev; @@ -570,7 +573,7 @@ static int hook_load_preprocessor(struct bpf_program *prog) bool need_prologue = false; int err, i; - if (IS_ERR(priv) || !priv) { + if (IS_ERR_OR_NULL(priv)) { pr_debug("Internal error when hook preprocessor\n"); return -BPF_LOADER_ERRNO__INTERNAL; } @@ -642,8 +645,11 @@ int bpf__probe(struct bpf_object *obj) goto out; priv = bpf_program__priv(prog); - if (IS_ERR(priv) || !priv) { - err = PTR_ERR(priv); + if (IS_ERR_OR_NULL(priv)) { + if (!priv) + err = -BPF_LOADER_ERRNO__INTERNAL; + else + err = PTR_ERR(priv); goto out; } @@ -693,7 +699,7 @@ int bpf__unprobe(struct bpf_object *obj) struct bpf_prog_priv *priv = bpf_program__priv(prog); int i; - if (IS_ERR(priv) || !priv || priv->is_tp) + if (IS_ERR_OR_NULL(priv) || priv->is_tp) continue; for (i = 0; i < priv->pev.ntevs; i++) { @@ -751,7 +757,7 @@ int bpf__foreach_event(struct bpf_object *obj, struct perf_probe_event *pev; int i, fd; - if (IS_ERR(priv) || !priv) { + if (IS_ERR_OR_NULL(priv)) { pr_debug("bpf: failed to get private field\n"); return -BPF_LOADER_ERRNO__INTERNAL; } diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c new file mode 100644 index 000000000000..e271e05e51bc --- /dev/null +++ b/tools/perf/util/bpf-utils.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + +#include <errno.h> +#include <stdlib.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <bpf/bpf.h> +#include "bpf-utils.h" +#include "debug.h" + +struct bpil_array_desc { + int array_offset; /* e.g. offset of jited_prog_insns */ + int count_offset; /* e.g. offset of jited_prog_len */ + int size_offset; /* > 0: offset of rec size, + * < 0: fix size of -size_offset + */ +}; + +static struct bpil_array_desc bpil_array_desc[] = { + [PERF_BPIL_JITED_INSNS] = { + offsetof(struct bpf_prog_info, jited_prog_insns), + offsetof(struct bpf_prog_info, jited_prog_len), + -1, + }, + [PERF_BPIL_XLATED_INSNS] = { + offsetof(struct bpf_prog_info, xlated_prog_insns), + offsetof(struct bpf_prog_info, xlated_prog_len), + -1, + }, + [PERF_BPIL_MAP_IDS] = { + offsetof(struct bpf_prog_info, map_ids), + offsetof(struct bpf_prog_info, nr_map_ids), + -(int)sizeof(__u32), + }, + [PERF_BPIL_JITED_KSYMS] = { + offsetof(struct bpf_prog_info, jited_ksyms), + offsetof(struct bpf_prog_info, nr_jited_ksyms), + -(int)sizeof(__u64), + }, + [PERF_BPIL_JITED_FUNC_LENS] = { + offsetof(struct bpf_prog_info, jited_func_lens), + offsetof(struct bpf_prog_info, nr_jited_func_lens), + -(int)sizeof(__u32), + }, + [PERF_BPIL_FUNC_INFO] = { + offsetof(struct bpf_prog_info, func_info), + offsetof(struct bpf_prog_info, nr_func_info), + offsetof(struct bpf_prog_info, func_info_rec_size), + }, + [PERF_BPIL_LINE_INFO] = { + offsetof(struct bpf_prog_info, line_info), + offsetof(struct bpf_prog_info, nr_line_info), + offsetof(struct bpf_prog_info, line_info_rec_size), + }, + [PERF_BPIL_JITED_LINE_INFO] = { + offsetof(struct bpf_prog_info, jited_line_info), + offsetof(struct bpf_prog_info, nr_jited_line_info), + offsetof(struct bpf_prog_info, jited_line_info_rec_size), + }, + [PERF_BPIL_PROG_TAGS] = { + offsetof(struct bpf_prog_info, prog_tags), + offsetof(struct bpf_prog_info, nr_prog_tags), + -(int)sizeof(__u8) * BPF_TAG_SIZE, + }, + +}; + +static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, + int offset) +{ + __u32 *array = (__u32 *)info; + + if (offset >= 0) + return array[offset / sizeof(__u32)]; + return -(int)offset; +} + +static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, + int offset) +{ + __u64 *array = (__u64 *)info; + + if (offset >= 0) + return array[offset / sizeof(__u64)]; + return -(int)offset; +} + +static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset, + __u32 val) +{ + __u32 *array = (__u32 *)info; + + if (offset >= 0) + array[offset / sizeof(__u32)] = val; +} + +static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset, + __u64 val) +{ + __u64 *array = (__u64 *)info; + + if (offset >= 0) + array[offset / sizeof(__u64)] = val; +} + +struct perf_bpil * +get_bpf_prog_info_linear(int fd, __u64 arrays) +{ + struct bpf_prog_info info = {}; + struct perf_bpil *info_linear; + __u32 info_len = sizeof(info); + __u32 data_len = 0; + int i, err; + void *ptr; + + if (arrays >> PERF_BPIL_LAST_ARRAY) + return ERR_PTR(-EINVAL); + + /* step 1: get array dimensions */ + err = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (err) { + pr_debug("can't get prog info: %s", strerror(errno)); + return ERR_PTR(-EFAULT); + } + + /* step 2: calculate total size of all arrays */ + for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { + bool include_array = (arrays & (1UL << i)) > 0; + struct bpil_array_desc *desc; + __u32 count, size; + + desc = bpil_array_desc + i; + + /* kernel is too old to support this field */ + if (info_len < desc->array_offset + sizeof(__u32) || + info_len < desc->count_offset + sizeof(__u32) || + (desc->size_offset > 0 && info_len < (__u32)desc->size_offset)) + include_array = false; + + if (!include_array) { + arrays &= ~(1UL << i); /* clear the bit */ + continue; + } + + count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + + data_len += count * size; + } + + /* step 3: allocate continuous memory */ + data_len = roundup(data_len, sizeof(__u64)); + info_linear = malloc(sizeof(struct perf_bpil) + data_len); + if (!info_linear) + return ERR_PTR(-ENOMEM); + + /* step 4: fill data to info_linear->info */ + info_linear->arrays = arrays; + memset(&info_linear->info, 0, sizeof(info)); + ptr = info_linear->data; + + for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { + struct bpil_array_desc *desc; + __u32 count, size; + + if ((arrays & (1UL << i)) == 0) + continue; + + desc = bpil_array_desc + i; + count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + bpf_prog_info_set_offset_u32(&info_linear->info, + desc->count_offset, count); + bpf_prog_info_set_offset_u32(&info_linear->info, + desc->size_offset, size); + bpf_prog_info_set_offset_u64(&info_linear->info, + desc->array_offset, + ptr_to_u64(ptr)); + ptr += count * size; + } + + /* step 5: call syscall again to get required arrays */ + err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len); + if (err) { + pr_debug("can't get prog info: %s", strerror(errno)); + free(info_linear); + return ERR_PTR(-EFAULT); + } + + /* step 6: verify the data */ + for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { + struct bpil_array_desc *desc; + __u32 v1, v2; + + if ((arrays & (1UL << i)) == 0) + continue; + + desc = bpil_array_desc + i; + v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + desc->count_offset); + if (v1 != v2) + pr_warning("%s: mismatch in element count\n", __func__); + + v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + desc->size_offset); + if (v1 != v2) + pr_warning("%s: mismatch in rec size\n", __func__); + } + + /* step 7: update info_len and data_len */ + info_linear->info_len = sizeof(struct bpf_prog_info); + info_linear->data_len = data_len; + + return info_linear; +} + +void bpil_addr_to_offs(struct perf_bpil *info_linear) +{ + int i; + + for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { + struct bpil_array_desc *desc; + __u64 addr, offs; + + if ((info_linear->arrays & (1UL << i)) == 0) + continue; + + desc = bpil_array_desc + i; + addr = bpf_prog_info_read_offset_u64(&info_linear->info, + desc->array_offset); + offs = addr - ptr_to_u64(info_linear->data); + bpf_prog_info_set_offset_u64(&info_linear->info, + desc->array_offset, offs); + } +} + +void bpil_offs_to_addr(struct perf_bpil *info_linear) +{ + int i; + + for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { + struct bpil_array_desc *desc; + __u64 addr, offs; + + if ((info_linear->arrays & (1UL << i)) == 0) + continue; + + desc = bpil_array_desc + i; + offs = bpf_prog_info_read_offset_u64(&info_linear->info, + desc->array_offset); + addr = offs + ptr_to_u64(info_linear->data); + bpf_prog_info_set_offset_u64(&info_linear->info, + desc->array_offset, addr); + } +} diff --git a/tools/perf/util/bpf-utils.h b/tools/perf/util/bpf-utils.h new file mode 100644 index 000000000000..86a5055cdfad --- /dev/null +++ b/tools/perf/util/bpf-utils.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __PERF_BPF_UTILS_H +#define __PERF_BPF_UTILS_H + +#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) + +#ifdef HAVE_LIBBPF_SUPPORT + +#include <bpf/libbpf.h> + +/* + * Get bpf_prog_info in continuous memory + * + * struct bpf_prog_info has multiple arrays. The user has option to choose + * arrays to fetch from kernel. The following APIs provide an uniform way to + * fetch these data. All arrays in bpf_prog_info are stored in a single + * continuous memory region. This makes it easy to store the info in a + * file. + * + * Before writing perf_bpil to files, it is necessary to + * translate pointers in bpf_prog_info to offsets. Helper functions + * bpil_addr_to_offs() and bpil_offs_to_addr() + * are introduced to switch between pointers and offsets. + * + * Examples: + * # To fetch map_ids and prog_tags: + * __u64 arrays = (1UL << PERF_BPIL_MAP_IDS) | + * (1UL << PERF_BPIL_PROG_TAGS); + * struct perf_bpil *info_linear = + * get_bpf_prog_info_linear(fd, arrays); + * + * # To save data in file + * bpil_addr_to_offs(info_linear); + * write(f, info_linear, sizeof(*info_linear) + info_linear->data_len); + * + * # To read data from file + * read(f, info_linear, <proper_size>); + * bpil_offs_to_addr(info_linear); + */ +enum perf_bpil_array_types { + PERF_BPIL_FIRST_ARRAY = 0, + PERF_BPIL_JITED_INSNS = 0, + PERF_BPIL_XLATED_INSNS, + PERF_BPIL_MAP_IDS, + PERF_BPIL_JITED_KSYMS, + PERF_BPIL_JITED_FUNC_LENS, + PERF_BPIL_FUNC_INFO, + PERF_BPIL_LINE_INFO, + PERF_BPIL_JITED_LINE_INFO, + PERF_BPIL_PROG_TAGS, + PERF_BPIL_LAST_ARRAY, +}; + +struct perf_bpil { + /* size of struct bpf_prog_info, when the tool is compiled */ + __u32 info_len; + /* total bytes allocated for data, round up to 8 bytes */ + __u32 data_len; + /* which arrays are included in data */ + __u64 arrays; + struct bpf_prog_info info; + __u8 data[]; +}; + +struct perf_bpil * +get_bpf_prog_info_linear(int fd, __u64 arrays); + +void +bpil_addr_to_offs(struct perf_bpil *info_linear); + +void +bpil_offs_to_addr(struct perf_bpil *info_linear); + +#endif /* HAVE_LIBBPF_SUPPORT */ +#endif /* __PERF_BPF_UTILS_H */ diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index ba0f20853651..3ce8d03cb7ec 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -13,6 +13,7 @@ #include <perf/bpf_perf.h> #include "bpf_counter.h" +#include "bpf-utils.h" #include "counts.h" #include "debug.h" #include "evsel.h" @@ -61,14 +62,13 @@ static int bpf_program_profiler__destroy(struct evsel *evsel) static char *bpf_target_prog_name(int tgt_fd) { - struct bpf_prog_info_linear *info_linear; struct bpf_func_info *func_info; + struct perf_bpil *info_linear; const struct btf_type *t; struct btf *btf = NULL; char *name = NULL; - info_linear = bpf_program__get_prog_info_linear( - tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); + info_linear = get_bpf_prog_info_linear(tgt_fd, 1UL << PERF_BPIL_FUNC_INFO); if (IS_ERR_OR_NULL(info_linear)) { pr_debug("failed to get info_linear for prog FD %d\n", tgt_fd); return NULL; @@ -127,9 +127,9 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id) skel->rodata->num_cpu = evsel__nr_cpus(evsel); - bpf_map__resize(skel->maps.events, evsel__nr_cpus(evsel)); - bpf_map__resize(skel->maps.fentry_readings, 1); - bpf_map__resize(skel->maps.accum_readings, 1); + bpf_map__set_max_entries(skel->maps.events, evsel__nr_cpus(evsel)); + bpf_map__set_max_entries(skel->maps.fentry_readings, 1); + bpf_map__set_max_entries(skel->maps.accum_readings, 1); prog_name = bpf_target_prog_name(prog_fd); if (!prog_name) { @@ -265,7 +265,7 @@ static int bpf_program_profiler__read(struct evsel *evsel) return 0; } -static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, +static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { struct bpf_prog_profiler_bpf *skel; @@ -277,7 +277,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, assert(skel != NULL); ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu, &fd, BPF_ANY); + &cpu_map_idx, &fd, BPF_ANY); if (ret) return ret; } @@ -307,6 +307,20 @@ static bool bperf_attr_map_compatible(int attr_map_fd) (map_info.value_size == sizeof(struct perf_event_attr_map_entry)); } +int __weak +bpf_map_create(enum bpf_map_type map_type, + const char *map_name __maybe_unused, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts __maybe_unused) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return bpf_create_map(map_type, key_size, value_size, max_entries, 0); +#pragma GCC diagnostic pop +} + static int bperf_lock_attr_map(struct target *target) { char path[PATH_MAX]; @@ -320,10 +334,10 @@ static int bperf_lock_attr_map(struct target *target) } if (access(path, F_OK)) { - map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, + map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(struct perf_event_attr), sizeof(struct perf_event_attr_map_entry), - ATTR_MAP_SIZE, 0); + ATTR_MAP_SIZE, NULL); if (map_fd < 0) return -1; @@ -399,7 +413,7 @@ static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, return -1; } - bpf_map__resize(skel->maps.events, libbpf_num_possible_cpus()); + bpf_map__set_max_entries(skel->maps.events, libbpf_num_possible_cpus()); err = bperf_leader_bpf__load(skel); if (err) { pr_err("Failed to load leader skeleton\n"); @@ -540,7 +554,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) filter_type == BPERF_FILTER_TGID) key = evsel->core.threads->map[i].pid; else if (filter_type == BPERF_FILTER_CPU) - key = evsel->core.cpus->map[i]; + key = evsel->core.cpus->map[i].cpu; else break; @@ -566,12 +580,12 @@ out: return err; } -static int bperf__install_pe(struct evsel *evsel, int cpu, int fd) +static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { struct bperf_leader_bpf *skel = evsel->leader_skel; return bpf_map_update_elem(bpf_map__fd(skel->maps.events), - &cpu, &fd, BPF_ANY); + &cpu_map_idx, &fd, BPF_ANY); } /* @@ -584,7 +598,7 @@ static int bperf_sync_counters(struct evsel *evsel) num_cpu = all_cpu_map->nr; for (i = 0; i < num_cpu; i++) { - cpu = all_cpu_map->map[i]; + cpu = all_cpu_map->map[i].cpu; bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); } return 0; @@ -605,15 +619,17 @@ static int bperf__disable(struct evsel *evsel) static int bperf__read(struct evsel *evsel) { struct bperf_follower_bpf *skel = evsel->follower_skel; - __u32 num_cpu_bpf = cpu__max_cpu(); + __u32 num_cpu_bpf = cpu__max_cpu().cpu; struct bpf_perf_event_value values[num_cpu_bpf]; int reading_map_fd, err = 0; - __u32 i, j, num_cpu; + __u32 i; + int j; bperf_sync_counters(evsel); reading_map_fd = bpf_map__fd(skel->maps.accum_readings); for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) { + struct perf_cpu entry; __u32 cpu; err = bpf_map_lookup_elem(reading_map_fd, &i, values); @@ -623,16 +639,15 @@ static int bperf__read(struct evsel *evsel) case BPERF_FILTER_GLOBAL: assert(i == 0); - num_cpu = all_cpu_map->nr; - for (j = 0; j < num_cpu; j++) { - cpu = all_cpu_map->map[j]; + perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) { + cpu = entry.cpu; perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter; perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled; perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running; } break; case BPERF_FILTER_CPU: - cpu = evsel->core.cpus->map[i]; + cpu = evsel->core.cpus->map[i].cpu; perf_counts(evsel->counts, i, 0)->val = values[cpu].counter; perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled; perf_counts(evsel->counts, i, 0)->run = values[cpu].running; @@ -757,11 +772,11 @@ static inline bool bpf_counter_skip(struct evsel *evsel) evsel->follower_skel == NULL; } -int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd) +int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) { if (bpf_counter_skip(evsel)) return 0; - return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd); + return evsel->bpf_counter_ops->install_pe(evsel, cpu_map_idx, fd); } int bpf_counter__load(struct evsel *evsel, struct target *target) diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h index 65ebaa6694fb..4dbf26408b69 100644 --- a/tools/perf/util/bpf_counter.h +++ b/tools/perf/util/bpf_counter.h @@ -16,7 +16,7 @@ typedef int (*bpf_counter_evsel_op)(struct evsel *evsel); typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel, struct target *target); typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel, - int cpu, + int cpu_map_idx, int fd); struct bpf_counter_ops { @@ -40,7 +40,7 @@ int bpf_counter__enable(struct evsel *evsel); int bpf_counter__disable(struct evsel *evsel); int bpf_counter__read(struct evsel *evsel); void bpf_counter__destroy(struct evsel *evsel); -int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); +int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd); #else /* HAVE_BPF_SKEL */ diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 89aa5e71db1a..ac60c08e8e2a 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -48,7 +48,7 @@ static int bperf_load_program(struct evlist *evlist) struct cgroup *cgrp, *leader_cgrp; __u32 i, cpu; __u32 nr_cpus = evlist->core.all_cpus->nr; - int total_cpus = cpu__max_cpu(); + int total_cpus = cpu__max_cpu().cpu; int map_size, map_fd; int prog_fd, err; @@ -65,14 +65,14 @@ static int bperf_load_program(struct evlist *evlist) /* we need one copy of events per cpu for reading */ map_size = total_cpus * evlist->core.nr_entries / nr_cgroups; - bpf_map__resize(skel->maps.events, map_size); - bpf_map__resize(skel->maps.cgrp_idx, nr_cgroups); + bpf_map__set_max_entries(skel->maps.events, map_size); + bpf_map__set_max_entries(skel->maps.cgrp_idx, nr_cgroups); /* previous result is saved in a per-cpu array */ map_size = evlist->core.nr_entries / nr_cgroups; - bpf_map__resize(skel->maps.prev_readings, map_size); + bpf_map__set_max_entries(skel->maps.prev_readings, map_size); /* cgroup result needs all events (per-cpu) */ map_size = evlist->core.nr_entries; - bpf_map__resize(skel->maps.cgrp_readings, map_size); + bpf_map__set_max_entries(skel->maps.cgrp_readings, map_size); set_max_rlimit(); @@ -125,7 +125,7 @@ static int bperf_load_program(struct evlist *evlist) for (cpu = 0; cpu < nr_cpus; cpu++) { int fd = FD(evsel, cpu); __u32 idx = evsel->core.idx * total_cpus + - evlist->core.all_cpus->map[cpu]; + evlist->core.all_cpus->map[cpu].cpu; err = bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY); @@ -212,7 +212,7 @@ static int bperf_cgrp__sync_counters(struct evlist *evlist) int prog_fd = bpf_program__fd(skel->progs.trigger_read); for (i = 0; i < nr_cpus; i++) { - cpu = evlist->core.all_cpus->map[i]; + cpu = evlist->core.all_cpus->map[i].cpu; bperf_trigger_reading(prog_fd, cpu); } @@ -245,7 +245,7 @@ static int bperf_cgrp__read(struct evsel *evsel) { struct evlist *evlist = evsel->evlist; int i, cpu, nr_cpus = evlist->core.all_cpus->nr; - int total_cpus = cpu__max_cpu(); + int total_cpus = cpu__max_cpu().cpu; struct perf_counts_values *counts; struct bpf_perf_event_value *values; int reading_map_fd, err = 0; @@ -266,13 +266,13 @@ static int bperf_cgrp__read(struct evsel *evsel) idx = evsel->core.idx; err = bpf_map_lookup_elem(reading_map_fd, &idx, values); if (err) { - pr_err("bpf map lookup falied: idx=%u, event=%s, cgrp=%s\n", + pr_err("bpf map lookup failed: idx=%u, event=%s, cgrp=%s\n", idx, evsel__name(evsel), evsel->cgrp->name); goto out; } for (i = 0; i < nr_cpus; i++) { - cpu = evlist->core.all_cpus->map[i]; + cpu = evlist->core.all_cpus->map[i].cpu; counts = perf_counts(evsel->counts, i, 0); counts->val = values[cpu].counter; diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c new file mode 100644 index 000000000000..d756cc66eef3 --- /dev/null +++ b/tools/perf/util/bpf_ftrace.c @@ -0,0 +1,152 @@ +#include <stdio.h> +#include <fcntl.h> +#include <stdint.h> +#include <stdlib.h> + +#include <linux/err.h> + +#include "util/ftrace.h" +#include "util/cpumap.h" +#include "util/thread_map.h" +#include "util/debug.h" +#include "util/evlist.h" +#include "util/bpf_counter.h" + +#include "util/bpf_skel/func_latency.skel.h" + +static struct func_latency_bpf *skel; + +int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) +{ + int fd, err; + int i, ncpus = 1, ntasks = 1; + struct filter_entry *func; + + if (!list_is_singular(&ftrace->filters)) { + pr_err("ERROR: %s target function(s).\n", + list_empty(&ftrace->filters) ? "No" : "Too many"); + return -1; + } + + func = list_first_entry(&ftrace->filters, struct filter_entry, list); + + skel = func_latency_bpf__open(); + if (!skel) { + pr_err("Failed to open func latency skeleton\n"); + return -1; + } + + /* don't need to set cpu filter for system-wide mode */ + if (ftrace->target.cpu_list) { + ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus); + bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus); + } + + if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) { + ntasks = perf_thread_map__nr(ftrace->evlist->core.threads); + bpf_map__set_max_entries(skel->maps.task_filter, ntasks); + } + + set_max_rlimit(); + + err = func_latency_bpf__load(skel); + if (err) { + pr_err("Failed to load func latency skeleton\n"); + goto out; + } + + if (ftrace->target.cpu_list) { + u32 cpu; + u8 val = 1; + + skel->bss->has_cpu = 1; + fd = bpf_map__fd(skel->maps.cpu_filter); + + for (i = 0; i < ncpus; i++) { + cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu; + bpf_map_update_elem(fd, &cpu, &val, BPF_ANY); + } + } + + if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) { + u32 pid; + u8 val = 1; + + skel->bss->has_task = 1; + fd = bpf_map__fd(skel->maps.task_filter); + + for (i = 0; i < ntasks; i++) { + pid = perf_thread_map__pid(ftrace->evlist->core.threads, i); + bpf_map_update_elem(fd, &pid, &val, BPF_ANY); + } + } + + skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin, + false, func->name); + if (IS_ERR(skel->links.func_begin)) { + pr_err("Failed to attach fentry program\n"); + err = PTR_ERR(skel->links.func_begin); + goto out; + } + + skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end, + true, func->name); + if (IS_ERR(skel->links.func_end)) { + pr_err("Failed to attach fexit program\n"); + err = PTR_ERR(skel->links.func_end); + goto out; + } + + /* XXX: we don't actually use this fd - just for poll() */ + return open("/dev/null", O_RDONLY); + +out: + return err; +} + +int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + skel->bss->enabled = 1; + return 0; +} + +int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + skel->bss->enabled = 0; + return 0; +} + +int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, + int buckets[]) +{ + int i, fd, err; + u32 idx; + u64 *hist; + int ncpus = cpu__max_cpu().cpu; + + fd = bpf_map__fd(skel->maps.latency); + + hist = calloc(ncpus, sizeof(*hist)); + if (hist == NULL) + return -ENOMEM; + + for (idx = 0; idx < NUM_BUCKET; idx++) { + err = bpf_map_lookup_elem(fd, &idx, hist); + if (err) { + buckets[idx] = 0; + continue; + } + + for (i = 0; i < ncpus; i++) + buckets[idx] += hist[i]; + } + + free(hist); + return 0; +} + +int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + func_latency_bpf__destroy(skel); + return 0; +} diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h deleted file mode 100644 index 186a5551ddb9..000000000000 --- a/tools/perf/util/bpf_skel/bperf.h +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -// Copyright (c) 2021 Facebook - -#ifndef __BPERF_STAT_H -#define __BPERF_STAT_H - -typedef struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); - __uint(max_entries, 1); -} reading_map; - -#endif /* __BPERF_STAT_H */ diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c index b8fa3cb2da23..f193998530d4 100644 --- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c @@ -1,14 +1,23 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" #include "bperf_u.h" -reading_map diff_readings SEC(".maps"); -reading_map accum_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} accum_readings SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH); diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c index 4f70d1459e86..e2a2d4cd7779 100644 --- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c @@ -1,10 +1,8 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -13,8 +11,19 @@ struct { __uint(map_flags, BPF_F_PRESERVE_ELEMS); } events SEC(".maps"); -reading_map prev_readings SEC(".maps"); -reading_map diff_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} prev_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); SEC("raw_tp/sched_switch") int BPF_PROG(on_switch) diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c index ab12b4c4ece2..97037d3b3d9f 100644 --- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c +++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2020 Facebook -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c new file mode 100644 index 000000000000..ea94187fe443 --- /dev/null +++ b/tools/perf/util/bpf_skel/func_latency.bpf.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2021 Google +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +// This should be in sync with "util/ftrace.h" +#define NUM_BUCKET 22 + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, 10000); +} functime SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} cpu_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} task_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, NUM_BUCKET); +} latency SEC(".maps"); + + +int enabled = 0; +int has_cpu = 0; +int has_task = 0; + +SEC("kprobe/func") +int BPF_PROG(func_begin) +{ + __u64 key, now; + + if (!enabled) + return 0; + + key = bpf_get_current_pid_tgid(); + + if (has_cpu) { + __u32 cpu = bpf_get_smp_processor_id(); + __u8 *ok; + + ok = bpf_map_lookup_elem(&cpu_filter, &cpu); + if (!ok) + return 0; + } + + if (has_task) { + __u32 pid = key & 0xffffffff; + __u8 *ok; + + ok = bpf_map_lookup_elem(&task_filter, &pid); + if (!ok) + return 0; + } + + now = bpf_ktime_get_ns(); + + // overwrite timestamp for nested functions + bpf_map_update_elem(&functime, &key, &now, BPF_ANY); + return 0; +} + +SEC("kretprobe/func") +int BPF_PROG(func_end) +{ + __u64 tid; + __u64 *start; + + if (!enabled) + return 0; + + tid = bpf_get_current_pid_tgid(); + + start = bpf_map_lookup_elem(&functime, &tid); + if (start) { + __s64 delta = bpf_ktime_get_ns() - *start; + __u32 key; + __u64 *hist; + + bpf_map_delete_elem(&functime, &tid); + + if (delta < 0) + return 0; + + // calculate index using delta in usec + for (key = 0; key < (NUM_BUCKET - 1); key++) { + if (delta < ((1000UL) << key)) + break; + } + + hist = bpf_map_lookup_elem(&latency, &key); + if (!hist) + return 0; + + *hist += 1; + } + + return 0; +} diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h index 2df8a45bd088..d3731a876b6c 100644 --- a/tools/perf/util/c++/clang-c.h +++ b/tools/perf/util/c++/clang-c.h @@ -12,8 +12,9 @@ extern "C" { extern void perf_clang__init(void); extern void perf_clang__cleanup(void); -extern int test__clang_to_IR(void); -extern int test__clang_to_obj(void); +struct test_suite; +extern int test__clang_to_IR(struct test_suite *test, int subtest); +extern int test__clang_to_obj(struct test_suite *test, int subtest); extern int perf_clang__compile_bpf(const char *filename, void **p_obj_buf, @@ -26,9 +27,6 @@ extern int perf_clang__compile_bpf(const char *filename, static inline void perf_clang__init(void) { } static inline void perf_clang__cleanup(void) { } -static inline int test__clang_to_IR(void) { return -1; } -static inline int test__clang_to_obj(void) { return -1;} - static inline int perf_clang__compile_bpf(const char *filename __maybe_unused, void **p_obj_buf __maybe_unused, diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp index 21b23605f78b..a4683ca53697 100644 --- a/tools/perf/util/c++/clang-test.cpp +++ b/tools/perf/util/c++/clang-test.cpp @@ -35,7 +35,8 @@ __test__clang_to_IR(void) } extern "C" { -int test__clang_to_IR(void) +int test__clang_to_IR(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { perf_clang_scope _scope; @@ -48,7 +49,8 @@ int test__clang_to_IR(void) return -1; } -int test__clang_to_obj(void) +int test__clang_to_obj(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { perf_clang_scope _scope; diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index c8885dfa3667..df7b18fb6b6e 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -43,8 +43,6 @@ createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, "-cc1", "-triple", "bpf-pc-linux", "-fsyntax-only", - "-ferror-limit", "19", - "-fmessage-length", "127", "-O2", "-nostdsysteminc", "-nobuiltininc", @@ -55,7 +53,11 @@ createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, "-x", "c"}; CCArgs.append(CFlags.begin(), CFlags.end()); - CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs); + CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs +#if CLANG_VERSION_MAJOR >= 11 + ,/*BinaryName=*/nullptr +#endif + ); FrontendOptions& Opts = CI->getFrontendOpts(); Opts.Inputs.clear(); @@ -151,13 +153,16 @@ getBPFObjectFromModule(llvm::Module *Module) legacy::PassManager PM; bool NotAdded; -#if CLANG_VERSION_MAJOR < 7 - NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, - TargetMachine::CGFT_ObjectFile); + NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream +#if CLANG_VERSION_MAJOR >= 7 + , /*DwoOut=*/nullptr +#endif +#if CLANG_VERSION_MAJOR < 10 + , TargetMachine::CGFT_ObjectFile #else - NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr, - TargetMachine::CGFT_ObjectFile); + , llvm::CGFT_ObjectFile #endif + ); if (NotAdded) { llvm::errs() << "TargetMachine can't emit a file of this type\n"; return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8e2777133bd9..131207b91d15 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1600,7 +1600,7 @@ void callchain_cursor_reset(struct callchain_cursor *cursor) map__zput(node->ms.map); } -void callchain_param_setup(u64 sample_type) +void callchain_param_setup(u64 sample_type, const char *arch) { if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) { if ((sample_type & PERF_SAMPLE_REGS_USER) && @@ -1612,6 +1612,18 @@ void callchain_param_setup(u64 sample_type) else callchain_param.record_mode = CALLCHAIN_FP; } + + /* + * It's necessary to use libunwind to reliably determine the caller of + * a leaf function on aarch64, as otherwise we cannot know whether to + * start from the LR or FP. + * + * Always starting from the LR can result in duplicate or entirely + * erroneous entries. Always skipping the LR and starting from the FP + * can result in missing entries. + */ + if (callchain_param.record_mode == CALLCHAIN_FP && !strcmp(arch, "arm64")) + dwarf_callchain_users = true; } static bool chain_match(struct callchain_list *base_chain, diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 5824134f983b..d95615daed73 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -280,6 +280,8 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused, } #endif +void arch__add_leaf_frame_record_opts(struct record_opts *opts); + char *callchain_list__sym_name(struct callchain_list *cl, char *bf, size_t bfsize, bool show_dso); char *callchain_node__scnprintf_value(struct callchain_node *node, @@ -298,7 +300,7 @@ int callchain_branch_counts(struct callchain_root *root, u64 *branch_count, u64 *predicted_count, u64 *abort_count, u64 *cycles_count); -void callchain_param_setup(u64 sample_type); +void callchain_param_setup(u64 sample_type, const char *arch); bool callchain_cnode_matched(struct callchain_node *base_cnode, struct callchain_node *pair_cnode); diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c index 582f3aeaf5e4..7a447d918458 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -4,6 +4,7 @@ #include <string.h> #include "evsel.h" #include "counts.h" +#include <perf/threadmap.h> #include <linux/zalloc.h> struct perf_counts *perf_counts__new(int ncpus, int nthreads) @@ -55,9 +56,12 @@ void evsel__reset_counts(struct evsel *evsel) perf_counts__reset(evsel->counts); } -int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads) +int evsel__alloc_counts(struct evsel *evsel) { - evsel->counts = perf_counts__new(ncpus, nthreads); + struct perf_cpu_map *cpus = evsel__cpus(evsel); + int nthreads = perf_thread_map__nr(evsel->core.threads); + + evsel->counts = perf_counts__new(perf_cpu_map__nr(cpus), nthreads); return evsel->counts != NULL ? 0 : -ENOMEM; } diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h index 7ff36bf6d644..5de275194f2b 100644 --- a/tools/perf/util/counts.h +++ b/tools/perf/util/counts.h @@ -18,21 +18,21 @@ struct perf_counts { static inline struct perf_counts_values* -perf_counts(struct perf_counts *counts, int cpu, int thread) +perf_counts(struct perf_counts *counts, int cpu_map_idx, int thread) { - return xyarray__entry(counts->values, cpu, thread); + return xyarray__entry(counts->values, cpu_map_idx, thread); } static inline bool -perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread) +perf_counts__is_loaded(struct perf_counts *counts, int cpu_map_idx, int thread) { - return *((bool *) xyarray__entry(counts->loaded, cpu, thread)); + return *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread)); } static inline void -perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded) +perf_counts__set_loaded(struct perf_counts *counts, int cpu_map_idx, int thread, bool loaded) { - *((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded; + *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread)) = loaded; } struct perf_counts *perf_counts__new(int ncpus, int nthreads); @@ -40,7 +40,7 @@ void perf_counts__delete(struct perf_counts *counts); void perf_counts__reset(struct perf_counts *counts); void evsel__reset_counts(struct evsel *evsel); -int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads); +int evsel__alloc_counts(struct evsel *evsel); void evsel__free_counts(struct evsel *evsel); #endif /* __PERF_COUNTS_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 87d3eca9b872..12b2243222b0 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -13,9 +13,13 @@ #include <linux/ctype.h> #include <linux/zalloc.h> -static int max_cpu_num; -static int max_present_cpu_num; +static struct perf_cpu max_cpu_num; +static struct perf_cpu max_present_cpu_num; static int max_node_num; +/** + * The numa node X as read from /sys/devices/system/node/nodeX indexed by the + * CPU number. + */ static int *cpunode_map; static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) @@ -33,9 +37,9 @@ static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) * otherwise it would become 65535. */ if (cpus->cpu[i] == (u16) -1) - map->map[i] = -1; + map->map[i].cpu = -1; else - map->map[i] = (int) cpus->cpu[i]; + map->map[i].cpu = (int) cpus->cpu[i]; } } @@ -54,7 +58,7 @@ static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map int cpu, i = 0; for_each_set_bit(cpu, mask->mask, nbits) - map->map[i++] = cpu; + map->map[i++].cpu = cpu; } return map; @@ -87,7 +91,7 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr) cpus->nr = nr; for (i = 0; i < nr; i++) - cpus->map[i] = -1; + cpus->map[i].cpu = -1; refcount_set(&cpus->refcnt, 1); } @@ -104,7 +108,7 @@ struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr) cpus->nr = nr; for (i = 0; i < nr; i++) - cpus->map[i] = cpu_map__empty_aggr_cpu_id(); + cpus->map[i] = aggr_cpu_id__empty(); refcount_set(&cpus->refcnt, 1); } @@ -122,28 +126,21 @@ static int cpu__get_topology_int(int cpu, const char *name, int *value) return sysfs__read_int(path, value); } -int cpu_map__get_socket_id(int cpu) +int cpu__get_socket_id(struct perf_cpu cpu) { - int value, ret = cpu__get_topology_int(cpu, "physical_package_id", &value); + int value, ret = cpu__get_topology_int(cpu.cpu, "physical_package_id", &value); return ret ?: value; } -struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, - void *data __maybe_unused) +struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data __maybe_unused) { - int cpu; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id = aggr_cpu_id__empty(); - if (idx > map->nr) - return id; - - cpu = map->map[idx]; - - id.socket = cpu_map__get_socket_id(cpu); + id.socket = cpu__get_socket_id(cpu); return id; } -static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) +static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer) { struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer; struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer; @@ -160,57 +157,64 @@ static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) return a->thread - b->thread; } -int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), - void *data) +struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, + aggr_cpu_id_get_t get_id, + void *data) { - int nr = cpus->nr; - struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr); - int cpu, s2; - struct aggr_cpu_id s1; + int idx; + struct perf_cpu cpu; + struct cpu_aggr_map *c = cpu_aggr_map__empty_new(cpus->nr); if (!c) - return -1; + return NULL; /* Reset size as it may only be partially filled */ c->nr = 0; - for (cpu = 0; cpu < nr; cpu++) { - s1 = f(cpus, cpu, data); - for (s2 = 0; s2 < c->nr; s2++) { - if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2])) + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + bool duplicate = false; + struct aggr_cpu_id cpu_id = get_id(cpu, data); + + for (int j = 0; j < c->nr; j++) { + if (aggr_cpu_id__equal(&cpu_id, &c->map[j])) { + duplicate = true; break; + } } - if (s2 == c->nr) { - c->map[c->nr] = s1; + if (!duplicate) { + c->map[c->nr] = cpu_id; c->nr++; } } + /* Trim. */ + if (c->nr != cpus->nr) { + struct cpu_aggr_map *trimmed_c = + realloc(c, + sizeof(struct cpu_aggr_map) + sizeof(struct aggr_cpu_id) * c->nr); + + if (trimmed_c) + c = trimmed_c; + } /* ensure we process id in increasing order */ - qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id); + qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), aggr_cpu_id__cmp); + + return c; - *res = c; - return 0; } -int cpu_map__get_die_id(int cpu) +int cpu__get_die_id(struct perf_cpu cpu) { - int value, ret = cpu__get_topology_int(cpu, "die_id", &value); + int value, ret = cpu__get_topology_int(cpu.cpu, "die_id", &value); return ret ?: value; } -struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) +struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data) { - int cpu, die; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id; + int die; - if (idx > map->nr) - return id; - - cpu = map->map[idx]; - - die = cpu_map__get_die_id(cpu); + die = cpu__get_die_id(cpu); /* There is no die_id on legacy system. */ if (die == -1) die = 0; @@ -220,79 +224,59 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat * with the socket ID and then add die to * make a unique ID. */ - id = cpu_map__get_socket(map, idx, data); - if (cpu_map__aggr_cpu_id_is_empty(id)) + id = aggr_cpu_id__socket(cpu, data); + if (aggr_cpu_id__is_empty(&id)) return id; id.die = die; return id; } -int cpu_map__get_core_id(int cpu) +int cpu__get_core_id(struct perf_cpu cpu) { - int value, ret = cpu__get_topology_int(cpu, "core_id", &value); + int value, ret = cpu__get_topology_int(cpu.cpu, "core_id", &value); return ret ?: value; } -int cpu_map__get_node_id(int cpu) -{ - return cpu__get_node(cpu); -} - -struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) +struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data) { - int cpu; - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - - if (idx > map->nr) - return id; + struct aggr_cpu_id id; + int core = cpu__get_core_id(cpu); - cpu = map->map[idx]; - - cpu = cpu_map__get_core_id(cpu); - - /* cpu_map__get_die returns a struct with socket and die set*/ - id = cpu_map__get_die(map, idx, data); - if (cpu_map__aggr_cpu_id_is_empty(id)) + /* aggr_cpu_id__die returns a struct with socket and die set. */ + id = aggr_cpu_id__die(cpu, data); + if (aggr_cpu_id__is_empty(&id)) return id; /* * core_id is relative to socket and die, we need a global id. * So we combine the result from cpu_map__get_die with the core id */ - id.core = cpu; + id.core = core; return id; + } -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data) { - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + struct aggr_cpu_id id; - if (idx < 0 || idx >= map->nr) + /* aggr_cpu_id__core returns a struct with socket, die and core set. */ + id = aggr_cpu_id__core(cpu, data); + if (aggr_cpu_id__is_empty(&id)) return id; - id.node = cpu_map__get_node_id(map->map[idx]); + id.cpu = cpu; return id; -} -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) -{ - return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); } -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep) +struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data __maybe_unused) { - return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); -} - -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep) -{ - return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); -} + struct aggr_cpu_id id = aggr_cpu_id__empty(); -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap) -{ - return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); + id.node = cpu__get_node(cpu); + return id; } /* setup simple routines to easily access node numbers given a cpu number */ @@ -335,8 +319,8 @@ static void set_max_cpu_num(void) int ret = -1; /* set up default */ - max_cpu_num = 4096; - max_present_cpu_num = 4096; + max_cpu_num.cpu = 4096; + max_present_cpu_num.cpu = 4096; mnt = sysfs__mountpoint(); if (!mnt) @@ -349,7 +333,7 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_cpu_num); + ret = get_max_num(path, &max_cpu_num.cpu); if (ret) goto out; @@ -360,11 +344,11 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_present_cpu_num); + ret = get_max_num(path, &max_present_cpu_num.cpu); out: if (ret) - pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num); + pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu); } /* Determine highest possible node in the system for sparse allocation */ @@ -403,31 +387,31 @@ int cpu__max_node(void) return max_node_num; } -int cpu__max_cpu(void) +struct perf_cpu cpu__max_cpu(void) { - if (unlikely(!max_cpu_num)) + if (unlikely(!max_cpu_num.cpu)) set_max_cpu_num(); return max_cpu_num; } -int cpu__max_present_cpu(void) +struct perf_cpu cpu__max_present_cpu(void) { - if (unlikely(!max_present_cpu_num)) + if (unlikely(!max_present_cpu_num.cpu)) set_max_cpu_num(); return max_present_cpu_num; } -int cpu__get_node(int cpu) +int cpu__get_node(struct perf_cpu cpu) { if (unlikely(cpunode_map == NULL)) { pr_debug("cpu_map not initialized\n"); return -1; } - return cpunode_map[cpu]; + return cpunode_map[cpu.cpu]; } static int init_cpunode_map(void) @@ -437,13 +421,13 @@ static int init_cpunode_map(void) set_max_cpu_num(); set_max_node_num(); - cpunode_map = calloc(max_cpu_num, sizeof(int)); + cpunode_map = calloc(max_cpu_num.cpu, sizeof(int)); if (!cpunode_map) { pr_err("%s: calloc failed\n", __func__); return -1; } - for (i = 0; i < max_cpu_num; i++) + for (i = 0; i < max_cpu_num.cpu; i++) cpunode_map[i] = -1; return 0; @@ -502,47 +486,39 @@ int cpu__setup_cpunode_map(void) return 0; } -bool cpu_map__has(struct perf_cpu_map *cpus, int cpu) -{ - return perf_cpu_map__idx(cpus, cpu) != -1; -} - -int cpu_map__cpu(struct perf_cpu_map *cpus, int idx) -{ - return cpus->map[idx]; -} - size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) { - int i, cpu, start = -1; + int i, start = -1; bool first = true; size_t ret = 0; #define COMMA first ? "" : "," for (i = 0; i < map->nr + 1; i++) { + struct perf_cpu cpu = { .cpu = INT_MAX }; bool last = i == map->nr; - cpu = last ? INT_MAX : map->map[i]; + if (!last) + cpu = map->map[i]; if (start == -1) { start = i; if (last) { ret += snprintf(buf + ret, size - ret, "%s%d", COMMA, - map->map[i]); + map->map[i].cpu); } - } else if (((i - start) != (cpu - map->map[start])) || last) { + } else if (((i - start) != (cpu.cpu - map->map[start].cpu)) || last) { int end = i - 1; if (start == end) { ret += snprintf(buf + ret, size - ret, "%s%d", COMMA, - map->map[start]); + map->map[start].cpu); } else { ret += snprintf(buf + ret, size - ret, "%s%d-%d", COMMA, - map->map[start], map->map[end]); + map->map[start].cpu, map->map[end].cpu); } first = false; start = i; @@ -569,23 +545,23 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) int i, cpu; char *ptr = buf; unsigned char *bitmap; - int last_cpu = cpu_map__cpu(map, map->nr - 1); + struct perf_cpu last_cpu = perf_cpu_map__cpu(map, map->nr - 1); if (buf == NULL) return 0; - bitmap = zalloc(last_cpu / 8 + 1); + bitmap = zalloc(last_cpu.cpu / 8 + 1); if (bitmap == NULL) { buf[0] = '\0'; return 0; } for (i = 0; i < map->nr; i++) { - cpu = cpu_map__cpu(map, i); + cpu = perf_cpu_map__cpu(map, i).cpu; bitmap[cpu / 8] |= 1 << (cpu % 8); } - for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) { + for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) { unsigned char bits = bitmap[cpu / 8]; if (cpu % 8) @@ -614,32 +590,35 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ return online; } -bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b) +bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b) { - return a.thread == b.thread && - a.node == b.node && - a.socket == b.socket && - a.die == b.die && - a.core == b.core; + return a->thread == b->thread && + a->node == b->node && + a->socket == b->socket && + a->die == b->die && + a->core == b->core && + a->cpu.cpu == b->cpu.cpu; } -bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a) +bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a) { - return a.thread == -1 && - a.node == -1 && - a.socket == -1 && - a.die == -1 && - a.core == -1; + return a->thread == -1 && + a->node == -1 && + a->socket == -1 && + a->die == -1 && + a->core == -1 && + a->cpu.cpu == -1; } -struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void) +struct aggr_cpu_id aggr_cpu_id__empty(void) { struct aggr_cpu_id ret = { .thread = -1, .node = -1, .socket = -1, .die = -1, - .core = -1 + .core = -1, + .cpu = (struct perf_cpu){ .cpu = -1 }, }; return ret; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index a27eeaf086e8..703ae6d3386e 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -2,71 +2,134 @@ #ifndef __PERF_CPUMAP_H #define __PERF_CPUMAP_H -#include <stdio.h> #include <stdbool.h> +#include <stdio.h> #include <internal/cpumap.h> #include <perf/cpumap.h> +/** Identify where counts are aggregated, -1 implies not to aggregate. */ struct aggr_cpu_id { + /** A value in the range 0 to number of threads. */ int thread; + /** The numa node X as read from /sys/devices/system/node/nodeX. */ int node; + /** + * The socket number as read from + * /sys/devices/system/cpu/cpuX/topology/physical_package_id. + */ int socket; + /** The die id as read from /sys/devices/system/cpu/cpuX/topology/die_id. */ int die; + /** The core id as read from /sys/devices/system/cpu/cpuX/topology/core_id. */ int core; + /** CPU aggregation, note there is one CPU for each SMT thread. */ + struct perf_cpu cpu; }; +/** A collection of aggr_cpu_id values, the "built" version is sorted and uniqued. */ struct cpu_aggr_map { refcount_t refcnt; + /** Number of valid entries. */ int nr; + /** The entries. */ struct aggr_cpu_id map[]; }; struct perf_record_cpu_map_data; struct perf_cpu_map *perf_cpu_map__empty_new(int nr); -struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr); struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data); size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); -int cpu_map__get_socket_id(int cpu); -struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__get_die_id(int cpu); -struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__get_core_id(int cpu); -struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__get_node_id(int cpu); -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp); -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep); -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep); -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep); const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ -static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) +int cpu__setup_cpunode_map(void); + +int cpu__max_node(void); +struct perf_cpu cpu__max_cpu(void); +struct perf_cpu cpu__max_present_cpu(void); + +/** + * cpu_map__is_dummy - Events associated with a pid, rather than a CPU, use a single dummy map with an entry of -1. + */ +static inline bool cpu_map__is_dummy(struct perf_cpu_map *cpus) { - if (!sock || s > sock->nr || s < 0) - return 0; - return sock->map[s]; + return perf_cpu_map__nr(cpus) == 1 && perf_cpu_map__cpu(cpus, 0).cpu == -1; } -int cpu__setup_cpunode_map(void); +/** + * cpu__get_node - Returns the numa node X as read from + * /sys/devices/system/node/nodeX for the given CPU. + */ +int cpu__get_node(struct perf_cpu cpu); +/** + * cpu__get_socket_id - Returns the socket number as read from + * /sys/devices/system/cpu/cpuX/topology/physical_package_id for the given CPU. + */ +int cpu__get_socket_id(struct perf_cpu cpu); +/** + * cpu__get_die_id - Returns the die id as read from + * /sys/devices/system/cpu/cpuX/topology/die_id for the given CPU. + */ +int cpu__get_die_id(struct perf_cpu cpu); +/** + * cpu__get_core_id - Returns the core id as read from + * /sys/devices/system/cpu/cpuX/topology/core_id for the given CPU. + */ +int cpu__get_core_id(struct perf_cpu cpu); -int cpu__max_node(void); -int cpu__max_cpu(void); -int cpu__max_present_cpu(void); -int cpu__get_node(int cpu); +/** + * cpu_aggr_map__empty_new - Create a cpu_aggr_map of size nr with every entry + * being empty. + */ +struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr); + +typedef struct aggr_cpu_id (*aggr_cpu_id_get_t)(struct perf_cpu cpu, void *data); + +/** + * cpu_aggr_map__new - Create a cpu_aggr_map with an aggr_cpu_id for each cpu in + * cpus. The aggr_cpu_id is created with 'get_id' that may have a data value + * passed to it. The cpu_aggr_map is sorted with duplicate values removed. + */ +struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, + aggr_cpu_id_get_t get_id, + void *data); -int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), - void *data); +bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b); +bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a); +struct aggr_cpu_id aggr_cpu_id__empty(void); -int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); -bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); -bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b); -bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a); -struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void); +/** + * aggr_cpu_id__socket - Create an aggr_cpu_id with the socket populated with + * the socket for cpu. The function signature is compatible with + * aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__die - Create an aggr_cpu_id with the die and socket populated + * with the die and socket for cpu. The function signature is compatible with + * aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__core - Create an aggr_cpu_id with the core, die and socket + * populated with the core, die and socket for cpu. The function signature is + * compatible with aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__core - Create an aggr_cpu_id with the cpu, core, die and socket + * populated with the cpu, core, die and socket for cpu. The function signature + * is compatible with aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data); +/** + * aggr_cpu_id__node - Create an aggr_cpu_id with the numa node populated for + * cpu. The function signature is compatible with aggr_cpu_id_get_t. + */ +struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data); #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index ec77e2a7b3ca..d275d843c155 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -14,14 +14,16 @@ #include "env.h" #include "pmu-hybrid.h" -#define CORE_SIB_FMT \ +#define PACKAGE_CPUS_FMT \ + "%s/devices/system/cpu/cpu%d/topology/package_cpus_list" +#define PACKAGE_CPUS_FMT_OLD \ "%s/devices/system/cpu/cpu%d/topology/core_siblings_list" -#define DIE_SIB_FMT \ +#define DIE_CPUS_FMT \ "%s/devices/system/cpu/cpu%d/topology/die_cpus_list" -#define THRD_SIB_FMT \ - "%s/devices/system/cpu/cpu%d/topology/thread_siblings_list" -#define THRD_SIB_FMT_NEW \ +#define CORE_CPUS_FMT \ "%s/devices/system/cpu/cpu%d/topology/core_cpus_list" +#define CORE_CPUS_FMT_OLD \ + "%s/devices/system/cpu/cpu%d/topology/thread_siblings_list" #define NODE_ONLINE_FMT \ "%s/devices/system/node/online" #define NODE_MEMINFO_FMT \ @@ -39,8 +41,12 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu) u32 i = 0; int ret = -1; - scnprintf(filename, MAXPATHLEN, CORE_SIB_FMT, + scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT, sysfs__mountpoint(), cpu); + if (access(filename, F_OK) == -1) { + scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT_OLD, + sysfs__mountpoint(), cpu); + } fp = fopen(filename, "r"); if (!fp) goto try_dies; @@ -54,23 +60,23 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu) if (p) *p = '\0'; - for (i = 0; i < tp->core_sib; i++) { - if (!strcmp(buf, tp->core_siblings[i])) + for (i = 0; i < tp->package_cpus_lists; i++) { + if (!strcmp(buf, tp->package_cpus_list[i])) break; } - if (i == tp->core_sib) { - tp->core_siblings[i] = buf; - tp->core_sib++; + if (i == tp->package_cpus_lists) { + tp->package_cpus_list[i] = buf; + tp->package_cpus_lists++; buf = NULL; len = 0; } ret = 0; try_dies: - if (!tp->die_siblings) + if (!tp->die_cpus_list) goto try_threads; - scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT, + scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT, sysfs__mountpoint(), cpu); fp = fopen(filename, "r"); if (!fp) @@ -85,23 +91,23 @@ try_dies: if (p) *p = '\0'; - for (i = 0; i < tp->die_sib; i++) { - if (!strcmp(buf, tp->die_siblings[i])) + for (i = 0; i < tp->die_cpus_lists; i++) { + if (!strcmp(buf, tp->die_cpus_list[i])) break; } - if (i == tp->die_sib) { - tp->die_siblings[i] = buf; - tp->die_sib++; + if (i == tp->die_cpus_lists) { + tp->die_cpus_list[i] = buf; + tp->die_cpus_lists++; buf = NULL; len = 0; } ret = 0; try_threads: - scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT_NEW, + scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT, sysfs__mountpoint(), cpu); if (access(filename, F_OK) == -1) { - scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT, + scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT_OLD, sysfs__mountpoint(), cpu); } fp = fopen(filename, "r"); @@ -115,13 +121,13 @@ try_threads: if (p) *p = '\0'; - for (i = 0; i < tp->thread_sib; i++) { - if (!strcmp(buf, tp->thread_siblings[i])) + for (i = 0; i < tp->core_cpus_lists; i++) { + if (!strcmp(buf, tp->core_cpus_list[i])) break; } - if (i == tp->thread_sib) { - tp->thread_siblings[i] = buf; - tp->thread_sib++; + if (i == tp->core_cpus_lists) { + tp->core_cpus_list[i] = buf; + tp->core_cpus_lists++; buf = NULL; } ret = 0; @@ -139,16 +145,14 @@ void cpu_topology__delete(struct cpu_topology *tp) if (!tp) return; - for (i = 0 ; i < tp->core_sib; i++) - zfree(&tp->core_siblings[i]); + for (i = 0 ; i < tp->package_cpus_lists; i++) + zfree(&tp->package_cpus_list[i]); - if (tp->die_sib) { - for (i = 0 ; i < tp->die_sib; i++) - zfree(&tp->die_siblings[i]); - } + for (i = 0 ; i < tp->die_cpus_lists; i++) + zfree(&tp->die_cpus_list[i]); - for (i = 0 ; i < tp->thread_sib; i++) - zfree(&tp->thread_siblings[i]); + for (i = 0 ; i < tp->core_cpus_lists; i++) + zfree(&tp->core_cpus_list[i]); free(tp); } @@ -161,10 +165,11 @@ static bool has_die_topology(void) if (uname(&uts) < 0) return false; - if (strncmp(uts.machine, "x86_64", 6)) + if (strncmp(uts.machine, "x86_64", 6) && + strncmp(uts.machine, "s390x", 5)) return false; - scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT, + scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT, sysfs__mountpoint(), 0); if (access(filename, F_OK) == -1) return false; @@ -183,7 +188,7 @@ struct cpu_topology *cpu_topology__new(void) struct perf_cpu_map *map; bool has_die = has_die_topology(); - ncpus = cpu__max_present_cpu(); + ncpus = cpu__max_present_cpu().cpu; /* build online CPU map */ map = perf_cpu_map__new(NULL); @@ -205,16 +210,16 @@ struct cpu_topology *cpu_topology__new(void) tp = addr; addr += sizeof(*tp); - tp->core_siblings = addr; + tp->package_cpus_list = addr; addr += sz; if (has_die) { - tp->die_siblings = addr; + tp->die_cpus_list = addr; addr += sz; } - tp->thread_siblings = addr; + tp->core_cpus_list = addr; for (i = 0; i < nr; i++) { - if (!cpu_map__has(map, i)) + if (!perf_cpu_map__has(map, (struct perf_cpu){ .cpu = i })) continue; ret = build_cpu_topology(tp, i); @@ -320,7 +325,7 @@ struct numa_topology *numa_topology__new(void) if (!node_map) goto out; - nr = (u32) node_map->nr; + nr = (u32) perf_cpu_map__nr(node_map); tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0])*nr); if (!tp) @@ -329,7 +334,7 @@ struct numa_topology *numa_topology__new(void) tp->nr = nr; for (i = 0; i < nr; i++) { - if (load_numa_node(&tp->nodes[i], node_map->map[i])) { + if (load_numa_node(&tp->nodes[i], perf_cpu_map__cpu(node_map, i).cpu)) { numa_topology__delete(tp); tp = NULL; break; diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h index d9af97177068..854e18f9041e 100644 --- a/tools/perf/util/cputopo.h +++ b/tools/perf/util/cputopo.h @@ -5,12 +5,33 @@ #include <linux/types.h> struct cpu_topology { - u32 core_sib; - u32 die_sib; - u32 thread_sib; - char **core_siblings; - char **die_siblings; - char **thread_siblings; + /* The number of unique package_cpus_lists below. */ + u32 package_cpus_lists; + /* The number of unique die_cpu_lists below. */ + u32 die_cpus_lists; + /* The number of unique core_cpu_lists below. */ + u32 core_cpus_lists; + /* + * An array of strings where each string is unique and read from + * /sys/devices/system/cpu/cpuX/topology/package_cpus_list. From the ABI + * each of these is a human-readable list of CPUs sharing the same + * physical_package_id. The format is like 0-3, 8-11, 14,17. + */ + const char **package_cpus_list; + /* + * An array of string where each string is unique and from + * /sys/devices/system/cpu/cpuX/topology/die_cpus_list. From the ABI + * each of these is a human-readable list of CPUs within the same die. + * The format is like 0-3, 8-11, 14,17. + */ + const char **die_cpus_list; + /* + * An array of string where each string is unique and from + * /sys/devices/system/cpu/cpuX/topology/core_cpus_list. From the ABI + * each of these is a human-readable list of CPUs within the same + * core. The format is like 0-3, 8-11, 14,17. + */ + const char **core_cpus_list; }; struct numa_topology_node { diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index f323adb1af85..4f672f7d008c 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -537,7 +537,7 @@ static void cs_etm__dump_event(struct cs_etm_queue *etmq, fprintf(stdout, "\n"); color_fprintf(stdout, color, - ". ... CoreSight %s Trace data: size %zu bytes\n", + ". ... CoreSight %s Trace data: size %#zx bytes\n", cs_etm_decoder__get_name(etmq->decoder), buffer->size); do { diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index aa862a26d95c..9e0aee276df8 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -318,6 +318,8 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, offset = tmp_val; len = offset >> 16; offset &= 0xffff; + if (flags & TEP_FIELD_IS_RELATIVE) + offset += fmtf->offset + fmtf->size; } if (flags & TEP_FIELD_IS_ARRAY) { @@ -1437,7 +1439,7 @@ static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex) bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL)) goto err; -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_BIG_ENDIAN); #else bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_LITTLE_ENDIAN); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 2c06abf6dcd2..65e6c22f38e4 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -179,7 +179,7 @@ static int trace_event_printer(enum binary_printer_ops op, break; case BINARY_PRINT_CHAR_DATA: printed += color_fprintf(fp, color, "%c", - isprint(ch) ? ch : '.'); + isprint(ch) && isascii(ch) ? ch : '.'); break; case BINARY_PRINT_CHAR_PAD: printed += color_fprintf(fp, color, " "); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 9ed9a5676d35..9cc8a1772b4b 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -14,6 +14,7 @@ #ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> #include "bpf-event.h" +#include "bpf-utils.h" #endif #include "compress.h" #include "env.h" diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 83723ba11dc8..011da3924fc1 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -193,7 +193,7 @@ struct dso { int fd; int status; u32 status_seen; - size_t file_size; + u64 file_size; struct list_head open_entry; u64 debug_frame_offset; u64 eh_frame_hdr_offset; diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index cf773f0dec38..579e44c59914 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -16,6 +16,7 @@ struct perf_env perf_env; #ifdef HAVE_LIBBPF_SUPPORT #include "bpf-event.h" +#include "bpf-utils.h" #include <bpf/libbpf.h> void perf_env__insert_bpf_prog_info(struct perf_env *env, @@ -74,12 +75,13 @@ out: return node; } -void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) +bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) { struct rb_node *parent = NULL; __u32 btf_id = btf_node->id; struct btf_node *node; struct rb_node **p; + bool ret = true; down_write(&env->bpf_progs.lock); p = &env->bpf_progs.btfs.rb_node; @@ -93,6 +95,7 @@ void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) p = &(*p)->rb_right; } else { pr_debug("duplicated btf %u\n", btf_id); + ret = false; goto out; } } @@ -102,6 +105,7 @@ void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) env->bpf_progs.btfs_cnt++; out: up_write(&env->bpf_progs.lock); + return ret; } struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) @@ -281,13 +285,13 @@ out_enomem: int perf_env__read_cpu_topology_map(struct perf_env *env) { - int cpu, nr_cpus; + int idx, nr_cpus; if (env->cpu != NULL) return 0; if (env->nr_cpus_avail == 0) - env->nr_cpus_avail = cpu__max_present_cpu(); + env->nr_cpus_avail = cpu__max_present_cpu().cpu; nr_cpus = env->nr_cpus_avail; if (nr_cpus == -1) @@ -297,10 +301,12 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) if (env->cpu == NULL) return -ENOMEM; - for (cpu = 0; cpu < nr_cpus; ++cpu) { - env->cpu[cpu].core_id = cpu_map__get_core_id(cpu); - env->cpu[cpu].socket_id = cpu_map__get_socket_id(cpu); - env->cpu[cpu].die_id = cpu_map__get_die_id(cpu); + for (idx = 0; idx < nr_cpus; ++idx) { + struct perf_cpu cpu = { .cpu = idx }; + + env->cpu[idx].core_id = cpu__get_core_id(cpu); + env->cpu[idx].socket_id = cpu__get_socket_id(cpu); + env->cpu[idx].die_id = cpu__get_die_id(cpu); } env->nr_cpus_avail = nr_cpus; @@ -377,7 +383,7 @@ static int perf_env__read_arch(struct perf_env *env) static int perf_env__read_nr_cpus_avail(struct perf_env *env) { if (env->nr_cpus_avail == 0) - env->nr_cpus_avail = cpu__max_present_cpu(); + env->nr_cpus_avail = cpu__max_present_cpu().cpu; return env->nr_cpus_avail ? 0 : -ENOENT; } @@ -483,7 +489,7 @@ const char *perf_env__pmu_mappings(struct perf_env *env) return env->pmu_mappings; } -int perf_env__numa_node(struct perf_env *env, int cpu) +int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu) { if (!env->nr_numa_map) { struct numa_node *nn; @@ -491,7 +497,7 @@ int perf_env__numa_node(struct perf_env *env, int cpu) for (i = 0; i < env->nr_numa_nodes; i++) { nn = &env->numa_nodes[i]; - nr = max(nr, perf_cpu_map__max(nn->map)); + nr = max(nr, perf_cpu_map__max(nn->map).cpu); } nr++; @@ -510,13 +516,14 @@ int perf_env__numa_node(struct perf_env *env, int cpu) env->nr_numa_map = nr; for (i = 0; i < env->nr_numa_nodes; i++) { - int tmp, j; + struct perf_cpu tmp; + int j; nn = &env->numa_nodes[i]; - perf_cpu_map__for_each_cpu(j, tmp, nn->map) - env->numa_map[j] = i; + perf_cpu_map__for_each_cpu(tmp, j, nn->map) + env->numa_map[tmp.cpu] = i; } } - return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1; + return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1; } diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 1383876f72b3..a3541f98e1fc 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/rbtree.h> +#include "cpumap.h" #include "rwsem.h" struct perf_cpu_map; @@ -167,8 +168,8 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); -void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); +bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); -int perf_env__numa_node(struct perf_env *env, int cpu); +int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index ac706304afe9..fe24801f8e9f 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -57,6 +57,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", [PERF_RECORD_CGROUP] = "CGROUP", [PERF_RECORD_TEXT_POKE] = "TEXT_POKE", + [PERF_RECORD_AUX_OUTPUT_HW_ID] = "AUX_OUTPUT_HW_ID", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -237,6 +238,14 @@ int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused, return machine__process_itrace_start_event(machine, event); } +int perf_event__process_aux_output_hw_id(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine) +{ + return machine__process_aux_output_hw_id_event(machine, event); +} + int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -407,6 +416,12 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp) event->itrace_start.pid, event->itrace_start.tid); } +size_t perf_event__fprintf_aux_output_hw_id(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " hw_id: %#"PRI_lx64"\n", + event->aux_output_hw_id.hw_id); +} + size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp) { bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT; @@ -534,6 +549,9 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL case PERF_RECORD_TEXT_POKE: ret += perf_event__fprintf_text_poke(event, machine, fp); break; + case PERF_RECORD_AUX_OUTPUT_HW_ID: + ret += perf_event__fprintf_aux_output_hw_id(event, fp); + break; default: ret += fprintf(fp, "\n"); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 19ad64f2bd83..c59331eea1d9 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -44,13 +44,16 @@ struct perf_event_attr; /* perf sample has 16 bits size limit */ #define PERF_SAMPLE_MAX_SIZE (1 << 16) +/* number of register is bound by the number of bits in regs_dump::mask (64) */ +#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64)) + struct regs_dump { u64 abi; u64 mask; u64 *regs; /* Cached values/mask filled by first register access. */ - u64 cache_regs[PERF_REGS_MAX]; + u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE]; u64 cache_mask; }; @@ -330,6 +333,10 @@ int perf_event__process_itrace_start(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_aux_output_hw_id(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_switch(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -397,6 +404,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); size_t perf_event__fprintf_task(union perf_event *event, FILE *fp); size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp); size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_aux_output_hw_id(union perf_event *event, FILE *fp); size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c index 7c554234b43d..7f234215147d 100644 --- a/tools/perf/util/evlist-hybrid.c +++ b/tools/perf/util/evlist-hybrid.c @@ -124,22 +124,23 @@ int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list) events_nr++; - if (matched_cpus->nr > 0 && (unmatched_cpus->nr > 0 || - matched_cpus->nr < cpus->nr || - matched_cpus->nr < pmu->cpus->nr)) { + if (perf_cpu_map__nr(matched_cpus) > 0 && + (perf_cpu_map__nr(unmatched_cpus) > 0 || + perf_cpu_map__nr(matched_cpus) < perf_cpu_map__nr(cpus) || + perf_cpu_map__nr(matched_cpus) < perf_cpu_map__nr(pmu->cpus))) { perf_cpu_map__put(evsel->core.cpus); perf_cpu_map__put(evsel->core.own_cpus); evsel->core.cpus = perf_cpu_map__get(matched_cpus); evsel->core.own_cpus = perf_cpu_map__get(matched_cpus); - if (unmatched_cpus->nr > 0) { + if (perf_cpu_map__nr(unmatched_cpus) > 0) { cpu_map__snprint(matched_cpus, buf1, sizeof(buf1)); pr_warning("WARNING: use %s in '%s' for '%s', skip other cpus in list.\n", buf1, pmu->name, evsel->name); } } - if (matched_cpus->nr == 0) { + if (perf_cpu_map__nr(matched_cpus) == 0) { evlist__remove(evlist, evsel); evsel__delete(evsel); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 5f92319ce258..eaad04e1672a 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -342,36 +342,65 @@ static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel) return perf_thread_map__nr(evlist->core.threads); } -void evlist__cpu_iter_start(struct evlist *evlist) -{ - struct evsel *pos; - - /* - * Reset the per evsel cpu_iter. This is needed because - * each evsel's cpumap may have a different index space, - * and some operations need the index to modify - * the FD xyarray (e.g. open, close) - */ - evlist__for_each_entry(evlist, pos) - pos->cpu_iter = 0; -} +struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity) +{ + struct evlist_cpu_iterator itr = { + .container = evlist, + .evsel = evlist__first(evlist), + .cpu_map_idx = 0, + .evlist_cpu_map_idx = 0, + .evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus), + .cpu = (struct perf_cpu){ .cpu = -1}, + .affinity = affinity, + }; -bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu) -{ - if (ev->cpu_iter >= ev->core.cpus->nr) - return true; - if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu) - return true; - return false; + if (itr.affinity) { + itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0); + affinity__set(itr.affinity, itr.cpu.cpu); + itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu); + /* + * If this CPU isn't in the evsel's cpu map then advance through + * the list. + */ + if (itr.cpu_map_idx == -1) + evlist_cpu_iterator__next(&itr); + } + return itr; +} + +void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr) +{ + while (evlist_cpu_itr->evsel != evlist__last(evlist_cpu_itr->container)) { + evlist_cpu_itr->evsel = evsel__next(evlist_cpu_itr->evsel); + evlist_cpu_itr->cpu_map_idx = + perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus, + evlist_cpu_itr->cpu); + if (evlist_cpu_itr->cpu_map_idx != -1) + return; + } + evlist_cpu_itr->evlist_cpu_map_idx++; + if (evlist_cpu_itr->evlist_cpu_map_idx < evlist_cpu_itr->evlist_cpu_map_nr) { + evlist_cpu_itr->evsel = evlist__first(evlist_cpu_itr->container); + evlist_cpu_itr->cpu = + perf_cpu_map__cpu(evlist_cpu_itr->container->core.all_cpus, + evlist_cpu_itr->evlist_cpu_map_idx); + if (evlist_cpu_itr->affinity) + affinity__set(evlist_cpu_itr->affinity, evlist_cpu_itr->cpu.cpu); + evlist_cpu_itr->cpu_map_idx = + perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus, + evlist_cpu_itr->cpu); + /* + * If this CPU isn't in the evsel's cpu map then advance through + * the list. + */ + if (evlist_cpu_itr->cpu_map_idx == -1) + evlist_cpu_iterator__next(evlist_cpu_itr); + } } -bool evsel__cpu_iter_skip(struct evsel *ev, int cpu) +bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr) { - if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) { - ev->cpu_iter++; - return false; - } - return true; + return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr; } static int evsel__strcmp(struct evsel *pos, char *evsel_name) @@ -400,37 +429,36 @@ static int evlist__is_enabled(struct evlist *evlist) static void __evlist__disable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; - struct affinity affinity; - int cpu, i, imm = 0; + struct evlist_cpu_iterator evlist_cpu_itr; + struct affinity saved_affinity, *affinity = NULL; bool has_imm = false; - if (affinity__setup(&affinity) < 0) - return; + // See explanation in evlist__close() + if (!cpu_map__is_dummy(evlist->core.cpus)) { + if (affinity__setup(&saved_affinity) < 0) + return; + affinity = &saved_affinity; + } /* Disable 'immediate' events last */ - for (imm = 0; imm <= 1; imm++) { - evlist__for_each_cpu(evlist, i, cpu) { - affinity__set(&affinity, cpu); - - evlist__for_each_entry(evlist, pos) { - if (evsel__strcmp(pos, evsel_name)) - continue; - if (evsel__cpu_iter_skip(pos, cpu)) - continue; - if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd) - continue; - if (pos->immediate) - has_imm = true; - if (pos->immediate != imm) - continue; - evsel__disable_cpu(pos, pos->cpu_iter - 1); - } + for (int imm = 0; imm <= 1; imm++) { + evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) { + pos = evlist_cpu_itr.evsel; + if (evsel__strcmp(pos, evsel_name)) + continue; + if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd) + continue; + if (pos->immediate) + has_imm = true; + if (pos->immediate != imm) + continue; + evsel__disable_cpu(pos, evlist_cpu_itr.cpu_map_idx); } if (!has_imm) break; } - affinity__cleanup(&affinity); + affinity__cleanup(affinity); evlist__for_each_entry(evlist, pos) { if (evsel__strcmp(pos, evsel_name)) continue; @@ -462,26 +490,25 @@ void evlist__disable_evsel(struct evlist *evlist, char *evsel_name) static void __evlist__enable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; - struct affinity affinity; - int cpu, i; - - if (affinity__setup(&affinity) < 0) - return; + struct evlist_cpu_iterator evlist_cpu_itr; + struct affinity saved_affinity, *affinity = NULL; - evlist__for_each_cpu(evlist, i, cpu) { - affinity__set(&affinity, cpu); + // See explanation in evlist__close() + if (!cpu_map__is_dummy(evlist->core.cpus)) { + if (affinity__setup(&saved_affinity) < 0) + return; + affinity = &saved_affinity; + } - evlist__for_each_entry(evlist, pos) { - if (evsel__strcmp(pos, evsel_name)) - continue; - if (evsel__cpu_iter_skip(pos, cpu)) - continue; - if (!evsel__is_group_leader(pos) || !pos->core.fd) - continue; - evsel__enable_cpu(pos, pos->cpu_iter - 1); - } + evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) { + pos = evlist_cpu_itr.evsel; + if (evsel__strcmp(pos, evsel_name)) + continue; + if (!evsel__is_group_leader(pos) || !pos->core.fd) + continue; + evsel__enable_cpu(pos, evlist_cpu_itr.cpu_map_idx); } - affinity__cleanup(&affinity); + affinity__cleanup(affinity); evlist__for_each_entry(evlist, pos) { if (evsel__strcmp(pos, evsel_name)) continue; @@ -800,7 +827,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx) static int perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp, - int output, int cpu) + int output, struct perf_cpu cpu) { struct mmap *map = container_of(_map, struct mmap, core); struct mmap_params *mp = container_of(_mp, struct mmap_params, core); @@ -1264,14 +1291,14 @@ void evlist__set_selected(struct evlist *evlist, struct evsel *evsel) void evlist__close(struct evlist *evlist) { struct evsel *evsel; + struct evlist_cpu_iterator evlist_cpu_itr; struct affinity affinity; - int cpu, i; /* * With perf record core.cpus is usually NULL. * Use the old method to handle this for now. */ - if (!evlist->core.cpus) { + if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) { evlist__for_each_entry_reverse(evlist, evsel) evsel__close(evsel); return; @@ -1279,15 +1306,12 @@ void evlist__close(struct evlist *evlist) if (affinity__setup(&affinity) < 0) return; - evlist__for_each_cpu(evlist, i, cpu) { - affinity__set(&affinity, cpu); - evlist__for_each_entry_reverse(evlist, evsel) { - if (evsel__cpu_iter_skip(evsel, cpu)) - continue; - perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1); - } + evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) { + perf_evsel__close_cpu(&evlist_cpu_itr.evsel->core, + evlist_cpu_itr.cpu_map_idx); } + affinity__cleanup(&affinity); evlist__for_each_entry_reverse(evlist, evsel) { perf_evsel__free_fd(&evsel->core); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 97bfb8d0be4f..64cba56fbc74 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -64,6 +64,7 @@ struct evlist { struct evsel *selected; struct events_stats stats; struct perf_env *env; + const char *hybrid_pmu_name; void (*trace_event_sample_raw)(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); @@ -110,6 +111,7 @@ int __evlist__add_default_attrs(struct evlist *evlist, __evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) int arch_evlist__add_default_attrs(struct evlist *evlist); +struct evsel *arch_evlist__leader(struct list_head *list); int evlist__add_dummy(struct evlist *evlist); @@ -325,17 +327,53 @@ void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel); #define evlist__for_each_entry_safe(evlist, tmp, evsel) \ __evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel) -#define evlist__for_each_cpu(evlist, index, cpu) \ - evlist__cpu_iter_start(evlist); \ - perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) +/** Iterator state for evlist__for_each_cpu */ +struct evlist_cpu_iterator { + /** The list being iterated through. */ + struct evlist *container; + /** The current evsel of the iterator. */ + struct evsel *evsel; + /** The CPU map index corresponding to the evsel->core.cpus for the current CPU. */ + int cpu_map_idx; + /** + * The CPU map index corresponding to evlist->core.all_cpus for the + * current CPU. Distinct from cpu_map_idx as the evsel's cpu map may + * contain fewer entries. + */ + int evlist_cpu_map_idx; + /** The number of CPU map entries in evlist->core.all_cpus. */ + int evlist_cpu_map_nr; + /** The current CPU of the iterator. */ + struct perf_cpu cpu; + /** If present, used to set the affinity when switching between CPUs. */ + struct affinity *affinity; +}; + +/** + * evlist__for_each_cpu - without affinity, iterate over the evlist. With + * affinity, iterate over all CPUs and then the evlist + * for each evsel on that CPU. When switching between + * CPUs the affinity is set to the CPU to avoid IPIs + * during syscalls. + * @evlist_cpu_itr: the iterator instance. + * @evlist: evlist instance to iterate. + * @affinity: NULL or used to set the affinity to the current CPU. + */ +#define evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity) \ + for ((evlist_cpu_itr) = evlist__cpu_begin(evlist, affinity); \ + !evlist_cpu_iterator__end(&evlist_cpu_itr); \ + evlist_cpu_iterator__next(&evlist_cpu_itr)) + +/** Returns an iterator set to the first CPU/evsel of evlist. */ +struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity); +/** Move to next element in iterator, updating CPU, evsel and the affinity. */ +void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr); +/** Returns true when iterator is at the end of the CPUs and evlist. */ +bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr); struct evsel *evlist__get_tracking_event(struct evlist *evlist); void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); -void evlist__cpu_iter_start(struct evlist *evlist); -bool evsel__cpu_iter_skip(struct evsel *ev, int cpu); -bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu); - struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str); struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index dbfeceb2546c..22d3267ce294 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -241,7 +241,7 @@ void evsel__init(struct evsel *evsel, { perf_evsel__init(&evsel->core, attr, idx); evsel->tracking = !idx; - evsel->unit = ""; + evsel->unit = strdup(""); evsel->scale = 1.0; evsel->max_events = ULONG_MAX; evsel->evlist = NULL; @@ -276,13 +276,8 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) } if (evsel__is_clock(evsel)) { - /* - * The evsel->unit points to static alias->unit - * so it's ok to use static string in here. - */ - static const char *unit = "msec"; - - evsel->unit = unit; + free((char *)evsel->unit); + evsel->unit = strdup("msec"); evsel->scale = 1e-6; } @@ -294,7 +289,7 @@ static bool perf_event_can_profile_kernel(void) return perf_event_paranoid_check(1); } -struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config) +struct evsel *evsel__new_cycles(bool precise __maybe_unused, __u32 type, __u64 config) { struct perf_event_attr attr = { .type = type, @@ -305,18 +300,16 @@ struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config) event_attr_init(&attr); - if (!precise) - goto new_event; - /* * Now let the usual logic to set up the perf_event_attr defaults * to kick in when we return and before perf_evsel__open() is called. */ -new_event: evsel = evsel__new(&attr); if (evsel == NULL) goto out; + arch_evsel__fixup_new_cycles(&evsel->core.attr); + evsel->precise_max = true; /* use asprintf() because free(evsel) assumes name is allocated */ @@ -410,6 +403,11 @@ struct evsel *evsel__clone(struct evsel *orig) if (evsel->filter == NULL) goto out_err; } + if (orig->metric_id) { + evsel->metric_id = strdup(orig->metric_id); + if (evsel->metric_id == NULL) + goto out_err; + } evsel->cgrp = cgroup__get(orig->cgrp); evsel->tp_format = orig->tp_format; evsel->handler = orig->handler; @@ -417,7 +415,11 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->max_events = orig->max_events; evsel->tool_event = orig->tool_event; - evsel->unit = orig->unit; + free((char *)evsel->unit); + evsel->unit = strdup(orig->unit); + if (evsel->unit == NULL) + goto out_err; + evsel->scale = orig->scale; evsel->snapshot = orig->snapshot; evsel->per_pkg = orig->per_pkg; @@ -779,6 +781,17 @@ out_unknown: return "unknown"; } +const char *evsel__metric_id(const struct evsel *evsel) +{ + if (evsel->metric_id) + return evsel->metric_id; + + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE && evsel->tool_event) + return "duration_time"; + + return "unknown"; +} + const char *evsel__group_name(struct evsel *evsel) { return evsel->group_name ?: "anon group"; @@ -1047,6 +1060,21 @@ void __weak arch_evsel__set_sample_weight(struct evsel *evsel) evsel__set_sample_bit(evsel, WEIGHT); } +void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_unused) +{ +} + +static void evsel__set_default_freq_period(struct record_opts *opts, + struct perf_event_attr *attr) +{ + if (opts->freq) { + attr->freq = 1; + attr->sample_freq = opts->freq; + } else { + attr->sample_period = opts->default_interval; + } +} + /* * The enable_on_exec/disabled value strategy: * @@ -1113,14 +1141,12 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, * We default some events to have a default interval. But keep * it a weak assumption overridable by the user. */ - if (!attr->sample_period) { - if (opts->freq) { - attr->freq = 1; - attr->sample_freq = opts->freq; - } else { - attr->sample_period = opts->default_interval; - } - } + if ((evsel->is_libpfm_event && !attr->sample_period) || + (!evsel->is_libpfm_event && (!attr->sample_period || + opts->user_freq != UINT_MAX || + opts->user_interval != ULLONG_MAX))) + evsel__set_default_freq_period(opts, attr); + /* * If attr->freq was set (here or earlier), ask for period * to be sampled. @@ -1355,9 +1381,9 @@ int evsel__append_addr_filter(struct evsel *evsel, const char *filter) } /* Caller has to clear disabled after going through all CPUs. */ -int evsel__enable_cpu(struct evsel *evsel, int cpu) +int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx) { - return perf_evsel__enable_cpu(&evsel->core, cpu); + return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx); } int evsel__enable(struct evsel *evsel) @@ -1370,9 +1396,9 @@ int evsel__enable(struct evsel *evsel) } /* Caller has to set disabled after going through all CPUs. */ -int evsel__disable_cpu(struct evsel *evsel, int cpu) +int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx) { - return perf_evsel__disable_cpu(&evsel->core, cpu); + return perf_evsel__disable_cpu(&evsel->core, cpu_map_idx); } int evsel__disable(struct evsel *evsel) @@ -1423,6 +1449,8 @@ void evsel__exit(struct evsel *evsel) zfree(&evsel->group_name); zfree(&evsel->name); zfree(&evsel->pmu_name); + zfree(&evsel->unit); + zfree(&evsel->metric_id); evsel__zero_per_pkg(evsel); hashmap__free(evsel->per_pkg_mask); evsel->per_pkg_mask = NULL; @@ -1436,7 +1464,7 @@ void evsel__delete(struct evsel *evsel) free(evsel); } -void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, +void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -1444,12 +1472,12 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, if (!evsel->prev_raw_counts) return; - if (cpu == -1) { + if (cpu_map_idx == -1) { tmp = evsel->prev_raw_counts->aggr; evsel->prev_raw_counts->aggr = *count; } else { - tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread); - *perf_counts(evsel->prev_raw_counts, cpu, thread) = *count; + tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); + *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count; } count->val = count->val - tmp.val; @@ -1457,46 +1485,28 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, count->run = count->run - tmp.run; } -void perf_counts_values__scale(struct perf_counts_values *count, - bool scale, s8 *pscaled) +static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread) { - s8 scaled = 0; + struct perf_counts_values *count = perf_counts(evsel->counts, cpu_map_idx, thread); - if (scale) { - if (count->run == 0) { - scaled = -1; - count->val = 0; - } else if (count->run < count->ena) { - scaled = 1; - count->val = (u64)((double) count->val * count->ena / count->run); - } - } - - if (pscaled) - *pscaled = scaled; -} - -static int evsel__read_one(struct evsel *evsel, int cpu, int thread) -{ - struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread); - - return perf_evsel__read(&evsel->core, cpu, thread, count); + return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count); } -static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run) +static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, + u64 val, u64 ena, u64 run) { struct perf_counts_values *count; - count = perf_counts(counter->counts, cpu, thread); + count = perf_counts(counter->counts, cpu_map_idx, thread); count->val = val; count->ena = ena; count->run = run; - perf_counts__set_loaded(counter->counts, cpu, thread, true); + perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true); } -static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data) +static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int thread, u64 *data) { u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; @@ -1515,7 +1525,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, v = (struct sample_read_value *) data; - evsel__set_count(leader, cpu, thread, v[0].value, ena, run); + evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run); for (i = 1; i < nr; i++) { struct evsel *counter; @@ -1524,13 +1534,13 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, if (!counter) return -EINVAL; - evsel__set_count(counter, cpu, thread, v[i].value, ena, run); + evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run); } return 0; } -static int evsel__read_group(struct evsel *leader, int cpu, int thread) +static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread) { struct perf_stat_evsel *ps = leader->stats; u64 read_format = leader->core.attr.read_format; @@ -1551,67 +1561,67 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread) ps->group_data = data; } - if (FD(leader, cpu, thread) < 0) + if (FD(leader, cpu_map_idx, thread) < 0) return -EINVAL; - if (readn(FD(leader, cpu, thread), data, size) <= 0) + if (readn(FD(leader, cpu_map_idx, thread), data, size) <= 0) return -errno; - return evsel__process_group_data(leader, cpu, thread, data); + return evsel__process_group_data(leader, cpu_map_idx, thread, data); } -int evsel__read_counter(struct evsel *evsel, int cpu, int thread) +int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) { u64 read_format = evsel->core.attr.read_format; if (read_format & PERF_FORMAT_GROUP) - return evsel__read_group(evsel, cpu, thread); + return evsel__read_group(evsel, cpu_map_idx, thread); - return evsel__read_one(evsel, cpu, thread); + return evsel__read_one(evsel, cpu_map_idx, thread); } -int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale) +int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale) { struct perf_counts_values count; size_t nv = scale ? 3 : 1; - if (FD(evsel, cpu, thread) < 0) + if (FD(evsel, cpu_map_idx, thread) < 0) return -EINVAL; - if (evsel->counts == NULL && evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0) + if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0) return -ENOMEM; - if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0) + if (readn(FD(evsel, cpu_map_idx, thread), &count, nv * sizeof(u64)) <= 0) return -errno; - evsel__compute_deltas(evsel, cpu, thread, &count); + evsel__compute_deltas(evsel, cpu_map_idx, thread, &count); perf_counts_values__scale(&count, scale, NULL); - *perf_counts(evsel->counts, cpu, thread) = count; + *perf_counts(evsel->counts, cpu_map_idx, thread) = count; return 0; } static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other, - int cpu) + int cpu_map_idx) { - int cpuid; + struct perf_cpu cpu; - cpuid = perf_cpu_map__cpu(evsel->core.cpus, cpu); - return perf_cpu_map__idx(other->core.cpus, cpuid); + cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx); + return perf_cpu_map__idx(other->core.cpus, cpu); } -static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu) +static int evsel__hybrid_group_cpu_map_idx(struct evsel *evsel, int cpu_map_idx) { struct evsel *leader = evsel__leader(evsel); if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) || (!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) { - return evsel__match_other_cpu(evsel, leader, cpu); + return evsel__match_other_cpu(evsel, leader, cpu_map_idx); } - return cpu; + return cpu_map_idx; } -static int get_group_fd(struct evsel *evsel, int cpu, int thread) +static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) { struct evsel *leader = evsel__leader(evsel); int fd; @@ -1625,11 +1635,11 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread) */ BUG_ON(!leader->core.fd); - cpu = evsel__hybrid_group_cpu(evsel, cpu); - if (cpu == -1) + cpu_map_idx = evsel__hybrid_group_cpu_map_idx(evsel, cpu_map_idx); + if (cpu_map_idx == -1) return -1; - fd = FD(leader, cpu, thread); + fd = FD(leader, cpu_map_idx, thread); BUG_ON(fd == -1); return fd; @@ -1643,16 +1653,16 @@ static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int } static int update_fds(struct evsel *evsel, - int nr_cpus, int cpu_idx, + int nr_cpus, int cpu_map_idx, int nr_threads, int thread_idx) { struct evsel *pos; - if (cpu_idx >= nr_cpus || thread_idx >= nr_threads) + if (cpu_map_idx >= nr_cpus || thread_idx >= nr_threads) return -EINVAL; evlist__for_each_entry(evsel->evlist, pos) { - nr_cpus = pos != evsel ? nr_cpus : cpu_idx; + nr_cpus = pos != evsel ? nr_cpus : cpu_map_idx; evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx); @@ -1666,10 +1676,10 @@ static int update_fds(struct evsel *evsel, return 0; } -bool evsel__ignore_missing_thread(struct evsel *evsel, - int nr_cpus, int cpu, - struct perf_thread_map *threads, - int thread, int err) +static bool evsel__ignore_missing_thread(struct evsel *evsel, + int nr_cpus, int cpu_map_idx, + struct perf_thread_map *threads, + int thread, int err) { pid_t ignore_pid = perf_thread_map__pid(threads, thread); @@ -1692,7 +1702,7 @@ bool evsel__ignore_missing_thread(struct evsel *evsel, * We should remove fd for missing_thread first * because thread_map__remove() will decrease threads->nr. */ - if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread)) + if (update_fds(evsel, nr_cpus, cpu_map_idx, threads->nr, thread)) return false; if (thread_map__remove(threads, thread)) @@ -1781,7 +1791,7 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, nthreads = threads->nr; if (evsel->core.fd == NULL && - perf_evsel__alloc_fd(&evsel->core, cpus->nr, nthreads) < 0) + perf_evsel__alloc_fd(&evsel->core, perf_cpu_map__nr(cpus), nthreads) < 0) return -ENOMEM; evsel->open_flags = PERF_FLAG_FD_CLOEXEC; @@ -1807,7 +1817,7 @@ static void evsel__disable_missing_features(struct evsel *evsel) evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) evsel->core.attr.mmap2 = 0; - if (perf_missing_features.exclude_guest) + if (evsel->pmu && evsel->pmu->missing_features.exclude_guest) evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0; if (perf_missing_features.lbr_flags) evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | @@ -1900,10 +1910,27 @@ bool evsel__detect_missing_features(struct evsel *evsel) perf_missing_features.mmap2 = true; pr_debug2_peo("switching off mmap2\n"); return true; - } else if (!perf_missing_features.exclude_guest && - (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) { - perf_missing_features.exclude_guest = true; - pr_debug2_peo("switching off exclude_guest, exclude_host\n"); + } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) && + (evsel->pmu == NULL || evsel->pmu->missing_features.exclude_guest)) { + if (evsel->pmu == NULL) { + evsel->pmu = evsel__find_pmu(evsel); + if (evsel->pmu) + evsel->pmu->missing_features.exclude_guest = true; + else { + /* we cannot find PMU, disable attrs now */ + evsel->core.attr.exclude_host = false; + evsel->core.attr.exclude_guest = false; + } + } + + if (evsel->exclude_GH) { + pr_debug2_peo("PMU has no exclude_host/guest support, bailing out\n"); + return false; + } + if (!perf_missing_features.exclude_guest) { + perf_missing_features.exclude_guest = true; + pr_debug2_peo("switching off exclude_guest, exclude_host\n"); + } return true; } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; @@ -1957,9 +1984,9 @@ bool evsel__increase_rlimit(enum rlimit_action *set_rlimit) static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads, - int start_cpu, int end_cpu) + int start_cpu_map_idx, int end_cpu_map_idx) { - int cpu, thread, nthreads; + int idx, thread, nthreads; int pid = -1, err, old_errno; enum rlimit_action set_rlimit = NO_CHANGE; @@ -1986,7 +2013,7 @@ fallback_missing_features: display_attr(&evsel->core.attr); - for (cpu = start_cpu; cpu < end_cpu; cpu++) { + for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; @@ -1997,17 +2024,18 @@ retry_open: if (!evsel->cgrp && !evsel->core.system_wide) pid = perf_thread_map__pid(threads, thread); - group_fd = get_group_fd(evsel, cpu, thread); + group_fd = get_group_fd(evsel, idx, thread); test_attr__ready(); pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", - pid, cpus->map[cpu], group_fd, evsel->open_flags); + pid, perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags); - fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[cpu], + fd = sys_perf_event_open(&evsel->core.attr, pid, + perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags); - FD(evsel, cpu, thread) = fd; + FD(evsel, idx, thread) = fd; if (fd < 0) { err = -errno; @@ -2017,10 +2045,11 @@ retry_open: goto try_fallback; } - bpf_counter__install_pe(evsel, cpu, fd); + bpf_counter__install_pe(evsel, idx, fd); if (unlikely(test_attr__enabled)) { - test_attr__open(&evsel->core.attr, pid, cpus->map[cpu], + test_attr__open(&evsel->core.attr, pid, + perf_cpu_map__cpu(cpus, idx), fd, group_fd, evsel->open_flags); } @@ -2061,7 +2090,8 @@ try_fallback: if (evsel__precise_ip_fallback(evsel)) goto retry_open; - if (evsel__ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) { + if (evsel__ignore_missing_thread(evsel, perf_cpu_map__nr(cpus), + idx, threads, thread, err)) { /* We just removed 1 thread, so lower the upper nthreads limit. */ nthreads--; @@ -2076,7 +2106,7 @@ try_fallback: if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit)) goto retry_open; - if (err != -EINVAL || cpu > 0 || thread > 0) + if (err != -EINVAL || idx > 0 || thread > 0) goto out_close; if (evsel__detect_missing_features(evsel)) @@ -2088,12 +2118,12 @@ out_close: old_errno = errno; do { while (--thread >= 0) { - if (FD(evsel, cpu, thread) >= 0) - close(FD(evsel, cpu, thread)); - FD(evsel, cpu, thread) = -1; + if (FD(evsel, idx, thread) >= 0) + close(FD(evsel, idx, thread)); + FD(evsel, idx, thread) = -1; } thread = nthreads; - } while (--cpu >= 0); + } while (--idx >= 0); errno = old_errno; return err; } @@ -2101,7 +2131,7 @@ out_close: int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { - return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1); + return evsel__open_cpu(evsel, cpus, threads, 0, perf_cpu_map__nr(cpus)); } void evsel__close(struct evsel *evsel) @@ -2110,13 +2140,12 @@ void evsel__close(struct evsel *evsel) perf_evsel__free_id(&evsel->core); } -int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu) +int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx) { - if (cpu == -1) - return evsel__open_cpu(evsel, cpus, NULL, 0, - cpus ? cpus->nr : 1); + if (cpu_map_idx == -1) + return evsel__open_cpu(evsel, cpus, NULL, 0, perf_cpu_map__nr(cpus)); - return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1); + return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1); } int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads) @@ -2221,6 +2250,54 @@ void __weak arch_perf_parse_sample_weight(struct perf_sample *data, data->weight = *array; } +u64 evsel__bitfield_swap_branch_flags(u64 value) +{ + u64 new_val = 0; + + /* + * branch_flags + * union { + * u64 values; + * struct { + * mispred:1 //target mispredicted + * predicted:1 //target predicted + * in_tx:1 //in transaction + * abort:1 //transaction abort + * cycles:16 //cycle count to last branch + * type:4 //branch type + * reserved:40 + * } + * } + * + * Avoid bswap64() the entire branch_flag.value, + * as it has variable bit-field sizes. Instead the + * macro takes the bit-field position/size, + * swaps it based on the host endianness. + * + * tep_is_bigendian() is used here instead of + * bigendian() to avoid python test fails. + */ + if (tep_is_bigendian()) { + new_val = bitfield_swap(value, 0, 1); + new_val |= bitfield_swap(value, 1, 1); + new_val |= bitfield_swap(value, 2, 1); + new_val |= bitfield_swap(value, 3, 1); + new_val |= bitfield_swap(value, 4, 16); + new_val |= bitfield_swap(value, 20, 4); + new_val |= bitfield_swap(value, 24, 40); + } else { + new_val = bitfield_swap(value, 63, 1); + new_val |= bitfield_swap(value, 62, 1); + new_val |= bitfield_swap(value, 61, 1); + new_val |= bitfield_swap(value, 60, 1); + new_val |= bitfield_swap(value, 44, 16); + new_val |= bitfield_swap(value, 40, 4); + new_val |= bitfield_swap(value, 0, 40); + } + + return new_val; +} + int evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { @@ -2408,6 +2485,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, if (type & PERF_SAMPLE_BRANCH_STACK) { const u64 max_branch_nr = UINT64_MAX / sizeof(struct branch_entry); + struct branch_entry *e; + unsigned int i; OVERFLOW_CHECK_u64(array); data->branch_stack = (struct branch_stack *)array++; @@ -2416,10 +2495,33 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, return -EFAULT; sz = data->branch_stack->nr * sizeof(struct branch_entry); - if (evsel__has_branch_hw_idx(evsel)) + if (evsel__has_branch_hw_idx(evsel)) { sz += sizeof(u64); - else + e = &data->branch_stack->entries[0]; + } else { data->no_hw_idx = true; + /* + * if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied, + * only nr and entries[] will be output by kernel. + */ + e = (struct branch_entry *)&data->branch_stack->hw_idx; + } + + if (swapped) { + /* + * struct branch_flag does not have endian + * specific bit field definition. And bswap + * will not resolve the issue, since these + * are bit fields. + * + * evsel__bitfield_swap_branch_flags() uses a + * bitfield_swap macro to swap the bit position + * based on the host endians. + */ + for (i = 0; i < data->branch_stack->nr; i++, e++) + e->flags.value = evsel__bitfield_swap_branch_flags(e->flags.value); + } + OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; } @@ -2597,6 +2699,8 @@ void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(sample->raw_data + field->offset); offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } return sample->raw_data + offset; @@ -2841,6 +2945,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "wrong clockid (%d).", clockid); if (perf_missing_features.aux_output) return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); + if (!target__has_cpu(target)) + return scnprintf(msg, size, + "Invalid event (%s) in per-thread mode, enable system wide with '-a'.", + evsel__name(evsel)); break; case ENODATA: return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. " @@ -2864,15 +2972,15 @@ struct perf_env *evsel__env(struct evsel *evsel) static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) { - int cpu, thread; + int cpu_map_idx, thread; - for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) { + for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) { for (thread = 0; thread < xyarray__max_y(evsel->core.fd); thread++) { - int fd = FD(evsel, cpu, thread); + int fd = FD(evsel, cpu_map_idx, thread); if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, - cpu, thread, fd) < 0) + cpu_map_idx, thread, fd) < 0) return -1; } } @@ -2885,7 +2993,7 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist) struct perf_cpu_map *cpus = evsel->core.cpus; struct perf_thread_map *threads = evsel->core.threads; - if (perf_evsel__alloc_id(&evsel->core, cpus->nr, threads->nr)) + if (perf_evsel__alloc_id(&evsel->core, perf_cpu_map__nr(cpus), threads->nr)) return -ENOMEM; return store_evsel_ids(evsel, evlist); @@ -2928,3 +3036,15 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader) { evsel->core.leader = &leader->core; } + +int evsel__source_count(const struct evsel *evsel) +{ + struct evsel *pos; + int count = 0; + + evlist__for_each_entry(evsel->evlist, pos) { + if (pos->metric_leader == evsel) + count++; + } + return count; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 1f7edfa8568a..041b42d33bf5 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -11,6 +11,7 @@ #include <perf/evsel.h> #include "symbol_conf.h" #include <internal/cpumap.h> +#include <perf/cpumap.h> struct bpf_object; struct cgroup; @@ -22,6 +23,7 @@ struct target; struct hashmap; struct bperf_leader_bpf; struct bperf_follower_bpf; +struct perf_pmu; typedef int (evsel__sb_cb_t)(union perf_event *event, void *data); @@ -68,6 +70,7 @@ struct evsel { double scale; const char *unit; struct cgroup *cgrp; + const char *metric_id; enum perf_tool_event tool_event; /* parse modifier helper */ int exclude_GH; @@ -119,7 +122,6 @@ struct evsel { bool errored; struct hashmap *per_pkg_mask; int err; - int cpu_iter; struct { evsel__sb_cb_t *cb; void *data; @@ -152,6 +154,9 @@ struct evsel { }; unsigned long open_flags; int precise_ip_original; + + /* for missing_features */ + struct perf_pmu *pmu; }; struct perf_missing_features { @@ -187,12 +192,9 @@ static inline struct perf_cpu_map *evsel__cpus(struct evsel *evsel) static inline int evsel__nr_cpus(struct evsel *evsel) { - return evsel__cpus(evsel)->nr; + return perf_cpu_map__nr(evsel__cpus(evsel)); } -void perf_counts_values__scale(struct perf_counts_values *count, - bool scale, s8 *pscaled); - void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread, struct perf_counts_values *count); @@ -261,6 +263,7 @@ bool evsel__match_bpf_counter_events(const char *name); int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *evsel__name(struct evsel *evsel); +const char *evsel__metric_id(const struct evsel *evsel); const char *evsel__group_name(struct evsel *evsel); int evsel__group_desc(struct evsel *evsel, char *buf, size_t size); @@ -277,16 +280,17 @@ void __evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_forma void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier); void arch_evsel__set_sample_weight(struct evsel *evsel); +void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr); int evsel__set_filter(struct evsel *evsel, const char *filter); int evsel__append_tp_filter(struct evsel *evsel, const char *filter); int evsel__append_addr_filter(struct evsel *evsel, const char *filter); -int evsel__enable_cpu(struct evsel *evsel, int cpu); +int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx); int evsel__enable(struct evsel *evsel); int evsel__disable(struct evsel *evsel); -int evsel__disable_cpu(struct evsel *evsel, int cpu); +int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx); -int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu); +int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx); int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads); int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); @@ -298,10 +302,6 @@ bool evsel__detect_missing_features(struct evsel *evsel); enum rlimit_action { NO_CHANGE, SET_TO_MAX, INCREASED_MAX }; bool evsel__increase_rlimit(enum rlimit_action *set_rlimit); -bool evsel__ignore_missing_thread(struct evsel *evsel, - int nr_cpus, int cpu, - struct perf_thread_map *threads, - int thread, int err); bool evsel__precise_ip_fallback(struct evsel *evsel); struct perf_sample; @@ -330,32 +330,32 @@ static inline bool evsel__match2(struct evsel *e1, struct evsel *e2) (e1->core.attr.config == e2->core.attr.config); } -int evsel__read_counter(struct evsel *evsel, int cpu, int thread); +int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread); -int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale); +int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale); /** * evsel__read_on_cpu - Read out the results on a CPU and thread * * @evsel - event selector to read value - * @cpu - CPU of interest + * @cpu_map_idx - CPU of interest * @thread - thread of interest */ -static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread) +static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread) { - return __evsel__read_on_cpu(evsel, cpu, thread, false); + return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, false); } /** * evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled * * @evsel - event selector to read value - * @cpu - CPU of interest + * @cpu_map_idx - CPU of interest * @thread - thread of interest */ -static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread) +static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu_map_idx, int thread) { - return __evsel__read_on_cpu(evsel, cpu, thread, true); + return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, true); } int evsel__parse_sample(struct evsel *evsel, union perf_event *event, @@ -482,4 +482,18 @@ struct evsel *evsel__leader(struct evsel *evsel); bool evsel__has_leader(struct evsel *evsel, struct evsel *leader); bool evsel__is_leader(struct evsel *evsel); void evsel__set_leader(struct evsel *evsel, struct evsel *leader); +int evsel__source_count(const struct evsel *evsel); + +/* + * Macro to swap the bit-field postition and size. + * Used when, + * - dont need to swap the entire u64 && + * - when u64 has variable bit-field sizes && + * - when presented in a host endian which is different + * than the source endian of the perf.data file + */ +#define bitfield_swap(src, pos, size) \ + ((((src) >> (pos)) & ((1ull << (size)) - 1)) << (63 - ((pos) + (size) - 1))) + +u64 evsel__bitfield_swap_branch_flags(u64 value); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index bfedd7b23521..8c2ea8001329 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -11,6 +11,7 @@ #include "strlist.h" #include "symbol.h" #include "srcline.h" +#include "dso.h" static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) { @@ -144,12 +145,17 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_arrow && !first) printed += fprintf(fp, " <-"); - if (print_ip) - printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); - if (map) addr = map->map_ip(map, node->ip); + if (print_ip) { + /* Show binary offset for userspace addr */ + if (map && !map->dso->kernel) + printed += fprintf(fp, "%c%16" PRIx64, s, addr); + else + printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); + } + if (print_sym) { printed += fprintf(fp, " "); node_al.addr = addr; diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index a850fd0be3ee..675f318ce7c1 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -5,13 +5,18 @@ #include <stdlib.h> #include <string.h> #include "metricgroup.h" +#include "cpumap.h" +#include "cputopo.h" #include "debug.h" #include "expr.h" #include "expr-bison.h" #include "expr-flex.h" +#include "smt.h" +#include <linux/err.h> #include <linux/kernel.h> #include <linux/zalloc.h> #include <ctype.h> +#include <math.h> #ifdef PARSER_DEBUG extern int expr_debug; @@ -19,13 +24,15 @@ extern int expr_debug; struct expr_id_data { union { - double val; + struct { + double val; + int source_count; + } val; struct { double val; const char *metric_name; const char *metric_expr; } ref; - struct expr_id *parent; }; enum { @@ -35,8 +42,6 @@ struct expr_id_data { EXPR_ID_DATA__REF, /* A reference but the value has been computed. */ EXPR_ID_DATA__REF_VALUE, - /* A parent is remembered for the recursion check. */ - EXPR_ID_DATA__PARENT, } kind; }; @@ -59,21 +64,39 @@ static bool key_equal(const void *key1, const void *key2, return !strcmp((const char *)key1, (const char *)key2); } -/* Caller must make sure id is allocated */ -int expr__add_id(struct expr_parse_ctx *ctx, const char *id) +struct hashmap *ids__new(void) +{ + struct hashmap *hash; + + hash = hashmap__new(key_hash, key_equal, NULL); + if (IS_ERR(hash)) + return NULL; + return hash; +} + +void ids__free(struct hashmap *ids) +{ + struct hashmap_entry *cur; + size_t bkt; + + if (ids == NULL) + return; + + hashmap__for_each_entry(ids, cur, bkt) { + free((char *)cur->key); + free(cur->value); + } + + hashmap__free(ids); +} + +int ids__insert(struct hashmap *ids, const char *id) { struct expr_id_data *data_ptr = NULL, *old_data = NULL; char *old_key = NULL; int ret; - data_ptr = malloc(sizeof(*data_ptr)); - if (!data_ptr) - return -ENOMEM; - - data_ptr->parent = ctx->parent; - data_ptr->kind = EXPR_ID_DATA__PARENT; - - ret = hashmap__set(&ctx->ids, id, data_ptr, + ret = hashmap__set(ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); if (ret) free(data_ptr); @@ -82,9 +105,58 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id) return ret; } +struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2) +{ + size_t bkt; + struct hashmap_entry *cur; + int ret; + struct expr_id_data *old_data = NULL; + char *old_key = NULL; + + if (!ids1) + return ids2; + + if (!ids2) + return ids1; + + if (hashmap__size(ids1) < hashmap__size(ids2)) { + struct hashmap *tmp = ids1; + + ids1 = ids2; + ids2 = tmp; + } + hashmap__for_each_entry(ids2, cur, bkt) { + ret = hashmap__set(ids1, cur->key, cur->value, + (const void **)&old_key, (void **)&old_data); + free(old_key); + free(old_data); + + if (ret) { + hashmap__free(ids1); + hashmap__free(ids2); + return NULL; + } + } + hashmap__free(ids2); + return ids1; +} + +/* Caller must make sure id is allocated */ +int expr__add_id(struct expr_parse_ctx *ctx, const char *id) +{ + return ids__insert(ctx->ids, id); +} + /* Caller must make sure id is allocated */ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) { + return expr__add_id_val_source_count(ctx, id, val, /*source_count=*/1); +} + +/* Caller must make sure id is allocated */ +int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id, + double val, int source_count) +{ struct expr_id_data *data_ptr = NULL, *old_data = NULL; char *old_key = NULL; int ret; @@ -92,10 +164,11 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) data_ptr = malloc(sizeof(*data_ptr)); if (!data_ptr) return -ENOMEM; - data_ptr->val = val; + data_ptr->val.val = val; + data_ptr->val.source_count = source_count; data_ptr->kind = EXPR_ID_DATA__VALUE; - ret = hashmap__set(&ctx->ids, id, data_ptr, + ret = hashmap__set(ctx->ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); if (ret) free(data_ptr); @@ -140,7 +213,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) data_ptr->ref.metric_expr = ref->metric_expr; data_ptr->kind = EXPR_ID_DATA__REF; - ret = hashmap__set(&ctx->ids, name, data_ptr, + ret = hashmap__set(ctx->ids, name, data_ptr, (const void **)&old_key, (void **)&old_data); if (ret) free(data_ptr); @@ -156,9 +229,24 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data) { - return hashmap__find(&ctx->ids, id, (void **)data) ? 0 : -1; + return hashmap__find(ctx->ids, id, (void **)data) ? 0 : -1; +} + +bool expr__subset_of_ids(struct expr_parse_ctx *haystack, + struct expr_parse_ctx *needles) +{ + struct hashmap_entry *cur; + size_t bkt; + struct expr_id_data *data; + + hashmap__for_each_entry(needles->ids, cur, bkt) { + if (expr__get_id(haystack, cur->key, &data)) + return false; + } + return true; } + int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **datap) { @@ -173,21 +261,18 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, switch (data->kind) { case EXPR_ID_DATA__VALUE: - pr_debug2("lookup(%s): val %f\n", id, data->val); - break; - case EXPR_ID_DATA__PARENT: - pr_debug2("lookup(%s): parent %s\n", id, data->parent->id); + pr_debug2("lookup(%s): val %f\n", id, data->val.val); break; case EXPR_ID_DATA__REF: pr_debug2("lookup(%s): ref metric name %s\n", id, data->ref.metric_name); pr_debug("processing metric: %s ENTRY\n", id); data->kind = EXPR_ID_DATA__REF_VALUE; - if (expr__parse(&data->ref.val, ctx, data->ref.metric_expr, 1)) { + if (expr__parse(&data->ref.val, ctx, data->ref.metric_expr)) { pr_debug("%s failed to count\n", id); return -1; } - pr_debug("processing metric: %s EXIT: %f\n", id, data->val); + pr_debug("processing metric: %s EXIT: %f\n", id, data->ref.val); break; case EXPR_ID_DATA__REF_VALUE: pr_debug2("lookup(%s): ref val %f metric name %s\n", id, @@ -205,15 +290,28 @@ void expr__del_id(struct expr_parse_ctx *ctx, const char *id) struct expr_id_data *old_val = NULL; char *old_key = NULL; - hashmap__delete(&ctx->ids, id, + hashmap__delete(ctx->ids, id, (const void **)&old_key, (void **)&old_val); free(old_key); free(old_val); } -void expr__ctx_init(struct expr_parse_ctx *ctx) +struct expr_parse_ctx *expr__ctx_new(void) { - hashmap__init(&ctx->ids, key_hash, key_equal, NULL); + struct expr_parse_ctx *ctx; + + ctx = malloc(sizeof(struct expr_parse_ctx)); + if (!ctx) + return NULL; + + ctx->ids = hashmap__new(key_hash, key_equal, NULL); + if (IS_ERR(ctx->ids)) { + free(ctx); + return NULL; + } + ctx->runtime = 0; + + return ctx; } void expr__ctx_clear(struct expr_parse_ctx *ctx) @@ -221,20 +319,32 @@ void expr__ctx_clear(struct expr_parse_ctx *ctx) struct hashmap_entry *cur; size_t bkt; - hashmap__for_each_entry((&ctx->ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { free((char *)cur->key); free(cur->value); } - hashmap__clear(&ctx->ids); + hashmap__clear(ctx->ids); +} + +void expr__ctx_free(struct expr_parse_ctx *ctx) +{ + struct hashmap_entry *cur; + size_t bkt; + + hashmap__for_each_entry(ctx->ids, cur, bkt) { + free((char *)cur->key); + free(cur->value); + } + hashmap__free(ctx->ids); + free(ctx); } static int __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr, - int start, int runtime) + bool compute_ids) { struct expr_scanner_ctx scanner_ctx = { - .start_token = start, - .runtime = runtime, + .runtime = ctx->runtime, }; YY_BUFFER_STATE buffer; void *scanner; @@ -253,7 +363,7 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr, expr_set_debug(1, scanner); #endif - ret = expr_parse(val, ctx, scanner); + ret = expr_parse(val, ctx, compute_ids, scanner); expr__flush_buffer(buffer, scanner); expr__delete_buffer(buffer, scanner); @@ -262,15 +372,15 @@ __expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr, } int expr__parse(double *final_val, struct expr_parse_ctx *ctx, - const char *expr, int runtime) + const char *expr) { - return __expr__parse(final_val, ctx, expr, EXPR_PARSE, runtime) ? -1 : 0; + return __expr__parse(final_val, ctx, expr, /*compute_ids=*/false) ? -1 : 0; } -int expr__find_other(const char *expr, const char *one, - struct expr_parse_ctx *ctx, int runtime) +int expr__find_ids(const char *expr, const char *one, + struct expr_parse_ctx *ctx) { - int ret = __expr__parse(NULL, ctx, expr, EXPR_OTHER, runtime); + int ret = __expr__parse(NULL, ctx, expr, /*compute_ids=*/true); if (one) expr__del_id(ctx, one); @@ -281,13 +391,60 @@ int expr__find_other(const char *expr, const char *one, double expr_id_data__value(const struct expr_id_data *data) { if (data->kind == EXPR_ID_DATA__VALUE) - return data->val; + return data->val.val; assert(data->kind == EXPR_ID_DATA__REF_VALUE); return data->ref.val; } -struct expr_id *expr_id_data__parent(struct expr_id_data *data) +double expr_id_data__source_count(const struct expr_id_data *data) { - assert(data->kind == EXPR_ID_DATA__PARENT); - return data->parent; + assert(data->kind == EXPR_ID_DATA__VALUE); + return data->val.source_count; +} + +double expr__get_literal(const char *literal) +{ + static struct cpu_topology *topology; + double result = NAN; + + if (!strcasecmp("#smt_on", literal)) { + result = smt_on() > 0 ? 1.0 : 0.0; + goto out; + } + + if (!strcmp("#num_cpus", literal)) { + result = cpu__max_present_cpu().cpu; + goto out; + } + + /* + * Assume that topology strings are consistent, such as CPUs "0-1" + * wouldn't be listed as "0,1", and so after deduplication the number of + * these strings gives an indication of the number of packages, dies, + * etc. + */ + if (!topology) { + topology = cpu_topology__new(); + if (!topology) { + pr_err("Error creating CPU topology"); + goto out; + } + } + if (!strcmp("#num_packages", literal)) { + result = topology->package_cpus_lists; + goto out; + } + if (!strcmp("#num_dies", literal)) { + result = topology->die_cpus_lists; + goto out; + } + if (!strcmp("#num_cores", literal)) { + result = topology->core_cpus_lists; + goto out; + } + + pr_err("Unrecognized literal '%s'", literal); +out: + pr_debug2("literal: %s = %f\n", literal, result); + return result; } diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 85df3e4771e4..bd2116983bbb 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -13,39 +13,51 @@ struct metric_ref; -struct expr_id { - char *id; - struct expr_id *parent; -}; - struct expr_parse_ctx { - struct hashmap ids; - struct expr_id *parent; + struct hashmap *ids; + int runtime; }; struct expr_id_data; struct expr_scanner_ctx { - int start_token; int runtime; }; -void expr__ctx_init(struct expr_parse_ctx *ctx); +struct hashmap *ids__new(void); +void ids__free(struct hashmap *ids); +int ids__insert(struct hashmap *ids, const char *id); +/* + * Union two sets of ids (hashmaps) and construct a third, freeing ids1 and + * ids2. + */ +struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2); + +struct expr_parse_ctx *expr__ctx_new(void); void expr__ctx_clear(struct expr_parse_ctx *ctx); +void expr__ctx_free(struct expr_parse_ctx *ctx); + void expr__del_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val); +int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id, + double val, int source_count); int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref); int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data); +bool expr__subset_of_ids(struct expr_parse_ctx *haystack, + struct expr_parse_ctx *needles); int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **datap); + int expr__parse(double *final_val, struct expr_parse_ctx *ctx, - const char *expr, int runtime); -int expr__find_other(const char *expr, const char *one, - struct expr_parse_ctx *ids, int runtime); + const char *expr); + +int expr__find_ids(const char *expr, const char *one, + struct expr_parse_ctx *ids); double expr_id_data__value(const struct expr_id_data *data); -struct expr_id *expr_id_data__parent(struct expr_id_data *data); +double expr_id_data__source_count(const struct expr_id_data *data); +double expr__get_literal(const char *literal); #endif diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l index 13e5e3c75f56..0a13eb20c814 100644 --- a/tools/perf/util/expr.l +++ b/tools/perf/util/expr.l @@ -6,6 +6,7 @@ #include <linux/compiler.h> #include "expr.h" #include "expr-bison.h" +#include <math.h> char *expr_get_text(yyscan_t yyscanner); YYSTYPE *expr_get_lval(yyscan_t yyscanner); @@ -41,11 +42,9 @@ static char *normalize(char *str, int runtime) char *dst = str; while (*str) { - if (*str == '@') - *dst++ = '/'; - else if (*str == '\\') + if (*str == '\\') *dst++ = *++str; - else if (*str == '?') { + else if (*str == '?') { char *paramval; int i = 0; int size = asprintf(¶mval, "%d", runtime); @@ -79,6 +78,17 @@ static int str(yyscan_t scanner, int token, int runtime) yylval->str = normalize(yylval->str, runtime); return token; } + +static int literal(yyscan_t scanner) +{ + YYSTYPE *yylval = expr_get_lval(scanner); + + yylval->num = expr__get_literal(expr_get_text(scanner)); + if (isnan(yylval->num)) + return EXPR_ERROR; + + return LITERAL; +} %} number ([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+) @@ -87,25 +97,18 @@ sch [-,=] spec \\{sch} sym [0-9a-zA-Z_\.:@?]+ symbol ({spec}|{sym})+ +literal #[0-9a-zA-Z_\.\-]+ %% struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner); - { - int start_token = sctx->start_token; - - if (sctx->start_token) { - sctx->start_token = 0; - return start_token; - } - } - d_ratio { return D_RATIO; } max { return MAX; } min { return MIN; } if { return IF; } else { return ELSE; } -#smt_on { return SMT_ON; } +source_count { return SOURCE_COUNT; } +{literal} { return literal(yyscanner); } {number} { return value(yyscanner); } {symbol} { return str(yyscanner, ID, sctx->runtime); } "|" { return '|'; } diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index b2ada8f8309a..a30b825adb7b 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -1,42 +1,43 @@ /* Simple expression parser */ %{ #define YYDEBUG 1 -#include <stdio.h> -#include "util.h" +#include <assert.h> +#include <math.h> +#include <stdlib.h> #include "util/debug.h" -#include <stdlib.h> // strtod() #define IN_EXPR_Y 1 #include "expr.h" -#include "smt.h" -#include <string.h> - -static double d_ratio(double val0, double val1) -{ - if (val1 == 0) { - return 0; - } - return val0 / val1; -} - %} %define api.pure full %parse-param { double *final_val } %parse-param { struct expr_parse_ctx *ctx } +%parse-param { bool compute_ids } %parse-param {void *scanner} %lex-param {void* scanner} %union { double num; char *str; + struct ids { + /* + * When creating ids, holds the working set of event ids. NULL + * implies the set is empty. + */ + struct hashmap *ids; + /* + * The metric value. When not creating ids this is the value + * read from a counter, a constant or some computed value. When + * creating ids the value is either a constant or BOTTOM. NAN is + * used as the special BOTTOM value, representing a "set of all + * values" case. + */ + double val; + } ids; } -%token EXPR_PARSE EXPR_OTHER EXPR_ERROR -%token <num> NUMBER -%token <str> ID -%destructor { free ($$); } <str> -%token MIN MAX IF ELSE SMT_ON D_RATIO +%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT EXPR_ERROR %left MIN MAX IF %left '|' %left '^' @@ -45,83 +46,256 @@ static double d_ratio(double val0, double val1) %left '-' '+' %left '*' '/' '%' %left NEG NOT -%type <num> expr if_expr +%type <num> NUMBER LITERAL +%type <str> ID +%destructor { free ($$); } <str> +%type <ids> expr if_expr +%destructor { ids__free($$.ids); } <ids> %{ static void expr_error(double *final_val __maybe_unused, struct expr_parse_ctx *ctx __maybe_unused, + bool compute_ids __maybe_unused, void *scanner, const char *s) { pr_debug("%s\n", s); } +/* + * During compute ids, the special "bottom" value uses NAN to represent the set + * of all values. NAN is selected as it isn't a useful constant value. + */ +#define BOTTOM NAN + +/* During computing ids, does val represent a constant (non-BOTTOM) value? */ +static bool is_const(double val) +{ + return isfinite(val); +} + +static struct ids union_expr(struct ids ids1, struct ids ids2) +{ + struct ids result = { + .val = BOTTOM, + .ids = ids__union(ids1.ids, ids2.ids), + }; + return result; +} + +static struct ids handle_id(struct expr_parse_ctx *ctx, char *id, + bool compute_ids, bool source_count) +{ + struct ids result; + + if (!compute_ids) { + /* + * Compute the event's value from ID. If the ID isn't known then + * it isn't used to compute the formula so set to NAN. + */ + struct expr_id_data *data; + + result.val = NAN; + if (expr__resolve_id(ctx, id, &data) == 0) { + result.val = source_count + ? expr_id_data__source_count(data) + : expr_id_data__value(data); + } + result.ids = NULL; + free(id); + } else { + /* + * Set the value to BOTTOM to show that any value is possible + * when the event is computed. Create a set of just the ID. + */ + result.val = BOTTOM; + result.ids = ids__new(); + if (!result.ids || ids__insert(result.ids, id)) { + pr_err("Error creating IDs for '%s'", id); + free(id); + } + } + return result; +} + +/* + * If we're not computing ids or $1 and $3 are constants, compute the new + * constant value using OP. Its invariant that there are no ids. If computing + * ids for non-constants union the set of IDs that must be computed. + */ +#define BINARY_LONG_OP(RESULT, OP, LHS, RHS) \ + if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \ + assert(LHS.ids == NULL); \ + assert(RHS.ids == NULL); \ + RESULT.val = (long)LHS.val OP (long)RHS.val; \ + RESULT.ids = NULL; \ + } else { \ + RESULT = union_expr(LHS, RHS); \ + } + +#define BINARY_OP(RESULT, OP, LHS, RHS) \ + if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \ + assert(LHS.ids == NULL); \ + assert(RHS.ids == NULL); \ + RESULT.val = LHS.val OP RHS.val; \ + RESULT.ids = NULL; \ + } else { \ + RESULT = union_expr(LHS, RHS); \ + } + %} %% -start: -EXPR_PARSE all_expr -| -EXPR_OTHER all_other +start: if_expr +{ + if (compute_ids) + ctx->ids = ids__union($1.ids, ctx->ids); + + if (final_val) + *final_val = $1.val; +} +; -all_other: all_other other -| +if_expr: expr IF expr ELSE expr +{ + if (fpclassify($3.val) == FP_ZERO) { + /* + * The IF expression evaluated to 0 so treat as false, take the + * ELSE and discard everything else. + */ + $$.val = $5.val; + $$.ids = $5.ids; + ids__free($1.ids); + ids__free($3.ids); + } else if (!compute_ids || is_const($3.val)) { + /* + * If ids aren't computed then treat the expression as true. If + * ids are being computed and the IF expr is a non-zero + * constant, then also evaluate the true case. + */ + $$.val = $1.val; + $$.ids = $1.ids; + ids__free($3.ids); + ids__free($5.ids); + } else if ($1.val == $5.val) { + /* + * LHS == RHS, so both are an identical constant. No need to + * evaluate any events. + */ + $$.val = $1.val; + $$.ids = NULL; + ids__free($1.ids); + ids__free($3.ids); + ids__free($5.ids); + } else { + /* + * Value is either the LHS or RHS and we need the IF expression + * to compute it. + */ + $$ = union_expr($1, union_expr($3, $5)); + } +} +| expr +; -other: ID +expr: NUMBER +{ + $$.val = $1; + $$.ids = NULL; +} +| ID { $$ = handle_id(ctx, $1, compute_ids, /*source_count=*/false); } +| SOURCE_COUNT '(' ID ')' { $$ = handle_id(ctx, $3, compute_ids, /*source_count=*/true); } +| expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); } +| expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); } +| expr '^' expr { BINARY_LONG_OP($$, ^, $1, $3); } +| expr '<' expr { BINARY_OP($$, <, $1, $3); } +| expr '>' expr { BINARY_OP($$, >, $1, $3); } +| expr '+' expr { BINARY_OP($$, +, $1, $3); } +| expr '-' expr { BINARY_OP($$, -, $1, $3); } +| expr '*' expr { BINARY_OP($$, *, $1, $3); } +| expr '/' expr +{ + if (fpclassify($3.val) == FP_ZERO) { + pr_debug("division by zero\n"); + YYABORT; + } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { + assert($1.ids == NULL); + assert($3.ids == NULL); + $$.val = $1.val / $3.val; + $$.ids = NULL; + } else { + /* LHS and/or RHS need computing from event IDs so union. */ + $$ = union_expr($1, $3); + } +} +| expr '%' expr +{ + if (fpclassify($3.val) == FP_ZERO) { + pr_debug("division by zero\n"); + YYABORT; + } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { + assert($1.ids == NULL); + assert($3.ids == NULL); + $$.val = (long)$1.val % (long)$3.val; + $$.ids = NULL; + } else { + /* LHS and/or RHS need computing from event IDs so union. */ + $$ = union_expr($1, $3); + } +} +| D_RATIO '(' expr ',' expr ')' +{ + if (fpclassify($5.val) == FP_ZERO) { + /* + * Division by constant zero always yields zero and no events + * are necessary. + */ + assert($5.ids == NULL); + $$.val = 0.0; + $$.ids = NULL; + ids__free($3.ids); + } else if (!compute_ids || (is_const($3.val) && is_const($5.val))) { + assert($3.ids == NULL); + assert($5.ids == NULL); + $$.val = $3.val / $5.val; + $$.ids = NULL; + } else { + /* LHS and/or RHS need computing from event IDs so union. */ + $$ = union_expr($3, $5); + } +} +| '-' expr %prec NEG +{ + $$.val = -$2.val; + $$.ids = $2.ids; +} +| '(' if_expr ')' { - expr__add_id(ctx, $1); -} -| -MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/' | '%' | '(' | ')' | ',' -| -'<' | '>' | D_RATIO - -all_expr: if_expr { *final_val = $1; } - ; - -if_expr: - expr IF expr ELSE expr { $$ = $3 ? $1 : $5; } - | expr - ; - -expr: NUMBER - | ID { - struct expr_id_data *data; - - if (expr__resolve_id(ctx, $1, &data)) { - free($1); - YYABORT; - } - - $$ = expr_id_data__value(data); - free($1); - } - | expr '|' expr { $$ = (long)$1 | (long)$3; } - | expr '&' expr { $$ = (long)$1 & (long)$3; } - | expr '^' expr { $$ = (long)$1 ^ (long)$3; } - | expr '<' expr { $$ = $1 < $3; } - | expr '>' expr { $$ = $1 > $3; } - | expr '+' expr { $$ = $1 + $3; } - | expr '-' expr { $$ = $1 - $3; } - | expr '*' expr { $$ = $1 * $3; } - | expr '/' expr { if ($3 == 0) { - pr_debug("division by zero\n"); - YYABORT; - } - $$ = $1 / $3; - } - | expr '%' expr { if ((long)$3 == 0) { - pr_debug("division by zero\n"); - YYABORT; - } - $$ = (long)$1 % (long)$3; - } - | '-' expr %prec NEG { $$ = -$2; } - | '(' if_expr ')' { $$ = $2; } - | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; } - | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; } - | SMT_ON { $$ = smt_on() > 0; } - | D_RATIO '(' expr ',' expr ')' { $$ = d_ratio($3,$5); } - ; + $$ = $2; +} +| MIN '(' expr ',' expr ')' +{ + if (!compute_ids) { + $$.val = $3.val < $5.val ? $3.val : $5.val; + $$.ids = NULL; + } else { + $$ = union_expr($3, $5); + } +} +| MAX '(' expr ',' expr ')' +{ + if (!compute_ids) { + $$.val = $3.val > $5.val ? $3.val : $5.val; + $$.ids = NULL; + } else { + $$ = union_expr($3, $5); + } +} +| LITERAL +{ + $$.val = $1; + $$.ids = NULL; +} +; %% diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h new file mode 100644 index 000000000000..887f68a185f7 --- /dev/null +++ b/tools/perf/util/ftrace.h @@ -0,0 +1,81 @@ +#ifndef __PERF_FTRACE_H__ +#define __PERF_FTRACE_H__ + +#include <linux/list.h> + +#include "target.h" + +struct evlist; + +struct perf_ftrace { + struct evlist *evlist; + struct target target; + const char *tracer; + struct list_head filters; + struct list_head notrace; + struct list_head graph_funcs; + struct list_head nograph_funcs; + unsigned long percpu_buffer_size; + bool inherit; + int graph_depth; + int func_stack_trace; + int func_irq_info; + int graph_nosleep_time; + int graph_noirqs; + int graph_verbose; + int graph_thresh; + unsigned int initial_delay; +}; + +struct filter_entry { + struct list_head list; + char name[]; +}; + +#define NUM_BUCKET 22 /* 20 + 2 (for outliers in both direction) */ + +#ifdef HAVE_BPF_SKEL + +int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace); +int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace); +int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace); +int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace, + int buckets[]); +int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace); + +#else /* !HAVE_BPF_SKEL */ + +static inline int +perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, + int buckets[] __maybe_unused) +{ + return -1; +} + +static inline int +perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused) +{ + return -1; +} + +#endif /* HAVE_BPF_SKEL */ + +#endif /* __PERF_FTRACE_H__ */ diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index d4137559be05..3db3293213a9 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -42,7 +42,7 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #error "unsupported architecture" #endif -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ #define GEN_ELF_ENDIAN ELFDATA2MSB #else #define GEN_ELF_ENDIAN ELFDATA2LSB diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 1c7414f66655..6da12e522edc 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -48,6 +48,7 @@ #include "util/util.h" // perf_exe() #include "cputopo.h" #include "bpf-event.h" +#include "bpf-utils.h" #include "clockid.h" #include "pmu-hybrid.h" @@ -471,7 +472,7 @@ static int write_nrcpus(struct feat_fd *ff, u32 nrc, nra; int ret; - nrc = cpu__max_present_cpu(); + nrc = cpu__max_present_cpu().cpu; nr = sysconf(_SC_NPROCESSORS_ONLN); if (nr < 0) @@ -582,21 +583,21 @@ static int write_cpu_topology(struct feat_fd *ff, if (!tp) return -1; - ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib)); + ret = do_write(ff, &tp->package_cpus_lists, sizeof(tp->package_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->core_sib; i++) { - ret = do_write_string(ff, tp->core_siblings[i]); + for (i = 0; i < tp->package_cpus_lists; i++) { + ret = do_write_string(ff, tp->package_cpus_list[i]); if (ret < 0) goto done; } - ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib)); + ret = do_write(ff, &tp->core_cpus_lists, sizeof(tp->core_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->thread_sib; i++) { - ret = do_write_string(ff, tp->thread_siblings[i]); + for (i = 0; i < tp->core_cpus_lists; i++) { + ret = do_write_string(ff, tp->core_cpus_list[i]); if (ret < 0) break; } @@ -616,15 +617,15 @@ static int write_cpu_topology(struct feat_fd *ff, return ret; } - if (!tp->die_sib) + if (!tp->die_cpus_lists) goto done; - ret = do_write(ff, &tp->die_sib, sizeof(tp->die_sib)); + ret = do_write(ff, &tp->die_cpus_lists, sizeof(tp->die_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->die_sib; i++) { - ret = do_write_string(ff, tp->die_siblings[i]); + for (i = 0; i < tp->die_cpus_lists; i++) { + ret = do_write_string(ff, tp->die_cpus_list[i]); if (ret < 0) goto done; } @@ -1006,17 +1007,17 @@ static int write_bpf_prog_info(struct feat_fd *ff, node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); - len = sizeof(struct bpf_prog_info_linear) + + len = sizeof(struct perf_bpil) + node->info_linear->data_len; /* before writing to file, translate address to offset */ - bpf_program__bpil_addr_to_offs(node->info_linear); + bpil_addr_to_offs(node->info_linear); ret = do_write(ff, node->info_linear, len); /* * translate back to address even when do_write() fails, * so that this function never changes the data. */ - bpf_program__bpil_offs_to_addr(node->info_linear); + bpil_offs_to_addr(node->info_linear); if (ret < 0) goto out; } @@ -1162,7 +1163,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp) u32 nr, cpu; u16 level; - nr = cpu__max_cpu(); + nr = cpu__max_cpu().cpu; for (cpu = 0; cpu < nr; cpu++) { for (level = 0; level < MAX_CACHE_LVL; level++) { @@ -1194,7 +1195,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp) static int write_cache(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { - u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL; + u32 max_caches = cpu__max_cpu().cpu * MAX_CACHE_LVL; struct cpu_cache_level caches[max_caches]; u32 cnt = 0, i, version = 1; int ret; @@ -2320,6 +2321,7 @@ out: #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ {\ + free(ff->ph->env.__feat_env); \ ff->ph->env.__feat_env = do_read_string(ff); \ return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } @@ -3018,9 +3020,9 @@ static int process_dir_format(struct feat_fd *ff, #ifdef HAVE_LIBBPF_SUPPORT static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_info_node *info_node; struct perf_env *env = &ff->ph->env; + struct perf_bpil *info_linear; u32 count, i; int err = -1; @@ -3049,7 +3051,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) goto out; } - info_linear = malloc(sizeof(struct bpf_prog_info_linear) + + info_linear = malloc(sizeof(struct perf_bpil) + data_len); if (!info_linear) goto out; @@ -3071,7 +3073,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) goto out; /* after reading from file, translate offset to address */ - bpf_program__bpil_offs_to_addr(info_linear); + bpil_offs_to_addr(info_linear); info_node->info_linear = info_linear; perf_env__insert_bpf_prog_info(env, info_node); } @@ -4123,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session, struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; int type = fe->header.type; u64 feat = fe->feat_id; + int ret = 0; if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { pr_warning("invalid record type %d in pipe-mode\n", type); @@ -4140,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session, ff.size = event->header.size - sizeof(*fe); ff.ph = &session->header; - if (feat_ops[feat].process(&ff, NULL)) - return -1; + if (feat_ops[feat].process(&ff, NULL)) { + ret = -1; + goto out; + } if (!feat_ops[feat].print || !tool->show_feat_hdr) - return 0; + goto out; if (!feat_ops[feat].full_only || tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { @@ -4153,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session, fprintf(stdout, "# %s info available, use -I to display\n", feat_ops[feat].name); } - - return 0; +out: + free_event_desc(ff.events); + return ret; } size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) @@ -4256,9 +4262,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, switch (ev->type) { case PERF_EVENT_UPDATE__UNIT: + free((char *)evsel->unit); evsel->unit = strdup(ev->data); break; case PERF_EVENT_UPDATE__NAME: + free(evsel->name); evsel->name = strdup(ev->data); break; case PERF_EVENT_UPDATE__SCALE: @@ -4267,11 +4275,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, break; case PERF_EVENT_UPDATE__CPUS: ev_cpus = (struct perf_record_event_update_cpus *)ev->data; - map = cpu_map__new_data(&ev_cpus->cpus); - if (map) + if (map) { + perf_cpu_map__put(evsel->core.own_cpus); evsel->core.own_cpus = map; - else + } else pr_err("failed to get event_update cpus\n"); default: break; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 65fe65ba03c2..0a8033b09e28 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10); hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13); hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13); - hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13); + hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13); + hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13); + if (symbol_conf.nanosecs) hists__new_col_len(hists, HISTC_TIME, 16); else @@ -289,15 +291,10 @@ static long hist_time(unsigned long htime) return htime; } -static void he_stat__add_period(struct he_stat *he_stat, u64 period, - u64 weight, u64 ins_lat, u64 p_stage_cyc) +static void he_stat__add_period(struct he_stat *he_stat, u64 period) { - he_stat->period += period; - he_stat->weight += weight; he_stat->nr_events += 1; - he_stat->ins_lat += ins_lat; - he_stat->p_stage_cyc += p_stage_cyc; } static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) @@ -308,9 +305,6 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->period_guest_sys += src->period_guest_sys; dest->period_guest_us += src->period_guest_us; dest->nr_events += src->nr_events; - dest->weight += src->weight; - dest->ins_lat += src->ins_lat; - dest->p_stage_cyc += src->p_stage_cyc; } static void he_stat__decay(struct he_stat *he_stat) @@ -598,9 +592,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, struct hist_entry *he; int64_t cmp; u64 period = entry->stat.period; - u64 weight = entry->stat.weight; - u64 ins_lat = entry->stat.ins_lat; - u64 p_stage_cyc = entry->stat.p_stage_cyc; bool leftmost = true; p = &hists->entries_in->rb_root.rb_node; @@ -619,11 +610,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (!cmp) { if (sample_self) { - he_stat__add_period(&he->stat, period, weight, ins_lat, p_stage_cyc); + he_stat__add_period(&he->stat, period); hist_entry__add_callchain_period(he, period); } if (symbol_conf.cumulate_callchain) - he_stat__add_period(he->stat_acc, period, weight, ins_lat, p_stage_cyc); + he_stat__add_period(he->stat_acc, period); /* * This mem info was allocated from sample__resolve_mem @@ -733,9 +724,6 @@ __hists__add_entry(struct hists *hists, .stat = { .nr_events = 1, .period = sample->period, - .weight = sample->weight, - .ins_lat = sample->ins_lat, - .p_stage_cyc = sample->p_stage_cyc, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent) | al->filtered, @@ -748,6 +736,9 @@ __hists__add_entry(struct hists *hists, .raw_size = sample->raw_size, .ops = ops, .time = hist_time(sample->time), + .weight = sample->weight, + .ins_lat = sample->ins_lat, + .p_stage_cyc = sample->p_stage_cyc, }, *he = hists__findnew_entry(hists, &entry, al, sample_self); if (!hists->has_callchains && he && he->callchain_size != 0) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 5343b62476e6..2a15e22fb89c 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -75,7 +75,8 @@ enum hist_column { HISTC_MEM_BLOCKED, HISTC_LOCAL_INS_LAT, HISTC_GLOBAL_INS_LAT, - HISTC_P_STAGE_CYC, + HISTC_LOCAL_P_STAGE_CYC, + HISTC_GLOBAL_P_STAGE_CYC, HISTC_NR_COLS, /* Last entry */ }; @@ -369,7 +370,6 @@ enum { }; void perf_hpp__init(void); -void perf_hpp__column_unregister(struct perf_hpp_fmt *format); void perf_hpp__cancel_cumulate(void); void perf_hpp__setup_output_field(struct perf_hpp_list *list); void perf_hpp__reset_output_field(struct perf_hpp_list *list); diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index af1e78d76228..2c8147a62203 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -35,7 +35,7 @@ #define INTEL_BTS_ERR_NOINSN 5 #define INTEL_BTS_ERR_LOST 9 -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ #define le64_to_cpu bswap_64 #else #define le64_to_cpu diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index bc629359826f..b41c2e9c6f88 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -18,3 +18,5 @@ CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder ifeq ($(CC_NO_CLANG), 1) CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init endif + +CFLAGS_intel-pt-insn-decoder.o += -Wno-packed 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 5ab631702769..0e013c2d9eb4 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -608,6 +608,7 @@ static inline void intel_pt_update_sample_time(struct intel_pt_decoder *decoder) { decoder->sample_timestamp = decoder->timestamp; decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + decoder->state.cycles = decoder->tot_cyc_cnt; } static void intel_pt_reposition(struct intel_pt_decoder *decoder) @@ -1204,61 +1205,69 @@ out_no_progress: static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) { + enum intel_pt_sample_type type = decoder->state.type; bool ret = false; + decoder->state.type &= ~INTEL_PT_BRANCH; + 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.type |= INTEL_PT_TRANSACTION; if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX) decoder->state.type |= INTEL_PT_BRANCH; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; decoder->state.flags = decoder->fup_tx_flags; - return true; + ret = true; } if (decoder->set_fup_ptw) { decoder->set_fup_ptw = false; - decoder->state.type = INTEL_PT_PTW; + 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; + ret = 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.type |= INTEL_PT_MWAIT_OP; 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; } if (decoder->set_fup_bep) { decoder->set_fup_bep = false; decoder->state.type |= INTEL_PT_BLK_ITEMS; - decoder->state.type &= ~INTEL_PT_BRANCH; + ret = true; + } + if (decoder->overflow) { + decoder->overflow = false; + if (!ret && !decoder->pge) { + if (decoder->hop) { + decoder->state.type = 0; + decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; + } + decoder->pge = true; + decoder->state.type |= INTEL_PT_BRANCH | INTEL_PT_TRACE_BEGIN; + decoder->state.from_ip = 0; + decoder->state.to_ip = decoder->ip; + return true; + } + } + if (ret) { decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; - ret = true; + } else { + decoder->state.type = type; } return ret; } @@ -1607,7 +1616,16 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder) intel_pt_clear_tx_flags(decoder); intel_pt_set_nr(decoder); decoder->timestamp_insn_cnt = 0; - decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->state.from_ip = decoder->ip; + decoder->ip = 0; + decoder->pge = false; + 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; + decoder->set_fup_bep = false; decoder->overflow = true; return -EOVERFLOW; } @@ -2665,6 +2683,8 @@ static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder); /* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err) { + *err = 0; + /* Leap from PSB to PSB, getting ip from FUP within PSB+ */ if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) { *err = intel_pt_scan_for_psb(decoder); @@ -2677,6 +2697,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in return HOP_IGNORE; case INTEL_PT_TIP_PGD: + decoder->pge = false; if (!decoder->packet.count) { intel_pt_set_nr(decoder); return HOP_IGNORE; @@ -2704,18 +2725,21 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in if (!decoder->packet.count) return HOP_IGNORE; intel_pt_set_ip(decoder); - if (intel_pt_fup_event(decoder)) - return HOP_RETURN; - if (!decoder->branch_enable) + if (decoder->set_fup_mwait || decoder->set_fup_pwre) + *no_tip = true; + if (!decoder->branch_enable || !decoder->pge) *no_tip = true; if (*no_tip) { decoder->state.type = INTEL_PT_INSTRUCTION; decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; + intel_pt_fup_event(decoder); return HOP_RETURN; } + intel_pt_fup_event(decoder); + decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH; *err = intel_pt_walk_fup_tip(decoder); - if (!*err) + if (!*err && decoder->state.to_ip) decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; return HOP_RETURN; @@ -2896,7 +2920,7 @@ static bool intel_pt_psb_with_fup(struct intel_pt_decoder *decoder, int *err) { struct intel_pt_psb_info data = { .fup = false }; - if (!decoder->branch_enable || !decoder->pge) + if (!decoder->branch_enable) return false; intel_pt_pkt_lookahead(decoder, intel_pt_psb_lookahead_cb, &data); @@ -2923,6 +2947,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder) if (err) return err; next: + err = 0; if (decoder->cyc_threshold) { if (decoder->sample_cyc && last_packet_type != INTEL_PT_CYC) decoder->sample_cyc = false; @@ -2961,6 +2986,7 @@ next: case INTEL_PT_TIP_PGE: { decoder->pge = true; + decoder->overflow = false; intel_pt_mtc_cyc_cnt_pge(decoder); intel_pt_set_nr(decoder); if (decoder->packet.count == 0) { @@ -2998,7 +3024,7 @@ next: break; } intel_pt_set_last_ip(decoder); - if (!decoder->branch_enable) { + if (!decoder->branch_enable || !decoder->pge) { decoder->ip = decoder->last_ip; if (intel_pt_fup_event(decoder)) return 0; @@ -3466,10 +3492,10 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) decoder->set_fup_pwre = false; decoder->set_fup_exstop = false; decoder->set_fup_bep = false; + decoder->overflow = 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; } @@ -3484,7 +3510,6 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - decoder->overflow = false; decoder->state.from_ip = 0; decoder->state.to_ip = decoder->ip; @@ -3606,7 +3631,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) } decoder->have_last_ip = true; - decoder->pkt_state = INTEL_PT_STATE_NO_IP; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_psb(decoder); if (err) @@ -3703,7 +3728,8 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) if (err) { decoder->state.err = intel_pt_ext_err(err); - decoder->state.from_ip = decoder->ip; + if (err != -EOVERFLOW) + decoder->state.from_ip = decoder->ip; intel_pt_update_sample_time(decoder); decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt; intel_pt_set_nr(decoder); 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 4b5e79fcf557..8fd68f7a0963 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -218,6 +218,7 @@ struct intel_pt_state { uint64_t to_ip; uint64_t tot_insn_cnt; uint64_t tot_cyc_cnt; + uint64_t cycles; uint64_t timestamp; uint64_t est_timestamp; uint64_t trace_nr; 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 593f20e9774c..9d5e65cec89b 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 @@ -143,7 +143,7 @@ static void intel_pt_insn_decoder(struct insn *insn, if (branch == INTEL_PT_BR_CONDITIONAL || branch == INTEL_PT_BR_UNCONDITIONAL) { -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ switch (insn->immediate.nbytes) { case 1: intel_pt_insn->rel = insn->immediate.value; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index 09feb5b07d32..5f5dfc8753f3 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -82,10 +82,10 @@ static int intel_pt_log_open(void) if (f) return 0; - if (!log_name[0]) - return -1; - - f = fopen(log_name, "w+"); + if (log_name[0]) + f = fopen(log_name, "w+"); + else + f = stdout; if (!f) { intel_pt_enable_logging = false; return -1; 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 02a3395d6ce3..4bd154848cad 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 @@ -16,7 +16,7 @@ #define BIT63 ((uint64_t)1 << 63) -#if __BYTE_ORDER == __BIG_ENDIAN +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ #define le16_to_cpu bswap_16 #define le32_to_cpu bswap_32 #define le64_to_cpu bswap_64 diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 6f852b305e92..e8613cbda331 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -111,6 +111,7 @@ struct intel_pt { u64 cbr_id; u64 psb_id; + bool single_pebs; bool sample_pebs; struct evsel *pebs_evsel; @@ -148,6 +149,14 @@ enum switch_state { INTEL_PT_SS_EXPECTING_SWITCH_IP, }; +/* applicable_counters is 64-bits */ +#define INTEL_PT_MAX_PEBS 64 + +struct intel_pt_pebs_event { + struct evsel *evsel; + u64 id; +}; + struct intel_pt_queue { struct intel_pt *pt; unsigned int queue_nr; @@ -163,6 +172,7 @@ struct intel_pt_queue { bool step_through_buffers; bool use_buffer_pid_tid; bool sync_switch; + bool sample_ipc; pid_t pid, tid; int cpu; int switch_state; @@ -189,6 +199,7 @@ struct intel_pt_queue { u64 last_br_cyc_cnt; unsigned int cbr_seen; char insn[INTEL_PT_INSN_BUF_SZ]; + struct intel_pt_pebs_event pebs[INTEL_PT_MAX_PEBS]; }; static void intel_pt_dump(struct intel_pt *pt __maybe_unused, @@ -1571,7 +1582,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) sample.branch_stack = (struct branch_stack *)&dummy_bs; } - if (ptq->state->flags & INTEL_PT_SAMPLE_IPC) + if (ptq->sample_ipc) sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_br_cyc_cnt; if (sample.cyc_cnt) { sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_br_insn_cnt; @@ -1622,7 +1633,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) else sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; - if (ptq->state->flags & INTEL_PT_SAMPLE_IPC) + if (ptq->sample_ipc) sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_cnt; if (sample.cyc_cnt) { sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_in_insn_cnt; @@ -1978,15 +1989,13 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack, } } -static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) +static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id) { const struct intel_pt_blk_items *items = &ptq->state->items; struct perf_sample sample = { .ip = 0, }; union perf_event *event = ptq->event_buf; struct intel_pt *pt = ptq->pt; - struct evsel *evsel = pt->pebs_evsel; u64 sample_type = evsel->core.attr.sample_type; - u64 id = evsel->core.id[0]; u8 cpumode; u64 regs[8 * sizeof(sample.intr_regs.mask)]; @@ -2112,6 +2121,45 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) return intel_pt_deliver_synth_event(pt, event, &sample, sample_type); } +static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + struct evsel *evsel = pt->pebs_evsel; + u64 id = evsel->core.id[0]; + + return intel_pt_do_synth_pebs_sample(ptq, evsel, id); +} + +static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) +{ + const struct intel_pt_blk_items *items = &ptq->state->items; + struct intel_pt_pebs_event *pe; + struct intel_pt *pt = ptq->pt; + int err = -EINVAL; + int hw_id; + + if (!items->has_applicable_counters || !items->applicable_counters) { + if (!pt->single_pebs) + pr_err("PEBS-via-PT record with no applicable_counters\n"); + return intel_pt_synth_single_pebs_sample(ptq); + } + + for_each_set_bit(hw_id, (unsigned long *)&items->applicable_counters, INTEL_PT_MAX_PEBS) { + pe = &ptq->pebs[hw_id]; + if (!pe->evsel) { + if (!pt->single_pebs) + pr_err("PEBS-via-PT record with no matching event, hw_id %d\n", + hw_id); + return intel_pt_synth_single_pebs_sample(ptq); + } + err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id); + if (err) + return err; + } + + return err; +} + static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, pid_t pid, pid_t tid, u64 ip, u64 timestamp) { @@ -2198,8 +2246,15 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; - ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt; - ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt; + if (pt->synth_opts.approx_ipc) { + ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt; + ptq->ipc_cyc_cnt = ptq->state->cycles; + ptq->sample_ipc = true; + } else { + ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt; + ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt; + ptq->sample_ipc = ptq->state->flags & INTEL_PT_SAMPLE_IPC; + } /* * Do PEBS first to allow for the possibility that the PEBS timestamp @@ -2510,6 +2565,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) ptq->sync_switch = false; intel_pt_next_tid(pt, ptq); } + ptq->timestamp = state->est_timestamp; if (pt->synth_opts.errors) { err = intel_ptq_synth_error(ptq, state); if (err) @@ -2882,6 +2938,30 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt, event->itrace_start.tid); } +static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample) +{ + u64 hw_id = event->aux_output_hw_id.hw_id; + struct auxtrace_queue *queue; + struct intel_pt_queue *ptq; + struct evsel *evsel; + + queue = auxtrace_queues__sample_queue(&pt->queues, sample, pt->session); + evsel = evlist__id2evsel_strict(pt->session->evlist, sample->id); + if (!queue || !queue->priv || !evsel || hw_id > INTEL_PT_MAX_PEBS) { + pr_err("Bad AUX output hardware ID\n"); + return -EINVAL; + } + + ptq = queue->priv; + + ptq->pebs[hw_id].evsel = evsel; + ptq->pebs[hw_id].id = sample->id; + + return 0; +} + static int intel_pt_find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { @@ -3009,6 +3089,8 @@ static int intel_pt_process_event(struct perf_session *session, err = intel_pt_process_switch(pt, sample); else if (event->header.type == PERF_RECORD_ITRACE_START) err = intel_pt_process_itrace_start(pt, event, sample); + else if (event->header.type == PERF_RECORD_AUX_OUTPUT_HW_ID) + err = intel_pt_process_aux_output_hw_id(pt, event, sample); else if (event->header.type == PERF_RECORD_SWITCH || event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); @@ -3393,9 +3475,13 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt) evlist__for_each_entry(pt->session->evlist, evsel) { if (evsel->core.attr.aux_output && evsel->core.id) { + if (pt->single_pebs) { + pt->single_pebs = false; + return; + } + pt->single_pebs = true; pt->sample_pebs = true; pt->pebs_evsel = evsel; - return; } } } @@ -3539,6 +3625,7 @@ static int intel_pt_parse_vm_tm_corr_arg(struct intel_pt *pt, char **args) *args = p; return 0; } + p += 1; while (1) { vmcs = strtoull(p, &p, 0); if (errno) @@ -3651,8 +3738,6 @@ int intel_pt_process_auxtrace_info(union perf_event *event, if (err) goto err_free; - intel_pt_log_set_name(INTEL_PT_PMU_NAME); - if (session->itrace_synth_opts->set) { pt->synth_opts = *session->itrace_synth_opts; } else { @@ -3667,6 +3752,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event, pt->synth_opts.thread_stack = opts->thread_stack; } + if (!(pt->synth_opts.log_plus_flags & AUXTRACE_LOG_FLG_USE_STDOUT)) + intel_pt_log_set_name(INTEL_PT_PMU_NAME); + pt->session = session; pt->machine = &session->machines.host; /* No kvm support */ pt->auxtrace_type = auxtrace_info->type; diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index c397be0c2e32..15f60fd09424 100644 --- a/tools/perf/util/libunwind/arm64.c +++ b/tools/perf/util/libunwind/arm64.c @@ -23,7 +23,9 @@ #include "unwind.h" #include "libunwind-aarch64.h" +#define perf_event_arm_regs perf_event_arm64_regs #include <../../../../arch/arm64/include/uapi/asm/perf_regs.h> +#undef perf_event_arm_regs #include "../../arch/arm64/util/unwind-libunwind.c" /* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind, diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 44e40bad0e33..394550003693 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -16,6 +16,7 @@ #include "map_symbol.h" #include "branch.h" #include "mem-events.h" +#include "path.h" #include "srcline.h" #include "symbol.h" #include "sort.h" @@ -34,6 +35,7 @@ #include "bpf-event.h" #include <internal/lib.h> // page_size #include "cgroup.h" +#include "arm64-frame-pointer-unwind-support.h" #include <linux/ctype.h> #include <symbol/kallsyms.h> @@ -755,6 +757,14 @@ int machine__process_itrace_start_event(struct machine *machine __maybe_unused, return 0; } +int machine__process_aux_output_hw_id_event(struct machine *machine __maybe_unused, + union perf_event *event) +{ + if (dump_trace) + perf_event__fprintf_aux_output_hw_id(event, stdout); + return 0; +} + int machine__process_switch_event(struct machine *machine __maybe_unused, union perf_event *event) { @@ -1407,7 +1417,7 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i struct stat st; /*sshfs might return bad dent->d_type, so we have to stat*/ - snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name); + path__join(path, sizeof(path), dir_name, dent->d_name); if (stat(path, &st)) continue; @@ -2028,6 +2038,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret = machine__process_bpf(machine, event, sample); break; case PERF_RECORD_TEXT_POKE: ret = machine__process_text_poke(machine, event, sample); break; + case PERF_RECORD_AUX_OUTPUT_HW_ID: + ret = machine__process_aux_output_hw_id_event(machine, event); break; default: ret = -1; break; @@ -2061,6 +2073,7 @@ static void ip__resolve_ams(struct thread *thread, ams->addr = ip; ams->al_addr = al.addr; + ams->al_level = al.level; ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; @@ -2080,6 +2093,7 @@ static void ip__resolve_data(struct thread *thread, ams->addr = addr; ams->al_addr = al.addr; + ams->al_level = al.level; ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; @@ -2700,6 +2714,15 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread, return err; } +static u64 get_leaf_frame_caller(struct perf_sample *sample, + struct thread *thread, int usr_idx) +{ + if (machine__normalized_is(thread->maps->machine, "arm64")) + return get_leaf_frame_caller_aarch64(sample, thread, usr_idx); + else + return 0; +} + static int thread__resolve_callchain_sample(struct thread *thread, struct callchain_cursor *cursor, struct evsel *evsel, @@ -2713,9 +2736,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, struct ip_callchain *chain = sample->callchain; int chain_nr = 0; u8 cpumode = PERF_RECORD_MISC_USER; - int i, j, err, nr_entries; + int i, j, err, nr_entries, usr_idx; int skip_idx = -1; int first_call = 0; + u64 leaf_frame_caller; if (chain) chain_nr = chain->nr; @@ -2840,6 +2864,34 @@ check_calls: continue; } + /* + * PERF_CONTEXT_USER allows us to locate where the user stack ends. + * Depending on callchain_param.order and the position of PERF_CONTEXT_USER, + * the index will be different in order to add the missing frame + * at the right place. + */ + + usr_idx = callchain_param.order == ORDER_CALLEE ? j-2 : j-1; + + if (usr_idx >= 0 && chain->ips[usr_idx] == PERF_CONTEXT_USER) { + + leaf_frame_caller = get_leaf_frame_caller(sample, thread, usr_idx); + + /* + * check if leaf_frame_Caller != ip to not add the same + * value twice. + */ + + if (leaf_frame_caller && leaf_frame_caller != ip) { + + err = add_callchain_ip(thread, cursor, parent, + root_al, &cpumode, leaf_frame_caller, + false, NULL, NULL, 0); + if (err) + return (err < 0) ? err : 0; + } + } + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, false, NULL, NULL, 0); @@ -3069,14 +3121,19 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, } /* - * Compares the raw arch string. N.B. see instead perf_env__arch() if a - * normalized arch is needed. + * Compares the raw arch string. N.B. see instead perf_env__arch() or + * machine__normalized_is() if a normalized arch is needed. */ bool machine__is(struct machine *machine, const char *arch) { return machine && !strcmp(perf_env__raw_arch(machine->env), arch); } +bool machine__normalized_is(struct machine *machine, const char *arch) +{ + return machine && !strcmp(perf_env__arch(machine->env), arch); +} + int machine__nr_cpus_avail(struct machine *machine) { return machine ? perf_env__nr_cpus_avail(machine->env) : 0; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 7377ed6efdf1..c5a45dc8df4c 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -124,6 +124,8 @@ int machine__process_aux_event(struct machine *machine, union perf_event *event); int machine__process_itrace_start_event(struct machine *machine, union perf_event *event); +int machine__process_aux_output_hw_id_event(struct machine *machine, + union perf_event *event); int machine__process_switch_event(struct machine *machine, union perf_event *event); int machine__process_namespaces_event(struct machine *machine, @@ -206,6 +208,7 @@ static inline bool machine__is_host(struct machine *machine) } bool machine__is(struct machine *machine, const char *arch); +bool machine__normalized_is(struct machine *machine, const char *arch); int machine__nr_cpus_avail(struct machine *machine); struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 7d22ade082c8..e08817b0c30f 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -18,6 +18,7 @@ struct addr_map_symbol { struct map_symbol ms; u64 addr; u64 al_addr; + char al_level; u64 phys_addr; u64 data_page_size; }; diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index f0e75df72b80..ed0ab838bcc5 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -301,12 +301,25 @@ static const char * const mem_lvlnum[] = { [PERF_MEM_LVLNUM_NA] = "N/A", }; +static const char * const mem_hops[] = { + "N/A", + /* + * While printing, 'Remote' will be added to represent + * 'Remote core, same node' accesses as remote field need + * to be set with mem_hops field. + */ + "core, same node", + "node, same socket", + "socket, same board", + "board", +}; + int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) { size_t i, l = 0; u64 m = PERF_MEM_LVL_NA; u64 hit, miss; - int printed; + int printed = 0; if (mem_info) m = mem_info->data_src.mem_lvl; @@ -320,21 +333,27 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); - if (mem_info && mem_info->data_src.mem_remote) { strcat(out, "Remote "); l += 7; } - printed = 0; - for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { - if (!(m & 0x1)) - continue; - if (printed++) { - strcat(out, " or "); - l += 4; + /* + * Incase mem_hops field is set, we can skip printing data source via + * PERF_MEM_LVL namespace. + */ + if (mem_info && mem_info->data_src.mem_hops) { + l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]); + } else { + for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { + if (!(m & 0x1)) + continue; + if (printed++) { + strcat(out, " or "); + l += 4; + } + l += scnprintf(out + l, sz - l, mem_lvl[i]); } - l += scnprintf(out + l, sz - l, mem_lvl[i]); } if (mem_info && mem_info->data_src.mem_lvl_num) { @@ -472,8 +491,12 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) /* * Skylake might report unknown remote level via this * bit, consider it when evaluating remote HITMs. + * + * Incase of power, remote field can also be used to denote cache + * accesses from the another core of same node. Hence, setting + * mrem only when HOPS is zero along with set remote field. */ - bool mrem = data_src->mem_remote; + bool mrem = (data_src->mem_remote && !data_src->mem_hops); int err = 0; #define HITM_INC(__f) \ diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 29b747ac31c1..d8492e339521 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -11,6 +11,7 @@ #include "evsel.h" #include "strbuf.h" #include "pmu.h" +#include "pmu-hybrid.h" #include "expr.h" #include "rblist.h" #include <string.h> @@ -18,6 +19,7 @@ #include "strlist.h" #include <assert.h> #include <linux/ctype.h> +#include <linux/list_sort.h> #include <linux/string.h> #include <linux/zalloc.h> #include <subcmd/parse-options.h> @@ -84,6 +86,7 @@ static void metric_event_delete(struct rblist *rblist __maybe_unused, struct metric_expr *expr, *tmp; list_for_each_entry_safe(expr, tmp, &me->head, nd) { + free((char *)expr->metric_name); free(expr->metric_refs); free(expr->metric_events); free(expr); @@ -116,289 +119,207 @@ struct metric_ref_node { struct list_head list; }; +/** + * The metric under construction. The data held here will be placed in a + * metric_expr. + */ struct metric { struct list_head nd; - struct expr_parse_ctx pctx; + /** + * The expression parse context importantly holding the IDs contained + * within the expression. + */ + struct expr_parse_ctx *pctx; + /** The name of the metric such as "IPC". */ const char *metric_name; + /** Modifier on the metric such as "u" or NULL for none. */ + const char *modifier; + /** The expression to parse, for example, "instructions/cycles". */ const char *metric_expr; + /** + * The "ScaleUnit" that scales and adds a unit to the metric during + * output. + */ const char *metric_unit; - struct list_head metric_refs; - int metric_refs_cnt; - int runtime; + /** Optional null terminated array of referenced metrics. */ + struct metric_ref *metric_refs; + /** + * Is there a constraint on the group of events? In which case the + * events won't be grouped. + */ bool has_constraint; + /** + * Parsed events for the metric. Optional as events may be taken from a + * different metric whose group contains all the IDs necessary for this + * one. + */ + struct evlist *evlist; }; -#define RECURSION_ID_MAX 1000 +static void metricgroup___watchdog_constraint_hint(const char *name, bool foot) +{ + static bool violate_nmi_constraint; + + if (!foot) { + pr_warning("Splitting metric group %s into standalone metrics.\n", name); + violate_nmi_constraint = true; + return; + } -struct expr_ids { - struct expr_id id[RECURSION_ID_MAX]; - int cnt; -}; + if (!violate_nmi_constraint) + return; + + pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n" + " echo 0 > /proc/sys/kernel/nmi_watchdog\n" + " perf stat ...\n" + " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); +} -static struct expr_id *expr_ids__alloc(struct expr_ids *ids) +static bool metricgroup__has_constraint(const struct pmu_event *pe) { - if (ids->cnt >= RECURSION_ID_MAX) - return NULL; - return &ids->id[ids->cnt++]; + if (!pe->metric_constraint) + return false; + + if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") && + sysctl__nmi_watchdog_enabled()) { + metricgroup___watchdog_constraint_hint(pe->metric_name, false); + return true; + } + + return false; } -static void expr_ids__exit(struct expr_ids *ids) +static struct metric *metric__new(const struct pmu_event *pe, + const char *modifier, + bool metric_no_group, + int runtime) { - int i; + struct metric *m; + + m = zalloc(sizeof(*m)); + if (!m) + return NULL; - for (i = 0; i < ids->cnt; i++) - free(ids->id[i].id); + m->pctx = expr__ctx_new(); + if (!m->pctx) { + free(m); + return NULL; + } + + m->metric_name = pe->metric_name; + m->modifier = modifier ? strdup(modifier) : NULL; + if (modifier && !m->modifier) { + expr__ctx_free(m->pctx); + free(m); + return NULL; + } + m->metric_expr = pe->metric_expr; + m->metric_unit = pe->unit; + m->pctx->runtime = runtime; + m->has_constraint = metric_no_group || metricgroup__has_constraint(pe); + m->metric_refs = NULL; + m->evlist = NULL; + + return m; } -static bool contains_event(struct evsel **metric_events, int num_events, - const char *event_name) +static void metric__free(struct metric *m) +{ + free(m->metric_refs); + expr__ctx_free(m->pctx); + free((char *)m->modifier); + evlist__delete(m->evlist); + free(m); +} + +static bool contains_metric_id(struct evsel **metric_events, int num_events, + const char *metric_id) { int i; for (i = 0; i < num_events; i++) { - if (!strcmp(metric_events[i]->name, event_name)) + if (!strcmp(evsel__metric_id(metric_events[i]), metric_id)) return true; } return false; } -static bool evsel_same_pmu_or_none(struct evsel *ev1, struct evsel *ev2) -{ - if (!ev1->pmu_name || !ev2->pmu_name) - return true; - - return !strcmp(ev1->pmu_name, ev2->pmu_name); -} - /** - * Find a group of events in perf_evlist that correspond to those from a parsed - * metric expression. Note, as find_evsel_group is called in the same order as - * perf_evlist was constructed, metric_no_merge doesn't need to test for - * underfilling a group. - * @perf_evlist: a list of events something like: {metric1 leader, metric1 - * sibling, metric1 sibling}:W,duration_time,{metric2 leader, metric2 sibling, - * metric2 sibling}:W,duration_time - * @pctx: the parse context for the metric expression. - * @metric_no_merge: don't attempt to share events for the metric with other - * metrics. - * @has_constraint: is there a constraint on the group of events? In which case - * the events won't be grouped. - * @metric_events: out argument, null terminated array of evsel's associated - * with the metric. - * @evlist_used: in/out argument, bitmap tracking which evlist events are used. - * @return the first metric event or NULL on failure. + * setup_metric_events - Find a group of events in metric_evlist that correspond + * to the IDs from a parsed metric expression. + * @ids: the metric IDs to match. + * @metric_evlist: the list of perf events. + * @out_metric_events: holds the created metric events array. */ -static struct evsel *find_evsel_group(struct evlist *perf_evlist, - struct expr_parse_ctx *pctx, - bool metric_no_merge, - bool has_constraint, - struct evsel **metric_events, - unsigned long *evlist_used) +static int setup_metric_events(struct hashmap *ids, + struct evlist *metric_evlist, + struct evsel ***out_metric_events) { - struct evsel *ev, *current_leader = NULL; - struct expr_id_data *val_ptr; - int i = 0, matched_events = 0, events_to_match; - const int idnum = (int)hashmap__size(&pctx->ids); + struct evsel **metric_events; + const char *metric_id; + struct evsel *ev; + size_t ids_size, matched_events, i; - /* - * duration_time is always grouped separately, when events are grouped - * (ie has_constraint is false) then ignore it in the matching loop and - * add it to metric_events at the end. - */ - if (!has_constraint && - hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr)) - events_to_match = idnum - 1; - else - events_to_match = idnum; + *out_metric_events = NULL; + ids_size = hashmap__size(ids); + + metric_events = calloc(sizeof(void *), ids_size + 1); + if (!metric_events) + return -ENOMEM; + + matched_events = 0; + evlist__for_each_entry(metric_evlist, ev) { + struct expr_id_data *val_ptr; - evlist__for_each_entry (perf_evlist, ev) { /* - * Events with a constraint aren't grouped and match the first - * events available. + * Check for duplicate events with the same name. For + * example, uncore_imc/cas_count_read/ will turn into 6 + * events per socket on skylakex. Only the first such + * event is placed in metric_events. */ - if (has_constraint && ev->weak_group) - continue; - /* Ignore event if already used and merging is disabled. */ - if (metric_no_merge && test_bit(ev->core.idx, evlist_used)) + metric_id = evsel__metric_id(ev); + if (contains_metric_id(metric_events, matched_events, metric_id)) continue; - if (!has_constraint && !evsel__has_leader(ev, current_leader)) { - /* - * Start of a new group, discard the whole match and - * start again. - */ - matched_events = 0; - memset(metric_events, 0, - sizeof(struct evsel *) * idnum); - current_leader = evsel__leader(ev); - } /* - * Check for duplicate events with the same name. For example, - * uncore_imc/cas_count_read/ will turn into 6 events per socket - * on skylakex. Only the first such event is placed in - * metric_events. If events aren't grouped then this also - * ensures that the same event in different sibling groups - * aren't both added to metric_events. + * Does this event belong to the parse context? For + * combined or shared groups, this metric may not care + * about this event. */ - if (contains_event(metric_events, matched_events, ev->name)) - continue; - /* Does this event belong to the parse context? */ - if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) + if (hashmap__find(ids, metric_id, (void **)&val_ptr)) { metric_events[matched_events++] = ev; - if (matched_events == events_to_match) - break; - } - - if (events_to_match != idnum) { - /* Add the first duration_time. */ - evlist__for_each_entry(perf_evlist, ev) { - if (!strcmp(ev->name, "duration_time")) { - metric_events[matched_events++] = ev; + if (matched_events >= ids_size) break; - } } } - - if (matched_events != idnum) { - /* Not a whole match */ - return NULL; + if (matched_events < ids_size) { + free(metric_events); + return -EINVAL; } - - metric_events[idnum] = NULL; - - for (i = 0; i < idnum; i++) { + for (i = 0; i < ids_size; i++) { ev = metric_events[i]; - /* Don't free the used events. */ - set_bit(ev->core.idx, evlist_used); + ev->collect_stat = true; + /* - * The metric leader points to the identically named event in - * metric_events. + * The metric leader points to the identically named + * event in metric_events. */ ev->metric_leader = ev; /* - * Mark two events with identical names in the same group (or - * globally) as being in use as uncore events may be duplicated - * for each pmu. Set the metric leader of such events to be the - * event that appears in metric_events. + * Mark two events with identical names in the same + * group (or globally) as being in use as uncore events + * may be duplicated for each pmu. Set the metric leader + * of such events to be the event that appears in + * metric_events. */ - evlist__for_each_entry_continue(perf_evlist, ev) { - /* - * If events are grouped then the search can terminate - * when then group is left. - */ - if (!has_constraint && - ev->core.leader != metric_events[i]->core.leader && - evsel_same_pmu_or_none(evsel__leader(ev), evsel__leader(metric_events[i]))) - break; - if (!strcmp(metric_events[i]->name, ev->name)) { - set_bit(ev->core.idx, evlist_used); + metric_id = evsel__metric_id(ev); + evlist__for_each_entry_continue(metric_evlist, ev) { + if (!strcmp(evsel__metric_id(ev), metric_id)) ev->metric_leader = metric_events[i]; - } - } - } - - return metric_events[0]; -} - -static int metricgroup__setup_events(struct list_head *groups, - bool metric_no_merge, - struct evlist *perf_evlist, - struct rblist *metric_events_list) -{ - struct metric_event *me; - struct metric_expr *expr; - int i = 0; - int ret = 0; - struct metric *m; - struct evsel *evsel, *tmp; - unsigned long *evlist_used; - - evlist_used = bitmap_zalloc(perf_evlist->core.nr_entries); - if (!evlist_used) - return -ENOMEM; - - list_for_each_entry (m, groups, nd) { - struct evsel **metric_events; - struct metric_ref *metric_refs = NULL; - - metric_events = calloc(sizeof(void *), - hashmap__size(&m->pctx.ids) + 1); - if (!metric_events) { - ret = -ENOMEM; - break; - } - evsel = find_evsel_group(perf_evlist, &m->pctx, - metric_no_merge, - m->has_constraint, metric_events, - evlist_used); - if (!evsel) { - pr_debug("Cannot resolve %s: %s\n", - m->metric_name, m->metric_expr); - free(metric_events); - continue; - } - for (i = 0; metric_events[i]; i++) - metric_events[i]->collect_stat = true; - me = metricgroup__lookup(metric_events_list, evsel, true); - if (!me) { - ret = -ENOMEM; - free(metric_events); - break; - } - expr = malloc(sizeof(struct metric_expr)); - if (!expr) { - ret = -ENOMEM; - free(metric_events); - break; - } - - /* - * Collect and store collected nested expressions - * for metric processing. - */ - if (m->metric_refs_cnt) { - struct metric_ref_node *ref; - - metric_refs = zalloc(sizeof(struct metric_ref) * (m->metric_refs_cnt + 1)); - if (!metric_refs) { - ret = -ENOMEM; - free(metric_events); - free(expr); - break; - } - - i = 0; - list_for_each_entry(ref, &m->metric_refs, list) { - /* - * Intentionally passing just const char pointers, - * originally from 'struct pmu_event' object. - * We don't need to change them, so there's no - * need to create our own copy. - */ - metric_refs[i].metric_name = ref->metric_name; - metric_refs[i].metric_expr = ref->metric_expr; - i++; - } - } - - expr->metric_refs = metric_refs; - expr->metric_expr = m->metric_expr; - expr->metric_name = m->metric_name; - expr->metric_unit = m->metric_unit; - expr->metric_events = metric_events; - expr->runtime = m->runtime; - list_add(&expr->nd, &me->head); - } - - evlist__for_each_entry_safe(perf_evlist, tmp, evsel) { - if (!test_bit(evsel->core.idx, evlist_used)) { - evlist__remove(perf_evlist, evsel); - evsel__delete(evsel); } } - bitmap_free(evlist_used); - - return ret; + *out_metric_events = metric_events; + return 0; } static bool match_metric(const char *n, const char *list) @@ -422,7 +343,7 @@ static bool match_metric(const char *n, const char *list) return false; } -static bool match_pe_metric(struct pmu_event *pe, const char *metric) +static bool match_pe_metric(const struct pmu_event *pe, const char *metric) { return match_metric(pe->metric_group, metric) || match_metric(pe->metric_name, metric); @@ -506,7 +427,7 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw) putchar('\n'); } -static int metricgroup__print_pmu_event(struct pmu_event *pe, +static int metricgroup__print_pmu_event(const struct pmu_event *pe, bool metricgroups, char *filter, bool raw, bool details, struct rblist *groups, @@ -581,14 +502,14 @@ struct metricgroup_print_sys_idata { bool details; }; -typedef int (*metricgroup_sys_event_iter_fn)(struct pmu_event *pe, void *); +typedef int (*metricgroup_sys_event_iter_fn)(const struct pmu_event *pe, void *); struct metricgroup_iter_data { metricgroup_sys_event_iter_fn fn; void *data; }; -static int metricgroup__sys_event_iter(struct pmu_event *pe, void *data) +static int metricgroup__sys_event_iter(const struct pmu_event *pe, void *data) { struct metricgroup_iter_data *d = data; struct perf_pmu *pmu = NULL; @@ -607,7 +528,7 @@ static int metricgroup__sys_event_iter(struct pmu_event *pe, void *data) return 0; } -static int metricgroup__print_sys_event_iter(struct pmu_event *pe, void *data) +static int metricgroup__print_sys_event_iter(const struct pmu_event *pe, void *data) { struct metricgroup_print_sys_idata *d = data; @@ -616,10 +537,10 @@ static int metricgroup__print_sys_event_iter(struct pmu_event *pe, void *data) } void metricgroup__print(bool metrics, bool metricgroups, char *filter, - bool raw, bool details) + bool raw, bool details, const char *pmu_name) { - struct pmu_events_map *map = pmu_events_map__find(); - struct pmu_event *pe; + const struct pmu_events_map *map = pmu_events_map__find(); + const struct pmu_event *pe; int i; struct rblist groups; struct rb_node *node, *next; @@ -642,6 +563,10 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, break; if (!pe->metric_expr) continue; + if (pmu_name && perf_pmu__is_hybrid(pe->pmu) && + strcmp(pmu_name, pe->pmu)) { + continue; + } if (metricgroup__print_pmu_event(pe, metricgroups, filter, raw, details, &groups, metriclist) < 0) @@ -686,150 +611,391 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, strlist__delete(metriclist); } -static void metricgroup__add_metric_weak_group(struct strbuf *events, - struct expr_parse_ctx *ctx) +static const char *code_characters = ",-=@"; + +static int encode_metric_id(struct strbuf *sb, const char *x) { - struct hashmap_entry *cur; - size_t bkt; - bool no_group = true, has_duration = false; + char *c; + int ret = 0; - hashmap__for_each_entry((&ctx->ids), cur, bkt) { - pr_debug("found event %s\n", (const char *)cur->key); - /* - * Duration time maps to a software event and can make - * groups not count. Always use it outside a - * group. - */ - if (!strcmp(cur->key, "duration_time")) { - has_duration = true; - continue; + for (; *x; x++) { + c = strchr(code_characters, *x); + if (c) { + ret = strbuf_addch(sb, '!'); + if (ret) + break; + + ret = strbuf_addch(sb, '0' + (c - code_characters)); + if (ret) + break; + } else { + ret = strbuf_addch(sb, *x); + if (ret) + break; } - strbuf_addf(events, "%s%s", - no_group ? "{" : ",", - (const char *)cur->key); - no_group = false; } - if (!no_group) { - strbuf_addf(events, "}:W"); - if (has_duration) - strbuf_addf(events, ",duration_time"); - } else if (has_duration) - strbuf_addf(events, "duration_time"); + return ret; } -static void metricgroup__add_metric_non_group(struct strbuf *events, - struct expr_parse_ctx *ctx) +static int decode_metric_id(struct strbuf *sb, const char *x) { - struct hashmap_entry *cur; - size_t bkt; - bool first = true; + const char *orig = x; + size_t i; + char c; + int ret; - hashmap__for_each_entry((&ctx->ids), cur, bkt) { - if (!first) - strbuf_addf(events, ","); - strbuf_addf(events, "%s", (const char *)cur->key); - first = false; + for (; *x; x++) { + c = *x; + if (*x == '!') { + x++; + i = *x - '0'; + if (i > strlen(code_characters)) { + pr_err("Bad metric-id encoding in: '%s'", orig); + return -1; + } + c = code_characters[i]; + } + ret = strbuf_addch(sb, c); + if (ret) + return ret; } + return 0; } -static void metricgroup___watchdog_constraint_hint(const char *name, bool foot) +static int decode_all_metric_ids(struct evlist *perf_evlist, const char *modifier) { - static bool violate_nmi_constraint; + struct evsel *ev; + struct strbuf sb = STRBUF_INIT; + char *cur; + int ret = 0; - if (!foot) { - pr_warning("Splitting metric group %s into standalone metrics.\n", name); - violate_nmi_constraint = true; - return; - } + evlist__for_each_entry(perf_evlist, ev) { + if (!ev->metric_id) + continue; - if (!violate_nmi_constraint) - return; + ret = strbuf_setlen(&sb, 0); + if (ret) + break; - pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n" - " echo 0 > /proc/sys/kernel/nmi_watchdog\n" - " perf stat ...\n" - " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); + ret = decode_metric_id(&sb, ev->metric_id); + if (ret) + break; + + free((char *)ev->metric_id); + ev->metric_id = strdup(sb.buf); + if (!ev->metric_id) { + ret = -ENOMEM; + break; + } + /* + * If the name is just the parsed event, use the metric-id to + * give a more friendly display version. + */ + if (strstr(ev->name, "metric-id=")) { + bool has_slash = false; + + free(ev->name); + for (cur = strchr(sb.buf, '@') ; cur; cur = strchr(++cur, '@')) { + *cur = '/'; + has_slash = true; + } + + if (modifier) { + if (!has_slash && !strchr(sb.buf, ':')) { + ret = strbuf_addch(&sb, ':'); + if (ret) + break; + } + ret = strbuf_addstr(&sb, modifier); + if (ret) + break; + } + ev->name = strdup(sb.buf); + if (!ev->name) { + ret = -ENOMEM; + break; + } + } + } + strbuf_release(&sb); + return ret; } -static bool metricgroup__has_constraint(struct pmu_event *pe) +static int metricgroup__build_event_string(struct strbuf *events, + const struct expr_parse_ctx *ctx, + const char *modifier, + bool has_constraint) { - if (!pe->metric_constraint) - return false; + struct hashmap_entry *cur; + size_t bkt; + bool no_group = true, has_duration = false; + int ret = 0; - if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") && - sysctl__nmi_watchdog_enabled()) { - metricgroup___watchdog_constraint_hint(pe->metric_name, false); - return true; +#define RETURN_IF_NON_ZERO(x) do { if (x) return x; } while (0) + + hashmap__for_each_entry(ctx->ids, cur, bkt) { + const char *sep, *rsep, *id = cur->key; + + pr_debug("found event %s\n", id); + /* + * Duration time maps to a software event and can make + * groups not count. Always use it outside a + * group. + */ + if (!strcmp(id, "duration_time")) { + has_duration = true; + continue; + } + /* Separate events with commas and open the group if necessary. */ + if (no_group) { + if (!has_constraint) { + ret = strbuf_addch(events, '{'); + RETURN_IF_NON_ZERO(ret); + } + + no_group = false; + } else { + ret = strbuf_addch(events, ','); + RETURN_IF_NON_ZERO(ret); + } + /* + * Encode the ID as an event string. Add a qualifier for + * metric_id that is the original name except with characters + * that parse-events can't parse replaced. For example, + * 'msr@tsc@' gets added as msr/tsc,metric-id=msr!3tsc!3/ + */ + sep = strchr(id, '@'); + if (sep != NULL) { + ret = strbuf_add(events, id, sep - id); + RETURN_IF_NON_ZERO(ret); + ret = strbuf_addch(events, '/'); + RETURN_IF_NON_ZERO(ret); + rsep = strrchr(sep, '@'); + ret = strbuf_add(events, sep + 1, rsep - sep - 1); + RETURN_IF_NON_ZERO(ret); + ret = strbuf_addstr(events, ",metric-id="); + RETURN_IF_NON_ZERO(ret); + sep = rsep; + } else { + sep = strchr(id, ':'); + if (sep != NULL) { + ret = strbuf_add(events, id, sep - id); + RETURN_IF_NON_ZERO(ret); + } else { + ret = strbuf_addstr(events, id); + RETURN_IF_NON_ZERO(ret); + } + ret = strbuf_addstr(events, "/metric-id="); + RETURN_IF_NON_ZERO(ret); + } + ret = encode_metric_id(events, id); + RETURN_IF_NON_ZERO(ret); + ret = strbuf_addstr(events, "/"); + RETURN_IF_NON_ZERO(ret); + + if (sep != NULL) { + ret = strbuf_addstr(events, sep + 1); + RETURN_IF_NON_ZERO(ret); + } + if (modifier) { + ret = strbuf_addstr(events, modifier); + RETURN_IF_NON_ZERO(ret); + } } + if (has_duration) { + if (no_group) { + /* Strange case of a metric of just duration_time. */ + ret = strbuf_addf(events, "duration_time"); + } else if (!has_constraint) + ret = strbuf_addf(events, "}:W,duration_time"); + else + ret = strbuf_addf(events, ",duration_time"); + } else if (!no_group && !has_constraint) + ret = strbuf_addf(events, "}:W"); - return false; + return ret; +#undef RETURN_IF_NON_ZERO } -int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused) +int __weak arch_get_runtimeparam(const struct pmu_event *pe __maybe_unused) { return 1; } +/* + * A singly linked list on the stack of the names of metrics being + * processed. Used to identify recursion. + */ +struct visited_metric { + const char *name; + const struct visited_metric *parent; +}; + struct metricgroup_add_iter_data { struct list_head *metric_list; - const char *metric; - struct expr_ids *ids; + const char *metric_name; + const char *modifier; int *ret; bool *has_match; bool metric_no_group; + struct metric *root_metric; + const struct visited_metric *visited; + const struct pmu_events_map *map; }; +static int add_metric(struct list_head *metric_list, + const struct pmu_event *pe, + const char *modifier, + bool metric_no_group, + struct metric *root_metric, + const struct visited_metric *visited, + const struct pmu_events_map *map); + +/** + * resolve_metric - Locate metrics within the root metric and recursively add + * references to them. + * @metric_list: The list the metric is added to. + * @modifier: if non-null event modifiers like "u". + * @metric_no_group: Should events written to events be grouped "{}" or + * global. Grouping is the default but due to multiplexing the + * user may override. + * @root_metric: Metrics may reference other metrics to form a tree. In this + * case the root_metric holds all the IDs and a list of referenced + * metrics. When adding a root this argument is NULL. + * @visited: A singly linked list of metric names being added that is used to + * detect recursion. + * @map: The map that is searched for metrics, most commonly the table for the + * architecture perf is running upon. + */ +static int resolve_metric(struct list_head *metric_list, + const char *modifier, + bool metric_no_group, + struct metric *root_metric, + const struct visited_metric *visited, + const struct pmu_events_map *map) +{ + struct hashmap_entry *cur; + size_t bkt; + struct to_resolve { + /* The metric to resolve. */ + const struct pmu_event *pe; + /* + * The key in the IDs map, this may differ from in case, + * etc. from pe->metric_name. + */ + const char *key; + } *pending = NULL; + int i, ret = 0, pending_cnt = 0; + + /* + * Iterate all the parsed IDs and if there's a matching metric and it to + * the pending array. + */ + hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) { + const struct pmu_event *pe; + + pe = metricgroup__find_metric(cur->key, map); + if (pe) { + pending = realloc(pending, + (pending_cnt + 1) * sizeof(struct to_resolve)); + if (!pending) + return -ENOMEM; + + pending[pending_cnt].pe = pe; + pending[pending_cnt].key = cur->key; + pending_cnt++; + } + } + + /* Remove the metric IDs from the context. */ + for (i = 0; i < pending_cnt; i++) + expr__del_id(root_metric->pctx, pending[i].key); + + /* + * Recursively add all the metrics, IDs are added to the root metric's + * context. + */ + for (i = 0; i < pending_cnt; i++) { + ret = add_metric(metric_list, pending[i].pe, modifier, metric_no_group, + root_metric, visited, map); + if (ret) + break; + } + + free(pending); + return ret; +} + +/** + * __add_metric - Add a metric to metric_list. + * @metric_list: The list the metric is added to. + * @pe: The pmu_event containing the metric to be added. + * @modifier: if non-null event modifiers like "u". + * @metric_no_group: Should events written to events be grouped "{}" or + * global. Grouping is the default but due to multiplexing the + * user may override. + * @runtime: A special argument for the parser only known at runtime. + * @root_metric: Metrics may reference other metrics to form a tree. In this + * case the root_metric holds all the IDs and a list of referenced + * metrics. When adding a root this argument is NULL. + * @visited: A singly linked list of metric names being added that is used to + * detect recursion. + * @map: The map that is searched for metrics, most commonly the table for the + * architecture perf is running upon. + */ static int __add_metric(struct list_head *metric_list, - struct pmu_event *pe, + const struct pmu_event *pe, + const char *modifier, bool metric_no_group, int runtime, - struct metric **mp, - struct expr_id *parent, - struct expr_ids *ids) + struct metric *root_metric, + const struct visited_metric *visited, + const struct pmu_events_map *map) { - struct metric_ref_node *ref; - struct metric *m; + const struct visited_metric *vm; + int ret; + bool is_root = !root_metric; + struct visited_metric visited_node = { + .name = pe->metric_name, + .parent = visited, + }; + + for (vm = visited; vm; vm = vm->parent) { + if (!strcmp(pe->metric_name, vm->name)) { + pr_err("failed: recursion detected for %s\n", pe->metric_name); + return -1; + } + } - if (*mp == NULL) { + if (is_root) { /* - * We got in here for the parent group, - * allocate it and put it on the list. + * This metric is the root of a tree and may reference other + * metrics that are added recursively. */ - m = zalloc(sizeof(*m)); - if (!m) + root_metric = metric__new(pe, modifier, metric_no_group, runtime); + if (!root_metric) return -ENOMEM; - expr__ctx_init(&m->pctx); - m->metric_name = pe->metric_name; - m->metric_expr = pe->metric_expr; - m->metric_unit = pe->unit; - m->runtime = runtime; - m->has_constraint = metric_no_group || metricgroup__has_constraint(pe); - INIT_LIST_HEAD(&m->metric_refs); - m->metric_refs_cnt = 0; - - parent = expr_ids__alloc(ids); - if (!parent) { - free(m); - return -EINVAL; - } - - parent->id = strdup(pe->metric_name); - if (!parent->id) { - free(m); - return -ENOMEM; - } - *mp = m; } else { + int cnt = 0; + /* - * We got here for the referenced metric, via the - * recursive metricgroup__add_metric call, add - * it to the parent group. + * This metric was referenced in a metric higher in the + * tree. Check if the same metric is already resolved in the + * metric_refs list. */ - m = *mp; + if (root_metric->metric_refs) { + for (; root_metric->metric_refs[cnt].metric_name; cnt++) { + if (!strcmp(pe->metric_name, + root_metric->metric_refs[cnt].metric_name)) + return 0; + } + } - ref = malloc(sizeof(*ref)); - if (!ref) + /* Create reference. Need space for the entry and the terminator. */ + root_metric->metric_refs = realloc(root_metric->metric_refs, + (cnt + 2) * sizeof(struct metric_ref)); + if (!root_metric->metric_refs) return -ENOMEM; /* @@ -838,54 +1004,35 @@ static int __add_metric(struct list_head *metric_list, * need to change them, so there's no need to create * our own copy. */ - ref->metric_name = pe->metric_name; - ref->metric_expr = pe->metric_expr; + root_metric->metric_refs[cnt].metric_name = pe->metric_name; + root_metric->metric_refs[cnt].metric_expr = pe->metric_expr; - list_add(&ref->list, &m->metric_refs); - m->metric_refs_cnt++; + /* Null terminate array. */ + root_metric->metric_refs[cnt+1].metric_name = NULL; + root_metric->metric_refs[cnt+1].metric_expr = NULL; } - /* Force all found IDs in metric to have us as parent ID. */ - WARN_ON_ONCE(!parent); - m->pctx.parent = parent; - /* * For both the parent and referenced metrics, we parse - * all the metric's IDs and add it to the parent context. + * all the metric's IDs and add it to the root context. */ - if (expr__find_other(pe->metric_expr, NULL, &m->pctx, runtime) < 0) { - if (m->metric_refs_cnt == 0) { - expr__ctx_clear(&m->pctx); - free(m); - *mp = NULL; - } - return -EINVAL; + if (expr__find_ids(pe->metric_expr, NULL, root_metric->pctx) < 0) { + /* Broken metric. */ + ret = -EINVAL; + } else { + /* Resolve referenced metrics. */ + ret = resolve_metric(metric_list, modifier, metric_no_group, root_metric, + &visited_node, map); } - /* - * We add new group only in the 'parent' call, - * so bail out for referenced metric case. - */ - if (m->metric_refs_cnt) - return 0; - - if (list_empty(metric_list)) - list_add(&m->nd, metric_list); - else { - struct list_head *pos; - - /* Place the largest groups at the front. */ - list_for_each_prev(pos, metric_list) { - struct metric *old = list_entry(pos, struct metric, nd); + if (ret) { + if (is_root) + metric__free(root_metric); - if (hashmap__size(&m->pctx.ids) <= - hashmap__size(&old->pctx.ids)) - break; - } - list_add(&m->nd, pos); - } + } else if (is_root) + list_add(&root_metric->nd, metric_list); - return 0; + return ret; } #define map_for_each_event(__pe, __idx, __map) \ @@ -900,10 +1047,10 @@ static int __add_metric(struct list_head *metric_list, (match_metric(__pe->metric_group, __metric) || \ match_metric(__pe->metric_name, __metric))) -struct pmu_event *metricgroup__find_metric(const char *metric, - struct pmu_events_map *map) +const struct pmu_event *metricgroup__find_metric(const char *metric, + const struct pmu_events_map *map) { - struct pmu_event *pe; + const struct pmu_event *pe; int i; map_for_each_event(pe, i, map) { @@ -914,136 +1061,21 @@ struct pmu_event *metricgroup__find_metric(const char *metric, return NULL; } -static int recursion_check(struct metric *m, const char *id, struct expr_id **parent, - struct expr_ids *ids) -{ - struct expr_id_data *data; - struct expr_id *p; - int ret; - - /* - * We get the parent referenced by 'id' argument and - * traverse through all the parent object IDs to check - * if we already processed 'id', if we did, it's recursion - * and we fail. - */ - ret = expr__get_id(&m->pctx, id, &data); - if (ret) - return ret; - - p = expr_id_data__parent(data); - - while (p->parent) { - if (!strcmp(p->id, id)) { - pr_err("failed: recursion detected for %s\n", id); - return -1; - } - p = p->parent; - } - - /* - * If we are over the limit of static entris, the metric - * is too difficult/nested to process, fail as well. - */ - p = expr_ids__alloc(ids); - if (!p) { - pr_err("failed: too many nested metrics\n"); - return -EINVAL; - } - - p->id = strdup(id); - p->parent = expr_id_data__parent(data); - *parent = p; - - return p->id ? 0 : -ENOMEM; -} - -static int add_metric(struct list_head *metric_list, - struct pmu_event *pe, - bool metric_no_group, - struct metric **mp, - struct expr_id *parent, - struct expr_ids *ids); - -static int __resolve_metric(struct metric *m, - bool metric_no_group, - struct list_head *metric_list, - struct pmu_events_map *map, - struct expr_ids *ids) -{ - struct hashmap_entry *cur; - size_t bkt; - bool all; - int ret; - - /* - * Iterate all the parsed IDs and if there's metric, - * add it to the context. - */ - do { - all = true; - hashmap__for_each_entry((&m->pctx.ids), cur, bkt) { - struct expr_id *parent; - struct pmu_event *pe; - - pe = metricgroup__find_metric(cur->key, map); - if (!pe) - continue; - - ret = recursion_check(m, cur->key, &parent, ids); - if (ret) - return ret; - - all = false; - /* The metric key itself needs to go out.. */ - expr__del_id(&m->pctx, cur->key); - - /* ... and it gets resolved to the parent context. */ - ret = add_metric(metric_list, pe, metric_no_group, &m, parent, ids); - if (ret) - return ret; - - /* - * We added new metric to hashmap, so we need - * to break the iteration and start over. - */ - break; - } - } while (!all); - - return 0; -} - -static int resolve_metric(bool metric_no_group, - struct list_head *metric_list, - struct pmu_events_map *map, - struct expr_ids *ids) -{ - struct metric *m; - int err; - - list_for_each_entry(m, metric_list, nd) { - err = __resolve_metric(m, metric_no_group, metric_list, map, ids); - if (err) - return err; - } - return 0; -} - static int add_metric(struct list_head *metric_list, - struct pmu_event *pe, + const struct pmu_event *pe, + const char *modifier, bool metric_no_group, - struct metric **m, - struct expr_id *parent, - struct expr_ids *ids) + struct metric *root_metric, + const struct visited_metric *visited, + const struct pmu_events_map *map) { - struct metric *orig = *m; int ret = 0; pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name); if (!strstr(pe->metric_expr, "?")) { - ret = __add_metric(metric_list, pe, metric_no_group, 1, m, parent, ids); + ret = __add_metric(metric_list, pe, modifier, metric_no_group, 0, + root_metric, visited, map); } else { int j, count; @@ -1054,29 +1086,25 @@ static int add_metric(struct list_head *metric_list, * those events to metric_list. */ - for (j = 0; j < count && !ret; j++, *m = orig) - ret = __add_metric(metric_list, pe, metric_no_group, j, m, parent, ids); + for (j = 0; j < count && !ret; j++) + ret = __add_metric(metric_list, pe, modifier, metric_no_group, j, + root_metric, visited, map); } return ret; } -static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, +static int metricgroup__add_metric_sys_event_iter(const struct pmu_event *pe, void *data) { struct metricgroup_add_iter_data *d = data; - struct metric *m = NULL; int ret; - if (!match_pe_metric(pe, d->metric)) + if (!match_pe_metric(pe, d->metric_name)) return 0; - ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); - if (ret) - goto out; - - ret = resolve_metric(d->metric_no_group, - d->metric_list, NULL, d->ids); + ret = add_metric(d->metric_list, pe, d->modifier, d->metric_no_group, + d->root_metric, d->visited, d->map); if (ret) goto out; @@ -1087,32 +1115,61 @@ out: return ret; } -static int metricgroup__add_metric(const char *metric, bool metric_no_group, - struct strbuf *events, +/** + * metric_list_cmp - list_sort comparator that sorts metrics with more events to + * the front. duration_time is excluded from the count. + */ +static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l, + const struct list_head *r) +{ + const struct metric *left = container_of(l, struct metric, nd); + const struct metric *right = container_of(r, struct metric, nd); + struct expr_id_data *data; + int left_count, right_count; + + left_count = hashmap__size(left->pctx->ids); + if (!expr__get_id(left->pctx, "duration_time", &data)) + left_count--; + + right_count = hashmap__size(right->pctx->ids); + if (!expr__get_id(right->pctx, "duration_time", &data)) + right_count--; + + return right_count - left_count; +} + +/** + * metricgroup__add_metric - Find and add a metric, or a metric group. + * @metric_name: The name of the metric or metric group. For example, "IPC" + * could be the name of a metric and "TopDownL1" the name of a + * metric group. + * @modifier: if non-null event modifiers like "u". + * @metric_no_group: Should events written to events be grouped "{}" or + * global. Grouping is the default but due to multiplexing the + * user may override. + * @metric_list: The list that the metric or metric group are added to. + * @map: The map that is searched for metrics, most commonly the table for the + * architecture perf is running upon. + */ +static int metricgroup__add_metric(const char *metric_name, const char *modifier, + bool metric_no_group, struct list_head *metric_list, - struct pmu_events_map *map) + const struct pmu_events_map *map) { - struct expr_ids ids = { .cnt = 0, }; - struct pmu_event *pe; - struct metric *m; + const struct pmu_event *pe; LIST_HEAD(list); int i, ret; bool has_match = false; - map_for_each_metric(pe, i, map, metric) { + /* + * Iterate over all metrics seeing if metric matches either the name or + * group. When it does add the metric to the list. + */ + map_for_each_metric(pe, i, map, metric_name) { has_match = true; - m = NULL; - - ret = add_metric(&list, pe, metric_no_group, &m, NULL, &ids); - if (ret) - goto out; - - /* - * Process any possible referenced metrics - * included in the expression. - */ - ret = resolve_metric(metric_no_group, - &list, map, &ids); + ret = add_metric(&list, pe, modifier, metric_no_group, + /*root_metric=*/NULL, + /*visited_metrics=*/NULL, map); if (ret) goto out; } @@ -1122,34 +1179,20 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group, .fn = metricgroup__add_metric_sys_event_iter, .data = (void *) &(struct metricgroup_add_iter_data) { .metric_list = &list, - .metric = metric, + .metric_name = metric_name, + .modifier = modifier, .metric_no_group = metric_no_group, - .ids = &ids, .has_match = &has_match, .ret = &ret, + .map = map, }, }; pmu_for_each_sys_event(metricgroup__sys_event_iter, &data); } /* End of pmu events. */ - if (!has_match) { + if (!has_match) ret = -EINVAL; - goto out; - } - - list_for_each_entry(m, &list, nd) { - if (events->len > 0) - strbuf_addf(events, ","); - - if (m->has_constraint) { - metricgroup__add_metric_non_group(events, - &m->pctx); - } else { - metricgroup__add_metric_weak_group(events, - &m->pctx); - } - } out: /* @@ -1157,95 +1200,325 @@ out: * even if it's failed */ list_splice(&list, metric_list); - expr_ids__exit(&ids); return ret; } +/** + * metricgroup__add_metric_list - Find and add metrics, or metric groups, + * specified in a list. + * @list: the list of metrics or metric groups. For example, "IPC,CPI,TopDownL1" + * would match the IPC and CPI metrics, and TopDownL1 would match all + * the metrics in the TopDownL1 group. + * @metric_no_group: Should events written to events be grouped "{}" or + * global. Grouping is the default but due to multiplexing the + * user may override. + * @metric_list: The list that metrics are added to. + * @map: The map that is searched for metrics, most commonly the table for the + * architecture perf is running upon. + */ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, - struct strbuf *events, struct list_head *metric_list, - struct pmu_events_map *map) + const struct pmu_events_map *map) { - char *llist, *nlist, *p; - int ret = -EINVAL; + char *list_itr, *list_copy, *metric_name, *modifier; + int ret, count = 0; - nlist = strdup(list); - if (!nlist) + list_copy = strdup(list); + if (!list_copy) return -ENOMEM; - llist = nlist; + list_itr = list_copy; - strbuf_init(events, 100); - strbuf_addf(events, "%s", ""); + while ((metric_name = strsep(&list_itr, ",")) != NULL) { + modifier = strchr(metric_name, ':'); + if (modifier) + *modifier++ = '\0'; - while ((p = strsep(&llist, ",")) != NULL) { - ret = metricgroup__add_metric(p, metric_no_group, events, - metric_list, map); - if (ret == -EINVAL) { - fprintf(stderr, "Cannot find metric or group `%s'\n", - p); + ret = metricgroup__add_metric(metric_name, modifier, + metric_no_group, metric_list, + map); + if (ret == -EINVAL) + pr_err("Cannot find metric or group `%s'\n", metric_name); + + if (ret) break; - } + + count++; } - free(nlist); + free(list_copy); - if (!ret) + if (!ret) { + /* + * Warn about nmi_watchdog if any parsed metrics had the + * NO_NMI_WATCHDOG constraint. + */ metricgroup___watchdog_constraint_hint(NULL, true); - + /* No metrics. */ + if (count == 0) + return -EINVAL; + } return ret; } -static void metric__free_refs(struct metric *metric) +static void metricgroup__free_metrics(struct list_head *metric_list) { - struct metric_ref_node *ref, *tmp; + struct metric *m, *tmp; - list_for_each_entry_safe(ref, tmp, &metric->metric_refs, list) { - list_del(&ref->list); - free(ref); + list_for_each_entry_safe (m, tmp, metric_list, nd) { + list_del_init(&m->nd); + metric__free(m); } } -static void metricgroup__free_metrics(struct list_head *metric_list) +/** + * build_combined_expr_ctx - Make an expr_parse_ctx with all has_constraint + * metric IDs, as the IDs are held in a set, + * duplicates will be removed. + * @metric_list: List to take metrics from. + * @combined: Out argument for result. + */ +static int build_combined_expr_ctx(const struct list_head *metric_list, + struct expr_parse_ctx **combined) { - struct metric *m, *tmp; + struct hashmap_entry *cur; + size_t bkt; + struct metric *m; + char *dup; + int ret; - list_for_each_entry_safe (m, tmp, metric_list, nd) { - metric__free_refs(m); - expr__ctx_clear(&m->pctx); - list_del_init(&m->nd); - free(m); + *combined = expr__ctx_new(); + if (!*combined) + return -ENOMEM; + + list_for_each_entry(m, metric_list, nd) { + if (m->has_constraint && !m->modifier) { + hashmap__for_each_entry(m->pctx->ids, cur, bkt) { + dup = strdup(cur->key); + if (!dup) { + ret = -ENOMEM; + goto err_out; + } + ret = expr__add_id(*combined, dup); + if (ret) + goto err_out; + } + } + } + return 0; +err_out: + expr__ctx_free(*combined); + *combined = NULL; + return ret; +} + +/** + * parse_ids - Build the event string for the ids and parse them creating an + * evlist. The encoded metric_ids are decoded. + * @metric_no_merge: is metric sharing explicitly disabled. + * @fake_pmu: used when testing metrics not supported by the current CPU. + * @ids: the event identifiers parsed from a metric. + * @modifier: any modifiers added to the events. + * @has_constraint: false if events should be placed in a weak group. + * @out_evlist: the created list of events. + */ +static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu, + struct expr_parse_ctx *ids, const char *modifier, + bool has_constraint, struct evlist **out_evlist) +{ + struct parse_events_error parse_error; + struct evlist *parsed_evlist; + struct strbuf events = STRBUF_INIT; + int ret; + + *out_evlist = NULL; + if (!metric_no_merge || hashmap__size(ids->ids) == 0) { + char *tmp; + /* + * We may fail to share events between metrics because + * duration_time isn't present in one metric. For example, a + * ratio of cache misses doesn't need duration_time but the same + * events may be used for a misses per second. Events without + * sharing implies multiplexing, that is best avoided, so place + * duration_time in every group. + * + * Also, there may be no ids/events in the expression parsing + * context because of constant evaluation, e.g.: + * event1 if #smt_on else 0 + * Add a duration_time event to avoid a parse error on an empty + * string. + */ + tmp = strdup("duration_time"); + if (!tmp) + return -ENOMEM; + + ids__insert(ids->ids, tmp); + } + ret = metricgroup__build_event_string(&events, ids, modifier, + has_constraint); + if (ret) + return ret; + + parsed_evlist = evlist__new(); + if (!parsed_evlist) { + ret = -ENOMEM; + goto err_out; + } + pr_debug("Parsing metric events '%s'\n", events.buf); + parse_events_error__init(&parse_error); + ret = __parse_events(parsed_evlist, events.buf, &parse_error, fake_pmu); + if (ret) { + parse_events_error__print(&parse_error, events.buf); + goto err_out; } + ret = decode_all_metric_ids(parsed_evlist, modifier); + if (ret) + goto err_out; + + *out_evlist = parsed_evlist; + parsed_evlist = NULL; +err_out: + parse_events_error__exit(&parse_error); + evlist__delete(parsed_evlist); + strbuf_release(&events); + return ret; } static int parse_groups(struct evlist *perf_evlist, const char *str, bool metric_no_group, bool metric_no_merge, struct perf_pmu *fake_pmu, - struct rblist *metric_events, - struct pmu_events_map *map) + struct rblist *metric_events_list, + const struct pmu_events_map *map) { - struct parse_events_error parse_error; - struct strbuf extra_events; + struct evlist *combined_evlist = NULL; LIST_HEAD(metric_list); + struct metric *m; int ret; - if (metric_events->nr_entries == 0) - metricgroup__rblist_init(metric_events); + if (metric_events_list->nr_entries == 0) + metricgroup__rblist_init(metric_events_list); ret = metricgroup__add_metric_list(str, metric_no_group, - &extra_events, &metric_list, map); + &metric_list, map); if (ret) goto out; - pr_debug("adding %s\n", extra_events.buf); - bzero(&parse_error, sizeof(parse_error)); - ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu); - if (ret) { - parse_events_print_error(&parse_error, extra_events.buf); - goto out; + + /* Sort metrics from largest to smallest. */ + list_sort(NULL, &metric_list, metric_list_cmp); + + if (!metric_no_merge) { + struct expr_parse_ctx *combined = NULL; + + ret = build_combined_expr_ctx(&metric_list, &combined); + + if (!ret && combined && hashmap__size(combined->ids)) { + ret = parse_ids(metric_no_merge, fake_pmu, combined, + /*modifier=*/NULL, + /*has_constraint=*/true, + &combined_evlist); + } + if (combined) + expr__ctx_free(combined); + + if (ret) + goto out; + } + + list_for_each_entry(m, &metric_list, nd) { + struct metric_event *me; + struct evsel **metric_events; + struct evlist *metric_evlist = NULL; + struct metric *n; + struct metric_expr *expr; + + if (combined_evlist && m->has_constraint) { + metric_evlist = combined_evlist; + } else if (!metric_no_merge) { + /* + * See if the IDs for this metric are a subset of an + * earlier metric. + */ + list_for_each_entry(n, &metric_list, nd) { + if (m == n) + break; + + if (n->evlist == NULL) + continue; + + if ((!m->modifier && n->modifier) || + (m->modifier && !n->modifier) || + (m->modifier && n->modifier && + strcmp(m->modifier, n->modifier))) + continue; + + if (expr__subset_of_ids(n->pctx, m->pctx)) { + pr_debug("Events in '%s' fully contained within '%s'\n", + m->metric_name, n->metric_name); + metric_evlist = n->evlist; + break; + } + + } + } + if (!metric_evlist) { + ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier, + m->has_constraint, &m->evlist); + if (ret) + goto out; + + metric_evlist = m->evlist; + } + ret = setup_metric_events(m->pctx->ids, metric_evlist, &metric_events); + if (ret) { + pr_debug("Cannot resolve IDs for %s: %s\n", + m->metric_name, m->metric_expr); + goto out; + } + + me = metricgroup__lookup(metric_events_list, metric_events[0], true); + + expr = malloc(sizeof(struct metric_expr)); + if (!expr) { + ret = -ENOMEM; + free(metric_events); + goto out; + } + + expr->metric_refs = m->metric_refs; + m->metric_refs = NULL; + expr->metric_expr = m->metric_expr; + if (m->modifier) { + char *tmp; + + if (asprintf(&tmp, "%s:%s", m->metric_name, m->modifier) < 0) + expr->metric_name = NULL; + else + expr->metric_name = tmp; + } else + expr->metric_name = strdup(m->metric_name); + + if (!expr->metric_name) { + ret = -ENOMEM; + free(metric_events); + goto out; + } + expr->metric_unit = m->metric_unit; + expr->metric_events = metric_events; + expr->runtime = m->pctx->runtime; + list_add(&expr->nd, &me->head); } - ret = metricgroup__setup_events(&metric_list, metric_no_merge, - perf_evlist, metric_events); + + + if (combined_evlist) { + evlist__splice_list_tail(perf_evlist, &combined_evlist->core.entries); + evlist__delete(combined_evlist); + } + + list_for_each_entry(m, &metric_list, nd) { + if (m->evlist) + evlist__splice_list_tail(perf_evlist, &m->evlist->core.entries); + } + out: metricgroup__free_metrics(&metric_list); - strbuf_release(&extra_events); return ret; } @@ -1256,14 +1529,14 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events) { struct evlist *perf_evlist = *(struct evlist **)opt->value; - struct pmu_events_map *map = pmu_events_map__find(); + const struct pmu_events_map *map = pmu_events_map__find(); return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge, NULL, metric_events, map); } int metricgroup__parse_groups_test(struct evlist *evlist, - struct pmu_events_map *map, + const struct pmu_events_map *map, const char *str, bool metric_no_group, bool metric_no_merge, @@ -1275,8 +1548,8 @@ int metricgroup__parse_groups_test(struct evlist *evlist, bool metricgroup__has_metric(const char *metric) { - struct pmu_events_map *map = pmu_events_map__find(); - struct pmu_event *pe; + const struct pmu_events_map *map = pmu_events_map__find(); + const struct pmu_event *pe; int i; if (!map) @@ -1328,7 +1601,10 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, return -ENOMEM; new_expr->metric_expr = old_expr->metric_expr; - new_expr->metric_name = old_expr->metric_name; + new_expr->metric_name = strdup(old_expr->metric_name); + if (!new_expr->metric_name) + return -ENOMEM; + new_expr->metric_unit = old_expr->metric_unit; new_expr->runtime = old_expr->runtime; diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index cc4a92492a61..2b42b778d1bf 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -14,24 +14,51 @@ struct rblist; struct pmu_events_map; struct cgroup; +/** + * A node in a rblist keyed by the evsel. The global rblist of metric events + * generally exists in perf_stat_config. The evsel is looked up in the rblist + * yielding a list of metric_expr. + */ struct metric_event { struct rb_node nd; struct evsel *evsel; struct list_head head; /* list of metric_expr */ }; +/** + * A metric referenced by a metric_expr. When parsing a metric expression IDs + * will be looked up, matching either a value (from metric_events) or a + * metric_ref. A metric_ref will then be parsed recursively. The metric_refs and + * metric_events need to be known before parsing so that their values may be + * placed in the parse context for lookup. + */ struct metric_ref { const char *metric_name; const char *metric_expr; }; +/** + * One in a list of metric_expr associated with an evsel. The data is used to + * generate a metric value during stat output. + */ struct metric_expr { struct list_head nd; + /** The expression to parse, for example, "instructions/cycles". */ const char *metric_expr; + /** The name of the meric such as "IPC". */ const char *metric_name; + /** + * The "ScaleUnit" that scales and adds a unit to the metric during + * output. For example, "6.4e-05MiB" means to scale the resulting metric + * by 6.4e-05 (typically converting a unit like cache lines to something + * more human intelligible) and then add "MiB" afterward when displayed. + */ const char *metric_unit; + /** Null terminated array of events used by the metric. */ struct evsel **metric_events; + /** Null terminated array of referenced metrics. */ struct metric_ref *metric_refs; + /** A value substituted for '?' during parsing. */ int runtime; }; @@ -43,19 +70,19 @@ int metricgroup__parse_groups(const struct option *opt, bool metric_no_group, bool metric_no_merge, struct rblist *metric_events); -struct pmu_event *metricgroup__find_metric(const char *metric, - struct pmu_events_map *map); +const struct pmu_event *metricgroup__find_metric(const char *metric, + const struct pmu_events_map *map); int metricgroup__parse_groups_test(struct evlist *evlist, - struct pmu_events_map *map, + const struct pmu_events_map *map, const char *str, bool metric_no_group, bool metric_no_merge, struct rblist *metric_events); void metricgroup__print(bool metrics, bool groups, char *filter, - bool raw, bool details); + bool raw, bool details, const char *pmu_name); bool metricgroup__has_metric(const char *metric); -int arch_get_runtimeparam(struct pmu_event *pe __maybe_unused); +int arch_get_runtimeparam(const struct pmu_event *pe __maybe_unused); void metricgroup__rblist_exit(struct rblist *metric_events); int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 512dc8b9c168..0e8ff8d1e206 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -94,7 +94,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx) } } -static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity) +static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, int affinity) { void *data; size_t mmap_len; @@ -138,7 +138,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx) } static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused, - int cpu __maybe_unused, int affinity __maybe_unused) + struct perf_cpu cpu __maybe_unused, int affinity __maybe_unused) { return 0; } @@ -240,7 +240,8 @@ void mmap__munmap(struct mmap *map) static void build_node_mask(int node, struct mmap_cpu_mask *mask) { - int c, cpu, nr_cpus; + int idx, nr_cpus; + struct perf_cpu cpu; const struct perf_cpu_map *cpu_map = NULL; cpu_map = cpu_map__online(); @@ -248,16 +249,16 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask) return; nr_cpus = perf_cpu_map__nr(cpu_map); - for (c = 0; c < nr_cpus; c++) { - cpu = cpu_map->map[c]; /* map c index to online cpu index */ + for (idx = 0; idx < nr_cpus; idx++) { + cpu = perf_cpu_map__cpu(cpu_map, idx); /* map c index to online cpu index */ if (cpu__get_node(cpu) == node) - set_bit(cpu, mask->bits); + set_bit(cpu.cpu, mask->bits); } } static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) { - map->affinity_mask.nbits = cpu__max_cpu(); + map->affinity_mask.nbits = cpu__max_cpu().cpu; map->affinity_mask.bits = bitmap_zalloc(map->affinity_mask.nbits); if (!map->affinity_mask.bits) return -1; @@ -265,12 +266,12 @@ static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params * if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask); else if (mp->affinity == PERF_AFFINITY_CPU) - set_bit(map->core.cpu, map->affinity_mask.bits); + set_bit(map->core.cpu.cpu, map->affinity_mask.bits); return 0; } -int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu) { if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", @@ -350,3 +351,14 @@ int perf_mmap__push(struct mmap *md, void *to, out: return rc; } + +int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, struct mmap_cpu_mask *clone) +{ + clone->nbits = original->nbits; + clone->bits = bitmap_zalloc(original->nbits); + if (!clone->bits) + return -ENOMEM; + + memcpy(clone->bits, original->bits, MMAP_CPU_MASK_BYTES(original)); + return 0; +} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index af33118354dd..83f6bd4d4082 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -7,6 +7,7 @@ #include <linux/types.h> #include <linux/ring_buffer.h> #include <linux/bitops.h> +#include <perf/cpumap.h> #include <stdbool.h> #include <pthread.h> // for cpu_set_t #ifdef HAVE_AIO_SUPPORT @@ -52,7 +53,7 @@ struct mmap_params { struct auxtrace_mmap_params auxtrace_mp; }; -int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu); +int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu); void mmap__munmap(struct mmap *map); union perf_event *perf_mmap__read_forward(struct mmap *map); @@ -64,4 +65,7 @@ size_t mmap__mmap_len(struct mmap *map); void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag); +int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, + struct mmap_cpu_mask *clone); + #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 608b20c72a5c..48aa3217300b 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -60,17 +60,49 @@ void namespaces__free(struct namespaces *namespaces) free(namespaces); } +static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path) +{ + FILE *f = NULL; + char *statln = NULL; + size_t linesz = 0; + char *nspid; + + f = fopen(path, "r"); + if (f == NULL) + return -1; + + while (getline(&statln, &linesz, f) != -1) { + /* Use tgid if CONFIG_PID_NS is not defined. */ + if (strstr(statln, "Tgid:") != NULL) { + nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'), + NULL, 10); + nsi->nstgid = nsi->tgid; + } + + if (strstr(statln, "NStgid:") != NULL) { + nspid = strrchr(statln, '\t'); + nsi->nstgid = (pid_t)strtol(nspid, NULL, 10); + /* + * If innermost tgid is not the first, process is in a different + * PID namespace. + */ + nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid; + break; + } + } + + fclose(f); + free(statln); + return 0; +} + int nsinfo__init(struct nsinfo *nsi) { char oldns[PATH_MAX]; char spath[PATH_MAX]; char *newns = NULL; - char *statln = NULL; - char *nspid; struct stat old_stat; struct stat new_stat; - FILE *f = NULL; - size_t linesz = 0; int rv = -1; if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) @@ -100,34 +132,9 @@ int nsinfo__init(struct nsinfo *nsi) if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX) goto out; - f = fopen(spath, "r"); - if (f == NULL) - goto out; - - while (getline(&statln, &linesz, f) != -1) { - /* Use tgid if CONFIG_PID_NS is not defined. */ - if (strstr(statln, "Tgid:") != NULL) { - nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'), - NULL, 10); - nsi->nstgid = nsi->tgid; - } - - if (strstr(statln, "NStgid:") != NULL) { - nspid = strrchr(statln, '\t'); - nsi->nstgid = (pid_t)strtol(nspid, NULL, 10); - /* If innermost tgid is not the first, process is in a different - * PID namespace. - */ - nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid; - break; - } - } - rv = 0; + rv = nsinfo__get_nspid(nsi, spath); out: - if (f != NULL) - (void) fclose(f); - free(statln); free(newns); return rv; } @@ -299,3 +306,12 @@ int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi) return ret; } + +bool nsinfo__is_in_root_namespace(void) +{ + struct nsinfo nsi; + + memset(&nsi, 0x0, sizeof(nsi)); + nsinfo__get_nspid(&nsi, "/proc/self/status"); + return !nsi.in_pidns; +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index ad9775db7b9c..9ceea9643507 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -59,6 +59,8 @@ void nsinfo__mountns_exit(struct nscookie *nc); char *nsinfo__realpath(const char *path, struct nsinfo *nsi); int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi); +bool nsinfo__is_in_root_namespace(void); + static inline void __nsinfo__zput(struct nsinfo **nsip) { if (nsip) { diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c index b234d95fb10a..284f8eabd3b9 100644 --- a/tools/perf/util/parse-events-hybrid.c +++ b/tools/perf/util/parse-events-hybrid.c @@ -38,7 +38,8 @@ static void config_hybrid_attr(struct perf_event_attr *attr, static int create_event_hybrid(__u32 config_type, int *idx, struct list_head *list, - struct perf_event_attr *attr, char *name, + struct perf_event_attr *attr, const char *name, + const char *metric_id, struct list_head *config_terms, struct perf_pmu *pmu) { @@ -47,7 +48,7 @@ static int create_event_hybrid(__u32 config_type, int *idx, __u64 config = attr->config; config_hybrid_attr(attr, config_type, pmu->type); - evsel = parse_events__add_event_hybrid(list, idx, attr, name, + evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id, pmu, config_terms); if (evsel) evsel->pmu_name = strdup(pmu->name); @@ -62,15 +63,19 @@ static int create_event_hybrid(__u32 config_type, int *idx, static int pmu_cmp(struct parse_events_state *parse_state, struct perf_pmu *pmu) { - if (!parse_state->hybrid_pmu_name) - return 0; + if (parse_state->evlist && parse_state->evlist->hybrid_pmu_name) + return strcmp(parse_state->evlist->hybrid_pmu_name, pmu->name); + + if (parse_state->hybrid_pmu_name) + return strcmp(parse_state->hybrid_pmu_name, pmu->name); - return strcmp(parse_state->hybrid_pmu_name, pmu->name); + return 0; } static int add_hw_hybrid(struct parse_events_state *parse_state, struct list_head *list, struct perf_event_attr *attr, - char *name, struct list_head *config_terms) + const char *name, const char *metric_id, + struct list_head *config_terms) { struct perf_pmu *pmu; int ret; @@ -84,7 +89,7 @@ static int add_hw_hybrid(struct parse_events_state *parse_state, copy_config_terms(&terms, config_terms); ret = create_event_hybrid(PERF_TYPE_HARDWARE, &parse_state->idx, list, attr, name, - &terms, pmu); + metric_id, &terms, pmu); free_config_terms(&terms); if (ret) return ret; @@ -94,14 +99,16 @@ static int add_hw_hybrid(struct parse_events_state *parse_state, } static int create_raw_event_hybrid(int *idx, struct list_head *list, - struct perf_event_attr *attr, char *name, + struct perf_event_attr *attr, + const char *name, + const char *metric_id, struct list_head *config_terms, struct perf_pmu *pmu) { struct evsel *evsel; attr->type = pmu->type; - evsel = parse_events__add_event_hybrid(list, idx, attr, name, + evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id, pmu, config_terms); if (evsel) evsel->pmu_name = strdup(pmu->name); @@ -113,7 +120,8 @@ static int create_raw_event_hybrid(int *idx, struct list_head *list, static int add_raw_hybrid(struct parse_events_state *parse_state, struct list_head *list, struct perf_event_attr *attr, - char *name, struct list_head *config_terms) + const char *name, const char *metric_id, + struct list_head *config_terms) { struct perf_pmu *pmu; int ret; @@ -126,7 +134,7 @@ static int add_raw_hybrid(struct parse_events_state *parse_state, copy_config_terms(&terms, config_terms); ret = create_raw_event_hybrid(&parse_state->idx, list, attr, - name, &terms, pmu); + name, metric_id, &terms, pmu); free_config_terms(&terms); if (ret) return ret; @@ -138,7 +146,8 @@ static int add_raw_hybrid(struct parse_events_state *parse_state, int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, struct list_head *list, struct perf_event_attr *attr, - char *name, struct list_head *config_terms, + const char *name, const char *metric_id, + struct list_head *config_terms, bool *hybrid) { *hybrid = false; @@ -150,16 +159,18 @@ int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, *hybrid = true; if (attr->type != PERF_TYPE_RAW) { - return add_hw_hybrid(parse_state, list, attr, name, + return add_hw_hybrid(parse_state, list, attr, name, metric_id, config_terms); } - return add_raw_hybrid(parse_state, list, attr, name, + return add_raw_hybrid(parse_state, list, attr, name, metric_id, config_terms); } int parse_events__add_cache_hybrid(struct list_head *list, int *idx, - struct perf_event_attr *attr, char *name, + struct perf_event_attr *attr, + const char *name, + const char *metric_id, struct list_head *config_terms, bool *hybrid, struct parse_events_state *parse_state) @@ -180,7 +191,7 @@ int parse_events__add_cache_hybrid(struct list_head *list, int *idx, copy_config_terms(&terms, config_terms); ret = create_event_hybrid(PERF_TYPE_HW_CACHE, idx, list, - attr, name, &terms, pmu); + attr, name, metric_id, &terms, pmu); free_config_terms(&terms); if (ret) return ret; diff --git a/tools/perf/util/parse-events-hybrid.h b/tools/perf/util/parse-events-hybrid.h index f33bd67aa851..cbc05fec02a2 100644 --- a/tools/perf/util/parse-events-hybrid.h +++ b/tools/perf/util/parse-events-hybrid.h @@ -11,11 +11,13 @@ int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, struct list_head *list, struct perf_event_attr *attr, - char *name, struct list_head *config_terms, + const char *name, const char *metric_id, + struct list_head *config_terms, bool *hybrid); int parse_events__add_cache_hybrid(struct list_head *list, int *idx, - struct perf_event_attr *attr, char *name, + struct perf_event_attr *attr, + const char *name, const char *metric_id, struct list_head *config_terms, bool *hybrid, struct parse_events_state *parse_state); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 51a2219df601..9739b05b999e 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -19,8 +19,6 @@ #include <subcmd/exec-cmd.h> #include "string2.h" #include "strlist.h" -#include "symbol.h" -#include "header.h" #include "bpf-loader.h" #include "debug.h" #include <api/fs/tracing_path.h> @@ -193,39 +191,6 @@ static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir) #define MAX_EVENT_LENGTH 512 -void parse_events__handle_error(struct parse_events_error *err, int idx, - char *str, char *help) -{ - if (WARN(!str, "WARNING: failed to provide error string\n")) { - free(help); - return; - } - switch (err->num_errors) { - case 0: - err->idx = idx; - err->str = str; - err->help = help; - break; - case 1: - err->first_idx = err->idx; - err->idx = idx; - err->first_str = err->str; - err->str = str; - err->first_help = err->help; - err->help = help; - break; - default: - pr_debug("Multiple errors dropping message: %s (%s)\n", - err->str, err->help); - free(err->str); - err->str = str; - free(err->help); - err->help = help; - break; - } - err->num_errors++; -} - struct tracepoint_path *tracepoint_id_to_path(u64 config) { struct tracepoint_path *path = NULL; @@ -334,12 +299,7 @@ const char *event_type(int type) return "unknown"; } -static int parse_events__is_name_term(struct parse_events_term *term) -{ - return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; -} - -static char *get_config_name(struct list_head *head_terms) +static char *get_config_str(struct list_head *head_terms, int type_term) { struct parse_events_term *term; @@ -347,17 +307,27 @@ static char *get_config_name(struct list_head *head_terms) return NULL; list_for_each_entry(term, head_terms, list) - if (parse_events__is_name_term(term)) + if (term->type_term == type_term) return term->val.str; return NULL; } +static char *get_config_metric_id(struct list_head *head_terms) +{ + return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_METRIC_ID); +} + +static char *get_config_name(struct list_head *head_terms) +{ + return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME); +} + static struct evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, bool init_attr, - char *name, struct perf_pmu *pmu, + const char *name, const char *metric_id, struct perf_pmu *pmu, struct list_head *config_terms, bool auto_merge_stats, const char *cpu_list) { @@ -386,6 +356,9 @@ __add_event(struct list_head *list, int *idx, if (name) evsel->name = strdup(name); + if (metric_id) + evsel->metric_id = strdup(metric_id); + if (config_terms) list_splice_init(config_terms, &evsel->config_terms); @@ -396,18 +369,21 @@ __add_event(struct list_head *list, int *idx, } struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, - char *name, struct perf_pmu *pmu) + const char *name, const char *metric_id, + struct perf_pmu *pmu) { - return __add_event(NULL, &idx, attr, false, name, pmu, NULL, false, - NULL); + return __add_event(/*list=*/NULL, &idx, attr, /*init_attr=*/false, name, + metric_id, pmu, /*config_terms=*/NULL, + /*auto_merge_stats=*/false, /*cpu_list=*/NULL); } static int add_event(struct list_head *list, int *idx, - struct perf_event_attr *attr, char *name, - struct list_head *config_terms) + struct perf_event_attr *attr, const char *name, + const char *metric_id, struct list_head *config_terms) { - return __add_event(list, idx, attr, true, name, NULL, config_terms, - false, NULL) ? 0 : -ENOMEM; + return __add_event(list, idx, attr, /*init_attr*/true, name, metric_id, + /*pmu=*/NULL, config_terms, + /*auto_merge_stats=*/false, /*cpu_list=*/NULL) ? 0 : -ENOMEM; } static int add_event_tool(struct list_head *list, int *idx, @@ -419,13 +395,17 @@ static int add_event_tool(struct list_head *list, int *idx, .config = PERF_COUNT_SW_DUMMY, }; - evsel = __add_event(list, idx, &attr, true, NULL, NULL, NULL, false, - "0"); + evsel = __add_event(list, idx, &attr, /*init_attr=*/true, /*name=*/NULL, + /*metric_id=*/NULL, /*pmu=*/NULL, + /*config_terms=*/NULL, /*auto_merge_stats=*/false, + /*cpu_list=*/"0"); if (!evsel) return -ENOMEM; evsel->tool_event = tool_event; - if (tool_event == PERF_TOOL_DURATION_TIME) - evsel->unit = "ns"; + if (tool_event == PERF_TOOL_DURATION_TIME) { + free((char *)evsel->unit); + evsel->unit = strdup("ns"); + } return 0; } @@ -466,7 +446,8 @@ int parse_events_add_cache(struct list_head *list, int *idx, { struct perf_event_attr attr; LIST_HEAD(config_terms); - char name[MAX_NAME_LEN], *config_name; + char name[MAX_NAME_LEN]; + const char *config_name, *metric_id; int cache_type = -1, cache_op = -1, cache_result = -1; char *op_result[2] = { op_result1, op_result2 }; int i, n, ret; @@ -531,13 +512,17 @@ int parse_events_add_cache(struct list_head *list, int *idx, return -ENOMEM; } + metric_id = get_config_metric_id(head_config); ret = parse_events__add_cache_hybrid(list, idx, &attr, - config_name ? : name, &config_terms, + config_name ? : name, + metric_id, + &config_terms, &hybrid, parse_state); if (hybrid) goto out_free_terms; - ret = add_event(list, idx, &attr, config_name ? : name, &config_terms); + ret = add_event(list, idx, &attr, config_name ? : name, metric_id, + &config_terms); out_free_terms: free_config_terms(&config_terms); return ret; @@ -571,7 +556,7 @@ static void tracepoint_error(struct parse_events_error *e, int err, } tracing_path__strerror_open_tp(err, help, sizeof(help), sys, name); - parse_events__handle_error(e, 0, strdup(str), strdup(help)); + parse_events_error__handle(e, 0, strdup(str), strdup(help)); } static int add_tracepoint(struct list_head *list, int *idx, @@ -795,7 +780,7 @@ int parse_events_load_bpf_obj(struct parse_events_state *parse_state, return 0; errout: - parse_events__handle_error(parse_state->error, 0, + parse_events_error__handle(parse_state->error, 0, strdup(errbuf), strdup("(add -v to see detail)")); return err; } @@ -815,7 +800,7 @@ parse_events_config_bpf(struct parse_events_state *parse_state, int err; if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) { - parse_events__handle_error(parse_state->error, term->err_term, + parse_events_error__handle(parse_state->error, term->err_term, strdup("Invalid config term for BPF object"), NULL); return -EINVAL; @@ -835,7 +820,7 @@ parse_events_config_bpf(struct parse_events_state *parse_state, else idx = term->err_term + error_pos; - parse_events__handle_error(parse_state->error, idx, + parse_events_error__handle(parse_state->error, idx, strdup(errbuf), strdup( "Hint:\tValid config terms:\n" @@ -907,7 +892,7 @@ int parse_events_load_bpf(struct parse_events_state *parse_state, -err, errbuf, sizeof(errbuf)); - parse_events__handle_error(parse_state->error, 0, + parse_events_error__handle(parse_state->error, 0, strdup(errbuf), strdup("(add -v to see detail)")); return err; } @@ -931,7 +916,7 @@ int parse_events_load_bpf_obj(struct parse_events_state *parse_state, struct bpf_object *obj __maybe_unused, struct list_head *head_config __maybe_unused) { - parse_events__handle_error(parse_state->error, 0, + parse_events_error__handle(parse_state->error, 0, strdup("BPF support is not compiled"), strdup("Make sure libbpf-devel is available at build time.")); return -ENOTSUP; @@ -943,7 +928,7 @@ int parse_events_load_bpf(struct parse_events_state *parse_state, bool source __maybe_unused, struct list_head *head_config __maybe_unused) { - parse_events__handle_error(parse_state->error, 0, + parse_events_error__handle(parse_state->error, 0, strdup("BPF support is not compiled"), strdup("Make sure libbpf-devel is available at build time.")); return -ENOTSUP; @@ -1014,7 +999,8 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, attr.type = PERF_TYPE_BREAKPOINT; attr.sample_period = 1; - return add_event(list, idx, &attr, NULL, NULL); + return add_event(list, idx, &attr, /*name=*/NULL, /*mertic_id=*/NULL, + /*config_terms=*/NULL); } static int check_type_val(struct parse_events_term *term, @@ -1025,7 +1011,7 @@ static int check_type_val(struct parse_events_term *term, return 0; if (err) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, type == PARSE_EVENTS__TERM_TYPE_NUM ? strdup("expected numeric value") : strdup("expected string value"), @@ -1059,6 +1045,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", + [PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id", }; static bool config_term_shrinked; @@ -1069,7 +1056,7 @@ config_term_avail(int term_type, struct parse_events_error *err) char *err_str; if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) { - parse_events__handle_error(err, -1, + parse_events_error__handle(err, -1, strdup("Invalid term_type"), NULL); return false; } @@ -1081,6 +1068,7 @@ config_term_avail(int term_type, struct parse_events_error *err) case PARSE_EVENTS__TERM_TYPE_CONFIG1: case PARSE_EVENTS__TERM_TYPE_CONFIG2: case PARSE_EVENTS__TERM_TYPE_NAME: + case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: case PARSE_EVENTS__TERM_TYPE_PERCORE: return true; @@ -1091,7 +1079,7 @@ config_term_avail(int term_type, struct parse_events_error *err) /* term_type is validated so indexing is safe */ if (asprintf(&err_str, "'%s' is not usable in 'perf stat'", config_term_names[term_type]) >= 0) - parse_events__handle_error(err, -1, err_str, NULL); + parse_events_error__handle(err, -1, err_str, NULL); return false; } } @@ -1135,7 +1123,7 @@ do { \ if (strcmp(term->val.str, "no") && parse_branch_str(term->val.str, &attr->branch_sample_type)) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("invalid branch sample type"), NULL); return -EINVAL; @@ -1144,7 +1132,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_TIME: CHECK_TYPE_VAL(NUM); if (term->val.num > 1) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("expected 0 or 1"), NULL); return -EINVAL; @@ -1171,6 +1159,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_NAME: CHECK_TYPE_VAL(STR); break; + case PARSE_EVENTS__TERM_TYPE_METRIC_ID: + CHECK_TYPE_VAL(STR); + break; case PARSE_EVENTS__TERM_TYPE_MAX_STACK: CHECK_TYPE_VAL(NUM); break; @@ -1180,7 +1171,7 @@ do { \ case PARSE_EVENTS__TERM_TYPE_PERCORE: CHECK_TYPE_VAL(NUM); if ((unsigned int)term->val.num > 1) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("expected 0 or 1"), NULL); return -EINVAL; @@ -1192,14 +1183,14 @@ do { \ case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: CHECK_TYPE_VAL(NUM); if (term->val.num > UINT_MAX) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("too big"), NULL); return -EINVAL; } break; default: - parse_events__handle_error(err, term->err_term, + parse_events_error__handle(err, term->err_term, strdup("unknown term"), parse_events_formats_error_string(NULL)); return -EINVAL; @@ -1253,7 +1244,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr, return config_term_common(attr, term, err); default: if (err) { - parse_events__handle_error(err, term->err_term, + parse_events_error__handle(err, term->err_term, strdup("unknown term"), strdup("valid terms: call-graph,stack-size\n")); } @@ -1440,6 +1431,7 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, { struct perf_event_attr attr; LIST_HEAD(config_terms); + const char *name, *metric_id; bool hybrid; int ret; @@ -1456,14 +1448,16 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, return -ENOMEM; } + name = get_config_name(head_config); + metric_id = get_config_metric_id(head_config); ret = parse_events__add_numeric_hybrid(parse_state, list, &attr, - get_config_name(head_config), + name, metric_id, &config_terms, &hybrid); if (hybrid) goto out_free_terms; - ret = add_event(list, &parse_state->idx, &attr, - get_config_name(head_config), &config_terms); + ret = add_event(list, &parse_state->idx, &attr, name, metric_id, + &config_terms); out_free_terms: free_config_terms(&config_terms); return ret; @@ -1471,7 +1465,7 @@ out_free_terms: int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, - enum perf_tool_event tool_event) + int tool_event) { return add_event_tool(list, &parse_state->idx, tool_event); } @@ -1549,7 +1543,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (asprintf(&err_str, "Cannot find PMU `%s'. Missing kernel support?", name) >= 0) - parse_events__handle_error(err, 0, err_str, NULL); + parse_events_error__handle(err, 0, err_str, NULL); return -EINVAL; } @@ -1564,8 +1558,11 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &parse_state->idx, &attr, true, NULL, - pmu, NULL, auto_merge_stats, NULL); + evsel = __add_event(list, &parse_state->idx, &attr, + /*init_attr=*/true, /*name=*/NULL, + /*metric_id=*/NULL, pmu, + /*config_terms=*/NULL, auto_merge_stats, + /*cpu_list=*/NULL); if (evsel) { evsel->pmu_name = name ? strdup(name) : NULL; evsel->use_uncore_alias = use_uncore_alias; @@ -1618,9 +1615,10 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, return -EINVAL; } - evsel = __add_event(list, &parse_state->idx, &attr, true, - get_config_name(head_config), pmu, - &config_terms, auto_merge_stats, NULL); + evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true, + get_config_name(head_config), + get_config_metric_id(head_config), pmu, + &config_terms, auto_merge_stats, /*cpu_list=*/NULL); if (!evsel) return -ENOMEM; @@ -1634,7 +1632,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (parse_state->fake_pmu) return 0; - evsel->unit = info.unit; + free((char *)evsel->unit); + evsel->unit = strdup(info.unit); evsel->scale = info.scale; evsel->per_pkg = info.per_pkg; evsel->snapshot = info.snapshot; @@ -1644,44 +1643,50 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, } int parse_events_multi_pmu_add(struct parse_events_state *parse_state, - char *str, struct list_head **listp) + char *str, struct list_head *head, + struct list_head **listp) { struct parse_events_term *term; - struct list_head *list; + struct list_head *list = NULL; struct perf_pmu *pmu = NULL; int ok = 0; + char *config; *listp = NULL; + + if (!head) { + head = malloc(sizeof(struct list_head)); + if (!head) + goto out_err; + + INIT_LIST_HEAD(head); + } + config = strdup(str); + if (!config) + goto out_err; + + if (parse_events_term__num(&term, + PARSE_EVENTS__TERM_TYPE_USER, + config, 1, false, &config, + NULL) < 0) { + free(config); + goto out_err; + } + list_add_tail(&term->list, head); + + /* Add it for all PMUs that support the alias */ list = malloc(sizeof(struct list_head)); if (!list) - return -1; + goto out_err; + INIT_LIST_HEAD(list); + while ((pmu = perf_pmu__scan(pmu)) != NULL) { struct perf_pmu_alias *alias; list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { - struct list_head *head; - char *config; - - head = malloc(sizeof(struct list_head)); - if (!head) - return -1; - INIT_LIST_HEAD(head); - config = strdup(str); - if (!config) - return -1; - if (parse_events_term__num(&term, - PARSE_EVENTS__TERM_TYPE_USER, - config, 1, false, &config, - NULL) < 0) { - free(list); - free(config); - return -1; - } - list_add_tail(&term->list, head); - if (!parse_events_add_pmu(parse_state, list, pmu->name, head, true, true)) { @@ -1689,17 +1694,26 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, pmu->name, alias->str); ok++; } - - parse_events_terms__delete(head); } } } - if (!ok) { - free(list); - return -1; + + if (parse_state->fake_pmu) { + if (!parse_events_add_pmu(parse_state, list, str, head, + true, true)) { + pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str); + ok++; + } } - *listp = list; - return 0; + +out_err: + if (ok) + *listp = list; + else + free(list); + + parse_events_terms__delete(head); + return ok ? 0 : -1; } int parse_events__modifier_group(struct list_head *list, @@ -1819,6 +1833,11 @@ out: return ret; } +__weak struct evsel *arch_evlist__leader(struct list_head *list) +{ + return list_first_entry(list, struct evsel, core.node); +} + void parse_events__set_leader(char *name, struct list_head *list, struct parse_events_state *parse_state) { @@ -1832,9 +1851,10 @@ void parse_events__set_leader(char *name, struct list_head *list, if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) return; - __perf_evlist__set_leader(list); - leader = list_entry(list->next, struct evsel, core.node); + leader = arch_evlist__leader(list); + __perf_evlist__set_leader(list, &leader->core); leader->group_name = name ? strdup(name) : NULL; + list_move(&leader->core.node, list); } /* list_event is assumed to point to malloc'ed memory */ @@ -2029,7 +2049,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) return 0; } -int parse_events_name(struct list_head *list, char *name) +int parse_events_name(struct list_head *list, const char *name) { struct evsel *evsel; @@ -2087,8 +2107,17 @@ static void perf_pmu__parse_init(void) pmu = NULL; while ((pmu = perf_pmu__scan(pmu)) != NULL) { list_for_each_entry(alias, &pmu->aliases, list) { - if (strchr(alias->name, '-')) + char *tmp = strchr(alias->name, '-'); + + if (tmp) { + char *tmp2 = NULL; + + tmp2 = strchr(tmp + 1, '-'); len++; + if (tmp2) + len++; + } + len++; } } @@ -2108,8 +2137,20 @@ static void perf_pmu__parse_init(void) list_for_each_entry(alias, &pmu->aliases, list) { struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; char *tmp = strchr(alias->name, '-'); + char *tmp2 = NULL; - if (tmp != NULL) { + if (tmp) + tmp2 = strchr(tmp + 1, '-'); + if (tmp2) { + SET_SYMBOL(strndup(alias->name, tmp - alias->name), + PMU_EVENT_SYMBOL_PREFIX); + p++; + tmp++; + SET_SYMBOL(strndup(tmp, tmp2 - tmp), PMU_EVENT_SYMBOL_SUFFIX); + p++; + SET_SYMBOL(strdup(++tmp2), PMU_EVENT_SYMBOL_SUFFIX2); + len += 3; + } else if (tmp) { SET_SYMBOL(strndup(alias->name, tmp - alias->name), PMU_EVENT_SYMBOL_PREFIX); p++; @@ -2136,23 +2177,38 @@ err: */ int perf_pmu__test_parse_init(void) { - struct perf_pmu_event_symbol *list; + struct perf_pmu_event_symbol *list, *tmp, symbols[] = { + {(char *)"read", PMU_EVENT_SYMBOL}, + {(char *)"event", PMU_EVENT_SYMBOL_PREFIX}, + {(char *)"two", PMU_EVENT_SYMBOL_SUFFIX}, + {(char *)"hyphen", PMU_EVENT_SYMBOL_SUFFIX}, + {(char *)"hyph", PMU_EVENT_SYMBOL_SUFFIX2}, + }; + unsigned long i, j; - list = malloc(sizeof(*list) * 1); + tmp = list = malloc(sizeof(*list) * ARRAY_SIZE(symbols)); if (!list) return -ENOMEM; - list->type = PMU_EVENT_SYMBOL; - list->symbol = strdup("read"); - - if (!list->symbol) { - free(list); - return -ENOMEM; + for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) { + tmp->type = symbols[i].type; + tmp->symbol = strdup(symbols[i].symbol); + if (!list->symbol) + goto err_free; } perf_pmu_events_list = list; - perf_pmu_events_list_num = 1; + perf_pmu_events_list_num = ARRAY_SIZE(symbols); + + qsort(perf_pmu_events_list, ARRAY_SIZE(symbols), + sizeof(struct perf_pmu_event_symbol), comp_pmu); return 0; + +err_free: + for (j = 0, tmp = list; j < i; j++, tmp++) + free(tmp->symbol); + free(list); + return -ENOMEM; } enum perf_pmu_event_symbol_type @@ -2299,6 +2355,52 @@ int __parse_events(struct evlist *evlist, const char *str, return ret; } +void parse_events_error__init(struct parse_events_error *err) +{ + bzero(err, sizeof(*err)); +} + +void parse_events_error__exit(struct parse_events_error *err) +{ + zfree(&err->str); + zfree(&err->help); + zfree(&err->first_str); + zfree(&err->first_help); +} + +void parse_events_error__handle(struct parse_events_error *err, int idx, + char *str, char *help) +{ + if (WARN(!str, "WARNING: failed to provide error string\n")) { + free(help); + return; + } + switch (err->num_errors) { + case 0: + err->idx = idx; + err->str = str; + err->help = help; + break; + case 1: + err->first_idx = err->idx; + err->idx = idx; + err->first_str = err->str; + err->str = str; + err->first_help = err->help; + err->help = help; + break; + default: + pr_debug("Multiple errors dropping message: %s (%s)\n", + err->str, err->help); + free(err->str); + err->str = str; + free(err->help); + err->help = help; + break; + } + err->num_errors++; +} + #define MAX_WIDTH 1000 static int get_term_width(void) { @@ -2308,8 +2410,8 @@ static int get_term_width(void) return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col; } -static void __parse_events_print_error(int err_idx, const char *err_str, - const char *err_help, const char *event) +static void __parse_events_error__print(int err_idx, const char *err_str, + const char *err_help, const char *event) { const char *str = "invalid or unsupported event: "; char _buf[MAX_WIDTH]; @@ -2363,22 +2465,18 @@ static void __parse_events_print_error(int err_idx, const char *err_str, } } -void parse_events_print_error(struct parse_events_error *err, - const char *event) +void parse_events_error__print(struct parse_events_error *err, + const char *event) { if (!err->num_errors) return; - __parse_events_print_error(err->idx, err->str, err->help, event); - zfree(&err->str); - zfree(&err->help); + __parse_events_error__print(err->idx, err->str, err->help, event); if (err->num_errors > 1) { fputs("\nInitial error:\n", stderr); - __parse_events_print_error(err->first_idx, err->first_str, + __parse_events_error__print(err->first_idx, err->first_str, err->first_help, event); - zfree(&err->first_str); - zfree(&err->first_help); } } @@ -2391,13 +2489,14 @@ int parse_events_option(const struct option *opt, const char *str, struct parse_events_error err; int ret; - bzero(&err, sizeof(err)); + parse_events_error__init(&err); ret = parse_events(evlist, str, &err); if (ret) { - parse_events_print_error(&err, str); + parse_events_error__print(&err, str); fprintf(stderr, "Run 'perf list' for a list of valid events\n"); } + parse_events_error__exit(&err); return ret; } @@ -2703,7 +2802,7 @@ next: return 0; } -static bool is_event_supported(u8 type, unsigned config) +static bool is_event_supported(u8 type, u64 config) { bool ret = true; int open_return; @@ -2823,10 +2922,18 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, int print_hwcache_events(const char *event_glob, bool name_only) { - unsigned int type, op, i, evt_i = 0, evt_num = 0; - char name[64]; - char **evt_list = NULL; + unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0; + char name[64], new_name[128]; + char **evt_list = NULL, **evt_pmus = NULL; bool evt_num_known = false; + struct perf_pmu *pmu = NULL; + + if (perf_pmu__has_hybrid()) { + npmus = perf_pmu__hybrid_pmu_num(); + evt_pmus = zalloc(sizeof(char *) * npmus); + if (!evt_pmus) + goto out_enomem; + } restart: if (evt_num_known) { @@ -2842,20 +2949,61 @@ restart: continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + unsigned int hybrid_supported = 0, j; + bool supported; + __evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name)); if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; - if (!is_event_supported(PERF_TYPE_HW_CACHE, - type | (op << 8) | (i << 16))) - continue; + if (!perf_pmu__has_hybrid()) { + if (!is_event_supported(PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16))) { + continue; + } + } else { + perf_pmu__for_each_hybrid_pmu(pmu) { + if (!evt_num_known) { + evt_num++; + continue; + } + + supported = is_event_supported( + PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16) | + ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT)); + if (supported) { + snprintf(new_name, sizeof(new_name), "%s/%s/", + pmu->name, name); + evt_pmus[hybrid_supported] = strdup(new_name); + hybrid_supported++; + } + } + + if (hybrid_supported == 0) + continue; + } if (!evt_num_known) { evt_num++; continue; } - evt_list[evt_i] = strdup(name); + if ((hybrid_supported == 0) || + (hybrid_supported == npmus)) { + evt_list[evt_i] = strdup(name); + if (npmus > 0) { + for (j = 0; j < npmus; j++) + zfree(&evt_pmus[j]); + } + } else { + for (j = 0; j < hybrid_supported; j++) { + evt_list[evt_i++] = evt_pmus[j]; + evt_pmus[j] = NULL; + } + continue; + } + if (evt_list[evt_i] == NULL) goto out_enomem; evt_i++; @@ -2867,6 +3015,13 @@ restart: evt_num_known = true; goto restart; } + + for (evt_i = 0; evt_i < evt_num; evt_i++) { + if (!evt_list[evt_i]) + break; + } + + evt_num = evt_i; qsort(evt_list, evt_num, sizeof(char *), cmp_string); evt_i = 0; while (evt_i < evt_num) { @@ -2885,6 +3040,10 @@ out_free: for (evt_i = 0; evt_i < evt_num; evt_i++) zfree(&evt_list[evt_i]); zfree(&evt_list); + + for (evt_i = 0; evt_i < npmus; evt_i++) + zfree(&evt_pmus[evt_i]); + zfree(&evt_pmus); return evt_num; out_enomem: @@ -2994,7 +3153,8 @@ out_enomem: * Print the help text for the event symbols: */ void print_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc, bool details_flag, bool deprecated) + bool long_desc, bool details_flag, bool deprecated, + const char *pmu_name) { print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); @@ -3006,7 +3166,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_hwcache_events(event_glob, name_only); print_pmu_events(event_glob, name_only, quiet_flag, long_desc, - details_flag, deprecated); + details_flag, deprecated, pmu_name); if (event_glob != NULL) return; @@ -3032,7 +3192,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_sdt_events(NULL, NULL, name_only); - metricgroup__print(true, true, NULL, name_only, details_flag); + metricgroup__print(true, true, NULL, name_only, details_flag, + pmu_name); print_libpfm_events(name_only, long_desc); } @@ -3083,7 +3244,7 @@ int parse_events_term__num(struct parse_events_term **term, struct parse_events_term temp = { .type_val = PARSE_EVENTS__TERM_TYPE_NUM, .type_term = type_term, - .config = config, + .config = config ? : strdup(config_term_names[type_term]), .no_value = no_value, .err_term = loc_term ? loc_term->first_column : 0, .err_val = loc_val ? loc_val->first_column : 0, @@ -3227,7 +3388,7 @@ void parse_events_evlist_error(struct parse_events_state *parse_state, if (!parse_state->error) return; - parse_events__handle_error(parse_state->error, idx, strdup(str), NULL); + parse_events_error__handle(parse_state->error, idx, strdup(str), NULL); } static void config_terms_list(char *buf, size_t buf_sz) @@ -3286,9 +3447,12 @@ fail: struct evsel *parse_events__add_event_hybrid(struct list_head *list, int *idx, struct perf_event_attr *attr, - char *name, struct perf_pmu *pmu, + const char *name, + const char *metric_id, + struct perf_pmu *pmu, struct list_head *config_terms) { - return __add_event(list, idx, attr, true, name, pmu, - config_terms, false, NULL); + return __add_event(list, idx, attr, /*init_attr=*/true, name, metric_id, + pmu, config_terms, /*auto_merge_stats=*/false, + /*cpu_list=*/NULL); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index bf6e41aa9b6a..a38b8b160e80 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -53,6 +53,7 @@ enum perf_pmu_event_symbol_type { PMU_EVENT_SYMBOL, /* normal style PMU event */ PMU_EVENT_SYMBOL_PREFIX, /* prefix of pre-suf style event */ PMU_EVENT_SYMBOL_SUFFIX, /* suffix of pre-suf style event */ + PMU_EVENT_SYMBOL_SUFFIX2, /* suffix of pre-suf2 style event */ }; struct perf_pmu_event_symbol { @@ -87,6 +88,7 @@ enum { PARSE_EVENTS__TERM_TYPE_PERCORE, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, + PARSE_EVENTS__TERM_TYPE_METRIC_ID, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -141,8 +143,6 @@ struct parse_events_state { char *hybrid_pmu_name; }; -void parse_events__handle_error(struct parse_events_error *err, int idx, - char *str, char *help); void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, @@ -162,7 +162,7 @@ void parse_events_terms__purge(struct list_head *terms); void parse_events__clear_array(struct parse_events_array *a); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); -int parse_events_name(struct list_head *list, char *name); +int parse_events_name(struct list_head *list, const char *name); int parse_events_add_tracepoint(struct list_head *list, int *idx, const char *sys, const char *event, struct parse_events_error *error, @@ -182,10 +182,9 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config); -enum perf_tool_event; int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, - enum perf_tool_event tool_event); + int tool_event); int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2, struct parse_events_error *error, @@ -200,10 +199,12 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, bool use_alias); struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, - char *name, struct perf_pmu *pmu); + const char *name, const char *metric_id, + struct perf_pmu *pmu); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, + struct list_head *head_config, struct list_head **listp); int parse_events_copy_term_list(struct list_head *old, @@ -219,7 +220,8 @@ void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str); void print_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc, bool details_flag, bool deprecated); + bool long_desc, bool details_flag, bool deprecated, + const char *pmu_name); struct event_symbol { const char *symbol; @@ -241,8 +243,12 @@ int is_valid_tracepoint(const char *event_string); int valid_event_mount(const char *eventfs); char *parse_events_formats_error_string(char *additional_terms); -void parse_events_print_error(struct parse_events_error *err, - const char *event); +void parse_events_error__init(struct parse_events_error *err); +void parse_events_error__exit(struct parse_events_error *err); +void parse_events_error__handle(struct parse_events_error *err, int idx, + char *str, char *help); +void parse_events_error__print(struct parse_events_error *err, + const char *event); #ifdef HAVE_LIBELF_SUPPORT /* @@ -267,7 +273,9 @@ int perf_pmu__test_parse_init(void); struct evsel *parse_events__add_event_hybrid(struct list_head *list, int *idx, struct perf_event_attr *attr, - char *name, struct perf_pmu *pmu, + const char *name, + const char *metric_id, + struct perf_pmu *pmu, struct list_head *config_terms); #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 923849024b15..5b6e4b5249cf 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -12,7 +12,6 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> -#include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" #include "evsel.h" @@ -139,18 +138,25 @@ static int pmu_str_check(yyscan_t scanner, struct parse_events_state *parse_stat yylval->str = strdup(text); - if (parse_state->fake_pmu) - return PE_PMU_EVENT_FAKE; - + /* + * If we're not testing then parse check determines the PMU event type + * which if it isn't a PMU returns PE_NAME. When testing the result of + * parse check can't be trusted so we return PE_PMU_EVENT_FAKE unless + * an '!' is present in which case the text can't be a PMU name. + */ switch (perf_pmu__parse_check(text)) { case PMU_EVENT_SYMBOL_PREFIX: return PE_PMU_EVENT_PRE; case PMU_EVENT_SYMBOL_SUFFIX: return PE_PMU_EVENT_SUF; + case PMU_EVENT_SYMBOL_SUFFIX2: + return PE_PMU_EVENT_SUF2; case PMU_EVENT_SYMBOL: - return PE_KERNEL_PMU_EVENT; + return parse_state->fake_pmu + ? PE_PMU_EVENT_FAKE : PE_KERNEL_PMU_EVENT; default: - return PE_NAME; + return parse_state->fake_pmu && !strchr(text,'!') + ? PE_PMU_EVENT_FAKE : PE_NAME; } } @@ -205,7 +211,7 @@ bpf_source [^,{}]+\.c[a-zA-Z0-9._]* num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ -name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]* +name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!]* name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? @@ -295,6 +301,7 @@ no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } +metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } r{num_raw_hex} { return raw(yyscanner); } r0x{num_raw_hex} { return raw(yyscanner); } , { return ','; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index d94e48e1ff9b..be8c51770051 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -69,7 +69,7 @@ static void inc_group_count(struct list_head *list, %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP %token PE_ERROR -%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE +%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_PMU_EVENT_SUF2 PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %token PE_ARRAY_ALL PE_ARRAY_RANGE %token PE_DRV_CFG_TERM %type <num> PE_VALUE @@ -87,7 +87,7 @@ static void inc_group_count(struct list_head *list, %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME -%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE +%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_PMU_EVENT_SUF2 PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %type <str> PE_DRV_CFG_TERM %type <str> event_pmu_name %destructor { free ($$); } <str> @@ -183,6 +183,11 @@ group_def ':' PE_MODIFIER_EVENT err = parse_events__modifier_group(list, $3); free($3); if (err) { + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; + + parse_events_error__handle(error, @3.first_column, + strdup("Bad modifier"), NULL); free_list_evsel(list); YYABORT; } @@ -240,6 +245,11 @@ event_name PE_MODIFIER_EVENT err = parse_events__modifier_event(list, $2, false); free($2); if (err) { + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; + + parse_events_error__handle(error, @2.first_column, + strdup("Bad modifier"), NULL); free_list_evsel(list); YYABORT; } @@ -342,13 +352,39 @@ PE_KERNEL_PMU_EVENT sep_dc struct list_head *list; int err; - err = parse_events_multi_pmu_add(_parse_state, $1, &list); + err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list); + free($1); + if (err < 0) + YYABORT; + $$ = list; +} +| +PE_KERNEL_PMU_EVENT opt_pmu_config +{ + struct list_head *list; + int err; + + /* frees $2 */ + err = parse_events_multi_pmu_add(_parse_state, $1, $2, &list); free($1); if (err < 0) YYABORT; $$ = list; } | +PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF '-' PE_PMU_EVENT_SUF2 sep_dc +{ + struct list_head *list; + char pmu_name[128]; + snprintf(pmu_name, sizeof(pmu_name), "%s-%s-%s", $1, $3, $5); + free($1); + free($3); + free($5); + if (parse_events_multi_pmu_add(_parse_state, pmu_name, NULL, &list) < 0) + YYABORT; + $$ = list; +} +| PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc { struct list_head *list; @@ -357,7 +393,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc snprintf(pmu_name, sizeof(pmu_name), "%s-%s", $1, $3); free($1); free($3); - if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0) + if (parse_events_multi_pmu_add(_parse_state, pmu_name, NULL, &list) < 0) YYABORT; $$ = list; } diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index 020411682a3c..c28dd50bd571 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -11,7 +11,7 @@ typedef void (*setup_probe_fn_t)(struct evsel *evsel); -static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) +static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const char *str) { struct evlist *evlist; struct evsel *evsel; @@ -29,7 +29,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) evsel = evlist__first(evlist); while (1) { - fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags); if (fd < 0) { if (pid == -1 && errno == EACCES) { pid = 0; @@ -43,7 +43,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) fn(evsel); - fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags); + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags); if (fd < 0) { if (errno == EINVAL) err = -EINVAL; @@ -61,12 +61,13 @@ static bool perf_probe_api(setup_probe_fn_t fn) { const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL}; struct perf_cpu_map *cpus; - int cpu, ret, i = 0; + struct perf_cpu cpu; + int ret, i = 0; cpus = perf_cpu_map__new(NULL); if (!cpus) return false; - cpu = cpus->map[0]; + cpu = perf_cpu_map__cpu(cpus, 0); perf_cpu_map__put(cpus); do { @@ -136,15 +137,17 @@ bool perf_can_record_cpu_wide(void) .exclude_kernel = 1, }; struct perf_cpu_map *cpus; - int cpu, fd; + struct perf_cpu cpu; + int fd; cpus = perf_cpu_map__new(NULL); if (!cpus) return false; - cpu = cpus->map[0]; + + cpu = perf_cpu_map__cpu(cpus, 0); perf_cpu_map__put(cpus); - fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); + fd = sys_perf_event_open(&attr, -1, cpu.cpu, -1, 0); if (fd < 0) return false; close(fd); diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 47b7531f51da..98af3fa4ea35 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -52,7 +52,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value) bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), - bit_name(HW_INDEX), + bit_name(TYPE_SAVE), bit_name(HW_INDEX), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 5ee47ae1509c..a982e40ee5a9 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <string.h> #include "perf_regs.h" #include "event.h" @@ -20,11 +21,679 @@ uint64_t __weak arch__user_reg_mask(void) } #ifdef HAVE_PERF_REGS_SUPPORT + +#define perf_event_arm_regs perf_event_arm64_regs +#include "../../arch/arm64/include/uapi/asm/perf_regs.h" +#undef perf_event_arm_regs + +#include "../../arch/arm/include/uapi/asm/perf_regs.h" +#include "../../arch/csky/include/uapi/asm/perf_regs.h" +#include "../../arch/mips/include/uapi/asm/perf_regs.h" +#include "../../arch/powerpc/include/uapi/asm/perf_regs.h" +#include "../../arch/riscv/include/uapi/asm/perf_regs.h" +#include "../../arch/s390/include/uapi/asm/perf_regs.h" +#include "../../arch/x86/include/uapi/asm/perf_regs.h" + +static const char *__perf_reg_name_arm64(int id) +{ + switch (id) { + case PERF_REG_ARM64_X0: + return "x0"; + case PERF_REG_ARM64_X1: + return "x1"; + case PERF_REG_ARM64_X2: + return "x2"; + case PERF_REG_ARM64_X3: + return "x3"; + case PERF_REG_ARM64_X4: + return "x4"; + case PERF_REG_ARM64_X5: + return "x5"; + case PERF_REG_ARM64_X6: + return "x6"; + case PERF_REG_ARM64_X7: + return "x7"; + case PERF_REG_ARM64_X8: + return "x8"; + case PERF_REG_ARM64_X9: + return "x9"; + case PERF_REG_ARM64_X10: + return "x10"; + case PERF_REG_ARM64_X11: + return "x11"; + case PERF_REG_ARM64_X12: + return "x12"; + case PERF_REG_ARM64_X13: + return "x13"; + case PERF_REG_ARM64_X14: + return "x14"; + case PERF_REG_ARM64_X15: + return "x15"; + case PERF_REG_ARM64_X16: + return "x16"; + case PERF_REG_ARM64_X17: + return "x17"; + case PERF_REG_ARM64_X18: + return "x18"; + case PERF_REG_ARM64_X19: + return "x19"; + case PERF_REG_ARM64_X20: + return "x20"; + case PERF_REG_ARM64_X21: + return "x21"; + case PERF_REG_ARM64_X22: + return "x22"; + case PERF_REG_ARM64_X23: + return "x23"; + case PERF_REG_ARM64_X24: + return "x24"; + case PERF_REG_ARM64_X25: + return "x25"; + case PERF_REG_ARM64_X26: + return "x26"; + case PERF_REG_ARM64_X27: + return "x27"; + case PERF_REG_ARM64_X28: + return "x28"; + case PERF_REG_ARM64_X29: + return "x29"; + case PERF_REG_ARM64_SP: + return "sp"; + case PERF_REG_ARM64_LR: + return "lr"; + case PERF_REG_ARM64_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_arm(int id) +{ + switch (id) { + case PERF_REG_ARM_R0: + return "r0"; + case PERF_REG_ARM_R1: + return "r1"; + case PERF_REG_ARM_R2: + return "r2"; + case PERF_REG_ARM_R3: + return "r3"; + case PERF_REG_ARM_R4: + return "r4"; + case PERF_REG_ARM_R5: + return "r5"; + case PERF_REG_ARM_R6: + return "r6"; + case PERF_REG_ARM_R7: + return "r7"; + case PERF_REG_ARM_R8: + return "r8"; + case PERF_REG_ARM_R9: + return "r9"; + case PERF_REG_ARM_R10: + return "r10"; + case PERF_REG_ARM_FP: + return "fp"; + case PERF_REG_ARM_IP: + return "ip"; + case PERF_REG_ARM_SP: + return "sp"; + case PERF_REG_ARM_LR: + return "lr"; + case PERF_REG_ARM_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_csky(int id) +{ + switch (id) { + case PERF_REG_CSKY_A0: + return "a0"; + case PERF_REG_CSKY_A1: + return "a1"; + case PERF_REG_CSKY_A2: + return "a2"; + case PERF_REG_CSKY_A3: + return "a3"; + case PERF_REG_CSKY_REGS0: + return "regs0"; + case PERF_REG_CSKY_REGS1: + return "regs1"; + case PERF_REG_CSKY_REGS2: + return "regs2"; + case PERF_REG_CSKY_REGS3: + return "regs3"; + case PERF_REG_CSKY_REGS4: + return "regs4"; + case PERF_REG_CSKY_REGS5: + return "regs5"; + case PERF_REG_CSKY_REGS6: + return "regs6"; + case PERF_REG_CSKY_REGS7: + return "regs7"; + case PERF_REG_CSKY_REGS8: + return "regs8"; + case PERF_REG_CSKY_REGS9: + return "regs9"; + case PERF_REG_CSKY_SP: + return "sp"; + case PERF_REG_CSKY_LR: + return "lr"; + case PERF_REG_CSKY_PC: + return "pc"; +#if defined(__CSKYABIV2__) + case PERF_REG_CSKY_EXREGS0: + return "exregs0"; + case PERF_REG_CSKY_EXREGS1: + return "exregs1"; + case PERF_REG_CSKY_EXREGS2: + return "exregs2"; + case PERF_REG_CSKY_EXREGS3: + return "exregs3"; + case PERF_REG_CSKY_EXREGS4: + return "exregs4"; + case PERF_REG_CSKY_EXREGS5: + return "exregs5"; + case PERF_REG_CSKY_EXREGS6: + return "exregs6"; + case PERF_REG_CSKY_EXREGS7: + return "exregs7"; + case PERF_REG_CSKY_EXREGS8: + return "exregs8"; + case PERF_REG_CSKY_EXREGS9: + return "exregs9"; + case PERF_REG_CSKY_EXREGS10: + return "exregs10"; + case PERF_REG_CSKY_EXREGS11: + return "exregs11"; + case PERF_REG_CSKY_EXREGS12: + return "exregs12"; + case PERF_REG_CSKY_EXREGS13: + return "exregs13"; + case PERF_REG_CSKY_EXREGS14: + return "exregs14"; + case PERF_REG_CSKY_TLS: + return "tls"; + case PERF_REG_CSKY_HI: + return "hi"; + case PERF_REG_CSKY_LO: + return "lo"; +#endif + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_mips(int id) +{ + switch (id) { + case PERF_REG_MIPS_PC: + return "PC"; + case PERF_REG_MIPS_R1: + return "$1"; + case PERF_REG_MIPS_R2: + return "$2"; + case PERF_REG_MIPS_R3: + return "$3"; + case PERF_REG_MIPS_R4: + return "$4"; + case PERF_REG_MIPS_R5: + return "$5"; + case PERF_REG_MIPS_R6: + return "$6"; + case PERF_REG_MIPS_R7: + return "$7"; + case PERF_REG_MIPS_R8: + return "$8"; + case PERF_REG_MIPS_R9: + return "$9"; + case PERF_REG_MIPS_R10: + return "$10"; + case PERF_REG_MIPS_R11: + return "$11"; + case PERF_REG_MIPS_R12: + return "$12"; + case PERF_REG_MIPS_R13: + return "$13"; + case PERF_REG_MIPS_R14: + return "$14"; + case PERF_REG_MIPS_R15: + return "$15"; + case PERF_REG_MIPS_R16: + return "$16"; + case PERF_REG_MIPS_R17: + return "$17"; + case PERF_REG_MIPS_R18: + return "$18"; + case PERF_REG_MIPS_R19: + return "$19"; + case PERF_REG_MIPS_R20: + return "$20"; + case PERF_REG_MIPS_R21: + return "$21"; + case PERF_REG_MIPS_R22: + return "$22"; + case PERF_REG_MIPS_R23: + return "$23"; + case PERF_REG_MIPS_R24: + return "$24"; + case PERF_REG_MIPS_R25: + return "$25"; + case PERF_REG_MIPS_R28: + return "$28"; + case PERF_REG_MIPS_R29: + return "$29"; + case PERF_REG_MIPS_R30: + return "$30"; + case PERF_REG_MIPS_R31: + return "$31"; + default: + break; + } + return NULL; +} + +static const char *__perf_reg_name_powerpc(int id) +{ + switch (id) { + case PERF_REG_POWERPC_R0: + return "r0"; + case PERF_REG_POWERPC_R1: + return "r1"; + case PERF_REG_POWERPC_R2: + return "r2"; + case PERF_REG_POWERPC_R3: + return "r3"; + case PERF_REG_POWERPC_R4: + return "r4"; + case PERF_REG_POWERPC_R5: + return "r5"; + case PERF_REG_POWERPC_R6: + return "r6"; + case PERF_REG_POWERPC_R7: + return "r7"; + case PERF_REG_POWERPC_R8: + return "r8"; + case PERF_REG_POWERPC_R9: + return "r9"; + case PERF_REG_POWERPC_R10: + return "r10"; + case PERF_REG_POWERPC_R11: + return "r11"; + case PERF_REG_POWERPC_R12: + return "r12"; + case PERF_REG_POWERPC_R13: + return "r13"; + case PERF_REG_POWERPC_R14: + return "r14"; + case PERF_REG_POWERPC_R15: + return "r15"; + case PERF_REG_POWERPC_R16: + return "r16"; + case PERF_REG_POWERPC_R17: + return "r17"; + case PERF_REG_POWERPC_R18: + return "r18"; + case PERF_REG_POWERPC_R19: + return "r19"; + case PERF_REG_POWERPC_R20: + return "r20"; + case PERF_REG_POWERPC_R21: + return "r21"; + case PERF_REG_POWERPC_R22: + return "r22"; + case PERF_REG_POWERPC_R23: + return "r23"; + case PERF_REG_POWERPC_R24: + return "r24"; + case PERF_REG_POWERPC_R25: + return "r25"; + case PERF_REG_POWERPC_R26: + return "r26"; + case PERF_REG_POWERPC_R27: + return "r27"; + case PERF_REG_POWERPC_R28: + return "r28"; + case PERF_REG_POWERPC_R29: + return "r29"; + case PERF_REG_POWERPC_R30: + return "r30"; + case PERF_REG_POWERPC_R31: + return "r31"; + case PERF_REG_POWERPC_NIP: + return "nip"; + case PERF_REG_POWERPC_MSR: + return "msr"; + case PERF_REG_POWERPC_ORIG_R3: + return "orig_r3"; + case PERF_REG_POWERPC_CTR: + return "ctr"; + case PERF_REG_POWERPC_LINK: + return "link"; + case PERF_REG_POWERPC_XER: + return "xer"; + case PERF_REG_POWERPC_CCR: + return "ccr"; + case PERF_REG_POWERPC_SOFTE: + return "softe"; + case PERF_REG_POWERPC_TRAP: + return "trap"; + case PERF_REG_POWERPC_DAR: + return "dar"; + case PERF_REG_POWERPC_DSISR: + return "dsisr"; + case PERF_REG_POWERPC_SIER: + return "sier"; + case PERF_REG_POWERPC_MMCRA: + return "mmcra"; + case PERF_REG_POWERPC_MMCR0: + return "mmcr0"; + case PERF_REG_POWERPC_MMCR1: + return "mmcr1"; + case PERF_REG_POWERPC_MMCR2: + return "mmcr2"; + case PERF_REG_POWERPC_MMCR3: + return "mmcr3"; + case PERF_REG_POWERPC_SIER2: + return "sier2"; + case PERF_REG_POWERPC_SIER3: + return "sier3"; + case PERF_REG_POWERPC_PMC1: + return "pmc1"; + case PERF_REG_POWERPC_PMC2: + return "pmc2"; + case PERF_REG_POWERPC_PMC3: + return "pmc3"; + case PERF_REG_POWERPC_PMC4: + return "pmc4"; + case PERF_REG_POWERPC_PMC5: + return "pmc5"; + case PERF_REG_POWERPC_PMC6: + return "pmc6"; + case PERF_REG_POWERPC_SDAR: + return "sdar"; + case PERF_REG_POWERPC_SIAR: + return "siar"; + default: + break; + } + return NULL; +} + +static const char *__perf_reg_name_riscv(int id) +{ + switch (id) { + case PERF_REG_RISCV_PC: + return "pc"; + case PERF_REG_RISCV_RA: + return "ra"; + case PERF_REG_RISCV_SP: + return "sp"; + case PERF_REG_RISCV_GP: + return "gp"; + case PERF_REG_RISCV_TP: + return "tp"; + case PERF_REG_RISCV_T0: + return "t0"; + case PERF_REG_RISCV_T1: + return "t1"; + case PERF_REG_RISCV_T2: + return "t2"; + case PERF_REG_RISCV_S0: + return "s0"; + case PERF_REG_RISCV_S1: + return "s1"; + case PERF_REG_RISCV_A0: + return "a0"; + case PERF_REG_RISCV_A1: + return "a1"; + case PERF_REG_RISCV_A2: + return "a2"; + case PERF_REG_RISCV_A3: + return "a3"; + case PERF_REG_RISCV_A4: + return "a4"; + case PERF_REG_RISCV_A5: + return "a5"; + case PERF_REG_RISCV_A6: + return "a6"; + case PERF_REG_RISCV_A7: + return "a7"; + case PERF_REG_RISCV_S2: + return "s2"; + case PERF_REG_RISCV_S3: + return "s3"; + case PERF_REG_RISCV_S4: + return "s4"; + case PERF_REG_RISCV_S5: + return "s5"; + case PERF_REG_RISCV_S6: + return "s6"; + case PERF_REG_RISCV_S7: + return "s7"; + case PERF_REG_RISCV_S8: + return "s8"; + case PERF_REG_RISCV_S9: + return "s9"; + case PERF_REG_RISCV_S10: + return "s10"; + case PERF_REG_RISCV_S11: + return "s11"; + case PERF_REG_RISCV_T3: + return "t3"; + case PERF_REG_RISCV_T4: + return "t4"; + case PERF_REG_RISCV_T5: + return "t5"; + case PERF_REG_RISCV_T6: + return "t6"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_s390(int id) +{ + switch (id) { + case PERF_REG_S390_R0: + return "R0"; + case PERF_REG_S390_R1: + return "R1"; + case PERF_REG_S390_R2: + return "R2"; + case PERF_REG_S390_R3: + return "R3"; + case PERF_REG_S390_R4: + return "R4"; + case PERF_REG_S390_R5: + return "R5"; + case PERF_REG_S390_R6: + return "R6"; + case PERF_REG_S390_R7: + return "R7"; + case PERF_REG_S390_R8: + return "R8"; + case PERF_REG_S390_R9: + return "R9"; + case PERF_REG_S390_R10: + return "R10"; + case PERF_REG_S390_R11: + return "R11"; + case PERF_REG_S390_R12: + return "R12"; + case PERF_REG_S390_R13: + return "R13"; + case PERF_REG_S390_R14: + return "R14"; + case PERF_REG_S390_R15: + return "R15"; + case PERF_REG_S390_FP0: + return "FP0"; + case PERF_REG_S390_FP1: + return "FP1"; + case PERF_REG_S390_FP2: + return "FP2"; + case PERF_REG_S390_FP3: + return "FP3"; + case PERF_REG_S390_FP4: + return "FP4"; + case PERF_REG_S390_FP5: + return "FP5"; + case PERF_REG_S390_FP6: + return "FP6"; + case PERF_REG_S390_FP7: + return "FP7"; + case PERF_REG_S390_FP8: + return "FP8"; + case PERF_REG_S390_FP9: + return "FP9"; + case PERF_REG_S390_FP10: + return "FP10"; + case PERF_REG_S390_FP11: + return "FP11"; + case PERF_REG_S390_FP12: + return "FP12"; + case PERF_REG_S390_FP13: + return "FP13"; + case PERF_REG_S390_FP14: + return "FP14"; + case PERF_REG_S390_FP15: + return "FP15"; + case PERF_REG_S390_MASK: + return "MASK"; + case PERF_REG_S390_PC: + return "PC"; + default: + return NULL; + } + + return NULL; +} + +static const char *__perf_reg_name_x86(int id) +{ + switch (id) { + case PERF_REG_X86_AX: + return "AX"; + case PERF_REG_X86_BX: + return "BX"; + case PERF_REG_X86_CX: + return "CX"; + case PERF_REG_X86_DX: + return "DX"; + case PERF_REG_X86_SI: + return "SI"; + case PERF_REG_X86_DI: + return "DI"; + case PERF_REG_X86_BP: + return "BP"; + case PERF_REG_X86_SP: + return "SP"; + case PERF_REG_X86_IP: + return "IP"; + case PERF_REG_X86_FLAGS: + return "FLAGS"; + case PERF_REG_X86_CS: + return "CS"; + case PERF_REG_X86_SS: + return "SS"; + case PERF_REG_X86_DS: + return "DS"; + case PERF_REG_X86_ES: + return "ES"; + case PERF_REG_X86_FS: + return "FS"; + case PERF_REG_X86_GS: + return "GS"; + case PERF_REG_X86_R8: + return "R8"; + case PERF_REG_X86_R9: + return "R9"; + case PERF_REG_X86_R10: + return "R10"; + case PERF_REG_X86_R11: + return "R11"; + case PERF_REG_X86_R12: + return "R12"; + case PERF_REG_X86_R13: + return "R13"; + case PERF_REG_X86_R14: + return "R14"; + case PERF_REG_X86_R15: + return "R15"; + +#define XMM(x) \ + case PERF_REG_X86_XMM ## x: \ + case PERF_REG_X86_XMM ## x + 1: \ + return "XMM" #x; + XMM(0) + XMM(1) + XMM(2) + XMM(3) + XMM(4) + XMM(5) + XMM(6) + XMM(7) + XMM(8) + XMM(9) + XMM(10) + XMM(11) + XMM(12) + XMM(13) + XMM(14) + XMM(15) +#undef XMM + default: + return NULL; + } + + return NULL; +} + +const char *perf_reg_name(int id, const char *arch) +{ + const char *reg_name = NULL; + + if (!strcmp(arch, "csky")) + reg_name = __perf_reg_name_csky(id); + else if (!strcmp(arch, "mips")) + reg_name = __perf_reg_name_mips(id); + else if (!strcmp(arch, "powerpc")) + reg_name = __perf_reg_name_powerpc(id); + else if (!strcmp(arch, "riscv")) + reg_name = __perf_reg_name_riscv(id); + else if (!strcmp(arch, "s390")) + reg_name = __perf_reg_name_s390(id); + else if (!strcmp(arch, "x86")) + reg_name = __perf_reg_name_x86(id); + else if (!strcmp(arch, "arm")) + reg_name = __perf_reg_name_arm(id); + else if (!strcmp(arch, "arm64")) + reg_name = __perf_reg_name_arm64(id); + + return reg_name ?: "unknown"; +} + int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { int i, idx = 0; u64 mask = regs->mask; + if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE) + return -EINVAL; + if (regs->cache_mask & (1ULL << id)) goto out; diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index eeac181ebccf..ce1127af05e4 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -11,8 +11,11 @@ struct sample_reg { const char *name; uint64_t mask; }; -#define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) } -#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) } + +#define SMPL_REG_MASK(b) (1ULL << (b)) +#define SMPL_REG(n, b) { .name = #n, .mask = SMPL_REG_MASK(b) } +#define SMPL_REG2_MASK(b) (3ULL << (b)) +#define SMPL_REG2(n, b) { .name = #n, .mask = SMPL_REG2_MASK(b) } #define SMPL_REG_END { .name = NULL } enum { @@ -31,22 +34,16 @@ extern const struct sample_reg sample_reg_masks[]; #define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP)) +const char *perf_reg_name(int id, const char *arch); int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); -static inline const char *perf_reg_name(int id) -{ - const char *reg_name = __perf_reg_name(id); - - return reg_name ?: "unknown"; -} - #else #define PERF_REGS_MASK 0 #define PERF_REGS_MAX 0 #define DWARF_MINIMAL_REGS PERF_REGS_MASK -static inline const char *perf_reg_name(int id __maybe_unused) +static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused) { return "unknown"; } diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index 756295dedccc..f0bcfcab1a93 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -87,7 +87,8 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, pmu = perf_pmu__find_by_type((unsigned int)attr.type); evsel = parse_events__add_event(evlist->core.nr_entries, - &attr, q, pmu); + &attr, q, /*metric_id=*/NULL, + pmu); if (evsel == NULL) goto error; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index bdabd62170d2..8dfbba15aeb8 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -315,7 +315,7 @@ static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc, char *val, struct pmu_event *pe) + char *desc, char *val, const struct pmu_event *pe) { struct parse_events_term *term; struct perf_pmu_alias *alias; @@ -710,9 +710,9 @@ static char *perf_pmu__getcpuid(struct perf_pmu *pmu) return cpuid; } -struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) +const struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) { - struct pmu_events_map *map; + const struct pmu_events_map *map; char *cpuid = perf_pmu__getcpuid(pmu); int i; @@ -737,7 +737,7 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) return map; } -struct pmu_events_map *__weak pmu_events_map__find(void) +const struct pmu_events_map *__weak pmu_events_map__find(void) { return perf_pmu__find_map(NULL); } @@ -824,7 +824,7 @@ out: * as aliases. */ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, - struct pmu_events_map *map) + const struct pmu_events_map *map) { int i; const char *name = pmu->name; @@ -834,7 +834,7 @@ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, i = 0; while (1) { const char *cpu_name = is_arm_pmu_core(name) ? name : "cpu"; - struct pmu_event *pe = &map->table[i++]; + const struct pmu_event *pe = &map->table[i++]; const char *pname = pe->pmu ? pe->pmu : cpu_name; if (!pe->name) { @@ -859,7 +859,7 @@ new_alias: static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) { - struct pmu_events_map *map; + const struct pmu_events_map *map; map = perf_pmu__find_map(pmu); if (!map) @@ -873,7 +873,7 @@ void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data) int i = 0; while (1) { - struct pmu_sys_events *event_table; + const struct pmu_sys_events *event_table; int j = 0; event_table = &pmu_sys_event_tables[i++]; @@ -882,7 +882,7 @@ void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data) break; while (1) { - struct pmu_event *pe = &event_table->table[j++]; + const struct pmu_event *pe = &event_table->table[j++]; int ret; if (!pe->name && !pe->metric_group && !pe->metric_name) @@ -900,7 +900,7 @@ struct pmu_sys_event_iter_data { struct perf_pmu *pmu; }; -static int pmu_add_sys_aliases_iter_fn(struct pmu_event *pe, void *data) +static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, void *data) { struct pmu_sys_event_iter_data *idata = data; struct perf_pmu *pmu = idata->pmu; @@ -1283,7 +1283,7 @@ static int pmu_config_term(const char *pmu_name, unknown_term = NULL; help_msg = parse_events_formats_error_string(pmu_term); if (err) { - parse_events__handle_error(err, term->err_term, + parse_events_error__handle(err, term->err_term, unknown_term, help_msg); } else { @@ -1316,7 +1316,7 @@ static int pmu_config_term(const char *pmu_name, if (term->no_value && bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) { if (err) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("no value assigned for term"), NULL); } @@ -1331,7 +1331,7 @@ static int pmu_config_term(const char *pmu_name, term->config, term->val.str); } if (err) { - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, strdup("expected numeric value"), NULL); } @@ -1348,7 +1348,7 @@ static int pmu_config_term(const char *pmu_name, if (err) { char *err_str; - parse_events__handle_error(err, term->err_val, + parse_events_error__handle(err, term->err_val, asprintf(&err_str, "value too big for format, maximum is %llu", (unsigned long long)max_val) < 0 @@ -1608,6 +1608,7 @@ static int cmp_sevent(const void *a, const void *b) { const struct sevent *as = a; const struct sevent *bs = b; + int ret; /* Put extra events last */ if (!!as->desc != !!bs->desc) @@ -1623,7 +1624,13 @@ static int cmp_sevent(const void *a, const void *b) if (as->is_cpu != bs->is_cpu) return bs->is_cpu - as->is_cpu; - return strcmp(as->name, bs->name); + ret = strcmp(as->name, bs->name); + if (!ret) { + if (as->pmu && bs->pmu) + return strcmp(as->pmu, bs->pmu); + } + + return ret; } static void wordwrap(char *s, int start, int max, int corr) @@ -1652,8 +1659,24 @@ bool is_pmu_core(const char *name) return !strcmp(name, "cpu") || is_arm_pmu_core(name); } +static bool pmu_alias_is_duplicate(struct sevent *alias_a, + struct sevent *alias_b) +{ + /* Different names -> never duplicates */ + if (strcmp(alias_a->name, alias_b->name)) + return false; + + /* Don't remove duplicates for hybrid PMUs */ + if (perf_pmu__is_hybrid(alias_a->pmu) && + perf_pmu__is_hybrid(alias_b->pmu)) + return false; + + return true; +} + void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc, bool details_flag, bool deprecated) + bool long_desc, bool details_flag, bool deprecated, + const char *pmu_name) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; @@ -1679,10 +1702,16 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, pmu = NULL; j = 0; while ((pmu = perf_pmu__scan(pmu)) != NULL) { + if (pmu_name && perf_pmu__is_hybrid(pmu->name) && + strcmp(pmu_name, pmu->name)) { + continue; + } + list_for_each_entry(alias, &pmu->aliases, list) { char *name = alias->desc ? alias->name : format_alias(buf, sizeof(buf), pmu, alias); - bool is_cpu = is_pmu_core(pmu->name); + bool is_cpu = is_pmu_core(pmu->name) || + perf_pmu__is_hybrid(pmu->name); if (alias->deprecated && !deprecated) continue; @@ -1730,8 +1759,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { /* Skip duplicates */ - if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) + if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) continue; + if (name_only) { printf("%s ", aliases[j].name); continue; @@ -1906,7 +1936,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) } void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, - char *name) + const char *name) { struct perf_pmu_format *format; __u64 masks = 0, bits; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 394898b07fd9..541889fa9f9c 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -49,6 +49,10 @@ struct perf_pmu { struct list_head caps; /* HEAD struct perf_pmu_caps -> list */ struct list_head list; /* ELEM */ struct list_head hybrid_list; + + struct { + bool exclude_guest; + } missing_features; }; extern struct perf_pmu perf_pmu__fake; @@ -111,7 +115,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); bool is_pmu_core(const char *name); void print_pmu_events(const char *event_glob, bool name_only, bool quiet, bool long_desc, bool details_flag, - bool deprecated); + bool deprecated, const char *pmu_name); bool pmu_have_event(const char *pname, const char *name); int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); @@ -120,21 +124,21 @@ int perf_pmu__test(void); struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, - struct pmu_events_map *map); + const struct pmu_events_map *map); -struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu); -struct pmu_events_map *pmu_events_map__find(void); +const struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu); +const struct pmu_events_map *pmu_events_map__find(void); bool pmu_uncore_alias_match(const char *pmu_name, const char *name); void perf_pmu_free_alias(struct perf_pmu_alias *alias); -typedef int (*pmu_sys_event_iter_fn)(struct pmu_event *pe, void *data); +typedef int (*pmu_sys_event_iter_fn)(const struct pmu_event *pe, void *data); void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); int perf_pmu__caps_parse(struct perf_pmu *pmu); void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, - char *name); + const char *name); bool perf_pmu__has_hybrid(void); int perf_pmu__match(char *pattern, char *name, char *tok); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index b2a02c9ab8ea..a834918a0a0d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -3083,6 +3083,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, for (j = 0; j < num_matched_functions; j++) { sym = syms[j]; + if (sym->type != STT_FUNC) + continue; + /* There can be duplicated symbols in the map */ for (i = 0; i < j; i++) if (sym->start == syms[i]->start) { diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index d7c976671e3a..a685d20165f7 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -18,6 +18,7 @@ util/mmap.c util/namespaces.c ../lib/bitmap.c ../lib/find_bit.c +../lib/list_sort.c ../lib/hweight.c ../lib/string.c ../lib/vsprintf.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 8feef3a05af7..52d8995cfd73 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -70,6 +70,18 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) } /* + * This one is needed not to drag the PMU bandwagon, jevents generated + * pmu_sys_event_tables, etc and evsel__find_pmu() is used so far just for + * doing per PMU perf_event_attr.exclude_guest handling, not really needed, so + * far, for the perf python binding known usecases, revisit if this become + * necessary. + */ +struct perf_pmu *evsel__find_pmu(struct evsel *evsel __maybe_unused) +{ + return NULL; +} + +/* * Add this one here not to drag util/metricgroup.c */ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, @@ -416,6 +428,8 @@ tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) offset = val; len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { @@ -449,7 +463,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) struct tep_event *tp_format; tp_format = trace_event__tp_format_id(evsel->core.attr.config); - if (!tp_format) + if (IS_ERR_OR_NULL(tp_format)) return NULL; evsel->tp_format = tp_format; @@ -624,17 +638,17 @@ static Py_ssize_t pyrf_cpu_map__length(PyObject *obj) { struct pyrf_cpu_map *pcpus = (void *)obj; - return pcpus->cpus->nr; + return perf_cpu_map__nr(pcpus->cpus); } static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i) { struct pyrf_cpu_map *pcpus = (void *)obj; - if (i >= pcpus->cpus->nr) + if (i >= perf_cpu_map__nr(pcpus->cpus)) return NULL; - return Py_BuildValue("i", pcpus->cpus->map[i]); + return Py_BuildValue("i", perf_cpu_map__cpu(pcpus->cpus, i).cpu); } static PySequenceMethods pyrf_cpu_map__sequence_methods = { @@ -1045,7 +1059,7 @@ static struct mmap *get_md(struct evlist *evlist, int cpu) for (i = 0; i < evlist->core.nr_mmaps; i++) { struct mmap *md = &evlist->mmap[i]; - if (md->core.cpu == cpu) + if (md->core.cpu.cpu == cpu) return md; } @@ -1431,7 +1445,7 @@ error: * Dummy, to avoid dragging all the test_attr infrastructure in the python * binding. */ -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, +void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags) { } diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index bff669b615ee..007a64681416 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call if (opts->group) evlist__set_leader(evlist); - if (evlist->core.cpus->map[0] < 0) + if (perf_cpu_map__cpu(evlist->core.cpus, 0).cpu < 0) opts->no_inherit = true; use_comm_exec = perf_can_comm_exec(); @@ -229,7 +229,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) { struct evlist *temp_evlist; struct evsel *evsel; - int err, fd, cpu; + int err, fd; + struct perf_cpu cpu = { .cpu = 0 }; bool ret = false; pid_t pid = -1; @@ -246,14 +247,16 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) { struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); - cpu = cpus ? cpus->map[0] : 0; + if (cpus) + cpu = perf_cpu_map__cpu(cpus, 0); + perf_cpu_map__put(cpus); } else { - cpu = evlist->core.cpus->map[0]; + cpu = perf_cpu_map__cpu(evlist->core.cpus, 0); } while (1) { - fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, perf_event_open_cloexec_flag()); if (fd < 0) { if (pid == -1 && errno == EACCES) { diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 68f471d9a88b..ef6c2715fdd9 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -77,6 +77,7 @@ struct record_opts { int ctl_fd; int ctl_fd_ack; bool ctl_fd_close; + int synth; }; extern const char * const *record_usage; diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 8130b56aa04b..f3fdad28a852 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -244,7 +244,7 @@ static bool s390_cpumsf_basic_show(const char *color, size_t pos, struct hws_basic_entry *basicp) { struct hws_basic_entry *basic = basicp; -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ struct hws_basic_entry local; unsigned long long word = be64toh(*(unsigned long long *)basicp); @@ -288,7 +288,7 @@ static bool s390_cpumsf_diag_show(const char *color, size_t pos, struct hws_diag_entry *diagp) { struct hws_diag_entry *diag = diagp; -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ struct hws_diag_entry local; unsigned long long word = be64toh(*(unsigned long long *)diagp); @@ -322,7 +322,7 @@ static unsigned long long trailer_timestamp(struct hws_trailer_entry *te, static bool s390_cpumsf_trailer_show(const char *color, size_t pos, struct hws_trailer_entry *te) { -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ struct hws_trailer_entry local; const unsigned long long flags = be64toh(te->flags); @@ -552,7 +552,7 @@ static unsigned long long get_trailer_time(const unsigned char *buf) te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ - sizeof(*te)); -#if __BYTE_ORDER == __LITTLE_ENDIAN +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ clock_base = be64toh(te->progusage[0]) >> 63 & 0x1; progusage2 = be64toh(te->progusage[1]); #else diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 08ec3c3ae0ee..cd3a34840389 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -135,12 +135,12 @@ static int get_counterset_start(int setnr) * the name of this counter. * If no match is found a NULL pointer is returned. */ -static const char *get_counter_name(int set, int nr, struct pmu_events_map *map) +static const char *get_counter_name(int set, int nr, const struct pmu_events_map *map) { int rc, event_nr, wanted = get_counterset_start(set) + nr; if (map) { - struct pmu_event *evp = map->table; + const struct pmu_event *evp = map->table; for (; evp->name || evp->event || evp->desc; ++evp) { if (evp->name == NULL || evp->event == NULL) @@ -159,7 +159,7 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) unsigned char *buf = sample->raw_data; const char *color = PERF_COLOR_BLUE; struct cf_ctrset_entry *cep, ce; - struct pmu_events_map *map; + const struct pmu_events_map *map; u64 *p; map = pmu_events_map__find(); diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 32a721b3e9a5..a5d945415bbc 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -392,6 +392,8 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(data + field->offset); offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } else offset = field->offset; XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index c0c010350bc2..e752e1f4a5f0 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -36,6 +36,7 @@ #include "../debug.h" #include "../dso.h" #include "../callchain.h" +#include "../env.h" #include "../evsel.h" #include "../event.h" #include "../thread.h" @@ -687,7 +688,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict, _PyUnicode_FromString(decode)); } -static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) +static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, char *bf, int size) { unsigned int i = 0, r; int printed = 0; @@ -702,7 +703,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) printed += scnprintf(bf + printed, size - printed, "%5s:0x%" PRIx64 " ", - perf_reg_name(r), val); + perf_reg_name(r, arch), val); } } @@ -711,6 +712,7 @@ static void set_regs_in_dict(PyObject *dict, struct evsel *evsel) { struct perf_event_attr *attr = &evsel->core.attr; + const char *arch = perf_env__arch(evsel__env(evsel)); /* * Here value 28 is a constant size which can be used to print @@ -722,12 +724,12 @@ static void set_regs_in_dict(PyObject *dict, int size = __sw_hweight64(attr->sample_regs_intr) * 28; char bf[size]; - regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf)); + regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, sizeof(bf)); pydict_set_item_string_decref(dict, "iregs", _PyUnicode_FromString(bf)); - regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf)); + regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, sizeof(bf)); pydict_set_item_string_decref(dict, "uregs", _PyUnicode_FromString(bf)); @@ -942,6 +944,8 @@ static void python_process_tracepoint(struct perf_sample *sample, offset = val; len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { @@ -1553,7 +1557,7 @@ static void get_handler_name(char *str, size_t size, } static void -process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp, +process_stat(struct evsel *counter, struct perf_cpu cpu, int thread, u64 tstamp, struct perf_counts_values *count) { PyObject *handler, *t; @@ -1573,7 +1577,7 @@ process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp, return; } - PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu.cpu)); PyTuple_SetItem(t, n++, _PyLong_FromLong(thread)); tuple_set_u64(t, n++, tstamp); @@ -1597,14 +1601,14 @@ static void python_process_stat(struct perf_stat_config *config, int cpu, thread; if (config->aggr_mode == AGGR_GLOBAL) { - process_stat(counter, -1, -1, tstamp, + process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp, &counter->counts->aggr); return; } for (thread = 0; thread < threads->nr; thread++) { - for (cpu = 0; cpu < cpus->nr; cpu++) { - process_stat(counter, cpus->map[cpu], + for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) { + process_stat(counter, perf_cpu_map__cpu(cpus, cpu), perf_thread_map__pid(threads, thread), tstamp, perf_counts(counter->counts, cpu, thread)); } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 352f16076e01..498b05708db5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -15,6 +15,7 @@ #include "map_symbol.h" #include "branch.h" #include "debug.h" +#include "env.h" #include "evlist.h" #include "evsel.h" #include "memswap.h" @@ -44,7 +45,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, size_t decomp_size, src_size; u64 decomp_last_rem = 0; size_t mmap_len, decomp_len = session->header.env.comp_mmap_len; - struct decomp *decomp, *decomp_last = session->decomp_last; + struct decomp *decomp, *decomp_last = session->active_decomp->decomp_last; if (decomp_last) { decomp_last_rem = decomp_last->size - decomp_last->head; @@ -71,7 +72,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, src = (void *)event + sizeof(struct perf_record_compressed); src_size = event->pack.header.size - sizeof(struct perf_record_compressed); - decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size, + decomp_size = zstd_decompress_stream(session->active_decomp->zstd_decomp, src, src_size, &(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem); if (!decomp_size) { munmap(decomp, mmap_len); @@ -81,13 +82,12 @@ static int perf_session__process_compressed_event(struct perf_session *session, decomp->size += decomp_size; - if (session->decomp == NULL) { - session->decomp = decomp; - session->decomp_last = decomp; - } else { - session->decomp_last->next = decomp; - session->decomp_last = decomp; - } + if (session->active_decomp->decomp == NULL) + session->active_decomp->decomp = decomp; + else + session->active_decomp->decomp_last->next = decomp; + + session->active_decomp->decomp_last = decomp; pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size); @@ -197,6 +197,8 @@ struct perf_session *__perf_session__new(struct perf_data *data, session->repipe = repipe; session->tool = tool; + session->decomp_data.zstd_decomp = &session->zstd_data; + session->active_decomp = &session->decomp_data; INIT_LIST_HEAD(&session->auxtrace_index); machines__init(&session->machines); ordered_events__init(&session->ordered_events, @@ -276,11 +278,11 @@ static void perf_session__delete_threads(struct perf_session *session) machine__delete_threads(&session->machines.host); } -static void perf_session__release_decomp_events(struct perf_session *session) +static void perf_decomp__release_events(struct decomp *next) { - struct decomp *next, *decomp; + struct decomp *decomp; size_t mmap_len; - next = session->decomp; + do { decomp = next; if (decomp == NULL) @@ -299,7 +301,7 @@ void perf_session__delete(struct perf_session *session) auxtrace_index__free(&session->auxtrace_index); perf_session__destroy_kernel_maps(session); perf_session__delete_threads(session); - perf_session__release_decomp_events(session); + perf_decomp__release_events(session->decomp_data.decomp); perf_env__exit(&session->header.env); machines__exit(&session->machines); if (session->data) { @@ -509,6 +511,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->bpf = perf_event__process_bpf; if (tool->text_poke == NULL) tool->text_poke = perf_event__process_text_poke; + if (tool->aux_output_hw_id == NULL) + tool->aux_output_hw_id = perf_event__process_aux_output_hw_id; if (tool->read == NULL) tool->read = process_event_sample_stub; if (tool->throttle == NULL) @@ -1000,6 +1004,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap, [PERF_RECORD_CGROUP] = perf_event__cgroup_swap, [PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap, + [PERF_RECORD_AUX_OUTPUT_HW_ID] = perf_event__all64_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, @@ -1164,7 +1169,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) } } -static void regs_dump__printf(u64 mask, u64 *regs) +static void regs_dump__printf(u64 mask, u64 *regs, const char *arch) { unsigned rid, i = 0; @@ -1172,7 +1177,7 @@ static void regs_dump__printf(u64 mask, u64 *regs) u64 val = regs[i++]; printf(".... %-5s 0x%016" PRIx64 "\n", - perf_reg_name(rid), val); + perf_reg_name(rid, arch), val); } } @@ -1190,7 +1195,7 @@ static inline const char *regs_dump_abi(struct regs_dump *d) return regs_abi[d->abi]; } -static void regs__printf(const char *type, struct regs_dump *regs) +static void regs__printf(const char *type, struct regs_dump *regs, const char *arch) { u64 mask = regs->mask; @@ -1199,23 +1204,23 @@ static void regs__printf(const char *type, struct regs_dump *regs) mask, regs_dump_abi(regs)); - regs_dump__printf(mask, regs->regs); + regs_dump__printf(mask, regs->regs, arch); } -static void regs_user__printf(struct perf_sample *sample) +static void regs_user__printf(struct perf_sample *sample, const char *arch) { struct regs_dump *user_regs = &sample->user_regs; if (user_regs->regs) - regs__printf("user", user_regs); + regs__printf("user", user_regs, arch); } -static void regs_intr__printf(struct perf_sample *sample) +static void regs_intr__printf(struct perf_sample *sample, const char *arch) { struct regs_dump *intr_regs = &sample->intr_regs; if (intr_regs->regs) - regs__printf("intr", intr_regs); + regs__printf("intr", intr_regs, arch); } static void stack_user__printf(struct stack_dump *dump) @@ -1300,7 +1305,7 @@ char *get_page_size_name(u64 size, char *str) } static void dump_sample(struct evsel *evsel, union perf_event *event, - struct perf_sample *sample) + struct perf_sample *sample, const char *arch) { u64 sample_type; char str[PAGE_SIZE_NAME_LEN]; @@ -1321,10 +1326,10 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, branch_stack__printf(sample, evsel__has_branch_callstack(evsel)); if (sample_type & PERF_SAMPLE_REGS_USER) - regs_user__printf(sample); + regs_user__printf(sample, arch); if (sample_type & PERF_SAMPLE_REGS_INTR) - regs_intr__printf(sample); + regs_intr__printf(sample, arch); if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); @@ -1498,11 +1503,12 @@ static int machines__deliver_event(struct machines *machines, ++evlist->stats.nr_unknown_id; return 0; } - dump_sample(evsel, event, sample); if (machine == NULL) { ++evlist->stats.nr_unprocessable_samples; + dump_sample(evsel, event, sample, perf_env__arch(NULL)); return 0; } + dump_sample(evsel, event, sample, perf_env__arch(machine->env)); return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); @@ -1556,6 +1562,8 @@ static int machines__deliver_event(struct machines *machines, return tool->bpf(tool, event, sample, machine); case PERF_RECORD_TEXT_POKE: return tool->text_poke(tool, event, sample, machine); + case PERF_RECORD_AUX_OUTPUT_HW_ID: + return tool->aux_output_hw_id(tool, event, sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; @@ -2117,7 +2125,7 @@ static int __perf_session__process_decomp_events(struct perf_session *session) { s64 skip; u64 size; - struct decomp *decomp = session->decomp_last; + struct decomp *decomp = session->active_decomp->decomp_last; if (!decomp) return 0; @@ -2171,35 +2179,55 @@ struct reader { u64 data_offset; reader_cb_t process; bool in_place_update; + char *mmaps[NUM_MMAPS]; + size_t mmap_size; + int mmap_idx; + char *mmap_cur; + u64 file_pos; + u64 file_offset; + u64 head; + struct zstd_data zstd_data; + struct decomp_data decomp_data; }; static int -reader__process_events(struct reader *rd, struct perf_session *session, - struct ui_progress *prog) +reader__init(struct reader *rd, bool *one_mmap) { u64 data_size = rd->data_size; - u64 head, page_offset, file_offset, file_pos, size; - int err = 0, mmap_prot, mmap_flags, map_idx = 0; - size_t mmap_size; - char *buf, *mmaps[NUM_MMAPS]; - union perf_event *event; - s64 skip; - - page_offset = page_size * (rd->data_offset / page_size); - file_offset = page_offset; - head = rd->data_offset - page_offset; - - ui_progress__init_size(prog, data_size, "Processing events..."); + char **mmaps = rd->mmaps; + rd->head = rd->data_offset; data_size += rd->data_offset; - mmap_size = MMAP_SIZE; - if (mmap_size > data_size) { - mmap_size = data_size; - session->one_mmap = true; + rd->mmap_size = MMAP_SIZE; + if (rd->mmap_size > data_size) { + rd->mmap_size = data_size; + if (one_mmap) + *one_mmap = true; } - memset(mmaps, 0, sizeof(mmaps)); + memset(mmaps, 0, sizeof(rd->mmaps)); + + if (zstd_init(&rd->zstd_data, 0)) + return -1; + rd->decomp_data.zstd_decomp = &rd->zstd_data; + + return 0; +} + +static void +reader__release_decomp(struct reader *rd) +{ + perf_decomp__release_events(rd->decomp_data.decomp); + zstd_fini(&rd->zstd_data); +} + +static int +reader__mmap(struct reader *rd, struct perf_session *session) +{ + int mmap_prot, mmap_flags; + char *buf, **mmaps = rd->mmaps; + u64 page_offset; mmap_prot = PROT_READ; mmap_flags = MAP_SHARED; @@ -2210,47 +2238,63 @@ reader__process_events(struct reader *rd, struct perf_session *session, mmap_prot |= PROT_WRITE; mmap_flags = MAP_PRIVATE; } -remap: - buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, rd->fd, - file_offset); + + if (mmaps[rd->mmap_idx]) { + munmap(mmaps[rd->mmap_idx], rd->mmap_size); + mmaps[rd->mmap_idx] = NULL; + } + + page_offset = page_size * (rd->head / page_size); + rd->file_offset += page_offset; + rd->head -= page_offset; + + buf = mmap(NULL, rd->mmap_size, mmap_prot, mmap_flags, rd->fd, + rd->file_offset); if (buf == MAP_FAILED) { pr_err("failed to mmap file\n"); - err = -errno; - goto out; + return -errno; } - mmaps[map_idx] = buf; - map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); - file_pos = file_offset + head; + mmaps[rd->mmap_idx] = rd->mmap_cur = buf; + rd->mmap_idx = (rd->mmap_idx + 1) & (ARRAY_SIZE(rd->mmaps) - 1); + rd->file_pos = rd->file_offset + rd->head; if (session->one_mmap) { session->one_mmap_addr = buf; - session->one_mmap_offset = file_offset; + session->one_mmap_offset = rd->file_offset; } -more: - event = fetch_mmaped_event(head, mmap_size, buf, session->header.needs_swap); + return 0; +} + +enum { + READER_OK, + READER_NODATA, +}; + +static int +reader__read_event(struct reader *rd, struct perf_session *session, + struct ui_progress *prog) +{ + u64 size; + int err = READER_OK; + union perf_event *event; + s64 skip; + + event = fetch_mmaped_event(rd->head, rd->mmap_size, rd->mmap_cur, + session->header.needs_swap); if (IS_ERR(event)) return PTR_ERR(event); - if (!event) { - if (mmaps[map_idx]) { - munmap(mmaps[map_idx], mmap_size); - mmaps[map_idx] = NULL; - } - - page_offset = page_size * (head / page_size); - file_offset += page_offset; - head -= page_offset; - goto remap; - } + if (!event) + return READER_NODATA; size = event->header.size; skip = -EINVAL; if (size < sizeof(struct perf_event_header) || - (skip = rd->process(session, event, file_pos)) < 0) { + (skip = rd->process(session, event, rd->file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n", - file_offset + head, event->header.size, + rd->file_offset + rd->head, event->header.size, event->header.type, strerror(-skip)); err = skip; goto out; @@ -2259,8 +2303,8 @@ more: if (skip) size += skip; - head += size; - file_pos += size; + rd->head += size; + rd->file_pos += size; err = __perf_session__process_decomp_events(session); if (err) @@ -2268,13 +2312,48 @@ more: ui_progress__update(prog, size); +out: + return err; +} + +static inline bool +reader__eof(struct reader *rd) +{ + return (rd->file_pos >= rd->data_size + rd->data_offset); +} + +static int +reader__process_events(struct reader *rd, struct perf_session *session, + struct ui_progress *prog) +{ + int err; + + err = reader__init(rd, &session->one_mmap); + if (err) + goto out; + + session->active_decomp = &rd->decomp_data; + +remap: + err = reader__mmap(rd, session); + if (err) + goto out; + +more: + err = reader__read_event(rd, session, prog); + if (err < 0) + goto out; + else if (err == READER_NODATA) + goto remap; + if (session_done()) goto out; - if (file_pos < data_size) + if (!reader__eof(rd)) goto more; out: + session->active_decomp = &session->decomp_data; return err; } @@ -2327,6 +2406,7 @@ out_err: */ ordered_events__reinit(&session->ordered_events); auxtrace__free_events(session); + reader__release_decomp(&rd); session->one_mmap = false; return err; } @@ -2458,16 +2538,16 @@ int perf_session__cpu_bitmap(struct perf_session *session, return -1; } - for (i = 0; i < map->nr; i++) { - int cpu = map->map[i]; + for (i = 0; i < perf_cpu_map__nr(map); i++) { + struct perf_cpu cpu = perf_cpu_map__cpu(map, i); - if (cpu >= nr_cpus) { + if (cpu.cpu >= nr_cpus) { pr_err("Requested CPU %d too large. " - "Consider raising MAX_NR_CPUS\n", cpu); + "Consider raising MAX_NR_CPUS\n", cpu.cpu); goto out_delete_map; } - set_bit(cpu, cpu_bitmap); + set_bit(cpu.cpu, cpu_bitmap); } err = 0; @@ -2519,7 +2599,7 @@ int perf_event__process_id_index(struct perf_session *session, if (!sid) return -ENOENT; sid->idx = e->idx; - sid->cpu = e->cpu; + sid->cpu.cpu = e->cpu; sid->tid = e->tid; } return 0; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 5d8bd14a0a39..46c854292ad6 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -20,6 +20,12 @@ struct thread; struct auxtrace; struct itrace_synth_opts; +struct decomp_data { + struct decomp *decomp; + struct decomp *decomp_last; + struct zstd_data *zstd_decomp; +}; + struct perf_session { struct perf_header header; struct machines machines; @@ -39,8 +45,8 @@ struct perf_session { u64 bytes_transferred; u64 bytes_compressed; struct zstd_data zstd_data; - struct decomp *decomp; - struct decomp *decomp_last; + struct decomp_data decomp_data; + struct decomp_data *active_decomp; }; struct decomp { diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c index 20bacd5972ad..2b0a36ebf27a 100644 --- a/tools/perf/util/smt.c +++ b/tools/perf/util/smt.c @@ -5,6 +5,56 @@ #include "api/fs/fs.h" #include "smt.h" +/** + * hweight_str - Returns the number of bits set in str. Stops at first non-hex + * or ',' character. + */ +static int hweight_str(char *str) +{ + int result = 0; + + while (*str) { + switch (*str++) { + case '0': + case ',': + break; + case '1': + case '2': + case '4': + case '8': + result++; + break; + case '3': + case '5': + case '6': + case '9': + case 'a': + case 'A': + case 'c': + case 'C': + result += 2; + break; + case '7': + case 'b': + case 'B': + case 'd': + case 'D': + case 'e': + case 'E': + result += 3; + break; + case 'f': + case 'F': + result += 4; + break; + default: + goto done; + } + } +done: + return result; +} + int smt_on(void) { static bool cached; @@ -15,9 +65,12 @@ int smt_on(void) if (cached) return cached_result; - if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0) - goto done; + if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) { + cached = true; + return cached_result; + } + cached_result = 0; ncpu = sysconf(_SC_NPROCESSORS_CONF); for (cpu = 0; cpu < ncpu; cpu++) { unsigned long long siblings; @@ -26,27 +79,21 @@ int smt_on(void) char fn[256]; snprintf(fn, sizeof fn, - "devices/system/cpu/cpu%d/topology/core_cpus", cpu); + "devices/system/cpu/cpu%d/topology/thread_siblings", cpu); if (sysfs__read_str(fn, &str, &strlen) < 0) { snprintf(fn, sizeof fn, - "devices/system/cpu/cpu%d/topology/thread_siblings", - cpu); + "devices/system/cpu/cpu%d/topology/core_cpus", cpu); if (sysfs__read_str(fn, &str, &strlen) < 0) continue; } /* Entry is hex, but does not have 0x, so need custom parser */ - siblings = strtoull(str, NULL, 16); + siblings = hweight_str(str); free(str); - if (hweight64(siblings) > 1) { + if (siblings > 1) { cached_result = 1; - cached = true; break; } } - if (!cached) { - cached_result = 0; -done: - cached = true; - } + cached = true; return cached_result; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 568a88c001c6..2da081ef532b 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -37,7 +37,7 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char *default_sort_order = "comm,dso,symbol"; const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles"; -const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc"; +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc"; const char default_top_sort_order[] = "dso,symbol"; const char default_diff_sort_order[] = "dso,symbol"; const char default_tracepoint_sort_order[] = "trace"; @@ -46,8 +46,8 @@ const char *field_order; regex_t ignore_callees_regex; int have_ignore_callees = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; -const char *dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"}; -const char *arch_specific_sort_keys[] = {"p_stage_cyc"}; +static const char *const dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"}; +static const char *const arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"}; /* * Replaces all occurrences of a char used with the: @@ -915,7 +915,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, struct addr_map_symbol *from = &he->branch_info->from; return _hist_entry__sym_snprintf(&from->ms, from->al_addr, - he->level, bf, size, width); + from->al_level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -928,7 +928,7 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, struct addr_map_symbol *to = &he->branch_info->to; return _hist_entry__sym_snprintf(&to->ms, to->al_addr, - he->level, bf, size, width); + to->al_level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -1325,109 +1325,104 @@ struct sort_entry sort_mispredict = { .se_width_idx = HISTC_MISPREDICT, }; -static u64 he_weight(struct hist_entry *he) -{ - return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0; -} - static int64_t -sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right) +sort__weight_cmp(struct hist_entry *left, struct hist_entry *right) { - return he_weight(left) - he_weight(right); + return left->weight - right->weight; } static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he)); + return repsep_snprintf(bf, size, "%-*llu", width, he->weight); } struct sort_entry sort_local_weight = { .se_header = "Local Weight", - .se_cmp = sort__local_weight_cmp, + .se_cmp = sort__weight_cmp, .se_snprintf = hist_entry__local_weight_snprintf, .se_width_idx = HISTC_LOCAL_WEIGHT, }; -static int64_t -sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return left->stat.weight - right->stat.weight; -} - static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight); + return repsep_snprintf(bf, size, "%-*llu", width, + he->weight * he->stat.nr_events); } struct sort_entry sort_global_weight = { .se_header = "Weight", - .se_cmp = sort__global_weight_cmp, + .se_cmp = sort__weight_cmp, .se_snprintf = hist_entry__global_weight_snprintf, .se_width_idx = HISTC_GLOBAL_WEIGHT, }; -static u64 he_ins_lat(struct hist_entry *he) -{ - return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0; -} - static int64_t -sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right) +sort__ins_lat_cmp(struct hist_entry *left, struct hist_entry *right) { - return he_ins_lat(left) - he_ins_lat(right); + return left->ins_lat - right->ins_lat; } static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he)); + return repsep_snprintf(bf, size, "%-*u", width, he->ins_lat); } struct sort_entry sort_local_ins_lat = { .se_header = "Local INSTR Latency", - .se_cmp = sort__local_ins_lat_cmp, + .se_cmp = sort__ins_lat_cmp, .se_snprintf = hist_entry__local_ins_lat_snprintf, .se_width_idx = HISTC_LOCAL_INS_LAT, }; -static int64_t -sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return left->stat.ins_lat - right->stat.ins_lat; -} - static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat); + return repsep_snprintf(bf, size, "%-*u", width, + he->ins_lat * he->stat.nr_events); } struct sort_entry sort_global_ins_lat = { .se_header = "INSTR Latency", - .se_cmp = sort__global_ins_lat_cmp, + .se_cmp = sort__ins_lat_cmp, .se_snprintf = hist_entry__global_ins_lat_snprintf, .se_width_idx = HISTC_GLOBAL_INS_LAT, }; static int64_t -sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right) +sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->p_stage_cyc - right->p_stage_cyc; +} + +static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) { - return left->stat.p_stage_cyc - right->stat.p_stage_cyc; + return repsep_snprintf(bf, size, "%-*u", width, + he->p_stage_cyc * he->stat.nr_events); } + static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, he->stat.p_stage_cyc); + return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc); } -struct sort_entry sort_p_stage_cyc = { - .se_header = "Pipeline Stage Cycle", - .se_cmp = sort__global_p_stage_cyc_cmp, +struct sort_entry sort_local_p_stage_cyc = { + .se_header = "Local Pipeline Stage Cycle", + .se_cmp = sort__p_stage_cyc_cmp, .se_snprintf = hist_entry__p_stage_cyc_snprintf, - .se_width_idx = HISTC_P_STAGE_CYC, + .se_width_idx = HISTC_LOCAL_P_STAGE_CYC, +}; + +struct sort_entry sort_global_p_stage_cyc = { + .se_header = "Pipeline Stage Cycle", + .se_cmp = sort__p_stage_cyc_cmp, + .se_snprintf = hist_entry__global_p_stage_cyc_snprintf, + .se_width_idx = HISTC_GLOBAL_P_STAGE_CYC, }; struct sort_entry sort_mem_daddr_sym = { @@ -1878,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size), DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat), DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat), - DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc), + DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc), + DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc), }; #undef DIM @@ -2385,6 +2381,8 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, tep_read_number_field(field, a->raw_data, &dyn); offset = dyn & 0xffff; size = (dyn >> 16) & 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; /* record max width for output */ if (size > hde->dynamic_len) diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index b67c469aba79..f994261888e1 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -49,9 +49,6 @@ struct he_stat { u64 period_us; u64 period_guest_sys; u64 period_guest_us; - u64 weight; - u64 ins_lat; - u64 p_stage_cyc; u32 nr_events; }; @@ -109,6 +106,9 @@ struct hist_entry { s32 socket; s32 cpu; u64 code_page_size; + u64 weight; + u64 ins_lat; + u64 p_stage_cyc; u8 cpumode; u8 depth; @@ -235,7 +235,8 @@ enum sort_type { SORT_CODE_PAGE_SIZE, SORT_LOCAL_INS_LAT, SORT_GLOBAL_INS_LAT, - SORT_PIPELINE_STAGE_CYC, + SORT_LOCAL_PIPELINE_STAGE_CYC, + SORT_GLOBAL_PIPELINE_STAGE_CYC, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 5b7d6c16d33f..af468e3bb6fa 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <inttypes.h> +#include <signal.h> #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/types.h> #include <linux/kernel.h> #include <linux/string.h> @@ -15,6 +17,7 @@ #include "srcline.h" #include "string2.h" #include "symbol.h" +#include "subcmd/run-command.h" bool srcline_full_filename; @@ -119,6 +122,8 @@ static struct symbol *new_inline_sym(struct dso *dso, return inline_sym; } +#define MAX_INLINE_NEST 1024 + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -273,8 +278,6 @@ static void addr2line_cleanup(struct a2l_data *a2l) free(a2l); } -#define MAX_INLINE_NEST 1024 - static int inline_list__append_dso_a2l(struct dso *dso, struct inline_node *node, struct symbol *sym) @@ -361,26 +364,14 @@ void dso__free_a2l(struct dso *dso) dso->a2l = NULL; } -static struct inline_node *addr2inlines(const char *dso_name, u64 addr, - struct dso *dso, struct symbol *sym) -{ - struct inline_node *node; - - node = zalloc(sizeof(*node)); - if (node == NULL) { - perror("not enough memory for the inline node"); - return NULL; - } - - INIT_LIST_HEAD(&node->val); - node->addr = addr; - - addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym); - return node; -} - #else /* HAVE_LIBBFD_SUPPORT */ +struct a2l_subprocess { + struct child_process addr2line; + FILE *to_child; + FILE *from_child; +}; + static int filename_split(char *filename, unsigned int *line_nr) { char *sep; @@ -402,114 +393,285 @@ static int filename_split(char *filename, unsigned int *line_nr) return 0; } -static int addr2line(const char *dso_name, u64 addr, - char **file, unsigned int *line_nr, - struct dso *dso __maybe_unused, - bool unwind_inlines __maybe_unused, - struct inline_node *node __maybe_unused, - struct symbol *sym __maybe_unused) +static void addr2line_subprocess_cleanup(struct a2l_subprocess *a2l) { - FILE *fp; - char cmd[PATH_MAX]; - char *filename = NULL; - size_t len; - int ret = 0; + if (a2l->addr2line.pid != -1) { + kill(a2l->addr2line.pid, SIGKILL); + finish_command(&a2l->addr2line); /* ignore result, we don't care */ + a2l->addr2line.pid = -1; + } - scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64, - dso_name, addr); + if (a2l->to_child != NULL) { + fclose(a2l->to_child); + a2l->to_child = NULL; + } - fp = popen(cmd, "r"); - if (fp == NULL) { - pr_warning("popen failed for %s\n", dso_name); - return 0; + if (a2l->from_child != NULL) { + fclose(a2l->from_child); + a2l->from_child = NULL; + } + + free(a2l); +} + +static struct a2l_subprocess *addr2line_subprocess_init(const char *path) +{ + const char *argv[] = { "addr2line", "-e", path, "-i", "-f", NULL }; + struct a2l_subprocess *a2l = zalloc(sizeof(*a2l)); + int start_command_status = 0; + + if (a2l == NULL) + goto out; + + a2l->to_child = NULL; + a2l->from_child = NULL; + + a2l->addr2line.pid = -1; + a2l->addr2line.in = -1; + a2l->addr2line.out = -1; + a2l->addr2line.no_stderr = 1; + + a2l->addr2line.argv = argv; + start_command_status = start_command(&a2l->addr2line); + a2l->addr2line.argv = NULL; /* it's not used after start_command; avoid dangling pointers */ + + if (start_command_status != 0) { + pr_warning("could not start addr2line for %s: start_command return code %d\n", + path, + start_command_status); + goto out; } - if (getline(&filename, &len, fp) < 0 || !len) { - pr_warning("addr2line has no output for %s\n", dso_name); + a2l->to_child = fdopen(a2l->addr2line.in, "w"); + if (a2l->to_child == NULL) { + pr_warning("could not open write-stream to addr2line of %s\n", path); goto out; } - ret = filename_split(filename, line_nr); - if (ret != 1) { - free(filename); + a2l->from_child = fdopen(a2l->addr2line.out, "r"); + if (a2l->from_child == NULL) { + pr_warning("could not open read-stream from addr2line of %s\n", path); goto out; } - *file = filename; + return a2l; out: - pclose(fp); - return ret; + if (a2l) + addr2line_subprocess_cleanup(a2l); + + return NULL; } -void dso__free_a2l(struct dso *dso __maybe_unused) +static int read_addr2line_record(struct a2l_subprocess *a2l, + char **function, + char **filename, + unsigned int *line_nr) { + /* + * Returns: + * -1 ==> error + * 0 ==> sentinel (or other ill-formed) record read + * 1 ==> a genuine record read + */ + char *line = NULL; + size_t line_len = 0; + unsigned int dummy_line_nr = 0; + int ret = -1; + + if (function != NULL) + zfree(function); + + if (filename != NULL) + zfree(filename); + + if (line_nr != NULL) + *line_nr = 0; + + if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len) + goto error; + + if (function != NULL) + *function = strdup(strim(line)); + + zfree(&line); + line_len = 0; + + if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len) + goto error; + + if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0) { + ret = 0; + goto error; + } + + if (filename != NULL) + *filename = strdup(line); + + zfree(&line); + line_len = 0; + + return 1; + +error: + free(line); + if (function != NULL) + zfree(function); + if (filename != NULL) + zfree(filename); + return ret; } -static struct inline_node *addr2inlines(const char *dso_name, u64 addr, - struct dso *dso __maybe_unused, - struct symbol *sym) +static int inline_list__append_record(struct dso *dso, + struct inline_node *node, + struct symbol *sym, + const char *function, + const char *filename, + unsigned int line_nr) { - FILE *fp; - char cmd[PATH_MAX]; - struct inline_node *node; - char *filename = NULL; - char *funcname = NULL; - size_t filelen, funclen; - unsigned int line_nr = 0; + struct symbol *inline_sym = new_inline_sym(dso, sym, function); - scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i -f %016"PRIx64, - dso_name, addr); + return inline_list__append(inline_sym, srcline_from_fileline(filename, line_nr), node); +} - fp = popen(cmd, "r"); - if (fp == NULL) { - pr_err("popen failed for %s\n", dso_name); - return NULL; +static int addr2line(const char *dso_name, u64 addr, + char **file, unsigned int *line_nr, + struct dso *dso, + bool unwind_inlines, + struct inline_node *node, + struct symbol *sym __maybe_unused) +{ + struct a2l_subprocess *a2l = dso->a2l; + char *record_function = NULL; + char *record_filename = NULL; + unsigned int record_line_nr = 0; + int record_status = -1; + int ret = 0; + size_t inline_count = 0; + + if (!a2l) { + dso->a2l = addr2line_subprocess_init(dso_name); + a2l = dso->a2l; } - node = zalloc(sizeof(*node)); - if (node == NULL) { - perror("not enough memory for the inline node"); + if (a2l == NULL) { + if (!symbol_conf.disable_add2line_warn) + pr_warning("%s %s: addr2line_subprocess_init failed\n", __func__, dso_name); goto out; } - INIT_LIST_HEAD(&node->val); - node->addr = addr; - - /* addr2line -f generates two lines for each inlined functions */ - while (getline(&funcname, &funclen, fp) != -1) { - char *srcline; - struct symbol *inline_sym; + /* + * Send our request and then *deliberately* send something that can't be interpreted as + * a valid address to ask addr2line about (namely, ","). This causes addr2line to first + * write out the answer to our request, in an unbounded/unknown number of records, and + * then to write out the lines "??" and "??:0", so that we can detect when it has + * finished giving us anything useful. We have to be careful about the first record, + * though, because it may be genuinely unknown, in which case we'll get two sets of + * "??"/"??:0" lines. + */ + if (fprintf(a2l->to_child, "%016"PRIx64"\n,\n", addr) < 0 || fflush(a2l->to_child) != 0) { + pr_warning("%s %s: could not send request\n", __func__, dso_name); + goto out; + } - strim(funcname); + switch (read_addr2line_record(a2l, &record_function, &record_filename, &record_line_nr)) { + case -1: + pr_warning("%s %s: could not read first record\n", __func__, dso_name); + goto out; + case 0: + /* + * The first record was invalid, so return failure, but first read another + * record, since we asked a junk question and have to clear the answer out. + */ + switch (read_addr2line_record(a2l, NULL, NULL, NULL)) { + case -1: + pr_warning("%s %s: could not read delimiter record\n", __func__, dso_name); + break; + case 0: + /* As expected. */ + break; + default: + pr_warning("%s %s: unexpected record instead of sentinel", + __func__, dso_name); + break; + } + goto out; + default: + break; + } - if (getline(&filename, &filelen, fp) == -1) - goto out; + if (file) { + *file = strdup(record_filename); + ret = 1; + } + if (line_nr) + *line_nr = record_line_nr; - if (filename_split(filename, &line_nr) != 1) + if (unwind_inlines) { + if (node && inline_list__append_record(dso, node, sym, + record_function, + record_filename, + record_line_nr)) { + ret = 0; goto out; + } + } - srcline = srcline_from_fileline(filename, line_nr); - inline_sym = new_inline_sym(dso, sym, funcname); - - if (inline_list__append(inline_sym, srcline, node) != 0) { - free(srcline); - if (inline_sym && inline_sym->inlined) - symbol__delete(inline_sym); - goto out; + /* We have to read the records even if we don't care about the inline info. */ + while ((record_status = read_addr2line_record(a2l, + &record_function, + &record_filename, + &record_line_nr)) == 1) { + if (unwind_inlines && node && inline_count++ < MAX_INLINE_NEST) { + if (inline_list__append_record(dso, node, sym, + record_function, + record_filename, + record_line_nr)) { + ret = 0; + goto out; + } + ret = 1; /* found at least one inline frame */ } } out: - pclose(fp); - free(filename); - free(funcname); + free(record_function); + free(record_filename); + return ret; +} - return node; +void dso__free_a2l(struct dso *dso) +{ + struct a2l_subprocess *a2l = dso->a2l; + + if (!a2l) + return; + + addr2line_subprocess_cleanup(a2l); + + dso->a2l = NULL; } #endif /* HAVE_LIBBFD_SUPPORT */ +static struct inline_node *addr2inlines(const char *dso_name, u64 addr, + struct dso *dso, struct symbol *sym) +{ + struct inline_node *node; + + node = zalloc(sizeof(*node)); + if (node == NULL) { + perror("not enough memory for the inline node"); + return NULL; + } + + INIT_LIST_HEAD(&node->val); + node->addr = addr; + + addr2line(dso_name, addr, NULL, NULL, dso, true, node, sym); + return node; +} + /* * Number of addr2line failures (without success) before disabling it for that * dso. diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 588601000f3f..9cbe351b141f 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -4,6 +4,7 @@ #include <linux/string.h> #include <linux/time64.h> #include <math.h> +#include <perf/cpumap.h> #include "color.h" #include "counts.h" #include "evlist.h" @@ -120,11 +121,10 @@ static void aggr_printout(struct perf_stat_config *config, id.die, config->csv_output ? 0 : -3, id.core, config->csv_sep); - } else if (id.core > -1) { + } else if (id.cpu.cpu > -1) { fprintf(config->output, "CPU%*d%s", config->csv_output ? 0 : -7, - evsel__cpus(evsel)->map[id.core], - config->csv_sep); + id.cpu.cpu, config->csv_sep); } break; case AGGR_THREAD: @@ -327,26 +327,24 @@ static void print_metric_header(struct perf_stat_config *config, fprintf(os->fh, "%*s ", config->metric_only_len, unit); } -static int first_shadow_cpu(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id) +static int first_shadow_cpu_map_idx(struct perf_stat_config *config, + struct evsel *evsel, const struct aggr_cpu_id *id) { - struct evlist *evlist = evsel->evlist; - int i; + struct perf_cpu_map *cpus = evsel__cpus(evsel); + struct perf_cpu cpu; + int idx; if (config->aggr_mode == AGGR_NONE) - return id.core; + return perf_cpu_map__idx(cpus, id->cpu); if (!config->aggr_get_id) return 0; - for (i = 0; i < evsel__nr_cpus(evsel); i++) { - int cpu2 = evsel__cpus(evsel)->map[i]; + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + struct aggr_cpu_id cpu_id = config->aggr_get_id(config, cpu); - if (cpu_map__compare_aggr_cpu_id( - config->aggr_get_id(config, evlist->core.cpus, cpu2), - id)) { - return cpu2; - } + if (aggr_cpu_id__equal(&cpu_id, id)) + return idx; } return 0; } @@ -505,7 +503,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int } perf_stat__print_shadow_stats(config, counter, uval, - first_shadow_cpu(config, counter, id), + first_shadow_cpu_map_idx(config, counter, &id), &out, &config->metric_events, st); if (!config->csv_output && !config->metric_only) { print_noise(config, counter, noise); @@ -516,23 +514,26 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int static void aggr_update_shadow(struct perf_stat_config *config, struct evlist *evlist) { - int cpu, s; + int idx, s; + struct perf_cpu cpu; struct aggr_cpu_id s2, id; u64 val; struct evsel *counter; + struct perf_cpu_map *cpus; for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; evlist__for_each_entry(evlist, counter) { + cpus = evsel__cpus(counter); val = 0; - for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { - s2 = config->aggr_get_id(config, evlist->core.cpus, cpu); - if (!cpu_map__compare_aggr_cpu_id(s2, id)) + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + s2 = config->aggr_get_id(config, cpu); + if (!aggr_cpu_id__equal(&s2, &id)) continue; - val += perf_counts(counter->counts, cpu, 0)->val; + val += perf_counts(counter->counts, idx, 0)->val; } perf_stat__update_shadow_stats(counter, val, - first_shadow_cpu(config, counter, id), + first_shadow_cpu_map_idx(config, counter, &id), &rt_stat); } } @@ -584,15 +585,16 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c alias = list_prepare_entry(counter, &(evlist->core.entries), core.node); list_for_each_entry_continue (alias, &evlist->core.entries, core.node) { - if (strcmp(evsel__name(alias), evsel__name(counter)) || - alias->scale != counter->scale || - alias->cgrp != counter->cgrp || - strcmp(alias->unit, counter->unit) || - evsel__is_clock(alias) != evsel__is_clock(counter) || - !strcmp(alias->pmu_name, counter->pmu_name)) - break; - alias->merged_stat = true; - cb(config, alias, data, false); + /* Merge events with the same name, etc. but on different PMUs. */ + if (!strcmp(evsel__name(alias), evsel__name(counter)) && + alias->scale == counter->scale && + alias->cgrp == counter->cgrp && + !strcmp(alias->unit, counter->unit) && + evsel__is_clock(alias) == evsel__is_clock(counter) && + strcmp(alias->pmu_name, counter->pmu_name)) { + alias->merged_stat = true; + cb(config, alias, data, false); + } } } @@ -627,25 +629,28 @@ struct aggr_data { u64 ena, run, val; struct aggr_cpu_id id; int nr; - int cpu; + int cpu_map_idx; }; static void aggr_cb(struct perf_stat_config *config, struct evsel *counter, void *data, bool first) { struct aggr_data *ad = data; - int cpu; + int idx; + struct perf_cpu cpu; + struct perf_cpu_map *cpus; struct aggr_cpu_id s2; - for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { + cpus = evsel__cpus(counter); + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { struct perf_counts_values *counts; - s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu); - if (!cpu_map__compare_aggr_cpu_id(s2, ad->id)) + s2 = config->aggr_get_id(config, cpu); + if (!aggr_cpu_id__equal(&s2, &ad->id)) continue; if (first) ad->nr++; - counts = perf_counts(counter->counts, cpu, 0); + counts = perf_counts(counter->counts, idx, 0); /* * When any result is bad, make them all to give * consistent output in interval mode. @@ -665,7 +670,7 @@ static void aggr_cb(struct perf_stat_config *config, static void print_counter_aggrdata(struct perf_stat_config *config, struct evsel *counter, int s, char *prefix, bool metric_only, - bool *first, int cpu) + bool *first, struct perf_cpu cpu) { struct aggr_data ad; FILE *output = config->output; @@ -695,10 +700,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - if (cpu != -1) { - id = cpu_map__empty_aggr_cpu_id(); - id.core = cpu; - } + if (cpu.cpu != -1) + id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); + printout(config, id, nr, counter, uval, prefix, run, ena, 1.0, &rt_stat); if (!metric_only) @@ -731,8 +735,8 @@ static void print_aggr(struct perf_stat_config *config, first = true; evlist__for_each_entry(evlist, counter) { print_counter_aggrdata(config, counter, s, - prefix, metric_only, - &first, -1); + prefix, metric_only, + &first, (struct perf_cpu){ .cpu = -1 }); } if (metric_only) fputc('\n', output); @@ -778,7 +782,7 @@ static struct perf_aggr_thread_value *sort_aggr_thread( continue; buf[i].counter = counter; - buf[i].id = cpu_map__empty_aggr_cpu_id(); + buf[i].id = aggr_cpu_id__empty(); buf[i].id.thread = thread; buf[i].uval = uval; buf[i].val = val; @@ -866,7 +870,7 @@ static void print_counter_aggr(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = cd.avg * counter->scale; - printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running, + printout(config, aggr_cpu_id__empty(), 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg, &rt_stat); if (!metric_only) fprintf(output, "\n"); @@ -878,9 +882,9 @@ static void counter_cb(struct perf_stat_config *config __maybe_unused, { struct aggr_data *ad = data; - ad->val += perf_counts(counter->counts, ad->cpu, 0)->val; - ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena; - ad->run += perf_counts(counter->counts, ad->cpu, 0)->run; + ad->val += perf_counts(counter->counts, ad->cpu_map_idx, 0)->val; + ad->ena += perf_counts(counter->counts, ad->cpu_map_idx, 0)->ena; + ad->run += perf_counts(counter->counts, ad->cpu_map_idx, 0)->run; } /* @@ -893,11 +897,12 @@ static void print_counter(struct perf_stat_config *config, FILE *output = config->output; u64 ena, run, val; double uval; - int cpu; + int idx; + struct perf_cpu cpu; struct aggr_cpu_id id; - for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { - struct aggr_data ad = { .cpu = cpu }; + perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) { + struct aggr_data ad = { .cpu_map_idx = idx }; if (!collect_data(config, counter, counter_cb, &ad)) return; @@ -909,8 +914,7 @@ static void print_counter(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - id = cpu_map__empty_aggr_cpu_id(); - id.core = cpu; + id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); printout(config, id, 0, counter, uval, prefix, run, ena, 1.0, &rt_stat); @@ -922,29 +926,32 @@ static void print_no_aggr_metric(struct perf_stat_config *config, struct evlist *evlist, char *prefix) { - int cpu; - int nrcpus = 0; - struct evsel *counter; - u64 ena, run, val; - double uval; - struct aggr_cpu_id id; + int all_idx; + struct perf_cpu cpu; - nrcpus = evlist->core.cpus->nr; - for (cpu = 0; cpu < nrcpus; cpu++) { + perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) { + struct evsel *counter; bool first = true; if (prefix) fputs(prefix, config->output); evlist__for_each_entry(evlist, counter) { - id = cpu_map__empty_aggr_cpu_id(); - id.core = cpu; + u64 ena, run, val; + double uval; + struct aggr_cpu_id id; + int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); + + if (counter_idx < 0) + continue; + + id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); if (first) { aggr_printout(config, counter, id, 0); first = false; } - val = perf_counts(counter->counts, cpu, 0)->val; - ena = perf_counts(counter->counts, cpu, 0)->ena; - run = perf_counts(counter->counts, cpu, 0)->run; + val = perf_counts(counter->counts, counter_idx, 0)->val; + ena = perf_counts(counter->counts, counter_idx, 0)->ena; + run = perf_counts(counter->counts, counter_idx, 0)->run; uval = val * counter->scale; printout(config, id, 0, counter, uval, prefix, @@ -1208,19 +1215,23 @@ static void print_percore_thread(struct perf_stat_config *config, { int s; struct aggr_cpu_id s2, id; + struct perf_cpu_map *cpus; bool first = true; + int idx; + struct perf_cpu cpu; - for (int i = 0; i < evsel__nr_cpus(counter); i++) { - s2 = config->aggr_get_id(config, evsel__cpus(counter), i); + cpus = evsel__cpus(counter); + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + s2 = config->aggr_get_id(config, cpu); for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; - if (cpu_map__compare_aggr_cpu_id(s2, id)) + if (aggr_cpu_id__equal(&s2, &id)) break; } print_counter_aggrdata(config, counter, s, prefix, false, - &first, i); + &first, cpu); } } @@ -1243,8 +1254,8 @@ static void print_percore(struct perf_stat_config *config, fprintf(output, "%s", prefix); print_counter_aggrdata(config, counter, s, - prefix, metric_only, - &first, -1); + prefix, metric_only, + &first, (struct perf_cpu){ .cpu = -1 }); } if (metric_only) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 34a7f5c1fff7..10af7804e482 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 +#include <math.h> #include <stdio.h> #include "evsel.h" #include "stat.h" #include "color.h" +#include "debug.h" #include "pmu.h" #include "rblist.h" #include "evlist.h" @@ -30,7 +32,7 @@ struct saved_value { struct evsel *evsel; enum stat_type type; int ctx; - int cpu; + int cpu_map_idx; struct cgroup *cgrp; struct runtime_stat *stat; struct stats stats; @@ -45,8 +47,8 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry) rb_node); const struct saved_value *b = entry; - if (a->cpu != b->cpu) - return a->cpu - b->cpu; + if (a->cpu_map_idx != b->cpu_map_idx) + return a->cpu_map_idx - b->cpu_map_idx; /* * Previously the rbtree was used to link generic metrics. @@ -103,7 +105,7 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused, } static struct saved_value *saved_value_lookup(struct evsel *evsel, - int cpu, + int cpu_map_idx, bool create, enum stat_type type, int ctx, @@ -113,7 +115,7 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, struct rblist *rblist; struct rb_node *nd; struct saved_value dm = { - .cpu = cpu, + .cpu_map_idx = cpu_map_idx, .evsel = evsel, .type = type, .ctx = ctx, @@ -211,10 +213,10 @@ struct runtime_stat_data { static void update_runtime_stat(struct runtime_stat *st, enum stat_type type, - int cpu, u64 count, + int cpu_map_idx, u64 count, struct runtime_stat_data *rsd) { - struct saved_value *v = saved_value_lookup(NULL, cpu, true, type, + struct saved_value *v = saved_value_lookup(NULL, cpu_map_idx, true, type, rsd->ctx, st, rsd->cgrp); if (v) @@ -227,7 +229,7 @@ static void update_runtime_stat(struct runtime_stat *st, * instruction rates, etc: */ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int cpu, struct runtime_stat *st) + int cpu_map_idx, struct runtime_stat *st) { u64 count_ns = count; struct saved_value *v; @@ -239,88 +241,88 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, count *= counter->scale; if (evsel__is_clock(counter)) - update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd); + update_runtime_stat(st, STAT_NSECS, cpu_map_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd); + update_runtime_stat(st, STAT_CYCLES, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, CYCLES_IN_TX)) - update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd); + update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TRANSACTION_START)) - update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd); + update_runtime_stat(st, STAT_TRANSACTION, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, ELISION_START)) - update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd); + update_runtime_stat(st, STAT_ELISION, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS)) update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED)) update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED)) update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES)) update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES)) update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING)) update_runtime_stat(st, STAT_TOPDOWN_RETIRING, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC)) update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND)) update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND)) update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS)) update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT)) update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT)) update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND)) update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_BACK, - cpu, count, &rsd); + cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd); + update_runtime_stat(st, STAT_BRANCHES, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd); + update_runtime_stat(st, STAT_CACHEREFS, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_L1_DCACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_L1_ICACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_LL_CACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_DTLB_CACHE, cpu_map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd); + update_runtime_stat(st, STAT_ITLB_CACHE, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, SMI_NUM)) - update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd); + update_runtime_stat(st, STAT_SMI_NUM, cpu_map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, APERF)) - update_runtime_stat(st, STAT_APERF, cpu, count, &rsd); + update_runtime_stat(st, STAT_APERF, cpu_map_idx, count, &rsd); if (counter->collect_stat) { - v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st, + v = saved_value_lookup(counter, cpu_map_idx, true, STAT_NONE, 0, st, rsd.cgrp); update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; } else if (counter->metric_leader) { v = saved_value_lookup(counter->metric_leader, - cpu, true, STAT_NONE, 0, st, rsd.cgrp); + cpu_map_idx, true, STAT_NONE, 0, st, rsd.cgrp); v->metric_total += count; v->metric_other++; } @@ -370,12 +372,16 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) { struct evsel *counter, *leader, **metric_events, *oc; bool found; - struct expr_parse_ctx ctx; + struct expr_parse_ctx *ctx; struct hashmap_entry *cur; size_t bkt; int i; - expr__ctx_init(&ctx); + ctx = expr__ctx_new(); + if (!ctx) { + pr_debug("expr__ctx_new failed"); + return; + } evlist__for_each_entry(evsel_list, counter) { bool invalid = false; @@ -383,25 +389,25 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) if (!counter->metric_expr) continue; - expr__ctx_clear(&ctx); + expr__ctx_clear(ctx); metric_events = counter->metric_events; if (!metric_events) { - if (expr__find_other(counter->metric_expr, - counter->name, - &ctx, 1) < 0) + if (expr__find_ids(counter->metric_expr, + counter->name, + ctx) < 0) continue; metric_events = calloc(sizeof(struct evsel *), - hashmap__size(&ctx.ids) + 1); + hashmap__size(ctx->ids) + 1); if (!metric_events) { - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); return; } counter->metric_events = metric_events; } i = 0; - hashmap__for_each_entry((&ctx.ids), cur, bkt) { + hashmap__for_each_entry(ctx->ids, cur, bkt) { const char *metric_name = (const char *)cur->key; found = false; @@ -438,6 +444,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) "Add %s event to groups to get metric expression for %s\n", metric_name, counter->name); + free(printed); printed = strdup(metric_name); } invalid = true; @@ -453,16 +460,16 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list) counter->metric_expr = NULL; } } - expr__ctx_clear(&ctx); + expr__ctx_free(ctx); } static double runtime_stat_avg(struct runtime_stat *st, - enum stat_type type, int cpu, + enum stat_type type, int cpu_map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp); if (!v) return 0.0; @@ -470,12 +477,12 @@ static double runtime_stat_avg(struct runtime_stat *st, } static double runtime_stat_n(struct runtime_stat *st, - enum stat_type type, int cpu, + enum stat_type type, int cpu_map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp); if (!v) return 0.0; @@ -483,7 +490,7 @@ static double runtime_stat_n(struct runtime_stat *st, } static void print_stalled_cycles_frontend(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -491,7 +498,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -506,7 +513,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, } static void print_stalled_cycles_backend(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -514,7 +521,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -525,7 +532,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, } static void print_branch_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -533,7 +540,7 @@ static void print_branch_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd); + total = runtime_stat_avg(st, STAT_BRANCHES, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -544,7 +551,7 @@ static void print_branch_misses(struct perf_stat_config *config, } static void print_l1_dcache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -552,7 +559,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -563,7 +570,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, } static void print_l1_icache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -571,7 +578,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -581,7 +588,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config, } static void print_dtlb_cache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -589,7 +596,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -599,7 +606,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, } static void print_itlb_cache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -607,7 +614,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -617,7 +624,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, } static void print_ll_cache_misses(struct perf_stat_config *config, - int cpu, double avg, + int cpu_map_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -625,7 +632,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config, double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd); + total = runtime_stat_avg(st, STAT_LL_CACHE, cpu_map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -683,61 +690,61 @@ static double sanitize_val(double x) return x; } -static double td_total_slots(int cpu, struct runtime_stat *st, +static double td_total_slots(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { - return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd); + return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu_map_idx, rsd); } -static double td_bad_spec(int cpu, struct runtime_stat *st, +static double td_bad_spec(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { double bad_spec = 0; double total_slots; double total; - total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) - - runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) + - runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd); + total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu_map_idx, rsd) - + runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu_map_idx, rsd) + + runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu_map_idx, rsd); - total_slots = td_total_slots(cpu, st, rsd); + total_slots = td_total_slots(cpu_map_idx, st, rsd); if (total_slots) bad_spec = total / total_slots; return sanitize_val(bad_spec); } -static double td_retiring(int cpu, struct runtime_stat *st, +static double td_retiring(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { double retiring = 0; - double total_slots = td_total_slots(cpu, st, rsd); + double total_slots = td_total_slots(cpu_map_idx, st, rsd); double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, - cpu, rsd); + cpu_map_idx, rsd); if (total_slots) retiring = ret_slots / total_slots; return retiring; } -static double td_fe_bound(int cpu, struct runtime_stat *st, +static double td_fe_bound(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { double fe_bound = 0; - double total_slots = td_total_slots(cpu, st, rsd); + double total_slots = td_total_slots(cpu_map_idx, st, rsd); double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES, - cpu, rsd); + cpu_map_idx, rsd); if (total_slots) fe_bound = fetch_bub / total_slots; return fe_bound; } -static double td_be_bound(int cpu, struct runtime_stat *st, +static double td_be_bound(int cpu_map_idx, struct runtime_stat *st, struct runtime_stat_data *rsd) { - double sum = (td_fe_bound(cpu, st, rsd) + - td_bad_spec(cpu, st, rsd) + - td_retiring(cpu, st, rsd)); + double sum = (td_fe_bound(cpu_map_idx, st, rsd) + + td_bad_spec(cpu_map_idx, st, rsd) + + td_retiring(cpu_map_idx, st, rsd)); if (sum == 0) return 0; return sanitize_val(1.0 - sum); @@ -748,15 +755,15 @@ static double td_be_bound(int cpu, struct runtime_stat *st, * the ratios we need to recreate the sum. */ -static double td_metric_ratio(int cpu, enum stat_type type, +static double td_metric_ratio(int cpu_map_idx, enum stat_type type, struct runtime_stat *stat, struct runtime_stat_data *rsd) { - double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd); - double d = runtime_stat_avg(stat, type, cpu, rsd); + double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) + + runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd); + double d = runtime_stat_avg(stat, type, cpu_map_idx, rsd); if (sum) return d / sum; @@ -768,23 +775,23 @@ static double td_metric_ratio(int cpu, enum stat_type type, * We allow two missing. */ -static bool full_td(int cpu, struct runtime_stat *stat, +static bool full_td(int cpu_map_idx, struct runtime_stat *stat, struct runtime_stat_data *rsd) { int c = 0; - if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) > 0) c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) > 0) c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) > 0) c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0) + if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd) > 0) c++; return c >= 2; } -static void print_smi_cost(struct perf_stat_config *config, int cpu, +static void print_smi_cost(struct perf_stat_config *config, int cpu_map_idx, struct perf_stat_output_ctx *out, struct runtime_stat *st, struct runtime_stat_data *rsd) @@ -792,9 +799,9 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu, double smi_num, aperf, cycles, cost = 0.0; const char *color = NULL; - smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd); - aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd); - cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd); + smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu_map_idx, rsd); + aperf = runtime_stat_avg(st, STAT_APERF, cpu_map_idx, rsd); + cycles = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd); if ((cycles == 0) || (aperf == 0)) return; @@ -811,51 +818,43 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu, static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, - int cpu, + int cpu_map_idx, struct runtime_stat *st) { double scale; - char *n, *pn; + char *n; int i, j, ret; - expr__ctx_init(pctx); for (i = 0; metric_events[i]; i++) { struct saved_value *v; struct stats *stats; u64 metric_total = 0; + int source_count; if (!strcmp(metric_events[i]->name, "duration_time")) { stats = &walltime_nsecs_stats; scale = 1e-9; + source_count = 1; } else { - v = saved_value_lookup(metric_events[i], cpu, false, + v = saved_value_lookup(metric_events[i], cpu_map_idx, false, STAT_NONE, 0, st, metric_events[i]->cgrp); if (!v) break; stats = &v->stats; scale = 1.0; + source_count = evsel__source_count(metric_events[i]); if (v->metric_other) metric_total = v->metric_total; } - - n = strdup(metric_events[i]->name); + n = strdup(evsel__metric_id(metric_events[i])); if (!n) return -ENOMEM; - /* - * This display code with --no-merge adds [cpu] postfixes. - * These are not supported by the parser. Remove everything - * after the space. - */ - pn = strchr(n, ' '); - if (pn) - *pn = 0; - - if (metric_total) - expr__add_id_val(pctx, n, metric_total); - else - expr__add_id_val(pctx, n, avg_stats(stats)*scale); + + expr__add_id_val_source_count(pctx, n, + metric_total ? : avg_stats(stats) * scale, + source_count); } for (j = 0; metric_refs && metric_refs[j].metric_name; j++) { @@ -875,22 +874,28 @@ static void generic_metric(struct perf_stat_config *config, const char *metric_name, const char *metric_unit, int runtime, - int cpu, + int cpu_map_idx, struct perf_stat_output_ctx *out, struct runtime_stat *st) { print_metric_t print_metric = out->print_metric; - struct expr_parse_ctx pctx; + struct expr_parse_ctx *pctx; double ratio, scale; int i; void *ctxp = out->ctx; - i = prepare_metric(metric_events, metric_refs, &pctx, cpu, st); - if (i < 0) + pctx = expr__ctx_new(); + if (!pctx) return; + pctx->runtime = runtime; + i = prepare_metric(metric_events, metric_refs, pctx, cpu_map_idx, st); + if (i < 0) { + expr__ctx_free(pctx); + return; + } if (!metric_events[i]) { - if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) { + if (expr__parse(&ratio, pctx, metric_expr) == 0) { char *unit; char metric_bf[64]; @@ -926,28 +931,32 @@ static void generic_metric(struct perf_stat_config *config, (metric_name ? metric_name : name) : "", 0); } - expr__ctx_clear(&pctx); + expr__ctx_free(pctx); } -double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st) +double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st) { - struct expr_parse_ctx pctx; + struct expr_parse_ctx *pctx; double ratio = 0.0; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0) + pctx = expr__ctx_new(); + if (!pctx) + return NAN; + + if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu_map_idx, st) < 0) goto out; - if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1)) + if (expr__parse(&ratio, pctx, mexp->metric_expr)) ratio = 0.0; out: - expr__ctx_clear(&pctx); + expr__ctx_free(pctx); return ratio; } void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int cpu, + double avg, int cpu_map_idx, struct perf_stat_output_ctx *out, struct rblist *metric_events, struct runtime_stat *st) @@ -966,7 +975,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (config->iostat_run) { iostat_print_metric(config, evsel, out); } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd); if (total) { ratio = avg / total; @@ -976,11 +985,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } - total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd); + total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu_map_idx, &rsd); total = max(total, runtime_stat_avg(st, STAT_STALLED_CYCLES_BACK, - cpu, &rsd)); + cpu_map_idx, &rsd)); if (total && avg) { out->new_line(config, ctxp); @@ -990,8 +999,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ratio); } } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0) - print_branch_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_BRANCHES, cpu_map_idx, &rsd) != 0) + print_branch_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( @@ -1000,8 +1009,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0) - print_l1_dcache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_L1_DCACHE, cpu_map_idx, &rsd) != 0) + print_l1_dcache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); } else if ( @@ -1010,8 +1019,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0) - print_l1_icache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_L1_ICACHE, cpu_map_idx, &rsd) != 0) + print_l1_icache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); } else if ( @@ -1020,8 +1029,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0) - print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu_map_idx, &rsd) != 0) + print_dtlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); } else if ( @@ -1030,8 +1039,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0) - print_itlb_cache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu_map_idx, &rsd) != 0) + print_itlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); } else if ( @@ -1040,27 +1049,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0) - print_ll_cache_misses(config, cpu, avg, out, st, &rsd); + if (runtime_stat_n(st, STAT_LL_CACHE, cpu_map_idx, &rsd) != 0) + print_ll_cache_misses(config, cpu_map_idx, avg, out, st, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CACHEREFS, cpu_map_idx, &rsd); if (total) ratio = avg * 100 / total; - if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0) + if (runtime_stat_n(st, STAT_CACHEREFS, cpu_map_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd); + print_stalled_cycles_frontend(config, cpu_map_idx, avg, out, st, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd); + print_stalled_cycles_backend(config, cpu_map_idx, avg, out, st, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd); + total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd); if (total) { ratio = avg / total; @@ -1069,7 +1078,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "Ghz", 0); } } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) { - total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd); if (total) print_metric(config, ctxp, NULL, @@ -1079,8 +1088,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "transactional cycles", 0); } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) { - total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); - total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd); + total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd); if (total2 < avg) total2 = avg; @@ -1090,19 +1099,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0); } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd); if (avg) ratio = total / avg; - if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0) + if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.0f", "cycles / transaction", ratio); else print_metric(config, ctxp, NULL, NULL, "cycles / transaction", 0); } else if (perf_stat_evsel__is(evsel, ELISION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd); + total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd); if (avg) ratio = total / avg; @@ -1115,28 +1124,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { - double fe_bound = td_fe_bound(cpu, st, &rsd); + double fe_bound = td_fe_bound(cpu_map_idx, st, &rsd); if (fe_bound > 0.2) color = PERF_COLOR_RED; print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) { - double retiring = td_retiring(cpu, st, &rsd); + double retiring = td_retiring(cpu_map_idx, st, &rsd); if (retiring > 0.7) color = PERF_COLOR_GREEN; print_metric(config, ctxp, color, "%8.1f%%", "retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) { - double bad_spec = td_bad_spec(cpu, st, &rsd); + double bad_spec = td_bad_spec(cpu_map_idx, st, &rsd); if (bad_spec > 0.1) color = PERF_COLOR_RED; print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) { - double be_bound = td_be_bound(cpu, st, &rsd); + double be_bound = td_be_bound(cpu_map_idx, st, &rsd); const char *name = "backend bound"; static int have_recovery_bubbles = -1; @@ -1149,14 +1158,14 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (be_bound > 0.2) color = PERF_COLOR_RED; - if (td_total_slots(cpu, st, &rsd) > 0) + if (td_total_slots(cpu_map_idx, st, &rsd) > 0) print_metric(config, ctxp, color, "%8.1f%%", name, be_bound * 100.); else print_metric(config, ctxp, NULL, NULL, name, 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) && - full_td(cpu, st, &rsd)) { - double retiring = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double retiring = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_RETIRING, st, &rsd); if (retiring > 0.7) @@ -1164,8 +1173,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "retiring", retiring * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) && - full_td(cpu, st, &rsd)) { - double fe_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double fe_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_FE_BOUND, st, &rsd); if (fe_bound > 0.2) @@ -1173,8 +1182,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", fe_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) && - full_td(cpu, st, &rsd)) { - double be_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double be_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BE_BOUND, st, &rsd); if (be_bound > 0.2) @@ -1182,8 +1191,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "backend bound", be_bound * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) && - full_td(cpu, st, &rsd)) { - double bad_spec = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd)) { + double bad_spec = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BAD_SPEC, st, &rsd); if (bad_spec > 0.1) @@ -1191,11 +1200,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", bad_spec * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double retiring = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double retiring = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_RETIRING, st, &rsd); - double heavy_ops = td_metric_ratio(cpu, + double heavy_ops = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_HEAVY_OPS, st, &rsd); double light_ops = retiring - heavy_ops; @@ -1211,11 +1220,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "light operations", light_ops * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double bad_spec = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double bad_spec = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BAD_SPEC, st, &rsd); - double br_mis = td_metric_ratio(cpu, + double br_mis = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BR_MISPREDICT, st, &rsd); double m_clears = bad_spec - br_mis; @@ -1231,11 +1240,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "machine clears", m_clears * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double fe_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double fe_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_FE_BOUND, st, &rsd); - double fetch_lat = td_metric_ratio(cpu, + double fetch_lat = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_FETCH_LAT, st, &rsd); double fetch_bw = fe_bound - fetch_lat; @@ -1251,11 +1260,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth", fetch_bw * 100.); } else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) && - full_td(cpu, st, &rsd) && (config->topdown_level > 1)) { - double be_bound = td_metric_ratio(cpu, + full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) { + double be_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_BE_BOUND, st, &rsd); - double mem_bound = td_metric_ratio(cpu, + double mem_bound = td_metric_ratio(cpu_map_idx, STAT_TOPDOWN_MEM_BOUND, st, &rsd); double core_bound = be_bound - mem_bound; @@ -1272,12 +1281,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, core_bound * 100.); } else if (evsel->metric_expr) { generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, - evsel->name, evsel->metric_name, NULL, 1, cpu, out, st); - } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) { + evsel->name, evsel->metric_name, NULL, 1, cpu_map_idx, out, st); + } else if (runtime_stat_n(st, STAT_NSECS, cpu_map_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; - total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd); + total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd); if (total) ratio = convert_unit_double(1000000000.0 * avg / total, &unit); @@ -1285,7 +1294,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { - print_smi_cost(config, cpu, out, st, &rsd); + print_smi_cost(config, cpu_map_idx, out, st, &rsd); } else { num = 0; } @@ -1298,7 +1307,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, out->new_line(config, ctxp); generic_metric(config, mexp->metric_expr, mexp->metric_events, mexp->metric_refs, evsel->name, mexp->metric_name, - mexp->metric_unit, mexp->runtime, cpu, out, st); + mexp->metric_unit, mexp->runtime, cpu_map_idx, out, st); } } if (num == 0) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 09ea334586f2..ee6f03481215 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -152,11 +152,13 @@ static void evsel__free_stat_priv(struct evsel *evsel) zfree(&evsel->stats); } -static int evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads) +static int evsel__alloc_prev_raw_counts(struct evsel *evsel) { + int cpu_map_nr = evsel__nr_cpus(evsel); + int nthreads = perf_thread_map__nr(evsel->core.threads); struct perf_counts *counts; - counts = perf_counts__new(ncpus, nthreads); + counts = perf_counts__new(cpu_map_nr, nthreads); if (counts) evsel->prev_raw_counts = counts; @@ -177,12 +179,9 @@ static void evsel__reset_prev_raw_counts(struct evsel *evsel) static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw) { - int ncpus = evsel__nr_cpus(evsel); - int nthreads = perf_thread_map__nr(evsel->core.threads); - if (evsel__alloc_stat_priv(evsel) < 0 || - evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || - (alloc_raw && evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0)) + evsel__alloc_counts(evsel) < 0 || + (alloc_raw && evsel__alloc_prev_raw_counts(evsel) < 0)) return -ENOMEM; return 0; @@ -293,11 +292,12 @@ static bool pkg_id_equal(const void *__key1, const void *__key2, return *key1 == *key2; } -static int check_per_pkg(struct evsel *counter, - struct perf_counts_values *vals, int cpu, bool *skip) +static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, + int cpu_map_idx, bool *skip) { struct hashmap *mask = counter->per_pkg_mask; struct perf_cpu_map *cpus = evsel__cpus(counter); + struct perf_cpu cpu = perf_cpu_map__cpu(cpus, cpu_map_idx); int s, d, ret = 0; uint64_t *key; @@ -328,7 +328,7 @@ static int check_per_pkg(struct evsel *counter, if (!(vals->run && vals->ena)) return 0; - s = cpu_map__get_socket(cpus, cpu, NULL).socket; + s = cpu__get_socket_id(cpu); if (s < 0) return -1; @@ -336,7 +336,7 @@ static int check_per_pkg(struct evsel *counter, * On multi-die system, die_id > 0. On no-die system, die_id = 0. * We use hashmap(socket, die) to check the used socket+die pair. */ - d = cpu_map__get_die(cpus, cpu, NULL).die; + d = cpu__get_die_id(cpu); if (d < 0) return -1; @@ -345,9 +345,10 @@ static int check_per_pkg(struct evsel *counter, return -ENOMEM; *key = (uint64_t)d << 32 | s; - if (hashmap__find(mask, (void *)key, NULL)) + if (hashmap__find(mask, (void *)key, NULL)) { *skip = true; - else + free(key); + } else ret = hashmap__add(mask, (void *)key, (void *)1); return ret; @@ -355,14 +356,14 @@ static int check_per_pkg(struct evsel *counter, static int process_counter_values(struct perf_stat_config *config, struct evsel *evsel, - int cpu, int thread, + int cpu_map_idx, int thread, struct perf_counts_values *count) { struct perf_counts_values *aggr = &evsel->counts->aggr; static struct perf_counts_values zero; bool skip = false; - if (check_per_pkg(evsel, count, cpu, &skip)) { + if (check_per_pkg(evsel, count, cpu_map_idx, &skip)) { pr_err("failed to read per-pkg counter\n"); return -1; } @@ -378,11 +379,11 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel, case AGGR_NODE: case AGGR_NONE: if (!evsel->snapshot) - evsel__compute_deltas(evsel, cpu, thread, count); + evsel__compute_deltas(evsel, cpu_map_idx, thread, count); perf_counts_values__scale(count, config->scale, NULL); if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) { perf_stat__update_shadow_stats(evsel, count->val, - cpu, &rt_stat); + cpu_map_idx, &rt_stat); } if (config->aggr_mode == AGGR_THREAD) { @@ -411,15 +412,15 @@ static int process_counter_maps(struct perf_stat_config *config, { int nthreads = perf_thread_map__nr(counter->core.threads); int ncpus = evsel__nr_cpus(counter); - int cpu, thread; + int idx, thread; if (counter->core.system_wide) nthreads = 1; for (thread = 0; thread < nthreads; thread++) { - for (cpu = 0; cpu < ncpus; cpu++) { - if (process_counter_values(config, counter, cpu, thread, - perf_counts(counter->counts, cpu, thread))) + for (idx = 0; idx < ncpus; idx++) { + if (process_counter_values(config, counter, idx, thread, + perf_counts(counter->counts, idx, thread))) return -1; } } @@ -531,7 +532,7 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target, - int cpu) + int cpu_map_idx) { struct perf_event_attr *attr = &evsel->core.attr; struct evsel *leader = evsel__leader(evsel); @@ -585,7 +586,7 @@ int create_perf_stat_counter(struct evsel *evsel, } if (target__has_cpu(target) && !target__has_per_thread(target)) - return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu); + return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx); return evsel__open_per_thread(evsel, evsel->core.threads); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 32c8527de347..335d19cc3063 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -108,8 +108,7 @@ struct runtime_stat { struct rblist value_list; }; -typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, - struct perf_cpu_map *m, int cpu); +typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu); struct perf_stat_config { enum aggr_mode aggr_mode; @@ -209,7 +208,7 @@ void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); void perf_stat__reset_shadow_per_stat(struct runtime_stat *st); void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int cpu, struct runtime_stat *st); + int cpu_map_idx, struct runtime_stat *st); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -249,10 +248,10 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target, - int cpu); + int cpu_map_idx); void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; -double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st); +double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st); #endif diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 96f941e01681..1e0c731fc539 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -728,20 +728,20 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus) int i; int ret = 0; struct perf_cpu_map *m; - int c; + struct perf_cpu c; m = perf_cpu_map__new(s); if (!m) return -1; - for (i = 0; i < m->nr; i++) { - c = m->map[i]; - if (c >= nr_cpus) { + for (i = 0; i < perf_cpu_map__nr(m); i++) { + c = perf_cpu_map__cpu(m, i); + if (c.cpu >= nr_cpus) { ret = -1; break; } - set_bit(c, cpumask_bits(b)); + set_bit(c.cpu, cpumask_bits(b)); } perf_cpu_map__put(m); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 0fc9a5410739..b2ed3140a1fa 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -274,7 +274,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char * if (symbol_conf.priv_size) { if (symbol_conf.init_annotation) { struct annotation *notes = (void *)sym; - pthread_mutex_init(¬es->lock, NULL); + annotation__init(notes); } sym = ((void *)sym) + symbol_conf.priv_size; } @@ -294,6 +294,13 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char * void symbol__delete(struct symbol *sym) { + if (symbol_conf.priv_size) { + if (symbol_conf.init_annotation) { + struct annotation *notes = symbol__annotation(sym); + + annotation__exit(notes); + } + } free(((void *)sym) - symbol_conf.priv_size); } @@ -702,6 +709,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name, if (!symbol_type__filter(type)) return 0; + /* Ignore local symbols for ARM modules */ + if (name[0] == '$') + return 0; + /* * module symbols are not sorted so we add all * symbols, setting length to 0, and rely on @@ -2630,3 +2641,25 @@ struct mem_info *mem_info__new(void) refcount_set(&mi->refcnt, 1); return mi; } + +/* + * Checks that user supplied symbol kernel files are accessible because + * the default mechanism for accessing elf files fails silently. i.e. if + * debug syms for a build ID aren't found perf carries on normally. When + * they are user supplied we should assume that the user doesn't want to + * silently fail. + */ +int symbol__validate_sym_arguments(void) +{ + if (symbol_conf.vmlinux_name && + access(symbol_conf.vmlinux_name, R_OK)) { + pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); + return -EINVAL; + } + if (symbol_conf.kallsyms_name && + access(symbol_conf.kallsyms_name, R_OK)) { + pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); + return -EINVAL; + } + return 0; +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 954d6a049ee2..fbf866d82dcc 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -40,22 +40,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, GElf_Shdr *shp, const char *name, size_t *idx); #endif -/** struct symbol - symtab entry - * - * @ignore - resolvable but tools ignore it (e.g. idle routines) +/** + * A symtab entry. When allocated this may be preceded by an annotation (see + * symbol__annotation), a browser_index (see symbol__browser_index) and rb_node + * to sort by name (see struct symbol_name_rb_node). */ struct symbol { struct rb_node rb_node; + /** Range of symbol [start, end). */ u64 start; u64 end; + /** Length of the string name. */ u16 namelen; + /** ELF symbol type as defined for st_info. E.g STT_OBJECT or STT_FUNC. */ u8 type:4; + /** ELF binding type as defined for st_info. E.g. STB_WEAK or STB_GLOBAL. */ u8 binding:4; + /** Set true for kernel symbols of idle routines. */ u8 idle:1; + /** Resolvable but tools ignore it (e.g. idle routines). */ u8 ignore:1; + /** Symbol for an inlined function. */ u8 inlined:1; + /** Has symbol__annotate2 been performed. */ + u8 annotate2:1; + /** Architecture specific. Unused except on PPC where it holds st_other. */ u8 arch_sym; - bool annotate2; + /** The name of length namelen associated with the symbol. */ char name[]; }; @@ -286,4 +297,6 @@ static inline void __mem_info__zput(struct mem_info **mi) #define mem_info__zput(mi) __mem_info__zput(&mi) +int symbol__validate_sym_arguments(void); + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a7e981b2d7de..b654de0841f8 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -715,7 +715,8 @@ static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *fork_event, union perf_event *namespaces_event, pid_t pid, int full, perf_event__handler_t process, - struct perf_tool *tool, struct machine *machine, bool mmap_data) + struct perf_tool *tool, struct machine *machine, + bool needs_mmap, bool mmap_data) { char filename[PATH_MAX]; struct dirent **dirent; @@ -739,7 +740,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, * send mmap only for thread group leader * see thread__init_maps() */ - if (pid == tgid && + if (pid == tgid && needs_mmap && perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data)) return -1; @@ -786,7 +787,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, break; rc = 0; - if (_pid == pid && !kernel_thread) { + if (_pid == pid && !kernel_thread && needs_mmap) { /* process the parent's maps too */ rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data); @@ -806,7 +807,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, - bool mmap_data) + bool needs_mmap, bool mmap_data) { union perf_event *comm_event, *mmap_event, *fork_event; union perf_event *namespaces_event; @@ -836,7 +837,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, perf_thread_map__pid(threads, thread), 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -862,7 +863,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, fork_event, namespaces_event, comm_event->comm.pid, 0, process, tool, machine, - mmap_data)) { + needs_mmap, mmap_data)) { err = -1; break; } @@ -882,6 +883,7 @@ out: static int __perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, + bool needs_mmap, bool mmap_data, struct dirent **dirent, int start, @@ -926,7 +928,7 @@ static int __perf_event__synthesize_threads(struct perf_tool *tool, */ __event__synthesize_thread(comm_event, mmap_event, fork_event, namespaces_event, pid, 1, process, - tool, machine, mmap_data); + tool, machine, needs_mmap, mmap_data); } err = 0; @@ -945,6 +947,7 @@ struct synthesize_threads_arg { struct perf_tool *tool; perf_event__handler_t process; struct machine *machine; + bool needs_mmap; bool mmap_data; struct dirent **dirent; int num; @@ -956,7 +959,8 @@ static void *synthesize_threads_worker(void *arg) struct synthesize_threads_arg *args = arg; __perf_event__synthesize_threads(args->tool, args->process, - args->machine, args->mmap_data, + args->machine, + args->needs_mmap, args->mmap_data, args->dirent, args->start, args->num); return NULL; @@ -965,7 +969,7 @@ static void *synthesize_threads_worker(void *arg) int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, - bool mmap_data, + bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize) { struct synthesize_threads_arg *args = NULL; @@ -994,7 +998,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (thread_nr <= 1) { err = __perf_event__synthesize_threads(tool, process, - machine, mmap_data, + machine, + needs_mmap, mmap_data, dirent, base, n); goto free_dirent; } @@ -1015,6 +1020,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, args[i].tool = tool; args[i].process = process; args[i].machine = machine; + args[i].needs_mmap = needs_mmap; args[i].mmap_data = mmap_data; args[i].dirent = dirent; } @@ -1180,12 +1186,12 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool, static void synthesize_cpus(struct cpu_map_entries *cpus, struct perf_cpu_map *map) { - int i; + int i, map_nr = perf_cpu_map__nr(map); - cpus->nr = map->nr; + cpus->nr = map_nr; - for (i = 0; i < map->nr; i++) - cpus->cpu[i] = map->map[i]; + for (i = 0; i < map_nr; i++) + cpus->cpu[i] = perf_cpu_map__cpu(map, i).cpu; } static void synthesize_mask(struct perf_record_record_cpu_map *mask, @@ -1196,13 +1202,13 @@ static void synthesize_mask(struct perf_record_record_cpu_map *mask, mask->nr = BITS_TO_LONGS(max); mask->long_size = sizeof(long); - for (i = 0; i < map->nr; i++) - set_bit(map->map[i], mask->mask); + for (i = 0; i < perf_cpu_map__nr(map); i++) + set_bit(perf_cpu_map__cpu(map, i).cpu, mask->mask); } static size_t cpus_size(struct perf_cpu_map *map) { - return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16); + return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16); } static size_t mask_size(struct perf_cpu_map *map, int *max) @@ -1211,9 +1217,9 @@ static size_t mask_size(struct perf_cpu_map *map, int *max) *max = 0; - for (i = 0; i < map->nr; i++) { + for (i = 0; i < perf_cpu_map__nr(map); i++) { /* bit position of the cpu is + 1 */ - int bit = map->map[i] + 1; + int bit = perf_cpu_map__cpu(map, i).cpu + 1; if (bit > *max) *max = bit; @@ -1348,7 +1354,7 @@ int perf_event__synthesize_stat_config(struct perf_tool *tool, } int perf_event__synthesize_stat(struct perf_tool *tool, - u32 cpu, u32 thread, u64 id, + struct perf_cpu cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine) @@ -1360,7 +1366,7 @@ int perf_event__synthesize_stat(struct perf_tool *tool, event.header.misc = 0; event.id = id; - event.cpu = cpu; + event.cpu = cpu.cpu; event.thread = thread; event.val = count->val; event.ena = count->ena; @@ -1757,7 +1763,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_ } e->idx = sid->idx; - e->cpu = sid->cpu; + e->cpu = sid->cpu.cpu; e->tid = sid->tid; } } @@ -1775,26 +1781,46 @@ out_err: int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, - unsigned int nr_threads_synthesize) + perf_event__handler_t process, bool needs_mmap, + bool data_mmap, unsigned int nr_threads_synthesize) { + /* + * When perf runs in non-root PID namespace, and the namespace's proc FS + * is not mounted, nsinfo__is_in_root_namespace() returns false. + * In this case, the proc FS is coming for the parent namespace, thus + * perf tool will wrongly gather process info from its parent PID + * namespace. + * + * To avoid the confusion that the perf tool runs in a child PID + * namespace but it synthesizes thread info from its parent PID + * namespace, returns failure with warning. + */ + if (!nsinfo__is_in_root_namespace()) { + pr_err("Perf runs in non-root PID namespace but it tries to "); + pr_err("gather process info from its parent PID namespace.\n"); + pr_err("Please mount the proc file system properly, e.g. "); + pr_err("add the option '--mount-proc' for unshare command.\n"); + return -EPERM; + } + if (target__has_task(target)) - return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap); + return perf_event__synthesize_thread_map(tool, threads, process, machine, + needs_mmap, data_mmap); else if (target__has_cpu(target)) - return perf_event__synthesize_threads(tool, process, - machine, data_mmap, + return perf_event__synthesize_threads(tool, process, machine, + needs_mmap, data_mmap, nr_threads_synthesize); /* command specified */ return 0; } int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, - unsigned int nr_threads_synthesize) + struct perf_thread_map *threads, bool needs_mmap, + bool data_mmap, unsigned int nr_threads_synthesize) { return __machine__synthesize_threads(machine, NULL, target, threads, - perf_event__process, data_mmap, - nr_threads_synthesize); + perf_event__process, needs_mmap, + data_mmap, nr_threads_synthesize); } static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id) @@ -2230,3 +2256,31 @@ int perf_event__synthesize_for_pipe(struct perf_tool *tool, return ret; } + +int parse_synth_opt(char *synth) +{ + char *p, *q; + int ret = 0; + + if (synth == NULL) + return -1; + + for (q = synth; (p = strsep(&q, ",")); p = q) { + if (!strcasecmp(p, "no") || !strcasecmp(p, "none")) + return 0; + + if (!strcasecmp(p, "all")) + return PERF_SYNTH_ALL; + + if (!strcasecmp(p, "task")) + ret |= PERF_SYNTH_TASK; + else if (!strcasecmp(p, "mmap")) + ret |= PERF_SYNTH_TASK | PERF_SYNTH_MMAP; + else if (!strcasecmp(p, "cgroup")) + ret |= PERF_SYNTH_CGROUP; + else + return -1; + } + + return ret; +} diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index c845e2b9b444..78a0450db164 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -6,6 +6,7 @@ #include <sys/types.h> // pid_t #include <linux/compiler.h> #include <linux/types.h> +#include <perf/cpumap.h> struct auxtrace_record; struct dso; @@ -27,6 +28,18 @@ struct target; union perf_event; +enum perf_record_synth { + PERF_SYNTH_TASK = 1 << 0, + PERF_SYNTH_MMAP = 1 << 1, + PERF_SYNTH_CGROUP = 1 << 2, + + /* last element */ + PERF_SYNTH_MAX = 1 << 3, +}; +#define PERF_SYNTH_ALL (PERF_SYNTH_MAX - 1) + +int parse_synth_opt(char *str); + typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); @@ -51,10 +64,10 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs); int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine); -int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_stat(struct perf_tool *tool, struct perf_cpu cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine); -int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data); -int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize); +int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data); +int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize); int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process); int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine); @@ -65,10 +78,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool, struct target *target, struct perf_thread_map *threads, - perf_event__handler_t process, bool data_mmap, + perf_event__handler_t process, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); int machine__synthesize_threads(struct machine *machine, struct target *target, - struct perf_thread_map *threads, bool data_mmap, + struct perf_thread_map *threads, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize); #ifdef HAVE_AUXTRACE_SUPPORT diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index bbbc0dcd461f..ef873f2cc38f 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -53,6 +53,7 @@ struct perf_tool { lost_samples, aux, itrace_start, + aux_output_hw_id, context_switch, throttle, unthrottle, diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 27945eeb0cb5..c1ebfc5d2e0c 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -95,15 +95,15 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", - top->evlist->core.cpus->nr > 1 ? "s" : "", + perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "", target->cpu_list); else { if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", - top->evlist->core.cpus->nr, - top->evlist->core.cpus->nr > 1 ? "s" : ""); + perf_cpu_map__nr(top->evlist->core.cpus), + perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : ""); } perf_top__reset_sample_counters(top); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 37a9492edb3e..fb4f6616b5fa 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -379,32 +379,32 @@ fetch_kernel_version(unsigned int *puint, char *str, return 0; } -const char *perf_tip(const char *dirpath) +int perf_tip(char **strp, const char *dirpath) { struct strlist *tips; struct str_node *node; - char *tip = NULL; struct strlist_config conf = { .dirname = dirpath, .file_only = true, }; + int ret = 0; + *strp = NULL; tips = strlist__new("tips.txt", &conf); if (tips == NULL) - return errno == ENOENT ? NULL : - "Tip: check path of tips.txt or get more memory! ;-p"; + return -errno; if (strlist__nr_entries(tips) == 0) goto out; node = strlist__entry(tips, random() % strlist__nr_entries(tips)); - if (asprintf(&tip, "Tip: %s", node->s) < 0) - tip = (char *)"Tip: get more memory! ;-)"; + if (asprintf(strp, "Tip: %s", node->s) < 0) + ret = -ENOMEM; out: strlist__delete(tips); - return tip; + return ret; } char *perf_exe(char *buf, int len) @@ -416,3 +416,18 @@ char *perf_exe(char *buf, int len) } return strcpy(buf, "perf"); } + +void perf_debuginfod_setup(struct perf_debuginfod *di) +{ + /* + * By default '!di->set' we clear DEBUGINFOD_URLS, so debuginfod + * processing is not triggered, otherwise we set it to 'di->urls' + * value. If 'di->urls' is "system" we keep DEBUGINFOD_URLS value. + */ + if (!di->set) + setenv("DEBUGINFOD_URLS", "", 1); + else if (di->urls && strcmp(di->urls, "system")) + setenv("DEBUGINFOD_URLS", di->urls, 1); + + pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS")); +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index ad737052e597..7b625cbd2dd8 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -11,6 +11,9 @@ #include <stddef.h> #include <linux/compiler.h> #include <sys/types.h> +#ifndef __cplusplus +#include <internal/cpumap.h> +#endif /* General helper functions */ void usage(const char *err) __noreturn; @@ -39,7 +42,7 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_FMT "%d.%d.%d" #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) -const char *perf_tip(const char *dirpath); +int perf_tip(char **strp, const char *dirpath); #ifndef HAVE_SCHED_GETCPU_SUPPORT int sched_getcpu(void); @@ -66,6 +69,12 @@ extern bool test_attr__enabled; void test_attr__ready(void); void test_attr__init(void); struct perf_event_attr; -void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, +void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu, int fd, int group_fd, unsigned long flags); + +struct perf_debuginfod { + const char *urls; + bool set; +}; +void perf_debuginfod_setup(struct perf_debuginfod *di); #endif /* GIT_COMPAT_UTIL_H */ |